Abstract

--- - Highlights The proposed Deep Risk Network (DRN) architecture, combined with a feature-based transfer learning strategy, significantly improves safety risk detection performance in previously unseen industrial scenarios using only 10-25% of new annotated data. DRN consistently outperforms commercial solutions like AWS Rekognition and NVIDIA DeepStream in both binary and multi-class classification tasks, particularly under do-main shifts and resource-constrained edge deployments. What are the main findings? A dual-stage deep learning architecture (Deep Risk Network) combined with feature-based transfer learning improves safety risk detection across diverse industrial video scenarios using limited new data. The proposed system outperforms commercial platforms (AWS Rekognition and NVIDIA DeepStream) in both classification accuracy and inference efficiency under domain shifts. What is the implication of the main finding? Safety monitoring systems can be deployed and adapted to new industrial environments with minimal annotated data and low computational cost. Transfer learning not only enhances model generalization but also improves interpretability by shifting focus toward safety-critical visual features.Highlights The proposed Deep Risk Network (DRN) architecture, combined with a feature-based transfer learning strategy, significantly improves safety risk detection performance in previously unseen industrial scenarios using only 10-25% of new annotated data. DRN consistently outperforms commercial solutions like AWS Rekognition and NVIDIA DeepStream in both binary and multi-class classification tasks, particularly under do-main shifts and resource-constrained edge deployments. What are the main findings? A dual-stage deep learning architecture (Deep Risk Network) combined with feature-based transfer learning improves safety risk detection across diverse industrial video scenarios using limited new data. The proposed system outperforms commercial platforms (AWS Rekognition and NVIDIA DeepStream) in both classification accuracy and inference efficiency under domain shifts. What is the implication of the main finding? Safety monitoring systems can be deployed and adapted to new industrial environments with minimal annotated data and low computational cost. Transfer learning not only enhances model generalization but also improves interpretability by shifting focus toward safety-critical visual features.Highlights The proposed Deep Risk Network (DRN) architecture, combined with a feature-based transfer learning strategy, significantly improves safety risk detection performance in previously unseen industrial scenarios using only 10-25% of new annotated data. DRN consistently outperforms commercial solutions like AWS Rekognition and NVIDIA DeepStream in both binary and multi-class classification tasks, particularly under do-main shifts and resource-constrained edge deployments. What are the main findings? A dual-stage deep learning architecture (Deep Risk Network) combined with feature-based transfer learning improves safety risk detection across diverse industrial video scenarios using limited new data. The proposed system outperforms commercial platforms (AWS Rekognition and NVIDIA DeepStream) in both classification accuracy and inference efficiency under domain shifts. What is the implication of the main finding? Safety monitoring systems can be deployed and adapted to new industrial environments with minimal annotated data and low computational cost. - Transfer learning not only enhances model generalization but also improves interpretability by shifting focus toward safety-critical visual features.Abstract This paper proposes a transfer learning-based approach to enhance video-driven safety risk detection in industrial environments, addressing the critical challenge of limited generalization across diverse operational scenarios. Conventional deep learning models trained on specific operational contexts often fail when applied to new environments with different lighting, camera angles, or machinery configurations, exhibiting a significant drop in performance (e.g., F1-score declining below 0.85). To overcome this issue, an incremental feature transfer learning strategy is introduced, enabling efficient adaptation of risk detection models using only small amounts of data from new scenarios. This approach leverages prior knowledge from pre-trained models to reduce the reliance on large-labeled datasets, particularly valuable in industrial settings where rare but critical safety risk events are difficult to capture. Additionally, training efficiency is improved compared with a classic approach, supporting deployment on resource-constrained edge devices. The strategy involves incremental retraining using video segments with average durations ranging from 2.5 to 25 min (corresponding to 5-50% of new scenario data), approximately, enabling scalable generalization across multiple forklift-related risk activities. Interpretability is enhanced through SHAP-based analysis, which reveals a redistribution of feature relevance toward critical components, thereby improving model transparency and reducing annotation demands. Experimental results confirm that the transfer learning strategy significantly improves detection accuracy, robustness, and adaptability, making it a practical and scalable solution for safety monitoring in dynamic industrial environments.