<p>Ore particle size distribution is an important metric for evaluating blasting outcomes and affects the energy consumption of ore crushing equipment. Faced with dense accumulation of ore, nonuniform size distributions, dust occlusion, and target loss due to motion, using computer vision methods, we propose a blasting ore size detection method based on efficient dehazing network and multi-dimensional feature fusion, which is an improvement to YOLOv8. Firstly, we constructs an efficient defogging backbone network that combines feature attention and composite scalable backbone so that the model can efficiently extract the features of ore images and enhance the robustness of the model to dust interference in the ore crushing process. Secondly, we introduces a new feature fusion network that combines the convolution model and the Vmamba sequence model as well as cross-layer fusion of multi-scale features so that the model can effectively adapt to the dramatic scale change of blasting ore, capture fine ore and large-size ore, avoid ore omission, and improve the accuracy of particle size statistics. Finally, the multi-dimensional feature fusion ability of Dynamic Head was introduced to optimize the target detection head, and the feature fusion was further optimized so that the feature tensor obtained from the ore image was adapted to the detection and positioning task of ore, and the discrimination ability of the model for ore was improved. Experiments were conducted on a manually labeled jaw fracture ore dataset. Compared to the YOLOv8n algorithm, the average precision (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\overline{P}\)</EquationSource> </InlineEquation>) for detecting eight size categories of ore increased by 7%. On datasets containing interference such as smoke, dust, and wet conditions, the mean average precision at the IoU threshold of 0.5 (mAP50) improved by 7.6%. For fine ores below D5 (72 mm), the detection precision (<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\overline{P}\)</EquationSource> </InlineEquation>) increased by 18.8%, while the recall rate (<InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(\overline{R}\)</EquationSource> </InlineEquation>) rose by 13.8%. On the total one-class dataset, the recall rate (<InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(\overline{R}\)</EquationSource> </InlineEquation>) and mAP50 reached 84% and 88.1%, respectively.</p>

Blasting ore size detection based on efficient dehazing network and multi-dimensional feature fusion

期刊论文
出版模式：

开放获取
发表日期：

2026年2月28日

查看全文

Pingfeng Li,
Shoudong Xie,
Wanzhong Zhang,
Deming Chen,
Sheng Peng,
Weibin Fang,
Dehao Zeng

摘要

Ore particle size distribution is an important metric for evaluating blasting outcomes and affects the energy consumption of ore crushing equipment. Faced with dense accumulation of ore, nonuniform size distributions, dust occlusion, and target loss due to motion, using computer vision methods, we propose a blasting ore size detection method based on efficient dehazing network and multi-dimensional feature fusion, which is an improvement to YOLOv8. Firstly, we constructs an efficient defogging backbone network that combines feature attention and composite scalable backbone so that the model can efficiently extract the features of ore images and enhance the robustness of the model to dust interference in the ore crushing process. Secondly, we introduces a new feature fusion network that combines the convolution model and the Vmamba sequence model as well as cross-layer fusion of multi-scale features so that the model can effectively adapt to the dramatic scale change of blasting ore, capture fine ore and large-size ore, avoid ore omission, and improve the accuracy of particle size statistics. Finally, the multi-dimensional feature fusion ability of Dynamic Head was introduced to optimize the target detection head, and the feature fusion was further optimized so that the feature tensor obtained from the ore image was adapted to the detection and positioning task of ore, and the discrimination ability of the model for ore was improved. Experiments were conducted on a manually labeled jaw fracture ore dataset. Compared to the YOLOv8n algorithm, the average precision ( \(\overline{P}\) ) for detecting eight size categories of ore increased by 7%. On datasets containing interference such as smoke, dust, and wet conditions, the mean average precision at the IoU threshold of 0.5 (mAP50) improved by 7.6%. For fine ores below D5 (72 mm), the detection precision ( \(\overline{P}\) ) increased by 18.8%, while the recall rate ( \(\overline{R}\) ) rose by 13.8%. On the total one-class dataset, the recall rate ( \(\overline{R}\) ) and mAP50 reached 84% and 88.1%, respectively.