CASIA OpenIR  > 毕业生  > 博士学位论文
城市交通场景下基于与或图模型的车辆检测方法研究
Alternative TitleVehicle Detection Based on And-Or Graph Models under Urban Traffic Conditions
李叶
Subtype工学博士
Thesis Advisor王飞跃
2014-05-24
Degree Grantor中国科学院大学
Place of Conferral中国科学院自动化研究所
Degree Discipline控制理论与控制工程
Keyword车辆检测 与或图模型 车辆遮挡 混合图像模板 概率模型 城市交通场景 Vehicle Detection And-or Graph Vehicle Occlusion Hybrid Image Template Probability Model Urban Traffic Condition
Abstract随着高清摄像机在智能交通系统中的推广应用和图像处理技术的发展,基于图像的检测技术已成为最重要的车辆检测方法之一,并得到广泛的研究,在车辆检测准确率上不断提高。但是在城市交通场景中基于图像的车辆检测技术仍面临一些难题:1)车辆遮挡,由于城市交通拥堵带来车辆之间遮挡的问题,易引起车辆定位不准确;2)非车对象干扰,城市交通特别是交叉路口处存在大量的非车对象如行人和非机动车等,干扰车辆检测;3)多尺度车辆,在城市交通图像中与摄像机不同距离的车辆会有极大的尺度变化,包括 大小、清晰度、形状等方面的变化,针对多尺度车辆的检测率还有待提高。 本文针对城市交通场景中基于图像的车辆检测技术面临的一系列问题,基于与或图(And-Or Graph,AOG)模型提出了多个车辆检测方法,由于与或图模型的层次结构及对结构、几何、外观、概率信息的融合,提高在车辆遮挡、非车对象干扰和多尺度车辆情况下的车辆检测准确率。本文的工作和贡献主要包括以下几个方面: 1.针对路段交通场景中车辆遮挡引起的车辆定位不准确问题,本文开展了遮挡情况下车辆检测方法的研究。提出了基于与或图的检测方法,利用与或图构建车辆表示模型,利用自下而上的推理检测车辆。在与或图构建中,根据易遮挡程度选择车窗和车尾灯作为车辆特征,然后分层分解这些特征为多个更小的部分特征,这样即使在严重车辆遮挡情况下,仍有一些部分特征可被检测,该模型可对遮挡情况下的车辆进行有效描述。最后基于构建的与或图模型,通过自下而上的推理组合部分特征实现车辆检测。经过量化评估实验和对比实验的验证,本文提出的基于与或图的车辆检测方法能够在带有严重车辆遮挡的路段交通场景中有效定位车辆,同时适应天气变化。 2.针对路口交通场景中非车对象对车辆检测技术的干扰问题,本文开展了路口交通场景下车辆检测方法的研究。提出了基于混合图像模板(Hybrid Image Template,HIT)和与或图模型的车辆检测方法HIT-AOG,利用车窗和车牌作为车辆特征,并将其分解为部分特征,然后利用混合图像模板融合多种特征描述子(边缘、纹理、颜色和平整度)表示部分特征,有效地区分车辆和非车对象,从而提高路口交通场景下车辆的检测准确率。通过量化评估实验和对比实验证明,该方法在存在大量非车对象的路口交通场景中可有效地检测车辆,并能够处理非车与车辆遮挡和车辆之间遮挡的问题。 3.针对城市交通场景中车辆尺度变化带来的车辆检测率较低的问题,本文开展了针对多尺度车辆的检测方法研究。提出了多尺度AOG车辆检测方法,构建多尺度与或图模型表示和检测车辆,利用全局特征描述低尺度车辆,局部特征描述高尺度车辆,并使用多种特征描述子表示全局和局部特征,最后利用与或图模型组合局部特征和全局特征,实现基于双重特征的多尺度车辆检测。经过量化评估和对比实验证明,该方法可以在存在多尺度车辆的城市交通场景中实现有效的车辆检测,并能够处理车辆遮挡。 综上所述,本文针对城市交通场景中基于图像的车辆检测方法所遇到的问题开展研究工作,以与或图模型作为研究手段,提出多个车辆检测方法提...
Other AbstractWith the widely application of high-definition cameras in intelligent transportation system and the rapid development of image processing technology, image-based vehicle detection technology has become one of the most important vehicle detection techniques. Currently the image-based vehicle detection methods are extensively studied and their detection accuracies continue to increase. However, vehicle detection methods in urban traffic scene face some challenges: 1) vehicle occlusion. The traffic congestion causes vehicle occlusion which leads to inaccurate vehicle positioning. 2) non-vehicle object interference. In urban traffic scene, especially at the intersection, there are lots of non-vehicle objects, such as pedestrians, non-motor vehicle, etc. These objects degrade the performance of vehicle detection methods. 3) multi-scale vehicles. The image size, clarity and viewing angle of a vehicle are different when the vehicle is at different distances from the camera. We call this phenomenon a multi-scale problem, which has posed a challenge for vehicle detection due to the time varying nature of vehicle features. To circumvent above mentioned problems, in this thesis we propose several vehicle detection methods based on And-Or Graph (AOG). These methods can deal with the problems of vehicle occlusion, non-vehicle object interference and multi-scale vehicles,because the AOG utilizes compositional structure for vehicle representation and integrates structural, geometric, appearance, and probabilistic information for vehicle detection. The main contributions of this thesis are listed as follows: 1. To improve the performance of vehicle detection methods in processing vehicle occlusion, we develop a novel vehicle detection method called vAOG. In our method we construct a vehicle AOG to represent vehicle objects in urban traffic condition. Then we apply bottom-up inference to pursue vehicles in a traffic image. During the construction of vehicle AOG, we select the window and taillight as the vehicle features due to that they are often visible when vehicle occlusion occurs. Furthermore, we hierarchically decompose these features into smaller part-features. If a vehicle is occluded, there are still several part-features visible for detection. The constructed vehicle AOG can well describe the vehicles in occlusion condition. Finally, based on the vehicle AOG model we use bottom-up inference and combine detected part-features to detect the vehicles. The qua...
shelfnumXWLW1996
Other Identifier201118014628012
Language中文
Document Type学位论文
Identifierhttp://ir.ia.ac.cn/handle/173211/6594
Collection毕业生_博士学位论文
Recommended Citation
GB/T 7714
李叶. 城市交通场景下基于与或图模型的车辆检测方法研究[D]. 中国科学院自动化研究所. 中国科学院大学,2014.
Files in This Item:
File Name/Size DocType Version Access License
CASIA_20111801462801(11661KB) 暂不开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[李叶]'s Articles
Baidu academic
Similar articles in Baidu academic
[李叶]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[李叶]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.