Augmented reality tracking method based on neural network

Abstract

The invention discloses an augmented reality tracking method based on a neural network. The augmented reality tracking method includes the steps that S1, a neural network structure is established; S2, motion data of a target object in an image sequence serve as training data so as to train the neural network, and weights of all layers in the neural network are adjusted; S3, the angular point features of a first image in a video are extracted; S4, through neural network prediction, the motion tendency of the target object is acquired; S5, the target object is tracked in the direction of the motion tendency of the target object and in the follow-up image sequence. According to the method, the motion tendency of the target object is predicted through the neural network, the search range and the number of iteration times in the calculation process are reduced, thus, the tracking calculation time is shortened, and the tracking efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of augmented reality, in particular to a neural network-based augmented reality tracking method. Background technique [0002] Augmented reality is a technology that generates a virtual three-dimensional model through a computer and superimposes the virtual model on the real world to achieve augmented reality, also known as mixed reality. [0003] At present, many augmented reality systems are marker-based augmented reality systems, which need to prepare markers in advance and extract the feature information of the markers and store them in the database. When the camera captures the markers again, it will recognize, track, locate and superimpose the model. In the marker-based augmented reality system, markers can be two-dimensional codes, circles, etc. Tencent Technology (Shenzhen) Co., Ltd. disclosed a two-dimensional code augmented reality realization method and device in 2014 (Chinese patent application n...

AI Technical Summary

Problems solved by technology

Marker-based augmented reality systems are easy to implement, but their application scenarios are greatly limited due to the need to prepare markers in advance

[0004] However, the existing marker-based augmented reality system has the disadvantage of limited application scenarios due to the preparation of markers in advance; the existing tracking method does not predict the movement trend of the target object, so the tracking calculation time is long

Images