Dangerous driving behavior recognition method, device and apparatus and storage medium
A dangerous driving and behavior technology, applied in the field of communication, can solve problems such as interfering with the driver's driving, failure to recognize the driver's dangerous driving behavior, and driver's driving behavior specification constraints, so as to achieve the effect of ensuring the safety of drivers and passengers
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0105] When a method for identifying a dangerous driving behavior provided by an embodiment of the present invention is applied to identify smoking behavior, one or more frames of images in the video data are analyzed to determine that the driver has dangerous driving behavior, such as figure 2 As shown, the method includes:
[0106] Step 201, extracting images of a first preset number of frames from the video data.
[0107] In a specific implementation, the first preset number may be set according to an empirical value or an actual scenario, for example, it may be set to 30 under normal circumstances.
[0108] Step 202: Determine whether the driver has smoking behavior in each frame of images.
[0109] In the specific implementation, for each frame of image, a pre-trained face key point model is used to segment the face area from the frame of image, which specifically includes: the position of the face and specific key areas of the face, such as eyebrows, mouth, Eyes, nose...
Embodiment 2
[0120] When a method for identifying dangerous driving behavior provided by the embodiment of the present invention is applied to identify the behavior of making and receiving calls, one or more frames of images in the video data are analyzed to determine that the driver has dangerous driving behavior, such as image 3 As shown, the method includes:
[0121] Step 301: Extract images of a second preset number of frames from the video data.
[0122] In a specific implementation, the first preset number may be set according to an empirical value or an actual scenario, for example, it may be set to 30 under normal circumstances.
[0123] Step 302: Determine whether the driver has a behavior of making and receiving calls in each frame of images.
[0124] In the specific implementation, for each frame of image, a pre-trained face key point model is used to segment the face area from the frame of image, which specifically includes: the position of the face and specific key areas of ...
Embodiment 3
[0136] When a method for identifying a dangerous driving behavior provided by an embodiment of the present invention is applied to identify fatigue driving behavior, one or more frames of images in the video data are analyzed to determine that the driver has dangerous driving behavior, such as Figure 4 As shown, the method includes:
[0137] Step 401 , extract any frame of image from the video data, and determine the sixth probability that the driver has fatigue driving behavior in the frame of image.
[0138] In the specific implementation, for each frame of image, a pre-trained face key point model is used to segment the face area from the frame of image, which specifically includes: the position of the face and specific key areas of the face, such as eyebrows, mouth, Eyes, nose, facial contours, etc.
[0139] The pre-trained mouth shape recognition model is used to analyze the mouth shape, including the judgment of closed mouth and open mouth, and determine the probabilit...
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