High-precision target identification and detection method under grid background

A detection method and high-precision technology, applied in the field of computer vision, can solve problems such as color interference, poor anti-sunlight performance, and inability to accurately calculate the distance between the UAV and the target landing net, and achieve the effect of high-precision calculation

Active Publication Date: 2019-09-06
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] (1) The simple centering algorithm cannot accurately calculate the distance between the UAV and the target landing net, and the strategy of collision net recovery puts forward higher requirements
[0004] (2) The target recognition algorithm based on color has poor anti-sunlight performance, and it is easy for the color to be interfered by similar targets.
[0005] (3) The recognition algorithm based on two-dimensional codes such as ArUco Marker cannot solve the problem of the influence of the grid of the recycling net on the target outline
[0006] To sum up: the existing technology cannot realize the long-distance high-precision recognition under the grid background

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
  • High-precision target identification and detection method under grid background
  • High-precision target identification and detection method under grid background
  • High-precision target identification and detection method under grid background

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0056] The invention provides a high-precision target recognition and detection method under a grid background, comprising the following steps:

[0057] Step 1: Design the target

[0058] The target is a white bottom plate with one corner cut off; the bottom plate is provided with an icon array formed by regular arrangement of a plurality of identical icons; the size of the icons and the spacing between the icons are known. Icons are regular graphics such as circles, rectangles, hexagons or stars, and are black.

[0059] Among them, in order to improve the reliability of the contour extraction, a black frame is added around the base plate, which is more conducive to the extraction of the contour of the base plate.

[0060] Such as figure 1 As shown, the target parameters: the bottom plate is a white square with one corner missing, and the icon array is a ...

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 high-precision target identification and detection method under a grid background. By using the method, the real-time and high-precision identification of the target under the grid background can be realized, and reliable visual navigation information is provided for the net collision recovery of the unmanned aerial vehicle. The method comprises the following steps: firstly, designing a target; updating an algorithm based on a gradient search threshold value and an optimal threshold value; obtaining an appropriate binarization threshold value; realizing target identification under a netted background by using morphological filtering and a coarse and fine contour screening algorithm. Meanwhile, in order to realize real-time detection, algorithm acceleration is realized by adopting a mode of generating an interested area and downsampling, and position resolving information is provided for navigation by adopting an image processing mode in a net collision recovery process of the unmanned aerial vehicle, so that the unmanned aerial vehicle can realize an autonomous recovery function.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a high-precision target recognition and detection method under a grid background. Background technique [0002] With the continuous development of UAV technology, the self-recovery methods of fixed-wing UAVs mainly include aerial hooking, parachute recovery, net and rope recovery, airbag shock recovery and recoil rocket recovery. Among them, the recovery of the collision net can reduce the damage to the airframe and airborne equipment caused by the gust of wind and the impact on the ground. Large oil volume, prolong battery life. At present, the visual guidance method is mainly used to realize the collision recovery. The reliability and accuracy of the visual guidance part play a decisive role in the collision recovery. The existing visual recognition methods in the collision recovery process have the following problems to be solved: [0003] (1) The simple centering al...

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): G06K9/00G06T7/13G06T7/136G06T7/70
CPCG06T7/13G06T7/136G06T7/70G06V20/10
Inventor 王佳楠江佳齐单家元
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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