TRICam - An Embedded Platform for Remote Traffic Surveillance

In this paper we present a novel embedded platform, dedicated especially to the surveillance of remote locations under harsh environmental conditions, featuring various video and audio compression algorithms as well as support for local systems and devices. The presented solution follows a radically decentralized approach and is able to act as an autonomous video server. Using up to three Texas InstrumentsTM TMS320C6414 DSPs, it is possible to use high-level computer vision algorithms in real-time in order to extract the information from the video stream which is relevant to the surveillance task. The focus of this paper is on the task of vehicle detection and tracking in images. In particular, we discuss the issues specific for embedded systems, and we describe how they influenced our work. We give a detailed description of several algorithms and justify their use in our implementation. The power of our approach is shown on two real-world applications, namely vehicle detection on highways and license plate detection on urban traffic videos.