Data segmentation method based on seedling density to improve the accuracy of rapeseed seedling recognition
Keywords:
rapeseed seedling, dense area, YOLOv7, object detection, countingAbstract
The accurate recognition of rapeseed seedlings is the premise of achieving accurate counting. Traditional target detection algorithms and current improved algorithms cannot balance the counting accuracy and seedling recognition at different densities. Thus, this study proposed improved YOLOv7 recognition models by automatically dividing dense and non-dense datasets. For the non-dense dataset, the attention mechanism CA is introduced, and the loss function DIoU is substituted; for the dense dataset, the attention mechanism CBAM is introduced, and the loss function GIoU is substituted, so that the network focuses on the target object to improve the accuracy of the model. The results show that the improved accuracy of the non-dense area reaches 97.78%, mAP@0.5 reaches 98.32%, and mAP@0.5:0.95 reaches 66.86%. The accuracy of the improved dense area reaches 97.85%, mAP@0.5 reaches 95.91%, and mAP@0.5:0.95 reaches 69.9%. In addition, this paper compared SSD, YOLOv5, YOLOv7, YOLOv7-tiny, and the improved YOLOv7 and validates the feasibility of the improved YOLOv7 model. The improved YOLOv7 model proposed in this paper can provide a useful reference for future research directions of seedling recognition.
Key words: rapeseed seedling; dense area; YOLOv7; object detection; counting
DOI: 10.25165/j.ijabe.20261904.9572
Citation: Wang Q, Chen L Q, Zheng Q, Liu L C. Data segmentation method based on seedling density to improve the accuracy
of rapeseed seedling recognition. Int J Agric & Biol Eng, 2026; 19(4): 282–291.
References
[1] Wang Q. Development status and countermeasures of oilseed rape industry in Anhui Province. Modern Agricultural Science and Technology, 2023（10）: 213–216. （in Chinese） DOI: 10.3969/j.issn.1007-5739.2023.10.054.
[2] Zhao D H, Cao Z W, Chen L J, Zhang G X, Zhu Y Z, Han J. Optimising the effect of nitrogen on winter oilseed rape grain yield in China: A meta-analysis. European Journal of Agronomy, 2023; 144: 126755.
[3] Xu X, Zhao Y. A Band Math-ROC operation for early differentiation between Sclerotinia sclerotiorum and Botrytis cinerea in oilseed rape. Computers and Electronics in Agriculture, 2015; 118: 116–123.
[4] Wang H, Han S, Zhou X, Bu R, Wu J. Fertilizer application technology for mechanically sown winter rapeseed in the river basin of Anhui Province. China Agricultural Technology Extension, 2019; S1: 91–93.
[5] Yang H B, Lan Y B, Lu L Q, Gong D C, Miao J C, Zhao J. New method for cotton fractional vegetation cover extraction based on UAV RGB images. Int J Agric & Biol Eng, 2022; 15（4）: 172–180.
[6] Zhuang L H, Wang C Y, Hao H Y, Li J H, Xu L Q, Liu S Y, et al. Maize emergence rate and leaf emergence speed estimation via image detection under field rail-based phenotyping platform. Computers and Electronics in Agriculture, 2024; 220: 108838.
[7] Hu W Z, Wane S O, Zhu J K, Li D S, Zhang Q, Bie X T, et al. Review of deep learning-based weed identification in crop fields. Int J Agric & Biol Eng, 2023; 16（4）: 1–10.
[8] Lin H B, Lu Y D, Ding R C, Xiu Y F, Yang F Z. Detection of wheat seedling lines in the complex environment via deep learning. Int J Agric & Biol Eng, 2024; 17（5）: 255–265.
[9] Rai N, Zhang Y, Ram B G, Schumacher L, Yellavajjala R K, Bajwa S, et al. Applications of deep learning in precision weed management: A review. Computers and Electronics in Agriculture, 2023; 206: 107698.
[10] Meng X P, Li C C, Li J B, Li X Y, Guo F C, Xiao Z. YOLOv7-MA: Improved YOLOv7-based wheat head detection and counting. Remote Sensing, 2023; 15（15）: 3770.
