Articles | Volume 18, issue 20
https://doi.org/10.5194/amt-18-5457-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-18-5457-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
17 Oct 2025
Research article |
| 17 Oct 2025
| 17 Oct 2025
Surveillance Camera-Based Deep Learning Framework for High-Resolution Near Surface Precipitation Type Observation
Xing Wang
School of Computer Engineering, Nanjing Institute of Technology, Nanjing, 211167, China
School of Atmospheric Sciences, Nanjing University, Jiangsu 210023, China
Key Laboratory of Radar Meteorology and State Key Laboratory of Severe Weather, China Meteorology Administration, Beijing 100044, China
Kun Zhao
CORRESPONDING AUTHOR
School of Atmospheric Sciences, Nanjing University, Jiangsu 210023, China
Key Laboratory of Radar Meteorology and State Key Laboratory of Severe Weather, China Meteorology Administration, Beijing 100044, China
Hao Huang
School of Atmospheric Sciences, Nanjing University, Jiangsu 210023, China
Key Laboratory of Radar Meteorology and State Key Laboratory of Severe Weather, China Meteorology Administration, Beijing 100044, China
Ang Zhou
School of Atmospheric Sciences, Nanjing University, Jiangsu 210023, China
Key Laboratory of Radar Meteorology and State Key Laboratory of Severe Weather, China Meteorology Administration, Beijing 100044, China
Haiqin Chen
School of Atmospheric Sciences, Nanjing University, Jiangsu 210023, China
Key Laboratory of Radar Meteorology and State Key Laboratory of Severe Weather, China Meteorology Administration, Beijing 100044, China
Cited articles
Aloufi, N., Alnori, A., and Basuhail, A. J. E.: Enhancing Autonomous Vehicle Perception in Adverse Weather: A Multi Objectives Model for Integrated Weather Classification and Object Detection, Electronics, 13, 3063, https://doi.org/10.3390/electronics13153063, 2024.
Arienzo, M. M., Collins, M., and Jennings, K. S.: Enhancing engagement of citizen scientists to monitor precipitation phase, Frontiers in Earth Science, 9, 617594, https://doi.org/10.3389/feart.2021.617594, 2021.
Askbom, L.: Road condition classification from CCTV images using machine learning, MS thesis, https://odr.chalmers.se/server/api/core/bitstreams/39745dde-45d6-4c9a-9621-fd1c611d8ef7/content (last access: 7 October 2025), 2023.
Atlas, D., Srivastava, R., and Sekhon, R. S.: Doppler radar characteristics of precipitation at vertical incidence, Reviews of Geophysics, 11, 1–35, https://doi.org/10.1029/rg011i001p00001, 1973.
Bharadwaj, H. S., Biswas, S., and Ramakrishnan, K.: A large scale dataset for classification of vehicles in urban traffic scenes, Proceedings of the Tenth Indian Conference on Computer Vision, Graphics and Image Processing, 2016, 1–8, https://doi.org/10.1145/3009977.3010040, 2016.
Brandes, E. A., Ikeda, K., Zhang, G., Schönhuber, M., and Rasmussen, R. M.: A statistical and physical description of hydrometeor distributions in Colorado snowstorms using a video disdrometer, Journal of Applied Meteorology and Climatology, 46, 634–650, https://doi.org/10.1175/JAM2489.1, 2007.
Carr, S. and Kennedy, K.: Improving the ratio of memory operations to floating-point operations in loops, ACM Transactions on Programming Languages and Systems (TOPLAS), 16, 1768–1810, https://doi.org/10.1145/197320.197366, 1994.
Carrillo, J. and Crowley, M.: Integration of roadside camera images and weather data for monitoring winter road surface conditions, arXiv [preprint], https://doi.org/10.48550/arXiv.2009.12165, 2020.
Casellas, E., Bech, J., Veciana, R., Pineda, N., Rigo, T., Miró, J. R., and Sairouni, A.: Surface precipitation phase discrimination in complex terrain, Journal of Hydrology, 592, 125780, https://doi.org/10.1016/j.jhydrol.2020.125780, 2021a.
