LittleBrother: Vision Systems Supporting Detection of Offenders in Public Places.

目前的视觉监控系统只有在摄像头完全覆盖的情况下才能跟踪一个区域内的人。该项目将开发一种视觉监控系统，能够在只需要有限视觉覆盖的公共建筑中跟踪和记录人们的活动。我们将提出一种新的方法来匹配来自远距离摄像机的单个个体的图像，通过使用对不同身体部位、估计高度和构建类型分解的颜色直方图等特征。使用这些跟踪信息建立记录，将有效地支持保安人员在发生违法行为时识别责任方。

Current visual surveillance systems can track people in an area only if complete camera coverage is provided. This project will develop a visual surveillance system able to track and record people's movements in a public building requiring only limited visual coverage. We will propose novel ways of matching images of a single individual from distant cameras by using features such as color histograms decomposed for the different body parts, estimated height, and build type. Creating a record with this tracking information will effectively support security officers in the identification of responsible parties in the event of an offence.