Siamese network-based method for pedestrian re-identification
A pedestrian re-identification and network technology, applied in the field of pedestrian re-identification, can solve the problems of low reliability of results, increase the workload of manual research and judgment, reduce the degree of automation of video analysis, etc., achieve the effect of reducing query time and improving the degree of discrimination
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0031] The present invention uses a pre-trained ResNet-50 network to perform feature extraction on images. In order to measure the degree of similarity between images, two identical ResNet-50 networks are used to form a Siamese network, and then a training data set is used to perform this Siamese network. Training, this Siamese network can classify the input image labels, and can also complete the measurement of the similarity between two images.
[0032] Combine Figure 1~2 , The method for pedestrian re-identification based on Siamese network of the present invention includes the following steps:
[0033] Step 1: Pre-training the ResNet-50 network: Use the ImageNet data set as the training data set to train a ResNet-50 network so that the ResNet-50 network has an ideal initial value; the ideal initial value refers to the ability to learn image features ;
[0034] Step 2: Fine-tune the ResNet-50 network: Replace the softmax output layer of the ResNet-50 network with a convolutiona...
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