Image processing performance of a digital signal processing system for guidance control of Automated Transit Vehicles

This paper presents a study on the performance of processing images from a CCD camera using digital signal processing systems for guidance control of Automated Transit Vehicles (ATVs). The processing speed and quality of the image are the two important factors for guidance control of automated transit vehicles using CCD vision. The quality of the processed image depends on the image processing algorithm and enhancement techniques employed. Several algorithms have been experimented and their performance comparison is provided. In order to achieve the required processing performance a network of TMS320C40 parallel processors are experimented. The paper presents several topologies experimented to process these images in real-time. A frame rate of 16.5 is achieved with one of the topologies.