Automatic Precipitation Measurement Based on Raindrop Imaging and Artificial Intelligence

Hsieh, Chia‐Wei; Chi, Po-Wei; Chen, Chih-Yen; Weng, Chun-Jen; Wang, Limin

doi:10.1109/tgrs.2019.2933054

Cited by 5 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the early stage, the studies of precipitation intensity estimation using monitoring-based images utilized image processing techniques, such as foreground extraction [34], the morphological component analysis [35], and matrix decomposition [36], to extract rain streaks from the monitoring-based images, used to remove/identify rain streaks from the images. Then, studies use various methods, such as counting [37], neural networks (NN) [38], support vector machines (SVM) [39], and training the identification model for estimating precipitation intensity. These studies utilize the computer vision technique to classify the monitoring-based images for the precipitation intensity estimation.…”

Section: Related Workmentioning

confidence: 99%

SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation

Lin

Huang

Lin

et al. 2022

Sensors

View full text Add to dashboard Cite

Precipitation intensity estimation is a critical issue in the analysis of weather conditions. Most existing approaches focus on building complex models to extract rain streaks. However, an efficient approach to estimate the precipitation intensity from surveillance cameras is still challenging. This study proposes a convolutional neural network known as the signal filtering convolutional neural network (SF-CNN) to handle precipitation intensity using surveillance-based images. The SF-CNN has two main blocks, the signal filtering block (SF block) and the gradually decreasing dimension block (GDD block), to extract features for the precipitation intensity estimation. The SF block with the filtering operation is constructed in different parts of the SF-CNN to remove the noise from the features containing rain streak information. The GDD block continuously takes the pair of the convolutional operation with the activation function to reduce the dimension of features. Our main contributions are (1) an SF block considering the signal filtering process and effectively removing the useless signals and (2) a procedure of gradually decreasing the dimension of the feature able to learn and reserve the information of features. Experiments on the self-collected dataset, consisting of 9394 raining images with six precipitation intensity levels, demonstrate the proposed approach’s effectiveness against the popular convolutional neural networks. To the best of our knowledge, the self-collected dataset is the largest dataset for monitoring infrared images of precipitation intensity.

show abstract

Section: Related Workmentioning

confidence: 99%

SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation

Lin

Huang

Lin

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Here the data transmission takes place through internet by using GSM/GPRS modules and the sensors used in this system are temperature sensor and the humidity sensor which are connected to the microcontroller. Chi-Wen Hsieh, Chih-Yen Chen, Lijuan Wang [5] One more method to measure rainfall using tipping bucket was by using ground rainfall measurement. Here an instrument called Video-based Disdrometer was used to obtain a high speed image of source.…”

Section: Related Workmentioning

confidence: 99%

“…Here CMOS integrated camera in an instrument called Video-based Disdrometer was used to obtain a high speed image of source. It had a backlight for lens to increase the depth in the presence of Planar LED [5]. Wireless Sensor was another new technology which provided real time data of field from sensors [6].…”

Section: Introductionmentioning

confidence: 99%

Tipping Bucket Rain Gauge Data Processing System: A Review

Mali¹

2021

IJRASET

View full text Add to dashboard Cite

The tipping bucket system consists of funnel which collects the water of the rain in a container which is like a seesaw type module which tips side by side and collects the water. When the level of the water decreases below a preset level, the lever changes its side, causing the collected water to dump in a vessel and electrical signal is sent. By this system the high, medium or heavy rainfall character can be obtained. The rainfall character is calculated by the rainfall in 1 hour and corresponding number of pulses clicking in a period of 10 minutes. Various types of tipping bucket systems are reviewed by using rainfall and snow precipitation, using internet enabling, using rain drop imaging and artificial intelligence and also using wireless sensor network and GSM data transmission. Tipping Bucket is the most useful parameter for measuring the rainfall. In this way the rainfall is measured using the Tipping Bucket Rain Gauge System.

show abstract

Realizing Future Intelligent Networks via Spatial and Multi-Temporal Data Acquisition in Disdrometer Networks

Periola

Ogudo

Alonge

2020

2020 International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems (icABCD)

View full text Add to dashboard Cite

Automatic Precipitation Measurement Based on Raindrop Imaging and Artificial Intelligence

Abstract: The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record.

Cited by 5 publications

References 35 publications

SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation

SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation

Tipping Bucket Rain Gauge Data Processing System: A Review

Realizing Future Intelligent Networks via Spatial and Multi-Temporal Data Acquisition in Disdrometer Networks

Contact Info

Product

Resources

About