Performance evaluation of faster R-CNN on GPU for object detection
B. Adam, Fadhlan Hafizhelmi Kamaru Zaman, Ahmad Ihsan Mohd Yassin, Husna Zainol Abidin, Zairi Ismael Rizman · Journal of Fundamental and Applied Sciences · 2018
This paper presents a performance evaluation of Faster Region Network method with different parameters to observe the mean average precision.Faster R-CNN replaces the previous proposal method with Region Proposal Network to complete the network.RPN predicts object bounds and its scores at each region making it a fully convolutional network.RPN produces almost cost shares fully image convolutional features with detection network.The use of this technique improve training and testing speed and mean average precision (mAP) compared to SPPnet.It can achieves approximately 10ms per image for object detection and time cost in region proposal.The dataset used to train and test is on VOC 2007.This technique is implemented in MATLAB R2017a using Caffe on NVidia GTX 1060 and GTX 1080.