Publications | Max Planck Institute for Intelligent Systems

am ics Marco, A. Gaussian Process Optimization for Self-Tuning Control Polytechnic University of Catalonia (BarcelonaTech), October 2015 (mastersthesis)

PDF Project Page [BibTex]

From Points to Probability Measures: A Statistical Learning on Distributions with Kernel Mean Embedding

Muandet, K.

University of Tübingen, Germany, University of Tübingen, Germany, September 2015 (phdthesis)

[BibTex]

ei Muandet, K. From Points to Probability Measures: A Statistical Learning on Distributions with Kernel Mean Embedding University of Tübingen, Germany, University of Tübingen, Germany, September 2015 (phdthesis)

[BibTex]

Machine Learning Approaches to Image Deconvolution

Schuler, C.

University of Tübingen, Germany, University of Tübingen, Germany, September 2015 (phdthesis)

[BibTex]

ei Schuler, C. Machine Learning Approaches to Image Deconvolution University of Tübingen, Germany, University of Tübingen, Germany, September 2015 (phdthesis)

[BibTex]

Adaptive and Learning Concepts in Hydraulic Force Control

Doerr, A.

University of Stuttgart, September 2015 (mastersthesis)

am ics

[BibTex]

am ics Doerr, A. Adaptive and Learning Concepts in Hydraulic Force Control University of Stuttgart, September 2015 (mastersthesis)

[BibTex]

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.

PDF Project Page [BibTex]

am Kloss, A. Object Detection Using Deep Learning - Learning where to search using visual attention Eberhard Karls Universität Tübingen, May 2015 (mastersthesis)

PDF Project Page [BibTex]

Blind Retrospective Motion Correction of MR Images

Loktyushin, A.

University of Tübingen, Germany, May 2015 (phdthesis)

[BibTex]

ei Loktyushin, A. Blind Retrospective Motion Correction of MR Images University of Tübingen, Germany, May 2015 (phdthesis)

[BibTex]

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.

PDF Project Page [BibTex]

am Widmaier, F. Robot Arm Tracking with Random Decision Forests Eberhard-Karls-Universität Tübingen, May 2015 (mastersthesis)

PDF Project Page [BibTex]

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 dened realistic models can be important for computer vision. More work at the intersection of vision and graphics is thus encouraged.

PDF [BibTex]

ps Zuffi, S. Shape Models of the Human Body for Distributed Inference Brown University, May 2015 (phdthesis)

PDF [BibTex]

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.

[BibTex]

ps Bogo, F. From Scans to Models: Registration of 3D Human Shapes Exploiting Texture Information University of Padova, March 2015 (phdthesis)

[BibTex]

Haptic Textures for Online Shopping

Culbertson, H., Kuchenbecker, K. J.

Interactive demonstrations in The Retail Collective exhibit, presented at the Dx3 Conference in Toronto, Canada, March 2015 (misc)

[BibTex]

hi Culbertson, H., Kuchenbecker, K. J. Haptic Textures for Online Shopping Interactive demonstrations in The Retail Collective exhibit, presented at the Dx3 Conference in Toronto, Canada, March 2015 (misc)

[BibTex]

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.

[BibTex]

ps Sevilla-Lara, L. Long Range Motion Estimation and Applications Long Range Motion Estimation and Applications, University of Massachusetts Amherst, University of Massachusetts Amherst, Febuary 2015 (phdthesis)

[BibTex]

Policy Search for Imitation Learning

Doerr, A.

University of Stuttgart, January 2015 (thesis)

am ics

link (url) Project Page [BibTex]

am ics Doerr, A. Policy Search for Imitation Learning University of Stuttgart, January 2015 (thesis)

link (url) Project Page [BibTex]

A Cognitive Brain-Computer Interface for Patients with Amyotrophic Lateral Sclerosis

Hohmann, M.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2015 (mastersthesis)

[BibTex]

ei Hohmann, M. A Cognitive Brain-Computer Interface for Patients with Amyotrophic Lateral Sclerosis Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2015 (mastersthesis)

[BibTex]

Sequential Image Deconvolution Using Probabilistic Linear Algebra

Gao, M.

