Image-based two-passenger one-dangerous vehicle detection method and device

A vehicle detection and image technology, applied in the field of vehicle detection, to ensure the effect of inspection and detection

Pending Publication Date: 2020-08-11
北京巨视科技有限公司
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But there is no means at present to realize the detection and identification of two passengers and one dangerous vehicle

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
  • Image-based two-passenger one-dangerous vehicle detection method and device
  • Image-based two-passenger one-dangerous vehicle detection method and device

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0039] An image-based two-passenger and one-dangerous vehicle detection method of the present invention, such as figure 1 shown, including the following steps:

[0040] S1. Establish a vehicle information database of passenger cars and trucks belonging to two passengers and one dangerous vehicle;

[0041] S2. Detect the target vehicle from the real-time image, and identify the license plate, brand and type of the target vehicle;

[0042] S3. Compare the target vehicle information with the passenger car and truck vehicle information in the database, and determine whether the target vehicle belongs to the passenger car and truck type with two passengers and one hazard; if the target vehicle belongs to the passenger car type with two passengers and one hazard, output the target vehicle information, to track;

[0043] S4. If the target vehicle belongs to the truck type with two passengers and one dangerous goods, determine whether there is a dangerous goods mark on the target ve...

specific Embodiment 2

[0088] An image-based two-passenger and one-dangerous vehicle detection method of the present invention, such as figure 2 shown, including the following steps:

[0089] Q1. Collect images of the target vehicle in real time, and identify the license plate and brand of the target vehicle from the image;

[0090] Q2. Compare the license plate information of the target vehicle with the passenger vehicle information in the database belonging to Liangke; judge whether the target vehicle belongs to Liangke according to the comparison result; if so, output the passenger vehicle information for control; if No, go to the next step;

[0091] Q3. Compare the license plate information of the target vehicle with the information of the trucks and vehicles belonging to the first danger in the database; judge whether the target vehicle belongs to the first danger vehicle according to the comparison result; if not, it does not belong to the first danger vehicle, and output the truck vehicle ...

specific Embodiment 3

[0095] An image-based two-passenger-one-danger vehicle detection device of the present invention includes an image acquisition module, a vehicle detection module, a license plate recognition module, a vehicle brand recognition module, and a dangerous goods mark detection module connected in sequence.

[0096] The image collection module is used to collect the image of the vehicle, and the vehicle detection module uses deep learning method to identify the vehicle information in the image.

[0097] The license plate recognition module is used to recognize the license plate of the recognized vehicle by using a traditional method combined with a deep learning method; the deep learning method includes using at least one convolutional neural network to identify the vehicle license plate in the image, and correcting the license plate in combination with a perspective transformation matrix.

[0098] The vehicle brand recognition module adopts the classification neural network to identi...

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 discloses an image-based two-passenger one-dangerous vehicle detection method and device. The method comprises the following steps: establishing a vehicle information database of passenger cars and trucks belonging to two-passenger one-dangerous vehicles; detecting passing vehicles in real time, identifying the passing vehicles, identifying brands of the passing vehicles, comparing the identified passing vehicle information with two-passenger one-dangerous vehicle information in a database, judging whether the passing vehicles belong to passenger car and truck types in the two-passenger one-dangerous vehicles or not, and tracking the vehicles belonging to customer types; and for the vehicles belonging to the truck type, judging whether the vehicles have dangerous goods marksor not, judging the truck with the dangerous goods marks as a dangerous vehicle, and tracking the dangerous vehicle. The intelligent detection and control of two passengers and one dangerous vehicle are realized, and the safety supervision of vehicle operation is ensured.

Description

technical field [0001] The invention relates to the technical field of vehicle detection, in particular to an image-based method and device for detecting two passengers and one dangerous vehicle. Background technique [0002] "Two Passenger" vehicles refer to chartered vehicles engaged in tourism, and passenger vehicles of Class III or above on the line, and "First Dangerous" vehicles refer to special road vehicles for transporting dangerous chemicals, fireworks and firecrackers, and civilian explosives. Once these vehicles have traffic accidents, they often cause serious consequences such as mass casualties and heavy property losses. [0003] Based on the particularity of two-passenger and one-danger vehicles, it is very important to inspect and control them. It is also very important to know the relevant information of two-passenger and one-danger vehicles in a timely manner and to grasp their traces. But there is no means at present to realize the detection and identific...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/54G06V10/40G06V20/625G06V2201/08G06N3/045G06F18/2415
Inventor 席方凯王海峰
Owner 北京巨视科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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