Semantic segmentation of road scene based on multi-scale perforated convolutional neural network

Abstract

The invention discloses a road scene semantic segmentation method based on a multi-scale perforated convolutional neural network. In a training stage, a multi-scale perforated convolutional neural network is constructed. The hidden layer thereof comprises nine neural network blocks, five cascade layers and six up-sampling blocks. The original road scene images are input into the multi-scale perforated convolutional neural network for training, and 12 corresponding semantic segmentation prediction maps are obtained. By calculating the loss function value between the set of 12 semantic segmentation prediction maps corresponding to the original road scene image and the set of 12 monothermally coded images processed from the corresponding real semantic segmentation image, The optimal weight vector and bias term of multi-scale perforated convolution neural network classification training model are obtained. In the testing phase, the road scene images to be segmented are input into the multi-scale perforated convolutional neural network classification training model, and the predictive semantic segmentation images are obtained. The invention has the advantages of improving the efficiencyand 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 road scene semantic segmentation method based on a multi-scale perforated convolutional neural network. Background technique [0002] With the rapid development of the intelligent transportation industry, road scene understanding has been more and more widely used in intelligent transportation of assisted driving and unmanned driving systems. One of the most challenging tasks in autonomous driving is road scene understanding, including lane detection and semantic segmentation under computer vision tasks. Lane detection helps guide the vehicle, and semantic segmentation provides more detailed location of objects in the surrounding environment. Semantic segmentation is an important direction of computer vision. Its essence is to classify images at the pixel level. Its application in road scene understanding is to segment objects including roads, cars, pedestrians, ...

AI Technical Summary

Problems solved by technology

[0004] Most of the existing road scene semantic segmentation methods use deep learning methods, which use the combination of convolutional layers and pooling layers. As a result, the feature information of the obtained image is reduced, and eventually the restored edge information is rough and the segmentation accuracy is low.

Images