面向旋翼无人机的高压输电线在线检测方法
Fast line detection method applied in UAV high voltage line inspection
查看参考文献25篇
文摘
|
面向旋翼无人机电力巡线的高压输电线在线检测对算法实时性、鲁棒性要求高的问题,提出了一种基于边界搜索和Radon变换(BSRT)的高压输电线识别算法。分析了高压输电线在图像中的边界贯穿特征,提出了以图像四条边界作为起始点的搜索策略,给出了边界约束下的直线特征Radon变换能量函数和求解方法。复杂度分析结果表明本算法与经典的Radon算法相比,复杂度降低了一个数量级。以人工合成图像和无人机实际航拍图像,对本算法、Radon算法和LSD算法在实时性和有效性方面进行了实验对比分析,实验结果表明,本算法的处理速度较Radon算法有很大的提高,与LSD算法的处理速度基本处于同一量级,但本算法的高压输电线检测精度大幅优于传统的Radon和LSD算法。理论分析及实验结果证明,提出的BSRT方法有效地解决了经典Radon算法的高复杂度和LSD算法的复杂背景高敏感性的问题,具有较好的应用价值。 |
其他语种文摘
|
Facing the problem of requiring high real time and high robustness in online detection task of high voltage transmission line by rotor UAV, this paper proposed a high voltage transmission line recognition algorithm based on boundary search Radon transform (BSRT).It analyzed features of high voltage transmission lines in images, proposed a search strategy started from 4 boundaries of an image, and gave the energy formula and solution of line feature Radon transform (RT) under the restriction of boundaries.The complexity analysis shows that comparing to the classical RT, the complexity of the algorithm proposed by this paper reduced an order of magnitude.Experimental comparison analysis to the algorithm of this paper, the RT, and the LSD had been carried on in real-time and effectiveness using synthetic and real UAV aerial images, and the results show that the speed of this paper algorithm was greatly improved comparing to the RT and nearly on the same level with the LSD,and at the same time the accuracy of this paper algorithm is greatly better than that of the classical RT and the LSD.The theory analysis and experiment results show that the proposed method effectively solves the problems of high complexity of the classical RT and high complex background sensitivity of the LSD and has a good application value. |
来源
|
计算机应用研究
,2014,31(10):3196-3200 【核心库】
|
关键词
|
Radon变换
;
线段检测器
;
边界搜索
|
地址
|
中国科学院沈阳自动化研究所, 沈阳, 110016
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
1001-3695 |
学科
|
自动化技术、计算机技术 |
基金
|
国家自然科学基金重点资助项目
;
辽宁省科技厅博士启动基金
|
文献收藏号
|
CSCD:5240728
|
参考文献 共
25
共2页
|
1.
Radon J. Uber die Bestimmung von Funktionen durch ihre Integralwerte langs gewisser mannigfaltigkeiten.
Berichte Sachsische Akademie der Wissenschaften,1917,69:262-277
|
被引
3
次
|
|
|
|
2.
Hough P V C. Machine analysis of bubble chamber pictures.
Proc of International Conference on High Energy Accelerators and Instrumentation,1959
|
被引
1
次
|
|
|
|
3.
Duda R O. Use of the Hough transformation to detect lines and curves in pictures.
Communications of the ACM,1972,15(1):11-15
|
被引
205
次
|
|
|
|
4.
Von Gioi R G. LSD:a fast line segment detector with a false detection control.
IEEE Trans on Pattern Analysis Machine Intelligence,2010,32(4):722-732
|
被引
211
次
|
|
|
|
5.
Li Hungwen. Fast Hough transform:a hierarchical approach.
Computer Vision Graphics and Image Processing,1986,36(2/3):139-161
|
被引
1
次
|
|
|
|
6.
Illingworth J. The adaptive Hough transform.
IEEE Trans on Pattern Analysis Machine Intelligence,1987,9(5):690-698
|
被引
27
次
|
|
|
|
7.
Guerreiro R F C. Incremental local Hough transform for line segment extraction.
Proc of IEEE International Conference on Image Processing,2011:2841-2844
|
被引
1
次
|
|
|
|
8.
Illingworth J. A survey of the Hough transform.
Computer Vision Graphics & Image Processing,1988,44(1):87-116
|
被引
95
次
|
|
|
|
9.
Copeland A C. Localized Radon tranform-based detection of linear features in noisy images.
Proc of Conference on Computer Vision and Pattern Recognition,1994:664-667
|
被引
1
次
|
|
|
|
10.
Markoe A.
Analytic tomography,2006:278-362
|
被引
1
次
|
|
|
|
11.
Von Gioi R G.
LSD:a line segment detector,2012
|
被引
1
次
|
|
|
|
12.
Akinlar C. EDlines:real-time line segment detection by edge drawing.
Proc of IEEE International Conference on Image Processing,2011:2837-2840
|
被引
1
次
|
|
|
|
13.
Wikipedia.
Radon transform,2012
|
被引
1
次
|
|
|
|
14.
Ma Qirong. An algorithm for power line detection and warning based on a millimeter-wave radar video.
IEEE Trans on Image Processing,2011,20(12):3534-3543
|
被引
2
次
|
|
|
|
15.
Li Zhirong. Knowledge-based power line detection for UAV surveillance and inspection systems.
Proc of the 23rd International Conference on Image and Vision Computing,2008:26-28
|
被引
1
次
|
|
|
|
16.
Fu Li. Obstacle detection algorithms for aviation.
Proc of IEEE International Conference on Computer Science and Automation Engineering,2011:710-714
|
被引
1
次
|
|
|
|
17.
Courmontagne P H. An improvement of ship wake detection based on the Radon transform.
Signal Processing,2005,85(8):1634-1654
|
被引
9
次
|
|
|
|
18.
Van Ginkel M.
A short introduction to the Radon and Hough transforms and how they relate to each other,QI-2004-01,2004
|
被引
1
次
|
|
|
|
19.
Deans S R. Hough transform from the Radon transform.
IEEE Trans on Pattern Analysis Machine Intelligence,1981,3(2):185-188
|
被引
13
次
|
|
|
|
20.
Toft P.
The Radon transform theory and implementation,1996
|
被引
1
次
|
|
|
|
|