Optical image stitching for UAV based on weighted adjustment and regional separation

LU Heng; LI Long-guo; FU Xiao; ZHUANG Wen-hua; CAI Shi-xiang

doi:10.3788/OPE.20152313.0739

您当前的位置：

首页 >

文章列表页 >

Optical image stitching for UAV based on weighted adjustment and regional separation

更新时间：2020-08-13

- Optical image stitching for UAV based on weighted adjustment and regional separation
- Optics and Precision Engineering Vol. 23, Issue 10z, Pages: 738-743(2015)
- 作者机构：
  
  1. 四川大学水力学与山区河流开发保护国家重点实验室,四川成都,610065
  2. 四川大学水利水电学院, 四川成都 610065
  3. 成都理工大学国土资源部地学空间信息技术重点实验室, 四川成都 610059
  4. 西南交通大学地球科学与环境工程学院, 四川成都 611756
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20152313.0739
  CLC： TP75;P231.5
- Received：02 June 2015，
  
  Revised：30 June 2015，
  
  Published：14 November 2015
- 稿件说明：
移动端阅览
鲁恒, 李龙国, 付萧等. 无人机光学影像分区域加权平差拼接[J]. 光学精密工程, 2015,23(10z): 738-743

LU Heng, LI Long-guo, FU Xiao etc. Optical image stitching for UAV based on weighted adjustment and regional separation[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 738-743
鲁恒, 李龙国, 付萧等. 无人机光学影像分区域加权平差拼接[J]. 光学精密工程, 2015,23(10z): 738-743 DOI： 10.3788/OPE.20152313.0739.

LU Heng, LI Long-guo, FU Xiao etc. Optical image stitching for UAV based on weighted adjustment and regional separation[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 738-743 DOI： 10.3788/OPE.20152313.0739.

摘要

针对无人机影像数量多、畸变大

在影像拼接过程中会产生大量累积误差的问题

对如何减少拼接过程中的误差累积进行了研究。首先

根据记录影像匹配过程中心点位置计算大致的匹配区域以减少匹配时间。接着

进行区域网概算

列出误差方程

并对不同地形特征区域赋予权值进行分区域加权平差。最后

利用无人机影像分别对本文方法和传统的直接拼接法进行实验。实验结果表明:本文提出的方法可使鬼影和错位现象减少12%

拼接效率提高15%

拼接后获得的面积扩大了8%。结果显示本文方法能从误差控制和效率上较好地完成无人机影像拼接。

Abstract

When the images from an Unmanned Aerial Vehicle(UAV) is stitched

it will produce a lot of accumulated errors because of the large image quantity and image distortion. Therefore

a method to efficiently reduce the accumulated error was researched. Firstly

a general matching area was calculated according to the record center position in the stitching process to reduce the matching time. Then error equation was listed to carry on the regional network

and different terrain feature areas were given to conduct the area weighted adjustment. Finally

UAV images were used to the experiment for proposed method in this paper and the traditional direct splicing method. The experimental results on the proposed method show that the ghost and dislocation phenomenon are decreased by 12%

stitching efficiency increased by 15%

and the area of the stitching after expanding has improved by 8%. It concludes that the method can stitch UAV image better in the error control and efficiency.

关键词

Keywords

references

RANGO A, LALIBERTE A. Impact of flight regulations on effective use of unmanned aircraft systems for natural resources applications[J]. Journal of Applied Remote Sensing, 2010,4(1):043539.

ANDREA S, ALBERT R. Texture and scale in object-based analysis of subdecimeter resolution Unmanned Aerial Vehicle(UAV) imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009,47(3):761-769.

MA L, CHENG L, HAN W Q, et al.. Cultivated land information extraction from high-resolution unmanned aerial vehicle imagery data[J]. Journal of Applied Remote Sensing, 2014,8(1):083673.

王利民,刘佳,杨玲波,等. 基于无人机影像的农情遥感监测应用[J]. 农业工程学报,2013,29(18):136-145. WANG L M, LIU J, YAGN L B, et al.. Applications of unmanned aerial vehicle images on agricultural remote sensing monitoring[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013,29(18):136-145.

鲁恒,李永树,何敬,等. 一种基于特征点的无人机影像自动拼接方法[J]. 地理与地理信息科学,2010,26(5):16-19. LU H, LI Y SH, HE J, et al.. An automatic mosaic method in unmanned aerial vehicle images based on feature points[J].Geography and Geo-information Science,,2010,26(5):16-19.

Andrea S, Jeffrey E, Rango A, et al.. Acquisition, or Thorectification, and Object-based Classification of Unmanned Aerial Vehicle(UAV) Imagery for Rangeland Monitoring[J].Photogrammetric Engineering & Remote Sensing,2010,48(6):661-672.

ZHOU G Q. Near real time ortho rectification and mosaic of small UAV video flow for time critical event response[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(3):739-747.

LOWE D G. Distinctive image features from scale-invariant key points[J]. International Journal of Computer Vision, 2004, 60(2):91-110.

YAN K,RAHUL S. PCA-SIFT:a more distinctive representation for local image descriptors[C].Computer Vision and Pattern Recognition,2004,20(2):560-513.

YUAN X X, ZHU W, WU J L, et al.. GPS-supported bundle block adjustment without ground control points[J]. Geomatics and Information Science of Wuhan University, 2004, 29(10):852-857.

YUAN X X, JI SH P, XIE CH. Bundle block adjustment based on imagery given orientation parameters[J]. Geomatics and Information Science of Wuhan University, 2005, 30(11):955-959.

Views

378

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Lightweight deep learning network for accurate localization of optical image components

Design of longitudinal control law for small fixed-wing UAV during auto landing

Precise ground target location of subsonic UAV by compensating delay of navigation information

Linearized modeling and gain scheduling control for UAV taxiing

Compression for UAV reconnaissance images

Related Author

NIU Xiaoming

ZENG Li

YANG Fei

HE Guanghui

Jiu-zhou GAO

Hong-guang JIA

ZHAN Feng-jiang

SHEN Hong-hai

Related Institution

College of Mathematics and Statistics， Chongqing University

Chang Chun Champion Optics Co.， Ltd.

Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences

University of Chinese Academy of Sciences

Nanjing University of Aeronautics and Astronautics

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