Search Results

The mean shift tracking algorithm has become a standard in the field of visual object tracking, caused by its real time capability and robustness to object changes in pose, size, or illumination. The standard mean shift tracking approach is an iterative procedure that is based on kernel weighted color histograms for object modelling and the Bhattacharyyan coefficient as a similarity measure between target and candidate histogram model. The benefits of the approach could not been transferred to monochrome vision systems yet, because the loss of information from color to grey-scale histogram object models is too high and the system performance drops seriously. We propose a new framework that solves this problem by using histograms of HoG-features as object model and the SOAMST approach by Ning et al. for track estimation. Mean shift tracking requires a histogram for object modelling.

In this paper we present a fast symmetry search and filtering algorithm for monocular vision based pedestrian candidate detection application. First the ROI of symmetry search is focused on the pedestrian leg region, where the background is relatively simple ground plane. Afterward, the search region is divided into 2 × 4 sub blocks and symmetry density and distribution of each sub block is calculated. Finally, by comparing the symmetry density and distribution of the sub blocks, the correct symmetry axis of the pedestrian candidate is search and also some no-pedestrian candidates are filtered out. The results shown in this method are fast, cost effective and well suited for real-time vision applications.

Automotive radar application is a focus in active traffic safety research activities. And accurate lateral position estimation from the leading target vehicle through radar is of great interest. This paper presents a method based on the regression tree, which estimates the rear centroid of leading target vehicle with a long range FLR (Forward Looking Radar) of limited resolution with multiple radar detections distributed on the target vehicle. Hours of radar log data together with reference value of leading vehicle's lateral offset are utilized both as training data and test data as well. A ten-fold cross validation is applied to evaluate the performance of the generated regression trees together with fused decision forest for each percentage of the training data.