数字农科院2.0

ENT-YOLO: An improved lightweight YOLO for cotton organ detection in mulched drip irrigation systems in southern Xinjiang

文献类型： 外文期刊

作者： Shao, Jingcui;Zhao, Qingqing;Gong, Zhi;Guo, Xinhua;Geng, Shiyi;Li, Zhaoyang;Li, Dongwei

作者机构：

关键词： Cotton organs;YOLO;Deep learning;Object detection;Spatial distribution map

期刊名称： AGRICULTURAL WATER MANAGEMENT

ISSN： 0378-3774

年卷期： 2025 年 323 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： The quantity and spatial distribution of cotton organs reflect the plant's growth responses to soil water, fertilizer, and salinity conditions. Precise organ detection can provide a scientific basis for the regulation of water, fertilizer and salt in mulched drip irrigation. However, cotton organ detection in field environments remains challenging owing to the presence of complex occlusions and the highly variable morphology of target organs, with these difficulties being particularly pronounced in arid regions such as southern Xinjiang. To address these challenges, this study proposes ENT-YOLO, a compact yet high precision detection model built upon the YOLOv11n. First, the CSP-EDLAN module is introduced to replace the original C3k2 structure, effectively reducing model parameters. Second, CIoU loss is integrated with NWD loss to enhance bounding box regression accuracy. Finally, a TADDH detection head is incorporated to enhance feature representation and localization robustness for organs exhibiting variable morphology and blurred texture. Experimental results on the self-constructed cotton organ detection dataset (COD-DS) show that ENT-YOLO achieves 76.36 % precision, 73.44 % recall, and 79.77 % mAP@0.5, with only 8.4 GFLOPs and 2.10 M parameters. The AP for the bud-flower class and the boll class increases by 3.13 % and 1.17 %, respectively, compared with the baseline model. The overall model size is merely 4.2 MB, representing a 19.2 % reduction relative to YOLOv11n. In comparison with mainstream detectors, ENT-YOLO demonstrates an improved balance between accuracy and compactness. Moreover, the spatial distribution map of the target organs is constructed using ENT-YOLO detection outputs, it lays a methodological foundation for the subsequent quantitative analysis of the spatial distribution and quantity of key organs such as buds, flowers and bolls. The results provide useful references for cotton growth stage determination and irrigation management.

分类号：

  • 相关文献

[1]Ag-YOLO: A Real-Time Low-Cost Detector for Precise Spraying With Case Study of Palms. Zhenwang Qin,Wensheng Wang,Karl Heinz Dammer,Leifeng Guo,Zhen Cao. 2021

[2]Convolutional Neural Network for Object Detection in Garlic Root Cutting Equipment. Yang, Ke,Peng, Baoliang,Gu, Fengwei,Zhang, Yanhua,Wang, Shenying,Yu, Zhaoyang,Hu, Zhichao. 2022

[3]Ag-YOLO: A Real-Time Low-Cost Detector for Precise Spraying With Case Study of Palms. Zhenwang Qin,Wensheng Wang,Karl Heinz Dammer,Leifeng Guo,Zhen Cao. 2022

[4]Experimental Study of Garlic Root Cutting Based on Deep Learning Application in Food Primary Processing. Yang K.,Yu Z.,Gu F.,Zhang Y.,Wang S.,Peng B.,Hu Z.. 2022

[5]Mapping Maize Planting Densities Using Unmanned Aerial Vehicles, Multispectral Remote Sensing, and Deep Learning Technology. Jianing Shen,Qilei Wang,Meng Zhao,Jingyu Hu,Jian Wang,Meiyan Shu,Yang Liu,Wei Guo,Hongbo Qiao,Qinglin Niu,Jibo Yue. 2024

[6]A Lightweight and Rapid Dragon Fruit Detection Method for Harvesting Robots. Fei Yuan,Jinpeng Wang,Wenqin Ding,Song Mei,Chenzhe Fang,Sunan Chen,Hongping Zhou. 2025

[7]MRUNet: A two-stage segmentation model for small insect targets in complex environments. Fu kuan WANG,Yi qi HUANG,Zhao cheng HUANG,Hao SHEN,Cong HUANG,Xi QIAO,Wan qiang QIAN. 2023

[8]Real-Time Object Detection Based on UAV Remote Sensing: A Systematic Literature Review. Zhen Cao,Lammert Kooistra,Wensheng Wang,Leifeng Guo,João Valente. 2023

[9]Automatic detection and counting of planthoppers on white flat plate images captured by AR glasses for planthopper field survey. Haiyuan Sheng,Qing Yao,Ju Luo,Yongjian Liu,Xiangfu Chen,Zhongru Ye,Tiezhuang Zhao,Heping Ling,Jian Tang,Shuhua Liu. 2024

[10]YOLOv5DA: An Improved YOLOv5 Model for Posture Detection of Grouped Pigs. Wenhui Shi,Xiaopin Wang,Xuan Li,Yuhua Fu,Xiaolei Liu,Haiyan Wang. 2025

[11]Design and implementation of a seed potato cutting robot using deep learning and delta robotic system with accuracy and speed for automated processing of agricultural products. Jie Huang,Fangxuan Yi,Yingjun Cui,Xiangyou Wang,Chengqian Jin,Fernando Auat Cheein. 2025

[12]Study on Cherry Blossom Detection and Pollination Parameter Optimization Using the SMD-YOLO Model. Ren, Longlong,Du, Yonghui,Li, Yuqiang,Gao, Ang,Ma, Wei,Song, Yuepeng,Han, Xingchang. 2025

[13]Mapping grapevine leafroll disease epidemics from UAV images. Yixue Liu,Jinya Su,Dizhu Liu,Yuyang Song,Yulin Fang,Baofeng Su,Peng Yang. 2025

[14]基于YOLOv8网络的棉蚜图像识别算法及软件系统设计. 马盼,杨子恒,万虎,何顺,黄远,徐胜勇. 2023

[15]基于机器视觉的蚕豆荚高精度检测方法研究. 夏子林,张新洲,王文波,夏先飞,陈兰,顾寄南. 2025

[16]基于知识蒸馏的多教师棉田杂草检测模型. 朱养鑫,郝珊珊,郑伟健,金诚谦,印祥,周鹏. 2025

[17]基于YOLO与扩散模型的冠层环境灰茶尺蠖幼虫检测方法. 罗学论,Mostafa GOUDA,宋馨蓓,胡妍,张文凯,何勇,张瑾,李晓丽. 2025

[18]基于无人机视频流的小麦穗数精准监测研究. 韩桐鹤,张博涵,费帅鹏,李雷,孙海艳,王多霞,孟亚雄,肖永贵. 2025

[19]基于YOLOv8网络的棉蚜图像识别算法及软件系统设计. 马盼,杨子恒,万虎,何顺,黄远,徐胜勇. 2024

[20]PAB-Mamba-YOLO: VSSM assists in YOLO for aggressive behavior detection among weaned piglets. Xue Xia,Ning Zhang,Zhibin Guan,Xin Chai,Shixin Ma,Xiujuan Chai,Tan Sun. 2025

作者其他论文 更多>>