Casellas, E., Bech, J., Veciana, R., Pineda, N., Miró, J. R., Moré, J., Rigo, T., and Sairouni, A.: Nowcasting the precipitation phase combining weather radar data, surface observations, and NWP model forecasts, Quarterly Journal of the Royal Meteorological Society, 147, 3135–3153, https://doi.org/10.1002/qj.4121, 2021b.
Chen, S., Shu, T., Zhao, H., and Tang, Y. Y.: MASK-CNN-Transformer for real-time multi-label weather recognition, Knowledge-Based Systems, 278, 110881, https://doi.org/10.2139/ssrn.4431880, 2023.
Chu, W.-T., Zheng, X.-Y., and Ding, D.-S.: Camera as weather sensor: Estimating weather information from single images, Journal of Visual Communication and Image Representation, 46, 233–249, https://doi.org/10.1016/j.jvcir.2017.04.002, 2017.
Crimmins, T. and Posthumus, E.: Do Carefully Timed Email Messages Increase Accuracy and Precision in Citizen Scientists' Reports of Events?, Citizen Science: Theory and Practice, 7, https://doi.org/10.5334/cstp.464, 2022.
Dahmane, K., Duthon, P., Bernardin, F., Colomb, M., Blanc, C., and Chausse, F.: Weather classification with traffic surveillance cameras, Proceedings of the 25th ITS World Congress, https://www.cerema.fr/system/files/documents/2018/09/Dahmane_ITS2018.pdf (last access: 30 September 2025), 2018.
Dahmane, K., Duthon, P., Bernardin, F., Colomb, M., Chausse, F., and Blanc, C.: Weathereye-proposal of an algorithm able to classify weather conditions from traffic camera images, Atmosphere, 12, 717, https://doi.org/10.3390/atmos12060717, 2021.
Dhananjaya, M. M., Kumar, V. R., and Yogamani, S.: Weather and light level classification for autonomous driving: Dataset, baseline and active learning, 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), 2816–2821, https://doi.org/10.1109/ITSC48978.2021.9564689, 2021.
Guerra, J. C. V., Khanam, Z., Ehsan, S., Stolkin, R., and McDonald-Maier, K.: Weather Classification: A new multi-class dataset, data augmentation approach and comprehensive evaluations of Convolutional Neural Networks, 2018 NASA/ESA Conference on Adaptive Hardware and Systems (AHS), 305–310, https://doi.org/10.1109/ahs.2018.8541482, 2018.
Haberlie, A. M., Ashley, W. S., and Pingel, T. J.: The effect of urbanisation on the climatology of thunderstorm initiation, Quarterly Journal of the Royal Meteorological Society, 141, 663–675, https://doi.org/10.1002/qj.2499, 2015.
He, K., Zhang, X., Ren, S., and Sun, J.: Deep residual learning for image recognition, Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016.
Heymsfield, A. and Wright, R.: Graupel and hail terminal velocities: Does a “supercritical” Reynolds number apply?, Journal of the Atmospheric Sciences, 71, 3392–3403, https://doi.org/10.1175/jas-d-14-0034.1, 2014.
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q.: Densely connected convolutional networks, Proceedings of the IEEE conference on computer vision and pattern recognition, 4700–4708, https://doi.org/10.1109/CVPR.2017.243, 2017.
Huang, Z., Xu, W., and Yu, K.: Bidirectional LSTM-CRF models for sequence tagging, arXiv [preprint], https://doi.org/10.48550/arXiv.1508.01991, 2015.
Ibrahim, M. R., Haworth, J., and Cheng, T.: WeatherNet: Recognising weather and visual conditions from street-level images using deep residual learning, ISPRS International Journal of Geo-Information, 8, 549, https://doi.org/10.3390/ijgi8120549, 2019.
Jennings, K. S., Arienzo, M. M., Collins, M., Hatchett, B. J., Nolin, A. W., and Aggett, G.: Crowdsourced Data Highlight Precipitation Phase Partitioning Variability in Rain-Snow Transition Zone, Earth and Space Science, 10, e2022EA002714, https://doi.org/10.1029/2022ea002714, 2023.
Kajikawa, M.: Measurement of falling velocity of individual graupel particles, Journal of the Meteorological Society of Japan. Ser. II, 53, 476–481, https://doi.org/10.2151/jmsj1965.53.6_476, 1975.
