Target detection method for autonomous landing of UAV based on maximum response of brisk detector

A technology of target detection and autonomous landing, which is applied in the direction of instruments, computer components, character and pattern recognition, etc. It can solve problems such as shaking, casualties, equipment, and small venues, and achieve high accuracy, good stability, and strong real-time performance Effect

Active Publication Date: 2018-08-31
NAT UNIV OF DEFENSE TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] During the landing process of the drone, there are problems such as platform movement, shaking, narrow space, and complex and changeable weather conditions. Misguided control at the end of the drone may cause safety accidents such as casualties or equipment damage.

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
  • Target detection method for autonomous landing of UAV based on maximum response of brisk detector
  • Target detection method for autonomous landing of UAV based on maximum response of brisk detector
  • Target detection method for autonomous landing of UAV based on maximum response of brisk detector

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described in detail below with reference to the drawings and specific embodiments of the specification.

[0036] Such as Image 6 As shown, the method of autonomous landing target detection for drones based on the maximum response of the BRISK detector of the present invention has the following steps:

[0037] (1) Input: UAV flight sequence diagram I, FAST operator parameter N, FAST corner detection threshold δ, scale space layer number n;

[0038] (2) Generate BRISK scale space;

[0039] Read in the numth drone flight acquisition image I num , Convert it to grayscale image I num_gray ; Generate n-level scale image c i , Image c i By c i-1 Obtained by half-sampling; generate n-1 intermediate layer image d i , D 0 From the original image c 0 Perform 1.5 times downsampling, d i By d i-1 Obtained by half sampling;

[0040] In specific applications, such as figure 1 As shown, the BRISK scale space consists of n layers c i And n intermediate lay...

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 UAV autonomous landing target detection method based on the maximum response of a BRISK detector. The steps are: (1) input: UAV flight sequence diagram I; (2) generate the BRISK scale space; The image in the human-machine flight sequence diagram I generates a scale space map; (3) image feature point detection; by performing FAST corner point detection on each layer of the BRISK scale space, determine the feature point in the visual image; (4) target Stable feature point extraction; extract the stable feature points of the target from the image feature points, that is, for all feature points, filter out the feature point with the largest response value, and the image coordinates of the feature point with the largest response value are UAV target image detection Location. The invention has the advantages of good stability, high accuracy, strong real-time performance, good applicability and the like.

Description

Technical field [0001] The present invention mainly relates to the field of UAV control, and specifically refers to a UAV autonomous landing target detection method based on the maximum response of the BRISK (BRISK: BinaryRobust Invariant Scalable Keypoints, scale invariant binary description key point detection algorithm) detector . Background technique [0002] During the landing of the UAV, there are problems such as platform movement, shaking, small site, complicated and changeable weather conditions, etc. The failure of the UAV's terminal guidance and control may cause safety accidents such as casualties or equipment damage. Therefore, how to realize automatic, safe, and fast positioning and guidance is a key issue that determines the cost, frequency and efficiency of the UAV. The optical-based guidance technology mainly studies how to realize the tracking and positioning of the UAV after entering the recovery area, and guiding it to land smoothly according to the set route...

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 & AuthorityPatents(China)
IPC IPC(8): G06K9/46
CPCG06V10/44
Inventor胡天江潘崇煜马兆伟沈林成朱华勇赵搏欣陈超王祥科尹栋王勋
OwnerNAT UNIV OF DEFENSE TECH