Deep convolutional neutral network and superpixel-based image semantic segmentation method

Abstract

The invention discloses a deep convolutional neutral network and superpixel-based image semantic segmentation method, which overcomes the problem that the precision of an existing semantic segmentation method still needs to be improved in the prior art. The method comprises the following steps of 1, training a deep convolutional neutral network classification model from images to category labels on an image classification data set; 2, adding a deconvolutional layer to the deep convolutional neutral network classification model, performing fine adjustment training on an image semantic segmentation data set, and realizing mapping from images to image semantic segmentation results; 3, inputting test images to a deep convolutional neutral network semantic segmentation model to obtain semantic labels of pixels, and inputting the test images to a superpixel segmentation algorithm to obtain a plurality of superpixel regions; and 4, fusing superpixels and the semantic labels to obtain a final improved semantic segmentation result. The method improves the precision of the existing semantic segmentation method and is of important significance in image identification and application.

Description

technical field [0001] The invention relates to an image semantic segmentation method, in particular to an image semantic segmentation method based on a deep convolutional neural network and superpixels. Background technique [0002] With the continuous decline in the classification error rate of convolutional neural networks on public data sets, researchers began to pay attention to image pixel-level segmentation, that is, image semantic segmentation. Semantic feature is a higher-level feature that marks each pixel in the image as a corresponding category. The general method is to realize semantic segmentation by discriminating image regions. Carreira et al., Farabet et al., Girshick et al. divided the image into several regions by means of superpixels, and extracted regional features through a deep convolutional neural network to classify them to achieve semantic segmentation of the entire image. In 2015, Long et al. proposed an end-to-end semantic segmentation model base...

AI Technical Summary

Problems solved by technology

[0004] The present invention overcomes the problem that the accuracy of the existing semantic segmentation method still needs to be improved in the prior art, and provides an image semantic segmentation method based on a deep convolutional neural network and superpixels with better use effect

Images