深度学习在麦穗计数中的应用分析
DOI:
https://doi.org/10.64549/jtii.v1i5.112Keywords:
麦穗计数, 深度学习, 田间图像, 自动计数Abstract
麦穗计数是开展小麦群体表型分析和产量估测的一项基础工作。随着深度学习技术的发展，利用田间图像实现麦穗自动计数受到广泛关注，并逐渐成为智慧农业领域的研究方向之一。本文围绕深度学习在麦穗计数中的应用，对现有方法进行梳理，比较不同方法的特点及适用场景，并结合田间应用需求，分析现有方法在实际应用中存在的问题。在此基础上，总结麦穗自动计数技术的发展方向，为麦穗自动计数技术的研究与应用提供参考。
References
[1] Zhang, G., Wang, Z., Liu, B., Gu, L., Zhen, W. and Yao, W., 2024. A density map-based method for counting wheat ears. Frontiers in Plant Science, 15, pp.1354428.
[2] 滕桂法,闫明月,姚竟发,等.基于改进YOLOv7模型的田间麦穗识别与计数[J].中国农机化学报,2025,46(12):2+77-85.
[3] 鲍文霞,苏彪彪,胡根生,等.基于FE-P2Pnet的无人机小麦图像麦穗计数方法[J].农业机械学报,2024,55(4):155-164+289.
[4] 孙俊,杨锴锋,罗元秋,等.基于无人机图像的多尺度感知麦穗计数方法[J].农业工程学报,2021,37(23):136-144.
[5] Yang, B., Chen, R., Gao, Z. and Zhi, H., 2024. FIDMT-GhostNet: a lightweight density estimation model for wheat ear counting. Frontiers in plant science, 15, pp.1435042.
[6] 王玲,张旗,冯天赐,等.基于YOLO v7-ST模型的小麦籽粒计数方法研究[J].农业机械学报,2023,54(10):188-197+204.
[7] Hong, Q., Liu, W., Zhu, Y., Ren, T., Shi, C., Lu, Z., Yang, Y., Deng, R., Qian, J. and Tan, C., 2024. CTHNet: A network for wheat ear counting with local-global features fusion based on hybrid architecture. Frontiers in Plant Science, 15, pp.1425131.
[8] Qian, Y., Qin, Y., Wei, H., Lu, Y., Huang, Y., Liu, P. and Fan, Y., 2024. MFNet: Multi-scale feature enhancement networks for wheat head detection and counting in complex scene. Computers and Electronics in Agriculture, 225, pp.109342.
[9] David, E., Ogidi, F., Smith, D., Chapman, S., De Solan, B., Guo, W., Baret, F. and Stavness, I., 2023. Global wheat head detection challenges: Winning models and application for head counting. Plant Phenomics, 5, pp.0059.
[10]Guan, S., Lin, Y., Lin, G., Su, P., Huang, S., Meng, X., Liu, P. and Yan, J., 2024. Real-time detection and counting of wheat spikes based on improved YOLOv10. Agronomy, 14(9), pp.1936.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 张天舒
This work is licensed under a Creative Commons Attribution 4.0 International License.