1 Department of Architecture, Design and Media Technology, The Faculty of Engineering and Science, Aalborg University, VBN2 Visual Analysis of People Laboratory, The Faculty of Engineering and Science, Aalborg University, VBN3 The Faculty of Engineering and Science, Aalborg University, VBN4 Vislab.it5 University of California at San Diego6 Aalborg U Robotics, The Faculty of Humanities, Aalborg University, VBN7 University of California at San Diego
Real-Time, Robust Algorithms and Evaluation
Detecting pedestrians is still a challenging task for automotive vision systems due to the extreme variability of targets, lighting conditions, occlusion, and high-speed vehicle motion. Much research has been focused on this problem in the last ten years and detectors based on classifiers have gained a special place among the different approaches presented. This paper presents a state-of-the-art pedestrian detection system based on a two-stage classifier. Candidates are extracted with a Haar cascade classifier trained with the Daimler Detection Benchmark data set and then validated through a part-based histogram-of-oriented-gradient (HOG) classifier with the aim of lowering the number of false positives. The surviving candidates are then filtered with feature-based tracking to enhance the recognition robustness and improve the results' stability. The system has been implemented on a prototype vehicle and offers high performance in terms of several metrics, such as detection rate, false positives per hour, and frame rate. The novelty of this system relies on the combination of a HOG part-based approach, tracking based on a specific optimized feature, and porting on a real prototype.
I E E E Transactions on Intelligent Transportation Systems, 2013, Vol 14, Issue 3, p. 1346-1359