UAV Remote Sensing Image Rural Building Detection Based on Convolutional Neural Network

Xing CHEN, Jun-cheng WU, Meng-jiao ZHANG

Abstract


In order to improve the accuracy of intelligent detection of rural buildings, this paper uses massive remote sensing data of UAV to train convolutional neural network and improves CaffeNet model. Experimental results are as the followings: With reference to the traditional CaffeNet, the improved a-CaffeNet has an accuracy rate of 97.30%. The test time and the training time are shortened by 30.4% and 11.84% respectively. According to the experiments, this method is more suitable for remote sensing image of rural buildings detection.

Keywords


Convolutional neural network, UAV remote sensing image, Rural building, Detection


DOI
10.12783/dtetr/aemce2019/29502

Refbacks

  • There are currently no refbacks.