An intelligent image annotation method based on YOLOv3 depth learning network
A deep learning network and image technology, applied in still image data retrieval, metadata still image retrieval, special data processing applications, etc., can solve the problems of other targets that cannot obtain high labeling accuracy, poor portability, etc., to reduce The effect of subjective initiative, improved performance, and reduced complex workload
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example
[0039] Example: Annotate image data containing various types of vehicles and pedestrians
[0040] Based on the YOLOv3 deep learning network, combined with the image intelligent labeling method proposed by the present invention, figure 2 (a) and (b) are the actual pictures of the application example of image intelligent labeling for the YOLOv3 deep learning network training model for updating two sets of image data. The numbers in the figure correspond to the category numbers, for example, the number 2 corresponds to the target category "car", and the number 7 corresponds to the target category "truck"; image 3 (a) and (b) are the actual pictures of the application example of image intelligent labeling for the YOLOv3 deep learning network training model for updating 6 sets of image data. Similarly, the numbers in the figure correspond to the category numbers, for example, the number 2 corresponds to the target category "car" , the number 7 corresponds to the target category ...
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