Semantic image segmentation method based on multichannel convolutional neural network

Abstract

The invention provides a semantic image segmentation method based on a multichannel convolutional neural network. A provided network model comprises 6 channels; fusion of shallow and deep features isrealized through addition operation of outputs of the channels; and compared with a single-channel network, the structure can improve segmentation performance of semantic images. The whole network model structure improves a receptive field by combining an a'trous algorithm, so that the captured global information is allowed to be richer; and in the test phase, the segmentation result is subjectedto optimization through a full connection condition random field, so that the segmentation performance of the semantic images can be further improved.

Description

technical field [0001] The invention belongs to the field of pattern recognition, and in particular relates to a semantic image segmentation method based on a multi-channel convolutional neural network. Background technique [0002] Image segmentation is an important research direction in machine vision. It is the process of dividing a digital image into multiple areas of interest. Objects in the same area have the same or similar properties. The purpose of segmentation is to enable the image to Better to express its meaning and easy to analyze, the segmented results can be used in image retrieval, object detection, automatic driving and other fields. Traditional image segmentation methods include histogram method, region segmentation, edge segmentation and so on. A common practice is that, for a given image, take an area centered on a certain pixel in the image, extract the corresponding features from this area, and use this feature to train the classifier, and finally cla...

AI Technical Summary

Problems solved by technology

However, the traditional convolutional neural network often only consi

Images