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

Urban Vehicle Tracking Method Based on Fast Region Convolutional Neural Network

A convolutional neural network and neural network technology, applied in biological neural network models, instruments, calculations, etc., can solve the problems of inappropriate video processing, low efficiency, slow algorithm running speed, etc., to achieve strong adaptability and reduce manual operations. , the effect of improving training speed

Active Publication Date: 2019-05-21
QINGDAO WINDAKA TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since most of the assumed areas of a picture target overlap, resulting in a large number of repeated calculations, the algorithm runs slowly and inefficiently, and is not suitable for video processing

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
  • Urban Vehicle Tracking Method Based on Fast Region Convolutional Neural Network
  • Urban Vehicle Tracking Method Based on Fast Region Convolutional Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0033] Such as figure 1 As shown, the present invention proposes an urban vehicle tracking method based on fast regional convolutional neural network, which is divided into two processes of network training and vehicle tracking.

[0034] In the network training process, build a fast area convolutional neural network, such as figure 2 As shown, the specific steps are:

[0035] (11) Establish a fully convolutional neural network, input the image into the full...

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 proposes an urban vehicle tracking method based on a fast regional convolutional neural network, marking the vehicle to be tracked in the monitoring video, inputting it into the neural network for fast training to obtain a model, and judging whether the vehicle is by identifying the road monitoring video Appear at this intersection, mark the positions of all the cameras that detected the vehicle on the map, connect them in chronological order, you can get the driving track of the vehicle, use the historical track of the vehicle to predict the driving direction of the vehicle, and in the shortest time Find out where the vehicle is in the city.

Description

technical field [0001] The invention relates to the field of image processing and machine learning, in particular to a method for tracking urban vehicles based on fast regional convolutional neural networks. Background technique [0002] In the video object recognition method, moving object detection is generally performed, and all moving objects are obtained after background removal, and each moving object is identified. This method is simple and effective, but if there are many moving objects in the video and the environment is more complicated, this method will be disturbed and the accuracy rate is low. [0003] In the image object detection method, the regional convolutional neural network works well. This method first obtains many target hypothetical regions, and then identifies all target hypothetical regions. However, since most of the assumed areas of a picture target overlap, resulting in a large number of repeated calculations, the algorithm runs slowly and has lo...

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): G06K9/00G06N3/02
CPCG06N3/02G06V20/42G06V2201/08G06V2201/07
Inventor 张卫山赵德海李忠伟宫文娟卢清华
Owner QINGDAO WINDAKA TECH
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