Deep-learning-based pedestrian re-identification method
A deep learning and re-identification technology, applied in the field of pedestrian re-identification, can solve the problems of feature expressiveness and discriminative limitation, and the reduction of matching effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0035] Example
[0036] Such as figure 1 As shown, the pedestrian re-identification method based on the deep convolutional neural network of the present invention includes the following steps:
[0037] S1. Propose a deep network structure suitable for pedestrian re-identification. The deep network structure adopts an eight-layer structure, including five convolutional layers and three fully connected layers. The deep network takes a pair of pedestrian images as input and directly Obtain their similarity scores from the bare pixels of the original image. There is no need to do any preprocessing of the original image, and no need to manually design complex features and descriptors.
[0038] Such as figure 2 As shown, the convolution kernel of the first five layers of convolutional layers can be regarded as multiple local feature detectors, starting from the bare pixels of the input image, extracting and obtaining robustness to illumination, posture, camera angle changes, etc. featur...
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