Scene segmentation method and system based on context prior

Abstract

The invention discloses a scene segmentation method and system based on context prior, and belongs to the field of pattern recognition. The method comprises the following steps: constructing a scene segmentation network; the network comprises a feature extraction module, a feature aggregation module, a context prior module and a feature fusion module. Wherein the first two modules sequentially perform feature extraction and feature aggregation on an input image; the context priori module learns the features obtained by aggregation to obtain a context priori graph, learns the context priori graph to obtain intra-class priori and inter-class priori, and weights the intra-class priori and inter-class priori with the output of the feature aggregation module to correspondingly obtain intra-class features and inter-class features; the feature fusion module is used for carrying out cascade fusion and up-sampling on the feature map, the intra-class features and the inter-class features outputby the feature extraction module and then outputting the features; and inputting the scene image to be segmented into the trained scene segmentation model to obtain a segmentation result. According tothe method, the intra-class features and the inter-class features can be clearly captured, and the accuracy of scene segmentation is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and more particularly relates to a scene segmentation method and system based on context prior. Background technique [0002] The goal of scene segmentation is to assign a category label to each pixel to provide a comprehensive scene understanding. It has a wide range of applications in fields such as augmented reality, autonomous driving, human-computer interaction, and video surveillance. Challenging question. [0003] Benefiting from the powerful feature representation of fully convolutional networks (FCNs), many methods achieve decent scene segmentation performance. However, limited by the convolutional layer structure, the context information provided by FCN is insufficient, resulting in an incomplete understanding of the scene and affecting the accuracy of the recognition results. Therefore, various methods have emerged to explore contextual information for more accurate segme...

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a scene segmentation method and system based on context prior, the purpose of which is to solve the problem that the existing scene segmentation method has contextual confusion, resulting in low accuracy of scene segmentation results technical problem

Images