Citation

Salem, Mohammed Ahmed and Besar, Rosli and Abdulkareem, Abdulaziz Mohsen and Abas, Fazly Salleh and Abd Aziz, Azlan and Amir Hamzah, Nur Asyiqin and Ab Aziz, Nor Azlina (2025) Human Motion Detection in Work Environment: A Survey. In: 2025 Multimedia University Engineering Conference, MECON 2025, 21 July 2025 - 23 July 2025, Cyberjaya, Malaysia.

Text 4.pdf - Published Version Restricted to Repository staff only Download (985kB)

Abstract

Monitoring human motion in workspace environments is essential for ensuring safety, improving productivity, and managing real-time risks. In recent years, advancements in computer vision, deep learning, and sensorbased systems have enabled more accurate detection of worker movements and activities. However, applying these technologies in dynamic, cluttered, and privacy-sensitive workspace environments comes with significant challenges. This paper presents a systematic literature review (SLR) that explores the current state of human motion detection in workspace settings. It reviews existing technologies, real-world applications, and highlights key limitations, including the lack of specialized datasets, real-time processing constraints, and privacy concerns. The paper also identifies open research opportunities, such as developing large, multimodal datasets, lightweight models for onsite use, privacy-preserving recognition techniques, and effective multi-sensor data fusion. The findings aim to guide future research and contribute to the development of smarter, safer, and more reliable motion detection systems for modern workspace environments.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Computer vision, deep learning
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	18 Mar 2026 08:15
Last Modified:	19 Mar 2026 01:57
URII:	http://shdl.mmu.edu.my/id/eprint/15584

Downloads

Edit (login required)