1. Introduction

2. Materials and Methods

2.1. Field Experiments

Field experiments were conducted during 2021 and 2023 in Tongliao City (43°42′ N, 122°25′ E) and Liaohe Town (43°43′N, 122°10′E) in Inner Mongolia. This region features a semi-arid continental monsoon climate with 2,500-2,800 h of annual sunshine, an average daily temperature of 21.0°C, a cumulative ≥10°C temperature of 3,000-3,300°C·d, a frost-free period of 150-169 d, and an average annual precipitation of 280-390 mm during the maize growing season (May-Eleventh). Both fields consisted of sandy loam soil and had previously been used for maize cultivation. A wide-narrow planting pattern was implemented, with alternating rows spaced at 80 cm and 40 cm. Irrigation was supplied through shallow buried drip lines at a rate of 300 m3/ha. Base fertilizer with an N, P, K ratio of 13:22:15 was applied at a rate of 525 kg/ha through water-fertilizer integration methods.

The maize variety Xianyu 335 was selected for the density experiment conducted in Qianxiaili Village. Trials were planted on May, 10, 2021 at densities of 30,000, 45,000, 60,000, 75,000, 90,000, 105,000, 120,000, and 135,000 plants/ha. Data was collected on May 29^th (2 leaves unfolded), June 1^st (3 leaves unfolded), June 5^th (4 leaves unfolded), and June 16^th (6 leaves unfolded).

Figure 1. Experimental area.

Figure 1. Experimental area.

The maize variety Dika 159 was selected for the flight altitude experiment conducted in Dongsheng Village. Trials were planted on May, 8, 2023 at a density of 90,000 plants/ha. Data was collected on May 27^th (2 leaves unfolded), May 31^st (3 leaves unfolded), June 4^th (4 leaves unfolded), June 7^th (5 leaves unfolded), and June 11^th (6 leaves unfolded).

In 2021 and 2023, we carried out validation trials on the agricultural lands of local farmers. These trials included three distinct types of cultivation areas: High Yielding Fields in 2021, Agricultural Cooperative plots in 2023, and Peasant Household farmland in 2021. Maize varieties Jingke 968, Tianyu 108, and Dika 159 were planted in each plot at densities of 100,000, 80,000, and 65,000 plants/ha. UAV visible light images were collected at noon during the 3-leaf stage from 8 sample areas (5 m × 2.4 m) within each field. Additional images were collected from 20 randomly selected sample areas (11.66 m²) in each field, which were monitored at noon on June 1^st, 2021 (3 leaves unfolded) and May 31^st, 2023 (3 leaves unfolded).

2.3. Data Construction and Preprocessing

2.3.1. Image Preprocessing

After RGB images were exported from the UAV, Agisoft Metashape Professional software was used for image stitching. Feature points in each image were initially automatically calculated and then matched in the image sequence through multiple iterations. Next, dense point clouds were generated before the final images were produced (Figure 2a).

Experimental fields were cropped and divided into multiple plots (Figure 2b). Original high-quality maize seedling images were cropped to 1000×1000 pixels by a sliding step [18]. Poor-quality images including those with large shooting angles, obvious occlusions, and uneven illumination were removed. Final images (900 total) were categorized by quantity of spreading leaves and quantity of straw.

Figure 3. Maize seedlings at (a) V2, (b) V3, (c) V4, (d) V5, (e) and V6 stages. (f) Low, (g) moderate, and (h) high quantities of stover.

Figure 3. Maize seedlings at (a) V2, (b) V3, (c) V4, (d) V5, (e) and V6 stages. (f) Low, (g) moderate, and (h) high quantities of stover.

The location and size of each seedling are labeled in each image [18] (Figure 4).

2.3.2. Data Enhancements

Images were adjusted during the data augmentation process, including horizontal and vertical flipping, random contrast and hue adjustments, and resolution alterations. These modifications were used to simulate the effects of varying lighting and environmental factors during different times of day and flight altitudes. Training and testing datasets were created from the resulting 14,815 images. The dataset was then divided, with 90% of images used for model training and 10% for validating model performance.

