Scenario-driven image characteristic point selection method for smart phone

Abstract

The invention discloses a scenario-driven image characteristic point selection method for a smart phone. The main problem of incapability of outputting a rational number of characteristic points according to scenario complexity information in the prior art is solved. The method is implemented by the following steps of: performing characteristic point detection on video frames acquired by a cameraof the phone; generating a description vector gpt detected characteristic points in each frame, and performing characteristic point matching by utilizing the description vectors; and analyzing a characteristic point matching result, and adaptively regulating the number of the characteristic points in each frame of image output under the two conditions that characteristics can be normally matched and that the characteristics cannot be normally matched, thereby realizing the output of a stable number of characteristic points with stable quality in a complex or simple scenario. The method has the advantages of low calculation amount and capability of adaptively outputting a stable number of characteristic points with stable quality according to scenario complexity, and an important foundation is laid for the establishment of a rapid characteristic tracking system for the smart phone.

Description

technical field [0001] The invention belongs to the field of image processing technology, and in particular relates to a method for extracting image feature points. Specifically, it is a scene-driven smart phone image feature point rapid selection method, which can be applied to feature matching, target tracking, object recognition, and motion. Target detection and tracking, augmented reality development and other fields. Background technique [0002] Image feature point extraction is a basic problem in image processing, and accurate and efficient feature point extraction algorithms provide a solid underlying foundation for solving other problems. [0003] Feature points are also called interest points, corner points, salient points, etc. Based on Moravec's description of interest points, Harris uses the autocorrelation matrix of the brightness function, that is, the second-order moment matrix, to realize the detection of feature points. Mikolajczyk and Schmid used the Lapl...

AI Technical Summary

Problems solved by technology

[0005] Although the current smart phone hardware configuration has been updated, the processing capacity is still very limited. It is difficult to meet the real-time requirements when complex processing of some graphics images is required, and most of the feature detection algorithms do not target the background of the image. The number of feature points required by the information adaptive adjustment algorithm often extracts too many feature points for an image with a complex background, which causes redundant calculations for the next image processing such as feature description or image matching; The feature points extracted from relatively simple images are too small, and sufficiently robust feature points cannot be found, which makes it difficult to accurately describe and match the next image.

Images