Lightweight Wheat Growth Stage Identification Model Based on Improved FasterNet

SHI Lei, LEI Jingkai, WANG ] Jian, YANG Chengkai, LIU Zhihao, XI Lei, XIONG Shufeng

Abstract

In response to the problems of low efficiency and strong subjectivity in obtaining information about the current stage of wheat development that relies on manual observation, a wheat image dataset consisting of four key growth stages of winter wheat: winterovering stage, green-turning stage, jointing stage, and heading stage, totaling 4599 images were constructed. A lightweight model FSST (fast shuffle swin transformer) based on FasterNet was proposed to carry out intelligent recognition of these four key growth stages. Firstly, based on the partial convolution of FasterNet, the Channel Shuffle mechanism was introduced to improve the computational speed of the model. Secondly, the Swin Transformer module was introduced to achieve feature fusion and self attention mechanism, it can improve the accuracy of identifying key growth stages of wheat. Then the structure of the whole model was adjusted to further reduce the network complexity, and the Lion optimizer was introduced into the training to accelerate the training speed of the model. Finally, model validation on the self-built wheat dataset with four key growth stages was performed. The results showed that the parameter quantity of the FSST model was only 1.22×107, the average recognition accuracy was 97.22%, the F1 score was 78.54%, and the FLOPs was 3.9×108. Compared with that of the FasterNet, GhostNet, ShuffleNetV2 and MobileNetV3 models, the recognition accuracy of the FSST model was higher, the operation speed was faster, and the recognition time was reduced by 84.04%, 73.74%, 72.22% and 77.01%, respectively. The FSST model proposed can effectively identify the key growth stage of wheat, and had the characteristics of fast, accurate, and lightweight recognition. It can provide a reference for optimizing the application of deep learning models in smart agriculture and offerring information technology support for real-time monitoring of field crop growth on resource-constrained mobile devices.

 

Keywords:wheat; growth stage identification; FasterNet; lightweight; Lion optimizer

 

Download Full Text:

PDF


References


YANG Shuqin, LIN Fengshan, XU Penghui, et al. Planting pow detection of multi-growth winter wheat field based on UAV remote sensing image [ J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54 ( 2 ) : 181 - 188. (in Chinese)

ZHOU Qi, WANG Jianjun, HUO Zhongyang, et al. UAV multi-spectral remote sensing estimation of wheat canopy SPAD value in different growth periods [ J]. Spectroscopy and Spectral Analysis, 2022,42 ( 10) :3269 -3274. (in Chinese)

LAN Shihao, LI Yingxue, WU Fang, et al. Winter wheat biomass estimation based on satellite spectral-scale reflectance [J]. Transactions of the CSAE, 2022, 38(24) ; 118 - 128. (in Chinese)

YANG Xin, YUAN Ziran, YE Yin, et al. Winter wheat total nitrogen content estimation based on UAV hyperspectral remote sensing[ J ]. Spectroscopy and Spectral Analysis, 2022,42(10) :3269 -3274. (in Chinese)

HE K, ZHANG X, HEN S, et al. Deep residual learning for image recognition [ С] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:770 -778.

XU Jianpeng, WANG Jie, XU Xiang, et al. Image recognition for different developmental stages of rice by RAdam deep convolutional neural networks [J ]. Transactions of the CSAE, 2021 ,37(8) : 143 - 150. (in Chinese)

SHEN Hualei, SU Xinqi, ZHAO Qiaoli, et al. Extraction of lodging area of wheat barieties by unmanned aerial vehicle remote sensing based on deep learning[ J ]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(9) ; 252 -260, 341. (in Chinese)

LI Yunxia, MA Juncheng, LIU Hongjie, et al. Field growth parameter estimation system of winter wheat using KGB digital images and deep learning[ J]. Transactions of the CSAE, 2021 , 37(24) : 189 - 198. (in Chinese)

SUN Shaojie, WU Menxin, ZHUANG Liwei, et al. Forecasting winter wheat yield at county level using CNN and BP neuralnetworks[ J ]. Transactions of the CSAE, 2022,38( 11); 151 - 160. (in Chinese)

TAN M, LE Q. Efllcientnet; rethinking model scaling for convolutional neural networks [С] // International Conference on Machine Learning, 2019:6105 -6114.

MAN, ZHANG X, ZHEN H T, et al. Shufflenet v2: practical guidelines for efficient CNN architecture design [ С ]//Proceedings of the European Conference on Computer Vision,2018; 116 - 131.

ANDREW H, ZHU M L, CHEN B, et al. MobileNetS; efficient convolutional neural networks for mobile vision applications [J]. arXiv preprint arXiv: 1704.04861,2017,4.

MARKS, ANDREW H, ZHU Menglong, et al. MobileNetV2; inverted residuals and linear bottlenecks[J ]. arXiv preprint arXiv: 1801.04381,2018,1.

ANDREW H, MARK S, CHU G, et al. Searching for MobileNetV3f J]. arXiv preprint arXiv: 1905.02244,2019,5.

HAN K, WANG Y H, TIAN Q, et al. GhostNet; more features from cheap operations! J]. arXiv preprint arXiv: 1911.

CHEN J R, KAO S H, HE H, et al. Run, don’t walk: chasing higher FLOPS for faster neural networks[ J]. arXiv preprint arXiv: 2303.03667, 2023, 3.

YANG Sensen, ZHANG Hao, XING Lu, et al. Light weight recognition of weeds in the field based on improved MobiieViT network [J]. Transactions of the CSAE, 2023,39(9) ; 152 - 160. (in Chinese)

MIAO Ronghui, LI Zhiwei, WU Jinglong. Lightweight maturity detection of cherry tomato based on improved YOLO v7[ J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54( 10) :225 -233. (in Chinese)

FAN Xiaofei, WANG Linbai, LIU Jingyan, et al. Com seed appearance quality estimation based on improved YOLO v4[ J]. Transactions of the Chinese Society for Agricultural Machinery, 2022,53(7) :226 -233. (in Chinese)


Refbacks

  • There are currently no refbacks.