Detection Method of Effective Tillering of Rice in Field Based on Lightweight Ghost-YOLOv8 and Smart Phone

doi:10.12133/j.smartag.SA202407012

Abstract

Abstract:

[Objective] The number of effective tillers per plant is one of the important agronomic traits affecting rice yield. In order to solve the problems of high cost and low accuracy of effective tiller detection caused by dense tillers, mutual occlusion and ineffective tillers in rice, a method for dividing effective tillers and ineffective tillers in rice was proposed. Combined with the deep learning model, a high-throughput and low-cost mobile phone App for effective tiller detection in rice was developed to solve the practical problems of effective tiller investigation in rice under field conditions. [Methods] The investigations of rice tillering showed that the number of effective tillers of rice was often higher than that of ineffective tillers. Based on the difference in growth height between effective and ineffective tillers of rice, a new method for distinguishing effective tillers from ineffective tillers was proposed. A fixed height position of rice plants was selected to divide effective tillers from ineffective tillers, and rice was harvested at this position. After harvesting, cross-sectional images of rice tillering stems were taken using a mobile phone, and the stems were detected and counted by the YOLOv8 model. Only the cross-section of the stem was identified during detection, while the cross-section of the panicle was not identified. The number of effective tillers of rice was determined by the number of detected stems. In order to meet the needs of field work, a mobile phone App for effective tiller detection of rice was developed for real-time detection. GhostNet was used to lighten the YOLOv8 model. Ghost Bottle-Neck was integrated into C2f to replace the original BottleNeck to form C2f-Ghost module, and then the ordinary convolution in the network was replaced by Ghost convolution to reduce the complexity of the model. Based on the lightweight Ghost-YOLOv8 model, a mobile App for effective tiller detection of rice was designed and constructed using the Android Studio development platform and intranet penetration counting. [Results and Discussions] The results of field experiments showed that there were differences in the growth height of effective tillers and ineffective tillers of rice. The range of 52 % to 55 % of the total plant height of rice plants was selected for harvesting, and the number of stems was counted as the number of effective tillers per plant. The range was used as the division standard of effective tillers and ineffective tillers of rice. The accuracy and recall rate of effective tillers counting exceeded 99%, indicating that the standard was accurate and comprehensive in guiding effective tillers counting. Using the GhostNet lightweight YOLOv8 model, the parameter quantity of the lightweight Ghost-YOLOv8 model was reduced by 43%, the FPS was increased by 3.9, the accuracy rate was 0.988, the recall rate was 0.980, and the mAP was 0.994. The model still maintains excellent performance while light weighting. Based on the lightweight Ghost-YOLOv8 model, a mobile phone App for detecting effective tillers of rice was developed. The App was tested on 100 cross-sectional images of rice stems collected under the classification criteria established in this study. Compared with the results of manual counting of effective tillers per plant, the accuracy of the App's prediction results was 99.61%, the recall rate was 98.76%, and the coefficient of determination was 0.985 9, indicating the reliability of the App and the established standards in detecting effective tillers of rice. [Conclusions] Through the lightweight Ghost-YOLOv8 model, the number of stems in the cross-sectional images of stems collected under the standard was detected to obtain the effective tiller number of rice. An Android-side rice effective tillering detection App was developed, which can meet the field investigation of rice effective tillering, help breeders to collect data efficiently, and provide a basis for field prediction of rice yield. Further research could supplement the cross-sectional image dataset of multiple rice stems to enable simultaneous measurement of effective tillers across multiple rice plants and improve work efficiency. Further optimization and enhancement of the App's functionality is necessary to provide more tiller-related traits, such as tiller angle.

Key words: effective tillers of rice, Android, YOLOv8, GhostNet, App, phenotype

CLC Number:

S511
TP391.4

CUI Jiale, ZENG Xiangfeng, REN Zhengwei, SUN Jian, TANG Chen, YANG Wanneng, SONG Peng. Detection Method of Effective Tillering of Rice in Field Based on Lightweight Ghost-YOLOv8 and Smart Phone[J]. Smart Agriculture, 2024, 6(5): 98-107.

