Semantic segmentation method based on feature pyramid attention and mixed attention cascading
A feature pyramid and semantic segmentation technology, applied in the field of pattern recognition, can solve the problems of low segmentation accuracy, difficult to meet the requirements of segmentation accuracy, poor processing of segmentation target edge details, etc., to achieve the effect of optimizing processing and ensuring the speed of inference
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0055]A semantic segmentation method based on feature pyramid attention and hybrid level, specific steps are:
[0056]Step 1, build a semantic segmentation training set, specifically:
[0057]The image is preprocessed in the CITYSCAPES road data set, according to the RGB mean (0.485, 0.456, 0.406) and variance of the data set (0.229, 0.224, 0.225), the 2975-sheet binding is not a training set, 500 Zhang Jing label image as a verification set.
[0058]Step 2, build a deep convolutional neural network, the overall structurefigure 2 Down:
[0059]The depth convolutional neural network includes an encoder portion, a feature pyramid focus module, a mixing focus module, a feature fusion portion, a decoding branch.
[0060]In a further embodiment, the encoder portion uses the structure in existing mobilenetv2, such asimage 3 A shows that the present invention has made adjustments to use as a semantic segmentation task, such asimage 3 b. In the table, the number of output channels, T represents the expans...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap