一种自适应视频跟踪算法及其ARM DSP实现

视觉跟踪作为图像处理和计算机视觉学科的重要分支,广泛应用与军事和民事的各个领域。对于相对运动速度较快的对象,传统的光流法计算精度不高,本文提出了一种视频跟踪算法,首先通过差分法检测图像差异,然后通过光流法实现视频自适应跟踪功能。设计了基于ARM和DSP的视频跟踪装置,详细讨论了硬件平台和接口设计,以S3C2410作为主控模块、TM320芯片作为图像处理模块。实验结果证明,该算法具有实时性、精度高、灵活性强的优点。

Adaptive algorithm for video tracking and realization on ARM+DSP system

AS an important branch of image processing and computer vision, video tracking is widely applied in military and civilian application. the Original optical flow method can not satisfy the requirement in accuracy for the object which has large relative velocity, A video tracking method is proposed, whether there is object by difference method, video tracking realized by optical flow algorithm. The ARM+DSP technology is used to video tracking device, and the design of the hardware platform and the interface is discussed, S3C2410 is used as the main module, the chip of TM420 is utilized as the video processing module. Experiments conducted that the algorithm has the advantages of high precision, strong flexibility and real-time performance.