2025 年 16 巻 論文ID: PP3938
Container handling in the terminals have been facing an increase of freight volume. To streamline container operations and adapt to DX (digital transformation) with evolving landscape, automation has been introduced across many terminals. However, work safety in container terminal is the top priority through ages and some of the container handling operation still need improvement. Nevertheless, certain aspects of container handling still rely on human reliability, posing potential risks of damage to human, containers, trucks, and machinery. This paper presents a computer vision-based approach to (1) identify drivers’ safety manner around container locking areas, (2) to detect the manual process of locking containers onto truck trailers, and (3) tracking the number of objects passing through the out-gate. Continuous monitoring of these procedures aids in reducing the occurrence of accidents and enhances driver’s awareness of their surroundings, thereby reinforcing safety in the working environment.