Figures/Tables 16

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Table 1

Fig.11

Table 2

Fig.12

Table 3

Fig.13

References 25

1	CAO J, ZHANG Z, TAO F L, et al. Integrating multi-source data for rice yield prediction across China using machine learning and deep learning approaches[J]. Agricultural and forest meteorology, 2021, 297: ID 108275.
2	HUO X, WU S, ZHU Z F, et al. NOG1 increases grain production in rice[J]. Nature communications, 2017, 8: ID 1497.
3	BIR M S H, ALI M A, AKTAR M M, et al. Growth competition between rice (oryza sativa) and barnyardgrass (echinochloa oryzicola) under varying mono-/ mixed cropping patterns and air temperatures[J]. Agronomy, 2024, 14(3): ID 574.
4	MA X, LI F, ZHANG Q, et al. Genetic architecture to cause dynamic change in tiller and panicle numbers revealed by genome-wide association study and transcriptome profile in rice[J]. The plant journal, 2020, 104(6): 1603-1616.
5	REN M M, HUANG M H, QIU H Y, et al. Genome-wide association study of the genetic basis of effective tiller number in rice[J]. Rice, 2021, 14(1): ID 56.
6	YANG W, XU X, DUAN L, et al. High-throughput measurement of rice tillers using a conveyor equipped with X-ray computed tomography[J]. The review of scientific instruments, 2011, 82(2): ID 025102.
7	HUANG Z F, GONG L, LIU C L, et al. Measurement of rice tillers based on magnetic resonance imaging[J]. IFAC-papers on line, 2016, 49(16): 254-258.
8	WU D, GUO Z L, YE J L, et al. Combining high-throughput micro-CT-RGB phenotyping and genome-wide association study to dissect the genetic architecture of tiller growth in rice[J]. Journal of experimental botany, 2019, 70(2): 545-561.
9	ZHAO B, ZHANG Q F, LIU Y C, et al. Detection method for rice seedling planting conditions based on image processing and an improved YOLOv8n model[J]. Applied sciences, 2024, 14(6): ID 2575.
10	SUBBARAYUDU C, KUBENDIRAN M. A comprehensive survey on machine learning and deep learning techniques for crop disease prediction in smart agriculture[J]. Nature environment and pollution technology, 2024, 23(2): 619-632.
11	BATHE K, PATIL N, PATIL S, et al. ConvDepthTransEnsembleNet: An improved deep learning approach for rice crop leaf disease classification[J]. SN computer science, 2024, 5(4): ID 436.
12	BHOOKYA N N, RAMANATHAN M, PONNUSAMY P. Leaf disease classification of various crops using deep learning based DBESeriesNet model[J]. SN computer science, 2024, 5(4): ID 406.
13	STILLER S, GRAHMANN K, GHAZARYAN G, et al. Improving spatial transferability of deep learning models for small-field crop yield prediction[J]. ISPRS open journal of photogrammetry and remote sensing, 2024, 12: ID 100064.
14	MEGHRAOUI K, SEBARI I, PILZ J, et al. Applied deep learning-based crop yield prediction: A systematic analysis of current developments and potential challenges[J]. Technologies, 2024, 12(4): ID 43.
15	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.
	SHEN Z H, LIU J J, ZHANG J Y. Detection and counting of wheat ears in fields based on improved YOLOX-s[J]. Jiangsu agricultural sciences, 2023, 51(12): 164-171.
16	HASAN M M, CHOPIN J P, LAGA H, et al. Detection and analysis of wheat spikes using Convolutional Neural Networks[J]. Plant methods, 2018, 14(1): ID 100.
17	MENG X P, LI C C, LI J B, et al. YOLOv7-MA: Improved YOLOv7-based wheat head detection and counting[J]. Remote sensing, 2023, 15(15): ID 3770.
18	WANG X L, YANG W, LYU Q, et al. Field rice panicle detection and counting based on deep learning[J]. Frontiers in plant science, 2022, 13: ID 966495.
19	JIN X, MADEC S, DUTARTRE D, et al. High-throughput measurements of stem characteristics to estimate ear density and above-ground biomass[J]. Plant phenomics (Washington, D C), 2019, 2019: ID 4820305.
20	DENG R L, JIANG Y, TAO M, et al. Deep learning-based automatic detection of productive tillers in rice[J]. Computers and electronics in agriculture, 2020, 177: ID 105703.
21	邓奎才. 水稻有效分蘖终止期的确定方法[J]. 现代农业科技, 2017(20): 52, 54.
	DENG K C. Determination method of effective tillering termination period of rice[J]. Modern agricultural science and technology, 2017(20): 52, 54.
22	高玉美. 怎样区别水稻有效无效分蘖[J]. 农业科技通讯, 1981(4): ID 11.
23	KANG J C, ZHAO L J, WANG K T, et al. Research on an improved YOLOV8 image segmentation model for crop pests. advances in computer, signals and systems[J]. Advances in computer, signals and systems, 2023, 7(3). 1-8.
24	WANG J, WANG J P. A lightweight YOLOv8 based on attention mechanism for mango pest and disease detection[J]. Journal of real-time image processing, 2024, 21(4): ID 136.
25	HAN K, WANG Y H, TIAN Q, et al. GhostNet: More features from cheap operations[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, New Jersey, USA: IEEE, 2020: 1577-1586.