Technical University of Munich, Germany, 2015 (mastersthesis)

[BibTex]

ei Gao, M. Sequential Image Deconvolution Using Probabilistic Linear Algebra Technical University of Munich, Germany, 2015 (mastersthesis)

[BibTex]

Causal Inference in Neuroimaging

Casarsa de Azevedo, L.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2015 (mastersthesis)

[BibTex]

ei Casarsa de Azevedo, L. Causal Inference in Neuroimaging Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2015 (mastersthesis)

[BibTex]

The effect of frowning on attention

Ibarra Chaoul, A.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2015 (mastersthesis)

[BibTex]

ei Ibarra Chaoul, A. The effect of frowning on attention Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2015 (mastersthesis)

[BibTex]

Strukturelle und spektroskopische Eigenschaften epitaktischer FeMn/Co Exchange-Bias-Systeme

Schmidt, M.

Universität Stuttgart, Stuttgart, 2015 (phdthesis)

mms

link (url) DOI [BibTex]

mms Schmidt, M. Strukturelle und spektroskopische Eigenschaften epitaktischer FeMn/Co Exchange-Bias-Systeme Universität Stuttgart, Stuttgart, 2015 (phdthesis)

link (url) DOI [BibTex]

Ultraschnelles Vortexkernschalten

Noske, M.

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

mms

[BibTex]

mms Noske, M. Ultraschnelles Vortexkernschalten Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2015 (phdthesis)

[BibTex]

Investigations of unusual hard magnetic MnBi LTP phase, utilizing temperature dependent SQUID-FORC

Muralidhar, Shreyas

Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

mms

[BibTex]

mms Muralidhar, Shreyas Investigations of unusual hard magnetic MnBi LTP phase, utilizing temperature dependent SQUID-FORC Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

[BibTex]

Magnetische Röntgenmikroskopie an Hochtemperatur-Supraleitern

Stahl, C.

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

mms

[BibTex]

mms Stahl, C. Magnetische Röntgenmikroskopie an Hochtemperatur-Supraleitern Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2015 (phdthesis)

[BibTex]

Decentralized network control, optimization and random walks on networks

De Bacco, C.

(2015PA112164), Université Paris Sud - Paris XI, sep 2015 (phdthesis)

pio

link (url) [BibTex]

pio De Bacco, C. Decentralized network control, optimization and random walks on networks (2015PA112164), Université Paris Sud - Paris XI, sep 2015 (phdthesis)

link (url) [BibTex]

Voltage-induced magnetic manipulation of a microstructured iron gold multilayer system

Sittig, Robert

Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

mms

[BibTex]

mms Sittig, Robert Voltage-induced magnetic manipulation of a microstructured iron gold multilayer system Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

[BibTex]

Ion beam lithographic and multilayer Fresnel zone plates for soft and hard X-rays: Nanofabrication and characterization

Keskinbora, K.

Universität Stuttgart, Stuttgart, 2015 (phdthesis)

mms

link (url) DOI [BibTex]

mms Keskinbora, K. Ion beam lithographic and multilayer Fresnel zone plates for soft and hard X-rays: Nanofabrication and characterization Universität Stuttgart, Stuttgart, 2015 (phdthesis)

link (url) DOI [BibTex]

Transfer of angular momentum from the spin system to the lattice during ultrafast magnetization

Tsatsoulis, T.

Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

mms

[BibTex]

mms Tsatsoulis, T. Transfer of angular momentum from the spin system to the lattice during ultrafast magnetization Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

[BibTex]

Derivation of phenomenological expressions for transition matrix elements for electron-phonon scattering

Illg, C., Haag, M., Müller, B. Y., Czycholl, G., Fähnle, M.

