Header logo is


2019


Towards Geometric Understanding of Motion
Towards Geometric Understanding of Motion

Ranjan, A.

University of Tübingen, December 2019 (phdthesis)

Abstract

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.

ps

PhD Thesis [BibTex]

2019


PhD Thesis [BibTex]


no image
X-ray microscopic characterization of high-Tc-supercoductors using image processing

Bihler, M.

Universität Stuttgart, Stuttgart, 2019 (mastersthesis)

mms

[BibTex]


no image
Novel X-ray lenses for direct and coherent imaging

Sanli, U. T.

Universität Stuttgart, Stuttgart, 2019 (phdthesis)

mms

link (url) DOI [BibTex]

link (url) DOI [BibTex]

2015


Gaussian Process Optimization for Self-Tuning Control
Gaussian Process Optimization for Self-Tuning Control

Marco, A.

Polytechnic University of Catalonia (BarcelonaTech), October 2015 (mastersthesis)

am ics

PDF Project Page [BibTex]

2015


PDF Project Page [BibTex]


no image
Adaptive and Learning Concepts in Hydraulic Force Control

Doerr, A.

University of Stuttgart, September 2015 (mastersthesis)

am ics

[BibTex]

[BibTex]


Object Detection Using Deep Learning - Learning where to search using visual attention
Object Detection Using Deep Learning - Learning where to search using visual attention

Kloss, A.

Eberhard Karls Universität Tübingen, May 2015 (mastersthesis)

Abstract
Detecting and identifying the different objects in an image fast and reliably is an important skill for interacting with one’s environment. The main problem is that in theory, all parts of an image have to be searched for objects on many different scales to make sure that no object instance is missed. It however takes considerable time and effort to actually classify the content of a given image region and both time and computational capacities that an agent can spend on classification are limited. Humans use a process called visual attention to quickly decide which locations of an image need to be processed in detail and which can be ignored. This allows us to deal with the huge amount of visual information and to employ the capacities of our visual system efficiently. For computer vision, researchers have to deal with exactly the same problems, so learning from the behaviour of humans provides a promising way to improve existing algorithms. In the presented master’s thesis, a model is trained with eye tracking data recorded from 15 participants that were asked to search images for objects from three different categories. It uses a deep convolutional neural network to extract features from the input image that are then combined to form a saliency map. This map provides information about which image regions are interesting when searching for the given target object and can thus be used to reduce the parts of the image that have to be processed in detail. The method is based on a recent publication of Kümmerer et al., but in contrast to the original method that computes general, task independent saliency, the presented model is supposed to respond differently when searching for different target categories.

am

PDF Project Page [BibTex]


Robot Arm Tracking with Random Decision Forests
Robot Arm Tracking with Random Decision Forests

Widmaier, F.

Eberhard-Karls-Universität Tübingen, May 2015 (mastersthesis)

Abstract
For grasping and manipulation with robot arms, knowing the current pose of the arm is crucial for successful controlling its motion. Often, pose estimations can be acquired from encoders inside the arm, but they can have significant inaccuracy which makes the use of additional techniques necessary. In this master thesis, a novel approach of robot arm pose estimation is presented, that works on single depth images without the need of prior foreground segmentation or other preprocessing steps. A random regression forest is used, which is trained only on synthetically generated data. The approach improves former work by Bohg et al. by considerably reducing the computational effort both at training and test time. The forest in the new method directly estimates the desired joint angles while in the former approach, the forest casts 3D position votes for the joints, which then have to be clustered and fed into an iterative inverse kinematic process to finally get the joint angles. To improve the estimation accuracy, the standard training objective of the forest training is replaced by a specialized function that makes use of a model-dependent distance metric, called DISP. Experimental results show that the specialized objective indeed improves pose estimation and it is shown that the method, despite of being trained on synthetic data only, is able to provide reasonable estimations for real data at test time.

am

PDF Project Page [BibTex]

PDF Project Page [BibTex]


Shape Models of the Human Body for Distributed Inference
Shape Models of the Human Body for Distributed Inference

Zuffi, S.

