Driver Assistance System Using Image Processing & Pattern Recognition

During night time driving conditions in order to change vehicle head lights between low beams and high beams is required to avoid glares for the drivers. Accordingly, high beams output will be selected when no other traffic is present and will be turned on low beams when other vehicles are detected. This system uses a micro-camera mounted in the windshield area and looking at forward of the vehicle. Digital image processing techniques are used to analyze light sources and to detect vehicles in the images. The status of head light is automatically changed between low beams and high beams as per the night driving conditions to avoid glares for the driver. High beams output will be selected when no other traffic is present and low beam will be turned on when other vehicles are detected. The detected bright objects are recognized and classified using support vector machine (SVM) for vehicles light and other light. The distance between camera assisted vehicle and detected vehicle is also estimated using perspective projection technique. The key features of developed system are vehicle's bright light detection, classification and distance estimation.