Video-based unmanned aerial vehicle cloud online traffic flow monitoring method

A traffic flow and unmanned aerial vehicle technology, applied in the field of traffic flow monitoring, real-time moving target classification and detection, can solve the problems of high time complexity, poor robustness, short communication distance, etc., to achieve remote data transmission, improve Robust, distance-independent effects

Inactive Publication Date: 2018-04-13
南京奇蛙智能科技有限公司
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a video-based UAV cloud online traffic flow monitoring method, which overcomes the high time complexity and poor robustness of the UAV detection method in the prior art, and the existence of communication in communication methods such as data. Technical issues with short distances

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
  • Video-based unmanned aerial vehicle cloud online traffic flow monitoring method
  • Video-based unmanned aerial vehicle cloud online traffic flow monitoring method
  • Video-based unmanned aerial vehicle cloud online traffic flow monitoring method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Such as figure 1 As shown, the UAV system mainly includes UAVs with gimbals, cameras, flight controllers, onboard embedded processors and 4G communication modules, ground monitoring systems, and cloud servers with powerful computing capabilities. The UAV shoots the required motor traffic video, and after the distortion correction and compression processing of the UAV on-board processor, the 4G communication module overcomes the distance limitation, and remotely transmits it to the ground monitoring center for centralized processing; to further improve wireless Human-machine automation; after the ground monitoring center receives the video, it uses the cloud computing capability of the cloud server to monitor the road condition video and count the traffic information of pedestrians and vehicles for subsequent maneuvering by using the target detection SSD algorithm based on deep learning and training Provide important references for handling measures such as traffic contr...

Embodiment 2

[0073] In this embodiment, multiple drones work together through the 4G communication module, and multiple drones shoot the required motor traffic video, and then after distortion correction and compression processing by the drone's on-board processor, they pass The communication module overcomes the distance limitation, and remotely transmits to the ground monitoring center for centralized processing.

[0074] Other parts are the same as in Embodiment 1.

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 video-based unmanned aerial vehicle cloud online traffic flow monitoring method. The method comprises that 1) an unmanned aerial vehicle flies according to the planning path,and shoots the road condition information video for a to-be-detected road section; 2) an unmanned aerial vehicle airborne embedded processor performs distortion correction on the shot video and compresses the shot video; 3 ), the unmanned aerial vehicle transmits the video data to a ground monitoring system through a 4G communication module; 4 ) after the ground monitoring system receives the video, the ground monitoring system executes and trains an SSD algorithm model according to the authority and requirement of the user or performs target detection by means of the trained SSD algorithm model, an administrator user can train the SSD algorithm model and perform SSD algorithm target detection, and an ordinary user can only carry out SSD algorithm target detection. According to the method, flexible monitoring road section selection is realized through a maneuvering unmanned aerial vehicle, and stronger autonomy is achieved; a target detection algorithm is adopted, and the consideration of the detection speed and the precision is achieved by means of cloud computing force, the robustness can be greatly improved, and centralized processing can be carried out on the ground monitoringcenter.

Description

technical field [0001] The invention belongs to the field of UAV image processing technology and computer vision, and in particular relates to a method for classifying and detecting real-time moving targets by UAVs based on vision and deep learning through the cloud, thereby realizing traffic flow monitoring. Background technique [0002] At present, there are existing pedestrian and traffic flow monitoring methods, such as collecting vehicle information through fixed surveillance cameras at intersections, and transmitting it to the traffic control center for traffic flow analysis and statistics. This method is to passively collect traffic information. , if the traffic flow is too large and the traffic needs to be evacuated, or when there is a car accident on the highway and it is necessary to understand the road conditions and rescue in time, the traditional methods are helpless; and the existing UAV visual monitoring methods, such as based on segmentation, classifiers, feat...

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): H04L29/08G08C17/02H04N7/18G06K9/00G06N3/08H04L12/24H04L12/26
CPCH04L41/069H04L41/145H04L43/08H04L67/025H04L67/10H04N7/181G06N3/08G08C17/02G06V20/54G06V2201/07
Inventor 廖振星段文博高月山张伟
Owner 南京奇蛙智能科技有限公司
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