A Configurable Computing Approach Towards Real-Time Target Tracking

Traditionally, tracking systems require dedicated hardware to handle the computational demands and input/output rates imposed by real-time video sources. An alternative presented in this paper uses configurable computing machines, which use interconnected FPGAs to provide fine-grain parallelism and reconfigurability so that high-speed performance is possible for many different applications. The efficacy of such architectures to image-based computing is illustrated here through the implementation of a tracking system that consists of two parts: a Gaussian pyramid generator and a correlation-based tracker. The pyramid generator converts each input image to a hierarchy of images, each representing the original image at a different resolution. An object is tracked on successive frames by a coarse-to-fine search through this image hierarchy, using the sum of absolute differences as the matching criterion. Splash 2 performs these operations at rates of 15 or 30 frames per second. Its perform...

• Type: Conference
• Year: 1998
• Where: IPPS
• Authors: Bharadwaj Pudipeddi, A. Lynn Abbott, Peter M. Athanas
• Keywords: Distributed And Parallel Computing, Gaussian Pyramid Generator, IPPS 1998, Pyramid Generator, Tracking System