SLAM method applied to a multi-lens combination panoramic camera

Abstract

The invention provides a SLAM method applied to a multi-lens combination panoramic camera, which well realizes the automatic positioning and map construction functions of a vehicle-mounted multi-lenscombination panoramic camera, and achieves a high positioning accuracy of 0.1 m level without resorting to an expensive GPS / IMU integrated navigation system. The method firstly performs camera calibration on a multi-lens combination device, and then establishes a parallel three-thread, wherein the pose tracking thread mainly completes system initialization, feature extraction on a panoramic image,matching and projection, pose solution optimization and selection of key frames; The sparse map construction thread is mainly responsible for establishing sparse map points according to the initial posture and matching points, optimizing the camera posture and map points locally, and eliminating the wrong map points and redundant key frames. The closed-loop correction thread is mainly responsiblefor detecting whether the motion of the camera has returned to the previous position (i.e. Closed-loop), adding closed-loop constraints to correct the posture and global posture and map point optimization (i.e. Global beam adjustment).

Description

technical field [0001] The invention relates to a SLAM method applied to a multi-lens combined panoramic camera, which belongs to the fields of photogrammetry and remote sensing, computer vision, robots and the like. Background technique [0002] With the development of sensor, automation and platform technology, using optical or distance sensors placed on the platform, the intelligent system that realizes self-localization and environmental perception at the same time has become a new research direction in photogrammetry, computer vision and robotics; and in mobile mapping Systems, unmanned vehicles, deep space exploration of Mars and the moon, drone reconnaissance, indoor navigation and other fields play a key role. If the optical sensor is used as the main source of information acquisition, this system is usually called vision-based automatic localization and map construction (Simultaneous Localization And Mapping, SLAM). Mainstream visual SLAM systems have two classific...

AI Technical Summary

Problems solved by technology

Panoramic imaging devices mounted on mobile mapping systems or ordinary cars are usually only used for street view collection, such as the street view images of Google and Baidu, which cannot realize the measurement function; geometric positioning and SLAM based on panoramic vision have also had a small number of applications. research, however, a complete, automated solution is currently lacking

Images