Study of object detection based on Faster R-CNN

Faster R-CNN (R corresponds to “Region”) which combined the RPN network and the Fast R-CNN network is one of the best ways to object detection of R-CNN series based on deep learning. The proposal obtained by RPN is directly connected to the ROI Pooling layer, which is a framework for CNN to achieve end-to-end object detection. The feasibility of Faster R-CNN implementation of ResNet101 network and PVANET network is discussed based on the implementation of Faster R-CNN in VGG16 network. Different Faster R-CNN models can be obtained by training with deep learning framework of Caffe. A better model can be obtained by comparing the experimental results using mean average precision (mAP) as an evaluation index. Numerical results show that Faster R-CNN trained by PVANET network obtained the highest mAP.