No abstract

A human detection and tracking method using a stereo camera is presented in this paper. Two human detection methods are independently implemented, and the results are combined to reduce misdetection and nondetection. The tracking step is based on particle filtering. In the data association phase, we introduce three features: distance, traveling direction, and color. The color feature is obtained from every segmented detection window. Eligibility and co-occurrence of the blocks provide robustness to occlusion. The proposed method is tested by using measurement data at the entrance of a building, where occlusion is frequently observed. The experiments demonstrate improved tracking performance over standard particle filtering.

No abstract

No abstract

This paper proposes a method for automatic tracking of multiple humans in various scenes using a stereo camera.Surveillance cameras are increasing these days for security. Typically, images of a camera are stored and are surveyed after an incident occurred. It is required to use the cameras online, and real-time automatic human tracking is required.The proposed method detects candidate regions of humans using Subtraction Stereo , which restricts stereo matching to foreground regions extracted by subtraction and obtains distance information for the regions. Human tracking is carried out for the extracted regions by using Particle Filter. Particle Filter consists of four steps, i.e., prediction, calculation of likelihood, data association, and resampling. Three features: distance, color, and direction of motion are used in the Particle Filter of the proposed method to achieve robust human tracking. When humans with similar cloth colors pass each other, occlusion occurs and human tracking often fails with distance and color only. The proposed method achieves the robustness to the occlusion by explicitly considering the direction of human motion. The proposed method is evaluated through experiments using a stereo camera that simulates a surveillance camera in real scenes. Tracking accuracy of more than 90% is achieved in three different scenes, which shows the effectiveness of the proposed method for human tracking.