Robust Mono Visual-Inertial Odometry Using Sparse Optical Flow With Edge Detection

Zeng, Qingxi; Gao, Chang; Chen, Zewang; Jin, Yu; Kan, Yuchao

doi:10.1109/jsen.2021.3070603

Cited by 7 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional sparse feature-based VO methods have limited accuracy and robustness in challenging environments (texture loss, motion blur, dynamic scenes) because the fact that the algorithm obtains fewer valid, matchable feature points in a given environment, and therefore often fails to track [6]. As deep learning gradually domi-nates computer vision tasks [7].…”

Section: Introductionmentioning

confidence: 99%

Self-Supervised Sparse Direct Visual Odometry with Half-Geometric Correspondence Network

Zhang,

Li,

Zhou

et al. 2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Current mainstream visual odometry method often suffers from tracking lost in low texture and motion blur scenarios due to fewer effective features and difficulty in getting stable matches. And feature matching process affects the overall real-time performance. For the fast localization task in low texture environments, this paper proposes an efficient self-supervised direct visual odometry framework based on keypoint extraction network, HGCN-VO. First we build the half-geometric correspondence network, HGCN, for fast extraction of robust keypoints in images. During training, we propose training method which uses basic shape elements to render generated simulated images with pseudo-labels as well as random homography transformations on real images for pre-training and migration learning and optimizing the keypoint loss from forward and reverse perspective transformed images. Finally we optimize the inter-frame position using a multilayer sparse direct method combined with bundle adjustment to improve the robustness of the method in low texture environments while increasing the processing speed. We evaluated the proposed method in KITTI, TUM, and challenging low-texture real-world scenarios and compared it with the current mainstream visual odometry methods, and the results show that the algorithm is sufficiently robust and accurate in low-texture environments and has a fast processing speed.

show abstract

Section: Introductionmentioning

confidence: 99%