Low-altitude remote sensing image high-precision matching method with consistent image space
A technology of image space, low-altitude remote sensing, applied in the field of low-altitude remote sensing image matching, can solve the problems of geometric deformation, easy failure, low matching success rate, etc.
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2014-11-05
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention relates to low-altitude remote sensing image matching, in particular to a low-altitude remote sensing image high-precision matching method with image square space consistency. Background technique
[0002] In recent years, from UAV remote sensing used in topographic surveying and mapping of the Diaoyu Islands, to disaster remote sensing monitoring and disaster assessment in the Lushan earthquake in Sichuan, to the normal monitoring of national marine resources, low-altitude remote sensing technology has highlighted its role in topographic surveying and mapping, disaster emergency monitoring and disaster situation assessment. Low-altitude remote sensing data processing technology has quickly become a research hotspot due to its advantages and application value in many fields such as assessment and environmental monitoring. Image matching is one of the key technologies of low-altitude remote sensing data processing, and its matching quality...
Examples
Embodiment Construction
[0009] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.
[0010] The high-precision matching method of low-altitude remote sensing images with consistent image space includes two core processes: initial image matching based on SURF features and precise image matching with geometric constraints. The two processes are described in detail below:
[0011] Based on the initial image matching of SURF features, the affine transformation relationship between the reference image and the search image is established. The SURF operator is a very well-known operator in the fields of computer vision and photogrammetry. It is widely used in many fields due to its anti-rotation and scale-invariant characteristics. Although SURF feature matching has the above-mentioned excellent characteristics, the algorithm itself ex...