Adaptive online performance analysis of an fast and efficient video based tracking algorithm of rigid objects

Online object tracking plays major role in both Digital image processing and Medical image processing, where it is necessary to take an account of appearance change caused by intrinsic factors (e.g., pose variation and shape deformation) and extrinsic factors (e.g., varying illumination camera motion, and occlusions). Especially for the moving object, target is tracking by the sparse prototypes, an efficient technique which having the excellent updating capability by reducing the tracking drift, such as heavy occlusion and motion blur. The probable reduction of these drifts can be achieved by the conversion of low resolution image into high resolution image using the MAP estimation. Hence the sparse prototypes algorithm makes the moving object tracking in a wide range of applications in computer vision, such as surveillance, human computer interaction, and medical imaging. The initialized state (e.g., position and size) of the target in a frame and the goal of tracking is to estimate the states of the target in the subsequent frames.