Intelligent recognition of citrus shoot growth based on improved YOLOX-Nano algorithm

YIN Xianbo; DENG Xiaoling; LAN Yubin; CHEN Xin

doi:10.7671/j.issn.1001-411X.202112039

Journal of South China Agricultural University > 2023 > 44(1): 142-150. > DOI: 10.7671/j.issn.1001-411X.202112039

YIN Xianbo, DENG Xiaoling, LAN Yubin, et al. Intelligent recognition of citrus shoot growth based on improved YOLOX-Nano algorithm[J]. Journal of South China Agricultural University, 2023, 44(1): 142-150. DOI: 10.7671/j.issn.1001-411X.202112039

Citation:

PDF (1593 KB)

Intelligent recognition of citrus shoot growth based on improved YOLOX-Nano algorithm

College of Electronic Engineering, South China Agricultural University/National Center for International Collaboration Research on Precision Agricultural Aviation Pesticide Spraying Technology, Guangzhou 510642, China

More Information

Received Date: December 23, 2021
Available Online: May 17, 2023

Graphical Abstract

Abstract

Abstract

Objective
In order to solve the problem of low recognition accuracy due to similar color of the background and new shoots, to realize the automatic monitoring of citrus shoot stage and explore the improved method of algorithm, the machine vision technology was used to carry out the research on intelligent perceiving the growth stage of citrus shoot.

Method
According to the characteristics of features extracted from different convolutional layers and the role of different attention mechanism, an improved YOLOX-Nano intelligent recognition model based on multi-attention mechanism was proposed, and a diversified orchard dataset for pre-training was established.

Result
The improved YOLOX-Nano algorithm achieved the mAP (Mean average precision) of 88.07% using the orchard dataset as a pre-training dataset. Compared with the model of YOLOV4-Lite series, the improved model significantly improved the recognition accuracy with less parameters and calculation. Compared with YOLOV4-MobileNetV3 and YOLOV4-GhostNet, the mAP of improved model increased by 6.58% and 6.03% respectively.

Conclusion
The improved model has greater advantage for lightweight deployment at orchard monitoring terminal. The findings provide feasible data and technical solutions for agricultural real-time perception and intelligent monitoring.
- Citrus,
- New shoot,
- Intelligent monitoring,
- Attention mechanism,
- YOLOX-Nano,
- Deep learning,
- Intelligent agriculture

FullText(HTML)

References (27)

