Signboard identification method and device for automatic driving
An automatic driving and signage technology, applied in the field of navigation, can solve the problems of positioning technology error, position deviation of signboard apex, inability to accurately identify signboards, etc., and achieve the effect of improving accuracy, avoiding too small, and optimizing reliability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0051] Example 1:
[0052] figure 1 It is a flow chart of the identification card identification method for automatic driving as shown in the embodiment of the present application.
[0053] See figure 1 , An identification method for automatic driving, including:
[0054] In step S101, the bound border frames of the identifier card and the plurality of vertices of the bounding box are obtained.
[0055] In one embodiment, the automatic driving vehicle is provided with a photographing device, including, but not limited to, a single-grade camera. Single-graphic camera is disposed at a suitable location of the vehicle, for example, a single-grade camera may be disposed at the front windshield of the vehicle or disposed at the rear view of the vehicle so that the vehicle automatic travel process single camera can shoot including road signage. image.
[0056] In one embodiment, the plurality of vertices of the bounding box and the bound boxes of the identifier card can be obtained by ...
Example Embodiment
[0069] Example 2:
[0070] figure 2 Another process diagram of the identification card identification method for automatic driving as shown in the embodiment of the present application.
[0071] See figure 2 , An identification method for automatic driving, including:
[0072] In step S201, a plurality of vertices of the bounding box of the identifier card and the boundary box are obtained.
[0073] This step can be found in the description of step S101, and details will not be described here.
[0074] In step S202, according to the boundary box of the identification card, the image including the N pixel width outside the boundary frame is acquired, and n is a positive intent of the statistical pixel offset error value greater than the boundary frame identified by the depth learning model.
[0075] In one embodiment, if Figure 4 As shown, the depth learning model does not fully contain the entire identification card according to the bottom right corner of the boundary block 401 o...
Example Embodiment
[0091] Example 3:
[0092] image 3 Another process diagram of the identification card identification method for automatic driving as shown in the embodiment of the present application.
[0093] See image 3 , An identification method for automatic driving, including:
[0094] In step S301, the bound border of the identifier card and the plurality of vertices of the boundary box are obtained.
[0095] This step can be found in the description of step S101, and details will not be described here.
[0096] In step S302, according to the boundary box of the identification card, the image including the N pixel width of the boundary frame is acquired, and n is a positive intent of the statistical pixel offset error value of the bounding frame that is greater than the depth learning model recognition.
[0097] This step can be found in the description of step S202, and details will not be described here.
[0098] In step S303, a plurality of corner blocks are generated on the image, each c...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap