Joint Space-Time Analysis and Characterization of Image Sequences

图像序列的联合时空分析和表征

• 批准号: 0209055
• 负责人: Janusz Konrad
• 金额: $ 30万
• 依托单位: Trustees of Boston University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2002
• 资助国家: 美国
• 起止时间: 2002-07-01 至 2005-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0209055&HistoricalAwards=false
• 关键词: Joint; Space; Time; Analysis; Characterization

Janusz KonradBoston UniversityThis research is concerned with the processing of visual information captured by a video camera. To date, image sequences have been typically analyzed and processed in groups of two frames; by differentiating one frame from another, short-term image dynamics can be measured, such as changed areas (e.g., occlusions) or pixel displacements. Although the approach has been very successful to date (e.g., MPEG compression standards), further gains are difficult to attain based on two image frames only. This research project offers a different approach to the analysis of image sequences - one based on a joint processing of multiple image frames at a time. This joint treatment of, for example, 10 or 20 frames is expected to result in new gains in video compression, more reliable video database querying, and more accurate detection of innovations (occlusion and exposure areas) that are of interest in surveillance applications.The primary problem attacked in the project is the joint space-time segmentation of an image sequence into "object tunnels", i.e., 3-D volumes carved out in the space of horizontal, vertical and temporal coordinates by a moving object. The estimation of object tunnels is approached as a volume competition problem, and solved using active-surface evolution equations embedded into the level-set solution framework. In order to model motion of points within each object tunnel, a new spatially-parametric, temporally-quadratic motion model is studied. Various cost functionals relating object-tunnel intensities to the underlying motion are investigated. Since the standard volume competition can only extract a single moving object from background, an extension to more objects by means of multiple "repelling" surfaces evolving simultaneously is studied as well.

Janusz KonradBoston university这项研究是关于摄像机捕捉到的视觉信息的处理。迄今为止，图像序列通常以两帧为一组进行分析和处理；通过区分一帧与另一帧，可以测量短期图像动态，例如变化的区域（例如，遮挡）或像素位移。尽管该方法迄今为止已经非常成功（例如，MPEG压缩标准），但仅基于两个图像帧很难获得进一步的增益。这个研究项目提供了一种不同的方法来分析图像序列——一种基于一次对多个图像帧进行联合处理的方法。例如，这种对10帧或20帧的联合处理有望在视频压缩、更可靠的视频数据库查询以及更准确地检测监控应用中感兴趣的创新（遮挡和曝光区域）方面取得新的进展。该项目主要解决的问题是将图像序列的联合时空分割成“物体隧道”，即运动物体在水平、垂直和时间坐标的空间中雕刻出的三维体。目标隧道的估计被视为一个体积竞争问题，并使用嵌入在水平集解框架中的活动表面进化方程来求解。为了模拟每个目标隧道内点的运动，研究了一种新的空间参数化、时间二次化运动模型。研究了物体隧道强度与底层运动之间的各种代价函数。由于标准体积竞争算法只能从背景中提取单个运动物体，因此本文还研究了通过多个“排斥”面同时演化来扩展到更多物体的方法。