A Crowd Detecting and Tracking Algorithm Based on Projection of Grayscale Image

摘要

In this paper an effective algorithm is developed to detect and track multiple people in a specific area. It advances a target detecting algorithm based on projection of grayscale image, while specifies a value function uniting features which are relatively unchanged for target tracking. And the result indicates a system based on our algorithms needs relatively less operations while the precision and efficiency are improved and the system has a certain self-adaptive capability.