Road target rapid detection early warning method and system

A target detection and target technology, applied in the field of computer vision, can solve problems such as inability to detect and early warning, and achieve the effect of avoiding detection of smaller targets, good practical value, and improving detection accuracy.

Active Publication Date: 2019-09-06
HUAZHONG UNIV OF SCI & TECH
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a method and system for rapid detection and early warning of road targets, thereby solving the technical problem in the prior art that detection and early warning of targets located on the driving route cannot be performed quickly and accurately

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
  • Road target rapid detection early warning method and system
  • Road target rapid detection early warning method and system
  • Road target rapid detection early warning method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] A method for rapid detection and early warning of road targets, when N is 3 and the target is a pedestrian, comprises the following steps:

[0089] Step 1: Collect road scene images, analyze the collected road scene images, and extract the trajectory and intersection points of lane lines in the image; set the center of the image as the lane line intersection points. Analyze the relationship f between the pixel height of pedestrians in the collected image and the distance of pedestrians; set the detection threshold Thr of pedestrian height ratio to 0.5.

[0090] Set the closest detected pedestrian distance to 5 meters. According to the relationship f, the pixel height of the pedestrian at 5 meters is 480, and the length and width of the first-level ROI are set to 480. (At this time, the aspect ratio of the road scene image is 1)

[0091] The sub-picture length and width of the first-level ROI are 480, and the minimum pedestrian height ratio threshold is set at 0.5, and...

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 road target rapid detection and early warning method and system, and belongs to the field of computer vision. The road target rapid detection and early warning method comprises the steps: employing an image collection device to collect road scene images, and extracting N levels of regions of interest from the road scene images according to a target distance from near to far; and sequentially carrying out target detection on the N levels of interested regions according to the sequence of the target distances from near to far, carrying out early warning after a certainlevel of interested region with a relatively short target distance detects that a target exists, and not detecting the subsequent level of interested region, wherein N is greater than or equal to 2, and the target distance is the distance between the target and the image collection device. Compared with an existing detection and early warning algorithm for targets such as pedestrians and vehicles,the road target rapid detection and early warning method has the advantages that the targets appearing on the driving route can be detected and early warned more quickly and accurately, and the practical value is high.

Description

technical field [0001] The invention belongs to the field of computer vision, and more specifically relates to a method and system for rapid detection and early warning of road targets. Background technique [0002] Pedestrian and vehicle detection technologies are widely used in assisted driving systems. In urban traffic scenarios, how to avoid traffic accidents has always been a hot issue. The current assisted driving mainly uses pedestrian and vehicle detection technology to detect and analyze the image in front of the driving motor vehicle, and actively alarms pedestrians and vehicles, which can assist the driver to avoid in advance and prevent traffic accidents. The current pedestrian and vehicle detection technology mainly uses related algorithms based on deep learning to detect and recognize pedestrians, vehicles and other targets in the input image. An important requirement of the assisted driving system is real-time performance. Vehicles travel very fast compared...

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): G06K9/00G06K9/32G06N3/04G06N3/08
CPCG06N3/084G06V20/588G06V10/25G06V2201/07G06N3/045
Inventor 陶文兵石京磊
Owner HUAZHONG UNIV OF SCI & TECH
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