High-resolution remote sensing scene classification method based on multi-scale CENTRIST characteristics
A scene classification, multi-scale technology, applied in scene recognition, instrument, character and pattern recognition, etc., can solve the problems of high classification accuracy and less than ideal classification accuracy, and achieve the effect of good discrimination and robustness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0035] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:
[0036] Although CENTRIST can extract the texture features of the image, because its neighborhood size is only 3×3, it is not enough to fully express the texture features of a larger area. How to effectively describe the texture features of a larger area and how to integrate multi-scale information is a problem Questions to consider.
[0037] image 3 It is a flow chart of remote sensing scene classification based on multi-scale CENTRIST features. Based on the above ideas, the present invention first divides remote sensing images into several sub-images by using spatial pyramids, and then uses multi-scale CENTRIST for feature extraction and concatenation of each sub-image. It is represented as multi-scale CENTRIST features, and finally the multi-scale CENTRIST features of different sub-images are concatenated to form the overall feature of the imag...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


