Mobile terminal real-time characteristic detection and matching method based on FAST-SURF

Abstract

The invention provides a mobile terminal real-time characteristic detection and matching method based on FAST-SURF. The method comprises the following steps: step 1, building a characteristic database on the basis of a collected image, including establishing a KD-tree on the basis of characteristic points on the image and forming characteristic database data; step 2, reading the image, converting the image into a gray-scale image, and calculating a gray-scale value of each point of the gray-scale image; step 3, using an improved FAST algorithm to detect the characteristic points; step 4, using a simplified SURF algorithm to set up descriptors of the characteristic points; and step 5, matching the descriptors with the characteristic points in the characteristic database. The method employs the improved FAST algorithm to detect the characteristic points, then uses the simplified SURF algorithm to calculate the directions of the characteristic points, and establishes the characteristic descriptors. Then the established characteristic points are matched with the characteristic descriptors in the database. It takes short time to process the image, and natural characteristic detection and matching can be processed on a mobile terminal.

Description

technical field [0001] The invention relates to a real-time feature detection and matching method of a mobile terminal based on FAST-SURF, and belongs to the technical field of mobile terminal augmented reality. Background technique [0002] In augmented reality technology, the tracking and registration method based on natural features is highly complex and requires high computing power. Among them, the tracking and registration method based on computer vision mainly involves the detection and matching of feature points. However, mobile devices are limited in technical performance due to their insufficient computing facilities (low throughput, poor floating-point computing power) and memory bandwidth (limited memory size, slow speed, and small cache). Therefore, it is a difficult problem to balance effect and efficiency on mobile devices. The biggest feature of the FAST algorithm is its computational efficiency. It is because of its high-speed performance that it is suitab...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the technical problem of insufficient processing capacity for natural feature extraction and matching of mobile terminals, the present invention provides a real-time feature detection and matching method for mobile terminals based on FAST-SURF, using the improved FAST algorithm to detect feature points, and then using the simplified SURF The algorithm calculates the direction of the feature point, and establishes the feature descriptor, and then matches the established feature point descriptor with the feature descriptor in the database

Images