Training method, recognition method and device for driver behavior recognition model
A technology for identifying models and training methods, applied in the field of image processing, which can solve problems such as low efficiency of driver behavior detection, achieve the effect of avoiding sample imbalance, small picture size, and ensuring sample balance
Active Publication Date: 2022-07-01
SUZHOU KEDA TECH
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In view of this, the embodiment of the present invention provides a driver behavior recognition model training method, recognition method and device to solve the problem of low detection efficiency of existing driver behavior
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0063] In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.
[0064] It should be noted that, the driver behavior recognition model provided by the embodiment of the present invention is used to recognize whether the driver has a preset behavior. For example, if the samples used to train the model are images of drivers looking at their phones and images of drivers not looking at their phones, then the t...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to the technical field of image processing, in particular to a training method, a recognition method and a device for a driver behavior recognition model. The training method includes acquiring a positive sample image and a negative sample image to obtain a training data set and a test data set; The driver behavior recognition model is compressed to obtain the first driver behavior recognition model; the first driver behavior recognition model is trained by using the training data set to obtain the second driver behavior recognition model, and the second driver behavior recognition model is obtained by using the test data set. The accuracy of the behavior recognition model is checked to obtain the accuracy of the second driver behavior recognition model; based on the accuracy of the second driver behavior recognition model, the second driving behavior recognition model is compressed to determine the target driver behavior recognition model. Model. In the training process, the driver behavior recognition model is compressed, so that the target driver behavior recognition model can meet the needs of real-time recognition.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to a training method, a recognition method and a device for a driver behavior recognition model. Background technique [0002] With the continuous development of the automobile industry and road traffic, more and more people choose cars as means of transportation, and the issue of safe driving of cars has become the focus of the relevant departments of road traffic. During the driving process, if the driver has dangerous behaviors such as answering the phone, looking at the mobile phone, smoking, etc., it is easy to distract the driver and affect the judgment of the driving environment; It can cause serious traffic accidents and cause unpredictable consequences to the body and even life of oneself and others. [0003] In recent years, deep learning-based detection of drivers making calls while driving, detection of drivers and passengers not wearing seat belts, etc., have ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06V20/59G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/597G06N3/045G06F18/214
Inventor 牛群遥葛鹤银郭旭
Owner SUZHOU KEDA TECH