透過您的圖書館登入
IP:18.191.102.112
  • 期刊

High-resolution Remote Sensing Image Classification based on Adaptive Bandwidth with Mean Drift Method

摘要


In this paper, based on the image element shape index, we introduce the object-oriented idea and improve the mean drift method with adaptive bandwidth to extract images with high spatial resolution, and the classification results obtained by using this method show that it is better than the image element shape index method in terms of accuracy and visual effect, which makes the image extraction better.

參考文獻


Comaniciu D, Meer P. Mean Shift: a Robust Approach Toward Feature Space Analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5) :603-619.
Dixon B, Candade N. Multispectral Landuse Classification using Neural Networks and Support Vector Machines: One or the Other or Both?[J]. International Journal of Remote Sensing, 2008, 29(4):1185-1206.
Mathur A, Foody G M. Multiclass and Binary SVM Classification: Implications for Training and Classification Users[J]. IEEE Geo-science and Remote Sensing Letters, 2008 5(2) :241-245.
Shen Zhanfeng, Luo Jiancheng, Hu Xiaodong, et al. Research on multi-scale mean drift segmentation algorithm for high-resolution remote sensing images[J]. Journal of Wuhan University (Information Science Edition), 2010, 35(3) :313-316.
Wang, Lei-Guang, Zheng, Chen, Lin, Li-Yu, et al. A fast segmentation method based on multiscale mean drift for high-resolution remote sensing images[J]. Spectroscopy and Spectral Analysis, 2011, 31(1): 177-183.

延伸閱讀