Shape sensing living example segmenting method based on object mask network

Abstract

The invention provides a shape sensing living example segmenting method based on an object mask network. The method mainly includes shape sensing and segmenting prediction and learning living example segmenting, the process includes the steps that intensive multi-valued mapping codes are used for modeling the shape of an object, for the minimum distance from each pixel to the boundary of the object in a box, and the multi-valued map is converted into binary system masks through inverse distance conversion to segment the object. The suggestion of an initial bounding box is generated through an area network; characteristic deformation is carried out on each execution area-of-interest, and the result is transmitted to the object mask network to generate a result. The object mask is integrated into a multi-level network cascade to construct a shape sensing living example segmenting network and a multi-level shape sensing living example segmenting network, and the networks are trained in an end-to-end mode. The shape sensing living example segmenting method is meticulous in segmentation, high in precision, small in error and beneficial for completing and expanding existing image segmenting theories and methods and provides a practical tool for image analysis and understanding and other applications.

Description

technical field [0001] The invention relates to the field of image segmentation, in particular to a shape-aware instance segmentation method based on an object mask network. Background technique [0002] With the development of science and technology, the number of digital images is also increasing day by day, so the demand for digital image technology is also increasing day by day. In order to better identify and understand the content in images, image segmentation techniques are particularly important. Image segmentation is an important bridge in the transition from image processing to image analysis and understanding, and is a basic scientific problem in computer vision and other related research fields. Image segmentation can realize the computer to distinguish the various parts of the image and identify their types and colors. In terms of transportation, since pedestrians, vehicles, road conditions, traffic lights, traffic warning signs, etc. can be identified through ...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem of imprecise image segmentation, the purpose of the present invention is to provide a shape-aware instance segmentation method based on object mask network, which uses dense multi-valued map coding to model the shape of the object, and for each pixel in the frame to The (truncated) minimum distance of object boundaries, and object segmentation is achieved by converting this multivalued map into a binary mask via an inverse distance transform

Images