基于改进YOLOX算法的杨梅成熟度检测方法

doi:10.13733/j.jcam.issn.2095-5553.2023.10.028

摘要/Abstract

摘要： 为实现杨梅采摘智能化，开发杨梅成熟度检测设备，提出一种基于改进YOLOX-NANO算法的杨梅果实成熟度检测方法。通过在特征加强提取网络层中引入通道注意力模块，提高网络对通道特征的提取能力；引入焦点损失函数代替标准交叉熵损失函数，解决单阶段网络正负样本不均衡问题，避免梯度方向指向非最优解；使用高效交并比损失函数，提高网络模型对目标识别的准确率。试验结果表明，在自建数据集上与原YOLOX-NANO相比，改进YOLOX-NANO算法对于三种不同成熟度杨梅果实的识别精度均有提升，平均精度达到92.67%，而网络模型大小只增加0.059MB，推理速度不变，在精度达到与标准结构网络相当的前提下，更易于部署到嵌入式设备中。

关键词: 杨梅, YOLOX-NANO算法, 通道注意力机制, 焦点损失函数, 高效交并比

Abstract: In order to realize the intelligent picking of Myrica rubra, a method based on the improved YOLOX-NANO algorithm is proposed to detect the ripeness of Myrica rubra. By introducing the ECA channel attention module into the featureenhanced extraction network, the networks ability to extract channel features is enhanced. The Focus loss function is introduced to replace the standard crossentropy loss function, which solves the problem of unbalance ofthe positive and negative samples in the singlestage network, and avoids the gradient direction pointing to a nonoptimal solution. The EIoU loss function is used to improve the accuracy of the network model for target recognition. The experimental results show thatcompared with the original YOLOX-NANO, the improved YOLOX-NANO algorithm has improved the recognition accuracy for three different ripeness of prune fruits with mAP of 92.67%. and the network model size only increases by 0.059MB, andthe reasoning speed is remained unchanged, it is easier to deploy in embedded devices for real production activities with the same accuracy comparable to that of the standard structured networks.

Key words: Myrica rubra, YOLOX-NANO algorithm, ECA, Focal Loss, EIoU

中图分类号:

S667.6

项新建, 周焜, 费正顺, 郑永平, 姚佳娜. 基于改进YOLOX算法的杨梅成熟度检测方法[J]. 中国农机化学报, 2023, 44(10): 201-208.

Xiang Xinjian, Zhou Kun, Fei Zhengshun, Zheng Yongping, Yao Jiana. Maturity detection method of Myrica rubra based on improved YOLOX algorithm[J]. Journal of Chinese Agricultural Mechanization, 2023, 44(10): 201-208.

