67 results
(View BibTeX file of all listed publications)
2019
Towards Geometric Understanding of Motion
University of Tübingen, December 2019 (phdthesis)
The motion of the world is inherently dependent on the spatial structure of the world and its geometry. Therefore, classical optical flow methods try to model this geometry to solve for the motion. However, recent deep learning methods take a completely different approach. They try to predict optical flow by learning from labelled data. Although deep networks have shown state-of-the-art performance on classification problems in computer vision, they have not been as effective in solving optical flow. The key reason is that deep learning methods do not explicitly model the structure of the world in a neural network, and instead expect the network to learn about the structure from data. We hypothesize that it is difficult for a network to learn about motion without any constraint on the structure of the world. Therefore, we explore several approaches to explicitly model the geometry of the world and its spatial structure in deep neural networks.
The spatial structure in images can be captured by representing it at multiple scales. To represent multiple scales of images in deep neural nets, we introduce a Spatial Pyramid Network (SpyNet). Such a network can leverage global information for estimating large motions and local information for estimating small motions. We show that SpyNet significantly improves over previous optical flow networks while also being the smallest and fastest neural network for motion estimation. SPyNet achieves a 97% reduction in model parameters over previous methods and is more accurate.
The spatial structure of the world extends to people and their motion. Humans have a very well-defined structure, and this information is useful in estimating optical flow for humans. To leverage this information, we create a synthetic dataset for human optical flow using a statistical human body model and motion capture sequences. We use this dataset to train deep networks and see significant improvement in the ability of the networks to estimate human optical flow.
The structure and geometry of the world affects the motion. Therefore, learning about the structure of the scene together with the motion can benefit both problems. To facilitate this, we introduce Competitive Collaboration, where several neural networks are constrained by geometry and can jointly learn about structure and motion in the scene without any labels. To this end, we show that jointly learning single view depth prediction, camera motion, optical flow and motion segmentation using Competitive Collaboration achieves state-of-the-art results among unsupervised approaches.
Our findings provide support for our hypothesis that explicit constraints on structure and geometry of the world lead to better methods for motion estimation.
2018
Model-based Optical Flow: Layers, Learning, and Geometry
Tuebingen University, April 2018 (phdthesis)
The estimation of motion in video sequences establishes temporal correspondences between pixels and surfaces and allows reasoning about a scene using multiple frames. Despite being a focus of research for over three decades, computing motion, or optical flow, remains challenging due to a number of difficulties, including the treatment of motion discontinuities and occluded regions, and the integration of information from more than two frames. One reason for these issues is that most optical flow algorithms only reason about the motion of pixels on the image plane, while not taking the image formation pipeline or the 3D structure of the world into account. One approach to address this uses layered models, which represent the occlusion structure of a scene and provide an approximation to the geometry. The goal of this dissertation is to show ways to inject additional knowledge about the scene into layered methods, making them more robust, faster, and more accurate. First, this thesis demonstrates the modeling power of layers using the example of motion blur in videos, which is caused by fast motion relative to the exposure time of the camera. Layers segment the scene into regions that move coherently while preserving their occlusion relationships. The motion of each layer therefore directly determines its motion blur. At the same time, the layered model captures complex blur overlap effects at motion discontinuities. Using layers, we can thus formulate a generative model for blurred video sequences, and use this model to simultaneously deblur a video and compute accurate optical flow for highly dynamic scenes containing motion blur. Next, we consider the representation of the motion within layers. Since, in a layered model, important motion discontinuities are captured by the segmentation into layers, the flow within each layer varies smoothly and can be approximated using a low dimensional subspace. We show how this subspace can be learned from training data using principal component analysis (PCA), and that flow estimation using this subspace is computationally efficient. The combination of the layered model and the low-dimensional subspace gives the best of both worlds, sharp motion discontinuities from the layers and computational efficiency from the subspace. Lastly, we show how layered methods can be dramatically improved using simple semantics. Instead of treating all layers equally, a semantic segmentation divides the scene into its static parts and moving objects. Static parts of the scene constitute a large majority of what is shown in typical video sequences; yet, in such regions optical flow is fully constrained by the depth structure of the scene and the camera motion. After segmenting out moving objects, we consider only static regions, and explicitly reason about the structure of the scene and the camera motion, yielding much better optical flow estimates. Furthermore, computing the structure of the scene allows to better combine information from multiple frames, resulting in high accuracies even in occluded regions. For moving regions, we compute the flow using a generic optical flow method, and combine it with the flow computed for the static regions to obtain a full optical flow field. By combining layered models of the scene with reasoning about the dynamic behavior of the real, three-dimensional world, the methods presented herein push the envelope of optical flow computation in terms of robustness, speed, and accuracy, giving state-of-the-art results on benchmarks and pointing to important future research directions for the estimation of motion in natural scenes.
