Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized as being non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificially generated datasets, which often do not reflect reality. By basing decision-making algorithms on Deep Neural Networks, prejudice and unfairness may be promoted unknowingly due to a lack of transparency. Hence, several so-called explanators, or explainers, have been developed. Explainers try to give insight into the inner structure of machine learning black boxes by analyzing the connection between the input and output. In this survey, we present the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about the taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.
1 December 2013 in ISPRS Journal of Photogrammetry and Remote Sensing
Data recorded by mobile LiDAR systems (MLS) can be used for the generation and refinement of city models or for the automatic detection of long-term changes in the public road space. Since for this task only static structures are of interest, all mobile objects need to be removed. This work presents a straightforward but powerful approach to remove the subclass of moving objects. A probabilistic volumetric representation is utilized to separate MLS measurements recorded by a Velodyne HDL-64E into mobile objects and static background. The method was subjected to a quantitative and a qualitative examination using multiple datasets recorded by a mobile mapping platform. The results show that depending on the chosen octree resolution 87-95% of the measurements are labeled correctly.
6 June 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical models of the human body surface are generally learned from thousands of high-quality 3D scans in predefined poses to cover the wide variety of human body shapes and articulations. Acquisition of such data requires expensive equipment, calibration procedures, and is limited to cooperative subjects who can understand and follow instructions, such as adults. We present a method for learning a statistical 3D Skinned Multi-Infant Linear body model (SMIL) from incomplete, low-quality RGB-D sequences of freely moving infants. Quantitative experiments show that SMIL faithfully represents the RGB-D data and properly factorizes the shape and pose of the infants. To demonstrate the applicability of SMIL, we fit the model to RGB-D sequences of freely moving infants and show, with a case study, that our method captures enough motion detail for General Movements Assessment (GMA), a method used in clinical practice for early detection of neurodevelopmental disorders in infants. SMIL provides a new tool for analyzing infant shape and movement and is a step towards an automated system for GMA.