参考文献

［1］　梁森苗, 朱婷婷, 张淑文, 等. 杨梅果实发育成熟度与颜色变化规律探究［J］. 浙江农业科学, 2019, 60(6): 879-882.Liang Sengmiao, Zhu Tingting, Zhang Shuwen, et al. Study on the maturity and color change of Chinese bayberry ［J］. Journal of Zhejiang Agricultural Sciences, 2019, 60(6): 879-882.
［2］　王立舒, 秦铭霞, 雷洁雅, 等. 基于改进YOLOv4-Tiny的蓝莓成熟度识别方法［J］. 农业工程学报, 2021, 37(18): 170-178.
Wang Lishu, Qin Mingxia, Lei Jieya, et al. Blueberry maturity recognition method based on improved YOLOv4-Tiny ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(18): 170-178.
［3］　刘莫尘, 高甜甜, 马宗旭, 等. 基于MSRCR-YOLOv4-tiny的田间玉米杂草检测模型［J］. 农业机械学报, 2022, 53(2): 246-255, 335.
Liu Mochen, Gao Tiantian, Ma Zongxu, et al. Target detection model of corn weeds in field environment based on MSRCR algorithm and YOLOv4-tiny ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(2): 246-255, 335.
［4］　徐黎明, 吕继东. SUSAN算子和Hough变换在杨梅果实识别中的应用［J］. 中国农机化报, 2015, 36(6): 216-220.
Xu Liming, Lü Jidong. Applications of SUSAN algorithm and Hough transform on recognition of bayberry fruit ［J］. Journal of Chinese Agricultural Mechanization, 2015, 36(6): 216-220.
［5］　Ghazal S, Qureshi W S, Khan U S, et al. Analysis of visual features and classifiers for fruit classification problem ［J］. Computers and Electronics in Agriculture, 2021, 187: 106267.
［6］　Khodabakhshian R, Emadi B, Khojastehpour M, et al. Determining quality and maturity of pomegranates using multispectral imaging ［J］. Journal of the Saudi Society of Agricultural Sciences, 2017, 16(4): 322-331.
［7］　Kang H, Chen C. Fast implementation of realtime fruit detection in apple orchards using deep learning ［J］. Computers and Electronics in Agriculture, 2020, 168: 105108.
［8］　Akram T, Sharif M, Saba T. Fruits diseases classification: exploiting a hierarchical framework for deep features fusion and selection ［J］. Multimedia Tools and Applications, 2020, 79(35): 25763-25783.
［9］　Kido S, Hirano Y, Hashimoto N. Detection and classification of lung abnormalities by use of convolutional neural network (CNN) and regions with CNN features (R-CNN) ［C］. 2018 International Workshop on Advanced Image Technology (IWAIT). IEEE, 2018: 1-4.
［10］　Purkait P, Zhao C, Zach C. SPPNet: Deep absolute pose regression with synthetic views ［J］. arXiv Preprint arXiv: 1712.03452, 2017.
［11］　Girshick R. Fast R-CNN ［C］. Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
［12］　Ren S, He K, Girshick R, et al. Faster R-CNN: Towards realtime object detection with region proposal networks ［J］. Advances in Neural Information Processing Systems, 2015, 28.
［13］　He K, Gkioxari G, Dollár P, et al. Mask R-CNN ［C］. Proceedings of the IEEE International Conference on Computer Vision, 2017: 2961-2969.
［14］　Redmon J, Farhadi A. YOLO9000: Better, faster, stronger ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263-7271.
［15］　Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector ［C］. European Conference on Computer Vision. Springer, Cham, 2016: 21-37.
［16］　Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection ［C］. Proceedings of the IEEE International Conference on Computer Vision, 2017: 2980-2988.
［17］　Ge Z, Liu S, Wang F, et al. YOLOX: Exceeding YOLO series in 2021 ［J］. arXiv Preprint arXiv: 2107. 08430, 2021.
［18］　Wang Q, Wu B, Zhu P, et al. Supplementary material for “ECANet: Efficient channel attention for deep convolutional neural networks” ［C］. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, WA, USA. 2020: 13-19.
［19］　Hu J, Shen L, Sun G. Squeezeandexcitation networks ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 7132-7141.
［20］　Woo S, Park J, Lee J Y, et al. CBAM: Convolutional block attention module ［C］. Proceedings of the European Conference on Computer Vision (ECCV), 2018: 3-19.
［21］　Park J, Woo S, Lee J Y, et al. Bam: Bottleneck attention module ［J］. arXiv Preprint arXiv: 1807.06514, 2018.
［22］　Cao Y, Xu J, Lin S, et al. GCNet: Nonlocal networks meet squeezeexcitation networks and beyond ［C］. Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2019.
［23］　Qin Z, Zhang P, Wu F, et al. FcaNet: Frequency channel attention networks ［C］. Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 783-792.
［24］　Zhang Y F, Ren W, Zhang Z, et al. Focal and efficient IOU loss for accurate bounding box regression ［J］. Neurocomputing, 2022, 506: 146-157.
［25］　Ahmed F, Tarlow D, Batra D. Optimizing expected intersectionoverunion with candidateconstrained CRFs ［C］. Proceedings of the IEEE International Conference on Computer Vision, 2015: 1850-1858.
［26］　Yosinski J, Clune J, Bengio Y, et al. How transferable are features in deep neural networks? ［J］. Advances in Neural Information Processing Systems, 2014, 27.