Front object recognition system for vehicles based on sensor fusion using stereo vision and laser range finder

This paper proposes a front object recognition system for the safety of driving, which is based on sensor fusion with laser range finder and stereo vision. The study utilizes a stereo vision system for objects detection. Since the calculation time of the stereo vision algorithm is too long, in order to detect objects immediately, a laser range finder is integrated to improve the calculation time and detection accuracy. On the completion of the detection stage, the support vector machine is used to recognize the objects. The experimental results show that the objects detection system yields an accuracy rate of 95%.