Brown University, May 2015 (phdthesis)

Abstract
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.

ps

PDF [BibTex]


From Scans to Models: Registration of 3D Human Shapes Exploiting Texture Information
From Scans to Models: Registration of 3D Human Shapes Exploiting Texture Information

Bogo, F.

University of Padova, March 2015 (phdthesis)

Abstract
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.

ps

[BibTex]


Long Range Motion Estimation and Applications
Long Range Motion Estimation and Applications

Sevilla-Lara, L.

Long Range Motion Estimation and Applications, University of Massachusetts Amherst, University of Massachusetts Amherst, Febuary 2015 (phdthesis)

Abstract
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.

ps

[BibTex]

[BibTex]


no image
Policy Search for Imitation Learning

Doerr, A.

University of Stuttgart, January 2015 (thesis)

am ics

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


no image
Strukturelle und spektroskopische Eigenschaften epitaktischer FeMn/Co Exchange-Bias-Systeme

Schmidt, M.

Universität Stuttgart, Stuttgart, 2015 (phdthesis)

mms

link (url) DOI [BibTex]


no image
Ultraschnelles Vortexkernschalten

Noske, M.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2015 (phdthesis)

mms

[BibTex]

[BibTex]


no image
Investigations of unusual hard magnetic MnBi LTP phase, utilizing temperature dependent SQUID-FORC

Muralidhar, Shreyas

Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Magnetische Röntgenmikroskopie an Hochtemperatur-Supraleitern

Stahl, C.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2015 (phdthesis)

mms

[BibTex]

[BibTex]


no image
Voltage-induced magnetic manipulation of a microstructured iron gold multilayer system

Sittig, Robert

Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Transfer of angular momentum from the spin system to the lattice during ultrafast magnetization

Tsatsoulis, T.

Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Quantum kinetic theory of ultrafast demagnetization by electron-phonon scattering

Briones Paz, J. Z.

Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

mms

[BibTex]

[BibTex]

2007


no image
Machine Learning of Motor Skills for Robotics

Peters, J.

University of Southern California, Los Angeles, CA, USA, University of Southern California, Los Angeles, CA, USA, 2007, clmc (phdthesis)

Abstract
Autonomous robots that can assist humans in situations of daily life have been a long standing vision of robotics, artificial intelligence, and cognitive sciences. A first step towards this goal is to create robots that can accomplish a multitude of different tasks, triggered by environmental context or higher level instruction. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s, however, made it clear that an approach purely based on reasoning and human insights would not be able to model all the perceptuomotor tasks that a robot should fulfill. Instead, new hope was put in the growing wake of machine learning that promised fully adaptive control algorithms which learn both by observation and trial-and-error. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this thesis, we investigate the ingredients for a general approach to motor skill learning in order to get one step closer towards human-like performance. For doing so, we study two major components for such an approach, i.e., firstly, a theoretically well-founded general approach to representing the required control structures for task representation and execution and, secondly, appropriate learning algorithms which can be applied in this setting. As a theoretical foundation, we first study a general framework to generate control laws for real robots with a particular focus on skills represented as dynamical systems in differential constraint form. We present a point-wise optimal control framework resulting from a generalization of Gauss' principle and show how various well-known robot control laws can be derived by modifying the metric of the employed cost function. The framework has been successfully applied to task space tracking control for holonomic systems for several different metrics on the anthropomorphic SARCOS Master Arm. In order to overcome the limiting requirement of accurate robot models, we first employ learning methods to find learning controllers for task space control. However, when learning to execute a redundant control problem, we face the general problem of the non-convexity of the solution space which can force the robot to steer into physically impossible configurations if supervised learning methods are employed without further consideration. This problem can be resolved using two major insights, i.e., the learning problem can be treated as locally convex and the cost function of the analytical framework can be used to ensure global consistency. Thus, we derive an immediate reinforcement learning algorithm from the expectation-maximization point of view which leads to a reward-weighted regression technique. This method can be used both for operational space control as well as general immediate reward reinforcement learning problems. We demonstrate the feasibility of the resulting framework on the problem of redundant end-effector tracking for both a simulated 3 degrees of freedom robot arm as well as for a simulated anthropomorphic SARCOS Master Arm. While learning to execute tasks in task space is an essential component to a general framework to motor skill learning, learning the actual task is of even higher importance, particularly as this issue is more frequently beyond the abilities of analytical approaches than execution. We focus on the learning of elemental tasks which can serve as the "building blocks of movement generation", called motor primitives. Motor primitives are parameterized task representations based on splines or nonlinear differential equations with desired attractor properties. While imitation learning of parameterized motor primitives is a relatively well-understood problem, the self-improvement by interaction of the system with the environment remains a challenging problem, tackled in the fourth chapter of this thesis. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and outline both established and novel algorithms for the gradient-based improvement of parameterized policies. We compare these algorithms in the context of motor primitive learning, and show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. In conclusion, in this thesis, we have contributed a general framework for analytically computing robot control laws which can be used for deriving various previous control approaches and serves as foundation as well as inspiration for our learning algorithms. We have introduced two classes of novel reinforcement learning methods, i.e., the Natural Actor-Critic and the Reward-Weighted Regression algorithm. These algorithms have been used in order to replace the analytical components of the theoretical framework by learned representations. Evaluations have been performed on both simulated and real robot arms.

