{"title":"Motion pattern interpretation and detection for tracking moving vehicles in airborne video","authors":"Qian Yu, G. Medioni","doi":"10.1109/CVPR.2009.5206541","DOIUrl":null,"url":null,"abstract":"Detection and tracking of moving vehicles in airborne videos is a challenging problem. Many approaches have been proposed to improve motion segmentation on frame-by-frame and pixel-by-pixel bases, however, little attention has been paid to analyze the long-term motion pattern, which is a distinctive property for moving vehicles in airborne videos. In this paper, we provide a straightforward geometric interpretation of a general motion pattern in 4D space (x, y, vx, vy). We propose to use the tensor voting computational framework to detect and segment such motion patterns in 4D space. Specifically, in airborne videos, we analyze the essential difference in motion patterns caused by parallax and independent moving objects, which leads to a practical method for segmenting motion patterns (flows) created by moving vehicles in stabilized airborne videos. The flows are used in turn to facilitate detection and tracking of each individual object in the flow. Conceptually, this approach is similar to “track-before-detect” techniques, which involves temporal information in the process as early as possible. As shown in the experiments, many difficult cases in airborne videos, such as parallax, noisy background modeling and long term occlusions, can be addressed by our approach.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"58","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 IEEE Conference on Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CVPR.2009.5206541","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 58
Abstract
Detection and tracking of moving vehicles in airborne videos is a challenging problem. Many approaches have been proposed to improve motion segmentation on frame-by-frame and pixel-by-pixel bases, however, little attention has been paid to analyze the long-term motion pattern, which is a distinctive property for moving vehicles in airborne videos. In this paper, we provide a straightforward geometric interpretation of a general motion pattern in 4D space (x, y, vx, vy). We propose to use the tensor voting computational framework to detect and segment such motion patterns in 4D space. Specifically, in airborne videos, we analyze the essential difference in motion patterns caused by parallax and independent moving objects, which leads to a practical method for segmenting motion patterns (flows) created by moving vehicles in stabilized airborne videos. The flows are used in turn to facilitate detection and tracking of each individual object in the flow. Conceptually, this approach is similar to “track-before-detect” techniques, which involves temporal information in the process as early as possible. As shown in the experiments, many difficult cases in airborne videos, such as parallax, noisy background modeling and long term occlusions, can be addressed by our approach.
机载视频中运动飞行器的检测与跟踪是一个具有挑战性的问题。人们提出了许多方法来改进逐帧和逐像素的运动分割,然而,很少有人关注分析长期运动模式,这是机载视频中运动车辆的一个独特特性。在本文中,我们提供了四维空间(x, y, vx, vy)中一般运动模式的直接几何解释。我们建议使用张量投票计算框架来检测和分割四维空间中的这种运动模式。具体来说,在机载视频中,我们分析了视差和独立运动物体引起的运动模式的本质区别,从而得出了一种实用的方法来分割稳定机载视频中运动车辆产生的运动模式(流)。依次使用流来促进流中每个单独对象的检测和跟踪。从概念上讲,这种方法类似于“检测前跟踪”技术,它尽可能早地涉及到过程中的时间信息。实验表明,我们的方法可以解决机载视频中的许多困难情况,如视差、噪声背景建模和长期遮挡。