计算机科学 ›› 2015, Vol. 42 ›› Issue (4): 285-291.doi: 10.11896/j.issn.1002-137X.2015.04.059

• 图形图像与模式识别 • 上一篇    下一篇

基于多层级联视觉显著性模型的肇事车辆锁定方法

柴桢亮,臧 笛   

  1. 同济大学计算机科学与技术系 上海201804同济大学嵌入式系统与服务计算教育部重点实验室 上海200092,同济大学计算机科学与技术系 上海201804同济大学嵌入式系统与服务计算教育部重点实验室 上海200092
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金(61103071),教育部博士学科点新教师基金(20110072120065),留学回国人员科研启动基金,2012年科技部国际合作专项(2012DFG11580)资助

Localization of Causing-traffic-trouble Vehicle with Multi-level Cascaded Visual Attention Model

CHAI Zhen-liang and ZANG Di   

  • Online:2018-11-14 Published:2018-11-14

摘要: 肇事车辆的锁定是智能交通系统中一个十分重要的问题,因此针对肇事车辆的锁定,提出了一种基于多层级联视觉注意模型的肇事车辆匹配方法。在模型的每一层中,基于传统视觉注意模型的思想,通过生成显著图的方式提取车辆的一个显著性特征,如颜色、车标,并将其与肇事车辆进行匹配,过滤掉特征不相似的车辆,经过多次显著性特征提取和匹配,最终获得唯一的肇事车辆。实验结果表明,该模型可以准确地从车辆数据库中锁定肇事车辆,且对光照变化和噪声有较强的鲁棒性。

关键词: 肇事车辆,车辆匹配,计算机视觉,视觉注意模型,车牌识别

Abstract: The localization of causing-traffic-trouble vehicle is one of the most key problems for intelligent transportation system (ITS).This paper proposed a multi-level cascaded visual attention model to localize the causing-traffic-trouble vehicle.In each level of the proposed model,one significant feature of the vehicle such as color or vehicle logo is extracted and compared to the vehicle which has caused an accident.Then vehicles that have no similar features can be filtered.By performing feature extraction and feature comparison for several times,only the causing-traffic-trouble vehicle will be left behind.The experimental results demonstrate that the proposed approach is able to locate the causing-traffic-trouble vehicle accurately and is robust to luminance and noise.

Key words: Causing-traffic-trouble vehicle,Vehicle matching,Computer vision,Visual attention model,Plate recognition

[1] 罗钟铉,刘成明.灰度图像匹配的快速算法[J].计算机辅助设计与图形学学报,2005,17(5):966-970
[2] Piccardi M,Cheng E D.Multi-frame moving object track matching based on an incremental major color spectrum histogram matching algorithm[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops,2005.IEEE,2005:19
[3] Liu S,Sun J,Dang J.A Linear Resection-Intersection BundleAdjustment Method[J].Information Technology Journal,2008,7(1):220-223
[4] Lowe D G.Distinctive image features from scale-invariant keypoints[J].International journal of computer vision,2004,60(2):91-110
[5] Hu X,Tang Y,Zhang Z.Video object matching based on SIFT algorithm[C]∥2008 International Conference on Neural Networks and Signal Processing.IEEE,2008:412-415
[6] Ke Y,Sukthankar R.PCA-SIFT:A more distinctive representation for local image descriptors[C]∥Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2004(CVPR 2004).IEEE,2004,2:506-513
[7] Alhwarin F,Wang C,Ristic-Durrant D,et al.Improved SIFT-Features Matching for Object Recognition[C]∥BCS International Academic Conference.2008:178-190
[8] Shan Y,Sawhney H S,Kumar R.Unsupervised learning of discriminative edge measures for vehicle matching between nonoverlapping cameras[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(4):700-711
[9] 曾志宏,李建洋,郑汉垣.融合深度信息的视觉注意计算模型[J].计算机工程,2010,36(20):200-202
[10] Baluch F,Itti L.Training top-down attention improves perfor-mance on a triple-conjunction search task[J].PloS one,2010,5(2):e9127
[11] Itti L,Koch C,Niebur E.A model of saliency-based visual attention for rapid scene analysis[J].IEEE Transactions on pattern analysis and machine intelligence,1998,20(11):1254-1259
[12] Stentiford F W M.Attention-based image similarity measurewith application to content-based information retrieval[C]∥Electronic Imaging 2003 International Society for Optics and Photonics,2003:221-232
[13] Hou X,Zhang L.Saliency detection:A spectral residual ap-proach[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2007(CVPR’07).IEEE,2007:1-8
[14] Hu Y,Rajan D,Chia L T.Adaptive local context suppression of multiple cues for salient visual attention detection[C]∥IEEE International Conference on Multimedia and Expo,2005(ICME 2005).IEEE,2005:4
[15] 楼汉琦,蔡晓东,李长俊.一种实现快速车标定位的方法[J].国外电子测量技术,2013(6):72-74
[16] 毛颂安.汽车车标检测方法的研究与实现[D].成都:电子科技大学,2012
[17] 周小龙,张小洪,冯欣.基于视觉显著图的车牌定位算法[J].光电工程,2009,36(11):145-150
[18] Siddiqui F U,Isa N A M.Enhanced moving K-means (EMKM) algorithm for image segmentation[J].IEEE Transactions on Consumer Electronics,2011,57(2):833-841
[19] Guo Y,Hsu S,Sawhney H S,et al.Robust object matching for persistent tracking with heterogeneous features[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(5):824-839
[20] Zhu L J,Hwang J N,Cheng H Y.Tracking of multiple objects across multiple cameras with overlapping and non-overlapping views[C]∥IEEE International Symposium on Circuits and Systems,2009(ISCAS 2009).IEEE,2009:1056-1060
[21] 李星,郭晓松,郭君斌.基于HOG特征和SVM的前向车辆识别方法[J].计算机科学,2013,40(11A):329-332

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!