一种多尺度远红外夜间交通行人识别方案

J4 ›› 2016, Vol. 33 ›› Issue (4): 411-419.

一种多尺度远红外夜间交通行人识别方案

李景富,杨志强

黄淮学院，河南驻马店 463000

收稿日期:2015-04-22 修回日期:2015-08-30 出版日期:2016-07-28 发布日期:2016-07-28
通讯作者: 李景富（1981-），河南确山人，硕士，实验师，主要研究方向为智能交通，信息安全，协同过滤。 E-mail:57150186@qq.com

A Multi-Scale Far Infrared Night Traffic Pedestrian Recognition scheme

Received:2015-04-22 Revised:2015-08-30 Published:2016-07-28 Online:2016-07-28

摘要/Abstract

摘要： 为降低夜间行车导致交通事故的概率，在能见度不理想的行车环境中为车辆提供主动安全系统，依据汽车辅助驾驶系统的基本要求，基于远红外传感技术，设计出夜间行人辅助模型。该模型通过远红外传感器来捕捉原始的数据源，利用灰度统计技术获取ROIs，构造出多尺度概率模板，在此基础上对数据源进行匹配检测，通过多帧校验综合处理技术将模型的漏检率和检测率进一步改善。实验表明，该模型的概率模板在匹配精度上相对于业内常用方法有了较大程度的改善，此外该模型还能够在郊区和市区两种交通路况下使用，实用性较好。

Abstract: In order to reduce the probability of traffic accident caused by night driving, and to provide initiative safety system for the vehicle in poor visibility environment, according to the basic requirements of the auxiliary driving system, based on infrared sensor technology, design a nighttime pedestrian auxiliary model. The model captures the original data source through infrared sensors, and obtains its ROIs through gray statistical technique, matches and detects the data source based on the building multi-scale probability template, and improves the detection rate and missing rate effectively by multi-frame checksum integrated processing technology. Experiments show that compared to the common method, the probability template’s matching accuracy improves a lot, In addition, this model can also be used under suburbs and the cities, so it has a good practicability.

Key words: Multi-frame check

李景富杨志强. 一种多尺度远红外夜间交通行人识别方案[J]. J4, 2016, 33(4): 411-419.

参考文献

[1]公安部交通管理局 , 2009 年全国道路交通事故情况 [EB/OL].http://www.mps.gov.cn/n16/n1252/n1837/n2557/2276407.html, 2010
[2]张春凤,宋加涛,王万良行人检测技术研究综述[J],电视技术,2014,38(3):157-162
[3]Borhade S, Shah M, Jadhav P, et al. Advanced Driver Assistance System [A].Proceedings of International Conference on Sensing Technology (ICST) [C]. Kolkata, India: IEEE, 2012: 718-722
[4]Olmeda D, de la Escalera A, Armingol J M. Contrast invariant features for human detection in far infrared images [A]. Proceedings of IEEE Intelligent Vehicles Symposium (IV) [C]. Alcala de Henares, Spain: IEEE, 2012: 117-122
[5]田广,徐奕,杨小康.步态识别在智能视频监控系统中的应用前景[J].电视技术,2011,35(15):24-29
[6]Cutler R, Davis L S. Robust real-time periodic motion detection, analysis and applications [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 781-796
[7]Gavrila D M, Munder S. Multi-cue pedestrian detection and tracking from a moving
vehicle [J]. International Journal of Computer Vision, 2007, 73(1): 41-59
[8]Gavrila D M. A bayesian, exemplar-based approach to hierarchical shape matching [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(8):1408-1421
[9]刘辉,张云生,张印辉等.基于灰度差分统计的火焰图像纹理特征提取[J].控制工程,2013,20(2):213-218
[10]陈侃,李彬,田联房.基于局部阈值和聚类中心迭代的肺结节检测算法[J].计算机学报,2012,39(2):302-304
[11]Ge J F, Luo Y P, Gyomei T. Real-time pedestrian detection and tracking at nighttime for driver-assistance systems [J]. IEEE Transactions on Intelligent Transportation Systems, 2009, 10(2): 283-298
[12]杨琨,曾立波,王殿成.数学形态学腐蚀膨胀运算的快速算法[J],计算机工程与应用,2011,34:54-56
[13]Gavrila D M. A bayesian, exemplar-based approach to hierarchical shape matching [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(8):1408-1421
[14]Gavrila D M, Munder S. Multi-cue pedestrian detection and tracking from a moving vehicle [J]. International Journal of Computer Vision, 2007, 73(1): 41-59
[15]Giebel J，Gavrila D M，Schn?rr C. A Bayesian framework for multi-cue 3D object tracking [J]. Lecture Notes in Computer Science, 2004, 3024: 241-252
[16]赵运基,裴海龙.基于增量学习的关节式目标跟踪算法[J].华南理工大学学报(自然科学版), 2012, 40(3): 88-93
[17]Bertozzi M, Broggi A, Gomez C H, et al. Pedestrian detection in far infrared images based on the use of probabilistic templates [A]. Proceeding of IEEE Intelligent Vehicles Symposium (IV) [C]. Istanbul, Turkey: IEEE, 2007: 327-332