基于简单线性迭代聚类优化的无人机图像去雾算法及其在风电场中的应用

doi:10.12096/j.2096-4528.pgt.20006

发电技术 ›› 2020, Vol. 41 ›› Issue (6): 608-616.DOI: 10.12096/j.2096-4528.pgt.20006

基于简单线性迭代聚类优化的无人机图像去雾算法及其在风电场中的应用

刘厦¹^,³(), 孙哲²(), 仇梓峰¹^,³^,*(), 胡炎³()

¹ 中国电子科技集团公司第五十四研究所, 河北省石家庄市 050081
² 海装驻邯郸地区军事代表室, 河北省石家庄市 050081
³ 中国电子科技集团公司航天信息应用技术重点实验室, 河北省石家庄市 050081

收稿日期:2020-03-17 出版日期:2020-12-31 发布日期:2021-01-12
通讯作者: 仇梓峰
作者简介:仇梓峰(1993), 男, 硕士, 工程师, 研究方向为基于无人机的图像处理, 本文通信作者, qzf93@qq.com
刘厦(1986), 男, 硕士, 工程师, 研究方向为无人机智能测控, ykbrjslj@sina.cn
孙哲(1983), 男, 工程师, 研究方向为计算机视觉, power61104@163.com
胡炎(1991), 男, 硕士, 工程师, 研究方向为模式识别、健康管理及机器学习, huyantju@126.com
基金资助:
国家重点研发计划项目(2017YFB0503003)

Unmanned Aerial Vehicle Image Dehazing Algorithm Based on Simple Linear Iterative Clustering Optimization and Its Application in Wind Farm

Sha LIU¹^,³(), Zhe SUN²(), Zifeng QIU¹^,³^,*(), Yan HU³()

¹ The 54 th Research Institute of CETC, Shijiazhuang 050081, Hebei Province, China
² Military Representatives Office of NED in Handan, Shijiazhuang 050081, Hebei Province, China
³ Key Laboratory of Aerospace Information Applications of CETC, Shijiazhuang 050081, Hebei Province, China

Received:2020-03-17 Published:2020-12-31 Online:2021-01-12
Contact: Zifeng QIU
Supported by:
National Key Research & Development Program of China(2017YFB0503003)

摘要/Abstract

摘要：

针对电力巡检过程中无人机（unmanned aerial vehicle，UAV）载荷因受雾气颗粒影响而导致UAV图像不清晰的问题，提出一种基于简单线性迭代聚类（simple linear iterative clustering，SLIC）优化的UAV图像去雾算法。通过雾天成像物理模型、暗通道先验定律、同质滤波与SLIC算法，改善电力巡检图像中白色区域及不均匀光照的影响，提升UAV图像去雾处理的效率，并对大气光强度参数进行自适应计算，以防止去雾过程中复原失真。实验结果表明提出的算法可有效恢复电力巡检图像的原始细节，并通过主观视觉评估及融合多种客观评价指标的对比，说明该算法相对于传统算法的优越性。

关键词: 风电场, 电力巡检, 图像去雾, 同质滤波, 简单线性迭代聚类(SLIC)

Abstract:

In order to solve the problem that the unmanned aerial vehicle (UAV) image is not clear due to the influence of fog particles, a UAV image dehazing algorithm based on simple linear iterative clustering (SLIC) optimization was proposed. Through the physical model of fog imaging, the prior law of dark channel, homogeneous filtering and SLIC algorithm, the influence of white area and uneven light in power inspection image was improved, the efficiency of UAV image dehazing was improved, and the adaptive calculation of atmospheric light intensity parameters was carried out to prevent the distortion in the dehazing process. The experimental results show that the algorithm can effectively restore the original details of the power inspection image. Through the comparison of subjective visual evaluation and fusion of a variety of objective evaluation indexes, it shows the superiority of the algorithm compared with the traditional algorithms.

Key words: wind farm, power inspection, image dehazing, homogeneous filtering, simple linear iterative clustering (SLIC)

中图分类号:

刘厦, 孙哲, 仇梓峰, 胡炎. 基于简单线性迭代聚类优化的无人机图像去雾算法及其在风电场中的应用[J]. 发电技术, 2020, 41(6): 608-616.

Sha LIU, Zhe SUN, Zifeng QIU, Yan HU. Unmanned Aerial Vehicle Image Dehazing Algorithm Based on Simple Linear Iterative Clustering Optimization and Its Application in Wind Farm[J]. Power Generation Technology, 2020, 41(6): 608-616.

