FAST feature homogenization extraction and IMU-based inter-frame feature mismatching removal method

Abstract

The invention discloses a FAST feature homogenization extraction and IMU-based inter-frame feature mismatching removal method. Firstly, a FAST feature homogenization extraction method is adopted to obtain uniform and quality FAST feature points as much as possible in a whole image range; extra calculation overhead is not generated; an IMU-based inter-frame feature mismatching removal method uses IMU sensor data (acceleration and angular velocity) to calculate translation and rotation transformation between adjacent images so as to derive a basic matrix model and judge: when the camera is static, feature mismatching is judged and removed according to the motion vector length of feature matching; and when the camera moves, judging and removing feature mismatching according to whether featurematching conforms to the basic matrix model or not.

Description

Technical field [0001] The invention discloses a FAST feature homogenization extraction and an IMU-based inter-frame feature mismatch removal method, which belongs to the technical field of computer vision and image processing. Background technique [0002] The feature extraction method is to select some easy-to-observe parts in the image as features. Among them, the corner feature has better recognition and the calculation is simpler. The following describes the existing corner feature extraction method: [0003] For each pixel in the image, the Harris method calculates the grayscale change of the pixel in the neighborhood of the point on the horizontal axis and the vertical axis. If the grayscale changes in both directions are obvious, determine that the pixel is a corner point. Shi and Tomasi proposed an improved method based on Harris in 1994, that is, the GFT (Good Feature to Track) method, which improves the corner judgment condition, that is, the gray change needs to be grea...

AI Technical Summary

Problems solved by technology

These methods are complex to calculate and consume too long calculation time, so they cannot be well used in some applications with real-time requirements.

[0010] In summary, the feature mismatch removal method described above depends on the quality of the image features. When the image feature matching contains many feature mismatches, the feature mismatch cannot be accurately judged, which reduces the accuracy of feature matching.

Images