Zhang Jun, Zhang Dongfang, Liu Jingyan, Zhou Yuhong, Cui Xiaoshuo, Fan Xiaofei
College of Mechanical and Electrical Engineering, Hebei Agricultural University, Baoding, 071000, China.
State Key Laboratory of North China Crop Improvement and Regulation, Hebei Agricultural University, Baoding, 071000, China.
Plant Methods. 2024 Dec 19;20(1):186. doi: 10.1186/s13007-024-01303-2.
Verticillium wilt greatly hampers Chinese cabbage growth, causing significant yield limitations. Rapid and accurate detection of Verticillium wilt in the Chinese cabbage (Brassica rapa L. ssp. pekinensis) can provide significant agronomic benefits. Here, we propose a detection model, DSConv-GAN, which is based on images acquired by an unmanned aerial vehicle (UAV). Based on YOLOv8, with the addition of the dynamic snake convolution (DSConv) module and the improved loss function maximum possible distance intersection-over-union (MPDIoU), we acquired enhanced complex structures and global characteristics in Chinese cabbage images under different growth conditions. To reduce the difficulty of acquiring diseased Chinese cabbage data, a cycle-consistent generative adversarial network (CycleGAN) was used to simulate and generate images of the Verticillium wilt characteristics for multiple fields. The detection of lightly infected plants achieved precision, recall, mean average precision (mAP), and F1-score of 81.3, 86.6, 87.7, and 83.9%, respectively. DSConv-GAN outperforms other models in terms of precision, detection speed, robustness, and generalization. The model is combined with software to improve the practicability of the proposed method. Our results demonstrate DSConv-GAN to be an effective intelligent farming tool that provides early, rapid, and accurate detection of Chinese cabbage Verticillium wilt in complex growing environments.
黄萎病严重阻碍大白菜生长，导致产量大幅受限。快速准确地检测大白菜（Brassica rapa L. ssp. pekinensis）中的黄萎病可带来显著的农艺效益。在此，我们提出一种基于无人机（UAV）获取图像的检测模型DSConv-GAN。基于YOLOv8，通过添加动态蛇形卷积（DSConv）模块和改进的损失函数最大可能距离交并比（MPDIoU），我们在不同生长条件下的大白菜图像中获得了增强的复杂结构和全局特征。为降低获取患病大白菜数据的难度，使用循环一致生成对抗网络（CycleGAN）来模拟并生成多个田间黄萎病特征的图像。对轻度感染植株的检测精度、召回率、平均精度均值（mAP）和F1分数分别达到81.3%、86.6%、87.7%和83.9%。DSConv-GAN在精度、检测速度、鲁棒性和泛化能力方面优于其他模型。该模型与软件相结合以提高所提方法的实用性。我们的结果表明DSConv-GAN是一种有效的智能农业工具，可在复杂生长环境中对大白菜黄萎病进行早期、快速且准确的检测。
