基于立体视觉及蛇模型的行人轮廓提取及其识别

刘述民; 黄影平; 张仁杰

doi:doi:10.3788/aos201434.0533001

光学学报, 2014, 34 (5): 0533001, 网络出版: 2014-04-24

基于立体视觉及蛇模型的行人轮廓提取及其识别

Pedestrian Contour Extraction and Its Recognition Using Stereovision and Snake Models

论文大纲

刘述民 ^1,2,*黄影平 ¹张仁杰 ¹

作者单位

¹ 上海理工大学光电与计算机工程学院, 上海 200093

² 江西理工大学软件学院, 江西南昌 330013

摘要

从复杂、动态多变的交通图像中准确提取障碍物的轮廓曲线是智能汽车的一个重要研究课题，它对行人保护起着十分重要的作用。Snake模型是用来自动提取物体边界的曲线模型。结合立体视觉技术和Snake模型以实现行人检测：运用基于稠密视差的立体分割方法查找并分割潜在行人目标区域，为了便于后期目标轮廓提取，基于边缘检索的立体匹配算法被进一步用于提取感趣区(ROIs)内的目标初始边界；在此基础上，用Snake模型提取目标的完整轮廓曲线；轮廓因子及目标高程被用于ROIs的验证，即行人识别。针对Snake模型易受噪声干扰及难以收敛到凹陷边界等缺陷，提出了改进的距离势能模型。以典型交通场景为分析对象，对所提出的方法进行了测试，得到了较为理想的结果。

Abstract

Accurate extraction of object contour from complex and dynamic traffic images is crucial for intelligent vehicles, and plays an important role for pedestrian protection. Snake Models are widely employed to object contour outomatic extraction. Presented here is a novel approach for pedestrian recognition by combining stereovision with Snake models. Object segmentation based on dense disparity map is used to locate and break up regions which contains potential pedestrians. Furthermore, edge-indexed stereo matching algorithm is employed to obtain the initial edges of the targets of the regions in order to facilitate object contour extraction in the later stage. Snake models are adopted to extract complete contour curves of the targets. Contour factors derived from the contour curves and target elevation are used to verify the targets i.e. pedestrian recognition. To overcome the limitations of Snake models, distance potential models are modified to immunize from noise and to make the model converge into the boundary concavity. The approach presented here is tested on substantial traffic images and the corresponding results prove the efficiency of the approach.

参考文献

[1] G David, M L Antonio, D S Angel, 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.

[2] 苏松志, 李绍滋, 陈淑媛, 等. 行人检测技术综述[J]. 电子学报, 2012, 40(4): 814-820.

Su Songzhi, Li Shaozi, Chen Shuyuan, et al.. A survey on pedestrian detection [J]. Acta Electronica Sinica, 2012, 40(4): 814-820.

[3] 贾慧星, 章毓晋. 车辆辅助驾驶系统中基于计算机视觉的行人检测研究综述[J]. 自动化学报, 2007, 33(1): 84-90.

Jia Huixing, Zhang Yujin. A survey of computer vision based pedestrian detection for driver assistance systems [J]. Acta Automatica Sinica, 2007, 33(1): 84-90.

[4] A Shashua, Y Gdalyahu, G Hayun. Pedestrian detection for driving assistance systems: single-frame classification and system level performance [C]. Parma IEEE Intelligent Vehicles Symposium, 2004: 1-6.

[5] N Dalal, B Triggs. Histograms of oriented gradients for human detection [C]. San Diego: Proc of IEEE CVPR, 2005, 1: 886-893.

[6] S Walk, N Majer, K Schindler, et al.. New features and insights for pedestrian detection [C]. San Diego: Proc of IEEE CVPR, 2010: 1030-1037.

[7] J X Wu, C Geyer, J M Rehg. Real-time human detection using contour cues [C]. Shanghai: Proc of IEEE ICRA, 2011: 860-867.

[8] 张海峰, 孟文东, 吴志波, 等. 单向激光测距及其测量试验[J]. 中国激光, 2013, 40(3): 0308005.

Zhang Haifeng, Meng Wendong, Wu Zhibo, et al.. One way laser ranging and is measuring experiment [J]. Chinese J Lasers, 2013, 40(3): 0308005.

[9] Y Yang, J Y Yang. Pedestrian detection on moving vehicle using stereo vision and 2D cue [C]. Proceedings of International Conference on Intelligent Science and Intelligent Data Engineering, 2013, 7751: 466-474.

[10] Y P Huang, S Fu, C Thompson. Stereovision-based object segmentation for automotive applications [J]. EURASIP Journal on Advance in Signal Processing, 1900, 2005 (14): 2322-2329.

