Traffic image multi-type vehicle detection method based on deep study

A vehicle detection and deep learning technology, which is applied in the field of multi-type vehicle detection in traffic images based on deep learning, can solve problems such as insufficient to meet the requirements of large-scale image data processing, reduce the amount of calculation, reduce the complexity, and improve accuracy Effect

Active Publication Date: 2016-11-09
安徽国联信息科技有限公司
View PDF2 Cites 61 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In short, the existing image-based vehicle detection technology either needs to use complex features designed by hand to provide judgment basis, or needs the region generation technology based on the underlying information of the image to provide data sources, which is not enough to deal with the processing requirements of large-scale image data, so There is a need for an accurate and fast vehicle detection method for large-scale image data with multiple scenes

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
  • Traffic image multi-type vehicle detection method based on deep study
  • Traffic image multi-type vehicle detection method based on deep study
  • Traffic image multi-type vehicle detection method based on deep study

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] A method for detecting multiple types of vehicles in traffic images based on deep learning, including a training process and a testing process:

[0072] The training process has the following steps:

[0073] (1) Vehicle information labeling: Collect all the original images obtained by different image acquisition terminals for processing, label the position coordinate information of the vehicle in the image, and add the simple judgment result of the vehicle type and the general direction information of the front of the vehicle, and put all the images and all the above label information are stored in the database; among them, the vehicle type is divided into cars, buses, light trucks, medium trucks, heavy trucks, commercial vehicles, There are eight categories of sports utility vehicles and engineering vehicles. Among them, light trucks mainly refer to pickup trucks and small passenger-cargo vans. Medium-sized trucks are different from heavy-duty trucks because the number...

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 traffic image multi-type vehicle detection method based on deep study. The traffic image multi-type vehicle detection method based on deep study firstly combines a nerve network characteristic with a region generation algorithm, realizes two processes-region generation and region determination-at the same time through using a nerve network conventional layer, uses a background model to determine a motion area of a discrete series image targeting a specific scene and provides an extra reference basis to region generation, and combines with a vehicle detection result to perform upgrading and correction on the background model according to different conditions. Besides, the traffic image multi-type vehicle detection method also brings forward a network model compression scheme to reduce model parameters and calculation time, brings forward a new detection result optimization means based on grouped error calculation to replace a conventional non-maximum-value inhibition scheme, and improves overall detection accuracy.

Description

technical field [0001] The invention relates to the technical field of vehicle detection, in particular to a method for detecting multiple types of vehicles in traffic images based on deep learning. Background technique [0002] With the development of society, people's living standards have been greatly improved in all aspects of "basic clothing, food, housing and transportation", which is reflected in the improvement of road infrastructure construction in various places and the rapid increase of the total number of cars in society in terms of "travel". However, road construction is a long-term process that requires long-term accumulation to achieve results, so it often cannot keep up with the growth rate of motor vehicles in various places. The solution to the problem is to use more scientific technical means to manage road traffic, which is intelligent transportation. system. The intelligent transportation system can count the flow of vehicles on the road, identify the d...

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): G06K9/00
CPCG06V20/584G06V20/52
Inventor 程鹏
Owner 安徽国联信息科技有限公司
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