Accurate Object Detection Based on Faster R-CNN in Remote Sensing Imagery

Abstract

Object detection in remote sensing imagery is a fundamental and challenging problem for accurate object detection. Faster-regions convolutional neural network (Faster R-CNN) in remote sensing imagery has reduced the running time of the detection networks. But in the traditional method of convolutional neural network (CNN), the process is very slow it takes too much time. Nowadays, anchor boxes are widely adopted in the stage of model detection. This paper aims to provide a method to improve the detection accuracy in remote sensing imagery by using Faster R-CNN and its compatible Residual Network (ResNet). We compared the mean Average Precision (mAP) with the two backbone network ResNet-50 (Reference Backbone) and ResNet-101 (Proposed Backbone) with the same set of anchor ratio, we found that mAP achieves more than 1.376% significant improvement.