Ensemble Deep Learning for Automated Damage Detection of Trailers at Intermodal Terminals

Abstract

Efficient damage detection of trailers is essential for improving processes at inland intermodal terminals. This paper presents an automated damage detection (ADD) algorithm for trailers utilizing ensemble learning based on YOLOv8 and RetinaNet networks. The algorithm achieves 88.33% accuracy and an 81.08% F1-score on the real-life trailer damage dataset by leveraging the strengths of each object detection model. YOLOv8 is trained explicitly for detecting belt damage, while RetinaNet handles detecting other damage types and is used for cropping trailers from images. These one-stage detectors outperformed the two-stage Faster R-CNN in all tested tasks within this research. Furthermore, the algorithm incorporates slice-aided hyper inference, which significantly contributes to the efficient processing of high-resolution trailer images. Integrating the proposed ADD solution into terminal operating systems allows a substantial workload reduction at the ingate of intermodal terminals and supports, therefore, more sustainable transportation solutions.