Fruit detection and segmentation will be essential for future agronomic management, with applications in yield estimation, growth monitoring, intelligent picking, disease detection and etc. In order to more accurately and efficiently realize the recognition and segmentation of apples in natural orchards, a robust segmentation net framework specially developed for fruit production is proposed. This model was improved for the more challenging problem which segments the overlapped apples from the monochromatic background regardless of various corruptions. The method extends Mask R-CNN by embedding an attention mechanism for focusing more on the informative pixels but also suppressing the noise caused by adverse factors (occlusions, overlaps, etc.), which could be more suitable and robust for operating in complex natural environment. Specifically, the Gaussian non-local attention mechanism is transplanted into Mask R-CNN for refining the semantic features generated continuously by residual network and feature pyramid network, then the model forward processing based on the balanced feature levels and finally segments the regions where the apples are located. Experimental results verify the hypothesis of current work and show that the proposed method outperforms other start-of-the-art detection and segmentation models, the AP box and AP mask metric values have reached 85.6% and 86.2% in a reasonable run time, respectively, which can meet the precision and robustness of vision system in agronomic management.

果实检测与分割对于未来农艺管理至关重要，可应用于产量估算、生长监测、智能采摘、病害检测等。提出了专门为水果生产开发的net框架。该模型针对更具挑战性的问题进行了改进，该问题从单色背景中分割出重叠的苹果，而不考虑各种损坏。该方法通过嵌入一种注意力机制来扩展 Mask R-CNN，以更多地关注信息像素，同时抑制不利因素（遮挡、重叠等）引起的噪声，这可能更适合在复杂的自然环境中运行，并且具有鲁棒性. 具体来说，将高斯非局部注意力机制移植到Mask R-CNN中，对残差网络和特征金字塔网络不断产生的语义特征进行细化，然后基于平衡的特征水平进行模型前向处理，最后对苹果所在的区域进行分割. 实验结果验证了当前工作的假设，并表明所提出的方法优于其他最先进的检测和分割模型，在合理的运行时间内，AP box 和 AP mask 度量值分别达到了 85.6% 和 86.2% ，可满足视觉系统在农艺管理中的精度和鲁棒性。然后模型基于平衡的特征水平进行前向处理，最后对苹果所在的区域进行分割。实验结果验证了当前工作的假设，并表明所提出的方法优于其他最先进的检测和分割模型，在合理的运行时间内，AP box 和 AP mask 度量值分别达到了 85.6% 和 86.2% ，可满足视觉系统在农艺管理中的精度和鲁棒性。然后模型基于平衡的特征水平进行前向处理，最后对苹果所在的区域进行分割。实验结果验证了当前工作的假设，并表明所提出的方法优于其他最先进的检测和分割模型，在合理的运行时间内，AP box 和 AP mask 度量值分别达到了 85.6% 和 86.2% ，可满足视觉系统在农艺管理中的精度和鲁棒性。