The estimation of wheat tiller number based on UAV images and gradual change features (GCFs)

Liu, Tao; Zhao, Youjun; Wu, Fei; Wang, Junchan; Chen, Chen; Zhou, Yuzhuang; Ju, Chengxin; Huo, Zhongyang; Zhong, Xiaochun; Liu, Shengping; Sun, Chengming

doi:10.1007/s11119-022-09949-5

Cited by 3 publications

(2 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, the model performance on wheat plants before tillering was not explored. It would be valuable work to comprehensively estimate wheat plant density before and after tillering, bringing more insights into the tillering mechanism [51]. Third, the plant row is meant to be extracted from the wheat heatmaps.…”

Section: Potential Future Workmentioning

confidence: 99%

Plant Density Estimation Using UAV Imagery and Deep Learning

et al. 2022

View full text Add to dashboard Cite

Plant density is a significant variable in crop growth. Plant density estimation by combining unmanned aerial vehicles (UAVs) and deep learning algorithms is a well-established procedure. However, flight companies for wheat density estimation are typically executed at early development stages. Further exploration is required to estimate the wheat plant density after the tillering stage, which is crucial to the following growth stages. This study proposed a plant density estimation model, DeNet, for highly accurate wheat plant density estimation after tillering. The validation results presented that (1) the DeNet with global-scale attention is superior in plant density estimation, outperforming the typical deep learning models of SegNet and U-Net; (2) the sigma value at 16 is optimal to generate heatmaps for the plant density estimation model; (3) the normalized inverse distance weighted technique is robust to assembling heatmaps. The model test on field-sampled datasets revealed that the model was feasible to estimate the plant density in the field, wherein a higher density level or lower zenith angle would degrade the model performance. This study demonstrates the potential of deep learning algorithms to capture plant density from high-resolution UAV imageries for wheat plants including tillers.

show abstract

Section: Potential Future Workmentioning

confidence: 99%

Plant Density Estimation Using UAV Imagery and Deep Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For example, automatic counting of the number of wheat seedlings was performed using RGB images; the average accuracy rate in different agricultural processes reached 89.94% [15]. The identity R 2 of the number of maize seedlings was 0.89 [16]; the average RMSE of the stems in the wheat multi-birth period was less than nine tillers per square meter [17], the accuracy of the ears of wheat was higher than 90%, and the standard deviation was less than 5% [18]. In another investigation, Liu et al [19] first cleaned up weeds in a maize field and then obtained images, which reduced the difficulty of counting maize seedlings and limited the scope of the model applicable.…”

Section: Introductionmentioning

confidence: 99%

Unmanned Aerial Vehicle-Scale Weed Segmentation Method Based on Image Analysis Technology for Enhanced Accuracy of Maize Seedling Counting

Yang,

Zhu,

Zhang

et al. 2024

Agriculture

Self Cite

View full text Add to dashboard Cite

The number of maize seedlings is a key determinant of maize yield. Thus, timely, accurate estimation of seedlings helps optimize and adjust field management measures. Differentiating “multiple seedlings in a single hole” of maize accurately using deep learning and object detection methods presents challenges that hinder effectiveness. Multivariate regression techniques prove more suitable in such cases, yet the presence of weeds considerably affects regression estimation accuracy. Therefore, this paper proposes a maize and weed identification method that combines shape features with threshold skeleton clustering to mitigate the impact of weeds on maize counting. The threshold skeleton method (TS) ensured that the accuracy and precision values of eliminating weeds exceeded 97% and that the missed inspection rate and misunderstanding rate did not exceed 6%, which is a significant improvement compared with traditional methods. Multi-image characteristics of the maize coverage, maize seedling edge pixel percentage, maize skeleton characteristic pixel percentage, and connecting domain features gradually returned to maize seedlings. After applying the TS method to remove weeds, the estimated R2 is 0.83, RMSE is 1.43, MAE is 1.05, and the overall counting accuracy is 99.2%. The weed segmentation method proposed in this paper can adapt to various seedling conditions. Under different emergence conditions, the estimated R2 of seedling count reaches a maximum of 0.88, with an RMSE below 1.29. The proposed approach in this study shows improved weed recognition accuracy on drone images compared to conventional image processing methods. It exhibits strong adaptability and stability, enhancing maize counting accuracy even in the presence of weeds.

show abstract

Enhanced Winter Wheat Seedling Classification and Identification Using the SETFL-ConvNeXt Model: Addressing Overfitting and Optimizing Training Strategies

Liu,

Yin,

Qian

et al. 2024

Agronomy

View full text Add to dashboard Cite

The growth status of winter wheat seedlings during the greening period is called the seedling situation. Timely and accurate determinations of the seedling situation type are important for subsequent field management measures and yield estimation. To solve the problems of low-efficiency artificial classification, subjective doping, inaccurate classification, and overfitting in transfer learning in classifying the seedling condition of winter wheat seedlings during the greening period, we propose an improved ConvNeXt winter wheat seedling status classification and identification network based on the pre-training–fine-tuning model addressing over-fitting in transfer learning. Based on ConvNeXt, a SETFL-ConvNeXt network (Squeeze and Excitation attention-tanh ConvNeXt using focal loss), a winter wheat seedling identification and grading network was designed by adding an improved SET attention module (Squeeze and Excitation attention-tanh) and replacing the Focal Loss function. The accuracy of the SETFL-ConvNeXt reached 96.68%. Compared with the classic ConvNeXt model, the accuracy of the Strong class, First class, and Third class increased by 1.188%, 2.199%, and 0.132%, respectively. With the model, we also compared the effects of different optimization strategies, five pre-training-fine-tuning models, and the degree of change in the pre-trained model. The accuracy of the fine-tuning models trained in the remaining layers increased by 0.19–6.19% using the last three frozen blocks, and the accuracy of the pre-trained model increased by 3.1–8.56% with the least degree of change method compared with the other methods. The SETFL-ConvNeXt network proposed in this study has high accuracy and can effectively address overfitting, providing theoretical and technical support for classifying winter wheat seedlings during the greening period. It also provides solutions and ideas for researchers who encounter overfitting.

show abstract

The estimation of wheat tiller number based on UAV images and gradual change features (GCFs)

Cited by 3 publications

References 56 publications

Plant Density Estimation Using UAV Imagery and Deep Learning

Plant Density Estimation Using UAV Imagery and Deep Learning

Unmanned Aerial Vehicle-Scale Weed Segmentation Method Based on Image Analysis Technology for Enhanced Accuracy of Maize Seedling Counting

Enhanced Winter Wheat Seedling Classification and Identification Using the SETFL-ConvNeXt Model: Addressing Overfitting and Optimizing Training Strategies

Contact Info

Product

Resources

About