南京大学学报(自然科学版) ›› 2017, Vol. 53 ›› Issue (3): 590.
张栋冰*
Zhang Dongbing*
摘要: 对传统的车辆目标检测方法进行改进,提出了一种基于形态学高帽变换(TOPHAT)与脉冲耦合神经网络(PCNN)相结合的车辆目标检测方法.首先对交通图像进行形态学高帽变化提取图像的目标区域、然后分析了PCNN特征对车辆图像与非车辆图像的区分度,统计了熵特征和脉冲点火特征分别对原始图像和TOPHAT图像的有效性,选取了迭代平均熵作为车辆检测的有效特征,并采用滑窗的方式进行车辆检测,最后利用边缘密度信息对检测出的车辆目标进行后续验证.实验从有效性和准确性两方面进行验证,实验图片来自实际交通路口,结果表明:该方法能够有效地进行车辆目标检测,同时与其他车辆目标检测方法相比,具有检测率高、误检率低,消耗时间少等特点,能够较好的实现智能交通中车辆目标的快速检测.
[1] Sun Z,Bebis G,Miller R.Onroad vehicle detection:A review.IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(11):694-711. [2] Malinovskiy Y,Wu Y J,Wang Y.Videobased vehicle detection and tracking using spatiotemporal maps.Transportation Research Record:Journal of the Transportation Research Board,2013,45(2121):81-89. [3] Gowacz A,Mikrut Z,Pawlik P.Video detection algorithm using an optical flow calculation method.In:International Conference on Multimedia Communications,Services and Security(MCSS 2012).Springer,2012:118-129. [4] Chao H,Gu Y,Napolitano M.A survey of optical flow techniques for robotics navigation applications.Journal of Intelligent & Robotic Systems Theory & Applications,2014,73(1-4):361-372. [5] 汤春明,聂美玲,丁腾飞等.基于最小特征匹配代价的夜间车辆检测和追踪.计算机应用与软件,2015,32(4):292-296.(Tang C M,Nie M L,Ding T F,et al.Nighttime vehicle detection and tracking based on minimum feature matching cost.Computer Applications and Software,2015,32(4):292-296.) [6] Zhou N,Li X,Li Z.Dim target detection based on spatiomorphological and wavelet transform clutter suppression.OptoElectronic Engineering,2009,36(11):25-28. [7] Cheng H Y,Weng C C,Chen Y Y.Vehicle detection in aerial surveillance using dynamic Bayesian networks.IEEE Transactions on Image Processing,2012,21(4):2152-2159. [8] 王 海,蔡英凤,袁朝春.基于多模式弱分类器的AdaBoostBagging车辆检测算法.交通运输工程学报,2015,15(2):118-126.(Wang H,Cai Y F,Yuan C C.AdaBoostBagging vehicle detection algorithm based on multimode weak classifier.Journal of Traffic and Transportation Engineering,2015,15(2):118-126.) [9] Wu B F,Juang J H.Adaptive vehicle detector approach for complex environments.IEEE Transactions on Intelligent Transportation Systems,2012,13(2):817-827. [10] 郭业才,蒋 峰,龚 溪.一种基于简化PCNN的色盲检测图分割方法.安徽大学学报(自然科学版),2013,1:50-54.(Guo Y C,Jiang F,Gong X.A segmentation method of color blindness detection image based on simplified PCNN.Journal of Anhui University(Natural Science Edition),2013,1:50-54.) [11] 黎 曦,郑 宏,刘 操.利用HSI色彩空间的PCNN人脸识别方法.武汉大学学报(信息科学版),2014,39(12):1499-1503.(Li X,Zheng H,Liu C.A method of face recognition based on HSIPCNN.Geomatics and Information Science of Wuhan University,2014,39(12):1499-1503.) [12] Wang Z,Ma Y,Cheng F,et al.Review of pulsecoupled neural networks.Image and Vision Computing,2010,28(1):5-13. [13] Chen J,Tadashi Shibata.A neuronMOSbased VLSI implementation of pulse coupled neural networks for image feature generation.IEEE Transactions on Circuits and SystemsI:Regular Papers,2010,57(6):1143-1151. [14] Wu C,Cao X,Lin R,et al.Registrationbased moving vehicle detection for lowaltitude urban traffic surveillance.In:2010 8th World Congress on Intelligent Control and Automation(WCICA).Ji’nan,China:IEEE,2010:373-378. [15] 刘 操,郑 宏,黎 曦等.基于多通道融合HOG特征的全天候运动车辆检测方法.武汉大学学报(信息科学版),2015,40(8):1048-1053.(Liu C,Zheng H,Li X,et al.A method of moving vehicle detection in allweather based on melted multichannel HOG feature.Geomatics and Information Science of Wuhan University,2015,40(8):1048-1053.) [16] Arróspide J,Salgado L,Marinas J.HOGlike gradientbased descriptor for visual vehicle detection.In:2012 IEEE Intelligent Vehicles Symposium(IV).Alcala de Henares,Spain:IEEE,2012:223-228. |
No related articles found! |
|