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

A large vehicle analysis system based on deep learning

A deep learning and analysis system technology, applied in the field of large-scale vehicle analysis systems, can solve the problems of dirty vehicles, obscured vehicles cannot be identified, cannot be fully effectively managed and prosecuted, etc., to achieve high efficiency, improve efficiency, The effect of improving product compatibility

Pending Publication Date: 2019-06-21
ZHEJIANG HAOTENG ELECTRONICS POLYTRON TECH INC
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The imaging capture mode used in the prior art cannot identify defaced vehicles and occluded vehicles
As a result, it is impossible to fully and effectively manage and prosecute illegal activities such as large-scale vehicle accident escape and city bans

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 large vehicle analysis system based on deep learning
  • A large vehicle analysis system based on deep learning
  • A large vehicle analysis system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] A large-scale vehicle analysis system based on deep learning, including a forward road capture camera, a reverse road capture camera is installed at a distance from the forward road capture camera, the forward road capture camera obtains the video stream of the vehicle head, and the reverse The road capture camera obtains the video stream of the rear of the vehicle; it also includes a GPU graphics analysis module installed on the server, and the video stream access module is connected with the forward road capture camera and the reverse road capture camera, and obtains the forward direction through the video stream access module. Capture the video streams of the vehicle front and rear of the road capture camera and reverse road capture camera and input the video stream to the GPU graphics analysis module, and the GPU graphics analysis module performs video decoding or video data conversion on the video stream to output structured graphics data , and the GPU graphics anal...

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 a large vehicle analysis system based on deep learning. The system comprises a forward road snapshot camera, a GPU graphic analysis module mounted on the server; a reverse roadsnapshot camera is installed at a certain distance away from the forward road snapshot camera, and the server obtains video streams of the forward road snapshot camera and the reverse road snapshot camera through the video stream access module and inputs the video streams to the GPU graphic analysis module; The GPU graphic analysis module performs video decoding or video data conversion on the video stream so as to output structured graphic data; the GPU graphic analysis module decomposes the video stream into a single-frame image and transmits the single-frame image to the deep learning algorithm module, and the deep learning algorithm module processes all vehicle information in the structured graphic data to obtain the whole vehicle information of the large vehicle and outputs the wholevehicle information of the large vehicle with illegal behaviors to the illegal information platform.

Description

technical field [0001] The present application relates to the field of road traffic, in particular to a deep learning-based large-scale vehicle analysis system for road traffic. Background technique [0002] At present, the number of trucks in my country is more than 20 million, accounting for 7.8% of the total number of motor vehicles, but the number of deaths caused by truck accidents accounts for about 28% of the total number of traffic accident deaths. In 2012, the accident rate per 10,000 vehicles of trucks was more than double that of the national traffic accident rate per 10,000 vehicles during the same period. Recently, there have been a number of road traffic accidents in Shandong, Fujian, Hebei and other places that resulted in mass deaths and injuries caused by truck accidents, causing heavy losses to the lives and property of the people. [0003] At present, there are more and more monitoring points in the construction of smart cities, and the supervision of lar...

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
IPC IPC(8): G06K9/00G06N3/04G06N3/08G06Q50/26G08G1/017
Inventor 吴宗林夏路刘远超何伟荣
Owner ZHEJIANG HAOTENG ELECTRONICS POLYTRON TECH INC
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