Vehicle Detection Method under Night Circumstance

Abstract:

In intelligent vehicle detection, vehicle detection at night especially detection in the condition of urban street always remains a problem. This paper proposes an effective vehicle detection algorithm. Firstly it extracts effective vehicle edge by the method of embossment which eliminates light interference. Then we detect the vehicle moving area by frame difference method and calculate the threshold by OTSU algorithm. Finally the noise points are removed by erosion and expansion. This method can better extract the moving objects.

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 3870-3873
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.3870
• Online since: August 2013
• Authors: Lin Guo, Xiang Hui Shen
• Keywords: Embossment, Erosion, Expansion, Frame Difference Method, Vehicle Detection at Night

References

[1] Liu Xun, in: Moving vehicle detection and recognition technology research in intelligent traffic, PhD thesis, Sichuan University (2005).

[2] Schreiner K, in: Night Vision: infrared takes to the road, of IEEE Computer Graphics and Applications, 19(5): 6～l0 (1999).

DOI: 10.1109/38.788791

[3] Fay D A, Waxman A M, Aguilar M, et a1, in: Fusion of multi-sensor imagery for night vision: color visualization, target learning and search, of Proceedings of the Third International Conference Oil Information Fusion, Paris (2000).

DOI: 10.1109/ific.2000.862702

[4] Taktak R, Dufaut M, Husson R, in: Vehicle detection at night using image processing and pattern recognition, of Proceedings of IEEE International Conference of Image Processing, Austin, Texas, USA (1994).

DOI: 10.1109/icip.1994.413579

[5] Tan Rongwei, Lei Yunqi, in: Nighttime moving vehicle detection, submitted to Journal of Computer Engineering and Applications (2005).