复杂背景下抗遮挡的车辆检测技术
|
摘要
随着车辆数目的急剧增加,如何有效地管理车辆以减少事故率的发生日益成为各个国家关心的重大问题。针对这种情况,各种智能交通系统应运而生,而有效地对车辆进行检测是该系统的核心环节,本文主要对车辆检测领域的背景建模、阴影去除、遮挡分离三大问题进行了研究,并提出了相应的改良方法。
目前比较常用的车辆检测技术有光流法、帧间差分法和背景帧差法,其中在对背景建模准确的情况下,背景帧差法在实时性和准确性两方面都有较好的性能,所以,关键任务是建立优秀的背景模型,本论文中,我们对均值滤波建模法进行了改进,通过引入直方图阈值预判,解决了传统均值滤波法在复杂背景下效果不好的难题；同时,由于在光照条件下,对前景的检测不可避免地会把阴影一同检测出来,严重影响了后续跟踪和分析,所以要对阴影进行去除,本论文中,我们对基于HSV空间的阴影检测算法进行了改进,通过引入八邻域均值来增强单像素点的抗噪性；此外,由于目前的车辆拥堵情况非常严重,车辆的互相遮挡不可避免,如何对车辆进行去遮挡处理是车辆检测及阴影去除后的必需环节,本文提出了一种基于转折角点的去遮挡方法,该方法分为目标区域块的空洞填充、转折角点的提取和分类、基于转折角点的模板匹配三个主要步骤,在目标区域块的空洞填充步骤中,本文提出了一种基于轮廓的空洞填充方法,在转折角点的提取和分类步骤中,本文通过圆盘移动方法提取目标区域块的转折角点并通过转折角点的倾斜角归一化直方图对转折角点进行分类,在基于转折角点的模板匹配步骤中,我们利用目标区域块和模板两者对应的循环链表进行比对,找出与目标区域块匹配的模板,根据模板提供的分离策略,实现遮挡分离。本文提出的基于转折角点的去遮挡方法适用于各类常见的遮挡情况,具有广泛的适用性。
With the rapid increase in the number of vehicles, How to manage vehicles effectively to reduce the rate of accidents has increasingly become the major problem many countries pay attention to. In view of this situation, all kinds of intelligent transportation systems(ITS) are proposed at the historic moment, and vehicle detection is the foundation of the system.
At present, optical flow method, the frame-difference method and background subtraction method are commonly used in vehicle detection technology. Among them, background subtraction method has better performance in real-time and accuracy if a good background model is established.In this paper, we use modified mean-value filtering method to establish background model. The modified method gets higher accuracy than the traditional method in the complex background by bringing in the histogram threshold value. At the same time, because of the influence of illumination, the shadow is detected together with the foreground vehicle, which has a serious impact on subsequent tracking and analysis. So we need to remove the shadow. In this paper, we use modified shadow detection algorithm base on HSV model, and this algorithm enhances noise immunity of single pixel point by bringing in eight neighborhood mean-value. Moreover, because of the serious vehicle congestion situation, the mutual occlusion among vehicles is inevitable, how to separate the vehicle occlusion is the necessary step after vehicle detection. In this paper, we put forward anti-occlusion algorithm based on angular point. Firstly, we pick up angular points through discoid moving algorithm, secondly, we store the angular points in a circular linked list, thirdly, we compare the data in circular linked list with the template library and find out the matching template, at last, we conduct the occlusion separation of the vehicle according to the known matching template. This anti-occlusion algorithm based on angular point can be applied to all kinds of common occlusion, and the algorithm has good feasibility.
