A Pedestrian Detection and Tracking System Based on Video Processing Technology

Author

Yuanyuan Chen ; Shuqin Guo ; Biaobiao Zhang ; Du, K.-L.

Author_Institution

Enjoyor Labs., Enjoyor Inc., Hangzhou, China

fYear

2013

fDate

3-4 Dec. 2013

Firstpage

69

Lastpage

73

Abstract

Pedestrian detection and tracking are widely applied to intelligent video surveillance, intelligent transportation, automotive autonomous driving or driving-assistance systems. We select OpenCV as the development tool for implementation of pedestrian detection, tracking, counting and risk warning in a video segment. We introduce a low-dimensional soft-output SVM pedestrian classifier to implement precise pedestrian detection. Experiments indicate that the system has high recognition accuracy, and can operate in real time.

Keywords

image classification; image sequences; object tracking; pedestrians; support vector machines; video signal processing; OpenCV development tool; automotive autonomous driving; driving-assistance systems; intelligent transportation; intelligent video surveillance; low-dimensional soft-output SVM pedestrian classifier; pedestrian counting; pedestrian detection and tracking system; pedestrian risk warning; video processing technology; video segment; Accuracy; Feature extraction; Gaussian mixture model; Histograms; Support vector machines; Trajectory; pedestr-ian counting; pedestrian detection; pedestrian tracking; risk warning;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Systems (GCIS), 2013 Fourth Global Congress on

Conference_Location

Hong Kong

Print_ISBN

978-1-4799-2885-9

Type

conf

DOI

10.1109/GCIS.2013.17

Filename

6805914