Research on the Bus Passenger Motion Vector Algorithm Based on Video Image

Abstract:

Video-based bus passenger collection is considered to have a greater potential for counting passengers, but the difficulty lies in how to solve the problem of accurately tracking and determining the direction of the moving target under the complex state of motion. The traditional target detection algorithm, like frame subtraction and edge detection, is very difficult to deal with the situation of immediate multi-objective. Based on image preprocessing, an algorithm about intelligent video multi-target tracking and traffic statistics is designed aiming at the above-mentioned situation. The core contents in this paper includes: the grid-density clustering and line segment clustering, extraction and segmentation target connected domain that is handled to be a circular, tracking the motion vector of target feature point, finally ,achieving accurate statistics on the number of people getting on and off. Experiments show that this algorithm can effectively track more people simultaneously and the bus traffic statistical accuracy achieves the goal.

• Periodical: Applied Mechanics and Materials (Volume 623)
• Pages: 149-155
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.623.149
• Online since: August 2014
• Authors: Huai Kun Xiang*, Lan Qiu Cheng
• Keywords: Feature Point Motion Vector Tracking, Grid-Density Clustering, Segment Clustering, Video Detection

References

[1] Zhang Hui, Dong Yuning. Summary of video-based vehicle detection algorithm. Journal of NanJing University of Posts and Telecommunications (Natural Science). 2007, 27(3) 88-94.

[2] Yang Lan. Recognition of Human Body and the Application in Pedestrians Counting System. DaLian Maritime University, Signal and Information Processing, (2006).

[3] Huang Chaolu. The Study On Counting Passengers Based On Machine Vision. Huazhong University of Science and Technology, Pattern Recognition and Intelligent Systems, (2011).

[4] Zhang Qi. Analysis System of the Passenger F1ow Based on Genetic Algorithm. Taiyuan University of Technology, Computer Science and Technology, (2011).

[5] Zhang Defeng. MATLAB digital image processing. China Machine Press, (2012).

[6] Massimo Piccardi. Background subtraction techniques: a review, IEEE International Conference on Systems, Man and Cybernetics, 2004, pp.3099-3104.

DOI: 10.1109/icsmc.2004.1400815

[7] M. Heikkila and M. Pietikainen. A texture-based method for modeling the background and detecting moving objects. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2006, 28(4), pp.657-662.

DOI: 10.1109/tpami.2006.68

[8] G. Antonini and J. P. Thiran. Counting pedestrians in video sequences using trajectory clustering. IEEE Transactions on Circuits and Systems for Video Technology, 2006, 16(8), pp.1008-1020.

DOI: 10.1109/tcsvt.2006.879118

[9] T. Yang et al. Clustering method for counting passengers getting in a bus with single camera. Optical Engineering, 2010, 49(3), pp.197-203.

DOI: 10.1117/1.3374439

[10] M. D. Breitenstein et al. Markovian tracking-by-detection from a single, uncalibrated camera. Proceedings of IEEE Int. Workshop Performance Evaluation of Tracking and Surveillance, PETS, June, (2009).

[11] Tian JingLei, Bi Sheng. A research on the System of Passenger Counting Technology Based on Video. Proceedings of The 12th National Conference on Image and Graphics, 2005, pp.278-281.

[12] Wang Weidong. Research and Application of Video Analysis on Bus Passenger Flow Counting. Hebei University of Technology, Computer Applied Technology, (2010).

[13] Li Zhihua. Research on Object Tracking and Classification for Intelligent Video Surveillance. ZheJiang University, Electronic Information Technology and Instruments, (2008).

[14] Zhou Jing. Classification of Moving Target Detection in Video Sequences. Northwestern University, Communication and Information System, (2011).