HCFF-Net: A Hybrid Contextual Feature Fusion Network for Robust Heavy Equipment Classification in Complex Construction Environments

초록

Construction equipment plays a crucial role in performing essential tasks such as construc-tion, demolition, and other maintenance. These machines enable workers to accomplishtasks that would otherwise be extremely difficult or impossible manually, significantlyenhancing efficiency and productivity. Heavy construction equipment classification is acritical component of intelligent construction monitoring systems; however, existing vision-based methods often struggle under real-world conditions such as occlusion, backgroundclutter, and scale variation. To address these challenges, this study proposes HCFF-Net,a hybrid contextual feature fusion network designed to enhance classification robustnessin complex construction environments. The proposed framework integrates a diversereceptive residual fusion (DRRF) block to capture multi-scale local and global features anda global contextual channel recalibration (GCCR) module to adaptively refine channel-wise representations using contextual information. Unlike conventional feature fusionstrategies, HCFF-Net effectively combines structural and contextual features to improvediscriminative capability under challenging visual conditions. For performance evalua-tion, experiments were performed on the publicly available Alberta Construction ImageDataset (ACID). The proposed HCFF-Net achieves a classification accuracy of 90.60% andan F1-score of 90.05% across multiple equipment categories, outperforming state-of-the-artmethods, validating its effectiveness for intelligent safety monitoring and management inconstruction environments.

키워드