Combining Data-Driven 2D and 3D Human Appearance Models
Eberhard Karls Universität Tübingen, 2018 (phdthesis)
Detailed 2D and 3D body estimation of humans has many applications in our everyday life: interaction with machines, virtual try-on of fashion or product adjustments based on a body size estimate are just some examples. Two key components of such systems are: (1) detailed pose and shape estimation and (2) generation of images. Ideally, they should use 2D images as input signal so that they can be applied easily and on arbitrary digital images. Due to the high complexity of human appearance and the depth ambiguities in 2D space, data driven models are the tool at hand to design such methods. In this work, we consider two aspects of such systems: in the first part, we propose general optimization and implementation techniques for machine learning models and make them available in the form of software packages. In the second part, we present in multiple steps, how the detailed analysis and generation of human appearance based on digital 2D images can be realized. We work with two machine learning methods: Decision Forests and Artificial Neural Networks. The contribution of this thesis to the theory of Decision Forests consists of the introduction of a generalized entropy function that is efficient to evaluate and tunable to specific tasks and allows us to establish relations to frequently used heuristics. For both, Decision Forests and Neural Networks, we present methods for implementation and a software package. Existing methods for 3D body estimation from images usually estimate the 14 most important, pose defining points in 2D and convert them to a 3D `skeleton'. In this work we show that a carefully crafted energy function is sufficient to recover a full 3D body shape automatically from the keypoints. In this way, we devise the first fully automatic method estimating 3D body pose and shape from a 2D image. While this method successfully recovers a coarse 3D pose and shape, it is still a challenge to recover details such as body part rotations. However, for more detailed models, it would be necessary to annotate data with a very rich set of cues. This approach does not scale to large datasets, since the effort per image as well as the required quality could not be reached due to how hard it is to estimate the position of keypoints on the body surface. To solve this problem, we develop a method that can alternate between optimizing the 2D and 3D models, improving them iteratively. The labeling effort for humans remains low. At the same time, we create 2D models reasoning about factors more items than existing methods and we extend the 3D pose and body shape estimation to rotation and body extent. To generate images of people, existing methods usually work with 3D models that are hard to adjust and to use. In contrast, we develop a method that builds on the possibilities for automatic 3D body estimation: we use it to create a dataset of 3D bodies together with 2D clothes and cloth segments. With this information, we develop a data driven model directly producing 2D images of people. Only the broad interplay of 2D and 3D body and appearance models in different forms makes it possible to achieve a high level of detail for analysis and generation of human appearance. The developed techniques can in principle also be used for the analysis and generation of images of other creatures and objects.
2017
Human Shape Estimation using Statistical Body Models
University of Tübingen, May 2017 (phdthesis)
Human body estimation methods transform real-world observations into predictions about human body state. These estimation methods benefit a variety of health, entertainment, clothing, and ergonomics applications. State may include pose, overall body shape, and appearance.
Body state estimation is underconstrained by observations; ambiguity presents itself both in the form of missing data within observations, and also in the form of unknown correspondences between observations. We address this challenge with the use of a statistical body model: a data-driven virtual human. This helps resolve ambiguity in two ways. First, it fills in missing data, meaning that incomplete observations still result in complete shape estimates. Second, the model provides a statistically-motivated penalty for unlikely states, which enables more plausible body shape estimates.
Body state inference requires more than a body model; we therefore build obser- vation models whose output is compared with real observations. In this thesis, body state is estimated from three types of observations: 3D motion capture markers, depth and color images, and high-resolution 3D scans. In each case, a forward process is proposed which simulates observations. By comparing observations to the results of the forward process, state can be adjusted to minimize the difference between simulated and observed data. We use gradient-based methods because they are critical to the precise estimation of state with a large number of parameters.
The contributions of this work include three parts. First, we propose a method for the estimation of body shape, nonrigid deformation, and pose from 3D markers. Second, we present a concise approach to differentiating through the rendering process, with application to body shape estimation. And finally, we present a statistical body model trained from human body scans, with state-of-the-art fidelity, good runtime performance, and compatibility with existing animation packages.
Learning Inference Models for Computer Vision
MPI for Intelligent Systems and University of Tübingen, 2017 (phdthesis)
Computer vision can be understood as the ability to perform 'inference' on image data. Breakthroughs in computer vision technology are often marked by advances in inference techniques, as even the model design is often dictated by the complexity of inference in them. This thesis proposes learning based inference schemes and demonstrates applications in computer vision. We propose techniques for inference in both generative and discriminative computer vision models.
Despite their intuitive appeal, the use of generative models in vision is hampered by the difficulty of posterior inference, which is often too complex or too slow to be practical. We propose techniques for improving inference in two widely used techniques: Markov Chain Monte Carlo (MCMC) sampling and message-passing inference. Our inference strategy is to learn separate discriminative models that assist Bayesian inference in a generative model. Experiments on a range of generative vision models show that the proposed techniques accelerate the inference process and/or converge to better solutions.
A main complication in the design of discriminative models is the inclusion of prior knowledge in a principled way. For better inference in discriminative models, we propose techniques that modify the original model itself, as inference is simple evaluation of the model. We concentrate on convolutional neural network (CNN) models and propose a generalization of standard spatial convolutions, which are the basic building blocks of CNN architectures, to bilateral convolutions. First, we generalize the existing use of bilateral filters and then propose new neural network architectures with learnable
bilateral filters, which we call `Bilateral Neural Networks'. We show how the bilateral filtering modules can be used for modifying existing CNN architectures for better image segmentation and propose a neural network approach for temporal information propagation in videos. Experiments demonstrate the potential of the proposed bilateral networks on a wide range of vision tasks and datasets.
In summary, we propose learning based techniques for better inference in several computer vision models ranging from inverse graphics to freely parameterized neural networks. In generative vision models, our inference techniques alleviate some of the crucial hurdles in Bayesian posterior inference, paving new ways for the use of model based machine learning in vision. In discriminative CNN models, the proposed filter generalizations aid in the design of new neural network architectures that can handle sparse high-dimensional data as well as provide a way for incorporating prior knowledge into CNNs.
