Information and Communication Engineering, Inner Mongolia University, Inner Mongolia Autonomous Region, China.
State Key Laboratory of Grassland Livestock Reproduction Regulation and Breeding, Inner Mongolia Autonomous Region, China.
PLoS One. 2022 Jun 10;17(6):e0259783. doi: 10.1371/journal.pone.0259783. eCollection 2022.
Automatically identifying the forage is the basis of intelligent fine breeding of cattle and sheep. In specific, it is a key step to study the relationship between the type and quantity of forage collected by cattle and sheep and their own growth, cashmere fineness, milk quality, meat quality and flavor, and so on. However, traditional method mainly rely on manual observation, which is time-consuming, laborious and inaccurate, and affects the normal grazing behavior of livestock. In this paper, the optimized Convolution Neural Network(CNN): edge autoencoder network(E-A-Net) algorithm is proposed to accurately identify the forage species, which provides the basis for ecological workers to carry out grassland evaluation, grassland management and precision feeding. We constructed the first forage grass dataset about Etuoke Banner. This dataset contains 3889 images in 22 categories. In the data preprocessing stage, the random cutout data enhancement is adopted to balance the original data, and the background is removed by employing threshold value-based image segmentation operation, in which the accuracy of herbage recognition in complex background is significantly improved. Moreover, in order to avoid the phenomenon of richer edge information disappearing in the process of multiple convolutions, a Sobel operator is utilized in this E-A-Net to extract the edge information of forage grasses. Information is integrated with the features extracted from the backbone network in multi-scale. Additionally, to avoid the localization of the whole information during the convolution process or alleviate the problem of the whole information disappearance, the pre-training autoencoder network is added to form a hard attention mechanism, which fuses the abstracted overall features of forage grasses with the features extracted from the backbone CNN. Compared with the basic CNN, E-A-Net alleviates the problem of edge information disappearing and overall feature disappearing with the deepening of network depth. Numerical simulations show that, compared with the benchmark VGG16, ResNet50 and EfficientNetB0, the f1 - score of the proposed method is improved by 1.6%, 2.8% and 3.7% respectively.
自动识别饲料是牛羊智能精细养殖的基础。具体来说，它是研究牛羊采集的饲料种类和数量与其自身生长、羊绒细度、奶质、肉质和风味等之间关系的关键步骤。然而，传统方法主要依赖于人工观察，既费时费力，又不准确，还会影响牲畜的正常放牧行为。在本文中，我们提出了一种优化的卷积神经网络（CNN）：边缘自动编码器网络（E-A-Net）算法，以准确识别饲料种类，为生态工作者开展草地评价、草地管理和精准饲养提供依据。我们构建了第一个额尔古纳旗饲料草数据集。该数据集包含 22 个类别的 3889 张图像。在数据预处理阶段，采用随机裁剪数据增强来平衡原始数据，并通过基于阈值的图像分割操作去除背景，显著提高了复杂背景下的牧草识别精度。此外，为避免在多次卷积过程中边缘信息丰富的消失现象，在 E-A-Net 中利用 Sobel 算子提取饲料草的边缘信息。在多尺度下，将边缘信息与骨干网络提取的特征进行融合。此外，为避免卷积过程中整体信息的定位或减轻整体信息消失的问题，添加预训练自动编码器网络形成硬注意力机制，将提取的饲料草整体特征与骨干 CNN 提取的特征进行融合。与基本 CNN 相比，E-A-Net 缓解了随着网络深度的增加边缘信息和整体特征消失的问题。数值模拟表明，与基准 VGG16、ResNet50 和 EfficientNetB0 相比，所提方法的 f1 -score 分别提高了 1.6%、2.8%和 3.7%。
