Japan Geoscience Union Meeting 2022

Presentation information

[J] Poster

M (Multidisciplinary and Interdisciplinary) » M-GI General Geosciences, Information Geosciences & Simulations

[M-GI35] Earth and planetary informatics with huge data management

Mon. May 30, 2022 11:00 AM - 1:00 PM Online Poster Zoom Room (38) (Ch.38)

convener:Ken T. Murata(National Institute of Information and Communications Technology), convener:Susumu Nonogaki(Geological Survey of Japan, National Institute of Advanced Industrial Science and Technology), Rie Honda(Department of Science and Technology, System of Natual Science, Kochi University), convener:Keiichiro Fukazawa(Academic Center for Computing and Media Studies, Kyoto University), Chairperson:Keiichiro Fukazawa(Academic Center for Computing and Media Studies, Kyoto University), Susumu Nonogaki(Geological Survey of Japan, National Institute of Advanced Industrial Science and Technology), Rie Honda(Department of Science and Technology, System of Natual Science, Kochi University), Ken T. Murata(National Institute of Information and Communications Technology)

11:00 AM - 1:00 PM

[MGI35-P09] Real-time snowfall detection with visual IoT system

*Kazutaka Kikuta1, Yuki MURAKAMI1, Ken T. Murata1 (1.National Institute of Information and Communications Technology)

Keywords:Visual IoT, Automatic detection

We propose a snowfall detection method using a mobile detection algorithm based on video IoT technology. Video IoT is a new concept IoT sensor which installed outdoors and can acquire high-resolution and high-time-resolution video. This time, we installed commercially available IP cameras, which have high cost performance and are easy to install in various positions. Using a single board computer (Raspberry Pi) on the edge side with the IP camera, a flexible operation such as acquiring a few seconds of video every few minutes is possible. This system can acquire data of the size and the number of snowflakes from videos. It is possible to detect the snow area from the image difference between the video frames and determine the degree of snowfall from the area and the number of snow areas. The shape and distribution of snowflakes reflected in the camera image change depending on the day and night (visible light and infrared light) and the installation position. In this study, we created a certain index regardless of the camera installation position from the information on the depth of the camera field of view and the snowfall observable area and organized the data obtained at various observation locations. With this method, automatic snowfall detection was realized from 1080p and 25fps videos.