Real-time image processing for object detection at high frame rates requires a high-performance system. Its effectiveness in object recognition over a wide range of image characteristics is proportional to its provision for varying signal processing techniques. Thus, a system designed to exhibit high performance with respect to one particular type of image and object can not be expected to prove suitable for images or objects with different characteristics. Therefore to detect different types of objects at high frame rates over a range of image characteristics, a system must offer a variety of signal processing techniques. Since general-purpose processors fall short of the performance needed in providing the necessary variety and combination of signal processing techniques, an object detection system has been designed and is being built using VLSI implementations of the signal processing techniques.
Date of creation, presentation, or exhibit
Department, Program, or Center
Computer Engineering (KGCOE)
Melton, Roy; Alford, Cecil; Huang, Tsai; and Becker, Latika, "A VLSI system implementation for real-time object detection" (1996). Accessed from
RIT – Main Campus