Image semantic segmentation method based on super-pixel edge and full convolutional network

Abstract

The invention proposes an image semantic segmentation method based on a super-pixel edge and a full convolutional network, so that a technical problem of low accuracy in the existing image semantic segmentation method is solved. The method comprises: a training sample set, a testing sample set, and a verification sample set are constructed; a full convolutional network outputting a pixel-level semantic mark is trained, tested, and verified; semantic segmentation is carried out on a to-be-segmented image by using the verified full convolutional network outputting a pixel-level semantic mark to otain a pixel-level semantic mark; BSLIC sub-pixel segmentation is carried out on the to-be-segmented image; and semantic marking is carried out on BSLIC super-pixels by using the pixel-level semantic mark to obtain a semantic segmentation result with combination of the super-pixel edge and the high-level semantic information outputted by the full convolutional network. Therefore, the original full convolutional network segmentation accuracy is kept and the segmentation accuracy of the small edge is improved, so that the image segmentation accuracy is enhanced. The image semantic segmentation method can be applied to classification, identification, and tracking occasions requiring target detection.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image semantic segmentation method, in particular to an image semantic segmentation method based on superpixel edges and a full convolution network, which can be used for image classification, target recognition, target tracking, etc., which require target detection occasion. Background technique [0002] In the field of digital image processing, the applications related to segmentation include target segmentation, foreground segmentation, image segmentation and image semantic segmentation, in which target segmentation aims to segment the main target in the image; foreground segmentation refers to the segmentation of video or image sequences The region of interest is segmented; image segmentation is to divide the image into several non-overlapping areas with different attributes. In image segmentation, the possibility of pixels being divided into any area is the same, a...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the defects in the above-mentioned prior art, and propose an image semantic segmentation method based on superpixel edge and full convolutional network, which is used to solve the low-accuracy technology existing in the existing image semantic segmentation method question

Images