Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China.
Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo 188-0002, Japan.
Sensors (Basel). 2022 Aug 23;22(17):6325. doi: 10.3390/s22176325.
Deep learning is widely used in modern orchard production for various inspection missions, which helps improve the efficiency of orchard operations. In the mission of visual detection during fruit picking, most current lightweight detection models are not yet effective enough to detect multi-type occlusion targets, severely affecting automated fruit-picking efficiency. This study addresses this problem by proposing the pioneering design of a multi-type occlusion apple dataset and an augmentation method of data balance. We divided apple occlusion into eight types and used the proposed method to balance the number of annotation boxes for multi-type occlusion apple targets. Finally, a validation experiment was carried out using five popular lightweight object detection models: yolox-s, yolov5-s, yolov4-s, yolov3-tiny, and efficidentdet-d0. The results show that, using the proposed augmentation method, the average detection precision of the five popular lightweight object detection models improved significantly. Specifically, the precision increased from 0.894 to 0.974, recall increased from 0.845 to 0.972, and mAP0.5 increased from 0.982 to 0.919 for yolox-s. This implies that the proposed augmentation method shows great potential for different fruit detection missions in future orchard applications.
深度学习在现代果园生产中被广泛应用于各种检测任务，有助于提高果园作业的效率。在采摘过程中的视觉检测任务中，大多数现有的轻量级检测模型在检测多类型遮挡目标方面还不够有效，严重影响了自动化采摘的效率。本研究通过提出一种多类型苹果遮挡数据集的开创性设计和数据平衡增强方法来解决这个问题。我们将苹果遮挡分为八类，并使用所提出的方法来平衡多类型苹果遮挡目标的标注框数量。最后，使用五个流行的轻量级目标检测模型（yolox-s、yolov5-s、yolov4-s、yolov3-tiny 和 efficientdet-d0）进行了验证实验。结果表明，使用所提出的增强方法，五个流行的轻量级目标检测模型的平均检测精度显著提高。具体来说，对于 yolox-s，精度从 0.894 提高到 0.974，召回率从 0.845 提高到 0.972，mAP0.5 从 0.982 提高到 0.919。这表明所提出的增强方法在未来果园应用中对不同的水果检测任务具有很大的潜力。