Decentralized Simultaneous Multi-target Exploration using a Connected Network of Multiple Robots
Nestmeyer, T., Robuffo Giordano, P., Bülthoff, H. H., Franchi, A.
In pages: 989-1011, Autonomous Robots, 2017 (incollection)
Capturing Hand-Object Interaction and Reconstruction of Manipulated Objects
University of Bonn, 2017 (phdthesis)
Hand motion capture with an RGB-D sensor gained recently a lot of research attention, however, even most recent approaches focus on the case of a single isolated hand.
We focus instead on hands that interact with other hands or with a rigid or articulated object.
Our framework successfully captures motion in such scenarios by combining a generative model with discriminatively trained salient points, collision detection and physics simulation to achieve a low tracking error with physically plausible poses.
All components are unified in a single objective function that can be optimized with standard optimization techniques.
We initially assume a-priori knowledge of the object's shape and skeleton.
In case of unknown object shape there are existing 3d reconstruction methods that capitalize on distinctive geometric or texture features.
These methods though fail for textureless and highly symmetric objects like household articles, mechanical parts or toys.
We show that extracting 3d hand motion for in-hand scanning effectively facilitates the reconstruction of such objects and we fuse the rich additional information of hands into a 3d reconstruction pipeline.
Finally, although shape reconstruction is enough for rigid objects, there is a lack of tools that build rigged models of articulated objects that deform realistically using RGB-D data.
We propose a method that creates a fully rigged model consisting of a watertight mesh, embedded skeleton and skinning weights by employing a combination of deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow.
2016
Non-parametric Models for Structured Data and Applications to Human Bodies and Natural Scenes
ETH Zurich, July 2016 (phdthesis)
The purpose of this thesis is the study of non-parametric models for structured data and their fields of application in computer vision. We aim at the development of context-sensitive architectures which are both expressive and efficient. Our focus is on directed graphical models, in particular Bayesian networks, where we combine the flexibility of non-parametric local distributions with the efficiency of a global topology with bounded treewidth. A bound on the treewidth is obtained by either constraining the maximum indegree of the underlying graph structure or by introducing determinism. The non-parametric distributions in the nodes of the graph are given by decision trees or kernel density estimators.
The information flow implied by specific network topologies, especially the resultant (conditional) independencies, allows for a natural integration and control of contextual information. We distinguish between three different types of context: static, dynamic, and semantic. In four different approaches we propose models which exhibit varying combinations of these contextual properties and allow modeling of structured data in space, time, and hierarchies derived thereof. The generative character of the presented models enables a direct synthesis of plausible hypotheses.
Extensive experiments validate the developed models in two application scenarios which are of particular interest in computer vision: human bodies and natural scenes. In the practical sections of this work we discuss both areas from different angles and show applications of our models to human pose, motion, and segmentation as well as object categorization and localization. Here, we benefit from the availability of modern datasets of unprecedented size and diversity. Comparisons to traditional approaches and state-of-the-art research on the basis of well-established evaluation criteria allows the objective assessment of our contributions.
2015
Proceedings of the 37th German Conference on Pattern Recognition
Gall, J., Gehler, P., Leibe, B.
Springer, German Conference on Pattern Recognition, October 2015 (proceedings)
Shape Models of the Human Body for Distributed Inference
Brown University, May 2015 (phdthesis)
In this thesis we address the problem of building shape models of the human body,
in 2D and 3D, which are realistic and efficient to use. We focus our efforts on the
human body, which is highly articulated and has interesting shape variations, but
the approaches we present here can be applied to generic deformable and articulated
objects. To address efficiency, we constrain our models to be part-based and have a
tree-structured representation with pairwise relationships between connected parts.
This allows the application of methods for distributed inference based on message
passing. To address realism, we exploit recent advances in computer graphics that
represent the human body with statistical shape models learned from 3D scans.
We introduce two articulated body models, a 2D model, named Deformable Structures
(DS), which is a contour-based model parameterized for 2D pose and projected
shape, and a 3D model, named Stitchable Puppet (SP), which is a mesh-based model
parameterized for 3D pose, pose-dependent deformations and intrinsic body shape.
We have successfully applied the models to interesting and challenging problems in
computer vision and computer graphics, namely pose estimation from static images,
pose estimation from video sequences, pose and shape estimation from 3D scan data.
This advances the state of the art in human pose and shape estimation and suggests
that carefully de ned realistic models can be important for computer vision.
More work at the intersection of vision and graphics is thus encouraged.
From Scans to Models: Registration of 3D Human Shapes Exploiting Texture Information
University of Padova, March 2015 (phdthesis)
New scanning technologies are increasing the importance of 3D mesh data, and of algorithms that can reliably register meshes obtained from multiple scans. Surface registration is important e.g. for building full 3D models from partial scans, identifying and tracking objects in a 3D scene, creating statistical shape models.
Human body registration is particularly important for many applications, ranging from biomedicine and robotics to the production of movies and video games; but obtaining accurate and reliable registrations is challenging, given the articulated, non-rigidly deformable structure of the human body.
In this thesis, we tackle the problem of 3D human body registration.
We start by analyzing the current state of the art, and find that: a) most registration techniques rely only on geometric information, which is ambiguous on flat surface areas; b) there is a lack of adequate datasets and benchmarks in the field. We address both issues.
Our contribution is threefold. First, we present a model-based registration technique for human meshes that combines geometry and surface texture information to provide highly accurate mesh-to-mesh correspondences. Our approach estimates scene lighting and surface albedo, and uses the albedo to construct a high-resolution textured 3D body model that is brought into registration with multi-camera image data using a robust matching term.
