Shandong Provincial University Laboratory for Protected Horticulture, Weifang University of Science and Technology, Weifang, China.
BMC Plant Biol. 2024 Aug 2;24(1):738. doi: 10.1186/s12870-024-05346-4.
Automated detection and identification of vegetable diseases can enhance vegetable quality and increase profits. Images of greenhouse-grown vegetable diseases often feature complex backgrounds, a diverse array of diseases, and subtle symptomatic differences. Previous studies have grappled with accurately pinpointing lesion positions and quantifying infection degrees, resulting in overall low recognition rates. To tackle the challenges posed by insufficient validation datasets and low detection and recognition rates, this study capitalizes on the geographical advantage of Shouguang, renowned as the "Vegetable Town," to establish a self-built vegetable base for data collection and validation experiments. Concentrating on a broad spectrum of fruit and vegetable crops afflicted with various diseases, we conducted on-site collection of greenhouse disease images, compiled a large-scale dataset, and introduced the Space-Time Fusion Attention Network (STFAN). STFAN integrates multi-source information on vegetable disease occurrences, bolstering the model's resilience. Additionally, we proposed the Multilayer Encoder-Decoder Feature Fusion Network (MEDFFN) to counteract feature disappearance in deep convolutional blocks, complemented by the Boundary Structure Loss function to guide the model in acquiring more detailed and accurate boundary information. By devising a detection and recognition model that extracts high-resolution feature representations from multiple sources, precise disease detection and identification were achieved. This study offers technical backing for the holistic prevention and control of vegetable diseases, thereby advancing smart agriculture. Results indicate that, on our self-built VDGE dataset, compared to YOLOv7-tiny, YOLOv8n, and YOLOv9, the proposed model (Multisource Information Fusion Method for Vegetable Disease Detection, MIFV) has improved mAP by 3.43%, 3.02%, and 2.15%, respectively, showcasing significant performance advantages. The MIFV model parameters stand at 39.07 M, with a computational complexity of 108.92 GFLOPS, highlighting outstanding real-time performance and detection accuracy compared to mainstream algorithms. This research suggests that the proposed MIFV model can swiftly and accurately detect and identify vegetable diseases in greenhouse environments at a reduced cost.
蔬菜病害的自动检测与识别可以提高蔬菜质量，增加利润。温室种植的蔬菜病害图像通常具有复杂的背景、多样的病害和细微的症状差异。以前的研究在准确确定病变位置和量化感染程度方面遇到了困难，导致整体识别率较低。为了解决验证数据集不足和检测识别率低的挑战，本研究利用寿光作为“蔬菜之乡”的地理优势，建立了一个自建的蔬菜基地，用于数据收集和验证实验。本研究集中于广泛的水果和蔬菜作物，这些作物受到各种疾病的影响，进行了温室病害图像的现场采集，编制了一个大型数据集，并引入了时空融合注意网络（STFAN）。STFAN 集成了蔬菜病害发生的多源信息，增强了模型的弹性。此外，我们提出了多层编解码器特征融合网络（MEDFFN）来克服深度卷积块中的特征消失问题，并辅以边界结构损失函数来指导模型获取更详细和准确的边界信息。通过设计一个从多个来源提取高分辨率特征表示的检测识别模型，实现了精确的病害检测和识别。本研究为蔬菜病害的整体防治提供了技术支持，从而推进了智慧农业的发展。结果表明，在我们自建的 VDGE 数据集上，与 YOLOv7-tiny、YOLOv8n 和 YOLOv9 相比，所提出的模型（蔬菜病害检测的多源信息融合方法，MIFV）的 mAP 分别提高了 3.43%、3.02%和 2.15%，表现出显著的性能优势。MIFV 模型的参数为 39.07 M，计算复杂度为 108.92 GFLOPS，与主流算法相比，具有出色的实时性能和检测精度。这项研究表明，所提出的 MIFV 模型可以快速准确地检测和识别温室环境中的蔬菜病害，成本较低。
