Indoor scene positioning method based on hybrid camera

Abstract

The invention discloses an indoor scene positioning method based on a hybrid camera. The indoor scene positioning method includes taking a depth image and a color image of an indoor scene by the hybrid camera; tracking position of the camera; utilizing a standard greed forest algorithm to train the depth image and the color image of the indoor scene to build a regression forest; when positioning the indoor scene, utilizing the depth image and the color image of a current frame photographed by the hybrid camera and the regression forest which is trained well to calculate world coordinates corresponding to the current camera to complete positioning. In the indoor scene positioning method, the hybrid camera is adopted for photographing, a regression forest algorithm is adopted to train each pixel point in a known scene, and sparse feature points or dense feature points do not need to be used for scene positioning, so that time for detecting, describing and matching the feature points is saved, camera positioning is enabled to have nothing to do with state, accumulated errors in camera tracking are avoided, and accuracy and efficiency of scene positioning are improved effectively.

Description

technical field [0001] The invention belongs to the technical field of indoor scene positioning, and in particular relates to an indoor scene positioning method based on a hybrid camera. Background technique [0002] With the rapid growth of digital image data, it is becoming more and more urgent for computers to automatically understand images. As an important research content of image understanding, scene localization has received extensive attention and is currently a research hotspot in the field of computer vision. Most of the current mainstream scene localization methods are based on color images. [0003] The scene localization methods based on color images can be roughly divided into two categories: the first one is the scene localization method based on sparse feature point matching. The strategy adopted by this type of algorithm is to extract a certain number of key points from the scene image when the camera is tracking normally, describe the features of these ke...

AI Technical Summary

Problems solved by technology

The disadvantage is that each key frame usually uses operations such as downsampling and brightness information normalization when encoding. As the number of key frames increases, the similarity calculation between key frames will become more and more difficult.

Moreover, for such scene recognition algorithms based on global image matching, the recognition results can only depend on a limited number of camera poses stored in the database, which seriously restricts the scalability of this type of method.

Images