Detection of ore waste is crucial for achieving automation in mineral metallurgy production.However,deep learning-based target detection algorithms still face several challenges in iron waste screening,including poor ...Detection of ore waste is crucial for achieving automation in mineral metallurgy production.However,deep learning-based target detection algorithms still face several challenges in iron waste screening,including poor lighting conditions in underground mining environments,dust disturbances,platform vibrations during operation,and limited resources for large-scale computing equipment.These factors contribute to extended computation times and unsatisfactory detection accuracy.To address these challenges,this paper proposes an ore waste detection algorithm based on an improved version of YOLOv5.To enhance feature extraction capabilities,the RepLKNet module is incorporated into the YOLOv5 backbone and neck networks.This module enhances the deformation information of feature extraction with the maximum effective Receptive Field to increase the model's accuracy.The Normalizationbased Attention Module(NAM)was introduced to enhance the attention mechanism by focusing on the most relevant features.This improves accuracy in detecting objects against noisy or unclear backgrounds,thereby further enhancing detection performance while reducing model parameters.Additionally,the loss function is optimized to constrain angular deviation using the SIOU loss function,which prevents the training frame from drifting during training and enhances convergence speed.To validate the performance of the proposed method,we tested it using a self-constructed dataset comprising 1,328 images obtained from the crushing station at Jinchuan Group's No.2 mine.The results indicate that,compared to YOLOv5s on the self-constructed dataset,the proposed algorithm achieves an 18.3%improvement in mAP(0.5),a 54%reduction in FLOPs,and a 52.53%decrease in model parameters.The effectiveness and superiority of the proposed algorithm are demonstrated through case studies and comparative analyses.展开更多
基金supported by the Department of science and technology of Shaanxi Province(NO.2023-ZDLGY-24).
文摘Detection of ore waste is crucial for achieving automation in mineral metallurgy production.However,deep learning-based target detection algorithms still face several challenges in iron waste screening,including poor lighting conditions in underground mining environments,dust disturbances,platform vibrations during operation,and limited resources for large-scale computing equipment.These factors contribute to extended computation times and unsatisfactory detection accuracy.To address these challenges,this paper proposes an ore waste detection algorithm based on an improved version of YOLOv5.To enhance feature extraction capabilities,the RepLKNet module is incorporated into the YOLOv5 backbone and neck networks.This module enhances the deformation information of feature extraction with the maximum effective Receptive Field to increase the model's accuracy.The Normalizationbased Attention Module(NAM)was introduced to enhance the attention mechanism by focusing on the most relevant features.This improves accuracy in detecting objects against noisy or unclear backgrounds,thereby further enhancing detection performance while reducing model parameters.Additionally,the loss function is optimized to constrain angular deviation using the SIOU loss function,which prevents the training frame from drifting during training and enhances convergence speed.To validate the performance of the proposed method,we tested it using a self-constructed dataset comprising 1,328 images obtained from the crushing station at Jinchuan Group's No.2 mine.The results indicate that,compared to YOLOv5s on the self-constructed dataset,the proposed algorithm achieves an 18.3%improvement in mAP(0.5),a 54%reduction in FLOPs,and a 52.53%decrease in model parameters.The effectiveness and superiority of the proposed algorithm are demonstrated through case studies and comparative analyses.
