Calculation method of low dynamic carrier speed fusing light flux and SIFT feature point matching in environment of uneven light intensity distribution

Abstract

The invention discloses a calculation method of low dynamic carrier speed fusing light flux and SIFT feature point matching in environment of uneven light intensity distribution. Through a car-loaded camera installed on a mobile carrier collecting dynamic images of the carrier, and using two algorithms of the pyramid Lucas-Kanade light flux and SIFT feature point matching, the feature points of the current frame image and the next frame image are detected and matched. Based on the frame displacements corresponding to the several feature points which are matched successfully, the speed V light flux and VSIFT under the coordinate system of the carrier are calculated, the difference delta V in between and the acceleration difference delta a are inputted in a modified self-adaptive Kalman filter to conduct direct correction of the carrier speed VSIFT calculated by using the light flux method. The calculation method of low dynamic carrier speed fusing light flux and SIFT feature point matching in environment of uneven light intensity distribution is high in solving precision and fast in solving speed, and can obviously increase the precision and real time feature in the estimation of the low dynamic carrier speed.

Description

Technical field [0001] The invention relates to the field of computer image processing, in particular to a design for obtaining a higher-precision moving carrier speed by fusing optical flow and SIFT feature point matching methods, and is suitable for visual aided navigation of mobile robots. Background technique [0002] At present, there are two main methods for obtaining the speed of a mobile carrier, one is to use a traditional code disc, and the other is a vision-based method. Compared with the traditional encoder method, the method of using the visual method to obtain the speed of the moving carrier will not be affected by the side slip of the wheel, and there will be no drift in the result when the car body is not moving. In recent years, the method of measuring the speed of low dynamic moving carriers based on vision has gradually become an important choice. However, a single method based on visual measurement speed cannot meet the requirements of real-time and high robu...

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: In order to overcome the deficiencies in the prior art, the present invention proposes a fusion optical flow in an environment with uneven light intensity distribution that improves the accuracy and real-time performance of solving problems without increasing the cost and other problems. Calculation Method of Low Dynamic Carrier Velocity Matched with SIFT Feature Points

Images