De-convolutional neural network-based scene semantic segmentation method

Abstract

The invention discloses a de-convolutional neural network-based scene semantic segmentation method. The method comprises the following steps of: S1, extracting intensive feature expression for a scene picture by using a full-convolutional neural network; and S2, carrying out up-sampling learning and object edge optimization on the intensive feature expression obtained in the step S1 through utilizing a locally sensitive de-convolutional neural network by means of a local affinity matrix of the picture, so as to obtain a score map of the picture and then realize refined scene semantic segmentation. Through the locally sensitive de-convolutional neural network, the sensitivity, to the local edge, of the full-convolutional neural network is strengthened by utilizing local bottom layer information, so that scene segmentation with higher precision is obtained.

Description

technical field [0001] The invention relates to the fields of pattern recognition, machine learning and computer vision, in particular to a scene semantic segmentation method based on a deconvolution neural network. Background technique [0002] With the rapid improvement of computer computing power, computer vision, artificial intelligence, machine perception and other fields are also developing rapidly. Scene semantic segmentation, as one of the basic problems in computer vision, has also been greatly developed. Scene semantic segmentation is to use computers to intelligently analyze images, and then determine the object category to which each pixel in the image belongs, such as floors, walls, people, chairs, etc. Traditional scene semantic segmentation algorithms generally only rely on RGB (red, green, and blue) images for segmentation, which are easily disturbed by light changes, object color changes, and noisy backgrounds. They are not robust in actual use and the accu...

AI Technical Summary

Problems solved by technology

These algorithms basically use the most advanced full convolutional neural network for scene segmentation, but each neural unit of the full convolutional neural network has a large receptive field, which can easily cause the edges of the segmented objects to be very rough.

Secondly, the simplest superposition strategy is also adopted in the fusion of RGB and depth information, without considering the fact that the data of these two modalities play completely different roles in distinguishing different objects in different scenes, resulting in many semantic segmentations. object classification error

Images