Color-Based Signal Light Tracking in Real-Time Video

Tracking or detecting the position and color of signal lights has an important role in transport industry. Auto detection of signal light colors and their position using computer vision techniques provides or acts as a proof against a fraudulent claim losses. The current technology, such as vehicle mounted recording system, provides event recognition videos and the cause behind an accident. But it does not provide the complete information about color associated with signal lights. The detection of the color of a signal light under different illuminations is a critical issue. In this research, an intelligent method for tracking color of signal lights using La*b* color model combined with contour tracking is proposed. This research finds application in transportation, law enforcement and insurance claims. The system increases the efficiency of the accident investigation process and reduces the economic loss associated with automobile accidents of all types.