Method and device for extracting scale-invariant features and method and device for recognizing objects

Abstract

The invention provides a method and a device for extracting scale-invariant features of images in video streams and a method and a device for recognizing objects on the basis of the method for extracting the features. The images comprise gray images and corresponding parallax images, correspond to moments t1 in the aspect of time, and include precedent images and posterior images in the video streams in the aspect of time. The method for extracting the features can include positioning critical points in the images; generating description regions around the critical points, and describing each description region around the corresponding critical point in four dimensions x, y, z and t; generating descriptors for each critical point on the basis of the description region of the critical point. Values of each description region in the range of each of the corresponding dimensions x, y, z and t are not equal to zero. The descriptors are used as the scale-invariant features of the critical points. The methods and the devices have the advantages that information of time domains, information of depth domains and information of image planes are closely combined with one another, so that the four-dimensional scale-invariant features can be extracted, and the methods and the devices are suitable to be applied to machine learning.

Description

technical field [0001] The present invention generally relates to image processing, and in particular, to feature extraction methods, object recognition methods and corresponding devices. Background technique [0002] Target recognition in real scenes has high requirements on local features, and requires features not to be affected by interference from nearby objects and partial occlusion. A major difficulty in object recognition is the selection of image features. [0003] The features used for object recognition are usually affected by the following factors: scale changes, image rotation, image blur, image compression, and brightness changes. [0004] There are many existing local features, including GLOH (Gradient Location Orientation Histogram, gradient position orientation histogram), SIFT (Scale Invariant Feature Transform, scale invariant feature transformation), direction controllable filter, etc. These features are based on two-dimensional image domain information...

AI Technical Summary

Problems solved by technology

These features are based on two-dimensional image domain information, it is difficult to solve some complex scenes, such as occlusion

Images