Title :
Vehicle detection fusing 2D visual features
Author :
Hoffman, Caio ; Dang, Thao ; Stiller, Christoph
Author_Institution :
Inst. fur Mess- und Regelungstech., Karlsruhe Univ., Germany
Abstract :
This paper presents a method for detection and tracking of vehicles by finding various characteristic features in the images of a monochrome camera. The detection process uses shadow and symmetry features to generate vehicle hypotheses. These are fused and tracked over time using an Interacting Multiple Model method (IMM). Results for natural traffic scenes demonstrate high reliability of the proposed method.
Keywords :
Kalman filters; cameras; feature extraction; filtering theory; object detection; road vehicles; 2D visual feature fusing; interacting multiple model method; monochrome camera; natural traffic scenes; reliability; shadow features; symmetry features; vehicle detection; vehicle hypotheses; vehicle tracking; Cameras; Computer vision; Feature extraction; Filters; Image sequences; Layout; Modems; Sensor phenomena and characterization; Vehicle detection; Vehicles;
Conference_Titel :
Intelligent Vehicles Symposium, 2004 IEEE
Print_ISBN :
0-7803-8310-9
DOI :
10.1109/IVS.2004.1336395
