Fujitsu (Japan)

Recognition-Guided Generative Skeleton Imputation for Robust Action Recognition Under Severe Occlusion in Construction Scenarios

Skeleton-based human action recognition can support digital construction and renovation monitoring by converting worker motions into structured information for safety and process management. However, workers are often occluded by tools, materials, furniture, and temporary structu...

Eliminating Temporal Misalignment in SAR Flood Detection with a ConvLSTM-Siamese Approach Using Sentinel-1 Time Series

Abstract. Flood risk has been increasing worldwide due to climate change and rapid urbanization. Rapid and accurate flood mapping is essential for reducing damage and supporting rescue activities. Synthetic Aperture Radar (SAR) has been widely used for flood monitoring because it...

Rectangular vs Hexagonal Grid Tessellation for Spatial Analysis of Invasive Species: A Case Study of Aromia bungii in Saitama, Japan

Abstract. Aromia bungii has established persistent infestations across Saitama Prefecture, Japan, yet the influence of grid tessellation and spatial weight configuration on the detection of infestation clustering patterns remains poorly understood. This study evaluated whether re...