Indoor scene identifying method based on point cloud fragment division

Abstract

The invention relates to an indoor scene identifying method based on point cloud fragment division. The indoor scene identifying method comprises the following steps of: pre-dividing a three-dimensional point cloud image according to a plane method vector and color information of a three-dimensional point cloud by combining a graph theory method, so that the image is divided into different point cloud fragments, and each fragment belongs to different objects; establishing a rate model framework for combining and identifying simultaneously to carry out combination and object classification on the point cloud segments, so as to identify different objects in a scene space; and expressing relation of an image characteristic, an object type and an object of the scene spaces and information of an area where the scenes are by using a scene space level model for combining semantic information with topological relation, and establishing a scene space information inference model based on an oriented picture, so as to obtain space semantic information of the scene. Compared with the prior art, the indoor scene identifying method has the advantages of accurate identification, simplicity and convenience in operation and the like.

Description

technical field [0001] The invention relates to a scene recognition method, in particular to an indoor scene recognition method based on point cloud segment segmentation. Background technique [0002] With the development of robot technology, the application field of robots has also begun to expand from the traditional factory manufacturing field to home, hospital, elderly care center, military, tourism, transportation, exploration, emergency rescue and disaster relief and other on-site and service fields. The characteristics of this type of environment are often uncertain or changing. How robots perceive and understand the environment becomes a challenge, and the basic and core issue of robot environment perception and understanding is scene recognition. For the scene recognition problem, the commonly used method is the Spatial Envelope scene descriptor (also known as the Gist of the scene) method, which describes the naturalness, openness, roughness and other characteristi...

AI Technical Summary

Problems solved by technology

In fact, a specific scene is composed of many different objects. Existing methods take more account of the statistical characteristics of scene features and pay less attention to the semantics of objects in the scene, or the spatial distribution and relationship of regions; scenes and objects are usually As an independent part or only a simple corresponding relationship has been established, a complete model system has not yet been formed

Images