A road scene semantic segmentation method based on a convolution neural network

Abstract

The invention discloses a road scene semantic segmentation method based on a convolution neural network. In a training stage, a convolution neural network is constructed. The hidden layer comprises five neural network blocks, five transition convolution layers, five skip deconvolution blocks and four cascade layers. The original road scene images are inputted into the convolution neural network for training, and 12 corresponding semantic segmentation prediction maps are obtained. Secondly, by calculating the loss function value between the set of 12 semantic segmentation prediction images corresponding to the original road scene images and the set of 12 heat-coded images corresponding to the real semantic segmentation images, the optimal weight vector and bias term of the classification training model of the convolution neural network are obtained. In the testing phase, the road scene images to be semantically segmented are inputted into the convolution neural network classification training model to obtain the predictive semantic segmentation images. The invention has the advantages of improving the efficiency and accuracy of the semantic segmentation of the road scene images.

Description

technical field [0001] The invention relates to a deep learning semantic segmentation method, in particular to a convolutional neural network-based semantic segmentation method for road scenes. Background technique [0002] The rise of the intelligent transportation industry has led to more and more applications of semantic segmentation in intelligent transportation systems. From traffic scene understanding and multi-target obstacle detection to visual navigation, semantic segmentation technology can be used to achieve. Currently, the most commonly used semantic segmentation methods include algorithms such as support vector machines and random forests. These algorithms mainly focus on binary classification tasks to detect and recognize specific objects such as road surfaces, vehicles, and pedestrians. These traditional machine learning methods often need to be implemented through high-complexity features, but it is simple and convenient to use deep learning to semantically ...

AI Technical Summary

Problems solved by technology

[0004] Most of the existing road scene semantic segmentation methods use deep learning methods. There are many models that combine convolutional layers and pooling layers. However, the feature maps obtained by purely using pooling operations and convolution operations are single and not representative. , which will lead to the reduction of the feature information of the obtained image, which will eventually lead to rough restoration of the effect information and low segmentation accuracy.

Images