Three-dimensional reconstruction method for indoor dynamic scene based on RGBD camera

Abstract

The invention discloses a three-dimensional reconstruction method for an indoor dynamic scene based on an RGBD camera. The three-dimensional reconstruction method comprises the steps of RGBD camera calibration, scene image acquisition, feature point extraction, dynamic point detection and elimination, elimination of dynamic points by using a mode of combining a convolutional neural network and a multi-view geometric method, tracking, new key frame insertion, local map optimization, loop detection and the like. By using the three-dimensional reconstruction method, the problems of inaccurate camera pose estimation and dynamic object ghosting of three-dimensional reconstruction in a dynamic scene are effectively solved, and the dynamic region detection step is optimized in time, and the effect of real-time reconstruction can be achieved. A camera track absolute error is used for measurement on a TUM data set, and the root-mean-square error of the camera track absolute error is increased to 0.025 from the previous 0.752.

Description

technical field [0001] The invention belongs to the field of three-dimensional imaging, in particular, it is a three-dimensional reconstruction method of an indoor dynamic scene based on an RGBD camera. Background technique [0002] With the advancement of computer technology in recent years, AR and VR technology has gradually become one of the hot research areas. In the field of smart home, it has important applications in the field of virtual shopping. How to effectively reconstruct the surrounding scenes is the direction of research. one. With the advancement of artificial intelligence technology, in the field of automatic driving of cars, the field of autonomous flight of drones also needs to solve the construction of surrounding scenes and its own positioning. [0003] The emergence of SLAM (simultaneous localization and map construction) technology has solved the above problems well. The SLAM system uses sensors mounted on objects (such as monocular and binocular cam...

AI Technical Summary

Problems solved by technology

[0005] Traditional SLAM methods solve the positioning and mapping problems in static scenes very well, but in scenes with dynamic objects, the positioning and mapping accuracy of these methods is very poor, because traditional SLAM methods are difficult to distinguish dynamic objects. objects and static objects, and they are treated the same

But in fact, the feature points extracted by the dynamic object are inconsistent with the feature points of the static background, which will seriously affect the positioning of the camera position, thereby affecting the result of the mapping

In practical applications, it is also necessary to eliminate dynamic objects. For example, in the path planning and navigation of sweeping robots, if dynamic objects such as people, dogs, and cats cannot be eliminated, the navigation path of the robot will be deviated.

[0006] The invention solves the problem of inaccurate trajectory estimation and ghosting during map reconstruction in the SLAM system

Images