[11] Wang S Y, Wu D S, Zheng X Y. TBC-YOLOv7: A refined YOLOv7-based algorithm for tea bud grading detection. Frontiers in Plant Science, 2023; 14: 1223410.
[12] Ma H X, Dong K B, Wang Y F, Wei S H, Huang W G, Gou J P. Research on lightweight plant recognition model based on improved YOLOv5s. Transactions of the CSAM, 2023; 54（8）: 267–276. （in Chinese）
[13] Zhang P, Li D. YOLO-VOLO-LS: A novel method for variety identification of early lettuce seedlings. Frontiers in Plant Science, 2022; 13: 806878.
[14] Zhu Z, He Y, Li W, Cai Z, Wang Q, Ma M. Improved YOLOv7 model for duck egg recognition and localization in complex environments. Transactions of the CSAE, 2023; 39（11）: 274–285. （in Chinese）
[15] Zhao K, Zhao L, Zhao Y, Deng H. Study on lightweight model of maize seedling object detection based on YOLOv7. Applied Sciences, 2023; 13（13）: 7731.
[16] Li Z D, Zhang Y F, Wang Y H, Zhao Q H, Liu L C, Zhang T, et al. Identification of rapeseed seedling number based on YC-YOLOv7 model. Transactions of the CSAM, 2024; 55（12）: 322–332. （in Chinese）
[17] Li L, Long C F, Yang Y J, Wang X, Liu X B. A detection method for rapeseed and weeds at the seedling stage based on FEPW R-CNN. Agriculture and Technology, 2025; 45（10）: 35–40. （in Chinese）
[18] Yang H, Liu Y, Wang S, Qu H, Li N, Wu J, et al. Improved apple fruit target recognition method based on YOLOv7 model. Agriculture, 2023; 13: 1278.
[19] Wu W, Li X L, Hu Z H, Liu X Z. Ship detection and recognition based on improved YOLOv7. Comput Mater Contin, 2023; 76: 489–498.
[20] Pan Y Y, Zhu N Z, Ding L, Li X H, Goh H-H, Han C, et al. Identification and counting of sugarcane seedlings in the field using improved faster R-CNN. Remote Sens, 2022; 14: 5846.
[21] Zhao L L, Zhu M L. MS-YOLOv7: YOLOv7 based on multi-scale for object detection on UAV aerial photography. Drones, 2023; 7: 188.
[22] Li Q X, Ma W J, Li H, Zhang X D, Zhang R Y, Zhou W H. Cotton-YOLO: Improved YOLOv7 for rapid detection of foreign fibers in seed cotton. Computers and Electronics in Agriculture, 2024; 219: 108752.
[23] Meng J, Kang F, Wang Y, Tong S, Zhang C, Chen C. Tea buds detection in complex background based on improved YOLOv7. IEEE Access, 2023; 11: 88295–88304.
[24] Wang J B, Wu J, Wu J W, Wang J P, Wang J. YOLOv7 optimization model based on attention mechanism applied in dense scenes. Applied Sciences, 2023; 13: 9173.
[25] Liu Y, Wang H R, Liu Y H, Luo Y Y, Li H Y, Chen H F, et al. A trunk detection method for camellia oleifera fruit harvesting robot based on improved YOLOv7. Forests, 2023; 14: 1453.
[26] Jiang T Y, Li C, Yang M, Wang Z L. An improved YOLOv5s algorithm for object detection with an attention mechanism. Electronics, 2022; 11: 2494.
[27] Sozzi M, Cantalamessa S, Cogato A, Kayad A, Marinello F. Automatic bunch detection in white grape varieties using YOLOv3, YOLOv4, and YOLOv5 deep learning algorithms. Agronomy, 2022; 12: 319.
[28] Li H R, Yan E P, Jiang J W, Mo D K. Monitoring of key Camellia Oleifera phenology features using field cameras and deep learning. Computers and Electronics in Agriculture, 2024; 219: 108748.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Agricultural and Biological Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
IJABE is an international peer reviewed, open access journal, adopting Creative Commons Copyright Notices as follows.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
