基于车载的运动行人区域估计方法

doi:10.13229/j.cnki.jdxbgxb20170358

吉林大学学报(工学版) ›› 2018, Vol. 48 ›› Issue (3): 694-703.doi: 10.13229/j.cnki.jdxbgxb20170358

基于车载的运动行人区域估计方法

李志慧¹, 胡永利¹, 赵永华², 马佳磊¹, 李海涛¹, 钟涛¹, 杨少辉³

1.吉林大学交通学院,长春 130022;
2.吉林大学计算机公共教学与研究中心,长春 130022;
3.中国城市规划设计研究院城市交通研究分院,北京100037;

收稿日期:2017-04-14 出版日期:2018-05-20 发布日期:2018-05-20
通讯作者: 赵永华(1979-),女,副教授,博士.研究方向:交通视频检测与处理.E-mail:zhaoyonghua@jlu.edu.cn
作者简介:李志慧(1977-),男,副教授,博士.研究方向:交通视频检测与处理.E-mail:lizhih@jlu.edu.cn
基金资助:
国家自然科学基金项目(51278220); 吉林省重点科技攻关项目(20140204028SF); 吉林省科技发展计划重点项目(20130206093SF).

Locating moving pedestrian from running vehicle

LI Zhi-hui¹, HU Yong-li¹, ZHAO Yong-hua², MA Jia-lei¹, LI Hai-tao¹, ZHONG Tao¹, YANG Shao-hui³

1.College of Transportation, Jilin University, Changchun 130022,China;
2.Public Computer Technology and Research Center, Jilin University, Changchun 130022,China;
3.Urban Transportation Institute, China Academy of Urban Planning & Design, Beijing 100037, China;

Received:2017-04-14 Online:2018-05-20 Published:2018-05-20

摘要/Abstract

摘要： 针对传统行人检测系统采用全局模板搜索匹配识别易造成大量的盲目空间搜索,降低了行人检测的实时性,且难于直接服务于车载环境下的无人驾驶、行人安全保障技术等应用的问题,基于运动行人与车载移动背景的运动差异性,提出了基于光流聚类的行人区域快速估计方法。该方法首先利用局部与全局光流相结合的计算方法,获取图像光流场;根据移动背景与前景的运动差异,建立了光流聚类算法和背景估计方法,获取剔除背景的可能前景光流图。然后利用图分割算法,实现光流矢量图分割,获取运动物体候选区域。最后根据人体形态特性,判别运动物体候选区域是否为行人有效区域,从而实现行人区域估计。基于JLU-PDS和Daimler国际行人共享测试库进行试验,结果表明本文算法具有较好的检测效果,能够极大地降低行人识别的空间搜索范围,为车载主动行人保障技术、无人驾驶、智能车辆等研究和应用提供了技术支持。

关键词: 交通运输系统工程, 行人检测, 自动驾驶, 智能车辆, 光流分割

Abstract: Traditional pedestrian detection system uses global template for search and recognition, resulting in large useless search and reducing the realtime pedestrian detection performance. In addition, it is difficult to apply to unmanned vehicle and pedestrian safety technology in the traffic environment. Based on the difference of motion between pedestrian and vehicle moving background, a fat pedestrian area estimation method is proposed using optical flow clustering. This method uses the combination of local and global optical flow to obtain the optical flow field. According to the difference between background and foreground, the optical flow clustering algorithm and background estimation method are established. Then, the image segmentation algorithm is used to realize the segmentation of optical flow vector. Finally, according to the characteristics of the human body, we can judge whether the candidate region of the moving object is an effective area for pedestrians and realize the pedestrian area estimation. Experiments are carried out based on JLU-PDS and Daimler international pedestrian sharing test library, and experimental environments include the crowed, shelter, streets, fields and other auxiliary working conditions. Results show that the algorithm has good detection effect and greatly reduces the sear space of pedestrian recognition. In addition, it provides technical support and basis for research and application of vehicle active pedestrian protection technology and unmanned intelligent vehicles.

Key words: engineering of communication and transportation system, pedestrian detection, autonomous vehicle, smart vehicle, optical flow segmentation

中图分类号:

U495

李志慧, 胡永利, 赵永华, 马佳磊, 李海涛, 钟涛, 杨少辉. 基于车载的运动行人区域估计方法[J]. 吉林大学学报(工学版), 2018, 48(3): 694-703.

LI Zhi-hui, HU Yong-li, ZHAO Yong-hua, MA Jia-lei, LI Hai-tao, ZHONG Tao, YANG Shao-hui. Locating moving pedestrian from running vehicle[J]. 吉林大学学报(工学版), 2018, 48(3): 694-703.

