For sensing system, the trustworthiness of the variant sensors is the crucial point when dealing with advanced driving assistant system application. In this paper, an approach to a hybrid camera-radar application of vehicle tracking is presented, able to meet the requirement of such demand. Most of the time, different types of commercial sensors available nowadays specialize in different situations, such as the ability of offering a wealth of detailed information about the scene for the camera or the powerful resistance to the severe weather for the millimeter-wave radar. Thus, the work here that combines the variant information provided by different sensors is indispensable and worthwhile. For the real-time requirement of merging the measurement of automotive millimeter-wave radar with high detection speed, this paper first proposes a fast vehicle tracking algorithm based on image perceptual hash encoding and the concomitant tracking drift problem is addressed by taking the advantage of the radar measurement. Then, the problem that two targets with minor azimuth angle difference cannot be separated accurately by the automotive radar is solved by using the image information provided by the camera, which enhances the radar angular resolving power to some extent. Finally, a camera-radar data fusion procedure is designed for achieving a more accurate and reliable co-tracker. A series of experiment indicate that the proposed tracking algorithm is feasible, effective and fast. The tracking drift defect is well made up by the use of radar measurement with few extra time consuming. Plus, the ability of radar separating closed targets have been further strengthened integrating the image information and the hybrid tracking outcome is more reliable, accuracy and robust.