引用本文:
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
过刊浏览    高级检索
本文已被:浏览 28次   下载 0  
分享到: 微信 更多
基于图像识别的无标尺水位测量技术研究
孙英豪1, 丁勇1, 李登华2,3, 谢东辉4
1.南京理工大学理学院;2.南京水利科学研究院;3.水利部土石坝破坏机理与防控技术重点试验室;4.宁波原水集团有限公司皎口水库分公司
摘要:
针对传统人工读取水位标尺效率低和现有基于水位标尺进行图像处理获取水位的环境适应性差、水位标尺量程短等问题,提出一种基于图像识别的无标尺水位测量技术,该技术无需借助水位标尺,仅需对水位标定,将采集到的水位图像输入到U-net神经网络进行训练,得到水体区域和非水体区域的图像语义分割模型,借助图像识别获取水位线坐标,最后根据水位标定的数学模型,采用线性插值和坐标拟合的方法计算水位。试验结果表明,该技术环境适应性强,昼、夜间的水位测量误差均小于1cm。采用该技术可以实现河道、水库等大量程的水位实时测量。
关键词:  图像识别  神经网络  语义分割  水位测量
DOI:
分类号:
基金项目:国家自然科学基金资助项目;国家自然科学基金联合基金项目;浙江省水利厅科技计划项目
Research on Measuring Technique of Water Level without Scale based on Image Recognition
Sun Yinghao1, Ding Yong1, Li Denghua2,3, Xie Donghui4
1.School of Science,Nanjing University of Science and Technology;2.Nanjing Hydraulic Research Institute;3.Key Laboratory of earth rock dam failure mechanism and prevention and control technology of the Ministry of water resources;4.Jiaokou reservoir branch of Ningbo Raw Water Group Co., Ltd
Abstract:
Aiming at the problems of low efficiency of traditional manual reading of water level gauge, poor environmental adaptability and short range of water level gauge obtained by image processing based on water level gauge, a ruler free water level measurement technology based on image recognition is proposed. This technology only needs to calibrate the water level without the help of water level gauge, and input the collected water level image into U-net neural network for training, The image semantic segmentation models of water area and non water area are obtained, and the water level coordinates are obtained by image recognition. Finally, according to the mathematical model of water level calibration, the water level value is calculated by linear interpolation and coordinate fitting. The test results show that the technology has strong environmental adaptability, and the water level measurement errors in day and night are less than 1cm. This technology can realize the real-time measurement of water level in a large range of rivers and reservoirs.
Key words:  Image recognition  Neural network  Semantic segmentation  Water level measurement
手机扫一扫看