目前比较常用的车辆检测技术有光流法、帧间差分法和背景帧差法,其中在对背景建模准确的情况下,背景帧差法在实时性和准确性两方面都有较好的性能,所以,关键任务是建立优秀的背景模型,本论文中,我们对均值滤波建模法进行了改进,通过引入直方图阈值预判,解决了传统均值滤波法在复杂背景下效果不好的难题；同时,由于在光照条件下,对前景的检测不可避免地会把阴影一同检测出来,严重影响了后续跟踪和分析,所以要对阴影进行去除,本论文中,我们对基于HSV空间的阴影检测算法进行了改进,通过引入八邻域均值来增强单像素点的抗噪性；此外,由于目前的车辆拥堵情况非常严重,车辆的互相遮挡不可避免,如何对车辆进行去遮挡处理是车辆检测及阴影去除后的必需环节,本文提出了一种基于转折角点的去遮挡方法,该方法分为目标区域块的空洞填充、转折角点的提取和分类、基于转折角点的模板匹配三个主要步骤,在目标区域块的空洞填充步骤中,本文提出了一种基于轮廓的空洞填充方法,在转折角点的提取和分类步骤中,本文通过圆盘移动方法提取目标区域块的转折角点并通过转折角点的倾斜角归一化直方图对转折角点进行分类,在基于转折角点的模板匹配步骤中,我们利用目标区域块和模板两者对应的循环链表进行比对,找出与目标区域块匹配的模板,根据模板提供的分离策略,实现遮挡分离。本文提出的基于转折角点的去遮挡方法适用于各类常见的遮挡情况,具有广泛的适用性。
With the rapid increase in the number of vehicles, How to manage vehicles effectively to reduce the rate of accidents has increasingly become the major problem many countries pay attention to. In view of this situation, all kinds of intelligent transportation systems(ITS) are proposed at the historic moment, and vehicle detection is the foundation of the system.
At present, optical flow method, the frame-difference method and background subtraction method are commonly used in vehicle detection technology. Among them, background subtraction method has better performance in real-time and accuracy if a good background model is established.In this paper, we use modified mean-value filtering method to establish background model. The modified method gets higher accuracy than the traditional method in the complex background by bringing in the histogram threshold value. At the same time, because of the influence of illumination, the shadow is detected together with the foreground vehicle, which has a serious impact on subsequent tracking and analysis. So we need to remove the shadow. In this paper, we use modified shadow detection algorithm base on HSV model, and this algorithm enhances noise immunity of single pixel point by bringing in eight neighborhood mean-value. Moreover, because of the serious vehicle congestion situation, the mutual occlusion among vehicles is inevitable, how to separate the vehicle occlusion is the necessary step after vehicle detection. In this paper, we put forward anti-occlusion algorithm based on angular point. Firstly, we pick up angular points through discoid moving algorithm, secondly, we store the angular points in a circular linked list, thirdly, we compare the data in circular linked list with the template library and find out the matching template, at last, we conduct the occlusion separation of the vehicle according to the known matching template. This anti-occlusion algorithm based on angular point can be applied to all kinds of common occlusion, and the algorithm has good feasibility.
引文
[1]Faro A,Giordano D, Spampinato C.Adaptive Background Modeling Integrated With Luminosity Sensors and Occlusion Processing for Reliable Vehicle Detection. Intelligent Transportation Systems IEEE Transactions.2011.1398-1412.
[2]Wanxin Xu,Meikang Qiu,Zhi Chen, Hai Su.Intelligent Vehicle Detection and Tracking for Highway Driving.Multimedia and Expo Workshops (ICMEW) 2012 IEEE International Conference.2012.67-72
[3]Makarau A,Richter R.,Muller R,Reinartz P.Adaptive Shadow Detection Using a Blackbody Radiator Model.Geoscience and Remote Sensing IEEE Transactions.2011.2049-2059
[4]Gorai A,Ghosh A. Hue-preserving color image enhancement using particle swarm optimization. Recent Advances in Intelligent Computational Systems (RAICS),2011 IEEE.2011.563-568.