am ei

[BibTex]

2007


[BibTex]


no image
On the theory of magnetization dynamics of non-collinear spin systems in the s-d model

De Angeli, L.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Zur ab-initio Elektronentheorie des Magnetismus bei endlichen Temperaturen

Dietermann, F.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Röntgenzirkulardichroische Untersuchungen an ferromagnetischen verdünnten Halbleitersystemen

Tietze, T.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Low-dimensional Fe on vicinal Ir(997): Growth and magnetic properties

Kawwam, M.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Micromagnetic simulations of switching processes and the role of thermal fluctuations

Macke, S.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Physisorption von Wasserstoff in neuen Materialien mit gro\sser spezifischer Oberfläche

Schmitz, B.

Universität Bonn, Bonn, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Towards spin injection into silicon

Dash, S. P.

Universität Stuttgart, Stuttgart, 2007 (phdthesis)

mms

link (url) [BibTex]

link (url) [BibTex]


no image
Bestimmung der kritischen Schichtdicken ferromagnetischer Plättchen für Eindomänenverhalten

Soehnle, S.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Zeitaufgelöste Röntgenmikroskopie an magnetischen Mikrostrukturen

Puzic, A.

Universität Stuttgart, Stuttgart, 2007 (phdthesis)

mms

link (url) [BibTex]

link (url) [BibTex]


no image
Vortex dynamics studied by time-resolved X-ray microscopy

Chou, K. W.

Universität Stuttgart, Stuttgart, 2007 (phdthesis)

mms

link (url) [BibTex]

link (url) [BibTex]


no image
Resonante magnetische Reflektometrie an Ferromagnet/Paramagnet Heterostrukturen

Ferreras Paz, V.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Herstellung und Charakterisierung dünner Niob-Schichten auf verschiedenen Substraten

Mayer, M. W. R.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Formation of hard magnetic L10-FePt/FePd monolayers from elemental multilayers

Goo, N. H.

Universität Stuttgart, Stuttgart, 2007 (phdthesis)

mms

link (url) [BibTex]

link (url) [BibTex]


no image
Zur ab-initio Elektronentheorie stark nichtkollinearer Spinsysteme

Köberle, I.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Theorie der Kernspektroskopie mit zirkular polarisierter Gammastrahlung

Engelhart, W.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Untersuchung der Adsorption von Wasserstoff in porösen Materialien

Hönes, K.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Untersuchung der mechanischen Eigenschaften dünner Chromschichten

Jüllig, P.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]

1992


Robust Incremental Optical Flow
Robust Incremental Optical Flow

Black, M. J.

Yale University, Department of Computer Science, New Haven, CT, 1992, Research Report YALEU-DCS-RR-923 (phdthesis)

ps

pdf Old C code (dense) Old C code (regression) Modern Code (Matlab) [BibTex]

1992


pdf Old C code (dense) Old C code (regression) Modern Code (Matlab) [BibTex]