Redirigiendo al acceso original de articulo en 24 segundos...
ARTÍCULO
TITULO

Accumulative Errors Optimization for Visual Odometry of ORB-SLAM2 Based on RGB-D Cameras

Jiangying Qin    
Ming Li    
Xuan Liao and Jiageng Zhong    

Resumen

Oriented feature from the accelerated segment test (oFAST) and rotated binary robust independent elementary features (rBRIEF) SLAM2 (ORB-SLAM2) represent a recognized complete visual simultaneous location and mapping (SLAM) framework with visual odometry as one of its core components. Given the accumulated error problem with RGB-Depth ORB-SLAM2 visual odometry, which causes a loss of camera tracking and trajectory drift, we created and implemented an improved visual odometry method to optimize the cumulative error. First, this paper proposes an adaptive threshold oFAST algorithm to extract feature points from images and rBRIEF is used to describe the feature points. Then, the fast library for approximate nearest neighbors strategy is used for image rough matching, the results of which are optimized by progressive sample consensus. The image matching precision is further improved by using an epipolar line constraint based on the essential matrix. Finally, the efficient Perspective-n-Point method is used to estimate the camera pose and a least-squares optimization problem is constructed to adjust the estimated value to obtain the final camera pose. The experimental results show that the proposed method has better robustness, higher image matching accuracy and more accurate determination of the camera motion trajectory.

 Artículos similares

       
 
Ehsan Sorooshnia, Payam Rahnamayiezekavat, Maria Rashidi, Mahsan Sadeghi and Bijan Samali    
In humid subtropical climates with a green environment, windows are the most dominant envelope elements affecting indoor visual and thermal comfort and visual connection to the outdoors. This research aims to optimize a dynamic external shading system fo... ver más
Revista: Buildings

 
Siham Mousa Alhaider    
The investigation of linguistic landscapes (LL) among the Arab community in downtown Brooklyn, New York City, is an underserved public space in the literature. This research focused on social and commercial or ?bottom-up signs? in LL to understand their ... ver más

 
Krzysztof Zagata and Beata Medynska-Gulij    
The main objective of this study is to identify features of mini-map design as a navigational aid in the virtual geographical space in 100 popular video games for a computer platform. The following research methods were used: visual comparative analysis,... ver más

 
Xingguo Zhang, Yinping Sun, Qize Li, Xiaodi Li and Xinyu Shi    
Aiming at the problem that the existing crowd counting methods cannot achieve accurate crowd counting and map visualization in a large scene, a crowd density estimation and mapping method based on surveillance video and GIS (CDEM-M) is proposed. Firstly,... ver más

 
Huapeng Tang, Danyang Qin, Jiaqiang Yang, Haoze Bie, Yue Li, Yong Zhu and Lin Ma    
In indoor low-light environments, the lack of light makes the captured images often suffer from quality degradation problems, including missing features in dark areas, noise interference, low brightness, and low contrast. Therefore, the feature extractio... ver más