全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

利用七宫格的遮挡车辆凹性检测与分割

DOI: 10.11834/jig.20140106

Keywords: 凹性分析,七宫格,凹陷区域,遮挡区域,车辆分割

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的交通场景中车辆间的距离过近或相互遮挡容易造成识别上的粘连,增加了准确检测目标车辆的难度,因此需要建立有效、可靠的遮挡车辆分割机制。方法首先在图像分块的基础上确定出车辆区域,根据车辆区域的长宽比和占空比进行多车判断;然后提出了一种基于七宫格的凹陷区域检测算法,用以找出车辆间的凹陷区域,通过匹配对应的凹陷区域得到遮挡区域;最后,将遮挡区域内检测出的车辆边缘轮廓作为分割曲线,从而分割遮挡车辆。结果实验结果表明,在满足实时性的前提下算法具有较高的识别率,且能够按车辆的边缘轮廓准确分割多个相互遮挡的车辆。与其他算法相比,该算法提高了分割成功率和分割精度,查全率和查准率均可达到90%。结论本文新的遮挡车辆分割算法,有效解决了遮挡车辆不宜分割和分割不准确的问题,具有较强的适应性。

References

[1]  Jiao B, Yan L L, Li W. Real-time Partial Sheltered Vehicles Segmentation and Shadow Elimination[J]. Journal of Chinese Computer Systems, 2012,8(33):1825-1829.[焦波,闫了了,李伟.实时部分遮挡车辆分割及阴影消除[J].小型微型计算机系统,2012,8(33):1825-1829.]
[2]  Kanhere N K, Pundlik S J, Birchfield S T. Vehicle segmentation and tracking from a low-angle off-axis camera[C]//Proceedings of Computer Vision and Pattern Recognition. San Diego, California:IEEE, 2005:1152-1158.
[3]  Liu H Y, Li J, Hong L R. Subspace vehicle recognition algorithm using local features[J]. Computer Engineering and Applications, 2010,46(30):156-180.[刘怀愚,李?,洪留荣.利用局部特征的子空间车辆识别算法[J].计算机工程与应用,2010,46(30):156-180.]
[4]  Fan N. Object classification and occlusion handling using quadratic feature correlation model and neural networks[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2011, 25(3):287-298.
[5]  Coifman B, Beymer D, Mclauchlan P, et al. A real-time computer vision system for vehicle tracking and traffic surveillance[J]. Transportation Research Part C:Emerging Technologies, 1998, 6(8):271-288.
[6]  Huang C L, Liao W C. A vision-based vehicle identification system[C]//Proceedings of International Conference on Pattern Recognition. Washington DC:IEEE Computer Society, 2004:364-367.
[7]  Jung Y K, Lee K W, Ho Y S. Content-based event retrieval using semantic scene interpretation for automated traffic surveillance[J]. IEEE Transactions on Intelligent Transportation Systems, 2001, 2(3):151-163.
[8]  Song X F, Ram N. Detection and tracking of moving vehicles in crowded scenes[C]//Proceedings of the IEEE Workshop on Motion and Video Computing. Washington DC, USA:IEEE, 2007:1-4.
[9]  Kothari S, Chaudry Q, Wang M D. Automated cell counting and cluster segmentation using concavity detection and ellipse fitting techniques[C]//Proceedings of IEEE International Symposium on Biomedical Imaging. Piscataway, NJ:IEEE Press, 2009:795-798.
[10]  Zhang W, Wu Q M, Yang X K, et al. Multilevel framework to detect and handle vehicle occlusion[J]. IEEE Transaction on Intelligent Transportation Systems, 2008, 9(3):161-174.
[11]  Goo J, Aggarwal J K, Gokmen M. Tracking and segmentation of highway vehicles in cluttered and crowded scenes[C]//IEEE Workshop on Applications of Computer Vision. Copper Mountain, CO: IEEE,2008:1-6.
[12]  Ji X P, Wei Z Q. Tracking method based on contour feature of vehicles and extended Kalman filter[J]. Journal of Image and Graphics, 2011,16(2):267-272.[纪筱鹏,魏志强.基于轮廓特征及扩展Kalman 滤波的车辆跟踪方法研究[J].中国图象图形学报,2011,16(2):267-272.]
[13]  Zhang X. Method for eliminating moving object shadows in video images[J]. Computer Engineering and Applications, 2013, 49(6):201-204.[张霞.视频图像中运动目标的阴影消除法[J].计算机工程与应用,2013,49(6):201-204.]
[14]  Rosten E, Drummond T. Machine learning for high-speed corner detection[C]//Proceeding of the European Conference on Computer Vision. Graz, Austria:Springer, 2006, 3951:430-443.
[15]  Maddalena L, Petrosino A. A self-organizing approach to background subtraction for visual surveillance applications[J]. IEEE Transactions on Image Processing, 2008, 17(7):1168-1177.
[16]  Wu X S, Liu Y, Qi Q F. Adhered vehicles segmentation based on concavity analysis[J]. Application Research of Computers, 2012,29(1):344-347.[吴忻生,刘洋,戚其丰.基于凹性分析的粘连车辆分割[J].计算机应用研究,2012,29(1):344-347.]
[17]  Chen C Y, Liu S H. Detection and segmentation of occluded vehicles based on skeleton features[C]//Proceedings of the 2nd International Conference on Instrumentation and Measurement, Computer, Communication and Control. Harbin, China:IEEE, 2012:1055-1059.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133