Semantic segmentation-based unstructured field road scene recognition method and device

Abstract

The invention discloses an unstructured field road scene recognition method and device based on semantic segmentation, and the method comprises the steps: obtaining an unstructured field road scene image construction data set, and carrying out the semantic annotation of the image data set; performing data amplification and division on the labeled data set; the method comprises the following steps: constructing a semantic segmentation model, fusing mixed expansion convolution into a MobilenetV2 feature extraction network, introducing a channel attention module to recalibrate feature channels in each stage of the feature extraction network, and designing a spatial pyramid pooling module to calculate multi-scale hierarchical features and splice the multi-scale hierarchical features with input features; initializing parameters of the feature extraction network for pre-training, adding the trained feature extraction network into a spatial pyramid pooling module and a pixel prediction network, deploying the feature extraction network on a training set and training the feature extraction network by adopting a stochastic gradient descent method; and after training is completed, inputting a to-be-recognized image into the semantic segmentation model to obtain a segmentation result. The method has a good segmentation effect and can realize balance between precision and speed.

Description

technical field [0001] The invention relates to the field of agricultural field road scene recognition, in particular to a semantic segmentation-based unstructured field road scene recognition method and device. Background technique [0002] The intelligent agricultural equipment system can complete agricultural tasks independently, efficiently and safely, and has good operation accuracy and efficiency. Environmental information perception is one of the key technologies of the intelligent agricultural equipment system, which determines the autonomous navigation ability and operation level of agricultural equipment. The machine vision system has the characteristics of wide detection range and rich information acquisition. It is one of the main sensing devices used by intelligent agricultural equipment for field information acquisition. Vision-based agricultural field road scene recognition and analysis is an important component of environmental information perception. The ma...

AI Technical Summary

Problems solved by technology

The semantic segmentation model based on the deep convolutional neural network can realize semantic pixel prediction and classification, and has a good segmentation effect, but it also has many weight parameters, high computational complexity, and slow reasoning speed. At the same time, it does not fully consider the image context information. The utilization rate of global features is low, resulting in low segmentation accuracy of complex scenes

Images