Bodo Rosenhahn – författare

This two-volume set constitutes the refereed proceedings of the workshops which complemented the 21th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD, held in September 2021. Due to the COVID-19 pandemic the conference and workshops were held online. The 104 papers were thoroughly reviewed and selected from 180 papers submited for the workshops. This two-volume set includes the proceedings of the following workshops:Workshop on Advances in Interpretable Machine Learning and Artificial Intelligence (AIMLAI 2021)Workshop on Parallel, Distributed and Federated Learning (PDFL 2021)Workshop on Graph Embedding and Mining  (GEM 2021)Workshop on Machine Learning for Irregular Time-series (ML4ITS 2021)Workshop on IoT, Edge, and Mobile for Embedded Machine Learning (ITEM 2021)Workshop on eXplainable Knowledge Discovery in Data Mining (XKDD 2021)Workshop on Bias and Fairness in AI (BIAS 2021)Workshop on Workshop on Active Inference (IWAI 2021)Workshop on Machine Learning for Cybersecurity (MLCS 2021)Workshop on Machine Learning in Software Engineering (MLiSE 2021)Workshop on MIning Data for financial applications (MIDAS 2021)Sixth Workshop on Data Science for Social Good (SoGood 2021)Workshop on Machine Learning for Pharma and Healthcare Applications (PharML 2021)Second Workshop on Evaluation and Experimental Design in Data Mining and Machine Learning (EDML 2020)Workshop on Machine Learning for Buildings Energy Management (MLBEM 2021)

Multimodal Scene Understanding: Algorithms, Applications and Deep Learning presents recent advances in multi-modal computing, with a focus on computer vision and photogrammetry. It provides the latest algorithms and applications that involve combining multiple sources of information and describes the role and approaches of multi-sensory data and multi-modal deep learning. The book is ideal for researchers from the fields of computer vision, remote sensing, robotics, and photogrammetry, thus helping foster interdisciplinary interaction and collaboration between these realms.

Researchers collecting and analyzing multi-sensory data collections - for example, KITTI benchmark (stereo+laser) - from different platforms, such as autonomous vehicles, surveillance cameras, UAVs, planes and satellites will find this book to be very useful.

Contains state-of-the-art developments on multi-modal computing Shines a focus on algorithms and applications Presents novel deep learning topics on multi-sensor fusion and multi-modal deep learning

Multimodal Scene Understanding: Algorithms, Applications and Deep Learning presents recent advances in multi-modal computing, with a focus on computer vision and photogrammetry. It provides the latest algorithms and applications that involve combining multiple sources of information and describes the role and approaches of multi-sensory data and multi-modal deep learning. The book is ideal for researchers from the fields of computer vision, remote sensing, robotics, and photogrammetry, thus helping foster interdisciplinary interaction and collaboration between these realms.Researchers collecting and analyzing multi-sensory data collections – for example, KITTI benchmark (stereo+laser) - from different platforms, such as autonomous vehicles, surveillance cameras, UAVs, planes and satellites will find this book to be very useful.- Contains state-of-the-art developments on multi-modal computing- Shines a focus on algorithms and applications- Presents novel deep learning topics on multi-sensor fusion and multi-modal deep learning

Edward Muybridge (1830–1904) is known as the pioneer in motion capt- ing with his famous experiments in 1887 called “Animal Locomotion”. Since then, the ?eld of animal or human motion analysis has grown in many dir- tions. However, research and results that involve human-like animation and the recovery of motion is still far from being satisfactory. The modelling, tracking, and understanding of human motion based on video sequences as a research ?eld has increased in importance particularly in thelastdecadewiththeemergenceofapplicationsinsportssciences,medicine, biomechanics, animation (online games), surveillance, and security. Progress in human motion analysis depends on empirically anchored and grounded research in computer vision, computer graphics, and biomechanics. Though these ?elds of research are often treated separately, human motion analysis requires the integration of methodologies from computer vision and computer graphics.Furthermore,theunderstandinganduseofbiomechanicsconstraints improves the robustness of such an approach. This book is based on a June 2006 workshop held in Dagstuhl, Germany. This workshop brought together for the ?rst time researchers from the afo- mentioned disciplines. Based on their diverse perspectives, these researchers havebeendevelopingnewmethodologiesandcontributing,throughtheir?- ings, to the domain of human motion analysis. The interdisciplinary character of the workshop allowed people to present a wide range of approaches that helped stimulate intellectual discussions and the exchange of new ideas.

