Feature recognition algorithm in intelligent planting and preparation technology of single-bud segment sugarcane

Xinpeng Liu; Xuehu Dong; Mingxin Hou; Zhaojun Niu; Zunxiang Li; Zhen Zhang; Li Huang

doi:10.25165/ijabe.v18i4.8544

Authors

Xinpeng Liu 1. Institute of Subtropical Crops, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang 524088, Guangdong, China; 6. Key Laboratory of Tropical Fruit Biology, Ministry of Agriculture and Rural Affairs, Zhanjiang 524091, Guangdong, China
Xuehu Dong 2. Hainan Agricultural Machinery Appraisal and Promotion Station, Haikou 570000, China;
Mingxin Hou 3. Guangdong Ocean University, Zhanjiang 524088, Guangdong, China;
Zhaojun Niu 4. Institute of Agricultural Machinery, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang 524088, Guangdong, China;
Zunxiang Li 1. Institute of Subtropical Crops, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang 524088, Guangdong, China; 6. Key Laboratory of Tropical Fruit Biology, Ministry of Agriculture and Rural Affairs, Zhanjiang 524091, Guangdong, China
Zhen Zhang 5. Chinese Academy of Tropical Agricultural Sciences, Haikou 570100, China;
Li Huang 3. Guangdong Ocean University, Zhanjiang 524088, Guangdong, China;

DOI:

https://doi.org/10.25165/ijabe.v18i4.8544

Keywords:

sugarcane seed with single bud, object detection, YOLOv5s, intelligent identification

Abstract

In order to avoid the uneven phenomenon of sugarcane planting, such as seed missing and reseeding, the computer vision technology was applied to the intelligent identification of sugarcane varieties with single-bud segment, and the design idea of rapid detection of sugarcane planting distribution was proposed in this study. With sugarcane species with single-bud segment as the research object, the sugarcane species distribution image was acquired, and LabelImg was used for image annotation and format conversion to build the YOLOv5s target detection model. On the basis of depth-separable convolution, SE module is spliced to obtain the weights of extracted features and extract key features of input feature map. By adding regularization to constrain the BN layer coefficient, sparse regularization is carried out on the BN layer to reduce the network input size and improve the model training speed. On this basis, 600 rounds of iterative training were carried out to complete the target recognition of sugarcane species characteristics in single-bud segment. The results showed that the recognition accuracy, mAP value, and Recall value of YOLOv5s single-bud segment target detection model are 98.95%, 98.89%, and 98.69%, and the loss value converges in advance between 0-0.02. The results showed that YOLOv5s could effectively detect and identify sugarcane seeds with single-bud segment during field planting, which lays a foundation for promoting precise and intelligent sugarcane planting. Keywords: sugarcane seed with single bud, object detection, YOLOv5s, intelligent identification DOI: 10.25165/j.ijabe.20251804.8544 Citation: Liu X P, Dong X H, Hou M X, Niu Z J, Li Z X, Zhang Z, et al. Feature recognition algorithm in intelligent planting and preparation technology of single-bud segment sugarcane. Int J Agric & Biol Eng, 2025; 18(4): 275–281.

References

Vianna M d S, Nassif D S P, Carvalho K d S, Marin F R. Modelling the trash blanket effect on sugar-cane growth and water use. Computers and Electronics in Agriculture, 2020; 172(5): 105361. [2] Elsheery N I, Sunoja V S J, Wen Y, Zhu J J, Muralidharan G, Cao K F. Foliar application of nanoparticles mitigates the chilling effect on photosynthesis and photoprotection in sugarcane. Plant Physiology and Biochemistry, 2020; 149(4): 50–60.

Yang R, Li J, Liu Q, Huang W S, Yin K, Qiao X, et al. Gradient-based method for the identification of multi-nodes in sugarcane. Information Processing in Agriculture, 2020; 7(4): 491–499.

Henry O, Patricia L, Raúl Mira, Angel D. Computer vision based food grain classification: A comprehensive survey. Computers and Electronics in Agriculture, 2021; 187(8): 1688–1699.

He Q, Shen H, Jin Y. Research on novel lightweight object detection and recognition algorithms. International Conference on Information Systems Engineering (ICISE), 2023; pp.442–448. DOI: 10.1109/ICISE60366. 2023.00100.

Li B Z, Jiang W Z, Gu J J. Research on target detection algorithm based on deep learning technology. IEEE International Conference on Power Electronics, Computer Applications (ICPECA), Shenyang, China, 2021; pp.137–142. DOI: 10.1109/ICPECA51329.2021.9362714.

He F G, Deng G R, Li M, Niu Z J, You X. Design of electromagnetic vibration-type single-bud sugarcane seed metering device. Sugar Tech, 2019; 21(5): 815–824.

Fan Y L, Zhou D Q, Deng Q R, He F G, Wang M L. Design and experiment of sugarcane seed cutting equipment based on machine vision. Journal of Agricultural Mechanization Research, 2021; 43(5): 55–60.

Liu X P, Niu Z J, Li M, Hou M X, Wei L J, Zhang Y, Huang L. Design and experimental research on disc-type seeding device for single-bud sugarcane seeds. Int J Agric & Biol Eng, 2023; 16(2): 115–124.

