Real-time image processing for object detection at high frame rates requires a high-performance system. Its effectiveness in object recognition over a wide second). (4) Display the intermediate filtered frame outputs in real time (minimum 15 screen updates per 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



Proceedings of the Transputer Research and Applications Conference 7, Athens Georgia: October 23-25, 1994. Note: imported from RIT’s Digital Media Library running on DSpace to RIT Scholar Works in February 2014.

Document Type

Conference Proceeding

Department, Program, or Center

Computer Engineering (KGCOE)


RIT – Main Campus