CSR-DMSS,SM: Cooperative Activity Analysis in Wireless Smart-Camera Networks (Wi-SCaNs)

点击翻译按钮获取中文摘要

ABSTRACTWith the advances in the hardware technology and ever-decreasing cost of imaging circuitry, cameras have becomeubiquitous in our lives. The large amounts of video data generated by multiple cameras necessitate automaticanalysis of activities from video. With the introduction of smart cameras, it has now become viable to installmany spatially-distributed cameras interconnected by wireless links. A smart camera is a stand-alone unit thatnot only captures images, but also includes a processor, memory and communication interface. This projecttakes a holistic view of the problems that need to be solved to build scalable, battery-powered wireless smart-camera networks (Wi-SCaNs). It focuses on providing a unifying solution to perform tasks distributively, andcommunicate in a P2P fashion over wireless links while making e±cient use of limited resources, such as energyand bandwidth. This research explicitly considers the challenges of wireless channels, and addresses the issuesof scarce resources, P2P protocol design and channel usage priorities simultaneously. The expected outcomes ofthis project include light-weight vision algorithms that are portable to embedded smart cameras, characterizationof the energy-bandwidth-delay tradeo®s in Wi-SCaNs, e±cient resource allocation strategies, and P2P wirelesscommunication protocols that leverage the knowledge of the wireless channel conditions. The outcomes will havean important positive impact, because they will fundamentally advance the automatic activity analysis solutionsby providing installation of any number of cameras anywhere, and will ¯nd wide-ranging applications includingsurveillance in military, commercial or public scenarios, elderly care and wildlife monitoring.1