Murthy C B, Hashmi M F, Keskar A G. Optimized MobileNetplus SSD: a real-time pedestrian detection on a low-end edge device. International Journal of Multimedia Information Retrieval, 2021; 10: 171-184.

Velumani K, Madec S, de Solan B, Lopez-Lozano R, Gillet J, Labrosse J, et al. An automatic method based on daily in situ images and deep learning to date wheat heading stage. Field Crops Research, 2020; 252: 107793.

Ji J T, Han Z H, Zhao K X, Li Q W, Du S C. Detection of the farmland plow areas using RGB-D images with an improved YOLOv5 model. Int J Agric & Biol Eng, 2024; 17(3): 156–165.

Shi H K, Xiao W F, Zhu S P, Li L B, Zhang J F. CA-YOLOv5: Detection model for healthy and diseased silkworms in mixed conditions based on improved YOLOv5. Int J Agric & Biol Eng, 2023; 16(6): 236–245.

Zou X G, Yin Z L, Li Y H, Gong F, Bai Y G, Zhao Z H, et al. Novel multiple object tracking method for yellow feather broilers in a flat breeding chamber based on improved YOLOv3 and deep SORT. Int J Agric & Biol Eng, 2023; 16(5): 44–55.

Zhao L J, Jia Y F, Yin W K, Li Z H, Liu C D, Luo H, et al. Recognition and localization method of maize weeding robot based on improved YOLOv5. Int J Agric & Biol Eng, 2025; 18(2): 248–258.

Deng R L, Tao M, Huang X N, Bangura K, Jiang Q, Jiang Y, et al. Automated counting grains on the rice panicle based on deep learning method. Sensors, 2021; 21(1): 281.

Kraft D, Bierbaum A, Kjaergaard M, Ratkevicius J, Kjaer-Nielsen A, Ryberg C, et al. Tactile object exploration using cursor navigation sensors. WorldHaptics, 3rd Joint EuroHaptics Conference and Symposium on Haptic Interfaces for Virtual Environment and Teleoperator Systems, Salt Lake City, UT, USA, 2009; pp.296–301. DOI: 10.1109/WHC.2009. 4810827.

Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, et al. SSD: Single shot multibox detector. Proceedings of the European Conference on Computer Vision. Cham: Springer, 2016; pp.21–37. DOI: 10.1007/978-3319-46448-0_2.

Ren S Q, He K M, Girshick R, Sun J. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017; 39(6): 1137–1149.

He K M, Zhang X Y, Ren S Q, Sun J. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015; 37(9): 1904–1916.

Bi L Y, Deng L X, Lou H T, Zhang H Y, Lin S J, Liu X C, et al. URSYOLOv5s: object detection algorithm for UAV remote sensing images. Physica Scripta, 2024; 99(8): 086005.

Aytekin A, Rezaeitabar Y, Dogru S, Ulusoy İ. Railway fastener inspection by real-time machine vision. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2015; 45(7): 1101–1107.

Zheng Z, Wang P, Ren D, Liu W, Ye R, Hu Q, et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Transactions on Cybernetics, 2022; 52(8): 8574–8586.

Nafea M M, Tan S Y, Jubair M A. A review of lightweight object detection algorithms for mobile augmented reality. International Journal of Advanced Computer Science and Applications (IJACSA), 2022; 13(11): 536–546.

Tan M X, Le Q V. MixConv: Mixed depthwise convolutional kernels. Published online December 1, 2019. DOI: 10.48550/arXiv.1907.09595.

Loshchilov I, Hutter F. Sgdr: Stochastic gradient descent with warm restarts. Published online May 3, 2017. DOI: 10.48550/arXiv.1608.03983.

Chu Y, Wang J, Ma L, Wu C. LMSFA-YOLO: A lightweight target detection network in Remote sensing images based on Multiscale feature fusion. J. King Saud Univ. Comput. Inf. Sci., 2025; 37(63): 1–21.

Song Z S, Liu Y, Zheng L, Tie J, Wang J. Identification of green citrus based on improved YOLOV3 in natural environment. Journal of Chinese Agricultural Mechanization, 2021; 42(11): 159–165.

Liu J B, Huang Y P, Wang S C, Zhao X X, Zou Q, Zhang X Y. Rail fastener defect inspection method for multi railways based on machine vision. Railway Sciences, 2022; 1(2): 210–223.

Zhou L, Zhang C, Taha M F, Wei X, He Y, Qiu Z, et al. Wheat kernel variety identification based on a large near-infrared spectral dataset and a novel deep learning-based feature selection method. Front Plant Sci, 2020; 11: 575810.

Jia Z W, Yang X H, Wang Z, Yu R R, Wang R B. Automatic lameness detection in dairy cows based on machine vision. Int J Agric & Biol Eng, 2023; 16(3): 217–224.

Feature recognition algorithm in intelligent planting and preparation technology of single-bud segment sugarcane

Authors

DOI:

Keywords:

Abstract

References

Downloads

Published

How to Cite

Issue

Section

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:

Information