Proceedings of the Annual Conference of JSAI
Online ISSN : 2758-7347
34th (2020)
Session ID : 2H5-GS-13-04
Conference information

Detection of the damage from the natural disaster using CCTV image based on GAN
*Ryuto YOSHIDATakato YASUNOJunichiro FUJIJunichi OKUBOMasazumi AMAKATA
Author information
Keywords: GAN, CCTV, anomaly detection
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract

When disasters occur, it is required to understand the damage as soon as possible. And, CCTV camera is good tool to monitor the damage in real time from remote location. However, CCTV camera that depends on visual check causes human errors like oversights. Purpose of this study is to develop methods that detects the damage automatically. Especially, this study focuses on the anomaly detection using GAN. As a result of this study, it was possible to detect the damage under simple condition.

Content from these authors
© 2020 The Japanese Society for Artificial Intelligence
Previous article Next article
feedback
Top