An Efficient DSP Implementation of Real-Time Stationary Vehicle Detection by Smart Camera at Outdoor Conditions

The advent of third generation smart cameras has increased the use of digital video in the areas of defense and civil surveillance and transportation systems. Advances in processor architecture, coupled with improved image processing algorithms, have made it feasible to design and operate complex vision applications on a smart camera. This paper presents an efficient traffic-monitoring algorithm to detect stationary vehicles in varying environmental lighting conditions. Illumination invariance is achieved by using adaptive thresholds based on reflectance modeling. The algorithm is implemented on a DSP-based smart camera and optimized to run in real-time. We explain the different optimizations implemented to achieve real-time performance of nearly 30 frames per second along with extensive experimental results to prove the efficiency of the system.