Second, by leveraging our technique, we present FAUST (Fine Alignment Using Scan Texture), a novel dataset collecting 300 high-resolution scans of 10 people in a wide range of poses. FAUST is the first dataset providing both real scans and automatically computed, reliable "ground-truth" correspondences between them.
Third, we explore possible uses of our approach in dermatology. By combining our registration technique with a melanocytic lesion segmentation algorithm, we propose a system that automatically detects new or evolving lesions over almost the entire body surface, thus helping dermatologists identify potential melanomas.
We conclude this thesis investigating the benefits of using texture information to establish frame-to-frame correspondences in dynamic monocular sequences captured with consumer depth cameras. We outline a novel approach to reconstruct realistic body shape and appearance models from dynamic human performances, and show preliminary results on challenging sequences captured with a Kinect.
Long Range Motion Estimation and Applications
Long Range Motion Estimation and Applications, University of Massachusetts Amherst, University of Massachusetts Amherst, February 2015 (phdthesis)
Finding correspondences between images underlies many computer vision problems, such as optical flow, tracking, stereovision and alignment. Finding these correspondences involves formulating a matching function and optimizing it. This optimization process is often gradient descent, which avoids exhaustive search, but relies on the assumption of being in the basin of attraction of the right local minimum. This is often the case when the displacement is small, and current methods obtain very accurate results for small motions. However, when the motion is large and the matching function is bumpy this assumption is less likely to be true. One traditional way of avoiding this abruptness is to smooth the matching function spatially by blurring the images. As the displacement becomes larger, the amount of blur required to smooth the matching function becomes also larger. This averaging of pixels leads to a loss of detail in the image. Therefore, there is a trade-off between the size of the objects that can be tracked and the displacement that can be captured.
In this thesis we address the basic problem of increasing the size of the basin of attraction in a matching function. We use an image descriptor called distribution fields (DFs). By blurring the images in DF space instead of in pixel space, we in- crease the size of the basin attraction with respect to traditional methods. We show competitive results using DFs both in object tracking and optical flow. Finally we demonstrate an application of capturing large motions for temporal video stitching.
2014
Modeling the Human Body in 3D: Data Registration and Human Shape Representation
Brown University, Department of Computer Science, May 2014 (phdthesis)
Model transport: towards scalable transfer learning on manifolds - supplemental material
Freifeld, O., Hauberg, S., Black, M. J.
(9), April 2014 (techreport)
This technical report is complementary to "Model Transport: Towards Scalable Transfer Learning on Manifolds" and contains proofs, explanation of the attached video (visualization of bases from the body shape experiments), and high-resolution images of select results of individual reconstructions from the shape experiments. It is identical to the supplemental mate- rial submitted to the Conference on Computer Vision and Pattern Recognition (CVPR 2014) on November 2013.
RoCKIn@Work in a Nutshell
Ahmad, A., Amigoni, A., Awaad, I., Berghofer, J., Bischoff, R., Bonarini, A., Dwiputra, R., Fontana, G., Hegger, F., Hochgeschwender, N., Iocchi, L., Kraetzschmar, G., Lima, P., Matteucci, M., Nardi, D., Schiaffonati, V., Schneider, S.
(FP7-ICT-601012 Revision 1.2), RoCKIn - Robot Competitions Kick Innovation in Cognitive Systems and Robotics, March 2014 (techreport)
The main purpose of RoCKIn@Work is to foster innovation in industrial service robotics. Innovative robot applications for industry call for the capability to work interactively with humans and reduced initial programming requirements. This will open new opportunities to automate challenging manufacturing processes, even for small to medium-sized lots and highly customer-specific production requirements. Thereby, the RoCKIn competitions pave the way for technology transfer and contribute to the continued commercial
competitiveness of European industry.
RoCKIn@Home in a Nutshell
Ahmad, A., Amigoni, F., Awaad, I., Berghofer, J., Bischoff, R., Bonarini, A., Dwiputra, R., Fontana, G., Hegger, F., Hochgeschwender, N., Iocchi, L., Kraetzschmar, G., Lima, P., Matteucci, M., Nardi, D., Schneider, S.
(FP7-ICT-601012 Revision 0.8), RoCKIn - Robot Competitions Kick Innovation in Cognitive Systems and Robotics, March 2014 (techreport)
RoCKIn@Home is a competition that aims at bringing together the benefits of scientific benchmarking with the attraction of scientific competitions in the realm of domestic service robotics. The objectives are to bolster research in service robotics for home applications and to raise public awareness of the current and future capabilities of such robot
systems to meet societal challenges like healthy ageing and longer independent living.
Simulated Annealing
In Encyclopedia of Computer Vision, pages: 737-741, 0, (Editors: Ikeuchi, K. ), Springer Verlag, 2014, to appear (inbook)
2013
Puppet Flow
(7), Max Planck Institute for Intelligent Systems, October 2013 (techreport)
We introduce Puppet Flow (PF), a layered model describing the optical flow of a person in a video sequence. We consider video frames composed by two layers: a foreground layer corresponding to a person, and background.
We model the background as an affine flow field. The foreground layer, being a moving person, requires reasoning about the articulated nature of the human body. We thus represent the foreground layer with the Deformable Structures model (DS), a parametrized 2D part-based human body representation. We call the motion field defined through articulated motion and deformation of the DS model, a Puppet Flow. By exploiting the DS representation, Puppet Flow is a parametrized optical flow field, where parameters are the person's pose, gender and body shape.