Edward Muybridge (1830–1904) is known as the pioneer in motion capt- ing with his famous experiments in 1887 called “Animal Locomotion”. Since then, the ?eld of animal or human motion analysis has grown in many dir- tions. However, research and results that involve human-like animation and the recovery of motion is still far from being satisfactory. The modelling, tracking, and understanding of human motion based on video sequences as a research ?eld has increased in importance particularly in thelastdecadewiththeemergenceofapplicationsinsportssciences,medicine, biomechanics, animation (online games), surveillance, and security. Progress in human motion analysis depends on empirically anchored and grounded research in computer vision, computer graphics, and biomechanics. Though these ?elds of research are often treated separately, human motion analysis requires the integration of methodologies from computer vision and computer graphics.Furthermore,theunderstandinganduseofbiomechanicsconstraints improves the robustness of such an approach. This book is based on a June 2006 workshop held in Dagstuhl, Germany. This workshop brought together for the ?rst time researchers from the afo- mentioned disciplines. Based on their diverse perspectives, these researchers havebeendevelopingnewmethodologiesandcontributing,throughtheir?- ings, to the domain of human motion analysis. The interdisciplinary character of the workshop allowed people to present a wide range of approaches that helped stimulate intellectual discussions and the exchange of new ideas.

This two-volume set constitutes the refereed proceedings of the workshops which complemented the 21th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD, held in September 2021. Due to the COVID-19 pandemic the conference and workshops were held online. The 104 papers were thoroughly reviewed and selected from 180 papers submited for the workshops. This two-volume set includes the proceedings of the following workshops:Workshop on Advances in Interpretable Machine Learning and Artificial Intelligence (AIMLAI 2021)Workshop on Parallel, Distributed and Federated Learning (PDFL 2021)Workshop on Graph Embedding and Mining  (GEM 2021)Workshop on Machine Learning for Irregular Time-series (ML4ITS 2021)Workshop on IoT, Edge, and Mobile for Embedded Machine Learning (ITEM 2021)Workshop on eXplainable Knowledge Discovery in Data Mining (XKDD 2021)Workshop on Bias and Fairness in AI (BIAS 2021)Workshop on Workshop on Active Inference (IWAI 2021)Workshop on Machine Learning for Cybersecurity (MLCS 2021)Workshop on Machine Learning in Software Engineering (MLiSE 2021)Workshop on MIning Data for financial applications (MIDAS 2021)Sixth Workshop on Data Science for Social Good (SoGood 2021)Workshop on Machine Learning for Pharma and Healthcare Applications (PharML 2021)Second Workshop on Evaluation and Experimental Design in Data Mining and Machine Learning (EDML 2020)Workshop on Machine Learning for Buildings Energy Management (MLBEM 2021)

This book constitutes the refereed proceedings of the 38th German Conference on Pattern Recognition, GCPR 2016, held in Hannover, Germany, in September 2016.The 36 revised full papers presented were carefully reviewed and selected from 85 submissions. The papers are organized in topical sections on image processing, learning, optimization, segmentation, applications, image analysis, motion and tracking.

This LNCS volume contains the papers presented at the second Workshop on Human Motion Understanding, Modeling, Capture and Animation, which took place on October 20th, 2007, accompanying the 11th IEEE International C- ference on Computer Vision in Rio de Janeiro, Brazil. In total, 38 papers were submitted to this workshop,of which 22 papers were accepted. We were careful to ensure a high standard of quality when selecting the papers. All submissions were double-blind reviewed by at least two experts. Out of the 22 accepted papers, 10 were selected for oral presentation and 12 for posters. We thank the authors of the accepted papers for taking the reviewers’ comments into account in the ?nal published versions of their papers. We thank all of the authors who submitted their work, and we trust that the reviewers’ comments have been of value for their research activities. The accepted papers re?ect the state of the art in the ?eld and cover various topicsrelatedto humanmotiontrackingandanalysis.Thepapersinthisvolume have been classi?ed into three categories based on the topics they cover: human motion capture and pose estimation, body and limb tracking and segmentation, and activity recognition.

