Detecting Human Actions in Drone Images Using YoloV5 and Stochastic Gradient Boosting

• Published in: Sensors Vol. 22; no. 18; p. 7020
• Main Authors: Ahmad, Tasweer, Cavazza, Marc, Matsuo, Yutaka, Prendinger, Helmut
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 16.09.2022; MDPI
• Subjects: action detection; action detection; YoloV5; gradient boosting classifier; Adaptation; Cameras; Chemical technology; Datasets; Deep learning; Drone aircraft; Drones; Environmental monitoring; Evacuations & rescues; gradient boosting classifier; Human Activities; Humans; Localization; Machine Learning; Methods; Neural networks; Sensors; TP1-1185; Unmanned Aerial Devices; Unmanned aerial vehicles; YoloV5; Japan

Human action recognition and detection from unmanned aerial vehicles (UAVs), or drones, has emerged as a popular technical challenge in recent years, since it is related to many use case scenarios from environmental monitoring to search and rescue. It faces a number of difficulties mainly due to ima...