Refining faster-RCNN for accurate object detection

Abstract

Object detector with region proposal networks such as Fast/Faster R-CNN [1, 2] have shown the state-of-the art performance on several benchmarks. However, they have limited success for detecting small objects. We argue the limitation is related to insufficient performance of Fast R-CNN block in Faster R-CNN. In this paper, we propose a refining block for Fast R-CNN. We further merge the block and Faster R-CNN into a single network (RF-RCNN). The RF-RCNN was applied on plate and human detection in RoadView image that consists of high resolution street images (over 30M pixels). As a result, the RF-RCNN showed great improvement over the Faster-RCNN.