Monocular SLAM (Simultaneous Localization and Mapping) method capable of creating large-scale map
A large-scale, map-based technology, applied in image analysis, image data processing, instruments, etc., can solve problems such as inability to build environmental maps, inflexibility, and inability to guarantee flexibility
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2016-08-03
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention belongs to the field of robot synchronous positioning and map creation, and relates to a monocular SLAM method capable of creating large-scale maps. Background technique
[0002] In recent years, with the further development of computer technology, digital image processing technology and image processing hardware, computer vision has begun to receive widespread attention in the field of robotics. SLAM is the abbreviation of Simultaneous Localization and Mapping (Simultaneous Localization and Mapping). This concept was first proposed by Smith, Self and Cheeseman in 1988. This method describes the situation in which the robot starts from an unknown location in an unknown environment and then explores the unknown environment: the robot repeatedly observes the environment during the movement, and then locates its own position and posture according to the environmental characteristics perceived by the sensor, and then according to its own posi...
Examples
Embodiment Construction
[0033] The present invention will be further described below in conjunction with the accompanying drawings.
[0034] Such as figure 1 Shown: a kind of monocular SLAM method that can create large-scale map, it is characterized in that: adopt following steps:
[0035] Step 1: Tracking of the new frame: the tracking component continuously tracks the new camera image (640×480 pixels) at a frequency of 30 Hz, and evaluates the rigid body pose of the image relative to the current frame in, Represents a set of Lie-algebra transformations, ξ represents a transformation in the set, initialized with the pose of the previous frame.
[0036] Step 2: Depth map estimation: The component uses the tracked frame to extract or replace the current keyframe, and extracts depth by filtering many frame-by-frame small baseline stereo comparisons plus interleaved spatial orthogonalization; if the camera moves too far, New keyframes are initialized from the existing projected points closest to th...