[11] 温晴川, 达飞鹏, 方旭. 基于双目立体视觉的视线跟踪系统标定[J]. 光学学报, 2012, 32(10): 1015002.

Wen Qingchuan, Da Feipeng, Fang Xu. Calibration for gaze tracking system based on binocular stereo vision [J]. Acta Optica Sinica, 2012, 32(10): 1015002.

[12] 张肃, 王文生. 复杂背景下运动目标的光学相关识别[J]. 光学学报, 2012, 32(1): 0107001.

Zhang Su, Wang Wensheng. Optical correlation recognition of the moving target in cluttered background [J]. Acta Optica Sinica, 2012, 32(1): 0107001.

[13] N T Duc, O Philip, Li Wangqing. Human detection with contour-based local motion binary patterns [C]. Brussels: Proceedings of International Conference on Image Processing, 2011: 3609-3612.

[14] 丁辰瑜, 葛万成. 基于形状上下文的公共场所行人检测系统[J]. 通信技术, 2012, 45(4): 46-49.

Ding Chenyu, Ge Wancheng, Chen Kangli. Pedestrian detection for public place based on shape context [J]. Communications Technology, 2012, 45(4): 46-49.

[15] M Kass, A Witkin, D Terzopoulos. Snakes: active contour models [J]. International Journal of Computer Vision, 1987, 1(4): 321-331.

[16] L D Cohen, I Cohen. Finite-element methods for active contour models and balloons for 2D and 3D images [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(11): 1131-1147.

[17] Chenyang Xu, J L Prince. Snakes, shapes, and gradient vector flow [J]. IEEE Transaction on Image Processing, 1998, 7(3): 359-369.

[18] Z Lyubomir, G Ardeshir, S Martin. R-snakes [J]. Image and Vision Computing, 2007, 25(6): 945-959.

[19] S Michal, B S Ohad. Free boundary conditions active contours with applications for vision [C]. Las Vegas: Proceedings of International Conference on ISVC, 2011: 180-191.

[20] F Zhang, X Zhang, K Cao, et al.. Contour extraction of gait recognition based on improved GVF Snake model [J]. Computers and Electrical Engineering, 2012, 38(4): 882-900.

[21] E Shahamatnia, M M Ebadzadeh. Application of particle swarm optimization and snake model hybrid on medical imaging [C]. Paris: Proceedings of International Workshop on Computational Intelligence in Medical Imaging, IEEE, 2011: 1-8.

[22] G K Christoph, E Markus, R Markus, et al.. The benefits of dense stereo for pedestrian detection [J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(4): 1096-1106.

[23] 王华英, 张志会, 刘飞飞, 等. 对基于图像分割与合并的相位展开算法的改进[J]. 中国激光, 2012, 39(10): 1009002.

Wang Huaying, Zhang Zhihui, Liu Feifei, et al.. Improved phase unwrapping algorithm based on image segmentation and mergers [J]. Acta Optica Sinica, 2012, 39(10): 1009002.

[24] 白明, 庄严, 王伟. 双目立体匹配算法的研究与进展[J]. 控制与决策, 2008, 23(7): 721-729.

Bai Ming, Zhuang Yan, Wang Wei. Progress in binocular stereo matching algorithms [J]. Control and Decision, 2008, 23(7): 721-729.

[25] N Sergiu, G Ion, B Silviu. Real time stereo vision based pedestrian detection using full body contours [C]. Cluj-Napoca: Proceedings of International Conference on Intelligent Computer Communication and Processing, 2009: 79-86.

[26] C Hilario, J M Collado, J Ma Armingol, et al.. Pedestrian detection for intelligent vehicles based on active contour modelsand stereo vision [C]. Las Pabnas: Proceedings of International Conference on EUROCAST, 2005: 537-542.

[27] Feifei Jin, Aibo Zheng, Shengke Wang. Pedestrian detection based on active contour models [C]. Qingdao: International Symposium on Information Processing, 2010: 121-125.

[28] Weigang Chen. Pedestrian detection embedded in level-set-based moving objects detection and tracking [C]. Chengdu: International Conference on Computer and Information Technology, IEEE, 2012: 561-566.

刘述民, 黄影平, 张仁杰. 基于立体视觉及蛇模型的行人轮廓提取及其识别[J]. 光学学报, 2014, 34(5): 0533001. Liu Shumin, Huang Yingping, Zhang Renjie. Pedestrian Contour Extraction and Its Recognition Using Stereovision and Snake Models[J]. Acta Optica Sinica, 2014, 34(5): 0533001.

基于立体视觉及蛇模型的行人轮廓提取及其识别

关于本站 Cookie 的使用提示

全站搜索

基于立体视觉及蛇模型的行人轮廓提取及其识别

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索