计算机应用 ›› 2015, Vol. 35 ›› Issue (4): 1133-1136.DOI: 10.11772/j.issn.1001-9081.2015.04.1133

• 虚拟现实与数字媒体 • 上一篇    下一篇

基于显著图的输电线路杆塔图像拼接方法

张旭1,2, 高佼1,2, 王万国1,2, 刘俍1,2, 张晶晶1,2   

  1. 1. 国网山东省电力公司电力科学研究院 国家电网公司电力机器人技术实验室, 济南 250002;
    2. 山东鲁能智能技术有限公司, 济南 250101
  • 收稿日期:2014-11-10 修回日期:2015-01-05 出版日期:2015-04-10 发布日期:2015-04-08
  • 通讯作者: 张旭
  • 作者简介:张旭(1984-),男,山东肥城人,工程师,硕士,主要研究方向:图像处理、模式识别; 高佼(1988-),男,山东章丘人,工程师,硕士,主要研究方向:图像处理、深度学习、双目视觉; 王万国(1984-),男,山东莘县人,工程师,硕士,主要研究方向:目标跟踪、图像处理;刘俍(1984-),男,山东济南人,工程师,硕士,主要研究方向:无人机巡检、计算机软件设计; 张晶晶(1985-),男,浙江金华人,工程师,硕士,主要研究方向:无人机巡检、图像处理、机器视觉。

Image mosaic approach of transmission tower based on saliency map

ZHANG Xu1,2, GAO Jiao1,2, WANG Wanguo1,2, LIU Liang1,2, ZHANG Jingjing1,2   

  1. 1. Electric Power Robotics Laboratory of State Grid Corporation of China, Shandong Electric Power Research Institute, Jinan Shandong 250002, China;
    2. Shandong Luneng Intelligence Technology Company Limited, Jinan Shandong 250101, China
  • Received:2014-11-10 Revised:2015-01-05 Online:2015-04-10 Published:2015-04-08

摘要:

无人机拍摄的输电线路杆塔图像分辨率高且背景复杂,基于传统特征点的拼接算法在背景中检测出大量的特征点增加了图像匹配的时间,影响了杆塔的匹配精度。针对该问题提出了一种既稳定又具有较小时间开销的输电线路杆塔图像自动拼接方法,利用改进的显著性检测算法得到杆塔图像的显著图,将图像的前景与背景分离,减少了背景对图像中杆塔拼接效果的影响;并采用基于定向的加速分割检测特征(FAST)和旋转不变性的二进制鲁棒独立元素特征(BRIEF)描述子(ORB)特征点的图像匹配算法,以提高特征点提取和匹配的速率;最后利用多尺度融合策略得到最终的拼接结果。实验结果表明,所提方法具有较好的拼接效果和拼接效率。

关键词: 无人机, 图像拼接, 显著性区域检测, 显著图, ORB特征, 图像匹配

Abstract:

Images of transmission tower acquired by Unmanned Aerial Vehicle (UAV) have high resolution and complex background, the traditional stitching algorithm using feature points can detect a large number of feature points from background which costs much time and affects the matching accuracy. For solving this problem, a new image mosaic algorithm with quick speed and strong robustness was proposed. To reduce the influence of the background, each image was first segmented into foreground and background based on a new implementation method of salient region detection. To improve the feature point extraction and reduce the computation complexity, transformation matrix was calculated and image registration was completed by ORB (Oriented Features from Accelerated Segment Test (FAST) and Rotated Binary Robust Independent Elementary Features (BRIEF)) feature. Finally, the image mosaic was realized with image fusion method based on multi-scale analysis. The experimental results indicate that the proposed algorithm can complete image mosaic precisely and quickly with satisfactory mosaic effect.

Key words: Unmanned Aerial Vehicle (UAV), image mosaic, salient region detection, saliency map, Oriented FAST and Rotated BRIEF (ORB) feature, image matching

中图分类号: