Scene segmentation method and system based on feature image restoration

Abstract

The invention relates to a scene segmentation method and system based on feature image restoration, wherein the method includes the steps of downsampling the original image, obtaining a downsampled image, and obtaining a downsampled feature map of the downsampled image through a feature learning network; the size of the downsampled feature map is restored to the original image size, an upsampled feature map is obtained, and the upsampled feature map is input into a scene segmentation network to obtain a scene segmentation result of the original image. The method realizes the fast segmentationspeed by downsampling the input image. A high segmentation accuracy can be obtained by using the original size input image. In addition, the invention also provides a method for assisting middle layersupervision and border region re-weighting to assist the optimization process of the scene segmentation neural network model, so as to improve the segmentation accuracy of the accelerated model on the premise of maintaining the acceleration of the model.

Description

technical field [0001] The method belongs to the field of machine learning and computer vision, and particularly relates to a scene segmentation method and system based on feature map restoration. Background technique [0002] Scene segmentation is an important and challenging problem in the field of computer vision, and has a wide range of application values ​​in production and life, such as automatic driving, assisted driving, video surveillance, etc. The goal of scene segmentation is to judge the category of each pixel in the scene image. In recent years, scene segmentation methods based on deep convolutional neural networks, such as those based on fully convolutional networks, have achieved great success. However, most of the existing scene segmentation methods mainly focus on improving the accuracy of segmentation, so they often use deeper neural networks and higher resolution feature maps, which will lead to slower segmentation speed. However, in practical applicatio...

AI Technical Summary

Problems solved by technology

In order to solve the problems caused by these two characteristics, many existing methods downsample the input image, which can simply and effectively improve the segmentation speed of the neural network model, but this is at the cost of sacrificing the segmentation accuracy, because in downsampling During the sampling process, a lot of detailed information in the image is lost

Images