文献类型： 会议论文
第一作者： Haotian Wu
作者： Haotian Wu 1 ; Junhua Kang 1 ; Heli Li 2 ;
作者机构： 1.College of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, China
2.Key Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China
关键词： UAV;Soybean Seedling;Object Detection;YOLO;Attention Mechanism
会议名称： ISPRS TC I Mid-term Symposium "Intelligent Sensing and Remote Sensing Application"
主办单位：
页码： 727-735
摘要： The utilization of unmanned aerial vehicle (UAV) for soybean seedling detection is an effective way to estimate soybean yield, which plays a crucial role in agricultural planning and decision-making. However, the soybean seedlings objects in the UAV image are small, in clusters, and occluded each other, which makes it very challenging to achieve accurate object detection and counting. To address these issues, we optimize the YOLOv8 model and propose a GAS-YOLOv8 network, aiming to enhance the detection accuracy for the task of soybean seedling detection based on UAV images. Firstly, a global attention mechanism (GAM) is incorporated into the neck module of YOLOv8, which reallocates weights and prioritizes global information to more effectively extract soybean seedling features. Secondly, the CIOU loss function is replaced with the SIOU loss, which includes an angle loss term to guide the regression of bounding boxes. Experimental results show that, on the soybean seedling dataset, the proposed GAS-YOLOv8 model achieves a 1.3% improvement in mAP@0.5 and a 6% enhancement in detection performance in dense seedling areas, when compared to the baseline model YOLOv8s.When compared to other object detection models (YOLOv5, Faster R-CNN, etc.), the GAS-YOLOv8 model similarly achieved the best detection performance. These results demonstrate the effectiveness of the GAS-YOLOv8 in detecting dense soybean seedlings, providing more accurate theoretical support for subsequent yield estimation.
分类号： tp7-53
- 相关文献
[1]利用无人机多光谱成像监测油茶碳储量. 陈龙跃,段丹丹,张祖铭,孙鹤,高佳华,姜毅,冉成. 2024
[2]Droplets movement and deposition of an eight-rotor agricultural UAV in downwash flow field. Tang Qing,Zhang Ruirui,Chen Liping,Xu Min,Yi Tongchuan,Zhang Bin,Tang Qing,Zhang Ruirui,Chen Liping,Xu Min,Yi Tongchuan,Zhang Bin,Tang Qing,Zhang Ruirui,Chen Liping,Xu Min,Yi Tongchuan,Zhang Bin. 2017
[3]Stitching of hyper-spectral UAV images based on feature bands selection. Xia, L.,Zhang, R. R.,Chen, L. P.,Jiang, H. J.,Xia, L.,Zhang, R. R.,Chen, L. P.,Jiang, H. J.,Xia, L.,Zhang, R. R.,Chen, L. P.,Jiang, H. J.,Xia, L.,Zhang, R. R.,Chen, L. P.,Jiang, H. J.,Zhao, F.. 2016
[4]The DOM Generation and Precise Radiometric Calibration of a UAV-Mounted Miniature Snapshot Hyperspectral Imager. Yang, Guijun,Wang, Yanjie,Feng, Haikuan,Xu, Bo,Yang, Xiaodong,Yang, Guijun,Feng, Haikuan,Xu, Bo,Li, Changchun,Wang, Yanjie,Yuan, Huanhuan. 2017
[5]Unmanned Aerial Vehicle Remote Sensing for Field-Based Crop Phenotyping: Current Status and Perspectives. Yang, Guijun,Liu, Jiangang,Zhao, Chunjiang,Yu, Haiyang,Xu, Bo,Yang, Xiaodong,Feng, Haikuan,Zhao, Xiaoqing,Li, Zhenhai,Li, Heli,Yang, Hao,Yang, Guijun,Zhao, Chunjiang,Yang, Xiaodong,Li, Zhenhai,Li, Heli,Yang, Hao,Yang, Guijun,Liu, Jiangang,Zhao, Chunjiang,Yu, Haiyang,Xu, Bo,Li, Zhenhong,Huang, Yanbo,Zhu, Dongmei,Zhang, Xiaoyan,Zhang, Ruyang. 2017
[6]A Lightweight Detection Method of Smartphone Assembly Parts. Bo Zhang,Wenbai Chen,Xiaohao Wang,Chunjiang Zhao. 2022
[7]Stitching of hyper-spectral UAV images based on feature bands selection. L. Xia,R. R. Zhang,L. P. Chen,F. Zhao,H. J. Jiang. 2016
