Tightly coupled binocular vision-inertial SLAM method using combined point-line features

Abstract

The invention relates to a tightly coupled binocular vision-inertial SLAM method using combined point-line features, comprising the following steps: determining a transformation relationship between acoordinate system of a camera and a coordinate system of an inertial measurement unit (IMU); establishing a thread of point-line features and IMU tracking to solve an initial three-dimensional point-line coordinate; using the IMU to predict the position of the point-line features to correctly establish associations between the features and data, and combining a re-projection error of the IMU andthe point-line features to solve the pose transformation of consecutive frames after initializing the IMU; establishing a thread of the local bundle adjustment of the point-line features and the IMU,optimizing the three-dimensional point-line coordinate, the pose of a key frame and a state quantity of the IMU in a local key frame window; and establishing a loop back detection thread for the point-line features, using the point-line features to weight and calculate the score of a word bag model to detect the loop back, and optimizing the global state quantity. The tightly coupled binocular vision-inertial SLAM method using the combined point-line features is capable of ensuring stability and high precision in the case where the number of feature points is few and the camera is moving quickly.

Description

technical field [0001] The invention relates to the field of synchronous positioning and map building (SLAM) of visual-inertial fusion, in particular to a tightly coupled binocular visual-inertial SLAM method for point-line feature fusion. Background technique [0002] Simultaneous Localization And Mapping (SLAM) is an important means for robots to determine their own position and sense the surrounding environment, and it is also a basic issue and research hotspot in the field of autonomous navigation. It mainly solves the problem of how to calculate the map representation of the surrounding environment through the data obtained by the sensor (such as: binocular camera, inertial measurement unit, etc.) . [0003] The binocular vision sensor has the advantages of light weight, easy installation, low price and scale determinism, making binocular vision SLAM a research hotspot. The inertial sensor (Inertial Measurement Unit, IMU) can provide its own motion information (such a...

AI Technical Summary

Problems solved by technology

When the image feature points are relatively sparse, the illumination changes are strong and the movement is violent, it is easy to affect the accuracy of the algorithm, and even cause the algorithm to fail.

Although the SLAM method of visual-inertial fusion can assist the association of image feature data through inertial sensors and optimize the inertial sensor data at the same time, when the image feature data association is wrong or the inertial sensor initialization estimation error is wrong, the measurement error will propagate to the solution of the entire algorithm , so that the accuracy of the entire visual-inertial fusion algorithm is seriously reduced

Images