D2.1.4 RoCKIn@Work - Innovation in Mobile Industrial Manipulation Competition Design, Rule Book, and Scenario Construction
Ahmad, A., Awaad, I., Amigoni, F., Berghofer, J., Bischoff, R., Bonarini, A., Dwiputra, R., Hegger, F., Hochgeschwender, N., Iocchi, L., Kraetzschmar, G., Lima, P., Matteucci, M., Nardi, D., Schneider, S.
(FP7-ICT-601012 Revision 0.7), RoCKIn - Robot Competitions Kick Innovation in Cognitive Systems and Robotics, sep 2013 (techreport)
RoCKIn is a EU-funded project aiming to foster scientific progress and innovation in cognitive systems and robotics through the design and implementation of competitions.
An additional objective of RoCKIn is to increase public awareness of the current state-of-the-art in robotics in Europe and to demonstrate the innovation potential of robotics applications for solving societal challenges and improving the competitiveness of Europe in the global markets.
In order to achieve these objectives, RoCKIn develops two competitions, one for domestic service robots (RoCKIn@Home) and one for industrial robots in factories (RoCKIn-@Work). These competitions are designed around challenges that are based on easy-to-communicate and convincing user stories, which catch the interest of both the general public and the scientifc community. The latter is in particular interested in solving open scientific challenges and to thoroughly assess, compare, and evaluate the developed approaches with competing ones. To allow this to happen, the competitions are designed to meet the requirements of benchmarking procedures and good experimental methods.
The integration of benchmarking technology with the competition concept is one of the main objectives of RoCKIn.
This document describes the first version of the RoCKIn@Work competition, which will be held for the first time in 2014. The first chapter of the document gives a brief overview, outlining the purpose and objective of the competition, the methodological approach taken by the RoCKIn project, the user story upon which the competition is based, the structure and organization of the competition, and the commonalities and differences
with the RoboCup@Work competition, which served as inspiration for RoCKIn@Work.
The second chapter provides details on the user story and analyzes the scientific and technical challenges it poses. Consecutive chapters detail the competition scenario, the
competition design, and the organization of the competition. The appendices contain information on a library of functionalities, which we believe are needed, or at least useful, for building competition entries, details on the scenario construction, and a detailed account of the benchmarking infrastructure needed — and provided by RoCKIn.
D2.1.1 RoCKIn@Home - A Competition for Domestic Service Robots Competition Design, Rule Book, and Scenario Construction
Ahmad, A., Awaad, I., Amigoni, F., Berghofer, J., Bischoff, R., Bonarini, A., Dwiputra, R., Hegger, F., Hochgeschwender, N., Iocchi, L., Kraetzschmar, G., Lima, P., Matteucci, M., Nardi, D., Schneider, S.
(FP7-ICT-601012 Revision 0.7), RoCKIn - Robot Competitions Kick Innovation in Cognitive Systems and Robotics, sep 2013 (techreport)
RoCKIn is a EU-funded project aiming to foster scientific progress and innovation in cognitive systems and robotics through the design and implementation of competitions.
An additional objective of RoCKIn is to increase public awareness of the current state-of-the-art in robotics in Europe and to demonstrate the innovation potential of robotics applications for solving societal challenges and improving the competitiveness of Europe in the global markets.
In order to achieve these objectives, RoCKIn develops two competitions, one for domestic service robots (RoCKIn@Home) and one for industrial robots in factories (RoCKIn-@Work). These competitions are designed around challenges that are based on easy-to-communicate and convincing user stories, which catch the interest of both the general public and the scientifc community. The latter is in particular interested in solving open scientific challenges and to thoroughly assess, compare, and evaluate the developed approaches with competing ones. To allow this to happen, the competitions are designed to meet the requirements of benchmarking procedures and good experimental methods.
The integration of benchmarking technology with the competition concept is one of the main objectives of RoCKIn.
This document describes the first version of the RoCKIn@Home competition, which will be held for the first time in 2014. The first chapter of the document gives a brief overview, outlining the purpose and objective of the competition, the methodological approach taken by the RoCKIn project, the user story upon which the competition is based, the structure and organization of the competition, and the commonalities and differences
with the RoboCup@Home competition, which served as inspiration for RoCKIn@Home.
The second chapter provides details on the user story and analyzes the scientific and technical challenges it poses. Consecutive chapters detail the competition scenario, the
competition design, and the organization of the competition. The appendices contain information on a library of functionalities, which we believe are needed, or at least useful, for building competition entries, details on the scenario construction, and a detailed account of the benchmarking infrastructure needed — and provided by RoCKIn.
Statistics on Manifolds with Applications to Modeling Shape Deformations
Brown University, August 2013 (phdthesis)
Statistical models of non-rigid deformable shape have wide application in many fi elds,
including computer vision, computer graphics, and biometry. We show that shape deformations
are well represented through nonlinear manifolds that are also matrix Lie groups.
These pattern-theoretic representations lead to several advantages over other alternatives,
including a principled measure of shape dissimilarity and a natural way to compose deformations.