Karaa, M., Ghazzai, H., and Sboui, L.: A dataset annotation system for snowy weather road surface classification, IEEE Open Journal of Systems Engineering, https://doi.org/10.1109/ojse.2024.3391326, 2024.
Khan, M. N. and Ahmed, M. M.: Weather and surface condition detection based on road-side webcams: Application of pre-trained convolutional neural network, International Journal of Transportation Science Technology, 11, 468–483, https://doi.org/10.1016/j.ijtst.2021.06.003, 2022.
Kiranyaz, S., Avci, O., Abdeljaber, O., Ince, T., Gabbouj, M., and Inman, D. J.: 1D convolutional neural networks and applications: A survey, Mechanical Systems and Signal Processing, 151, 107398, https://doi.org/10.1109/access.2024.3433513, 2021.
Kondapally, M., Kumar, K. N., Vishnu, C., and Mohan, C. K.: Towards a transitional weather scene recognition approach for autonomous vehicles, IEEE Transactions on Intelligent Transportation Systems, 25, 5201–5210, https://doi.org/10.1109/TITS.2023.3331882, 2023.
Kruger, A. and Krajewski, W. F.: Two-dimensional video disdrometer: A description, Journal of Atmospheric and Oceanic Technology, 19, 602–617, https://doi.org/10.1175/1520-0426(2002)019<0602:TDVDAD>2.0.CO;2, 2002.
Kurihata, H., Takahashi, T., Ide, I., Mekada, Y., Murase, H., Tamatsu, Y., and Miyahara, T.: Rainy weather recognition from in-vehicle camera images for driver assistance, IEEE Proceedings Intelligent Vehicles Symposium, 2005, 205–210, https://doi.org/10.1109/IVS.2005.1505103, 2005.
Landry, F.-G. and Akhloufi, M. A.: Deep learning and computer vision techniques for estimating snow coverage on roads using surveillance cameras, 2022 18th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 1–8, https://doi.org/10.1109/avss56176.2022.9959452, 2022.
Lee, I. J.: Big data processing framework of learning weather information and road traffic collision using distributed CEP from CCTV video: Cognitive image processing, 2017 IEEE 16th International Conference on Cognitive Informatics & Cognitive Computing (ICCI* CC), 400–406, https://doi.org/10.1109/ICCI-CC.2017.8109780, 2017.
Leroux, N. R., Vionnet, V., and Thériault, J. M.: Performance of precipitation phase partitioning methods and their impact on snowpack evolution in a humid continental climate, Hydrological Processes, 37, e15028, https://doi.org/10.1002/hyp.15028, 2023.
Li, Q., Kong, Y., and Xia, S.-M.: A method of weather recognition based on outdoor images, 2014 International Conference on Computer Vision Theory and Applications, 510–516, https://doi.org/10.5220/0004724005100516, 2014.
Li, S., Ren, W., Wang, F., Araujo, I. B., Tokuda, E. K., Junior, R. H., Cesar Jr., R. M., Wang, Z., and Cao, X.: A comprehensive benchmark analysis of single image deraining: Current challenges and future perspectives, International Journal of Computer Vision, 129, 1301–1322, https://doi.org/10.1007/s11263-020-01416-w, 2021.
Lu, C., Lin, D., Jia, J., and Tang, C.-K.: Two-class weather classification, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3718–3725, https://doi.org/10.1109/cvpr.2014.475, 2014.
Lü, M.-c., Liu, D., and Zhang, X.-j.: Study on Road Weather Recognition Method Based on Road Segmentation, Journal of Highway and Transportation Research and Development, 17, 26–35, https://doi.org/10.1061/jhtrcq.0000871, 2023.
Magono, C. and Lee, C. W.: Meteorological classification of natural snow crystals, Journal of the Faculty of Science, Hokkaido University, Series 7, Geophysics, 2, 321–335, https://doi.org/10.4159/harvard.9780674182769.c12, 1966.
Mishchenko, M. I., Travis, L. D., and Lacis, A. A.: Scattering, absorption, and emission of light by small particles, Cambridge University Press, https://doi.org/10.1016/0960-1686(93)90104-7, 2002.