图/表 7

图1 同质滤波效果对比

Fig.1 Comparison of homogeneous filtering effect

图2 SLIC优化效果

Fig.2 SLIC optimization effect

图3 基于SLIC优化的UAV图像去雾算法流程图

Fig.3 Flow chart of UAV image dehazing algorithm based on SLIC optimization

图4 输电线路去雾处理结果

Fig.4 Dehazing results of transmission lines

图5 风力发电机去雾结果

Fig.5 Dehazing results of wind turbines

表1 3种算法的去雾性能客观评估

Tab. 1 Objective evaluation of dehazing performance of three algorithms

图像	算法	C	K	E_N
图 4左	本文算法	42.56	1.31	9.58
	HE算法	33.49	1.42	7.69
	PEI算法	38.54	1.58	8.03
图 4右	本文算法	43.14	1.67	8.76
	HE算法	31.57	1.96	7.01
	PEI算法	33.25	1.84	7.21
图 5	本文算法	55.87	0.89	10.23
	HE算法	42.36	0.86	8.25
	PEI算法	43.61	1.02	8.67

表2 3种算法的去雾处理时间

Tab. 2 Processing time of dehazing performance of three algorithms s

图像	本文算法	HE算法	PEI算法
图 4左	0.96	1.52	1.41
图 4右	1.02	1.67	1.38
图 5	2.57	4.71	4.02

参考文献 25

1	宋慧娟. 基于混合现实的人工智能在电力巡检中的应用[J]. 电网与清洁能源, 2020, 36 (2): 75- 79.
	SONG H J . Application of the artificial intelligence based on mixed reality in power patrol inspection service[J]. Power System and Clean Energy, 2020, 36 (2): 75- 79.
2	孙旭日, 李延真, 彭博, 等. 基于生成对抗网络和深度残差神经网络的变电站异物检测[J]. 电网与清洁能源, 2020, 36 (9): 68- 75.
	SUN X R , LI Y Z , PENG B , et al. Substation foreign object detection based on generative adversarial network and deep residual neural network[J]. Power System and Clean Energy, 2020, 36 (9): 68- 75.
3	杨东升, 王道浩, 周博文, 等. 泛在电力物联网的关键技术与应用前景[J]. 发电技术, 2019, 40 (2): 107- 114.
	YANG D S , WANG D H , ZHOU B W , et al. Key technologies and application prospects of ubiquitous power internet of things[J]. Power Generation Technology, 2019, 40 (2): 107- 114.
4	彭福先, 张玮, 祝晓军, 等. 基于激光点云精确定位的输电线路无人机自主巡检系统研究[J]. 智慧电力, 2019, 47 (7): 117- 122.
	PENG F X , ZHANG W , ZHU X J , et al. Autonomous patrol and inspection system of unmanned aerial vehicle for electric transmission lines based on precise positioning of laser point cloud[J]. Smart Power, 2019, 47 (7): 117- 122.
5	仇梓峰, 王爽心, 李蒙. 基于无人机图像的风力发电机叶片缺陷识别[J]. 发电技术, 2018, 39 (3): 277- 285.
	QIU Z F , WANG S X , LI M . Defect detection of wind turbine blade based on unmanned aerial vehicle-taken images[J]. Power Generation Technology, 2018, 39 (3): 277- 285.
6	毛天奇, 王传策, 李云, 等. 基于SGC算法的复杂背景无人机巡检图像输电线提取方法[J]. 智慧电力, 2018, 46 (12): 105- 111. DOI
	MAO T Q , WANG C C , LI Y , et al. Transmission line extraction method based on SGC stereo matching algorithm for UAV inspection image under complex background[J]. Smart Power, 2018, 46 (12): 105- 111. DOI
7	王丹, 李建岐, 廖斌. 基于优化去雾算法的配网开关状态视频识别技术研究[J]. 电力信息与通信技术, 2017, 15 (10): 31- 37.
	WANG D , LI J Q , LIAO B . Research on video recognition technology of distribution switch based on optimized defogging algorithm[J]. Electric Power Information and Communication Technology, 2017, 15 (10): 31- 37.
8	禹晶, 徐东彬, 廖庆敏. 图像去雾技术研究进展[J]. 中国图象图形学报, 2011, 16 (9): 1561- 1576.
	YU J , XU D B , LIAO Q M . Image defogging:a survey[J]. Journal of Image and Graphics, 2011, 16 (9): 1561- 1576.
9	KIM J Y , KIM L S , HWANG S H . An advanced contrast enhancement using partially overlapped sub-block histogram equalization[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2001, 11 (4): 475- 484. DOI
10	XIE C H , QIAO W W , ZHANG X X , et al. Single image dehazing algorithm using wavelet decomposition and fast kernel regression model[J]. Journal of Electronic Imaging, 2016, 25 (4): 43- 58.
11	肖胜笔, 李燕. 具有颜色保真性的快速多尺度Retinex去雾算法[J]. 计算机工程与应用, 2015, 51 (6): 176- 180. DOI
	XIAO S B , LI Y . Fast multiscale Retinex algorithm of image haze removal with color fidelity[J]. Computer Engineering and Applications, 2015, 51 (6): 176- 180. DOI
12	GAO Y K , CHEN H Y , LI H B , et al. Single image dehazing using local linear fusion[J]. IET Image Processing, 2018, 12 (5): 637- 643. DOI
13	FANG S , XIA X S , HUO X , et al. Image dehazing using polarization effects of objects and airlight[J]. Optics Express, 2014, 22 (16): 195- 211.
14	KOPF J , NEUBERT B , CHEN B , et al. Deep photo:model-based photograph enhancement and viewing[J]. ACM Transactions on Graphics, 2008, 27 (5): 116- 125.
15	NARASIMHAN S G , NAYAR S K . Contrast restoration of weather degraded images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25 (6): 711- 724.
16	FATTAL R . Single image dehazing[J]. ACM Transactions on Graphics, 2008, 27 (3): 1- 13.
17	MENG G, WANG Y, DUAN J, et al.Efficient image dehazing with boundary constraint and contextual regularization[C]//2013 IEEE International Conference on Computer Vision.IEEE, 2014: 1-13.
18	HE K M , SUN J , TANG X O , et al. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33 (12): 2341- 2353. DOI
19	PEI S C, LEE T Y.Nighttime haze removal using color transfer pre-processing and dark channel prior[C]//201219th IEEE International Conference on Image Processing (ICIP).IEEE, 2012: 3-15.
20	FENG C, ZHUO S, ZHANG X, et al.Near-infrared guided color image dehazing[C]//2013 IEEE International Conference on Image Processing.IEEE, 2013: 1-13.
21	BUI T M , TRAN H N , KIM W , et al. Segmenting dark channel prior in single image dehazing[J]. Electronics Letters, 2014, 50 (7): 516- 518. DOI
22	YUE B X , LIU K L , WANG Z Y , et al. Accelerated haze removal for a single image by dark channel prior[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20 (8): 1109- 1118. DOI
23	CONG J , WEI B , YIN Y , et al. Performance evaluation of simple linear iterative clustering algorithm on medical image processing[J]. Bio-medical Materials and Engineering, 2014, 24 (6): 3231- 3238. DOI
24	SHAHAMAT H , POUYAN A A . Face recognition under large illumination variations using homomorphic filtering in spatial domain[J]. Journal of Visual Communication and Image Representation, 2014, 25 (5): 970- 977. DOI
25	QU J , LI Y , DONG W . Fusion of hyperspectral and panchromatic images using an average filter and a guided filter[J]. Journal of Visual Communication & Image Representation, 2018, 52- 63.