Figure 5. (a) Random contrast, (b) random hue adjustment, (c) horizontal flip, and (d) vertical flip. Images were modified to resolutions of (e) 800×800, (f) 500×500, and (g) 300×300.

Figure 5. (a) Random contrast, (b) random hue adjustment, (c) horizontal flip, and (d) vertical flip. Images were modified to resolutions of (e) 800×800, (f) 500×500, and (g) 300×300.

2.4. YOLOv8 Model Framework

YOLO (You Only Look Once) is a highly popular single-stage object detection framework, which exhibits enhanced processing speeds, performance, efficiency, and flexibility when compared with two-stage algorithms. YOLOv8 is comprised of a Backbone, Neck, and Head (Figure 6).

2.4.1. Backbone and Neck

The YOLOv8 Backbone employs the Darknet-53 network structure. Through effective feature learning and residual connections, the model avoids the gradient vanishing typical of deep neural networks, enabling it to capture high-level semantic features [19]. This module primarily functions to extract and fuse these higher-level features through multiple iterations of maximum pooling [20].

The C3 module in YOLOv8n is replaced with the more gradient-rich C2f module, which adjusts the number of channels based on the intended model scale to minimize weight [21]. This change enhances efficiency and efficacy when processing images of various sizes and complexities.

Figure 7. C3 and C2f modules.

Figure 7. C3 and C2f modules.

2.4.2. Head

The YOLOv8n Head structure exhibits two major improvements when compared to YOLOv5. Firstly, the newer model has separate classification and detection heads (Decoupled-Head), a structure type that has been increasing in popularity. Secondly, the model transitions away from the Anchor-Based approach to an Anchor-Free approach.

Figure 8. Coupled-Head and Decoupled-Head modules.

Figure 8. Coupled-Head and Decoupled-Head modules.

2.4.3. Loss Calculation

Loss calculation in the YOLOv8n model is simplified by removing the objectness branch and only considering the classification and regression branches. The classification branch continues to utilize Binary Cross-Entropy (BCE) Loss. YOLOv8n abandons the traditional IOU matching and unilateral proportion allocation methods in favor of the Task-Aligned Assigner for positive and negative sample matching. Additionally, the model introduces Distribution Focal Loss (DFL) [22] to improve the precision and reliability of object detection tasks. Loss calculations are conducted according to the following formulas:

$$DFL\left(S_i,S_{i+1}\right)=-\left(\left(y_{i+1}-y\right)\log \left(S_i\right)+\left(y-y_i\right)\log \left(S_{i+1}\right)\right)$$

(1)

In two consecutive distributions, $S_i$and $S_{i+1}$, the values $y_i$i and $y_{i+1}$ represent the corresponding probability density values at specific points or for the distributions as a whole. The weighting of the loss function is adjusted based on $y$, to reflect changes or differences in these probability densities.

Classification loss is typically calculated using cross-entropy loss, which measures the difference between the predicted class probabilities and the ground truth class labels:

$$L_{cls}=-\frac{1}{N}\sum _{i\in pos\bigcup Neg}\sum _{c=1}^c{y}_c^{\left(i\right)}\log \left({\widehat{y}}_c^{\left(i\right)}\right)$$

(2)

In these formulas, $i$ represents the sample index and $i\in pos\bigcup Neg$ denotes the set of positive and negative samples. $c$ represents the category index and $C$ denotes the total number of categories. The real label of the $i$^th sample for category $c$ is denoted by $y_c^{\left(i\right)}$, which indicates whether the sample actually belongs to category $c$ (typically 1 for yes, 0 for no). The model's predicted probability that the $i$^th sample belongs to category $c$ is represented by ${\widehat{y}}_c^{\left(i\right)}$.

$$L={\lambda }_{loc}{L}_{loc}+{\lambda }_{cls}{L}_{cls}$$

(3)

$L$ represents the total loss function. ${\lambda }_{cls}$ and ${\lambda }_{loc}$ are hyperparameters controlling the relative importance of localization and classification loss.

2.6. Test Parameter Setting and Training Process Analysis

The computer specifications and software environments used are described in Table 3. The training parameters were tailored to the characteristics of the task dataset. The training settings were tested with a batch size of 8, an image size of 640, a confidence threshold (conf_thres) of 0.3, and an intersection over union threshold (iou_thres) of 0.2.

