Y
Yoshihide Sekimoto
Researcher at University of Tokyo
Publications - 145
Citations - 2878
Yoshihide Sekimoto is an academic researcher from University of Tokyo. The author has contributed to research in topics: Computer science & Population. The author has an hindex of 21, co-authored 120 publications receiving 1681 citations.
Papers
More filters
Journal ArticleDOI
Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphone.
TL;DR: For the first time, a large-scale road damage dataset is prepared and it is demonstrated that the type of damage can be classified into eight types with high accuracy by applying the proposed object detection method.
Journal ArticleDOI
Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images
Proceedings ArticleDOI
Prediction of human emergency behavior and their mobility following large-scale disaster
TL;DR: A model of human behavior is developed that takes into account social relationship, intensity of disaster, damage level, government appointed shelters, news reporting, large population flow and etc. for accurately predicting human emergency behavior and their mobility following large-scale disaster.
Journal ArticleDOI
Non-compulsory measures sufficiently reduced human mobility in Tokyo during the COVID-19 epidemic.
Takahiro Yabe,Kota Tsubouchi,Naoya Fujiwara,Naoya Fujiwara,Takayuki Wada,Yoshihide Sekimoto,Satish V. Ukkusuri +6 more
TL;DR: By April 15th (1 week into state of emergency), human mobility behavior decreased by around 50%, resulting in a 70% reduction of social contacts in Tokyo, showing the strong relationships with non-compulsory measures.
Journal ArticleDOI
Generative adversarial network for road damage detection
TL;DR: Combining a progressive growing GAN along with Poisson blending artificially generates road damage images that can be used as new training data to improve the accuracy of road damage detection and the new Road Damage Dataset 2019 is released.