TY - JOUR
T1 - A Robust Keyframe-Based Visual SLAM for RGB-D Cameras in Challenging Scenarios
AU - Lin, Xi
AU - Huang, Yewei
AU - Sun, Dingyi
AU - Lin, Tzu Yuan
AU - Englot, Brendan
AU - Eustice, Ryan M.
AU - Ghaffari, Maani
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2023
Y1 - 2023
N2 - The accuracy of RGB-D SLAM systems is sensitive to the image quality, and can be significantly compromised in adverse situations such as when input images are blurry, lacking in texture features, or overexposed. In this paper, based on Continuous Direct Sparse Visual Odometry (CVO), we present a novel Keyframe-based CVO (KF-CVO) with intrinsic keyframe selection mechanism that effectively reduces the tracking error. We then extend KF-CVO to a RGB-D SLAM system, CVO SLAM, equipped with place recognition via ORB features, and joint bundle adjustment & pose graph optimization. Comprehensive evaluations on publicly available benchmarks show that the proposed RGB-D SLAM system achieves a higher success rate than current state-of-the-art-methods. The proposed system is more robust to difficult benchmark sequences than current state-of-the-art methods, where adverse situations such as rapid camera motions, environments lacking in texture, and overexposed images when strong illumination exists.
AB - The accuracy of RGB-D SLAM systems is sensitive to the image quality, and can be significantly compromised in adverse situations such as when input images are blurry, lacking in texture features, or overexposed. In this paper, based on Continuous Direct Sparse Visual Odometry (CVO), we present a novel Keyframe-based CVO (KF-CVO) with intrinsic keyframe selection mechanism that effectively reduces the tracking error. We then extend KF-CVO to a RGB-D SLAM system, CVO SLAM, equipped with place recognition via ORB features, and joint bundle adjustment & pose graph optimization. Comprehensive evaluations on publicly available benchmarks show that the proposed RGB-D SLAM system achieves a higher success rate than current state-of-the-art-methods. The proposed system is more robust to difficult benchmark sequences than current state-of-the-art methods, where adverse situations such as rapid camera motions, environments lacking in texture, and overexposed images when strong illumination exists.
KW - RGB-D camera
KW - Visual SLAM
KW - indoor environments
UR - http://www.scopus.com/inward/record.url?scp=85171531479&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85171531479&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2023.3312062
DO - 10.1109/ACCESS.2023.3312062
M3 - Article
AN - SCOPUS:85171531479
VL - 11
SP - 97239
EP - 97249
JO - IEEE Access
JF - IEEE Access
ER -