Double-frame depth and motion estimating method based on convolutional neural network

Abstract

The invention provides an image pixel classifying method based on the convolutional neural network. The method mainly includes the steps of image inputting, self-help network processing, iterative processing, image thinning and estimation result obtaining. The process includes estimating depth and camera motion by adopting the convolutional network and includes three stages that image pairs are sampled from a scene data set, and the image pairs with highlight conformity errors are discarded; the image pairs obtained after preprocessing are input into a self-help network to calculate optical flow, depth and camera motion; an iterative network is used for conducting iterative repetition multiple times to improve an existing estimation result; a high-resolution depth image and motion estimation are obtained after refining of a refining network. The network is obviously superior to a traditional motion structure, and the result is more accurate and robuster; different from the network of estimating depth through the single image, the network learns the concept of learning, is capable of using motion parallax for processing a new type of scene and allows motion estimation.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a convolutional neural network-based dual-frame estimation depth and motion method. Background technique [0002] With the rapid development of science and technology, in the field of deep learning research, the structure of motion is a long-term task in computer vision. Systems representing the state of the art are elaborate pipelines consisting of several sequential processing steps, which have certain inherent limitations. Before starting to estimate camera motion, the structure of the scene is usually inferred by dense consensus search, and incorrect estimation of camera motion leads to erroneous depth predictions. Furthermore, the process of estimating camera motion from the sparse agreement computed from keypoint detection and descriptor matching is prone to anomalies and does not work well in non-textured regions, and all motion structure methods are not suitable for small ...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of inaccurate depth and camera motion estimation and not wide application range, the purpose of the present invention is to provide a method for estimating depth and motion based on convolutional neural networks with two frames

Images