[5]Panetta K, Agaian S, Yicong Zhou,Wharton E.J. Parameterized Logarithmic Framework for Image Enhancement.Systems Man and Cybernetics Part B Cybernetics IEEE Transactions.2011.460-473
[6]Wei Liu, Zhengming Ma.Wavelet Image Threshold Denoising Based on Edge Detection.Computational Engineering in Systems Applications IMACS Multiconference.2006.72-78
[7]Yong Yang,Chongxun Zheng.Pan Lin.Image thresholding based on spatially weighted fuzzy c-means clustering.Computer and Information Technology,2004. CIT'04. The Fourth International Conference.2004.184-189
[8]Droske M, Rumpf M. Multiscale Joint Segmentation and Registration of Image Morphology. Pattern Analysis and Machine Intelligence IEEE Transactions.2007.2181-2194
[9]Herisse B,Hamel T,Mahony R.The landing problem of a VTOL Unmanned Aerial Vehicle on a moving platform using optical flow.Intelligent Robots and Systems (IROS),2010 IEEE/RSJ International Conference.2010.1600-1605
[10]Li Ying-hong,Tian Hong-fang,Zhang Yan.An improved Gaussian mixture background model with real-time adjustment of learning rate.Information Networking and Automation (ICINA),2010 International Conference.2010.V1512-V1515
[11]Ming-ming Gao,Ji-zhen Liu,Xiang-xiang Gao.Application of Compound Gaussian Mixture Model clustering in the data stream. Computer Application and System Modeling (ICCASM) 2010 International Conference.2010. V7-172-V7-177
[12]Chen Z.,Ellis T. Self-adaptive Gaussian mixture model for urban traffic monitoring system.Computer Vision Workshops (ICCV Workshops),2011 IEEE International Conference.2011.1769-1776
[13]Easwaran S,Gowdy J N. An improved initialization algorithm for use with the K-means algorithm for code book generation.Southeastcon 92 Proceedings IEEE.1992.471-474 vol.2
[14]Yinghua Lu,Huijie Xin,Jun Kong,etc. Shadow Removal Based on Shadow Direction and Shadow Attributes.Computational Intelligence for Modelling, Control and Automation,2006 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, International Conference.2006.37
[15]Bian Jianyong,Yang Runfeng,Yang Yang. A novel vehicle's shadow detection and removal algorithm.Consumer Electronics Communications and Networks (CECNet) 2012 2nd International Conference.2012.822-826
[16]Kuo-Liang Chung,Yi-Ru Lin,Yong-Huai Huang.Efficient Shadow Detection of Color Aerial Images Based on Successive Thresholding Scheme.Geoscience and Remote Sensing, IEEE Transactions.2009.671-682
[17]张丽,李志能.基于阴影检测的HSV空间自适应背景模型的车辆追踪检测.中国图象图形学报.2003年7期.
[18]王玉兰.一种调节和选择颜色的交互方法.小型微型计算机系统.1990年8期.
[19]Hui-xuan Fu,Feng Sun,Sheng Liu.Anti-occlusion tracking algorithm based on LSSVM prediction and Kalman-MeanShift.Intelligent Control and Automation (WCICA),2010 8th World Congress.2010.6031-6036
[20]欧阳宁,游锦海,莫建文等.遮挡情况下的多目标跟踪算法.计算机应用研究.2010年5期.
