Pedestrian detection method and system based on dynamic grouping convolution
A technology of pedestrian detection and convolution, applied in the field of neural networks, to achieve the effect of improving efficiency, increasing computing speed, and improving computing efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0055] This embodiment provides a pedestrian detection method based on dynamic grouping convolution, and the method is as follows:
[0056] S1. Obtain the behavioral data set, use the grouped convolution to construct the target detection network structure, and complete the initial training while retaining the original neural network structure; among them, the behavioral data set is collected according to the usage scene, and then uses manual annotation or intelligent annotation to obtain labels , complete the establishment of the data set; or use the public data set after screening to obtain and use; the pedestrian features included in the behavioral data set include the obvious features of the face, the characteristics of clothing and the corresponding features that need to be extracted according to the actual scene; the obvious features of the face include glasses; Clothing features including colour and style;
[0057] S2. Use the saliency score generator to calculate the sc...
Embodiment 2
[0080] This embodiment provides a pedestrian detection system based on dynamic grouping convolution, the system includes:
[0081] The building module is used to obtain the behavioral data set, use the grouped convolution to construct the target detection network structure, and complete the initial training while retaining the original neural network structure; among them, the behavioral data set is collected according to the usage scene, and then uses manual annotation or intelligent Label and obtain labels to complete the establishment of the data set; or use the public data set for screening and use; the pedestrian features included in the behavioral data set include obvious facial features, dressing features and corresponding features that need to be extracted according to the actual scene; obvious facial features including eyeglasses; clothing features including colour and style;
[0082] The sorting module is used to calculate the scores for the input channel and the out...
Embodiment 3
[0093] This embodiment also provides an electronic device, including: a memory and a processor;
[0094] Wherein, the memory stores computer execution instructions;
[0095] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method for pedestrian detection based on dynamic group convolution in any embodiment of the present invention.
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