Design and DSP Optimization of Real-time Multi-Camera Tracking

In recent years there is a dominanttrend towards the deploymentof advanced visual analysisalgorithms on embedded platforms. However, this deployment is very challenging as embedded systems usually afford limited resources such as calculating performance, memory and power. Therefore, to address this problem, In this paper we introduces anoptimized multi-camera tracking system based on multiple TI DSP TMS320DM6446for trackingobjects across multiple embedded smart cameras which embedsintelligent processors. Firstly, the overlapping areas and homography projection relations between adjacent cameras’ field of view is calculated. Based on the relations of cameras view obtained and tracked data of each single camera,a homography based target handover procedure is done for long-term multi-camera tracking.After that, we fully implemented the tracking system on the embedded smart cameras developed by our group.Finally, to combat the huge computational complexity, a novel hierarchical optimization method is proposed. Experimental results demonstrate the robustness and real-time efficiency in dynamic real-life environments and the computationalburden is significantly optimized by 98.84% which is low enough for further biometrics tasks such as recognition.