地球信息科学学报 ›› 2021, Vol. 23 ›› Issue (3): 505-513.doi: 10.12082/dqxxkx.2021.200292

• 遥感科学与应用技术 • 上一篇    下一篇

基于线段检测算法的倾斜摄影直角像控点目标检测方法

许承权1,*(), 柳庆威2   

  1. 1.闽江学院海洋学院,福州 350108
    2.中国地质大学(武汉)地理与信息工程学院,武汉 430074
  • 收稿日期:2020-06-08 修回日期:2020-09-26 出版日期:2021-03-25 发布日期:2021-05-25
  • 通讯作者: 许承权 E-mail:30418388@qq.com;30418388@qq.com
  • 作者简介:许承权(1980- ),男,福建莆田人,博士,副教授,主要从GNSS精密定位研究。E-mail: 30418388@qq.com
  • 基金资助:
    国家自然科学基金项目(41404008);福建省自然科学基金项目(2020J01834)

Detection of Tilted Aerial Photography Right-Angled Image Control Points Target based on LSD Algorithm

XU Chengquan1,*(), LIU Qingwei2   

  1. 1. Ocean College of Minjiang University, Fuzhou 350108, China
    2. College of Information Engineering, China University of Geosciences, Wuhan 430074, China
  • Received:2020-06-08 Revised:2020-09-26 Online:2021-03-25 Published:2021-05-25
  • Contact: XU Chengquan E-mail:30418388@qq.com;30418388@qq.com
  • Supported by:
    Natural Science Foundation of China(41404008);Natural Science Foundation of Fujian Province(2020J01834)

摘要:

针对航空摄影测量中空三加密时数据内业精校正的人工刺点效率低下,误差较大等问题,本文提出了一种基于线段检测(Line Segment Detector,LSD)算法的直角像控点目标检测方法。该方法首先通过Retinex算法增强影像彩色信息;再对影像进行双边滤波,在去除噪声的同时能很好的保留边缘信息;然后使用LSD算法提取线段,并结合最小二乘拟合将线段进行合并;经角度、距离和长度信息筛选出最外沿直角边,最后相交得到直角像控点。采用大疆无人机拍摄的“L”形像控点80景影像,“X”形像控点69景影像进行实验,结果表明,本文算法在复杂背景下的直角像控点检测中具有较高的准确率和精度,整体像控点提取准确率达到93.75%,像控点定位精度可以到2.37个像素,在复杂背景和目标失真的情况下依然能保持很高的准确率,定位精度明显优于人工刺点,相对于Radon和PPHT算法,本文算法的像控点组检测准确率明显提高,表明其检测精度受拍摄角度的影响较小。

关键词: 倾斜摄影, LSD直线检测, Retinex彩色增强, 直角像控点检测, 像控点, 空中三角测量, 目标检测, 双边滤波

Abstract:

Aiming at the problems of low accuracy and large error in artificial prick points during the internal work's precise correction of the aerial triangulation data during aerial photogrammetry, we propose a method in this paper for detecting the right-angled edge control points based on the LSD algorithm. First, the image is bilateral filtered to remove noise while preserving edge information and image color information enhanced by Retinex algorithm. Then, the right-angled edges of the image control point are extracted by LSD line detection, and the outermost right-angled edge is filtered by the angle, distance, and length information. Finally, the right-angled image control points are obtained through the intersection. We tested our method using 80 images of "L" image control points and 69 images of "X" image control points taken by Dajiang UAV. Results show that this method can get accurate pixel coordinates of image control points, and maintain a high accuracy in cases with complex background and target distortion. The overall image control point extraction accuracy rate was 93.75%, and the image control point positioning accuracy reached 2.3 pixels, which significantly overcame the artificial puncture points. Compared with Radon and PPHT algorithms, the accuracy of the image control point group detection is significantly improved in our results, which indicates a higher detection accuracy with less influence from the shooting angle.

Key words: aerial photography, LSD line detection, Retinex color enhancement, right-angled image control points detection, image control point, aerial triangulation, target detection, Bilateral filtering