Part-Based Pedestrian Detection and Tracking for Driver Assistance using two stage Classifier

Content Provider	Semantic Scholar
Author	Kumar, Abhinav Nithya, E.
Copyright Year	2014
Abstract	Pedestrian detection is an essential and significant task in any intelligent video surveillance system, as it provides the fundamental information for semantic understanding of the video footages and for improving safety systems for accident prevention. Pedestrian detection and tracking for driver assistance is mainly for the purpose of protecting the pedestrians using the automatic braking. This paper presents a state-of-the-art pedestrian detection system based on a two-stage classifier with Multiple Target Tracking. Candidates are detected and extracted with a Haar-cascade classifier trained with the Daimler Detection Benchmark data set. Then the extracted candidates are 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 Multiple Target Tracking (MTT) system tracking to enhance the recognition robustness and improve the result’s stability. Use of MTT in driver assistant systems makes them very efficient and effective in collision avoidance and early warning. 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.
File Format	PDF HTM / HTML
Alternate Webpage(s)	http://www.ijrsset.org/pdfs/v1-i4/2.pdf
Language	English
Access Restriction	Open
Content Type	Text
Resource Type	Article