This LNCS volume contains the papers presented at the second Workshop on Human Motion Understanding, Modeling, Capture and Animation, which took place on October 20th, 2007, accompanying the 11th IEEE International C- ference on Computer Vision in Rio de Janeiro, Brazil. In total, 38 papers were submitted to this workshop,of which 22 papers were accepted. We were careful to ensure a high standard of quality when selecting the papers. All submissions were double-blind reviewed by at least two experts. Out of the 22 accepted papers, 10 were selected for oral presentation and 12 for posters. We thank the authors of the accepted papers for taking the reviewers’ comments into account in the ?nal published versions of their papers. We thank all of the authors who submitted their work, and we trust that the reviewers’ comments have been of value for their research activities. The accepted papers re?ect the state of the art in the ?eld and cover various topicsrelatedto humanmotiontrackingandanalysis.Thepapersinthisvolume have been classi?ed into three categories based on the topics they cover: human motion capture and pose estimation, body and limb tracking and segmentation, and activity recognition.

Motion analysis is central to both human and machine vision. It involves the interpretation of image data over time and is crucial for a range of motion tasks suchasobstacledetection,depthestimation,videoanalysis,sceneinterpretation, videocompressionandotherapplications. Motionanalysisis unsolvedbecauseit requires modeling of the complicated relationships between the observed image data and the motion of objects and motion patterns (e. g. , falling rain) in the visual scene. The Dagstuhl Seminar 08291 on Statistical and Geometrical Approaches to Visual Motion Analysis was held during July 13-18, 2008 at the International Conference and Research Center (IBFI), Schloss Dagstuhl, near Wadern in G- many. The workshop focused on critical aspects of motion analysis, including motion segmentation, the modeling of motion patterns and the di?erent te- niques used. These techniques include variationalapproaches,level set methods, probabilistic models, graph cut approaches, factorization techniques, and neural networks. All these techniques can be subsumed within statistical and geomet- cal frameworks. We further involved experts in the study of human and primate vision.Primatevisualsystemsareextremely sophisticatedat processingmotion, thus there is much to be learnt from studying them. In particular, we discussed how to relate the computational models of primate visual systems to those - veloped for machine vision. In total, 15 papers were accepted for these proceedings after the workshop. We werecarefulto ensurea high standardof qualityfor the accepted papers. All submissions were double-blind reviewed by at least two experts.

This book constitutes the thoroughly refereed post-proceedings of the 15th International Workshop on Theoretic Foundations of Computer Vision, held as a Dagstuhl Seminar in Dagstuhl Castle, Germany, in June/July 2011. The 19 revised full papers presented were carefully reviewed and selected after a blind peer-review process. The topic of this Workshop was Outdoor and Large-Scale Real-World Scene Analysis, which covers all aspects, applications and open problems regarding the performance or design of computer vision algorithms capable of working in outdoor setups and/or large-scale environments. Developing these methods is important for driver assistance, city modeling and reconstruction, virtual tourism, telepresence, and motion capture.

This book constitutes the thoroughly refereed post-proceedings of the 15th International Workshop on Theoretic Foundations of Computer Vision, held as a Dagstuhl Seminar in Dagstuhl Castle, Germany, in June/July 2011. The 19 revised full papers presented were carefully reviewed and selected after a blind peer-review process. The topic of this Workshop was Outdoor and Large-Scale Real-World Scene Analysis, which covers all aspects, applications and open problems regarding the performance or design of computer vision algorithms capable of working in outdoor setups and/or large-scale environments. Developing these methods is important for driver assistance, city modeling and reconstruction, virtual tourism, telepresence, and motion capture.