Monocular dense simultaneous localization and mapping (SLAM) method

Abstract

The invention provides a monocular dense simultaneous localization and mapping (SLAM) method. A faster and more robust plane area detection algorithm is adopted, and highly stable and reliable plane areas are found out before reconstruction, then the reconstruction is performed, and the time is greatly reduced; before the reconstruction, the highly stable and reliable plane areas are found out, only these areas are reconstructed, only a small part of reconstruction results will be discarded in the next filtering process, and the reconstruction efficiency is greatly improved; due to the presence of noise in the plane area detection algorithm, a multi-plane segmentation method is used to reconstruct the plane areas; the monocular dense SLAM method of the invention can run in real time without using a GPU; and on a TUM data set, the dense reconstruction algorithm has a running time of only about 35% of the DPPTAM, and this algorithm is advantageous over the DPPTAM in terms of map precision and integrity rate.

Description

technical field [0001] The invention relates to real-time positioning and map reconstruction technology, in particular to a monocular dense real-time positioning and map reconstruction method. Background technique [0002] Real-time localization and map reconstruction technology (SLAM) can predict the attitude of sensors or robots and reconstruct the map of the surrounding environment in real time. This technology has a wide range of applications in the fields of robots and augmented reality. However, real-time monocular dense map reconstruction for indoor scenes is still a very challenging problem. Existing monocular SLAM systems either use key points to obtain a sparse map, or use high gradient points to obtain a semi-dense map. For key points or high gradient points, triangulation methods can be used to obtain depth. It is difficult to find matching points for large, untextured areas, and it is difficult to accurately predict the depth of these areas. Therefore, it is v...

AI Technical Summary

Problems solved by technology

[0003] 1. The time is slow: the algorithm used to detect the plane area is relatively slow, and it takes a lot of time to reconstruct each plane area;

[0004] 2. The efficiency is not high: After each plane is reconstructed, many reconstruction results will be discarded through filter conditions, resulting in low efficiency;

[0005] 3. The reconstruction accuracy is not high: there is noise in the plane detection algorithm, which may cause more than one plane in some areas. If these areas are reconstructed as only one plane, it will bring a large reconstruction error

Images