参考文献

[1] Papageorgiou C,Poggio T.A trainable system for object detection[J]. International Journal of Computer Vision,2000,38(1):15-33.
[2] Dollár P, Wojek C,Schiele B,et al.Pedestrian detection:a benchmark[J/OL].[2017-04-09].http:∥www-cs.ccny.cuny.edu/~zhu/GC-Spring2010/Papers/PedestrianBenchmark.pdf.
[3] Enzweiler M, Gavrila D M.Monocular pedestrian detection:survey and experiments[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(12):2179-2195.
[4] Zhang Shan-shan, Klein D A, Bauckhage C,et al.Fast moving pedestrian detection based on motion segmentation and new motion features[J]. Multimedia Tools and Applications,2016,75(11):6263-6282.
[5] Tkarli F,Aghagolzadeh A,Seyedarabi H.Combination of high-level features with low-level features for detection of pedestrian[J]. Signal Image and Video Processing,2016,10(1):93-101.
[6] Geronimo D,Lopez A M, Sappa A D,et al.Survey of pedestrian detection for advanced driver assistance systems[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(7):1239-1258.
[7] Prioletti A, Mϕgelmose A, Grisleri P,et al.Part-based pedestrian detection and feature-based tracking for driver assistance: real-time, robust algorithms, and evaluation[J]. IEEE Transactions on Intelligent Transportation Systems,2013,14(3):1346-1359.
[8] Dalal N.Finding people in images and videos[J/OL]. [2017-04-09].https:∥tel.archives-ouvertes.fr/tel-00390303/document.
[9] Zhu Q,Yeh M C,Cheng K T,et al.Fast human detection using a cascade of histograms of oriented gradients[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York,USA,2006:1491-1498.
[10] Itti L,Koch C,Niebur E.A Model of Saliency—Based Visual Attention for Rapid Scene Analysis[M]. New York:IEEE Computer Society, 1998.
[11] Gualdi G, Prati A, Cucchiara R.Multi-stage sampling with boosting cascades for pedestrian detection in images and videos[C]∥European Conference on Computer Vision,Heraklion,Crete,Greece,2010:196-209.
[12] Kamijo S,Sakauchi M.Simultaneous tracking of pedestrians and vehicles by the spatio—temporal Markov random field model[J]. Ipsj Sig Notes Cvim,2003,4:3732-3737.
[13] Elzein H,Lakshmanan S,Watta P.A motion and shape-based pedestrian detection algorithm[C]∥IEEE Intelligent Vehicles Symposium,Columbus, USA,2003:500-504.
[14] Garcia-Dopico A,Pedraza J L,Nieto M,et al.Locating moving objects in car-driving sequences[J/OL]. [2017-04-11].http:∥paperity.org/p/35073989/locating-moving-objects-in-car-driving-sequences.
[15] Lucas B D,Kanade T.An iterative image registration technique with an application to stereo vision[C]∥Proceedings of the 7th International Joint Conference on Artificial Intelligence, Vancouver BC, Canada,1981:121-130.
[16] Horn B K P, Schunck B G. Determining optical flow[J]. Artificial Intelligence,1981,17(1):185-203.
[17] Felzenszwalb P F,Huttenlocher D P.Efficient graph-based image segmentation[J]. International Journal of Computer Vision,2004,59(2):167-181.

相关文章 15

[1]	陈永恒,刘芳宏,曹宁博. 信控交叉口行人与提前右转机动车冲突影响因素[J]. 吉林大学学报(工学版), 2018, 48(6): 1669-1676.
[2]	常山,宋瑞,何世伟,黎浩东,殷玮川. 共享单车故障车辆回收模型[J]. 吉林大学学报(工学版), 2018, 48(6): 1677-1684.
[3]	曲大义,杨晶茹,邴其春,王五林,周警春. 基于干线车流排队特性的相位差优化模型[J]. 吉林大学学报(工学版), 2018, 48(6): 1685-1693.
[4]	宗芳, 齐厚成, 唐明, 吕建宇, 于萍. 基于GPS数据的日出行模式-出行目的识别[J]. 吉林大学学报(工学版), 2018, 48(5): 1374-1379.
[5]	刘翔宇, 杨庆芳, 隗海林. 基于随机游走算法的交通诱导小区划分方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1380-1386.
[6]	钟伟, 隽志才, 孙宝凤. 不完全网络的城乡公交一体化枢纽层级选址模型[J]. 吉林大学学报(工学版), 2018, 48(5): 1387-1397.
[7]	刘兆惠, 王超, 吕文红, 管欣. 基于非线性动力学分析的车辆运行状态参数数据特征辨识[J]. 吉林大学学报(工学版), 2018, 48(5): 1405-1410.
[8]	宗芳, 路峰瑞, 唐明, 吕建宇, 吴挺. 习惯和路况对小汽车出行路径选择的影响[J]. 吉林大学学报(工学版), 2018, 48(4): 1023-1028.
[9]	栾鑫, 邓卫, 程琳, 陈新元. 特大城市居民出行方式选择行为的混合Logit模型[J]. 吉林大学学报(工学版), 2018, 48(4): 1029-1036.
[10]	陈永恒, 刘鑫山, 熊帅, 汪昆维, 谌垚, 杨少辉. 冰雪条件下快速路汇流区可变限速控制[J]. 吉林大学学报(工学版), 2018, 48(3): 677-687.
[11]	王占中, 卢月, 刘晓峰, 赵利英. 基于改进和声搜索算法的越库车辆排序[J]. 吉林大学学报(工学版), 2018, 48(3): 688-693.
[12]	陈松, 李显生, 任园园. 公交车钩形转弯交叉口自适应信号控制方法[J]. 吉林大学学报(工学版), 2018, 48(2): 423-429.
[13]	苏书杰, 何露. 步行交通规划交叉路口行人瞬时动态拥塞疏散模型[J]. 吉林大学学报(工学版), 2018, 48(2): 440-447.
[14]	孟品超, 李学源, 贾洪飞, 李延忠. 基于滑动平均法的轨道交通短时客流实时预测[J]. 吉林大学学报(工学版), 2018, 48(2): 448-453.
[15]	王占中, 赵利英, 焦玉玲, 曹宁博. 信号交叉口自行车和行人混合交通流社会力模型[J]. 吉林大学学报(工学版), 2018, 48(1): 89-97.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于车载的运动行人区域估计方法

Locating moving pedestrian from running vehicle

RICH HTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10