基于局部加权非相干区域监督的葡萄精确分割算法

doi:10.3778/j.issn.1002-8331.2305-0416

摘要/Abstract

摘要： 精确实例分割作为葡萄产业园中智能化农艺管理的一项关键技术，对于智慧葡萄园的自动化管理具有重要意义。由于葡萄生长密集、重叠现象严重，传统Mask R-CNN算法分割葡萄时存在实例边缘不准确且重叠区域易错的问题。针对上述问题，提出一种基于局部加权非相干区域监督的葡萄精确分割算法。嵌入额外的非相干区域预测分支，提取葡萄的非相干区域（边缘）和局部非相干区域（重叠边界）；对于提取到的上述区域掩码进行加权监督，增强网络对易错区域的特征提取能力；基于像素亲和的多任务融合模块被提出，用于建模非相干分支和掩码分支间的像素亲和关系，进一步提升网络分割性能。利用该方法在与YOLACT++、Mask R-CNN、SOLOv2等实例分割网络在不同的评价指标上进行比较，实验结果表明该方法具有较好的分割性能，可以精确分割出葡萄边界及实例重叠区域。

关键词: 葡萄精确分割, 局部非相干区域, 加权监督, 像素亲和性融合

Abstract: Grape precise instance segmentation is a key technology for intelligent agricultural management in grape industry parks, and improving the accuracy of grape segmentation is of great significance for the automation of smart vineyards. Due to the dense growth and serious overlapping of grapes, traditional Mask R-CNN algorithms often suffer from inaccurate instance boundaries and errors in overlapping regions. To address these issues, a grape precise segmentation algorithm based on local weighted incoherent region supervision is proposed. Firstly, an additional incoherent region prediction branch is embedded to extract the incoherent regions (edges) and local incoherent regions (overlapping boundaries) of the grapes. Then, the extracted masks of the aforementioned regions are subjected to weighted supervision to enhance the ability of network to extract features from error-prone areas. Finally, a pixel-affinity-based multitask fusion module is proposed to model the pixel affinity relationship between the incoherent branch and the mask branch, and further improve the network instance segmentation performance. This research method is compared with instance segmentation network models such as YOLACT++, Mask R-CNN, and SOLOv2 using different evaluation metrics. Experimental results demonstrate that this method exhibits good segmentation performance and can accurately segment grape boundaries and instance overlapping areas.

Key words: grape precise segmentation, local incoherent regions, weighted supervision, pixel affinity fusion

雷志伟, 曾湄, 王逸涵, 刘雪垠, 李柏林. 基于局部加权非相干区域监督的葡萄精确分割算法[J]. 计算机工程与应用, 2024, 60(15): 252-260.

LEI Zhiwei, ZENG Mei, WANG Yihan, LIU Xueyin, LI Bailin. Grape Precise Segmentation Algorithm Based on Local Weighted Incoherent Region Supervision[J]. Computer Engineering and Applications, 2024, 60(15): 252-260.

