为了实现输变电工程的全过程智能管理,并保证杆塔吊装的安全以及吊装后使用效果,提出基于多尺度Retinex算法的杆塔多吊点约束绳系动点坐标计算方法。采用多尺度Retinex算法增强杆塔吊装图像质量,通过最小二乘法提取图像中的特征,通过特征匹配识别杆塔类别,采用Picard方法建立不同类别的杆塔动点坐标计算模型,计算杆塔多吊点约束绳系动点坐标。测试结果显示:具有较好的图像增强效果,BIQI指标和BRISQUE指标的测试结果均在4.6以上,能够完成图像中杆塔的区分,得出杆塔的类别结果,能够计算出吊点约束绳系动点坐标结果,保证杆塔的安全吊装,倾角均低于10°,截面弯矩则越均匀程度均在92.5%以上。
Abstract
In order to realize the whole process intelligent management of power transmission and transformation engineering, and ensure the safety of tower hoisting and the use effect after hoisting, a moving point coordinate calculation method based on multi-scale Retinex algorithm was proposed. The multi-scale Retinex algorithm was used to enhance the image quality of tower hoisting, the features were extracted by the least square method, and the categories of tower were identified by feature matching. The moving point coordinate calculation models of different categories of tower hoisting were established by Picard method, and the moving point coordinates of multi-lifting point constraint rope of tower hoisting were calculated. The test results show that this method has good image enhancement effect. The test results of BIQI index and BRISQUE index are more than 4.6. It can complete the distinction of towers in the image, obtain the classification results of towers, calculate the moving point coordinates of lifting point restraint rope system, and ensure the safe lifting of towers. The inclination angle is less than 10 °, and the more uniform the section bending moment is more than 92.5%.
关键词
计量学 /
多尺度Retinex算法 /
杆塔多吊点 /
约束绳 /
系动点 /
坐标计算 /
图像增强
Key words
metrology /
multi-scale Retinex algorithm /
tower hoisting point /
rope constraint /
department of fixed point /
coordinate calculation /
image enhancement
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］艾玉麒, 黄方林, 冯帆, 等. 基于频率法的理论计算吊杆索力研究［J］. 铁道科学与工程学报, 2020, 17(8):2030-2036.
Ai Y Q, Huang F L, Feng F, et al. Theoretical calculation of suspender tension based on frequency method［J］. Journal of Railway Science and Engineering, 2020, 17(8):2030-2036.
［2］王伟, 王钦钊, 沈岚, 等. 基于概率累积的非通视无源定位方法［J］. 系统工程与电子技术, 2022, 44(1):64-69.
Wang W, Wang Q Z, Shen L, et al. A NLOS passive localization method based on probability accumulation［J］. Systems Engineering and Electronics, 2022, 44(1):64-69.
［3］郝朝伟, 王明法, 张悦杉, 等. 以横梁受力为主的大跨拱桥桥面系加固大纵梁截面形式研究［J］. 世界桥梁, 2021, 49(6):103-109.
Hao C W, Wang M F, Zhang Y S, et al. Research on Deck Cross-Sections of Long-Span Arch Bridge with Crossbeams As Main Load Bearing Components after Strengthening by Adding Large Longitudinal Beams［J］. World Bridges, 2021, 49(6):103-109.
［4］魏赟, 欧阳鹏.基于快速亮通双边滤波器的Retinex图像增强算法［J］.小型微型计算机系统, 2021,42(9):1944-1949.
Wei Y, Ouyang P. Retinex Image Enhancement Algorithm Based on Fast Bright-pass Bilateral Filtering［J］. Journal of Chinese Computer Systems, 2021, 42(9):1944-1949.
［5］吴玉厚, 王晓伟, 张天. 基于改进引导滤波的预制构件吊点位置检测方法［J］. 沈阳建筑大学学报(自然科学版), 2020, 36(6):1113-1120.
Wu Y H, Wang X W, Zhang T. Detection Method of Lifting Point Positions of Prefabricated Component Based on Improved Guide Filter［J］. Journal of Shenyang Jianzhu University Natural Science, 2020, 36(6):1113-1120.
