Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for intelligent review of motor vehicle security inspection braking video

A motor vehicle and video technology, applied in the field of intelligent review of motor vehicle security inspection and braking video based on deep learning, can solve problems such as large human resources, low efficiency, and long video recording time

Active Publication Date: 2021-04-16
南昌市微轲联信息技术有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Generally speaking, the video recording time will be long, and the number of motor vehicles is large, so the low efficiency of manual review usually leads to the need for greater human resources

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for intelligent review of motor vehicle security inspection braking video
  • A method for intelligent review of motor vehicle security inspection braking video
  • A method for intelligent review of motor vehicle security inspection braking video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] The method for intelligent auditing of this motor vehicle security inspection braking video of the present invention:

[0049] Such as figure 1 As shown, after obtaining the video to be reviewed, it is divided into two steps: the first step is to verify the inspection vehicle in the video: by decomposing the video into image frames, using the neural network model to detect the license plate in the image frame, and The license plate is recognized, and the recognition result is compared with the registered license plate to obtain the vehicle identity information and confirm the vehicle to be inspected; the second step is to review the brake inspection in the video: including the length of the vehicle brake inspection and the duration of the brake wheel rotation , the length of time the brake tail lights are on.

[0050] By using the neural network model to detect and identify the vehicle position and wheel position in the image frame, use the frame difference method to j...

Embodiment 2

[0075] For motor vehicle brake tail light status inspection, such as Figure 4 shown. In this case, after using the neural network model to detect and recognize the brake tail light, the brake tail light image (image in RGB color space) is intercepted, and the image is converted to an image in YUV color space. Extract the luminance channel (ie Y channel) image in the image of the YUV color space, analyze the luminance value of the image, and then judge whether the brake tail light of the motor vehicle is on or off. Among them, the formula for converting an image in RGB color space to an image in YUV color space is as follows:

[0076] .

[0077] All the other steps are consistent with those in Example 1.

Embodiment 3

[0079] The actual operation process of the intelligent review of the motor vehicle security inspection brake video in this case is as follows:

[0080] 1. First obtain the brake detection video of the vehicle to be reviewed and the basic information of the vehicle to be reviewed through the interface.

[0081] 2. Use a video decoder to decode the brake detection video into image frames. For a video with a frame rate of 25fps, an image is taken every 5 frames for detection.

[0082] 3. Mark the motor vehicles, license plates, tires, and brake platforms in about 100,000 motor vehicle brake detection images, make the marked image data into a specific data set form, and use the YOLOV4 network model for training. Obtain a detection model that can detect motor vehicles, license plates, tires, and brake platforms in the image.

[0083] 4. Use the detection model trained in step 3 to detect the motor vehicle, license plate, tire, and brake platform in the image frame, select the mot...

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

No PUM Login to View More

Abstract

The invention relates to the technical field of motor vehicle security inspection, and discloses a method for intelligent review of motor vehicle security inspection brake videos. After obtaining the video to be reviewed, it is divided into two steps: the first step is to verify the inspection vehicle in the video, By decomposing the video into image frames, the neural network model is used to detect the license plate in the image frame, and recognize the license plate to obtain the vehicle identity information; the second step is to review the braking inspection in the video, including the duration of the vehicle braking inspection , the length of time the brake wheels turn, and the length of time the brake tail lights are on. After obtaining the results of various inspections, compare them with the national standards and specifications, and if they meet the national standards, they are qualified; otherwise, they are unqualified. Compared with the traditional manual inspection method, the present invention uses artificial intelligence technology to audit, which greatly saves human resources; has faster audit speed, greatly improves the efficiency of audit, reduces the waiting time of car owners, and improves the efficiency of car owners. car inspection experience.

Description

technical field [0001] The invention belongs to the technical field of motor vehicle security inspection, and in particular relates to a method for intelligent review of braking video of motor vehicle security inspection based on deep learning. Background technique [0002] In recent years, with the improvement of our country's economic level, the number of motor vehicles in our country has been greatly increased year by year, and motor vehicle security inspection can be said to be a lifeline of motor vehicles. In particular, the brake inspection of the motor vehicle is the most important thing in the inspection of the motor vehicle. Whether the braking device of a motor vehicle is qualified is often linked with the driver of the motor vehicle and the lives of passengers. Therefore, the country attaches great importance to the security inspection of motor vehicles, so a special administrative department is set up to supervise and review this. With the rapid increase of the...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06T7/90G06T7/11G06T7/136
CPCG06T7/90G06T7/11G06T7/136G06T2207/20081G06T2207/20084G06T2207/10016G06T2207/10024G06T2207/30168G06V20/42G06V2201/08G06V20/625
Inventor 熊信信熊奎秦浩刘耀祖
Owner 南昌市微轲联信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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