参考文献

[1] LI T, FENG Q, QIU Q, et al. Occluded apple fruit detection and localization with a frustum-based point-cloud-processing approach for robotic harvesting[J]. Remote Sensing, 2022, 14(3): 482.
[2] 王超学, 祁昕, 马罡, 等. 基于YOLO V3的葡萄病害人工智能识别系统[J]. 植物保护, 2022, 48(6): 278-288.
WANG C X, QI X, MA G, et al. Intelligent identification system of grape diseases based on YOLO V3[J]. Plant Protection, 2022, 48(6): 278-288.
[3] PéREZ-ZAVALA R, TORRES-TORRITI M, CHEEIN F A, et al. A pattern recognition strategy for visual grape bunch detection in vineyards[J]. Computers and Electronics in Agriculture, 2018, 151: 136-149.
[4] KOIRALA A, WALSH K B, WANG Z. Attempting to estimate the unseen—correction for occluded fruit in tree fruit load estimation by machine vision with deep learning[J]. Agronomy, 2021, 11(2): 347.
[5] ZHAO R, ZHU Y, LI Y. An end-to-end lightweight model for grape and picking point simultaneous detection[J]. Biosystems Engineering, 2022, 223: 174-188.
[6] 蒋心璐, 陈天恩, 王聪, 等. 农业害虫检测的深度学习算法综述[J]. 计算机工程与应用, 2023, 59(6): 30-44.
JIANG X L, CHEN T E, WANG C, et al. Survey of deep learning algorithms for agricultural pest detection[J]. Computer Engineering and Applications, 2023, 59(6): 30-44.
[7] KIERDORF J, WEBER I, KICHERER A, et al. Behind the leaves: estimation of occluded grapevine berries with conditional generative adversarial networks[J]. Frontiers in Artificial Intelligence, 2022, 5: 830026.
[8] DI GENNARO S F, TOSCANO P, CINAT P, et al. A low-cost and unsupervised image recognition methodology for yield estimation in a vineyard[J]. Frontiers in Plant Science, 2019, 10: 559.
[9] JIA W, ZHANG Z, SHAO W, et al. RS-NET: robust segmentation of green overlapped apples[J]. Precision Agriculture, 2022, 23(2): 492-513.
[10] LIU X, ZHAO D, JIA W, et al. Cucumber fruits detection in greenhouses based on instance segmentation[J]. IEEE Access, 2019, 7: 139635-139642.
[11] 黄磊磊, 苗玉彬. 基于深度学习的重叠柑橘分割与形态复原[J]. 农机化研究, 2023, 45(10): 70-75.
HUANG L L, MIAO Y B. Overlapping citrus segmentation and morphological restoration based on deep learning[J]. Journal of Agricultural Mechanization Research, 2023, 45(10): 70-75.
[12] TANG C, CHEN H, LI X, et al. Look closer to segment better: boundary patch refinement for instance segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, Jun 20-25, 2021. Piscataway, NJ: IEEE, 2021: 13926-13935.
[13] CHENG T, WANG X, HUANG L, et al. Boundary-preserving mask R-CNN[C]//16th European Conference on Computer Vision, Glasgow, Aug 23-28, 2020. Cham: Springer International Publishing, 2020: 660-676.
[14] KE L, DANELLJAN M, LI X, et al. Mask transfiner for high-quality instance segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, Jun 19-24, 2022. Piscataway, NJ: IEEE, 2022: 4412-4421.
[15] ZHANG Z, CUI Z, XU C, et al. Pattern-affinitive propagation across depth, surface normal and semantic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway, NJ: IEEE, 2019: 4106-4115.
[16] VANDENHENDE S, GEORGOULIS S, VAN GOOL L. MTI-Net: multi-scale task interaction networks for multi-task learning[C]//16th European Conference on Computer Vision, Glasgow, Aug 23-28, 2020. Cham, Switzerland: Springer International Publishing, 2020: 527-543.
[17] HE K, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 42(2): 386-397.
[18] ACUNA D, KAR A, FIDLER S. Devil is in the edges: learning semantic boundaries from noisy annotations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway, NJ: IEEE, 2019: 11075-11083.
[19] XIE S, TU Z. Holistically-nested edge detection[J]. International Journal of Computer Vision, 2017, 125(1/3): 3-18.
[20] CHENG B, GIRSHICK R, DOLLáR P, et al. Boundary IOU: improving object-centric image segmentation evaluation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, Jun 19-25, 2021. Piscataway, NJ: IEEE, 2021: 15334-15342.
[21] BOLYA D, ZHOU C, XIAO F, et al. Yolact: real-time instance segmentation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Oct 27-Nov 2 2019. Piscataway, NJ: IEEE, 2019: 9157-9166.
[22] WANG X, ZHANG R, KONG T, et al. Solov2: dynamic and fast instance segmentation[C]//Advances in Neural Information Processing Systems, 2020: 17721-17732.
[23] KIRILLOV A, WU Y, HE K, et al. Pointrend: image segmentation as rendering[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 14-19, 2020. Piscataway, NJ: IEEE, 2020: 9799-9808.