|本期目录/Table of Contents|

[1]张凯萍,李国霞.基于改进YOLOX的实时马铃薯叶片病害检测方法[J].江苏农业科学,2024,52(20):199-208.
 Zhang Kaiping,et al.Real-time potato leaf disease detection method based on improved YOLOX[J].Jiangsu Agricultural Sciences,2024,52(20):199-208.
点击复制

基于改进YOLOX的实时马铃薯叶片病害检测方法(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第52卷
期数:
2024年第20期
页码:
199-208
栏目:
病虫害智能检测
出版日期:
2024-10-20

文章信息/Info

Title:
Real-time potato leaf disease detection method based on improved YOLOX
作者:
张凯萍1 李国霞2
1.许昌电气职业学院信息工程系,河南许昌 461002; 2.郑州大学物理学院,河南郑州 450001
Author(s):
Zhang Kaipinget al
关键词:
马铃薯病害检测YOLOXMobileNetv3V通道网络交叉熵损失
Keywords:
-
分类号:
S126;TP391.41
DOI:
-
文献标志码:
A
摘要:
随着深度学习在图像识别领域的广泛应用,目标检测算法已取得显著进展。然而,在农业病害检测特别是马铃薯叶病害检测方面,仍面临诸多挑战,如自然光影响和数据不平衡问题等。为此,提出一种改进YOLOX的马铃薯叶病害检测方法。首先以轻量化MobileNet v3网络作为骨干替换原有的CSPDarkNet53网络,以提高模型在特征提取上的效率,同时减少计算量。其次引入V通道网络,增加模型对复杂光照环境的适应性,更精确地捕获纹理信息。最后设计一种自适应的交叉熵损失函数,以解决样本不平衡的问题,确保模型的鲁棒性和准确性。在公开数据集PlantVillage上进行试验验证,结果表明,改进模型平均准确率、浮点运算次数、内存和FPS分别为98.55%、14.63×109次、49.35 MB、125.92帧/s。相比原始YOLOX模型,平均准确率和单帧识别速度分别提高4.38百分点、36.65%;浮点运算次数和内存分别降低43.23%、34.33%。此外,与不同模型对比试验以及嵌入式平台上的试验结果均表明,本研究提出的改进YOLOX模型在准确率、计算效率和速度方面均具有明显的优势,为农作物叶片病害检测提供了一种有效的解决方案。
Abstract:
-

参考文献/References:

[1]赵丙秀,董宁. 基于WOA-BP神经网络下马铃薯产量预测分析模型[J]. 农机化研究,2024,46(3):47-51.
[2]刘崇林,赵胜雪,胡军,等. 两种淀粉薯收获期茎秆机械特性的试验研究[J]. 农机化研究,2020,42(6):117-122.
[3]胡新元,孙小花,罗爱花,等. 叶面喷施硫酸锌对马铃薯抗病性和产量的影响[J]. 西北农业学报,2023,32(8):1187-1193.
[4]王凡,李永玉,彭彦昆,等. 便携式马铃薯多品质参数局部透射光谱无损检测装置[J]. 农业机械学报,2018,49(7):348-354.
[5]刘二龙,魏霜,关丽军,等. 马铃薯成分微滴数字聚合酶链式反应定量检测方法建立[J]. 粮食与油脂,2021,34(3):120-123.
[6]Minaee S,Boykov Y,Porikli F,et al. Image segmentation using deep learning:a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(7):3523-3542.
[7]Zhao Z Q,Zheng P,Xu S T,et al. Object detection with deep learning:a review[J]. IEEE Transactions on Neural Networks and Learning Systems,2019,30(11):3212-3232.
[8]Chen X,Wan M J,Ma C,et al. Recognition of small targets in remote sensing image using multi-scale feature fusion-based shot multi-box detector[J]. Optics and Precision Engineering,2021,29(11):2672-2682.
[9]Khan M A,Akram T,Sharif M,et al. CCDF:automatic system for segmentation and recognition of fruit crops diseases based on correlation coefficient and deep CNN features[J]. Computers and electronics in agriculture,2018,155:220-236.
[10]Liu B,Ding Z F,Tian L L,et al. Grape leaf disease identification using improved deep convolutional neural networks[J]. Frontiers in Plant Science,2020,11:1082.
[11]Abbas A,Jain S,Gour M,et al. Tomato plant disease detection using transfer learning with C-GAN synthetic images[J]. Computers and Electronics in Agriculture,2021,187:106279.
[12]Zhang K K,Wu Q F,Chen Y P.Detecting soybean leaf disease from synthetic image using multi-feature fusion faster R-CNN[J]. Computers and Electronics in Agriculture,2021,183:106064.
[13]Saeed A,Abdel-Aziz A A,Mossad A,et al. Smart detection of tomato leaf diseases using transfer learning-based convolutional neural networks[J]. Agriculture,2023,13(1):139.
[14]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,Columbus,OH,USA. IEEE,2014:580-587.
[15]Girshick R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV).Santiago,Chile.IEEE,2015:1440-1448.
[16]Ren S Q,He K M,Girshick R,et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transations on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[17]Khalifa N E M,Taha M H N,Abou El-Maged L M,et al. Artificial intelligence in potato leaf disease classification:a deep learning approach[M]//Hassanien A E,Darwish A. Machine learning and big data analytics paradigms:analysis,applications and challenges. Cham:Springer International Publishing,2021:63-79.
[18]Zhang Y,Song C L,Zhang D W. Deep learning-based object detection improvement for tomato disease[J]. IEEE Access,2020,8:56607-56614.
[19]Redmon J,Divvala S,Girshick R,et al. You only look once:unified,real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas,NV,USA.IEEE,2016:779-788.
[20]Redmon J,Farhadi A. YOLO9000:better,faster,stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu,HI,USA.IEEE,2017:6517-6525.
[21]朱格,徐燕,孙莹莹,等. Darknet深度学习框架下基于YOLO v3的病虫害识别和农药喷洒系统[J]. 农业与技术,2023,43(10):33-38.
[22]Liu W,Anguelov D,Erhan D,et al. SSD:single shot MultiBox detector[M]//Leibe B,Matas J,Sebe N,et al. Computer vision-ECCV 2016.Cham:Springer International Publishing,2016:21-37.
[23]赵越,赵辉,姜永成,等. 基于深度学习的马铃薯叶片病害检测方法[J]. 中国农机化学报,2022,43(10):183-189.
[24]Rashid J,Khan I,Ali G,et al. Multi-level deep learning model for potato leaf disease recognition[J]. Electronics,2021,10(17):2064.
[25]Liu J,Wang X W. Tomato diseases and pests detection based on improved YOLY v3 convolutional neural network[J]. Frontiers in Plant Science,2020,11:898.
[26]宋玲,曹勉,胡小春,等. 基于YOLOX的复杂背景下木薯叶病害检测方法[J]. 农业机械学报,2023,54(3):301-307.
[27]刘延鑫,王俊峰,杜传印,等. 基于YOLO v3的多类烟草叶部病害检测研究[J]. 中国烟草科学,2022,43(2):94-100.
[28]张剑飞,柯赛. 基于YOLOX-s的农业害虫检测研究[J]. 计算机技术与发展,2023,33(5):208-213.
[29]沈志豪,刘金江,张建洋. 基于改进YOLOX-s的田间麦穗检测及计数[J]. 江苏农业科学,2023,51(12):164-171.
[30]Howard A,Sandler M,Chen B,et al. Searching for MobileNet v3[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV).Seoul,Korea (South).IEEE,2019:1314-1324.

相似文献/References:

[1]张世豪,董峦,赵昀杰.基于YOLOX的小麦穗旋转目标检测[J].江苏农业科学,2024,52(20):157.
 Zhang Shihao,et al.Rotating target detection of wheat ears based on YOLOX[J].Jiangsu Agricultural Sciences,2024,52(20):157.

备注/Memo

备注/Memo:
收稿日期:2023-10-06
基金项目:国家自然科学基金(编号:62002330)。
作者简介:张凯萍(1983—),女,河南许昌人,硕士,副教授,研究方向为机器学习、目标检测。E-mail:zhangkp1983@163.com。
通信作者:李国霞,教授,主要从事农业信息技术、计算机视觉研究。E-mail:zhangkp1983@163.com。
更新日期/Last Update: 2024-10-20