In recent years, according to the need of intelligent video surveillance system increasing rapidly in metropolitan cities ,a design based on $3C2440 microprocessor and embedded Linux operating system is adopted for re...In recent years, according to the need of intelligent video surveillance system increasing rapidly in metropolitan cities ,a design based on $3C2440 microprocessor and embedded Linux operating system is adopted for real-time video target tracking. However, it is very challenging as embedded systems usually afford limited processing power and limited resources. Therefore, to address this problem, a real-time tracking algorithm using multi-features based on compressive sensing is proposed and implemented The algorithm uses multiple matrix as the projection matrix of the compressive sensing and the compressed date as the multiple features to extract useful information needed by tracking process. Functions and libraries in OpenCV which were developed by Intel Corporation are utilized for building the tracking algorithms. It is tested with variant video sequences and the results show that the algorithm achieves stable tracking for the target moved of the light changed.展开更多
文摘In recent years, according to the need of intelligent video surveillance system increasing rapidly in metropolitan cities ,a design based on $3C2440 microprocessor and embedded Linux operating system is adopted for real-time video target tracking. However, it is very challenging as embedded systems usually afford limited processing power and limited resources. Therefore, to address this problem, a real-time tracking algorithm using multi-features based on compressive sensing is proposed and implemented The algorithm uses multiple matrix as the projection matrix of the compressive sensing and the compressed date as the multiple features to extract useful information needed by tracking process. Functions and libraries in OpenCV which were developed by Intel Corporation are utilized for building the tracking algorithms. It is tested with variant video sequences and the results show that the algorithm achieves stable tracking for the target moved of the light changed.
