Road scene semantic segmentation method based on category grouping in abnormal weather
A semantic segmentation and abnormal weather technology, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve problems such as inability to complete, not considering the importance of categories, and not considering the importance of categories to tasks, etc., to ensure safety Good effect of sex and segmentation effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0047] The overall operation process of the present invention is as figure 1 shown. Below in conjunction with the description of the accompanying drawings of specification 4, the present invention is described in detail:
[0048] Step 1: Prepare data; prepare data under abnormal weather as training set and test set. Using the method of rain and fog simulation generation to generate rain and fog weather data on the Cityscapes dataset, and at the same time obtain two real scene datasets under abnormal weather: BDD100K dataset and ACDC dataset. figure 2 Shown is the display of some data. The generated data set includes 4 types of rainy data of different intensities and 4 types of foggy data of different visibility.
[0049] Step 2: Group the road scene categories according to the importance of autonomous driving safety in abnormal weather to ensure that important categories are separated from non-important categories, and build a road scene semantic segmentation model based on...
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