A method and system for quickly generating SIFT descriptors

A descriptor and fast technology, applied in the field of computer vision, can solve problems such as the inability to complete 128 descriptor calculations, the inability to achieve rotation angle calculations, and impracticality, so as to reduce the use of memory resources, reduce the number of lookup table operations, The effect of reducing the data bit width
CN108664982BActive Publication Date: 2022-03-22SUN YAT SEN UNIV
3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN ยท China
Patent Type
Patents(China)
Current Assignee / Owner
SUN YAT SEN UNIV
Publication Date
2022-03-22

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a method for quickly generating a SIFT descriptor, comprising the following steps: S1. receiving Gaussian graph data information transmitted from the outside; S2. obtaining the main direction of the key point after passing through the amplitude and angle calculation module; S3 The obtained main direction will be sent to the rotation interval calculation module to calculate the rotated argument angle information; S4. The rotation interval calculation module will receive the initial argument angle information and the main direction, and then perform interval rotation according to the main direction, and finally determine its location Row and column information; at the same time receive the amplitude and weight 2 to weight the amplitude; S5.128bin calculation module receives the angle information after rotation, the coordinate information after rotation and the weighted amplitude, so as to calculate the 128-dimensional description sub for output.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the field of computer vision, and more specifically, relates to a method and system for rapidly generating SIFT descriptors. Background technique

[0002] In the research of image matching, the matching methods mainly include two types: grayscale-based matching and feature-based matching. Feature matching has become the focus of image matching research because of its relatively small amount of calculation and strong robustness to noise. The SIFT (Scale Invariant Feature Transform) algorithm is a milestone work in the field of local image feature descriptor research. Compared with other algorithms, in addition to scale invariance, rotation invariance, and affine invariance, it also has certain anti-noise ability. However, due to the large amount of calculation of the SIFT algorithm itself, traditional computers and DSP platforms can no longer meet the needs of real-time and fast processing. The pipeline design of the ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More