基于改进YOLOv4的植物叶茎交点目标检测研究

doi:10.3778/j.issn.1002-8331.2106-0239

摘要/Abstract

摘要： 由于植物根茎交点目标较小，识别率低，且在使用嵌入式设备进行植物移植与栽培的过程中资源及功耗受限。针对这类问题，提出了一种基于改进YOLOv4的目标检测解决方法，并设置于本场景。采集8?629张植物叶茎数据集图像，并对这些植物叶茎数据集进行标注，利用生成对抗网络（generative adversarial network，GAN）进行数据增强预处理。改进YOLOv4目标检测算法，选取4个不同尺度的锚框，以获得更多植物叶茎交点信息，同时对网络的结构和损失函数进行局部优化，使得网络在训练过程中更易于拟合目标。将主干网络更改为GhostNet网络，大幅度减少参数量与计算量，更利于在移动设备上的轻量化模型部署。实验结果表明，优化后的YOLOv4-GhostNet轻量化网络在保证检测精度的前提下，检测速度提高到79.3?frame/s，较YOLOv4提高了36.45%，网络帧率提高了51.07%，模型参数量减小了36.06%，能够有效检测叶茎交点目标。

关键词: 目标检测, 数据增强, 对抗网络, YOLOv4, GhostNet

Abstract: Due to the small target of the plant roots and stems, the recognition rate is low, and the resources and power consumption are limited in the process of plant transplantation and cultivation using embedded devices. Aiming at this kind of problem, an improved YOLOv4 target detection solution method is proposed, which is more equipped in this scene. Firstly, 8629 images of the plant leaf and stem data sets are collected, and these plant leaf and stem data sets are labeled, and the generative adversarial network（GAN） is used for data enhancement preprocessing. Then, the YOLOv4 target detection algorithm is improved, four anchor boxes of different scales are selected to obtain more plant leaf-stem intersection information, and the structure and loss function of the network are locally optimized to make the network easier fit the target during the training process. Finally, the backbone network is changed to the GhostNet network, which greatly reduces the amount of parameters and calculations, and is more conducive to the deployment of lightweight models on mobile devices. The experimental results show that the optimized YOLOv4-GhostNet lightweight network can increase the detection speed to 79.3 frame/s under the premise of ensuring the detection accuracy, which is 36.45% higher than YOLOv4, the network frame rate is increased by 51.07%, and the amount of model parameters is reduced by 36.06%, can effectively detect the leaf-stem intersection target.

Key words: target detection, data enhancement, confrontation network, YOLOv4, GhostNet

李文婧, 徐国伟, 孔维刚, 郭风祥, 宋庆增. 基于改进YOLOv4的植物叶茎交点目标检测研究[J]. 计算机工程与应用, 2022, 58(4): 221-228.

LI Wenjing, XU Guowei, KONG Weigang, GUO Fengxiang, SONG Qingzeng. Research on Target Detection of Plant Leaf-Stem Intersection Based on Improved YOLOv4[J]. Computer Engineering and Applications, 2022, 58(4): 221-228.

参考文献

[1] 王金龙，周志峰.基于SIFT图像特征提取与FLANN匹配算法的研究[J].计算机测量与控制，2018，26（2）：175-178.
WANG J L，ZHOU Z F.Research on SIFT image feature extraction and FLANN matching algorithm[J].Computer Measurement and Control，2018，26（2）：175-178.
[2] 耿庆田，赵浩宇，于繁华，等.基于改进HOG特征提取的车型识别算法[J].中国光学，2018，11（2）：174-181.
GENG Q T，ZHAO H Y，YU F H，et al.Vehicle recognition algorithm based on improved HOG feature extraction[J].China Optics，2018，11（2）：174-181.
[3] 周唯，彭认灿，董箭.LiDAR点云纹理特征提取方法[J].国防科技大学学报，2019，41（2）：124-131.
ZHOU W，PENG R C，DONG J.LiDAR point cloud texture feature extraction method[J].Journal of National University of Defense Technology，2019，41（2）：124-131.
[4] 李立，余翠，孙涛，等.基于颜色特征的数字钻孔图像溶隙结构识别方法[J].岩土力学，2019，40（8）：3274-3281.
LI L，YU Q，SUN T，et al.Digital borehole image dissolution structure recognition method based on color features[J].Rock and Soil Mechanics，2019，40（8）：3274-3281.
[5] 彭圆圆，肖昌炎.基于形状特征的肺裂检测算法[J].光学学报，2018，38（8）：225-232.
PENG Y Y，XIAO C Y.Lung fissure detection algorithm based on shape features[J].Acta Optica Sinica，2018，38（8）：225-232.
[6] 许德刚，王露，李凡.深度学习的典型目标检测算法研究综述[J].计算机工程与应用，2021，57（8）：10-25.
XU D G，WANG L，LI F.A review of research on typical target detection algorithms for deep learning[J].Computer Engineering and Applications，2021，57（8）：10-25.
[7] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition，2014：580-587.
[8] GIRSHICK R.Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision，2015：1440-1448.
[9] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//2015 Advances in Neural Information Processing Systems，2015：91-99.
[10] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//14th European Conference on Computer Vision.Cham：Springer，2016：21-37.
[11] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real time object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：6517-6525.
[12] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：6517-6525.
[13] REDMON J，FARHADI A.YOLOv3：an incremental improvement[J].arXiv：1804.02767，2018.
[14] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[15] HAN K，WANG Y，TIAN Q，et al.GhostNet：more features from cheap operations[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：1580-1589.
[16] 冉蓉，徐兴华，邱少华，等.基于深度卷积神经网络的裂纹检测方法综述[J].计算机工程与应用，2021，57（9）：23-35.
RAN R，XU X H，QIU S H，et al.A review of crack detection methods based on deep convolutional neural networks[J].Computer Engineering and Applications，2021，57（9）：23-35.
[17] GOODFELLOW I，POUGET-ABADIE J，MIRZA M，et al.Generative adversarial nets[C]//Advances in Neural Information Processing Systems，2014：2672-2680.
[18] RADFORD A，METZ L，CHINTALA S.Unsupervised representation learning with deep convolutional generative adversarial networks[J].arXiv：1511.06434，2015.
[19] MISRA D.Mish：a self regularized non-monotonic activation function[J].arXiv：1908.08681，2019.
[20] YU J，JIANG Y，WANG Z，et al.Unitbox：an advanced object detection network[C]//2016 ACM on Multimedia Conference，2016：516-520.
[21] REZATOFIGHI H，TSOI N，GWAK J Y，et al.Generalized intersection over union：a metric and a loss for bounding box regression[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition，Long Beach，2019：658-666.
[22] ZHENG Z H，WANG P，LIU W，et al.Distance-IoU loss：faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2019：12993-13000.