2015 (misc)

mms

link (url) [BibTex]

mms Illg, C., Haag, M., Müller, B. Y., Czycholl, G., Fähnle, M. Derivation of phenomenological expressions for transition matrix elements for electron-phonon scattering 2015 (misc)

link (url) [BibTex]

Quantum kinetic theory of ultrafast demagnetization by electron-phonon scattering

Briones Paz, J. Z.

Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

mms

[BibTex]

mms Briones Paz, J. Z. Quantum kinetic theory of ultrafast demagnetization by electron-phonon scattering Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

[BibTex]

2011

Multi-Modal Scene Understanding for Robotic Grasping

Bohg, J.

(2011:17):vi, 194, Trita-CSC-A, KTH Royal Institute of Technology, KTH, Computer Vision and Active Perception, CVAP, Centre for Autonomous Systems, CAS, KTH, Centre for Autonomous Systems, CAS, December 2011 (phdthesis)

Abstract

Current robotics research is largely driven by the vision of creating an intelligent being that can perform dangerous, difficult or unpopular tasks. These can for example be exploring the surface of planet mars or the bottom of the ocean, maintaining a furnace or assembling a car. They can also be more mundane such as cleaning an apartment or fetching groceries. This vision has been pursued since the 1960s when the first robots were built. Some of the tasks mentioned above, especially those in industrial manufacturing, are already frequently performed by robots. Others are still completely out of reach. Especially, household robots are far away from being deployable as general purpose devices. Although advancements have been made in this research area, robots are not yet able to perform household chores robustly in unstructured and open-ended environments given unexpected events and uncertainty in perception and execution.In this thesis, we are analyzing which perceptual and motor capabilities are necessary for the robot to perform common tasks in a household scenario. In that context, an essential capability is to understand the scene that the robot has to interact with. This involves separating objects from the background but also from each other.Once this is achieved, many other tasks become much easier. Configuration of object scan be determined; they can be identified or categorized; their pose can be estimated; free and occupied space in the environment can be outlined.This kind of scene model can then inform grasp planning algorithms to finally pick up objects.However, scene understanding is not a trivial problem and even state-of-the-art methods may fail. Given an incomplete, noisy and potentially erroneously segmented scene model, the questions remain how suitable grasps can be planned and how they can be executed robustly.In this thesis, we propose to equip the robot with a set of prediction mechanisms that allow it to hypothesize about parts of the scene it has not yet observed. Additionally, the robot can also quantify how uncertain it is about this prediction allowing it to plan actions for exploring the scene at specifically uncertain places. We consider multiple modalities including monocular and stereo vision, haptic sensing and information obtained through a human-robot dialog system. We also study several scene representations of different complexity and their applicability to a grasping scenario. Given an improved scene model from this multi-modal exploration, grasps can be inferred for each object hypothesis. Dependent on whether the objects are known, familiar or unknown, different methodologies for grasp inference apply. In this thesis, we propose novel methods for each of these cases. Furthermore,we demonstrate the execution of these grasp both in a closed and open-loop manner showing the effectiveness of the proposed methods in real-world scenarios.

pdf [BibTex]

2011

am Bohg, J. Multi-Modal Scene Understanding for Robotic Grasping (2011:17):vi, 194, Trita-CSC-A, KTH Royal Institute of Technology, KTH, Computer Vision and Active Perception, CVAP, Centre for Autonomous Systems, CAS, KTH, Centre for Autonomous Systems, CAS, December 2011 (phdthesis)

pdf [BibTex]

Please \soutdo not touch the robot

Romano, J. M., Kuchenbecker, K. J.

Hands-on demonstration presented at IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), San Francisco, California, sep 2011 (misc)

[BibTex]

hi Romano, J. M., Kuchenbecker, K. J. Please \soutdo not touch the robot Hands-on demonstration presented at IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), San Francisco, California, sep 2011 (misc)

[BibTex]