SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation
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...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/2/551 |
_version_ | 1797490476357517312 |
---|---|
author | Chih-Wei Lin Xiuping Huang Mengxiang Lin Sidi Hong |
author_facet | Chih-Wei Lin Xiuping Huang Mengxiang Lin Sidi Hong |
author_sort | Chih-Wei Lin |
collection | DOAJ |
description | 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. |
first_indexed | 2024-03-10T00:33:32Z |
format | Article |
id | doaj.art-8c4af0d3fa5142fb85540788d6e86c5c |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T00:33:32Z |
publishDate | 2022-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-8c4af0d3fa5142fb85540788d6e86c5c2023-11-23T15:20:32ZengMDPI AGSensors1424-82202022-01-0122255110.3390/s22020551SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity EstimationChih-Wei Lin0Xiuping Huang1Mengxiang Lin2Sidi Hong3College of Computer and Information Science, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Computer and Information Science, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Computer and Information Science, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of New Engineering Industry, Putian University, Putian 351100, ChinaPrecipitation 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.https://www.mdpi.com/1424-8220/22/2/551precipitation intensitysignal filteringdimensional reduction |
spellingShingle | Chih-Wei Lin Xiuping Huang Mengxiang Lin Sidi Hong SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation Sensors precipitation intensity signal filtering dimensional reduction |
title | SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation |
title_full | SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation |
title_fullStr | SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation |
title_full_unstemmed | SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation |
title_short | SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation |
title_sort | sf cnn signal filtering convolutional neural network for precipitation intensity estimation |
topic | precipitation intensity signal filtering dimensional reduction |
url | https://www.mdpi.com/1424-8220/22/2/551 |
work_keys_str_mv | AT chihweilin sfcnnsignalfilteringconvolutionalneuralnetworkforprecipitationintensityestimation AT xiupinghuang sfcnnsignalfilteringconvolutionalneuralnetworkforprecipitationintensityestimation AT mengxianglin sfcnnsignalfilteringconvolutionalneuralnetworkforprecipitationintensityestimation AT sidihong sfcnnsignalfilteringconvolutionalneuralnetworkforprecipitationintensityestimation |