Table 2. Model training specifications.

Table 2. Model training specifications.

Experimental environment
Processor	12th Gen Intel(R) Core(TM) i5-12600KF3.69 GHz
Operating system	Windows 10
Ram	64GB
Graphics card	NVIDIA GeForce RTX 3060
Programming language	Python 3.8
Model	YOLOv8n	YOLOv5、3	Other
Deep learning libraries	CUDA11.7	CUDA11.1	CUDA 10.2
Software	Ultralytics=8.0.105 Opencv=4.7.0.72	Opencv=4.1.2 Numpy=1.18.5	Mmcv=2.0.0 Mmdet=3.0.0 Mmengine=0.9.1

3. Results

3.1. Model Comparison

To further validate the performance of YOLOv8n, multiple one-stage and two-stage object detection models were trained and evaluated based on metrics such as AP₅₀, AP_50:95, params, and FLOPs (Table 4, Figure 11).

Table 3. Comparison of object detection model performances.

Table 3. Comparison of object detection model performances.

Category	Model	Backbone	Image size	AP50	AP50:95	Params	FLOPs
One-stage	YOLOv8n	New CSP-Darknet53	640×640	0.979	0.647	3.20M	8.7G
	YOLOv5n	CSP-Darknet53	640×640	0.955	0.511	1.90M	4.5G
	SSD	VGG16	416×416	0.946	0.530	23.75M	137.1G
	FCOS	Resnet50	640×640	0.925	0.495	31.84M	78.6G
	YOLOv3-tiny	Tiny-Darknet	640×640	0.922	0.453	8.44M	13.3G
	RetinaNet	Resnet50	300×300	0.863	0.412	36.10M	81.7G
Two-stage	Defomermable DETR	Resnet50	640×640	0.941	0.474	36.10M	27.4G
	Cascade R-CNN	Resnet50	640×640	0.888	0.569	68.94M	80.1G
	Faster R-CNN	Resnet50	640×640	0.887	0.530	41.12M	78.1G

Figure 9. Performance comparison of different models. (a) Relationship between AP₅₀, Params, and FLOPs. (b) Relationship between AP_50:95, Params, and FLOPs.

Figure 9. Performance comparison of different models. (a) Relationship between AP₅₀, Params, and FLOPs. (b) Relationship between AP_50:95, Params, and FLOPs.

The performances of YOLOv8n and YOLOv5n stand out among the single-stage models, achieving AP₅₀ values of 0.979 and 0.955, respectively, at an input image size of 640×640. Although SSD and FCOS also performed highly, their increased number of parameters and computational requirements under the same conditions render them less suitable for resource-constrained scenarios. YOLOv3-tiny and RetinaNet demonstrated slightly reduced performances and are better suited to environments with limited resources.

Deformable DETR showed the highest performance out of the two-stage models, achieving an AP₅₀ value of 0.941 at an input image size of 640×640. Moreover, the model has a reduced number of parameters and computational requirements, exhibiting an optimal balance between performance and efficiency. Comparatively, Faster R-CNN and Cascade R-CNN perform similarly at the same size but have more requirements, making them less ideal for resource-limited situations.

3.3. Impact of Flight Altitude and Growth Stage on Detection

In this study, plant detection was conducted through UAV flights at various growth stages and altitudes (20 m, 40 m, and 60 m). Metrics such as accuracy rate, miss rate, false detection rate, and rRMSE were calculated to explore potential impacts. Twenty images per altitude across five growth stages were collected, resulting in a total of 300 images for inference. Overall, changes in altitude were found to affect image resolution and coverage area.

Figure 11. Performance of YOLOv8n, YOLOv3-tiny, Deformable-DETR, and Faster R-CNN in terms of F1-score, Recall, Precision, and rRMSE at different flight altitudes and growth stages.

Figure 11. Performance of YOLOv8n, YOLOv3-tiny, Deformable-DETR, and Faster R-CNN in terms of F1-score, Recall, Precision, and rRMSE at different flight altitudes and growth stages.

