Abstract

The increasing importance of outdoor applications such as driver assistance systems or video surveillance tasks has recently triggered the development of optical flow methods that aim at performing robustly under uncontrolled illumination. Most of these methods are based on patch-based features such as the normalized cross correlation, the census transform or the rank transform. They achieve their robustness by locally discarding both absolute brightness and contrast. In this paper, we follow an alternative strategy: Instead of discarding potentially important image information, we propose a novel variational model that jointly estimates both illumination changes and optical flow. The key idea is to parametrize the illumination changes in terms of basis functions that are learned from training data. While such basis functions allow for a meaningful representation of illumination effects, they also help to distinguish real illumination changes from motion-induced brightness variations if supplemented by additional smoothness constraints. Experiments on the KITTI benchmark show the clear benefits of our approach. They do not only demonstrate that it is possible to obtain meaningful basis functions, they also show state-of-the-art results for robust optical flow estimation. Document type: Part of book or chapter of book

Abstract

This paper discusses the detection of moving objects (being a crucial part of driver assistance systems) using monocular or stereoscopic computer vision. In both cases, object detection is based on motion analysis of individually tracked image points (optical flow), providing a motion metric which corresponds to the likelihood that the tracked point is moving. Based on this metric, points are segmented into objects by employing a globally optimal graph-cut algorithm. Both approaches are comparatively evaluated using real-world vehicle image sequences. Document type: Part of book or chapter of book

Abstract

High precision ground truth data is a very important factor for the development and evaluation of computer vision algorithms and especially for advanced driver assistance systems. Unfortunately, some types of data, like accurate optical flow and depth as well as pixel-wise semantic annotations are very difficult to obtain. Document type: Part of book or chapter of book

Abstract

International audience; This paper deals with a new method that exploits optical flow field properties to simplify and strengthen the original c-velocity approach (Bouchafa and Zavidovique, 2012). C-velocity is a cumulative method based on a Hough-like transform adapted to velocities that allows 3D structure identification. In case of moving cameras, the 3D scene is assumed to be composed by a set of 3D planes that could be categorized in 3 main models: horizontal, lateral and vertical planes. We prove in this paper that, by using directly pixel coordinates to create what we will call the uv-velocity space, it is possible to detect 3D planes efficiently. We conduct our experiments on the KITTI optical flow dataset (Menze and Geiger, 2015) to prove our new concept besides the effectiveness of uv-velocity in detecting planes. In addition, we show how our approach could be applied to detect free navigation area (road), urban structures like buildings and obstacles from a moving camera in the context of Advanced Driver Assistance Systems.