Tracking and matching parallel computing method for wearable device

Abstract

The invention discloses a tracking and matching parallel computing method for a wearable device so as to achieve augmented reality tracking and matching. According to the tracking and matching parallel computing method, the SCAAT-EKF feature tracking technology is adopted, complementary fusion data acquisition is conducted on multiple sensors in the wearable device, and data collision can be effectively avoided; the operation strategy based on the double kernal CPU+GPU group kernel multi-channel is utilized, corner detection and extraction based on the Harris algorithm are conducted in the GPU, the double kernal CPU is used for conducting P-KLT tracking and matching calculation, and therefore algorithm fast parallel processing is achieved. The tracking and matching parallel computing method mainly comprises the steps of hybrid tracking and feature extraction for the wearable device, accurate extraction of feature points of target natural features without marks, Harris corner point detection achieved based on a GPU parallel processing mechanism, the CPU-based P-KLT parallel feature tracking algorithm and the secondary matching optimization algorithm. The tracking and matching parallel computing method for the wearable device achieves combination of the sensors of the wearable device and visual tracking and matching, and has the wide prospect in the augmented reality three-dimensional registration aspect.

Description

Technical field: [0001] The invention belongs to the field of augmented reality, and in particular relates to a tracking and matching parallel computing method for wearable devices. Background technique: [0002] Augmented reality is an interdisciplinary subject, which integrates technologies in the fields of pattern recognition, 3D reconstruction, and machine learning. It is a research hotspot in the field of graphics and images in recent years. And so on, derived many augmented reality application products, such as Google Glass, GALAXYGear and so on. Augmented reality for wearable devices integrates virtual information into the real world through graphics and visual technology, so that the real environment and virtual objects can be superimposed in the same space in real time. A new technology that seamlessly integrates real world information and virtual world information needs to be applied. In fact, the research on augmented reality technology for wearable devices main...

AI Technical Summary

Problems solved by technology

Although this can meet the real-time requirements, it introduces the defect of error accumulation, which reduces the stability of the system, makes the system error continue to increase during operation, and cannot meet the needs of long-term 3D registration.

In addition, the SIFT algorithm is one of the traditional feature matching methods. Although the descriptors are highly distinguishable, each descriptor occupies a relatively large space and requires a high space memory capacity, which is not easy to implement on wearable devices.

The SURF feature matching algorithm is one of the more popular wide-baseline feature point matching algorithms at present. It has a fast calculation speed, but the algorithm has a high computational complexity. SURF extraction and matching work is done for each frame, and the memory consumption is relatively large. Difficult to implement in real-time wearable augmented reality devices

Images