The F1-scores of all four models decreased across all growth stages (V2-V6) as flight altitude increased. Performances were relatively high at 20 m but declined significantly at 60 m. The Recall and Precision metrics display a similar but less severe trend. Overall, these models demonstrated greater efficacy at lower altitudes.

4. Discussion

5. Conclusions

References

1. Erenstein, O.; Jaleta, M.; Sonder, K.; Mottaleb, K.; Prasanna, B.M. Global maize production, consumption and trade: trends and R&D implications. Food Security 2022, 14, 1295–1319. [Google Scholar] [CrossRef]
2. LI shaoKun, Z.J. , DONG ShuTing, ZHAO Ming, LI ChaoHai, CUI YanHong, LIU YongHong, GAO JuLin, XUE JiQuan, WANG LiChun, WANG Pu, LU WeiPing, WANG JunHe, YANG QiFeng, WANG ZiMing.. Advances and Prospects of Maize Cultivation in China. Scientia Agricultura Sinica 2017, 50, 1941–1959. [Google Scholar]
3. Kimmelshue, C.L.; Goggi, S.; Moore, K.J. Seed Size, Planting Depth, and a Perennial Groundcover System Effect on Corn Emergence and Grain Yield. 2022, 12, 437. [CrossRef]
4. Onishi, M.; Ise, T. Explainable identification and mapping of trees using UAV RGB image and deep learning. Scientific reports 2021, 11, 903. [Google Scholar] [CrossRef]
5. Candiago, S.; Remondino, F.; De Giglio, M.; Dubbini, M.; Gattelli, M. Evaluating multispectral images and vegetation indices for precision farming applications from UAV images. Remote sensing 2015, 7, 4026–4047. [Google Scholar] [CrossRef]
6. Adão, T.; Hruška, J.; Pádua, L.; Bessa, J.; Peres, E.; Morais, R.; Sousa, J.J. Hyperspectral imaging: A review on UAV-based sensors, data processing and applications for agriculture and forestry. Remote sensing 2017, 9, 1110. [Google Scholar] [CrossRef]
7. Wallace, L.; Lucieer, A.; Watson, C.; Turner, D. Development of a UAV-LiDAR system with application to forest inventory. Remote sensing 2012, 4, 1519–1543. [Google Scholar] [CrossRef]
8. Liu Shuaibing, Y.G., Zhou Chengquan, Jing Haitao, Feng Haikuan, Xu Bo, Yang Hao. . Extraction of maize seedlingnumber information based on UA imagery. Transactions of the Chinese Society of Agricultural Engineering 2018, 34, 69–77.
9. Bai, Y.; Nie, C.; Wang, H.; Cheng, M.; Liu, S.; Yu, X.; Shao, M.; Wang, Z.; Wang, S.; Tuohuti, N.; et al. A fast and robust method for plant count in sunflower and maize at different seedling stages using high-resolution UAV RGB imagery. Precision Agriculture 2022, 23, 1720–1742. [Google Scholar] [CrossRef]
10. Liu, T.; Yang, T.; Li, C.; Li, R.; Wu, W.; Zhong, X.; Sun, C.; Guo, W. A method to calculate the number of wheat seedlings in the 1st to the 3rd leaf growth stages. Plant Methods 2018, 14, 101. [Google Scholar] [CrossRef] [PubMed]
11. Xu, B.; Chen, L.; Xu, M.; Tan, Y. Path Planning Algorithm for Plant Protection UAVs in Multiple Operation Areas. Transactions of the Chinese Society for Agricultural Machinery 2017, 48, 75–81. [Google Scholar]
12. Quan, L.; Feng, H.; Lv, Y.; Wang, Q.; Zhang, C.; Liu, J.; Yuan, Z. Maize seedling detection under different growth stages and complex field environments based on an improved Faster R–CNN. Biosystems Engineering 2019, 184, 1–23. [Google Scholar] [CrossRef]
13. Zhang, Y.; Xiao, D.; Liu, Y.; Wu, H. An algorithm for automatic identification of multiple developmental stages of rice spikes based on improved Faster R-CNN. The Crop Journal 2022, 10, 1323–1333. [Google Scholar] [CrossRef]
