ICD: VHR-oriented interactive change detection algorithm
In recent years, deep learning has become the mainstream development direction in the change detection field, and its accuracy and speed have also reached a high level. However, the change detection method based on deep learning cannot predict all the change areas accurately, and its application is limited due to local prediction defects. For this reason, we propose an interactive change detection network (ICD) for very high resolution (VHR) based on a deep convolution neural network. The network integrates positive and negative click information in the distance layer of the change detection network, and users can correct the prediction defects by adding clicks. We carried out experiments on the open source dataset WHU and LEVIR-CD. By adding clicks, their F1-scores can reach 0.920 and 0.912, respectively, which are 4.3% and 4.2% higher than the original network. To better evaluate the correction ability of clicks, we propose a set of evaluation index—click correction ranges, which is suitable for evaluating clicks, and we carry out experiments on the above models. The results show that the method of adding clicks can effectively correct the prediction defects and improve the result accuracy.
National Natural Science Foundation of China under Grant 42201504 and 41471318, Open Foundation of Key Lab of Virtual Geographic Environment of Ministry of Education (No. 2021VGE02)
Email Address of Submitting Author201302090@njnu.edu.cn
ORCID of Submitting Author0000-0003-4734-5535
Submitting Author's Institution1.School of Geographic Sciences, Nanjing Normal University, China; 2.School of Geography and Bioinformatics, Nanjing University of Posts and Telecommunications, China; 3.Nanjing Guotu Information Industry Co., Ltd.,China
Submitting Author's Country