年份	株数	有效分蘖数（划分区间）	无效分蘖数（划分区间）	有效分蘖数（整株）
2022	126	1 248	4	1 250
2023	297	3 107	4	3 123

模型	P	R	mAP	Param/M	GFLOPs	FPS
YOLOv7-Tiny	0.981	0.970	0.993	6.008	13.0	20.3
YOLOv10n	0.991	0.978	0.994	2.695	6.7	56.8
YOLOv8	0.989	0.985	0.994	3.006	8.1	71.9
Ghost-YOLOv8	0.988	0.980	0.994	1.714	5.0	75.8

[1]	LIU Xiaojun, WU Qian, SUN Chuanliang, QI Chao, ZHANG Gufeng, LEI Tianjie, LIANG Wanjie. Rice Disease Identification Method Based on Improved MobileViT Model and System Development [J]. Smart Agriculture, 2026, 8(1): 28-39.
[2]	XIE Wenhao, ZHANG Xin, DONG Wen, ZHENG Yizhen, CHENG Bo, TU Wenli, SUN Fengqing. Parcel-Scale Crop Distribution Mapping Based on Stacking Ensemble Learning [J]. Smart Agriculture, 2025, 7(6): 196-209.
[3]	WANG Yinhui, ZHAO Anzhou, LI Dan, ZHU Xiufang, ZHAO Jun, WANG Ziqing. Construction and Evaluation of Lightweight and Interpretable Soybean Remote Sensing Identification Model [J]. Smart Agriculture, 2025, 7(6): 136-148.
[4]	HAN Wenkai, LI Tao, FENG Qingchun, CHEN Liping. Lightweight Apple Instance Segmentation Algorithm Based on SSW-YOLOv11n for Complex Orchard Environments [J]. Smart Agriculture, 2025, 7(5): 114-123.
[5]	GAO Chenhong, ZHU Qibing, HUANG Min. Embedded Fluorescence Imaging Detection System for Fruit and Vegetable Quality Deterioration Based on Improved YOLOv8 [J]. Smart Agriculture, 2025, 7(5): 146-155.
[6]	ZHAO Yingping, LIANG Jinming, CHEN Beizhang, DENG Xiaoling, ZHANG Yi, XIONG Zheng, PAN Ming, MENG Xiangbao. Applications Research Progress and Prospects of Multi-Agent Large Language Models in Agricultural [J]. Smart Agriculture, 2025, 7(5): 37-51.
[7]	LIU Jie, ZHAO Kang, ZHAO Qinjun, SONG Ye. Acoustic-Vibration Detection Method for The Apple Moldy Core Disease Based on D-S Evidence Theory [J]. Smart Agriculture, 2025, 7(4): 119-131.
[8]	GUO Qi, FAN Yixuan, YAN Xinhuan, LIU Xuemei, CAO Ning, WANG Zhen, PAN Shaoxiang, TAN Mengnan, ZHENG Xiaodong, SONG Ye. Advances in the Application of Multi-source Data Fusion Technology in Non-Destructive Detection of Apple [J]. Smart Agriculture, 2025, 7(4): 31-46.
[9]	HU Lingyan, GUO Ruiya, GUO Zhanjun, XU Guohui, GAI Rongli, WANG Zumin, ZHANG Yumeng, JU Bowen, NIE Xiaoyu. U-Net Greenhouse Sweet Cherry Image Segmentation Method Integrating PDE Plant Temporal Image Contrastive Learning and GCN Skip Connections [J]. Smart Agriculture, 2025, 7(3): 131-142.
[10]	ZHANG Hui, HU Jun, SHI Hang, LIU Changxi, WU Miao. Precision Target Spraying System Integrated with Remote Deep Learning Recognition Model for Cabbage Plant Centers [J]. Smart Agriculture, 2024, 6(6): 85-95.
[11]	CHEN Junlin, ZHAO Peng, CAO Xianlin, NING Jifeng, YANG Shuqin. Lightweight YOLOv8s-Based Strawberry Plug Seedling Grading Detection and Localization via Channel Pruning [J]. Smart Agriculture, 2024, 6(6): 132-143.
[12]	MA Nan, CAO Shanshan, BAI Tao, KONG Fantao, SUN Wei. Research Progress and Prospect of Multi-robot Collaborative SLAM in Complex Agricultural Scenarios [J]. Smart Agriculture, 2024, 6(6): 23-43.
[13]	LI Hongbo, TIAN Xin, RUAN Zhiwen, LIU Shaowen, REN Weiqi, SU Zhongbin, GAO Rui, KONG Qingming. Seedling Stage Corn Line Detection Method Based on Improved YOLOv8 [J]. Smart Agriculture, 2024, 6(6): 72-84.
[14]	LIU Chang, SUN Yu, YANG Jing, WANG Fengchao, CHEN Jin. Grape Recognition and Localization Method Based on 3C-YOLOv8n and Depth Camera [J]. Smart Agriculture, 2024, 6(6): 121-131.
[15]	FU Zhuojun, HU Zheng, DENG Yangjun, LONG Chenfeng, ZHU Xinghui. Detection Method of Apple Alternaria Leaf Spot Based on Deep-Semi-NMF [J]. Smart Agriculture, 2024, 6(6): 144-154.