14. Gao, J.X.; Tan, F.; Cui, J.P.; Ma, B. A Method for Obtaining the Number of Maize Seedlings Based on the Improved YOLOv4 Lightweight Neural Network. Agriculture-Basel 2022, 12. [Google Scholar] [CrossRef]
15. Zhang, X.; Zhu, D.; Wen, R. SwinT-YOLO: Detection of densely distributed maize tassels in remote sensing images. Computers and Electronics in Agriculture 2023, 210. [Google Scholar] [CrossRef]
16. Li, R.; Wu, Y.P. Improved YOLO v5 Wheat Ear Detection Algorithm Based on Attention Mechanism. Electronics 2022, 11. [Google Scholar] [CrossRef]
17. Zhang, Y.; Li, M.Z.; Ma, X.X.; Wu, X.T.; Wang, Y.J. High-Precision Wheat Head Detection Model Based on One-Stage Network and GAN Model. Frontiers in Plant Science 2022, 13. [Google Scholar] [CrossRef] [PubMed]
18. Tzutalin, D. Labelimg. git code. 2015.
19. Pathak, D.; Raju, U.J.O. Content-based image retrieval using feature-fusion of GroupNormalized-Inception-Darknet-53 features and handcraft features. 2021, 246, 167754.
20. He, K.; Zhang, X.; Ren, S.; Sun, J.J.I.t.o.p.a.; intelligence, m. Spatial pyramid pooling in deep convolutional networks for visual recognition. 2015, 37, 1904–1916. [CrossRef]
21. Xiao, B.; Nguyen, M.; Yan, W.Q. Fruit ripeness identification using YOLOv8 model. Multimedia Tools and Applications 2023. [Google Scholar] [CrossRef]
22. Li, X.; Wang, W.; Wu, L.; Chen, S.; Hu, X.; Li, J.; Tang, J.; Yang, J.J.A.i.N.I.P.S. Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. 2020, 33, 21002–21012.
23. Li, X.; Chen, J.; He, Y.; Yang, G.; Li, Z.; Tao, Y.; Li, Y.; Li, Y.; Huang, L.; Feng, X. High-through counting of Chinese cabbage trichomes based on deep learning and trinocular stereo microscope. Computers and Electronics in Agriculture 2023, 212, 108134. [Google Scholar] [CrossRef]
24. Zhu, X.; Su, W.; Lu, L.; Li, B.; Wang, X.; Dai, J.J.a.p.a. Deformable detr: Deformable transformers for end-to-end object detection. 2020.
25. Song, G.; Liu, Y.; Wang, X. Revisiting the sibling head in object detector. In Proceedings of the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020; pp. 11563–11572.
26. Wu, Y.; Chen, Y.; Yuan, L.; Liu, Z.; Wang, L.; Li, H.; Fu, Y. Rethinking classification and localization for object detection. In Proceedings of the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020; pp. 10186–10195.
27. Li, X.; Chen, J.; He, Y.; Yang, G.; Li, Z.; Tao, Y.; Li, Y.; Li, Y.; Huang, L.; Feng, X.J.C.; et al. High-through counting of Chinese cabbage trichomes based on deep learning and trinocular stereo microscope. 2023, 212, 108134. [CrossRef]
28. Liu, S.; Baret, F.; Andrieu, B.; Burger, P.; Hemmerlé, M.J.F.i.P.S. Estimation of wheat plant density at early stages using high resolution imagery. 2017, 8, 739. [CrossRef]
29. Liu, M.; Su, W.-H.; Wang, X.-Q.J.R.S. Quantitative Evaluation of Maize Emergence Using UAV Imagery and Deep Learning. 2023, 15, 1979. [CrossRef]
30. Feng, Y.; Chen, W.; Ma, Y.; Zhang, Z.; Gao, P.; Lv, X.J.R.S. Cotton Seedling Detection and Counting Based on UAV Multispectral Images and Deep Learning Methods. 2023, 15, 2680. [CrossRef]
31. Gong, Y.; Yu, X.; Ding, Y.; Peng, X.; Zhao, J.; Han, Z. Effective fusion factor in FPN for tiny object detection. In Proceedings of the Proceedings of the IEEE/CVF winter conference on applications of computer vision, 2021; pp. 1160–1168.