A Novel Method for Tracking Moving Objects using Block-Based Similarity

Extracting and tracking active objects are two major issues in surveillance and monitoring applications such as nuclear reactors, mine security, and traffic controllers. In this paper, a block-based similarity algorithm is proposed in order to detect and track objects in the successive frames. We define similarity and cost functions based on the features of the blocks, leading to less computational complexity of the algorithm. Therefore, this method is suitable for real-time tracking. According to the experimental results, this method has a good performance and works well for occluded objects, cluttered environments and noisy sequences.