Indoor layout estimation method and system based on learning prediction

Abstract

The invention discloses a method and system for estimating indoor layout based on learning prediction. The method includes: constructing a training set, and using training samples in the training set to train a deconvolution network; the training samples are room layout diagrams and their The corresponding edge map, the room layout map and its corresponding edge map are used as the input and output of the deconvolution network respectively; the room layout map to be tested is input to the trained deconvolution network, and the predicted edge map is output; The vanishing point in the preset direction in the room layout diagram generates several sectors; then based on the predicted edge map, selects the sector with the local maximum edge intensity as the sampling sector from the generated sectors; the sampling sector is sampled , to obtain a series of candidate room layout estimation maps; then according to the similarity between the room layout estimation map and the obtained edge map, select the room layout estimation map closest to the predicted edge map from the candidate room layout estimation maps as the final layout of the room.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to an indoor layout estimation method and system based on learning prediction. Background technique [0002] Room layout estimation is to simulate the room space with a best-fit 3D volumetric structure. In other words, the problem is equivalent to finding all wall-floor, wall-wall, wall-ceiling boundaries from a room. Unfortunately, these borders are mixed with various edges that are not rooms and are not always visible. Accurate room layout estimation requires computers to understand the room from a global perspective, rather than relying solely on local cues. [0003] Image features based on region information are widely used in previous works. Hedau et al. proposed a classical framework for room layout estimation: in the candidate generation stage, three mutually orthogonal vanishing points are estimated. Then by uniformly sampling from the vertical and infinite horizontal van...

AI Technical Summary

Problems solved by technology

The above methods all rely on traditional manual extraction features, there are many parameters that need to be manually adjusted, and the final estimation results have a large error

Images