[21]Ning Ma,Bouchard.M,Goubran.R A.Speech enhancement using a masking threshold constrained Kalman filter and its heuristic implementations.Audio Speech and Language Processing IEEE Transactions. 2006.19-32
[22]Dengfeng Li,Hu Li,Xiuling Wei.Kahnan filtering-based modified Cam-Shift vehicle tracking algorithm for highway traffic conditions.Computer Application and System Modeling (ICCASM),2010 International Conference.2010.V 14-271-V14-275
[23]Shengluan Huang,Jingxin Hong.Moving object tracking system based on camshift and Kalman filter. Consumer Electronics Communications and Networks (CECNet) 2011 International Conference.2011.1423-1426
[24]Stubberud, S.C, Kramer, K.A., Geremia, J.A.Analysis of the effects of bearings-only sensors on the performance of the neural extended kalman filter tracking system. Computational Intelligence for Measurement Systems and Applications,2008. CIMSA 2008.2008 IEEE International Conference.2008. 54-59
[25]Yina Wei,Ullah G,,Parekh R,etc.Kalman filter tracking of intracellular neuronal voltage and current. Decision and Control and European Control Conference (CDC-ECC),2011 50th IEEE Conference.2011, 5844-5849
[26]Kramer K.A,Stubberud S.C.Tracking of Multiple Target Types with a Single Neural Extended Kalman Filter. Intelligent Systems,2006 3rd International IEEE Conference.2006.463-468
[27]Linda O,Vollmer T,Manic M.SVM-inspired dynamic safe navigation using convex hull constraction.Industrial Electronics and Applications,2009. ICIEA 2009.4th IEEE Conference.2009.1001-1006
[28]Hans S, Addepalli S.C, Gupta A,etc. On Privacy Preserving Convex Hull. Availability Reliability and Security 2009 ARES 09 International Conference.2009.187-192
[29]孙青,郑永果.复杂连通区域扫描线填充算法的问题及改进.信息技术与信息化.2007年3期.
[30]Strand, M.Fluorescence imaging laser line scan (FILLS) for very shallow water mine countermeasures.OCEANS 2001 MTS/IEEE Conference and Exhibition.2001.102-106 vol.1
[2]Wanxin Xu,Meikang Qiu,Zhi Chen, Hai Su.Intelligent Vehicle Detection and Tracking for Highway Driving.Multimedia and Expo Workshops (ICMEW) 2012 IEEE International Conference.2012.67-72
[3]Makarau A,Richter R.,Muller R,Reinartz P.Adaptive Shadow Detection Using a Blackbody Radiator Model.Geoscience and Remote Sensing IEEE Transactions.2011.2049-2059
[4]Gorai A,Ghosh A. Hue-preserving color image enhancement using particle swarm optimization. Recent Advances in Intelligent Computational Systems (RAICS),2011 IEEE.2011.563-568.
[5]Panetta K, Agaian S, Yicong Zhou,Wharton E.J. Parameterized Logarithmic Framework for Image Enhancement.Systems Man and Cybernetics Part B Cybernetics IEEE Transactions.2011.460-473
[6]Wei Liu, Zhengming Ma.Wavelet Image Threshold Denoising Based on Edge Detection.Computational Engineering in Systems Applications IMACS Multiconference.2006.72-78
[7]Yong Yang,Chongxun Zheng.Pan Lin.Image thresholding based on spatially weighted fuzzy c-means clustering.Computer and Information Technology,2004. CIT'04. The Fourth International Conference.2004.184-189
[8]Droske M, Rumpf M. Multiscale Joint Segmentation and Registration of Image Morphology. Pattern Analysis and Machine Intelligence IEEE Transactions.2007.2181-2194
[9]Herisse B,Hamel T,Mahony R.The landing problem of a VTOL Unmanned Aerial Vehicle on a moving platform using optical flow.Intelligent Robots and Systems (IROS),2010 IEEE/RSJ International Conference.2010.1600-1605
[10]Li Ying-hong,Tian Hong-fang,Zhang Yan.An improved Gaussian mixture background model with real-time adjustment of learning rate.Information Networking and Automation (ICINA),2010 International Conference.2010.V1512-V1515