References

[1]	邓秀新, 束怀瑞, 郝玉金, 等. 果树学科百年发展回顾[J]. 农学学报, 2018, 8(1): 24-34.
[2]	刘双喜, 徐春保, 张宏建, 等. 果园基肥施肥装备研究现状与发展分析[J]. 农业机械学报, 2020, 51(S2): 99-108. doi: 10.6041/j.issn.1000-1298.2020.S2.012
[3]	赵春江. 智慧农业的发展现状与未来展望[J]. 华南农业大学学报, 2021, 42(6): 1-7. doi: 10.7671/j.issn.1001-411X.202108039
[4]	DENG X, ZHU Z, YANG J, et al. Detection of Citrus Huanglongbing based on multi-input neural network model of UAV hyperspectral remote sensing[J]. RemoteSensing, 2020, 12(17): 2678.
[5]	戴泽翰, 郑正, 黄莉舒, 等. 基于深度卷积神经网络的柑橘黄龙病症状识别[J]. 华南农业大学学报, 2020, 41(4): 111-119. doi: 10.7671/j.issn.1001-411X.201909031
[6]	陆健强, 林佳翰, 黄仲强, 等. 基于Mixup算法和卷积神经网络的柑橘黄龙病果实识别研究[J]. 华南农业大学学报, 2021, 42(3): 94-101. doi: 10.7671/j.issn.1001-411X.202008041
[7]	胡嘉沛, 李震, 黄河清, 等. 采用改进 YOLOv4-Tiny 模型的柑橘木虱识别[J]. 农业工程学报, 2021, 37(17): 197-203. doi: 10.11975/j.issn.1002-6819.2021.17.022
[8]	王林惠, 兰玉彬, 刘志壮, 等. 便携式柑橘虫害实时监测系统的研制与试验[J]. 农业工程学报, 2021, 37(9): 282-288. doi: 10.11975/j.issn.1002-6819.2021.09.032
[9]	ZHANG J, LUO S, HOU C, et al. Detection of orchard citrus fruits using a monocular machine vision-based method for automatic fruit picking applications[J]. Computers and Electronics in Agriculture, 2018, 152: 64-73. doi: 10.1016/j.compag.2018.07.004
[10]	吕石磊, 卢思华, 李震, 等. 基于改进 YOLOv3-LITE 轻量级神经网络的柑橘识别方法[J]. 农业工程学报, 2019, 35(17): 205-214.
[11]	邓颖, 吴华瑞, 朱华吉. 基于实例分割的柑橘花朵识别及花量统计[J]. 农业工程学报, 2020, 36(7): 200-207. doi: 10.11975/j.issn.1002-6819.2020.07.023
[12]	APOLO-APOLOZ O E, MARTINEZ-GUANTER G, EGEA P, et al. Deep learning techni-quees for estimation of the yield and size of citrus fruits using a UAV[J]. European Journal of Agronomy, 2020, 115: 126030. doi: 10.1016/j.eja.2020.126030
[13]	金方伦, 邓江涛, 敖学希, 等. 柑橘潜叶蛾发生与控制柑橘夏梢的相关性及防治技术研究[J]. 湖北农业科学, 2013, 52(23): 5767-5770.
[14]	刘慧, 何利庭, 龚碧涯, 等. 柑橘木虱在湖南发生规律的初步研究[J]. 湖南农业科学, 2019(10): 49-52.
[15]	黄永敬, 李娟, 陈杰忠, 等. 沙糖桔控夏梢保果技术[J]. 广东农业科学, 2011, 38(14): 36-38. doi: 10.3969/j.issn.1004-874X.2011.14.013
[16]	LI Y, HE L, JIANG M, et al. In-field tea shoot detection and 3D localization using an RGB-D camera[J]. Computers and Electronics in Agriculture, 2021, 185: 106149. doi: 10.1016/J.COMPA-G.2021.106149
[17]	XU W, ZHAO L, LI J, et al. Detection and classification of tea buds based on deep learning[J]. Computers and Electronics in Agriculture, 2022, 192: 106547. doi: 10.1016/j.compag.2021.106547
[18]	袁加红, 张中正, 朱德泉, 等. 名优绿茶嫩芽识别与定位方法研究[J]. 安徽农业大学学报, 2016, 43(5): 676-681.
[19]	FANG L, WU Y, LI Y, et al. Ginger seeding detection and shoot orientation discrimination using an improved YOLOv4-LITE network[J]. Agronomy, 2021, 11: 2328. doi: 10.3390/agronomy11112328
[20]	SCARLETT L STEVE C JULIE T, et al. A computer vision system for early stage grape yield estimation based on shoot detection[J]. Computers and Electronics in Agriculture, 2017, 137: 88-101. doi: 10.1016/j.compag.2017.03.013
[21]	NIU Z, ZHONG G, YU H. A review on the attention mechanism of deep learning[J]. Neuro-computing, 2021, 452: 48-62.
[22]	李文涛, 张岩, 莫锦秋, 等. 基于改进YOLOv3-tiny的田间行人与农机障碍物检测[J]. 农业机械学报, 2020, 51(S1): 1-8. doi: 10.6041/j.issn.1000-1298.2020.S1.001
[23]	YING B, XU Y, ZHANG S, et al. Weed detection in images of carrot fields based on improved YOLOv4[J]. Traitement du Signal, 2021, 38(2): 341-348. doi: 10.18280/ts.380211
[24]	杨蜀秦, 刘杨启航, 王振, 等. 基于融合坐标信息的改进 YOLOv4 模型识别奶牛面部[J]. 农业工程学报, 2021, 37(15): 129-135. doi: 10.11975/j.issn.1002-6819.2021.15.016
[25]	HU J, SHEN L, SUN G. Squeeze-and-excitation networks[EB/OL]. [2017-09-05]. https://arxiv.org/pdf/1709.01507.pdf.
[26]	HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[EB/OL]. [2021-03-04]. https://arxiv.org/pdf/2103.02907.pdf.
[27]	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: 3320-3328.

Cited By

Cited by

Periodical cited type(3)

1.	戴丽媛，张诚，田晓丹，杨丽雅，赵世雯，沈长松. 基于COD的水资源生态环境监测模型研究. 安全与环境学报. 2025(04): 1603-1608 .
2.	陈天力，曾华，宋晨倩，池怡. 基于IGWOPSO-SVM算法的饮用水水源水质安全预警研究. 生态与资源. 2025(02): 1-3 .
3.	贺凯盈，成夏葳，岳军红. 水体异常高分辨率双向LSTM遥测系统设计. 计算机测量与控制. 2025(05): 89-96 .

Other cited types(2)

Get Citation

PDF

XML

Article views (198) PDF downloads (360) Cited by(5)

Turn off MathJax

Article Contents

Abstract

References

Intelligent recognition of citrus shoot growth based on improved YOLOX-Nano algorithm

Abstract

References

Cited by

Periodical cited type(3)

Other cited types(2)

Catalog

Export File

Citation

Format

Content