Authors

Abstract

To realize the automatic driving of agricultural machinery in the greenhouse, this paper uses image acquisition equipment to collect road images in the greenhouse and makes data sets, builds SETR (SEgmentation TRansformer) model based on Transformer framework and DeepLabv3+ model based on convolution neural network for semantic segmentation of road images in the greenhouse, and verifies the semantic segmentation ability of the two models to road images in the greenhouse. Several groups of training periods are set as observation points to observe the semantic segmentation effect of the two models on the greenhouse road image, and the test set which has not been trained by the model is used as the prediction object to verify the performance of the two models on the semantic segmentation of greenhouse road image. The SETR model reached 94.64% PA (Pixel Accuracy) on the greenhouse road data set, and 82.72% mIoU (Mean Intersection over Union), DeepLabv3+ model reached 90.80% PA and 72.35% mIoU on the greenhouse road data set. Both models have excellent performance in semantic segmentation of greenhouse road images, and the performance of SETR model is slightly better than that of DeepLabv3+ model. The semantic segmentation performance of the two models for greenhouse road images can meet the needs of actual deployment.

Abstract in Chinese

为实现农业机械在温室大棚中的自动驾驶，本文使用图像采集设备采集温室大棚中道路图像并制作了数据集，搭建基于Transformer框架的SETR模型与基于卷积神经网络的DeepLabv3+模型对温室大棚中道路图像进行语义分割，验证两种模型对温室大棚中道路图像语义分割能力。设置了多组训练周期作为观测点，观测两种模型对温室大棚道路图像的语义分割效果，以未投入过模型训练的测试集作为预测对象，验证两种模型对温室大棚道路图像语义分割的性能。SETR模型在温室大棚道路数据集上达到了94.64%的PA、82.72%的mIoU,DeepLabv3+模型在温室大棚道路数据集上达到了90.80%的PA、72.35%的mIoU，两种模型在对温室大棚道路图像的语义分割上均有优异表现，SETR模型的性能略高于DeepLabv3+模型，两种模型对温室大棚道路图像的语义分割性能均满足在实际部署的需求。