Abstract

The water level measurement method based on image processing has entered a stage of rapid development in recent years due to its visibility and confirmability. However, the water level measurement method based on image processing is very susceptible to water stains, residual water level line, lighting conditions and other factors, and the measurement accuracy is difficult to compare with the traditional water level measurement method. This paper proposes a water level measurement method based on image processing and sparse representation. The experiment indicated that the method has a strong robustness to light variation, local disability, foreign matter occlusion, and so forth. Further, the maximum error of the method is less than 0.9 cm, which is significantly smaller than other image processing based water level recognition methods such as frame difference method, image segmentation method and Hough transform.

中文翻译：

---

基于稀疏表示的水位测量方法

摘要

基于图像处理的水位测量方法由于其可见性和可确认性，近年来进入了快速发展的阶段。但是，基于图像处理的水位测量方法很容易受到水渍，残留水位线，光照条件等因素的影响，其测量精度难以与传统的水位测量方法相比。提出了一种基于图像处理和稀疏表示的水位测量方法。实验表明，该方法对光线变化，局部残障，异物阻塞等具有很强的鲁棒性。此外，该方法的最大误差小于0.9厘米，