The advantages and the problems of fusing radar and camera data for vehicle detection are well known; methods differ mainly for the fusion level: low level fusion, intermediate level fusion and high level fusion have all proved to reach good results. Low level fusion combines several sources of raw data to produce new raw data that is expected to be more informative and synthetic than the inputs; in intermediate level fusion various features such as edges, corners, lines, texture parameters, etc are combined into a feature map that is then used by further processing stages; while in high level fusion each source of input yields a decision and the decisions are fused. This work is developed using high level fusion and focuses on validation of radar targets. This paper describes a vehicle detection system fusing radar and vision data. Radar data are used to locate areas of interest on images. Vehicle search in these areas is based on vertical symmetry. All vehicles found in different image areas are mixed together and a series of filters are applied in order to delete false positives. The algorithm analyzes images on a frame by frame basis, without any temporal correlation. Two different statistics, frame-based and event-based, are computed to evaluate the method efficiency. Results and problems are discussed, and some ideas for possible enhancements are provided.
Radar-vision fusion for vehicle detection
Zusammenführung von Radar detektierten Bildern zur Fahrzeugerkennung
2006
6 Seiten, 8 Bilder, 1 Tabelle, 9 Quellen
Conference paper
English
Radar-Vision Fusion for Vehicle Detection
British Library Conference Proceedings | 2006
|Vehicle and guard rail detection using radar and vision data fusion
Tema Archive | 2007
|Vehicle and Guard Rail Detection Using Radar and Vision Data Fusion
British Library Conference Proceedings | 2007
|