Abstract
This paper proposes a fusion network for detecting changes between two high-resolution panchromatic images. The proposed fusion network consists of front- and back-end neural network architectures to generate dual outputs for change detection. Two networks for change detection were applied to handle image- and high-level changes of information, respectively. The fusion network employs single-path and dual-path networks to accomplish low-level and high-level differential detection, respectively. Based on two dual outputs, a two-stage decision algorithm was proposed to efficiently yield the final change detection results. The dual outputs were incorporated into the two-stage decision by operating logical operations. The proposed algorithm was designed to incorporate not only dual network outputs but also neighboring information. In this paper, a new fused loss function was presented to estimate the errors and optimize the proposed network during the learning stage. Based on our experimental evaluation, the proposed method yields a better detection performance than conventional neural network algorithms, with an average area under the curve of 0.9709, percentage correct classification of 99%, and Kappa of 75 for many test datasets.
Highlights
Change detection is a challenging task in remote sensing, used to identify areas of change between two images acquired at different times for the same geographical area
We found that the proposed algorithm can yield a better performance than existing algorithms by achieving an average area under the curve (AUC) of 0.9709, a percentage correct classification (PCC) of 99%, and a Kappa of 75 for several test datasets
The proposed method significantly outperformed the other algorithms with regard to the AUC for Areas 2 and 3 because it could properly detect the change events with the incorporation of low- and high-level differential features
Summary
Change detection is a challenging task in remote sensing, used to identify areas of change between two images acquired at different times for the same geographical area. A texture vector [11,12,13] is employed to extract statistical characteristics These changed features are fed into a classification or clustering algorithm to determine changed/unchanged pixels. The basic SVM can apply a binary classification to changed or unchanged pixels with texture information or using a change vector analysis These algorithms are not perfect in terms of incorporating accurate and full statistical characteristics for large multi-dimensional data. A Siamese convolutional network (SCN) [25,26,27] and dual-DCN (dDCN) [28] were proposed to detect changed areas by measuring the similarity with high-level network features These algorithms achieve a relatively good performance, false negatives are still observed.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
