Robotic apple harvesting has received much research attention in the past few years due to growing shortage and rising cost in labor. One key enabling technology towards automated harvesting is accurate and robust apple detection, which poses great challenges as a result of the complex orchard environment that involves varying lighting conditions and foliage/branch occlusions. This letter reports on the development of a novel deep learning-based apple detection framework named Suppression Mask R-CNN. Specifically, we first collect a comprehensive apple orchard dataset for "Gala" and "Blondee" apples, using a color camera, under different lighting conditions (overcast and front lighting vs. back lighting). We then develop a novel suppression Mask R-CNN for apple detection, in which a suppression branch is added to the standard Mask R-CNN to suppress non-apple features generated by the original network. Comprehensive evaluations are performed, which show that the developed suppression Mask R-CNN network outperforms state-of-the-art models with a higher F1-score of 0.905 and a detection time of 0.25 second per frame on a standard desktop computer.

由于短缺的日益严重和人工成本的上升，机器人苹果的收获在过去的几年中受到了很多研究的关注。准确而强大的苹果检测技术是实现自动收割的一项关键技术，由于果园环境复杂，光照环境和枝叶/枝叶遮蔽力各不相同，因此带来了巨大的挑战。这封信报道了基于新型深度学习的苹果检测框架Suppression Mask R-CNN的开发。具体来说，我们首先使用彩色相机在不同的光照条件下（阴天和前灯与后灯）为“ Gala”和“ Blondee”苹果收集了一个完整的苹果园数据集。然后，我们开发了一种用于苹果检测的新型抑制Mask R-CNN，其中，将抑制分支添加到标准Mask R-CNN，以抑制原始网络生成的非Apple功能。进行了全面的评估，表明开发的抑制Mask R-CNN网络在标准台式计算机上的F1-分数更高，为0.905，每帧检测时间为0.25秒，优于最新模型。