［6］乐英, 赵志成. 基于区域点云的工件位姿计算方法［J］. 中国工程机械学报, 2021, 19(4):295-301.
Yue Y, Zhao Z C. Calculation method of work piece pose based on regional point cloud［J］. Chinese Journal of Construction Machinery, 2021, 19(4):295-301.
［7］彭静, 薛奉金, 苑玉彬.基于多尺度Retinex和暗通道的自适应图像去雾算法［J］. 激光与光电子学进展, 2021, 58(4):117-125.
Peng J, Xue F J, Yuan Y B. Adaptive Image Defogging Algorithm Combining Multi-Scale Retinex and Dark Channel［J］. Laser & Optoelectronics Progress, 2021, 58(4):117-125.
［8］周清松, 黄嵩, 陈洪磊. 自适应补偿Retinex算法的多尺度图像渐晕校正［J］. 计算机仿真, 2021, 38(4):155-158.
Zhou Q S Huang S, Chen H L. Multi Scale Image Vignetting Correction Based on Adaptive Compensation Retinex Algorithm［J］. Computer Simulation, 2021, 38(4):155-158.
［9］骆家杭, 张旭. 基于改进型Retinex算法的彩色图像增强技术［J］. 计算机工程与科学, 2021, 43(5):891-896.
Luo J H, Zhang X. Color image enhancement technology based on improved Retinex algorithm［J］. Computer Engineering and Science, 2021, 43(5):891-896.
［10］王晓柱, 钮赛赛, 张凯, 等. 基于小波变换与特征提取的红外弱小目标图像融合［J］. 西北工业大学学报, 2020, 38(4):723-732.
Wang X Z, Niu S S, Zhang K, et al. Image Fusion of Infrared Weak-Small Target Based on Wavelet Transform and Feature Extraction［J］. Journal of Northwestern Polytechnical University, 2020, 38(4):723-732.
［11］刘胜昔, 程春玲. 改进的Gabor小波变换特征提取算法［J］.计算机应用研究, 2020, 37(2):606-610.
Liu S X, Cheng C L. Feature extraction algorithm based on improved Gabor wavelet transform［J］. Application Research of Computers, 2020, 37(2):606-610.
［12］万能, 周千昂, 郭可贵, 等. 基于前景杆塔识别的电力巡检精准自动复拍方法［J］.计算机应用,2021,41(S1):298-303.
Wan N, Zhou Q A, Guo K G, et al. Accurate autonomous retaking method based on foreground tower recognition in power tower inspection［J］. Journal of Computer Applications, 2021, 41(S1):298-303.
［13］张俊, 庞世强, 李晓斌, 等. 融合LSD算法与Hough变换的航拍输电线路图像杆塔自动识别方法［J］. 电子器件, 2021, 44(5):1210-1214.
Zhang J, Pang S Q, Li X B, et al. Automatic Tower Recognition Method Based on LSD Algorithm and Hough Transform in Aerial Transmission Line Image［J］. Chinese Journal of Electron Devices, 2021, 44(5):1210-1214.
［14］李国强, 彭炽刚, 汪勇, 等. 基于深度学习的杆塔三维姿态实时估计［J］. 电子技术应用, 2021, 47(6):87-91.
Li G Q, Peng C G, Wang Y, et al. Real-time estimation of three-dimensional attitude of towers based on deep learning［J］. Application of Electronic Technique, 2021, 47(6):87-91+95.
［15］蒋清乐, 卢继平, 孙涛, 等. 基于GPR偏移成像处理的杆塔接地体缺陷检测［J］. 高电压技术, 2021, 47(1):322-330.
Jiang Q L, Lu J P, Sun T, et al. Defect Detection of Pole Tower Grounding Body Based on GPR Offset Imaging［J］. High Voltage Engineering, 2021, 47(1):322-330.
基金
国网山东省电力公司科技项目(2021A-105)
PDF(24341 KB)
