Method on water level ruler reading recognition based on image processing

Chen, Guijun; Bai, Kejia; Liao, Xiaofeng; Liu, Shaopeng; Zhang, Lin; Zhang, Qian; Jia, Xiping

doi:10.1007/s11760-020-01719-y

Cited by 15 publications

(14 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy at night was lower but varied less. Various methods show accuracies of about 1 cm [19][20][21][22][23][24]. However, these methods use a staff gauge to create a strong contrast between the water surface and the stream wall, as well as to serve as a reference for measurements.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Measurement of Water Level in Urban Streams under Bad Weather Conditions

Azevedo

Brás

2021

Sensors

View full text Add to dashboard Cite

Flood control and water resources management require monitoring the water level in rivers and streams. Water level measurement techniques increasingly consider image processing procedures. Most of the systems use a staff gauge to support the waterline detection. However, these techniques can fail when applied to urban stream channels due to water undulation, debris on the water surface, and traces of rain captured by the camera, and other adverse effects on images can be quite dramatic on the results. The importance of considering these effects is that they are usually associated with the variation in the water level with the occurrence of rain. The technique proposed in this work uses a larger detection zone to minimize the effects that tend to obstruct the waterline. The developed system uses an infrared camera to operate during the day and night. Images acquired in different weather conditions helped to evaluate the proposed technique. The water level measurement accuracy was about 1.8 cm for images taken during the day and 2.8 cm for images taken at night. During short periods of heavy rain, the accuracy was 2.6 cm for the daytime and 3.4 cm for the nighttime. Infrared lighting can improve detection accuracy at night. The developed technique provides good accuracy under different weather conditions by combining information from various detection positions to deal with waterline detection issues.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Xu et al [22] proposed to improve the waterline detection accuracy by identifying the characters on the staff gauge image through a neural network. Image recognition with a staff gauge is also used in [23,24], obtaining a measurement error of 0.9 cm. Some image-based water level measurement systems do not use staff gauges.…”

Section: Introductionmentioning

confidence: 99%

Measurement of Water Level in Urban Streams under Bad Weather Conditions

Azevedo

Brás

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…In large-scale visual sensing, the cost may too high to set up the water level ruler for most of the cameras [17,18]. Furthermore, it is also difficult to find a consistent and common object as a reference ruler in all scenes.…”

Section: ) Universal Referencementioning

confidence: 99%

“…Traditional flood sensing models employ landmarks and rule-marks as reference objects to identify the flood extent boundaries by computing the edge and segments; however, this process is labor-intensive and time-consuming for a national-scale application [12,16]. Although certain methods can automatically compute the intersections of the flood marks, site-specific calibration and measurements must be realized and, thus, the application of these approaches to numerous cameras is challenging [17,18].…”

Section: Introductionmentioning

confidence: 99%

Deep Sensing of Urban Waterlogging

Chang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

In the monsoon season, sudden flood events occur frequently in urban areas, which hamper the social and economic activities and may threaten the infrastructure and lives. The use of an efficient largescale waterlogging sensing and information system can provide valuable near real-time disaster information to facilitate disaster management and enhance awareness of the general public to alleviate losses during and after flood disasters. Therefore, in this study, a visual sensing approach driven by deep neural networks and information and communication technology was developed to provide an end-to-end mechanism to realize waterlogging sensing and event-location mapping. The use of a deep sensing system in the monsoon season in Taiwan was demonstrated, and waterlogging events were predicted on the island-wide scale. The system could sense approximately 2379 vision sources through an internet of video things framework and transmit the event-location information in 5 min. The proposed approach can sense waterlogging events at a national scale and provide an efficient and highly scalable alternative to conventional waterlogging sensing methods.INDEX TERMS deep neural network, internet of video things, urban flood, urban waterlogging, visual sensing

show abstract

“…The camera-based systems are mostly based on a single optical camera, monitoring staff gauge but differing in image processing techniques for detecting water line on the staff and its conversion to water level. The technique is subject to poor visibility due to weather condition, ambient noise and image distortions (e.g., Chen et al, 2021;Kuo & Tai, 2022;Lin et al, 2018). Zhang et al (2019) and Azevedo and Brás (2021) developed monitoring systems using a single infrared camera to mitigate the visibility issue and image quality.…”

mentioning

confidence: 99%

Raspberry Pi Reflector (RPR): A Low‐Cost Water‐Level Monitoring System Based on GNSS Interferometric Reflectometry

Karegar

Kusche

Geremia‐Nievinski

et al. 2022

Water Resources Research

View full text Add to dashboard Cite

One of the challenges for hydrologists and environmental scientists is the need to obtain and sustain in situ water level measurements for calibrating and improving forecast models, validating satellite and airborne data products, and developing early-warning flood systems. Ground-based measurements are still scarce in many regions. In particular, stream flow monitoring gauges have been declining sharply since the mid 1980s due to high maintenance cost, funding shortfalls and (geo-) political constraints (Hannah et al., 2011;Reid et al., 2019;Ruhi et al., 2016Ruhi et al., , 2018. While satellite remote sensing techniques have been utilized to monitor oceanic and land surface water with unprecedented global coverage, their measurements are associated with moderate uncertainties and temporal resolution (>7-day return) (Escudier et al., 2017;Jarihani et al., 2013). The upcoming NASA's Surface Water Ocean Topography (SWOT) satellite mission will collect high-accuracy measurements of inland surface water elevation (10 cm error for 1 km 2 areas) at unprecedented scales (10-70 m resolution) using Ka-band interferometric synthetic aperture radar. SWOT will provide global maps of water surface elevation, slope and inundated areas for rivers wider than 100 m (Biancamaria et al., 2016). The SWOT interferometric swath will pass over a given location two or three times every 21-day orbital cycle (Tuozzolo et al., 2019). However, the coarse temporal resolution of satellite altimetry missions such as SWOT and the requirement for monitoring smaller rivers and tributaries underline the significance of in situ monitoring sites. Measurements of sea surface and river water level using ground-based sensors conventionally rely on contact methods, such as traditional float and stilling well gauges (Noye, 1974) and bubbler pressure gauges (Pugh, 1972), or proximal sensing gauges, such as acoustic (

show abstract

Method on water level ruler reading recognition based on image processing

Cited by 15 publications

References 6 publications

Measurement of Water Level in Urban Streams under Bad Weather Conditions

Measurement of Water Level in Urban Streams under Bad Weather Conditions

Deep Sensing of Urban Waterlogging

Raspberry Pi Reflector (RPR): A Low‐Cost Water‐Level Monitoring System Based on GNSS Interferometric Reflectometry

Contact Info

Product

Resources

About