Zhang Wenli, Liu Yuxin, Wang Chenhuizi, Zheng Chao, Cui Guoqiang, Guo Wei
Information Department, Beijing University of Technology, Beijing 100022, China.
Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo 188-0002, Japan.
Hortic Res. 2024 Jan 10;11(3):uhae007. doi: 10.1093/hr/uhae007. eCollection 2024 Mar.
Traditional agriculture is gradually being combined with artificial intelligence technology. High-performance fruit detection technology is an important basic technology in the practical application of modern smart orchards and has great application value. At this stage, fruit detection models need to rely on a large number of labeled datasets to support the training and learning of detection models, resulting in higher manual labeling costs. Our previous work uses a generative adversarial network to translate the source domain to the target fruit images. Thus, automatic labeling is performed on the actual dataset in the target domain. However, the method still does not achieve satisfactory results for translating fruits with significant shape variance. Therefore, this study proposes an improved fruit automatic labeling method, EasyDAM_V4, which introduces the Across-CycleGAN fruit translation model to achieve spanning translation between phenotypic features such as fruit shape, texture, and color to reduce domain differences effectively. We validated the proposed method using pear fruit as the source domain and three fruits with large phenotypic differences, namely pitaya, eggplant, and cucumber, as the target domain. The results show that the EasyDAM_V4 method achieves substantial cross-fruit shape translation, and the average accuracy of labeling reached 87.8, 87.0, and 80.7% for the three types of target domain datasets, respectively. Therefore, this research method can improve the applicability of the automatic labeling process even if significant shape variance exists between the source and target domain.
传统农业正逐渐与人工智能技术相结合。高性能水果检测技术是现代智能果园实际应用中的一项重要基础技术，具有很大的应用价值。现阶段，水果检测模型需要依赖大量带标签的数据集来支持检测模型的训练和学习，导致人工标注成本较高。我们之前的工作使用生成对抗网络将源域图像转换为目标水果图像，从而在目标域的实际数据集中进行自动标注。然而，对于形状差异较大的水果转换，该方法仍未取得令人满意的结果。因此，本研究提出了一种改进的水果自动标注方法EasyDAM_V4，它引入了跨周期生成对抗网络（Across-CycleGAN）水果转换模型，以实现水果形状、纹理和颜色等表型特征之间的跨度转换，从而有效减少域差异。我们以梨果为源域，以火龙果、茄子和黄瓜这三种表型差异较大的水果为目标域，对所提出的方法进行了验证。结果表明，EasyDAM_V4方法实现了显著的跨水果形状转换，对于三种目标域数据集，标注的平均准确率分别达到了87.8%、87.0%和80.7%。因此，即使源域和目标域之间存在显著的形状差异，本研究方法也能提高自动标注过程的适用性。
