Obstacle avoidance is one of the most important challenges for mobile robots as well as future vision based driver assistance systems. This task requires a precise extraction of depth and the robust and fast detection of moving objects. In order to reach these goals, this paper considers vision as a process in space and time. It presents a powerful fusion of depth and motion information for ima...

Real-time vision-based vehicle navigation tasks are typically computationally intensive and significantly complex in terms of resources used. Moreover, mobile applications of navigation systems place severe constraints on their size and power consumption. These constraints can be satisfied by using parallel image processing architectures and parallel control algorithms implemented with analog V...

Expert in structure from motion (SFM), multi-view geometry, 3D reconstruction, image based modeling and rendering, image/video mosaicking, feature tracking, image/video processing and analysis, and convex optimization. Expert in architecting, designing, implementing, testing, and deploying computer vision systems to handle large amount of video data. Strong background in computer vision, machin...

The problem of estimating motion and structure from a sequence of images has been a major research theme in machine vision for many years and remains one of the most challenging ones. In this work, we use sliding mode observers to estimate the motion and the structure of a moving body with the aid of a CCD camera. We consider a variety of dynamical systems which arise in machine vision applicat...

We designed and tested a two-dimensional silicon receptor array constructed from pixels that temporally highpass filter the incident image. There are no surround interactions in the array; all pixels operate independently except for their correlation due to the input image. The high-pass output signal is computed by sampling the output of an adaptive, high-gain, logarithmic photoreceptor during...

This paper presents the vision system of the robot soccer team Agilo RoboCuppers 1 { the RoboCup team of the image understanding group (FG BV) at the Technische Universitt at M unchen. We present a fast and robust color classiication method yielding signii-cant regions in the image. The boundaries between adjacent regions are used to localize objects like the ball or other robots on the eld. Fu...

The active vision paradigm plays a significant role in a recently established interdisciplinary research initiative (DFG Forschergruppe) at Heidelberg University. The goal of the Forschergruppe is to develop and apply advanced image sequence processing techniques to study key scientific questions in environmental sciences and biology that cannot be approached with conventional techniques. The F...

Motion smear is an important visual cue for motion perception by the human vision system (HVS). However, in image analysis research, exploiting motion smear has been largely ignored. Rather, motion smear is usually considered as a degradation of images that needs to be removed. In this paper, we establish a computational model that estimates image motion from motion smear information--"motion f...

This paper presents a method for the detection of objects that move independently of the observer in a 3D dynamic scene. Independent motion detection is achieved through processing of stereoscopic image sequences acquired by a binocular, rigidly moving observer. A weak assumption is made about the observer's motion (egomotion), namely that the direction of the translational and rotational compo...