[11]Ming-ming Gao,Ji-zhen Liu,Xiang-xiang Gao.Application of Compound Gaussian Mixture Model clustering in the data stream. Computer Application and System Modeling (ICCASM) 2010 International Conference.2010. V7-172-V7-177
[12]Chen Z.,Ellis T. Self-adaptive Gaussian mixture model for urban traffic monitoring system.Computer Vision Workshops (ICCV Workshops),2011 IEEE International Conference.2011.1769-1776
[13]Easwaran S,Gowdy J N. An improved initialization algorithm for use with the K-means algorithm for code book generation.Southeastcon 92 Proceedings IEEE.1992.471-474 vol.2
[14]Yinghua Lu,Huijie Xin,Jun Kong,etc. Shadow Removal Based on Shadow Direction and Shadow Attributes.Computational Intelligence for Modelling, Control and Automation,2006 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, International Conference.2006.37
[15]Bian Jianyong,Yang Runfeng,Yang Yang. A novel vehicle's shadow detection and removal algorithm.Consumer Electronics Communications and Networks (CECNet) 2012 2nd International Conference.2012.822-826
[16]Kuo-Liang Chung,Yi-Ru Lin,Yong-Huai Huang.Efficient Shadow Detection of Color Aerial Images Based on Successive Thresholding Scheme.Geoscience and Remote Sensing, IEEE Transactions.2009.671-682
[17]张丽,李志能.基于阴影检测的HSV空间自适应背景模型的车辆追踪检测.中国图象图形学报.2003年7期.
[18]王玉兰.一种调节和选择颜色的交互方法.小型微型计算机系统.1990年8期.
[19]Hui-xuan Fu,Feng Sun,Sheng Liu.Anti-occlusion tracking algorithm based on LSSVM prediction and Kalman-MeanShift.Intelligent Control and Automation (WCICA),2010 8th World Congress.2010.6031-6036
[20]欧阳宁,游锦海,莫建文等.遮挡情况下的多目标跟踪算法.计算机应用研究.2010年5期.
[21]Ning Ma,Bouchard.M,Goubran.R A.Speech enhancement using a masking threshold constrained Kalman filter and its heuristic implementations.Audio Speech and Language Processing IEEE Transactions. 2006.19-32
[22]Dengfeng Li,Hu Li,Xiuling Wei.Kahnan filtering-based modified Cam-Shift vehicle tracking algorithm for highway traffic conditions.Computer Application and System Modeling (ICCASM),2010 International Conference.2010.V 14-271-V14-275
[23]Shengluan Huang,Jingxin Hong.Moving object tracking system based on camshift and Kalman filter. Consumer Electronics Communications and Networks (CECNet) 2011 International Conference.2011.1423-1426
[24]Stubberud, S.C, Kramer, K.A., Geremia, J.A.Analysis of the effects of bearings-only sensors on the performance of the neural extended kalman filter tracking system. Computational Intelligence for Measurement Systems and Applications,2008. CIMSA 2008.2008 IEEE International Conference.2008. 54-59
[25]Yina Wei,Ullah G,,Parekh R,etc.Kalman filter tracking of intracellular neuronal voltage and current. Decision and Control and European Control Conference (CDC-ECC),2011 50th IEEE Conference.2011, 5844-5849
[26]Kramer K.A,Stubberud S.C.Tracking of Multiple Target Types with a Single Neural Extended Kalman Filter. Intelligent Systems,2006 3rd International IEEE Conference.2006.463-468
[27]Linda O,Vollmer T,Manic M.SVM-inspired dynamic safe navigation using convex hull constraction.Industrial Electronics and Applications,2009. ICIEA 2009.4th IEEE Conference.2009.1001-1006
[28]Hans S, Addepalli S.C, Gupta A,etc. On Privacy Preserving Convex Hull. Availability Reliability and Security 2009 ARES 09 International Conference.2009.187-192
[29]孙青,郑永果.复杂连通区域扫描线填充算法的问题及改进.信息技术与信息化.2007年3期.
[30]Strand, M.Fluorescence imaging laser line scan (FILLS) for very shallow water mine countermeasures.OCEANS 2001 MTS/IEEE Conference and Exhibition.2001.102-106 vol.1