Moreover, they enable building models using statistics on manifolds. Consequently,
such models are superior to those based on Euclidean representations. We
demonstrate this by modeling 2D and 3D human body shape. Shape deformations are
only one example of manifold-valued data. More generally, in many computer-vision and
machine-learning problems, nonlinear manifold representations arise naturally and provide
a powerful alternative to Euclidean representations. Statistics is traditionally concerned
with data in a Euclidean space, relying on the linear structure and the distances associated
with such a space; this renders it inappropriate for nonlinear spaces. Statistics can,
however, be generalized to nonlinear manifolds. Moreover, by respecting the underlying
geometry, the statistical models result in not only more e ffective analysis but also consistent
synthesis. We go beyond previous work on statistics on manifolds by showing how,
even on these curved spaces, problems related to modeling a class from scarce data can be
dealt with by leveraging information from related classes residing in di fferent regions of the
space. We show the usefulness of our approach with 3D shape deformations. To summarize
our main contributions: 1) We de fine a new 2D articulated model -- more expressive than
traditional ones -- of deformable human shape that factors body-shape, pose, and camera
variations. Its high realism is obtained from training data generated from a detailed 3D
model. 2) We defi ne a new manifold-based representation of 3D shape deformations that
yields statistical deformable-template models that are better than the current state-of-the-
art. 3) We generalize a transfer learning idea from Euclidean spaces to Riemannian
manifolds. This work demonstrates the value of modeling manifold-valued data and their
statistics explicitly on the manifold. Specifi cally, the methods here provide new tools for
shape analysis.
D1.1 Specification of General Features of Scenarios and Robots for Benchmarking Through Competitions
Ahmad, A., Awaad, I., Amigoni, F., Berghofer, J., Bischoff, R., Bonarini, A., Dwiputra, R., Fontana, G., Hegger, F., Hochgeschwender, N., Iocchi, L., Kraetzschmar, G., Lima, P., Matteucci, M., Nardi, D., Schiaffonati, V., Schneider, S.
(FP7-ICT-601012 Revision 1.0), RoCKIn - Robot Competitions Kick Innovation in Cognitive Systems and Robotics, July 2013 (techreport)
RoCKIn is a EU-funded project aiming to foster scientific progress and innovation in cognitive systems and robotics through the design and implementation of competitions.
An additional objective of RoCKIn is to increase public awareness of the current state-of-the-art in robotics and the innovation potential of robotics applications. From these objectives several requirements for the work performed in RoCKIn can be derived:
The RoCKIn competitions must start from convincing, easy-to-communicate user stories, that catch the attention of relevant stakeholders, the media, and the crowd. The user stories play the role of a mid- to long-term vision for a competition. Preferably, the user stories address economic, societal, or environmental problems.
The RoCKIn competitions must pose open scientific challenges of interest to sufficiently many researchers to attract existing and new teams of robotics researchers
for participation in the competition. The competitions need to promise some suitable reward, such as recognition in the scientific community, publicity for a team’s work, awards, or prize money, to justify the effort a team puts into the development of a competition entry. The competitions should be designed in such a way that they reward general, scientifically sound solutions to the challenge problems; such general solutions should score better than approaches that work only in narrowly defined contexts and are considred over-engineered.
The challenges motivating the RoCKIn competitions must be broken down into suitable intermediate goals that can be reached with a limited team effort until the next competition and the project duration.
The RoCKIn competitions must be well-defined and well-designed, with comprehensive rule books and instructions for the participants in order to guarantee a fair competition.
The RoCKIn competitions must integrate competitions with benchmarking in order to provide comprehensive feedback for the teams about the suitability of particular functional modules, their overall architecture, and system integration.
This document takes the first steps towards the RoCKIn goals. After outlining our approach, we present several user stories for further discussion within the community. The main objectives of this document are to identify and document relevant scenario features and the tasks and functionalities subject for benchmarking in the competitions.
SocRob-MSL 2013 Team Description Paper for Middle Sized League
Messias, J., Ahmad, A., Reis, J., Serafim, M., Lima, P.
17th Annual RoboCup International Symposium 2013, July 2013 (techreport)
This paper describes the status of the SocRob MSL robotic soccer team as required by the RoboCup 2013 qualification procedures. The team’s latest scientific and technical developments, since its last participation in RoboCup
MSL, include further advances in cooperative perception; novel communication methods for distributed robotics; progressive deployment of the ROS middleware; improved localization through feature tracking and Mixture MCL; novel
planning methods based on Petri nets and decision-theoretic frameworks; and hardware developments in ball-handling/kicking devices.
Probabilistic Models for 3D Urban Scene Understanding from Movable Platforms
Karlsruhe Institute of Technology, Karlsruhe Institute of Technology, April 2013 (phdthesis)
Visual 3D scene understanding is an important component in autonomous
driving and robot navigation. Intelligent vehicles for example often
base their decisions on observations obtained from video cameras
as they are cheap and easy to employ. Inner-city intersections represent
an interesting but also very challenging scenario in this context:
The road layout may be very complex and observations are often noisy
or even missing due to heavy occlusions. While Highway navigation
and autonomous driving on simple and annotated intersections have
already been demonstrated successfully, understanding and navigating
general inner-city crossings with little prior knowledge remains
an unsolved problem. This thesis is a contribution to understanding
multi-object traffic scenes from video sequences. All data is provided
by a camera system which is mounted on top of the autonomous driving
platform AnnieWAY. The proposed probabilistic generative model reasons
jointly about the 3D scene layout as well as the 3D location and
orientation of objects in the scene. In particular, the scene topology,
geometry as well as traffic activities are inferred from short video
sequences. The model takes advantage of monocular information in
the form of vehicle tracklets, vanishing lines and semantic labels.
