Within the realm of public health, the end-to-end traceability and monitoring of vaccines play an indispensable role in ascertaining the safety and efficacy of vaccines, especially the precise localization of vaccines in the vaccine cold storage. However, challenges such as limited space, dense stacking of boxes, and frequent obstructions in the vaccine cold storage, particularly in Small to Medium Cold Storage (SMCS), pose significant obstacles to effective localizing. Existing vaccine box localizing methods in cold storage, like manual localizing, Radio Frequency Identification (RFID) technology, and traditional visual localizing, struggle with obstructions and inefficiencies, leading to limited accuracy and real-time update capabilities. This paper introduces an innovative solution for vaccine box localization in obstructed environment within SMCS, leveraging computer vision technology. Specifically, to address the challenge of accurately locating vaccine boxes in densely stacked and heavily obstructed SMCS, this paper exploits the strong correlation between the vaccine boxes and workers during the storage process. The vaccine box is indirectly located by focusing on the less numerous and less obstructed cold storage workers. Furthermore, to enhance the tracking accuracy of the workers, the YOLOv5 model was modified, resulting in the development of the Vaccine Cold Storages YOLOV5 (VCS-YOLOv5) model tailored for obstructed environment in SMCS. Additionally, the final location of the vaccine box is determined by a behavior recognition model, identifying instances where the workers' hands are not in contact with the vaccine box. Extensive experiments confirm that VCS-YOLOv5 sets a new benchmark in vaccine box localization and worker tracking, significantly surpassing the performance of standard models in accuracy and real-time effectiveness.INDEX TERMS YOLOv5, object tracking, vaccine box location, small to medium obstructed cold storage, behavior recognition