RPV-II: A Stream-Based Real-Time Parallel Vision System and Its Application to Real-Time Volume Reconstruction

In this paper, we present RPV-II, a stream-based real-time parallel image processing environment on distributed parallel computers, or PC-cluster, and its performance evaluation using a realistic application. The system is based on our previous PC-cluster system for real-time image processing and computer vision, and is designed to overcome the problems of our previous system, one of which is long latency when we use pipelined structures. This becomes a serious problem when we apply the system to interactive applications. To make the latency shorter, we have introduced stream data transfer, or fine grained data transfer, to RPV-II. One frame data is divided into small elements such as pixels, lines and voxels, and we have developed efficient real-time data transfer mechanism of those. Using RPV-II we have developed a real-time volume reconstruction system by visual volume intersection method, and we have measured the system performance. Experimental results show better performance than that of our previous system, RPV.