Multi-source feature fusion network for grape berry instance segmentationOA
Accurate delineation of grape berry boundaries is essential for phenotypic measurement and growth assessment.This study proposes a multi-source feature fusion network(MFFNet)for instance segmentation of grape berries in dense clusters with frequent overlaps and blurred edges.MFFNet employs two parallel branches for feature extraction:a Swin Transformer backbone to capture hierarchical semantic features and an edge-detection branch that predicts an edge probability map to provide boundary cues.To address the substantial scale variation within a single image,the multilevel semantic features were enhanced using Adaptive Spatial Feature Fusion(ASFF).The edge probability map was introduced twice into the ASFFenhanced multi-scale features.First,edge cues were injected into the highest-resolution fused feature map to strengthen global boundary awareness across the cluster.Second,during mask generation,edge cues were reintroduced within each candidate instance region to refine local contours and improve the separation in the adhered areas.Experiments on a custom dataset collected in Yinchuan,Ningxia,showed that MFFNet achieved an mAP_(50)^(box)of 93.4%and mAP_(50)^(mask)of 93.4%,outperforming representative baselines,including Mask2Former and HTC.The proposed model remained stable on images with severe berry overlap and indistinct edges,supporting practical grape growth monitoring.
Mingcheng Yao;Xiaoxia Yang;Chengming Zhang;Menxin Wu;Jinlong Fan;Feng Li;Hongying Li;Jianguo Wei;Shujun Liu;Huake Zhang;Yanhui Jin
College of Information Science and Engineering,Shandong Agricultural University,Tai’an 271018,Shandong,ChinaCollege of Information Science and Engineering,Shandong Agricultural University,Tai’an 271018,Shandong,ChinaCollege of Information Science and Engineering,Shandong Agricultural University,Tai’an 271018,Shandong,ChinaThe National Meteorological Center,Beijing 100081,ChinaFaculty of Geographical Sciences,Beijing Normal University,Beijing 100875,ChinaShandong Provincial Climate Center,Jinan 250031,ChinaNingxia Institute of Meteorological Sciences,Yinchuan,Ningxia 750002,ChinaKey Laboratory of Meteorological Disaster Monitoring,Early Warning,and Risk Management for Characteristic Agriculture in Arid Regions,China Meteorological Administration,Yinchuan,Ningxia 750002,ChinaCollege of Information Science and Engineering,Shandong Agricultural University,Tai’an 271018,Shandong,ChinaCollege of Information Science and Engineering,Shandong Agricultural University,Tai’an 271018,Shandong,ChinaCollege of Information Science and Engineering,Shandong Agricultural University,Tai’an 271018,Shandong,China
农业科技
grape berryinstance segmentationedge detectionmulti-source feature fusionprecision agriculture
《International Journal of Agricultural and Biological Engineering》 2026 (2)
P.294-302,9
funded by the Fengyun Satellite Application Pioneer Program(PhaseⅢ)(Grant No.FY-APP-2024.0301)the Science Foundation of Shandong(Grant No.ZR2021MD097)the Natural Science Foundation of Ningxia(Grant No.2024AAC03419)Shandong Provincial Meteorological Bureau Innovation Team Special Project(Grant No.2024sdcxtd04).
评论