Mittal, S. and Sangwan, O. P.: Classifying weather images using deep neural networks for large scale datasets, International Journal of Advanced Computer Science and Applications, 14, https://doi.org/10.14569/ijacsa.2023.0140136, 2023.
Montero-Martínez, G., Kostinski, A. B., Shaw, R. A., and García-García, F.: Do all raindrops fall at terminal speed?, Geophysical Research Letters, 36, https://doi.org/10.1029/2008gl037111 2009.
Morris, C. and Yang, J. J.: A machine learning model pipeline for detecting wet pavement condition from live scenes of traffic cameras, Machine Learning with Applications, 5, 100070, https://doi.org/10.1016/j.mlwa.2021.100070, 2021.
Pavlic, M., Rigoll, G., and Ilic, S.: Classification of images in fog and fog-free scenes for use in vehicles, 2013 IEEE Intelligent Vehicles Symposium (IV), 481–486, https://doi.org/10.1109/ivs.2013.6629514, 2013.
Pruppacher, H. R. and Klett, J. D.: Microphysics of Clouds and Precipitation, Nature, 284, 88–88, https://doi.org/10.1038/284088b0, 1980.
Ramanna, S., Sengoz, C., Kehler, S., and Pham, D.: Near real-time map building with multi-class image set labeling and classification of road conditions using convolutional neural networks, Applied Artificial Intelligence, 35, 803–833, https://doi.org/10.1080/08839514.2021.1935590, 2021.
Roser, M. and Moosmann, F.: Classification of weather situations on single color images, 2008 IEEE Intelligent Vehicles Symposium, 798–803, https://doi.org/10.1109/ivs.2008.4621205, 2008.
Rump, S. M., Ogita, T., and Oishi, S. i.: Accurate floating-point summation part I: Faithful rounding, SIAM Journal on Scientific Computing, 31, 189–224, https://doi.org/10.1137/050645671, 2008.
Samo, M., Mafeni Mase, J. M., and Figueredo, G.: Deep Learning with Attention Mechanisms for Road Weather Detection, Sensors, 23, 798, https://doi.org/10.3390/s23020798, 2023.
Schirmacher, I., Schnitt, S., Klingebiel, M., Maherndl, N., Kirbus, B., and Crewell, S.: Clouds and precipitation in the initial phase of marine cold air outbreaks as observed by airborne remote sensing, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-5220, https://doi.org/10.5194/egusphere-egu24-5220, 2024.
Shibata, K., Takeuch, K., Kawai, S., and Horita, Y.: Detection of road surface conditions in winter using road surveillance cameras at daytime, night-time and twilight, International Journal of Computer Science and Network Security (IJCSNS), 14, 21, 2014.
Speirs, P., Gabella, M., and Berne, A.: A comparison between the GPM dual-frequency precipitation radar and ground-based radar precipitation rate estimates in the Swiss Alps and Plateau, Journal of Hydrometeorology, 18, 1247–1269, https://doi.org/10.1175/jhm-d-16-0085.1, 2017.
Sun, Z., Wang, P., Jin, Y., Wang, J., and Wang, L.: A practical weather detection method built in the surveillance system currently used to monitor the large-scale freeway in China, IEEE Access, 8, 112357–112367, https://doi.org/10.1109/access.2020.3002959, 2020.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z.: Rethinking the inception architecture for computer vision, Proceedings of the IEEE Conference on Computer Sision and Pattern Recognition, 2818–2826, 2016.
Tan, M. and Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks, International Conference on Machine Learning, 6105–6114, https://doi.org/10.48550/arXiv.1905.11946, 2019.
Toğaçar, M., Ergen, B., and Cömert, Z.: Detection of weather images by using spiking neural networks of deep learning models, Neural Computing and Applications, 33, 6147–6159, https://doi.org/10.1007/s00521-020-05388-3, 2021.
Triva, J., Grbić, R., Vranješ, M., and Teslić, N.: Weather Condition Classification in Vehicle Environment Based on Front-View Camera Images, 2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH), 1–4, https://doi.org/10.1109/infoteh53737.2022.9751279, 2022.
