Paper
9 October 2009 Analysis of land cover changes using multisource and multitemporal images in loess hilly and gully regions
Dongchuan Wang, Jianhua Gong, Lihui Zhang, Qixiang Lei, Quanyi Cao
Author Affiliations +
Proceedings Volume 7471, Second International Conference on Earth Observation for Global Changes; 74710D (2009) https://doi.org/10.1117/12.836470
Event: Second International Conference on Earth Observation for Global Changes, 2009, Chengdu, China
Abstract
Land use/cover change (LUCC) is one of the most sensitive factors that show the interactions between human activities and ecological environments. In loess hilly and gully regions, to prevent soil loss and achieve better ecological environments, soil conservation measures have been taken during the past decades. This research attempts to detect land cover changes of Xihe ecological demonstration region by supervised classification to evaluate the effect of soil conservation measures. Support Vector Machines (SVM) classifier was applied for its ability to produce reliable classifications using small training samples. RBF kernel was finally employed for it nonlinearly maps samples into a higher dimensional space. Multi-source images of about one and a half decades were acquired for change detection, including Landsat TM and ETM+, CBERS2B CCD images. To minimize seasonal impacts, post-classification comparison method was employed for image processing. Unified land use classification plan was set up for all the images. The accuracy of classification was evaluated using more than 300 ground truth points mainly identified from high resolution Quickbird and CBERS2B HR images. The trend of land cover changes were detected and analyzed, and the relationship between land cover changes and human activities have been probed preliminarily. Result shows the ecological environments of the study area had deteriorated to a large extent in the first period, while were greatly bettered in the second period and controlling human activities or consciously exerting active human activities is an effective way to improve ecological environments.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Dongchuan Wang, Jianhua Gong, Lihui Zhang, Qixiang Lei, and Quanyi Cao "Analysis of land cover changes using multisource and multitemporal images in loess hilly and gully regions", Proc. SPIE 7471, Second International Conference on Earth Observation for Global Changes, 74710D (9 October 2009); https://doi.org/10.1117/12.836470
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image classification

Soil science

Earth observing sensors

Landsat

Environmental sensing

Image resolution

Charge-coupled devices

Back to Top