Length-based vehicle classification in multi-lane traffic flow

Abstract

For the realtime classification of moving vehicles in the multi-lane traffic video sequences, a length-based method is proposed. To extract the moving regions of interest, the difference image between the updated background and current frame is obtained by using background subtraction, and then an edge-based shadow removal algorithm is implemented. Moreover, a thresholding segmentation method for the region detection of moving vehicle based on location search is developed. At the estimation stage, a registration line is set up in the detection area, then the vehicle length is estimated with the horizontal projection technique as soon as the vehicle leaves the registration line. Lastly, the vehicle is classified according to its length and the classification threshold. The proposed method is different from traditional methods that require complex camera calibrations. It calculates the pixel-based vehicle length by using uncalibrated traffic video sequences at lower computational cost. Furthermore, only one registration line is set up, which has high flexibility. Experimental results of three traffic video sequences show that the classification accuracies for the large and small vehicles are 97.1% and 96.7% respectively, which demonstrates the effectiveness of the proposed method.

Keywords

image processing / background subtraction / vehicle classification / virtual line / horizontal projection

References

[1] Buch N, Orwell J, Velastin S A. Detection and classification of vehicles for urban traffic scenes[C]. In: Proceedings of the 5th International Conference on Visual Information Engineering. Xi’an, China, 2008. 182–187.

[2] Ambardekar A, Nicolescu M, Bebis G. Efficient vehicle tracking and classification for an automated traffic surveillance system[C]. In: Proceedings of the 10th International Conference on Signal and Image Processing. Hawaii, USA, 2008. 220–225.

[3] Lai A H S, Fung G S K, Yung N H C. Vehicle type classification from visual-based dimension estimation[C]. In: IEEE Conference on Intelligent Transportation Systems. Oakland, USA, 2001. 201–206.

[4] Huang Lili. Roadside camera calibration and its application in length-based vehicle classification[C]. In: Proceedings of the 2nd International Asia Conference on Informatics in Control, Automation and Robotics. Wuhan, China, 2010. 329–332.

[5] Yu Yang, Yu Ming, Zhai Yandong et al. An algorithm of traffic parameters extraction for multi-lane roads[C]. In: Proceedings of the International Conference on Computer Science and Service System. Nanjing, China, 2011. 2972–2975.

[6] Zhang G., Avery Ryan P., Wang Yinhai. Video-based vehicle detection and classification system for real-time traffic data collection using uncalibrated video cameras[J]. Transportation Research Record, 1993, 2007, 138-147.

[7] Yang Z., Lin T., Li X., et al. Digital signal processing based real time vehicular detection system[J]. Transactions of Tianjin University, 2005, 11(2): 119-124.

[8] Avery R P, Wang Yinhai, Scott Rutherford G. Length-based vehicle classification using images from uncalibrated video cameras [C]. In: IEEE Conference on Intelligent Transportation Systems. Washington DC, USA, 2004. 737–742.

[9] Li Q., Li F., Lu Jun. A method to classify the vehicles in crossing based on a multi-class support vector machine and the acquirement of flowing parameter[J]. Journal of Image and Graphics, 2008, 13(4): 801-807.

[10] Wang Y., Nihan Nancy L. Can single-loop detectors do the work of dual-loop detectors?[J]. Journal of Transportation Engineering, 2003, 129(2): 169-176.

[11] Gupte S., Masoud O., Martin R. F. K., et al. Detection and classification of vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2002, 3(1): 37-47.

[12] Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man and Cybernetics, 1979, 9(1): 62-66

[13] Avery Ryan P., Zhang G., Wang Y., et al. An investigation into shadow removal from traffic images[J]. Transportation Research Record, 2000, 2007, 70-77.

[14] Canny J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.

[15] Zhou Z., Geng Xin. Projection functions for eye detection[J]. Pattern Recognition, 2004, 37(5): 1049-1056.