Vehicle re-identification method based on capsule network
A re-identification and vehicle technology, which is applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve the problem that convolutional neural networks cannot extract spatial position information, feature vectors are not aligned, and improve recognition accuracy, Guarantee the effect of recognition effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0058] The applicant found in the research that the capsule network model uses vector output instead of scalar output, which can capture the spatial relationship between image features, thereby improving the limitations of convolutional neural networks. Based on the above findings, the applicant designed the following capsule network-based vehicle re-identification method.
[0059] like figure 1 As shown, a capsule network-based vehicle re-identification method includes the following steps:
[0060] S1: Obtain a vehicle image data set, and divide the vehicle image data set into a training set and a test set;
[0061] S2: Construct a capsule network model for vehicle re-identification;
[0062] S3: Optimize the capsule network model through the vehicle images in the training set;
[0063] S4: Input the vehicle images to be recognized and the vehicle images in the test set into the optimized capsule network model: first calculate the feature vectors of the vehicle images to b...
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