Multi-scale pedestrian re-identification method based on multi-granularity depth feature fusion
A pedestrian re-identification, deep feature technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as occlusion interference, pedestrian posture changes, and low recognition rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0047] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings.
[0048] The present invention designs a multi-scale pedestrian re-identification method based on multi-grain depth feature fusion, such as figure 1 As shown, the steps are as follows:
[0049] Step 1: Select the pedestrian re-identification data set, and preprocess the training set in the data set;
[0050] Step 2: Select the residual network as the basic skeleton, including the global coarse-grained fusion learning branch, the local coarse-grained fusion learning branch, and the local attention fine-grained fusion learning branch;
[0051] Step 3: Use the global coarse-grained fusion learning branch to learn the multi-level coarse-grained feature information of pedestrians;
[0052] Step 4: Use the local coarse-grained fusion learning branch to extract the local features of pedestrians in the local area;
[0053] Step 5: Use the local at...
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