Spatial contextual feature plays an important role in high resolution remote sensing image. A new approach based on local variance analysis is introduced to spatial contextual feature extraction for change detection in this paper. In the proposed approach, the change magnitude between the paired central pixels of a local area (e.g., a 3 × 3 sliding window) in multitemporal images depends on surrounding pixels in the difference image, and this change magnitude is quantitatively measured based on the standard deviation of the difference image within the local area. This difference image contextual property may be useful particularly when high-resolution images are used. Finally, the change magnitude image is classified as a binary CD map by using SVM. This proposed approach is applied to SPOT-5 multitemporal datasets and two QuickBird multitemporal images from two case studies, which are quantitatively compared and validated. Experimental results show that the proposed approach is feasible.
[Zhong, Xiang; Hu, Chuli] China Univ Geosci, Fac Informat Engn, Wuhan 430074, Peoples R China.;[Hu, Chuli] China Univ Geosci, Natl Engn Res Ctr Geog Informat Syst, Wuhan 430074, Peoples R China.;[Xu, Jingyue] Cent China Normal Univ, Natl Res Ctr Cultural Ind, Wuhan 430074, Hubei, Peoples R China.
3rd International Conference on Agro-Geoinformatics (Agro-Geoinformatics)
AUG 11-14, 2014
Beijing, PEOPLES R CHINA
[Hu, Chuli] China Univ Geosci, Natl Engn Res Ctr Geog Informat Syst, Wuhan 430074, Peoples R China.^[Hu, Chuli;Zhong, Xiang] China Univ Geosci, Fac Informat Engn, Wuhan 430074, Peoples R China.^[Xu, Jingyue] Cent China Normal Univ, Natl Res Ctr Cultural Ind, Wuhan 430074, Hubei, Peoples R China.
International Conference on Agro-Geoinformatics
According to the feature of emergency event, we analyze the needed sensor collaborative planning requirements. In this paper, we propose the integrated query method for space-and ground-based sensors, including the organization and indexing of the sensor information resources, calculation of space-based sensor earth observation coverage and metadata item designation oriented to emergency collaborative observation. Based on the Java program platform and SensorML information model, we finally design and implement the integrated query tool GeosensorQuery. A real agriculture-related application on the flood emergency observation in the middle reaches of Yangtze River basin of China is conducted. The results verify the feasibility of our system.