School of Information and Computer, Anhui Agricultural University, Hefei 230036, China.
Anhui Provincial Engineering Laboratory for Beidou Precision Agriculture Information, Anhui Agricultural University, Hefei 230036, China.
Sensors (Basel). 2021 Oct 14;21(20):6826. doi: 10.3390/s21206826.
The extraction of wheat lodging is of great significance to post-disaster agricultural production management, disaster assessment and insurance subsidies. At present, the recognition of lodging wheat in the actual complex field environment still has low accuracy and poor real-time performance. To overcome this gap, first, four-channel fusion images, including RGB and DSM (digital surface model), as well as RGB and ExG (excess green), were constructed based on the RGB image acquired from unmanned aerial vehicle (UAV). Second, a Mobile U-Net model that combined a lightweight neural network with a depthwise separable convolution and U-Net model was proposed. Finally, three data sets (RGB, RGB + DSM and RGB + ExG) were used to train, verify, test and evaluate the proposed model. The results of the experiment showed that the overall accuracy of lodging recognition based on RGB + DSM reached 88.99%, which is 11.8% higher than that of original RGB and 6.2% higher than that of RGB + ExG. In addition, our proposed model was superior to typical deep learning frameworks in terms of model parameters, processing speed and segmentation accuracy. The optimized Mobile U-Net model reached 9.49 million parameters, which was 27.3% and 33.3% faster than the FCN and U-Net models, respectively. Furthermore, for RGB + DSM wheat lodging extraction, the overall accuracy of Mobile U-Net was improved by 24.3% and 15.3% compared with FCN and U-Net, respectively. Therefore, the Mobile U-Net model using RGB + DSM could extract wheat lodging with higher accuracy, fewer parameters and stronger robustness.
从倒伏小麦中提取信息对于灾后农业生产管理、灾害评估和保险补贴具有重要意义。目前，实际复杂田间环境下倒伏小麦的识别仍存在准确率低、实时性差的问题。为了克服这一差距，首先，基于无人机获取的 RGB 图像构建了包括 RGB 和 DSM（数字表面模型）以及 RGB 和 ExG（过量绿色）在内的四通道融合图像。其次，提出了一种结合轻量级神经网络和深度可分离卷积与 U-Net 模型的 Mobile U-Net 模型。最后，使用三个数据集（RGB、RGB + DSM 和 RGB + ExG）对所提出的模型进行训练、验证、测试和评估。实验结果表明，基于 RGB + DSM 的倒伏识别整体准确率达到 88.99%，比原始 RGB 高 11.8%，比 RGB + ExG 高 6.2%。此外，与典型的深度学习框架相比，所提出的模型在模型参数、处理速度和分割精度方面具有优势。优化后的 Mobile U-Net 模型的参数达到 949 万，分别比 FCN 和 U-Net 模型快 27.3%和 33.3%。此外，对于 RGB + DSM 的小麦倒伏提取，Mobile U-Net 的整体准确率分别比 FCN 和 U-Net 提高了 24.3%和 15.3%。因此，使用 RGB + DSM 的 Mobile U-Net 模型可以以更高的精度、更少的参数和更强的鲁棒性提取小麦倒伏信息。
