As automation technologies become increasingly prevalent at bulk cargo terminals, efficient and accurate target detection and localization technologies are crucial. This paper proposes an enhanced YOLOv5 detection method, incorporating a CA mechanism to effectively enhance the model's extraction of spatial information, thereby improving the accuracy of target localization. Moreover, the IoU loss function is modified to SIoU, optimizing the impact of bounding box scaling and rotation on predictive performance. To further enhance the localization accuracy of bulk unloading hoppers, this study introduces a secondary localization method based on traditional morphological algorithms, capable of precisely detecting the position of the hopper. Experimental results demonstrate that the proposed methods achieve high accuracy and reliability in detecting vehicles and bulk unloading hoppers at bulk cargo terminals.

--

Channel attention mechanism,Target localization,Bulk cargo terminals

• Other Engineering and Technology Sciences - Engineering and Technology
• Electrical Engineering, Electronic Engineering, Information Engineering - Engineering and Technology