Two-Stage Object Detection for Autonomous Vehicles With VGG-16 Based Faster R-CNN

The implementation of object detection for autonomous vehicles is essential as it is necessary to identify common object on the street so proper response could be designed. While single stage object may be smaller in computations, two-stage object detection is preferred due to the ability to localize the object. In this paper, we propose to use Faster R-CNN with VGG-16 backbone for detections of object on the street. We evaluate the method with open image subset by selecting objects that are common on street. We explore several hyper-parameters setup such as learning rate and the number of ROI regions to find the optimum set-up. We found that the use of learning rate 10-6 with Adam optimizer to be the optimum value for this task. We also found that increasing the number of ROI may benefit the performance. This shows that there is potential for getting a higher mAP with increase the amount of RoI.