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

A modified truck recognition method based on deep learning technology

A technology of deep learning and recognition methods, applied in the field of image recognition, to achieve the effect of reducing equipment requirements, reducing manual workload, and improving recognition efficiency and capabilities

Active Publication Date: 2020-09-29
北京慧智数据科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, urban road traffic management is becoming more and more intelligent. It can monitor road conditions in real time and find traffic accidents quickly. However, how to effectively and quickly identify modified vehicles, prevent traffic accidents, and ensure urban road safety needs to be solved urgently.

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 modified truck recognition method based on deep learning technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] see figure 1 , the present invention provides a method for identifying refitted trucks based on deep learning technology, the method comprising the following steps:

[0035] S1: Extract monitoring pictures from road traffic electronic monitoring equipment;

[0036] S2: Mark the vehicles in the surveillance pictures according to three types of trucks, functional vehicles, and rears to form a data set; the functional vehicles include muck trucks, hazardous chemical transport vehicles, and other special-purpose vehicles.

[0037] S3: Input the data set obtained by labeling in step S2 into the RefineDet target detection algorithm, and train to obtain a target detection model; the target detection model is used to detect the truck area from the monitoring picture; RefineDet is based on the improvement of the SSD algorithm, through Two-step cascade regression strategy to return the position and size of the target, so it also has high detection accuracy for small objects;

...

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 present invention provides a modified truck recognition method based on deep learning technology. This method collects a large number of picture data of modified trucks, and extracts the subtle differences and features between modified trucks and normal trucks based on deep learning technology and convolutional neural network technology. , realizing the effective identification of modified trucks. The beneficial effect of the present invention is that: the method of the present invention identifies the trucks on the road through the machine, and only needs to check the final result manually, which greatly reduces the workload, improves the monitoring efficiency, and effectively guarantees road safety; the method of the present invention Based on deep learning technology, iterations can be updated to adapt to actual road conditions; the method of the present invention uses convolutional neural network technology to extract subtle differences between modified trucks and normal trucks, and realizes end-to-end identification of modified trucks, reducing the need for equipment. Requirements, but also improve the recognition efficiency and ability.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and relates to a refitted truck recognition method, in particular to a refitted truck recognition method based on deep learning technology. Background technique [0002] With the increase of transportation costs, more and more freight drivers refit their trucks in order to increase their income, so that the trucks can load more goods. However, overloading of trucks is a very dangerous behavior. Overloaded and overloaded vehicles are in a state of overloading for a long time, which significantly reduces the safety performance of the vehicle's braking and operation, and is prone to tire blowouts, brake failures, leaf springs, and axle shafts. Such dangerous situations bring serious hidden dangers to traffic safety. According to statistics, more than 80% of the road traffic accidents of trucks are caused by over-limit and overloaded transportation. [0003] On the other hand, the load of...

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): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/54G06V20/52G06V10/44G06V2201/08G06N3/045G06F18/241G06F18/253
Inventor 张静乐齐聪雅
Owner 北京慧智数据科技有限公司
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