Additionally, the benefit of stereo features such as 3D scene flow
and occupancy grids is investigated. Motivated by the impressive
driving capabilities of humans, no further information such as GPS,
lidar, radar or map knowledge is required. Experiments conducted
on 113 representative intersection sequences show that the developed
approach successfully infers the correct layout in a variety of difficult
scenarios. To evaluate the importance of each feature cue, experiments
with different feature combinations are conducted. Additionally,
the proposed method is shown to improve object detection and object
orientation estimation performance.
A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them
Sun, D., Roth, S., Black, M. J.
(CS-10-03), Brown University, Department of Computer Science, January 2013 (techreport)
Modeling Shapes with Higher-Order Graphs: Theory and Applications
Wang, C., Zeng, Y., Samaras, D., Paragios, N.
In Shape Perception in Human and Computer Vision: An Interdisciplinary Perspective, (Editors: Zygmunt Pizlo and Sven Dickinson), Springer, 2013 (incollection)
Class-Specific Hough Forests for Object Detection
Gall, J., Lempitsky, V.
In Decision Forests for Computer Vision and Medical Image Analysis, pages: 143-157, 11, (Editors: Criminisi, A. and Shotton, J.), Springer, 2013 (incollection)
Image Gradient Based Level Set Methods in 2D and 3D
Xianhua Xie, Si Yong Yeo, Majid Mirmehdi, Igor Sazonov, Perumal Nithiarasu
In Deformation Models: Tracking, Animation and Applications, pages: 101-120, 0, (Editors: Manuel González Hidalgo and Arnau Mir Torres and Javier Varona Gómez), Springer, 2013 (inbook)
This chapter presents an image gradient based approach to perform 2D and 3D deformable model segmentation using level set. The 2D method uses an external force field that is based on magnetostatics and hypothesized magnetic interactions between the active contour and object boundaries. The major contribution of the method is that the interaction of its forces can greatly improve the active contour in capturing complex geometries and dealing with difficult initializations, weak edges and broken boundaries. This method is then generalized to 3D by reformulating its external force based on geometrical interactions between the relative geometries of the deformable model and the object boundary characterized by image gradient. The evolution of the deformable model is solved using the level set method so that topological changes are handled automatically. The relative geometrical configurations between the deformable model and the object boundaries contribute to a dynamic vector force field that changes accordingly as the deformable model evolves. The geometrically induced dynamic interaction force has been shown to greatly improve the deformable model performance in acquiring complex geometries and highly concave boundaries, and it gives the deformable model a high invariancy in initialization configurations. The voxel interactions across the whole image domain provide a global view of the object boundary representation, giving the external force a long attraction range. The bidirectionality of the external force field allows the new deformable model to deal with arbitrary cross-boundary initializations, and facilitates the handling of weak edges and broken boundaries.
2012
Virtual Human Bodies with Clothing and Hair: From Images to Animation
Brown University, Department of Computer Science, December 2012 (phdthesis)
Coregistration: Supplemental Material
(No. 4), Max Planck Institute for Intelligent Systems, October 2012 (techreport)
Lie Bodies: A Manifold Representation of 3D Human Shape. Supplemental Material
(No. 5), Max Planck Institute for Intelligent Systems, October 2012 (techreport)
MPI-Sintel Optical Flow Benchmark: Supplemental Material
(No. 6), Max Planck Institute for Intelligent Systems, October 2012 (techreport)
From Pixels to Layers: Joint Motion Estimation and Segmentation
Brown University, Department of Computer Science, July 2012 (phdthesis)
Exploiting pedestrian interaction via global optimization and social behaviors
Leal-Taixé, L., Pons-Moll, G., Rosenhahn, B.
In Theoretic Foundations of Computer Vision: Outdoor and Large-Scale Real-World Scene Analysis, Springer, April 2012 (incollection)
HUMIM Software for Articulated Tracking
Soren Hauberg, Kim S. Pedersen
(01/2012), Department of Computer Science, University of Copenhagen, January 2012 (techreport)
A geometric framework for statistics on trees
Aasa Feragen, Mads Nielsen, Soren Hauberg, Pechin Lo, Marleen de Bruijne, Francois Lauze
(11/02), Department of Computer Science, University of Copenhagen, January 2012 (techreport)
Data-driven Manifolds for Outdoor Motion Capture
Pons-Moll, G., Leal-Taix’e, L., Gall, J., Rosenhahn, B.
In Outdoor and Large-Scale Real-World Scene Analysis, 7474, pages: 305-328, LNCS, (Editors: Dellaert, Frank and Frahm, Jan-Michael and Pollefeys, Marc and Rosenhahn, Bodo and Leal-Taix’e, Laura), Springer, 2012 (incollection)
Scan-Based Flow Modelling in Human Upper Airways
Perumal Nithiarasu, Igor Sazonov, Si Yong Yeo
In Patient-Specific Modeling in Tomorrow’s Medicine, pages: 241 - 280, 0, (Editors: Amit Gefen), Springer, 2012 (inbook)
An Introduction to Random Forests for Multi-class Object Detection
Gall, J., Razavi, N., van Gool, L.
In Outdoor and Large-Scale Real-World Scene Analysis, 7474, pages: 243-263, LNCS, (Editors: Dellaert, Frank and Frahm, Jan-Michael and Pollefeys, Marc and Rosenhahn, Bodo and Leal-Taix’e, Laura), Springer, 2012 (incollection)
Home 3D body scans from noisy image and range data
Weiss, A., Hirshberg, D., Black, M. J.
