Feature detection of mineral zoning in spiral slope flow under complex conditions based on improved YOLOv5 algorithm

Abstract In actual processing plants, the quality and efficiency of the traditional spiral slope flow concentrator still rely on workers to observe the changes in the mineral belt. However, in realistic complex working conditions, the formation of mineral separation zones is subject to large uncertainties, and coupled with the limited efforts, experience, and responsibility of workers, it becomes important to free up labour and improve the efficiency and profitability of the beneficiation plant. Therefore, to solve the problem of difficult detection of fuzzy small target mineral separation point features in real scenes, an improved YOLOv5-based algorithm is proposed. Firstly, the dataset quality is well improved by image enhancement and pre-processing techniques, after that an innovative CASM attention mechanism is added to the backbone of the YOLOv5 model, followed by a multi-scale feature output and prediction enhancement in the neck part of the model, and an optimized loss function is designed to optimize the whole feature learning process. The improved effect of the model and the specific detection performance were tested using real mine belt image datasets, the ablation experiment verified the comprehensive effectiveness of the proposed improved method and finally compared it with the existing high-level attention mechanism and target detection algorithms. The experimental results show that the improved YOLOv5 algorithm proposed in this study has the best overall detection performance carrying a MAP of 0.954, which is over 20% better than YOLOv5. It is worth mentioning that the improvement to achieve this performance only increases the parameter values by 0.8M and GFLOPs by 1.8, moreover, in terms of the inference speed, it also achieves a respectable 63 FPS, implying that the proposed improved method achieves a better balance between the performance enhancement and the computational complexity of the model, the overall detection results fully satisfy the industrial requirements.