Depth map recovery method

Abstract

The invention discloses a depth map recovery method, comprising the following steps of A1, constituting a training set by the depth maps of a large number of various objects; A2, establishing a convolutional neural network (CNN), by using a nuclear separation method, acquiring the parameter of a hidden layer, establishing a convolutional network structure, and training the network structure and adjusting the network weight by using the depth maps in the training set; A3, in the output layer of the CNN, establishing an auto-regression model aiming at a possible result, and establishing an evaluation index; and A4, inputting an original depth map acquired by a depth sensor into the CNN, after denoising and classifying, recovering by an AR model, and if not conforming with requirements, inputting the result map into A2 until the high-quality depth map is acquired or the circulation is ended. According to the depth map recovery method, the image with low resolution and low signal to noise ratio acquired from the depth sensor can be recovered by using the depth convolution network. By using the depth map recovery method, the quality of the depth map can be significantly improved, and meanwhile the method for acquiring the depth map is also simplified.

Description

technical field [0001] The invention relates to the fields of computer vision technology and image processing, in particular to a depth map restoration method. technical background [0002] The technology belongs to the field of computer vision technology and image processing. The depth map is the depth information obtained from the actual shooting scene, and it plays a vital role in increasing the sense of reality, performing 3D reconstruction and 3D TV applications. Now the acquisition of the depth map is divided into two forms, one is passive and the other is active. This technology is mainly aimed at the depth map actively obtained by the depth sensor. However, the depth maps obtained by mainstream active depth sensors (such as ToF cameras, Kinect, etc.) have shortcomings such as low pixels and low signal-to-noise ratio. The depth map has pretty big holes. These problems have caused inconvenience to the application of the depth map. [0003] In order to obtain high-...

AI Technical Summary

Problems solved by technology

There are methods such as MRF, IMLS, Edge, and JGF in the depth restoration technology, but the recovery effect of using a single technology is not ideal

[0004] In order to restore the defective depth map obtained from the depth sensor, most of the current depth map restoration schemes based on filters are used, but the computational complexity converges slowly

Images