Email Alerts
RSS
Intelligent acquisition method of piezometric pipe group water depth based on image recognition technology
-
摘要: 为在水工模型试验中准确同步获取过水建筑物不同部位水压力，提出并设计了基于图像识别技术的测压管群水深智能获取方法与系统。该系统采用非接触式（侧拍）影像采集方式，实时拍摄多个测压管内水面浮标的运动影像（反映水深变化过程），将影像资料导入计算机；利用软件识别系统，采用灰度化、二值化及开操作等对图像进行预处理，然后使用findContours获取各个测压管水面浮标质心坐标，通过标定系数转换为实际水位数据，最终得到各个测压管内水深同步变化的时间序列。通过水工模型试验验证，该方法较传统人工测量方法获得的数据误差在±1.5%内，且获取方式更快捷、数据更丰富，可为水工模型试验中测压管群水深测量提供新的思路。Abstract: In order to accurately and quickly obtain the water pressure of different parts of the water-passing structure in the hydraulic model test, a method and a system for the intelligent acquisition of the water depth of the piezometric pipe group based on image recognition technology have been proposed and designed. The system adopts a non-contact (shot from a side) image acquisition method which can shoot real-time moving images of water surface buoys in a large number of pressure measuring tubes (reflecting the changing process of water depth), and then import the image data into the computer; the software recognition system adopts grayscale, binary values and opening operations to preprocess the image in preparation. When pretreatment work is finished, findContours would be used to obtain the centroid coordinates of the water surface buoys of each piezometer tube, which would be converted into actual water level data through calibration coefficients, and finally the time series of the synchronous changes of the water depth in each piezometer tube would be obtained. Compared with the traditional manual measurement method, the verification result of hydraulic model test shows that the data error obtained by this method is no more than ±1.5% compared with the traditional manual measurement method, but the acquisition method is faster, the data is richer, and the accuracy is higher.
-
Key words:
- piezometric tube group /
- image recognition /
- water depth /
- model test
-
图 2 各测压管水深随时间变化
Figure 2. Water depth variation of pressure measuring tubes along time
表 1 水深特征值对照
Table 1. Comparison of water depth characteristic values
测压管
编号人工测量结果/m 图像识别结果/m 平均值误差
/%最大值 最小值 平均值 最大值 最小值 平均值 1# 0.786 0.653 0.720 0.782 0.659 0.727 0.97 2# 0.780 0.625 0.703 0.782 0.628 0.706 0.43 3# 0.756 0.593 0.675 0.743 0.590 0.684 1.33 4# 0.791 0.645 0.718 0.777 0.653 0.724 0.84 5# 0.382 0.330 0.356 0.378 0.330 0.355 −0.28 6# 0.926 0.900 0.913 0.930 0.903 0.915 0.22 7# 0.927 0.883 0.905 0.925 0.877 0.893 −1.33 8# 0.900 0.817 0.859 0.901 0.821 0.859 0 注：平均值误差=（图像识别平均值−人工识别平均值）/人工识别平均值×100%。 
下载: 导出CSV
-
[1] 万雄卫, 徐盈, 肖皓, 等. 二滩水电站水垫塘抗冲磨修补研究[J]. 水利水电技术,2013,44(9):96-99 doi: 10.3969/j.issn.1000-0860.2013.09.024 WAN Xiongwei, XU Ying, XIAO Hao, et al. Study on erosion and abrasion resistant repairing for cushion pool of Ertan Hydropower Station[J]. Water Resources and Hydropower Engineering, 2013, 44(9): 96-99. (in Chinese) doi: 10.3969/j.issn.1000-0860.2013.09.024 [2] 中华人民共和国水利部. 水工(常规)模型试验规程: SL 155—2012[S]. 北京: 中国水利水电出版社, 2012. Ministry of Water Resources of the People’s Republic of China. Specification for normal hydraulic model test: SL 155—2012[S]. Beijing: China Water & Power Press, 2012. （in Chinese） [3] GAO A, WU S Q, WANG F F, et al. A newly developed unmanned aerial vehicle (UAV) imagery based technology for field measurement of water level[J]. Water, 2019, 11(1): 124. doi: 10.3390/w11010124 [4] 聂鼎, 张龑, 刘毅, 等. 基于图像处理的小型水库水位测量方法[J]. 水电能源科学,2019,37(11):28-32 NIE Ding, ZHANG Yan, LIU Yi, et al. Water level measurement method of small reservoir based on image processing[J]. Water Resources and Power, 2019, 37(11): 28-32. (in Chinese) [5] 李翊, 兰华勇, 严华. 基于图像处理和BP神经网络的水位识别研究[J]. 人民黄河,2015,37(12):12-15 doi: 10.3969/j.issn.1000-1379.2015.12.004 LI Yi, LAN Huayong, YAN Hua. Research on water-level recognition based on image processing and BP artificial neural network technology[J]. Yellow River, 2015, 37(12): 12-15. (in Chinese) doi: 10.3969/j.issn.1000-1379.2015.12.004 [6] 鲍江, 陶青川, 张鹏. 基于图像处理的水位线检测算法[J]. 水电能源科学,2015,33(4):96-99, 210 BAO Jiang, TAO Qingchuan, ZHANG Peng. Image processing based water level detection algorithm[J]. Water Resources and Power, 2015, 33(4): 96-99, 210. (in Chinese) [7] 徐兴, 洪添胜, 岳学军, 等. 基于数字图像的水位识别系统及其方法[J]. 排灌机械工程学报,2014,32(1):33-39 doi: 10.3969/j.issn.1674-8530.13.0069 XU Xing, HONG Tiansheng, YUE Xuejun, et al. Digital image-based water level recognizing system and method[J]. Journal of Drainage and Irrigation Machinery Engineering, 2014, 32(1): 33-39. (in Chinese) doi: 10.3969/j.issn.1674-8530.13.0069 [8] 王伟, 马福昌. 基于图像处理的水位自动测量技术[J]. 南水北调与水利科技,2012,10(6):147-150 WANG Wei, MA Fuchang. Research on automatic measurement technology of water level based on image processing[J]. South-to-North Water Diversion and Water Science & Technology, 2012, 10(6): 147-150. (in Chinese) [9] TAKAGI Y, TSUJIKAWA A, TAKATO M, et al. Development of a noncontact liquid level measuring system using image processing[J]. Water Science and Technology, 1998, 37(12): 381-387. doi: 10.2166/wst.1998.0564 [10] BRADSKI G R, KAEHLER A. Learning OpenCV[M]. Whitefish: Betascript Publishing, 2018. [11] 陈波, 张华, 汪双, 等. 基于全卷积神经网络的坝面裂纹检测方法研究[J]. 水力发电学报,2020,39(7):52-60 doi: 10.11660/slfdxb.20200706 CHEN Bo, ZHANG Hua, WANG Shuang, et al. Study on detection method of dam surface cracks based on full convolution neural network[J]. Journal of Hydroelectric Engineering, 2020, 39(7): 52-60. (in Chinese) doi: 10.11660/slfdxb.20200706 -
点击查看大图
图(2) / 表 (1)
计量
- 文章访问数: 194
- HTML全文浏览量: 82
- PDF下载量: 20
- 被引次数: 0