[1]	王进钊, 严干贵, 刘侃. 基于交替方向隐式平衡截断法的直驱风电场次同步振荡分析的模型降阶研究[J]. 发电技术, 2023, 44(6): 850-858.
[2]	康佳乐, 余浩, 段瑶, 陈武晖, 王丹辉. 风电场次同步振荡等值建模方法研究[J]. 发电技术, 2022, 43(6): 880-891.
[3]	陈晓光, 杨秀媛, 王镇林, 王浩扬. 考虑多目标优化模型的风电场储能容量配置方案[J]. 发电技术, 2022, 43(5): 718-730.
[4]	张永蕊, 阎洁, 林爱美, 韩爽, 刘永前. 多点数值天气预报风速和辐照度集中式修正方法研究[J]. 发电技术, 2022, 43(2): 278-286.
[5]	杨舟, 杨仁炘, 施刚, 张建文. 一种用于多端直流输电系统交流故障穿越的新型控制策略[J]. 发电技术, 2022, 43(2): 268-277.
[6]	张智伟, 张建平, 刘明, 纪海鹏, 诸浩君, 周圣荻. 芦潮港海上风资源变化特性分析[J]. 发电技术, 2022, 43(2): 260-267.
[7]	徐彬, 薛帅, 高厚磊, 彭放. 海上风电场及其关键技术发展现状与趋势[J]. 发电技术, 2022, 43(2): 227-235.
[8]	李铮, 郭小江, 申旭辉, 汤海雁. 我国海上风电发展关键技术综述[J]. 发电技术, 2022, 43(2): 186-197.
[9]	朱月,沙俊民,赵静. 含不同机组风电场低电压穿越能力仿真研究[J]. 发电技术, 2020, 41(3): 328-333.
[10]	陈宇,彭潇,丁婧,王亚洲,邵敬平. 电动汽车参与风电场输出功率波动平抑方法研究[J]. 发电技术, 2019, 40(1): 91-98.
[11]	王羽. 风电出力时序特性及其对省级电网的影响[J]. 发电技术, 2018, 39(5): 475-482.
[12]	樊新东,杨秀媛,金鑫城. 风电场有功功率控制综述[J]. 发电技术, 2018, 39(3): 268-276.
[13]	王一珺,杜文娟,陈晨,王海风. 基于复转矩系数法研究并网双馈风电场引发电力系统次同步振荡问题综述[J]. 发电技术, 2018, 39(3): 195-203.
[14]	兰维, 张中泉, 雷阳, 刘庆超, 叶小广. 风电机组出力性能分析方法研究[J]. 发电技术, 2017, 38(3): 26-29,46.
[15]	苏卫东. 新型多功能变压器在风电场的应用[J]. 发电技术, 2017, 38(1): 63-65.

基于简单线性迭代聚类优化的无人机图像去雾算法及其在风电场中的应用

Unmanned Aerial Vehicle Image Dehazing Algorithm Based on Simple Linear Iterative Clustering Optimization and Its Application in Wind Farm

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 25

相关文章 15

编辑推荐

Metrics

本文评价