Abstract: To address the challenges of strong adhesion,high inter-object similarity,and poor image quality in open-pit mine blast pile orerock images,conventional segmentation methods often yield low accuracy and unsatisfactory results.To this end,we introduce an attention mechanism into the traditional U-Net framework and propose an attention optimized CAU-Net method for segmenting blast pile ore-rock images.The proposed architecture retains U-Net as the backbone and incorporates at tention modules before each convolutional learning stage.Comparative segmentation experiments are conducted against three at tention models.The results show that the CAU-Net model significantly improves segmentation performance,achieving an accu racy (ACC) of 94.08% and an AUC (Area Under Curve) of 97.43%,indicating strong predictive capability.Further compar isons with threshold-based segmentation and the standard U-Net,together with evaluation using the Intersection over Union (IoU) metric,confirm that the proposed method can segment blast pile ore-rock images more accurately.The high-precision segmentation results,when applied to digital ore-rock fragmentation statistics,substantially enhance statistical accuracy and ef fectively advance the digitalization of mining operations.

Key words: blast pile in open-pit mine,deep learning,U-Net,attention mechanism,image segmentation