Integration method for depth feature and traditional feature based on AdaRank
A technology of deep features and integrated methods, applied in character and pattern recognition, instruments, computer components, etc., can solve the problem of low efficiency of pedestrian identity, achieve the effect of overall matching rate improvement, reasonable design, and good performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0039] Embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.
[0040] An ensemble method based on AdaRank-based deep features and traditional features, such as figure 1 shown, including the following steps:
[0041] Step 1. Segment the image data, and construct and train depth volumes and neural networks for different parts to obtain deep features. The specific implementation method is as follows:
[0042] The data is segmented according to the characteristics of the image, and the segmentation is based on different body parts of pedestrians. According to the principle of head, torso, and legs, each picture is divided into three parts of different sizes, which are used as three different training data, and the overall image is also used as a class of data. For these four different data, this method constructs four deep convolutional neural networks with slightly different structures. The cosine distanc...
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