Error Analysis in a Stereo Vision-Based Pedestrian Detection Sensor for Collision Avoidance Applications.docVIP

Sensors 2010, 10, 3741-3758; doi:10.3390/s100403741 OPEN ACCESS sensors ISSN 1424-8220 /journal/sensors Article Error Analysis in a Stereo Vision-Based Pedestrian Detection Sensor for Collision Avoidance Applications David F. Llorca *, Miguel A. Sotelo, Ignacio Parra, Manuel Oca?a and Luis M. Bergasa Electronics Department, University of Alcalá, Polytechnic School, University Campus, Alcalá de Henares, Madrid 28871, Spain; E-Mails: sotelo@depeca.uah.es (M.A.S.); parra@depeca.uah.es (I.P.); mocana@depeca.uah.es (M.O.); bergasa@depeca.uah.es (L.M.B.) * Author to whom correspondence should be addressed; E-Mail: llorca@depeca.uah.es; Tel.: +34-918856558 Ext. 4; Fax: +34-918856591. Received: 25 January 2010; in revised form: 18 March 2010 / Accepted: 23 March 2010 / Published: 13 April 2010 Abstract: This paper presents an analytical study of the depth estimation error of a stereo vision-based pedestrian detection sensor for automotive applications such as pedestrian collision avoidance and/or mitigation. The sensor comprises two synchronized and calibrated low-cost cameras. Pedestrians are detected by combining a 3D clustering method with Support Vector Machine-based (SVM) classification. The influence of the sensor parameters in the stereo quantization errors is analyzed in detail providing a point of reference for choosing the sensor setup according to the application requirements. The sensor is then validated in real experiments. Collision avoidance maneuvers by steering are carried out by manual driving. A real time kinematic differential global positioning system (RTK-DGPS) is used to provide ground truth data corresponding to both the pedestrian and the host vehicle locations. The performed field test provided encouraging results and proved the validity of the proposed sensor for being used in the automotive sector towards applications such as autonomous pedestrian colli