Supercharge Your Innovation With Domain-Expert AI Agents!

Unmanned aerial vehicle (UAV) aerial image sequence depth recovery-based building detection method

An image sequence and depth restoration technology, applied in the field of building detection, can solve problems such as poor detection accuracy, achieve the effect of improving accuracy, reducing system complexity and cost

Active Publication Date: 2018-05-11
HARBIN ENG UNIV
View PDF1 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The object of the present invention is to provide a building detection method based on the depth restoration of the drone aerial image sequence to solve the problems of poor detection accuracy in the prior art

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
  • Unmanned aerial vehicle (UAV) aerial image sequence depth recovery-based building detection method
  • Unmanned aerial vehicle (UAV) aerial image sequence depth recovery-based building detection method
  • Unmanned aerial vehicle (UAV) aerial image sequence depth recovery-based building detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The specific embodiment of the present invention will be further described below in conjunction with accompanying drawing:

[0062] S1. If figure 2 As shown in Fig. 1, the image sequence is obtained by using a drone equipped with a monocular camera to fly horizontally. I t ' and I t+1 ’ respectively represent two adjacent frames of images, (x t ,y t ) represents the coordinate point in the image at time t, (x t+1 ,y t+1 ) represents the coordinate point in the image at time t+1, then the affine transformation relationship between two adjacent frames of images can be defined as follows:

[0063]

[0064] where a 1 ,a 2 ,a 3 ,a 4 ,b 0 ,b 1 is the transformation parameter, which can be obtained by the least square method. The overlapping area of ​​the two images after transformation is denoted as Ω, I t and I t+1 denote the horizontally aligned images in region Ω, respectively.

[0065] S2. The present invention is based on the detection of buildings un...

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 an unmanned aerial vehicle (UAV) aerial image sequence depth recovery-based building detection method, and belongs to the technical field of building detection. The method specifically comprises the steps of collecting an image sequence by an unmanned aerial vehicle-mounted monocular camera; based on the movement information of an aircraft and the relation between the airspace and the time domain of the acquired image sequence, restoring the parallax of an image; converting the parallax into the depth, segmenting a building based on a manually preset depth threshold value. According to the invention, the depth of the image can be effectively estimated, and the building can be detected based on the depth information. The method for restoring the sequence depth of anunmanned aerial vehicle image is adopted for the first time. Therefore, the building can be effectively detected.

Description

technical field [0001] The invention belongs to the technical field of building detection, and in particular relates to a building detection method based on the depth restoration of a UAV aerial image sequence. Background technique [0002] With the rapid development of today's UAV technology, building detection based on UAV aerial video sequences has become a research hotspot. It is of great significance to be able to accurately detect buildings in complex backgrounds. The classic methods of building detection are as follows: edge contour detection, building matching method, etc. The aerial video background is complex, and it is difficult to locate specific buildings if edge contours are used for detection in densely built areas. There are various shapes of buildings in modern society. Although the matching method can stably identify buildings with more standardized shapes, it has weaker recognition ability for buildings with more complex shapes. The above two methods ar...

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
IPC IPC(8): G06K9/00G06T7/136G06T7/33
CPCG06T7/136G06T7/33G06T2207/10028G06T2207/10016G06V20/176
Inventor 项学智翟明亮吕宁肖德广尹力宋凯郭鑫立王帅张荣芳于泽婷张玉琦
Owner HARBIN ENG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com