Object Reacquisition and Tracking in Large-Scale Smart Camera Networks

Object reacquisition or reidentification is the process of matching objects between images taken from separate cameras. In this paper, we present our work on feature based object reidentification performed on autonomous embedded smart cameras and applied to traffic scenarios. We present a novel approach based on PCA-SIFT features and a vocabulary tree. By building unique object signatures from visual features, reidentification can be done efficiently coevally minimizing the communication overhead between separate camera nodes. Applied to large-scale traffic scenarios, important parameters including travel time, travel time variability, section density, and partial dynamic origin/destination demands can be obtained. The proposed approach works on spatially separated, un-calibrated, non-overlapping cameras, is highly scalable and solely based on appearance-based optical features. The entire system is implemented and evaluated with regard to a typical embedded smart camera platform featuring one single Texas Instruments trade fixed-point DSP.