摘要: |
This paper presents a vehicle tracking method which fuses data from image sensor and millimeter wave radar installed on the roadside. Image sensor is widely used for road monitoring systems, but it is difficult to detect a vehicle in poor visibility. On the other hand, millimeter waves are less attenuated by fog, rain, and snow. Consequently, it is prospective to detect vehicles in all weather by using millimeter wave radar together with image sensor. As for observation accuracy, image sensor is superior in the accuracy of angle measuring, but the accuracy of range measuring deteriorates. Millimeter wave radar is superior in the accuracy of range measuring, but is inferior in the accuracy of angle measuring. By utilizing these various features, therefore, the tracking performance is improved. This method has the correlation technique that uses a likelihood of range rate observed by radar, addition to a likelihood of position, so that this method be generally able to track the vehicles from observation vector even if false detection may occur. The performance of this method is evaluated by simulations and experiments on the Field Test Site. |