سامانه پشتیبانی خدمات اطلاعات

  اخبار و اعلانات

 آمار

تعداد نشریات162
تعداد شماره‌ها6,699
تعداد مقالات72,390
تعداد مشاهده مقاله129,665,725
تعداد دریافت فایل اصل مقاله102,400,707
Eftekhari, Akram, Samadzadegan, Farhad, DadrasJavan, Farzaneh. (1403). ChangeCoTNet : Building Change Detection by Contextual Transformer Deep Network. , 8(1), -. doi: 10.22059/eoge.2025.378306.1153
Akram Eftekhari; Farhad Samadzadegan; Farzaneh DadrasJavan. "ChangeCoTNet : Building Change Detection by Contextual Transformer Deep Network". , 8, 1, 1403, -. doi: 10.22059/eoge.2025.378306.1153
Eftekhari, Akram, Samadzadegan, Farhad, DadrasJavan, Farzaneh. (1403). 'ChangeCoTNet : Building Change Detection by Contextual Transformer Deep Network', , 8(1), pp. -. doi: 10.22059/eoge.2025.378306.1153
Eftekhari, Akram, Samadzadegan, Farhad, DadrasJavan, Farzaneh. ChangeCoTNet : Building Change Detection by Contextual Transformer Deep Network. , 1403; 8(1): -. doi: 10.22059/eoge.2025.378306.1153

ChangeCoTNet : Building Change Detection by Contextual Transformer Deep Network

Earth Observation and Geomatics Engineering
مقاله 1، دوره 8، شماره 1، شهریور 2024    اصل مقاله (796.94 K)
نوع مقاله: Original Article
شناسه دیجیتال (DOI): 10.22059/eoge.2025.378306.1153
نویسندگان
Akram Eftekhari* 1؛ Farhad Samadzadegan2؛ Farzaneh DadrasJavan3
1School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran
2School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran
3Dept. Of photogrammetry, School of Surveying and Geo Spatial Engineering, University of Tehran
چکیده
Building change detection (BCD) is a critical task in remote sensing, with applications in urban management and disaster assessment. However, achieving high accuracy in high-resolution BCD remains challenging due to the complexity of urban scenes. In this study, we propose ChangeCoTNet, a novel dual-branch deep learning model that integrates Contextual Transformer (CoT) blocks in the encoder and a Convolutional Neural Network (CNN) in the decoder. The CoT blocks enable the extraction of both static and dynamic contextual representations, while the Channel Attention Block (CAB) enhances discriminative feature extraction. The proposed model was implemented and evaluated on the LEVIR-CD and 2DCD datasets using a PyTorch backend. Experimental results demonstrate that ChangeCoTNet outperforms state-of-the-art methods, achieving F1-score improvements of 1.1% and 1.9% for the respective datasets. These results validate the effectiveness and efficiency of the proposed model in detecting changes with high precision and recall, making it a valuable tool for real-world applications.
کلیدواژه‌ها
Remote Sensing؛ Building Change Detection؛ Contextual Transformer؛ Dual branch Network؛ Self-Attention Mechanisms
آمار
تعداد مشاهده مقاله: 135
تعداد دریافت فایل اصل مقاله: 11





سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب