A bayonet vehicle retrieval system and method based on local features and deep learning
A local feature and deep learning technology, applied in the field of bayonet vehicle retrieval system, can solve the problems of not reaching the level of fine-grained vehicle retrieval and not being accurate enough
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0101] Embodiment: a kind of vehicle picture retrieval method based on local feature and deep learning, comprises the steps:
[0102] (1) extracting the image features of the image to be detected;
[0103] Image features can be global features or regional features, and can be extracted using deep neural networks or SIFT, SURF and other methods. The deep neural network includes Alexnet network, vgg network, GoogleNet network, etc. Specifically, the classic vgg16 network is used to extract vehicle features, the loss function is jointly trained with softmax and triple loss, and the last fully connected layer is extracted. The vector of 1000*1 dimension is used as global features. The SIFT method is used to extract the features of vehicle annual inspection marks and lights as local features.
[0104] (2) The product of the image feature of the image to be detected and the overall weight matrix is obtained to obtain the binary feature code of the image to be detected;
[0105]...
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