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

Electric vehicle detection and alarm method, device, equipment, medium and system

A technology for electric vehicles and detection frames, which is applied in image data processing, instrument, character and pattern recognition, etc., can solve the problems of poor detection accuracy of electric vehicles, and achieve the effect of reducing the false detection rate and improving the accuracy.

Pending Publication Date: 2021-10-01
ZHEJIANG DAHUA TECH CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present invention provides an electric vehicle detection method, device, electric vehicle detection equipment and storage medium to solve the problem of poor electric vehicle detection accuracy in the prior art

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
  • Electric vehicle detection and alarm method, device, equipment, medium and system
  • Electric vehicle detection and alarm method, device, equipment, medium and system
  • Electric vehicle detection and alarm method, device, equipment, medium and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] figure 1 A schematic diagram of the electric vehicle detection process provided by the embodiment of the present invention, the process includes the following steps:

[0075] S101: Obtain an image in the monitoring area, input the image into the pre-trained electric vehicle detection model, detect the overall body detection frame and the local body detection frame of the vehicle in the image based on the electric vehicle detection model, and The overall detection frame of the vehicle body is used to determine the rough category information of the corresponding vehicle, and the local feature information of the corresponding vehicle is determined based on the partial detection frame of the vehicle body.

[0076] S102: Based on the rough category information of the vehicle and the local feature information of the vehicle, determine whether the vehicle is an electric vehicle.

[0077] The electric vehicle detection method provided in the embodiment of the present invention...

Embodiment 2

[0083]In order to make the electric vehicle detection more accurate, on the basis of the above-mentioned embodiments, in the embodiment of the present invention, the vehicle body part detection frame in the image is detected based on the electric vehicle detection model, and the vehicle body part detection frame is determined based on the vehicle body part detection frame. The local characteristic information of the corresponding vehicle includes:

[0084] Detecting the wheel detection frame of the vehicle in the image based on the electric vehicle detection model, and determining the wheel feature information corresponding to the wheel detection frame, wherein the wheel feature information includes large wheels, small wheels and miniature wheels;

[0085] The determining whether the vehicle is an electric vehicle based on the rough category information of the vehicle and the local feature information of the vehicle includes:

[0086] If it is determined that the rough categor...

Embodiment 3

[0092] In order to further make the electric vehicle detection more accurate, on the basis of the above-mentioned embodiments, in the embodiment of the present invention, the detection of the vehicle body part detection frame in the image based on the electric vehicle detection model includes:

[0093] Detecting the wheel detection frame, the lamp detection frame and the windshield detection frame of the vehicle in the image based on the electric vehicle detection model;

[0094] The determining whether the vehicle is an electric vehicle based on the rough category information of the vehicle and the local feature information of the vehicle includes:

[0095] Determine the electric vehicle detection confidence score according to the rough category information of the vehicle, the wheel feature information, and whether the headlight detection frame and the windshield detection frame are detected; determine whether the vehicle is detected according to the electric vehicle detection...

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 electric vehicle detection and alarm method, device, equipment, medium and system. The method comprises the steps of obtaining an image in a monitoring area, inputting the image into a pre-trained electric vehicle detection model, detecting a vehicle body overall detection frame and a vehicle body local detection frame of a vehicle in the image based on the electric vehicle detection model, determining coarse category information of the corresponding vehicle based on the vehicle body overall detection frame, and determining local feature information of the corresponding vehicle based on the vehicle body local detection frame, and determining whether the vehicle is an electric vehicle based on the coarse category information of the vehicle and the local feature information of the vehicle. Compared with the scheme in the prior art, the feature of the vehicle local feature information is added, the difference between the electric vehicle and other vehicles can be better reflected, the false detection rate of the electric vehicle is reduced, and therefore the accuracy of electric vehicle detection is improved.

Description

technical field [0001] The invention relates to the technical field of image intelligent analysis, in particular to an electric vehicle detection and alarm method, device, equipment, medium and system. Background technique [0002] Electric vehicles enter the floor through the elevator, which will block the corridor, and pull the wires to charge, posing a major fire hazard. In order to reduce and avoid such incidents, the traditional method is to arrange community personnel to inspect whether the electric vehicle enters the elevator. The traditional method is time-consuming and laborious, and it cannot perform full-time detection. [0003] In order to solve the problem of arranging community personnel to conduct inspections to detect electric vehicles entering the elevator, it takes a lot of manpower and material resources. In the prior art, under the premise of not changing the original elevator monitoring system, an intelligent camera analysis is introduced. Identificatio...

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): G06T7/00G06K9/00G06K9/46G06K9/62
CPCG06T7/0002G06F18/214
Inventor 刘明章合群周祥明傅凯白家男
Owner ZHEJIANG DAHUA TECH CO LTD
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