Monocular light field image unsupervised depth estimation method based on convolutional neural network

Abstract

The invention discloses a monocular light field image unsupervised depth estimation method based on a convolutional neural network. According to the method, the disclosed large-scale light field imagedata set is firstly used as a training set, and samples of the training set tend to be balanced through data enhancement and data expansion; an improved ResNet50 network model is constructed; an encoder and a decoder are used for extracting high-level and low-level features of a model respectively, results of the encoder and the decoder are fused through a dense difference structure, meanwhile, asuper-resolution shielding detection network is additionally constructed, and the shielding problem between all visual angles can be accurately predicted through deep learning; the objective functionbased on the light field image depth estimation task is a multi-loss function, the preprocessed image is trained through a pre-defined network model, and finally generalization evaluation is carriedout on the network model on a test set. According to the method, the preprocessing effect on the light field image of the complex scene is obvious, and the effect of more accurate light field image unsupervised depth estimation is achieved.

Description

technical field [0001] The invention relates to the field of light field image processing, in particular to an unsupervised depth estimation method for monocular field images based on a convolutional neural network. Background technique [0002] Single image depth estimation is an important technique for obtaining scene depth based on images in 3D reconstruction, and it is also a classic problem in computer vision. In recent years, single image depth estimation based on supervised learning has developed rapidly. However, to obtain the accuracy of supervised learning Labeling is very difficult and will be affected by many external factors such as environment and light, and it will take a huge price to overcome these effects. Based on this, according to the characteristics of image depth, the present invention invented a monocular unsupervised depth estimation method based on deep convolutional neural network, which can quickly and accurately estimate the depth information of ...

AI Technical Summary

Problems solved by technology

[0002] Single image depth estimation is an important technique for obtaining scene depth based on images in 3D reconstruction, and it is also a classic problem in computer vision. In recent years, single image depth estimation based on supervised learning has developed rapidly. However, to obtain the accuracy of supervised learning The labeling of is very difficult and will be affected by many external factors such as environment, light and so on. To overcome these influences requires a huge price

Images