In Consumer Depth Cameras for Computer Vision: Research Topics and Applications, pages: 99-118, 6, (Editors: Andrea Fossati and Juergen Gall and Helmut Grabner and Xiaofeng Ren and Kurt Konolige), Springer-Verlag, 2012 (incollection)
2011
ISocRob-MSL 2011 Team Description Paper for Middle Sized League
Messias, J., Ahmad, A., Reis, J., Sousa, J., Lima, P.
15th Annual RoboCup International Symposium 2011, July 2011 (techreport)
This paper describes the status of the ISocRob MSL robotic soccer team as required by the RoboCup 2011 qualification procedures. The most relevant technical and scientifical developments carried out by the team, since its last
participation in the RoboCup MSL competitions, are here detailed. These include cooperative localization, cooperative object tracking, planning under uncertainty, obstacle detection and improvements to self-localization.
Steerable random fields for image restoration and inpainting
Roth, S., Black, M. J.
In Markov Random Fields for Vision and Image Processing, pages: 377-387, (Editors: Blake, A. and Kohli, P. and Rother, C.), MIT Press, 2011 (incollection)
This chapter introduces the concept of a Steerable Random Field (SRF). In contrast to traditional Markov random field (MRF) models in low-level vision, the random field potentials of a SRF are defined in terms of filter responses that are steered to the local image structure. This steering uses the structure tensor to obtain derivative responses that are either aligned with, or orthogonal to, the predominant local image structure. Analysis of the statistics of these steered filter responses in natural images leads to the model proposed here. Clique potentials are defined over steered filter responses using a Gaussian scale mixture model and are learned from training data. The SRF model connects random fields with anisotropic regularization and provides a statistical motivation for the latter. Steering the random field to the local image structure improves image denoising and inpainting performance compared with traditional pairwise MRFs.
Benchmark datasets for pose estimation and tracking
Andriluka, M., Sigal, L., Black, M. J.
In Visual Analysis of Humans: Looking at People, pages: 253-274, (Editors: Moesland and Hilton and Kr"uger and Sigal), Springer-Verlag, London, 2011 (incollection)
Fields of experts
Roth, S., Black, M. J.
In Markov Random Fields for Vision and Image Processing, pages: 297-310, (Editors: Blake, A. and Kohli, P. and Rother, C.), MIT Press, 2011 (incollection)
Fields of Experts are high-order Markov random field (MRF) models with potential functions that extend over large pixel neighborhoods. The clique potentials are modeled as a Product of Experts using nonlinear functions of many linear filter responses. In contrast to previous MRF approaches, all parameters, including the linear filters themselves, are learned from training data. A Field of Experts (FoE) provides a generic, expressive image prior that can capture the statistics of natural scenes, and can be used for a variety of machine vision tasks. The capabilities of FoEs are demonstrated with two example applications, image denoising and image inpainting, which are implemented using a simple, approximate inference scheme. While the FoE model is trained on a generic image database and is not tuned toward a specific application, the results compete with specialized techniques.
Model-Based Pose Estimation
Pons-Moll, G., Rosenhahn, B.
In Visual Analysis of Humans: Looking at People, pages: 139-170, 9, (Editors: T. Moeslund, A. Hilton, V. Krueger, L. Sigal), Springer, 2011 (inbook)
2010
ImageFlow: Streaming Image Search
Jampani, V., Ramos, G., Drucker, S.
MSR-TR-2010-148, Microsoft Research, Redmond, 2010 (techreport)
Traditional grid and list representations of image search results are the dominant interaction paradigms that users face on a daily basis, yet it is unclear that such paradigms are well-suited for experiences where the user‟s task is to browse images for leisure, to discover new information or to seek particular images to represent ideas. We introduce ImageFlow, a novel image search user interface that ex-plores a different alternative to the traditional presentation of image search results. ImageFlow presents image results on a canvas where we map semantic features (e.g., rele-vance, related queries) to the canvas‟ spatial dimensions (e.g., x, y, z) in a way that allows for several levels of en-gagement – from passively viewing a stream of images, to seamlessly navigating through the semantic space and ac-tively collecting images for sharing and reuse. We have implemented our system as a fully functioning prototype, and we report on promising, preliminary usage results.
2009
ISocRob-MSL 2009 Team Description Paper for Middle Sized League
Lima, P., Santos, J., Estilita, J., Barbosa, M., Ahmad, A., Carreira, J.
13th Annual RoboCup International Symposium 2009, July 2009 (techreport)
This paper describes the status of the ISocRob MSL roboticsoccer team as required by the RoboCup 2009 qualification procedures.Since its previous participation in RoboCup, the ISocRob team has car-ried out significant developments in various topics, the most relevantof which are presented here. These include self-localization, 3D objecttracking and cooperative object localization, motion control and rela-tional behaviors. A brief description of the hardware of the ISocRobrobots and of the software architecture adopted by the team is also in-cluded.
An introduction to Kernel Learning Algorithms
In Kernel Methods for Remote Sensing Data Analysis, pages: 25-48, 2, (Editors: Gustavo Camps-Valls and Lorenzo Bruzzone), Wiley, New York, NY, USA, 2009 (inbook)
Kernel learning algorithms are currently becoming a standard tool in the area of machine learning and pattern recognition.
In this chapter we review the fundamental theory of kernel learning. As the basic building block we introduce the kernel function,
which provides an elegant and general way to compare possibly very complex objects. We then review the concept
of a reproducing kernel Hilbert space and state the representer theorem. Finally we give an overview of the most
prominent algorithms, which are support vector classification and regression, Gaussian Processes and kernel principal analysis.
With multiple kernel learning and structured output prediction we also introduce some more recent advancements in the field.