Vehicle Detection with HOG and Linear SVM

Year 2021, Volume: 1 Issue: 1, 6 - 9, 30.06.2021

Nikola Tomikj Andrea Kulakov

Abstract

In this paper, we present a vehicle detection system by employing Histogram of Oriented Gradients (HOG) for feature extraction and linear SVM for classification. We study the influence of the colour space on the performance of the detector, concluding that decorrelated and perceptual colour spaces give the best results. An in-depth analysis is carried out on the effects of the HOG and SVM parameters, the threshold for the distance between features and the SVM classifying plane, and the non-maximum suppression (NMS) threshold on the performance of the detector, and we propose values that illustrate good performance for vehicle detection on images. We also discuss the issues of the approach and the reasons for its mediocre performance on videos. Finally, we address these issues by presenting ideas that can be considered for improving the system.

Keywords

computer vision, machine learning, HOG, SVM, color space, vehicle detection, autonomous vehicles

References

• N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection”, in international Conference on computer vision & Pattern Recognition (CVPR’05), IEEE Computer Society, vol. 1, 2005, pp. 886–893.
• I. M. Creusen, R. G. Wijnhoven, E. Herbschleb, and P. de With, “Color exploitation in hog-based traffic sign detection”, in 2010 IEEE International Conference on Image Processing, IEEE, 2010, pp. 2669–2672.
• L. Mao, M. Xie, Y. Huang, and Y. Zhang, “Preceding vehicle detection using histograms of oriented gradients”, in 2010 International Conference on Communications, Circuits and Systems (ICCCAS), IEEE, 2010, pp. 354–358.
• J. Arr ́ospide, L. Salgado, and M. Camplani, “Image-based on-road vehicle detection using cost-effective histograms of oriented gradients”, Journal of Visual Communication and Image Representation, vol. 24, no. 7, pp. 1182–1190, 2013.
• R. Girshick, “Fast r-cnn”, in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1440–1448.
• J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection”, in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779–788.
• G. Rossum, “Python reference manual”, Amsterdam, The Netherlands, The Netherlands, Tech. Rep., 1995.
• G. Bradski, “The OpenCV Library”, Dr. Dobb’s Journal of Software Tools, 2000.
• I. P. G. at UPM, Gti vehicle image database, https ://www.gti.ssr.upm.es/data/, 2011.
• A. Geiger, P. Lenz, C. Stiller, and R. Urtasun, “Vision meets robotics: The kitti dataset”, International Journal of Robotics Research (IJRR), 2013.