Changsong Shen

Learn More
In this paper, we propose a multi-camera video surveillance system with automatic camera selection. A new confidence measure, Quality-Of-View (QOV), is defined to automatically evaluate the camera's view performance for each time instant. This measure takes into account view angle and distance from subjects. By comparing each camera's QOVs, the system can(More)
This paper presents our progress on OpenVL-a novel software architecture to address efficiency through facilitating hardware acceleration, reusability and scalability for computer vision. A logical image understanding pipeline is introduced to allow parallel processing. As well, we discuss our middleware-VLUT that enables applications to operate(More)
This paper presents an Open Source Vision Library (OpenVL) for hardware acceleration of video-based surveillance systems and other computer vision applications to facilitate low latency, real-time response. Our approach is inspired by the success of OpenGL in promoting the development of hardware acceleration for computer graphics. Our goal is to create(More)
  • 1