12 December 2023 in Measurement Science and Technology
This paper proposes an RGB-D visual odometry method that leverages point, line, plane features and Manhattan structures to achieve robust frame tracking and precise pose estimation, especially in textureless scenes. A validation method is introduced that ensures accurate frame-to-frame rotation estimation by comparing rotation angles computed from multiple Manhattan structures. Depth verification methods involving parameter fitting and outlier removal for point, line, and plane features are implemented by investigating the covariance of sensor depth measurements. We also employ local bundle adjustment in the local mapping thread to refine keyframe poses and landmarks. Comprehensive ablation studies confirm the effectiveness of our contributions. Experimental results on public datasets demonstrate that our method achieves obvious advantages in accuracy and robustness while maintaining real-time performance.
24 June 2025 in Measurement Science and Technology
Category-level object pose estimation has attracted attention in robotics and augmented reality, as it enables generalization to unseen instances within known categories. However, significant intra-category shape variations and the complexity of effectively integrating geometric and visual information pose challenges to accurate pose and size estimation in vision measurement. Leveraging the widespread availability of affordable RGB-D sensors, this study explores an effective strategy for extracting and fusing appearance and geometric features to improve estimation performance. We introduce a vision foundation model for robust appearance feature extraction and propose a novel point-to-patch feature fusion strategy that leverages pixel-wise RGB-D correspondence to concatenate patch-level appearance features with point-level geometric features. The estimation process follows a two-stage paradigm, where object translation and size are first predicted, followed by rotation estimation guided by an auxiliary branch designed to facilitate learning of rotation-aware transformations. The proposed method achieves state-of-the-art performance on the CAMERA25 and REAL275 datasets, with enhanced generalization on the Wild6D dataset. Additionally, it supports real-time inference at 34 FPS on a single NVIDIA RTX A6000 GPU.
6 June 2025 in Engineering Research Express
LiDAR-based Simultaneous Localization and Mapping (SLAM) is essential for autonomous driving and intelligent transportation systems. Conventional SLAM approaches typically perform unidirectional feature matching, from target to source frames, thus neglecting reverse correspondence and limiting the exploitation of complex geometric relationships. In contrast, this study proposes a novel adaptive feature extraction and bidirectional feature matching framework that constructs edges and planes from both target and source point clouds. By integrating the geometric correlations of neighboring feature points directly into the residual equations, our approach strengthens geometric constraints and effectively eliminates redundant features. Experimental evaluations on the KITTI dataset and proprietary autonomous vehicle data demonstrate that the proposed method significantly enhances mapping consistency and system robustness, achieving a substantial reduction in Absolute Trajectory Error (ATE) compared to state-of-the-art techniques.