基于图像去雾技术的变电站图像清晰化方法

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (12449 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract As the substation changes from manned to unattended, operators use cameras and robots to monitor the equipment. However, the image collected from the substation under foggy conditions has low visibility and unclear problems, which leads to the failure of remote monitoring and operation, and increases the security risk of power grid operation. In this regard, this paper studies the foggy images of substations. According to the characteristics of the background color and lighting conditions of the collected images, a fog removal algorithm for the foggy images of substations based on the improved automatic color-grading algorithm is proposed. This algorithm is improved on the basis of the automatic color-grading scale fog removal algorithm, and adopts automatic optimization gamma correction, so that the images after fog removal are more consistent with the human visual perception. Finally, several commonly used defogging algorithms are selected for comparative analysis. Through subjective and objective evaluation, it is shown that the algorithm has better results in image details, brightness, fidelity, operation speed and other aspects compared with the contrast algorithms, which meets the requirements of field application, effectively solves the problem of poor image clarity in substation.

Key words： substation foggy image automatic color-grading algorithm automatic gamma correction image haze removal

Received: 13 March 2023

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	LU Shihao
	ZHU Yun
	LIAO Hua
	FENG Yuli
	ZHONG Wenming

Cite this article:

LU Shihao,ZHU Yun,LIAO Hua等. Substation image clearness method based on image defogging technology[J]. Electrical Engineering, 2023, 24(10): 51-56.

URL:

http://dqjs.cesmedia.cn/EN/Y2023/V24/I10/51

[1] 吴珊, 边晓燕, 张菁娴, 等. 面向新型电力系统灵活性提升的国内外辅助服务市场研究综述[J]. 电工技术学报, 2023, 38(6): 1662-1677.
[2] 王刘旺, 周自强, 林龙, 等. 人工智能在变电站运维管理中的应用综述[J]. 高电压技术, 2020, 46(1): 1-13.
[3] 陆世豪, 祝云, 周振茂. 基于多头注意力循环卷积神经网络的电力设备缺陷文本分类方法[J]. 广东电力, 2021, 34(6): 30-38.
[4] 姚军, 张志宏, 陈少哺, 等. 基于数据源改造的二次系统智能巡视技术[J]. 电气技术, 2022, 23(8): 84-90.
[5] LU Bo, BAI Bingchuan, ZHAO Xuefeng.Vision-based structural displacement measurement under ambient- light changes via deep learning and digital image processing[J]. Measurement, 2023, 208: 112480.
[6] HE Kaiming, SUN Jian, TANG Xiaoou.Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353.
[7] KHALID R, REHMAN S, RIAZ F, et al.Enhanced dynamic quadrant histogram equalization plateau limit for image contrast enhancement[C]//Proceedings of the 5th International Conference on Digital Information and Communication Technology and Its Applications (DICTAP), Beirut, Lebanon, 2015: 86-91.
[8] RIZZI A, GATTA C, MARINI D.A new algorithm for unsupervised global and local color correction[J]. Pattern Recognition Letters, 2003, 24(11): 1663-1677.
[9] ANIKEEVA I A.Method and algorithm of automatic color rendition quality assessment of digital aerial and space photos[J]. Geodesy and Cartography, 2018, 937(7): 45-56.
[10] 杨婷, 高武奇, 王鹏, 等. 自动色阶与双向特征融合的水下目标检测算法[J]. 激光与光电子学进展, 2023, 60(6): 132-143.
[11] 钱小燕. 单一图像多滤波联合快速去雾算法[J]. 科学技术与工程, 2015, 15(6): 236-240.
[12] 温立民, 巨永锋, 王会峰, 等. 基于双边滤波暗原色透射率细化的图像去雾算法[J]. 测控技术, 2020, 39(4): 62-65.
[13] NABAHAT M, MODARRES K F, JAFARI N N.Optimization of bilateral filter parameters using a whale optimization algorithm[J]. Research in Mathe- matics, 2022, 9(1): 2140863.
[14] 储清翠, 王华彬, 陶亮. 图像的局部自适应Gamma校正[J]. 计算机工程与应用, 2015, 51(7): 189-193, 208.
[15] 赵磊, 陈玎, 朱道立. 求解大规模SCAD回归问题的随机坐标下降算法研究[J]. 上海管理科学, 2019, 41(5): 97-103.
[16] 张登银, 鞠铭烨, 钱雯. 图像去雾算法研究现状与展望[J]. 南京邮电大学学报(自然科学版), 2020, 40(5): 101-111.
[17] 余顺园. 信息损耗约束下多尺度透射层融合图像去雾[J]. 自动化与仪器仪表, 2021(9): 38-44.
[18] 陈健, 李诗云, 林丽, 等. 模糊失真图像无参考质量评价综述[J]. 自动化学报, 2022, 48(3): 689-711.
[19] 谢庆, 杨天驰, 裴少通, 等. 基于多尺度协作模型的电气设备红外图像超分辨率故障辨识方法[J]. 电工技术学报, 2021, 36(21): 4608-4616.
[20] 梁新福, 罗日成, 党世轩, 等. 基于数字图像处理的电力线异物识别方法研究[J]. 电气技术, 2022, 23(2): 73-78.