The content of this article comes from the "Surveying and Mapping Bulletin" No. 6 in 2024, drawing review number: GS Jing (2024) No. 1024
Quantum multi-scale fusion of high-resolution satellite images for building change detection
ZHANG Yanping1, ZHANG Ka2,3,4,5, ZHAO Like6,7, TAO Xia2,3, ZHANG Bang8, WANG Yujun6,7, GU Zhen2,3, LIU Haolin2,3
1. Jiangsu Surveying and Mapping Product Quality Supervision and Inspection Station, Nanjing, Jiangsu 210013, China; 2. Key Laboratory of Virtual Geographic Environment, Ministry of Education, Nanjing Normal University, Nanjing 210023, Jiangsu, China; 3. School of Geographical Sciences, Nanjing Normal University, Nanjing, Jiangsu, 210023; 4. Jiangsu Collaborative Innovation Center for Geographic Information Resources Development and Utilization, Nanjing, Jiangsu, 210023; 5. Zhenjiang Jingqin Surveying and Mapping Co., Ltd., Zhenjiang 212009, Jiangsu, China; 6. Jiangsu Institute of Geological Survey, Nanjing 210018, Jiangsu, China; 7. Jiangsu Satellite Application Technology Center of Natural Resources, Nanjing, Jiangsu, 210018; 8. Suzhou Fire and Rescue Detachment, Suzhou 215000, China
Funds: National Natural Science Foundation of China (42271342; 42071301); Jiangsu University Advantageous Discipline Construction Project (164320H116)
Key words: high-resolution satellite imagery, building change detection, quantum theory, iterative slow feature analysis, multi-scale fusion
Citation format: ZHANG Yanping, ZHANG Ka, ZHAO LIKE, et al. Detection of Building Change in High-resolution Satellite Images with Quantum Multi-scale Fusion[J]. Bulletin of Surveying and Mapping, 2024(6): 65-70.doi: 10.13474/j.cnki.11-2246.2024.0612
Abstract:In order to improve the accuracy of the traditional pixel-based high-resolution satellite image change detection method, this paper proposes a high-resolution satellite image building change detection algorithm based on quantum multi-scale fusion. Firstly, the multi-scale segmentation of dual-phase high-resolution satellite images was carried out to form a multi-scale image dataset. Then, the multi-scale image dataset was transformed by iterative slow feature transformation to obtain the change intensity map of different scales, and then the multi-scale change intensity map was fused by quantum theory to obtain the fused change intensity map. Finally, the threshold segmentation of the change intensity map was completed by the maximum between-class variance method, and the binary change detection results were obtained. Using two sets of actual high-resolution satellite images of different time phases, the proposed algorithm is experimentally verified. The experimental results show that compared with the single-scale object-oriented change detection method and the entropy-weight method multi-scale fusion method, the proposed algorithm can achieve higher building change detection accuracy.
About author:ZHANG Yanping (1981—), male, master, senior engineer, mainly engaged in research work in geographic information processing. E-mail:[email protected] Corresponding author: Zhang Ka. E-mail:[email protected]
First instance: Yang Ruifang review: Song Qifan
Final Judge: Jin Jun
information