In current practice, broccoli heads are selectively harvested by hand. The goal of our work is to develop a robot that can selectively harvest broccoli heads, thereby reducing labor costs. An essential element of such a robot is an image-processing algorithm that can detect broccoli heads. In this study, we developed a deep learning algorithm for this purpose, using the Mask Region-based Convolutional Neural Network. To be applied on a robot, the algorithm must detect broccoli heads from any cultivar, meaning that it can generalize on the broccoli images. We hypothesized that our algorithm can be generalized through network simplification and data augmentation. We found that network simplification decreased the generalization performance, whereas data augmentation increased the generalization performance. In data augmentation, the geometric transformations (rotation, cropping, and scaling) led to a better image generalization than the photometric transformations (light, color, and texture). Furthermore, the algorithm was generalized on a broccoli cultivar when 5% of the training images were images of that cultivar. Our algorithm detected 229 of the 232 harvestable broccoli heads from three cultivars. We also tested our algorithm on an online broccoli data set, which our algorithm was not previously trained on. On this data set, our algorithm detected 175 of the 176 harvestable broccoli heads, proving that the algorithm was successfully generalized. Finally, we performed a cost-benefit analysis for a robot equipped with our algorithm. We concluded that the robot was more profitable than the human harvest and that our algorithm provided a sufficient basis for robot commercialization.

中文翻译：

---

数据增强和网络简化对使用 Mask R-CNN 基于图像的西兰花头部检测的影响

在目前的实践中，西兰花头是手工选择性收获的。我们工作的目标是开发一种可以选择性收获西兰花头的机器人，从而降低人工成本。这种机器人的一个基本要素是一种可以检测西兰花头部的图像处理算法。在这项研究中，我们为此目的开发了一种深度学习算法，使用基于掩码区域的卷积神经网络。要应用于机器人，该算法必须从任何品种中检测西兰花头，这意味着它可以泛化西兰花图像。我们假设我们的算法可以通过网络简化和数据增强来推广。我们发现网络简化降低了泛化性能，而数据增强提高了泛化性能。在数据增强中，几何变换（旋转、裁剪和缩放）导致比光度变换（光、颜色和纹理）更好的图像泛化。此外，当 5% 的训练图像是该品种的图像时，该算法在西兰花品种上推广。我们的算法从三个栽培品种中检测到 232 个可收获的西兰花头中的 229 个。我们还在一个在线西兰花数据集上测试了我们的算法，我们的算法之前没有接受过训练。在该数据集上，我们的算法检测到 176 个可收获的西兰花头中的 175 个，证明该算法已成功推广。最后，我们对配备我们算法的机器人进行了成本效益分析。