A Sample Update-Based Convolutional Neural Network Framework for Object Detection in Large-Area Remote Sensing Images

This letter addresses the issue of accurate object detection in large-area remote sensing images. Although many convolutional neural network (CNN)-based object detection models can achieve high accuracy in small image patches, the models perform poorly in large-area images due to the large quantity of false and missing detections that arise from complex backgrounds and diverse groundcover types. To address this challenge, this letter proposes a sample update-based CNN (SUCNN) framework for object detection in large-area remote sensing images. The proposed framework contains two stages. In the first stage, a base model—single-shot multibox detector—is trained with the training data set. In the second stage, artificial composite samples are generated to update the training set. The parameters of the first-stage model are fine-tuned with the updated data set to obtain the second-stage model. The first- and second-stage models are evaluated using the large-area remote sensing image test set. Comparison experiments show the effectiveness and superiority of the proposed SUCNN framework for object detection in large-area remote sensing images.

I. Introduction

Object detection in optical remote sensing images involves the identification of the locations and class labels of predicted objects in satellite or aerial images. Object detection has a vital role in an extensive range of remote sensing applications, such as urban planning, environmental monitoring, and other civil and military applications [1].