Object segmentation method and object segmentation device based on multilevel local region integration, and calculation equipment

Abstract

The invention discloses an object segmentation method and an object segmentation device based on multilevel local region integration, and calculation equipment, and belongs to the technical field of computer vision. The method comprises the steps as follows: for an image to be processed, selecting multiple local candidate regions according to multiple different preset scales; carrying out image segmentation on each local candidate region and predicting the binary segmentation mask of each local candidate region; carrying out image classification on each local candidate region and predicting the object category to which each local candidate region belongs; and according to the object category to which each local candidate region belongs and the binary segmentation mask of each local candidate region, integrating all the local candidate regions to get an object segmentation image. During detection of an object, the object can be segmented and the boundary thereof can be determined. After the segmentation result of local candidate regions is obtained, an effective way of local region integration is used, and a better optimization result can be obtained.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to an object segmentation method, device and computing device based on multi-level local region fusion. Background technique [0002] Image segmentation is a basic problem in the field of image processing, and has a wide range of applications in object recognition, robot navigation, scene understanding and other fields. Among them, object segmentation is a more essential problem than object detection and scene segmentation. Object detection expects to obtain the approximate position of each individual object. Usually, object detection marks the detected object through a rectangular detection frame, but cannot determine the boundary of the object; the scene is segmented into each type of scene to predict the category and the precise boundary, which can be used for different types of objects Make predictions and determine boundaries, but cannot distinguish between individuals...

AI Technical Summary

Problems solved by technology

Object detection expects to obtain the approximate position of each individual object. Usually, object detection marks the detected object through a rectangular detection frame, but cannot determine the boundary of the object; the scene is segmented into each type of scene to predict the category and the precise boundary, which can be used for different types of objects Make predictions and determine boundaries, but cannot distinguish between different individuals of the same class

[0003] The method of object segmentation in the prior art is mainly to obtain the candidates of the detection frame based on object detection, and then obtain the boundary through the segmentation method. The segmentation effect of this method is poor and the accuracy rate is not high.

Images