Robust human detection and localization in security applications

Human detection and localization has attracted much attention in security applications because of the increasing demand of safety and security in different environments, including surveillance systems, secure access control, person recognition, border monitoring, preventing criminal acts, intrusion detection, alarm monitoring, and so on. This article proposes a robust approach for human detection and localization by analyzing and matching corresponding facial features extracted from video sequences. The proposed technique captures the video scenes using a stereo system consisting of two cameras: left and right cameras with similar intrinsic parameters. The system first tracks the human by detecting the face area from the video scenes using an efficient fuzzy face detection algorithm. To localize the human position, the depth information is computed from the extracted face images by using a robust stereo matching algorithm. A neural network is used to match the correspondence pixels between the left and the right face images. Experimental evaluation demonstrates the competence and robustness of the proposed method. The low computation time required for the detection and localization of human objects compared with other methods raises its suitability toward its use in real-time applications.