Wu Yunlong, Yuan Shouqi, Tang Lingdi
Research Center of Fluid Machinery Engineering and Technology, Jiangsu University, Zhenjiang, 212013, China.
Data and Informatization Department, Jiangsu University, Zhenjiang, 212013, China.
Plant Methods. 2025 May 14;21(1):60. doi: 10.1186/s13007-025-01382-9.
The real-time monitoring and counting of maize seed germination at seedling stage is of great significance for seed quality detection, field management and yield estimation. Traditional manual monitoring and counting is very time-consuming, cumbersome and error-prone. In order to quickly and accurately identify and count maize seedlings in a complex field environment, this study proposes an end-to-end maize seedling plant detection model H-RT-DETR (Hierarchical-Real-Time DEtection TRansformer) based on hierarchical feature extraction and RT-DETR (Real-Time DEtection TRansformer). H-RT-DETR uses Hierarchical Feature Representation and Efficient Self-Attention as the backbone network for feature extraction, thereby improving the network's ability to extract features of maize seedling stage in UAV remote sensing images. Through experiments on the UAV remote sensing data set of maize seedling stage, the mean Average Precision mAP0.5-0.95, mAP0.5 and mAP0.75 of the improved H-RT-DETR model reached 51.2%, 94.7% and 48.1%, respectively, and the Average Recall (AR) reached 68.5%. In order to verify the efficiency of the proposed method, H-RT-DETR is compared with the widely used and advanced target recognition methods. The results show that the detection accuracy of H-RT-DETR is better than that of the comparison methods. In terms of detection speed, the H-RT-DETR model does not require Non-Maximum Suppression (NMS) post-processing operations, the Frames Per Second (FPS) on the test dataset reaches 84f/s, which is 19,12,11 and 21 higher than that of YOLOv5, YOLOv7, YOLOv8 and YOLOX, respectively, under the same hardware environment. This model can provide technical support for real-time detection of maize seedlings under UAV remote sensing images in terms of both detection accuracy and speed (see https://github.com/wylSUGAR/H-RT-DETR for model implementation and results).
玉米苗期种子萌发的实时监测与计数对于种子质量检测、田间管理和产量预估具有重要意义。传统的人工监测与计数非常耗时、繁琐且容易出错。为了在复杂的田间环境中快速准确地识别和计数玉米幼苗，本研究提出了一种基于分层特征提取和RT-DETR（实时检测变压器）的端到端玉米幼苗植株检测模型H-RT-DETR（分层实时检测变压器）。H-RT-DETR使用分层特征表示和高效自注意力作为特征提取的骨干网络，从而提高了网络提取无人机遥感图像中玉米苗期特征的能力。通过对玉米苗期无人机遥感数据集进行实验，改进后的H-RT-DETR模型的平均精度均值mAP0.5-0.95、mAP0.5和mAP0.75分别达到51.2%、94.7%和48.1%，平均召回率（AR）达到68.5%。为了验证所提方法的效率，将H-RT-DETR与广泛使用的先进目标识别方法进行了比较。结果表明，H-RT-DETR的检测精度优于比较方法。在检测速度方面，H-RT-DETR模型无需非极大值抑制（NMS）后处理操作，在测试数据集上的每秒帧数（FPS）达到84f/s，在相同硬件环境下分别比YOLOv5、YOLOv7、YOLOv8和YOLOX高19、12、11和21。该模型在检测精度和速度方面都能为无人机遥感图像下玉米幼苗的实时检测提供技术支持（模型实现和结果见https://github.com/wylSUGAR/H-RT-DETR）。
