Lu Jianbo, Liu Xiaobin, Ma Xiaoya, Tong Jin, Peng Jungui
School of Computer and Information Engineering, Nanning Normal University, Nanning, Guangxi, China.
Guangxi Key Lab of Human-machine Interaction and Intelligent Decision, Nanning Normal University, Nanning, Guangxi, China.
PeerJ Comput Sci. 2023 Sep 25;9:e1595. doi: 10.7717/peerj-cs.1595. eCollection 2023.
Using intelligent agriculture is an important way for the industry to achieve high-quality development. To improve the accuracy of the identification of crop diseases under conditions of limited computing resources, such as in mobile and edge computing, we propose an improved lightweight MobileNetV2 crop disease identification model. In this study, MobileNetV2 is used as the backbone network for the application of an improved Bottleneck structure. First, the number of operation channels is reduced using point-by-point convolution, the number of parameters of the model is reduced, and the re-parameterized multilayer perceptron (RepMLP) module is introduced; the latter can capture long-distance dependencies between features and obtain local information to enhance the global perception of the model. Second, the efficient channel-attention mechanism is added to adjust the image-feature channel weights so as to improve the recognition accuracy of the model, and the Hardswish activation function is introduced instead of the ReLU6 activation function to further improve performance. The final experimental results show that the improved MobilNetV2 model achieves 99.53% accuracy in the PlantVillage crop disease dataset, which is 0.3% higher than the original model, and the number of covariates is only 0.9M, which is 59% less than the original model. Also, the inference speed is improved by 8.5% over the original model. The crop disease identification method proposed in this article provides a reference for deployment and application on edge and mobile devices.
采用智能农业是该行业实现高质量发展的重要途径。为了在移动和边缘计算等计算资源有限的条件下提高作物病害识别的准确性，我们提出了一种改进的轻量级MobileNetV2作物病害识别模型。在本研究中，将MobileNetV2用作应用改进瓶颈结构的骨干网络。首先，使用逐点卷积减少操作通道数，降低模型参数数量，并引入重新参数化的多层感知器（RepMLP）模块；后者可以捕捉特征之间的长距离依赖关系并获取局部信息，以增强模型的全局感知能力。其次，添加高效通道注意力机制来调整图像特征通道权重，从而提高模型的识别准确率，并引入Hardswish激活函数代替ReLU6激活函数以进一步提升性能。最终实验结果表明，改进后的MobilNetV2模型在PlantVillage作物病害数据集中的准确率达到99.53%，比原模型高0.3%，协变量数量仅为0.9M，比原模型少59%。此外，推理速度比原模型提高了8.5%。本文提出的作物病害识别方法为在边缘和移动设备上的部署和应用提供了参考。