Vázquez-Martín, S., Kuhn, T., and Eliasson, S.: Shape dependence of snow crystal fall speed, Atmos. Chem. Phys., 21, 7545–7565, https://doi.org/10.5194/acp-21-7545-2021, 2021.
Wang, H., Xie, Q., Wu, Y., Zhao, Q., and Meng, D.: Single image rain streaks removal: a review and an exploration, International Journal of Machine Learning and Cybernetics, 11, 853–872, https://doi.org/10.1007/s13042-020-01061-2, 2020.
Wang, S., Li, Y., and Liu, W.: Multi-class weather classification fusing weather dataset and image features, Big Data: 6th CCF Conference, Big Data 2018, Xi'an, China, 11–13 October 2018, Proceedings 6, 149–159, https://doi.org/10.1007/978-981-13-2922-7_10, 2018.
Wang, X.: Surveillance Camera-Based Deep Learning Framework for High-Resolution Near Surface Precipitation Type Observation, TIB AV-Portal [video], https://doi.org/10.5446/71534, 2024.
Wang, X., Shi, S., Zhu, L., Nie, Y., and Lai, G.: Traditional and Novel Methods of Rainfall Observation and Measurement: A Review, Journal of Hydrometeorology, 24, 2153–2176, https://doi.org/10.1175/jhm-d-22-0122.1, 2023a.
Wang, X., Yang, Z., Feng, H., Zhao, J., Shi, S., and Cheng, L.: A Multi-Stream Attention-Aware Convolutional Neural Network: Monitoring of Sand and Dust Storms from Ordinary Urban Surveillance Cameras, Remote Sensing, 15, 5227, https://doi.org/10.3390/rs15215227, 2023b.
World Meteorological Organization (WMO): Manual on the Observation of Clouds and Other Meteors-International Cloud Atlas (WMO-No. 407), https://cloudatlas.wmo.int/en/home.html (last access: 12 August 2025), 2017.
Xia, J., Xuan, D., Tan, L., and Xing, L.: ResNet15: weather recognition on traffic road with deep convolutional neural network, Advances in Meteorology, 2020, 6972826, https://doi.org/10.1155/2020/6972826, 2020.
Xiao, H., Zhang, F., Shen, Z., Wu, K., and Zhang, J.: Classification of weather phenomenon from images by using deep convolutional neural network, Earth and Space Science, 8, e2020EA001604, https://doi.org/10.1029/2020ea001604, 2021.
Zhang, C., Nateghinia, E., Miranda-Moreno, L. F., and Sun, L.: Winter road surface condition classification using convolutional neural network (CNN): visible light and thermal image fusion, Canadian Journal of Civil Engineering, 49, 569–578, https://doi.org/10.1139/cjce-2020-0613, 2022.
Zhang, G.: Weather radar polarimetry, Crc Press, ISBN 9781315374666, 2016.
Zhao, B., Li, X., Lu, X., and Wang, Z.: A CNN–RNN architecture for multi-label weather recognition, Neurocomputing, 322, 47–57, https://doi.org/10.1016/j.neucom.2018.09.048, 2018.
Zhao, X., Liu, P., Liu, J., and Tang, X.: Feature extraction for classification of different weather conditions, Frontiers of Electrical and Electronic Engineering in China, 6, 339–346, https://doi.org/10.1007/s11460-011-0151-1, 2011.
Zhou, A., Zhao, K., Lee, W.-C., Huang, H., Hu, D., and Fu, P.: VDRAS and Polarimetric Radar Investigation of a Bow Echo Formation After a Squall Line Merged With a Preline Convective Cell, Journal of Geophysical Research: Atmospheres, 125, e2019JD031719, https://doi.org/10.1029/2019JD031719, 2020.
Short summary
Surveillance cameras have emerged as a new low-cost, high-resolution Near Surface Precipitation Type observer. A novel deep learning approach is developed to classify rain, snow, and graupel, achieving 93 % accuracy in real-world observations. The model remains robust to camera parameter variations and maintains reliable performance at wind speeds below 5 m s−1, demonstrating strong potential for large-scale practical applications.
Surveillance cameras have emerged as a new low-cost, high-resolution Near Surface Precipitation...
