快速行人越界检测算法研究
Fast Pedestrian Crossing Boundary Detection Method

作者: 高志辉 , 盘先跃 :国防科学技术大学,湖南 长沙;

关键词: 混合高斯模型霍夫直线检测颜色识别重心检测Gaussian Mixture Model Hough Line Detection Color Recognition Centroid Detection

摘要:
本文提出了一种综合运用混合高斯模型前景检测方法、Canny边缘检测、霍夫直线检测、颜色识别与重心检测方法,能较好的解决视频监控系统中行人越界检测的工程类问题。实验结果表明,此综合运用检测方法简单有效、易于实现,且检测准确率高、运行速度快。

Abstract: This paper presents a comprehensive method which combines Gaussian mixture model based on the foreground detection method with Hough line detection, color recognition and centroid detection methods to detect whether the pedestrian crosses the specific boundary in the video surveillance system. Experiments show that the proposed integrated method is simple yet efficient and easy to implement, and has characteristics of high accuracy, fast running speed.

文章引用: 高志辉 , 盘先跃 (2016) 快速行人越界检测算法研究。 软件工程与应用, 5, 146-153. doi: 10.12677/SEA.2016.52016

参考文献

[1] Wang, L. and He, D.C. (1990) Texture Classification Using Texture Spectrum. Pattern Recognition, 23, 905-910.
http://dx.doi.org/10.1016/0031-3203(90)90135-8

[2] Lowe, D.G. (1999) Object Recognition from Local Scale-Invariant Features. Proceedings of the International Conference on Computer Vision, 1150-1157.
http://dx.doi.org/10.1109/iccv.1999.790410

[3] Baya, H., Essa, A., Tuytelaarsb, T. and Van Goola, L. (2008) Speeded-Up Robust Features (SURF). Computer Vision and Image Understanding, 110, 346-359.

[4] Ghafouri, S. and Seyedarabi, H. (2013) Hybrid Method for Hand Gesture Recognition Based on Combination of Haar-Like and Hog Features. The 21st Iranian Conference on Electrical Engineering (ICEE), 14-16 May 2013, 1-4.
http://dx.doi.org/10.1109/iraniancee.2013.6599529

[5] Dalal, N. and Triggs, B. (2005) Histograms of Oriented Gradients for Human Detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1, 886-893.

[6] Canny, J. (1986) A Computational Approach to Edge Detection. IEEE Transactions Ransactions on Pattern Analysis and Maintellgence, pami-8.

[7] (1962) P.V.C. Method and Means for Recognizing Complex Patterns. US Patent 3069654.

[8] Stauffer, C. and Grimson, W.E.L. (2007) Adaptive Background Mixture Models for Real-Time Tracking. The Artificial Intellgence Laboratory, Massachusetts Institute of Technology, Cambridge.

[9] El Harrouss, O., Moujahid, D. and Tairi, H. (2015) Motion Detection Based on the Combining of the Background Subtraction and Spatial Color Information. Intelligent Systems and Computer Vision (ISCV), 25-26 March 2015, 1-4.
http://dx.doi.org/10.1109/isacv.2015.7105548

[10] Bloisi, D. and Iocchi, L. (2012) Independent Multimodal Back-ground Subtraction. Computational Modelling of Objects Represented in Images Fundamentals Methods & Applications III, 413, 39-44.

[11] Duan, D.G., Xie, M., Mo, Q., Han, Z.M. and Wan, Y.L. (2010) An Improved Hough Transform for Line Detection. International Conference on Computer Application and System Modeling (ICCASM), 2, V2-354-V2-357.

[12] 许静, 张冬宁, 张学军. 一种判定运动目标越界的算法[J]. 无线电工程, 2009(11): 32-34.

[13] Hariyono, J. and Jo, K.-H. (2015) Detection of Pedestrian Crossing Road. IEEE International Conference on Image Processing (ICIP), 27-30 September 2015, 4585-4588.

[14] Bonnin, S., Weisswange, T.H., Kummert, F. and Schmuedderich, J. (2014) Pedestrian Crossing Prediction Using Multiple Context-Based Models. IEEE 17th International Conference on Intelligent Transportation Systems (ITSC), 8-11 October 2014, 378-385.

[15] Fascioli, A., Fedriga, R.I. and Ghidoni, S. (2007) Vision-Based Monitoring of Pedestrian Crossings. 14th International Conference on Image Analysis and Processing, 10-14 September 2007, 566-574.
http://dx.doi.org/10.1109/iciap.2007.4362838

分享
Top