Object random walk-based visual saliency detection method and system for remote sensing image
A technology of remote sensing image and detection method, which is applied in the field of image processing, and can solve problems such as unfavorable, blurred edges of prominent areas, and too many nodes set
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0081] The technical scheme of remote sensing image visual saliency detection based on object random walk proposed by the present invention first performs multi-scale segmentation on the original remote sensing image, and merges adjacent regions with similar color characteristics at each scale to obtain multiple scale segmentations As a result, for the segmentation results at each scale, the visual features of each segmented region are extracted, and the image object set at the current scale is constructed. Then, for the object set at each scale, the corresponding feature difference between objects is calculated. Edge weights, and then calculate the transition probability of FOA between objects, obtain the transition probability matrix of FOA, and then calculate the smooth distribution of FOA among all objects according to the transition probability matrix of FOA, and further use the probability corresponding to each object in the smooth distribution Calculate its visual salien...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com