Object proposals detection
Tang Pei, Xiaoyu Wu · 2016
Object detection is one of the most foundational tasks in computer vision, state-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Although advances like SPPnet, RCNN and Fast R-CNN have improved a lot which is widely used in the fields of object detection, exposing region proposal computation and time consuming as bottleneck. Faster-RCNN born precisely to solve this problem, is an improvement on the original R-CNN designed to speed up the detection network. So we apply the Faster R-CNN to train a detector to rank a pool of proposals for faster evaluation which have reduced the running time of the detection network and performed better.