26 February 2024 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Falls represent a significant cause of injury among the elderly population. Extensive research has been devoted to the utilization of wearable IMU sensors in conjunction with machine learning techniques for fall detection. To address the challenge of acquiring costly training data, this paper presents a novel method that generates a substantial volume of synthetic IMU data with minimal actual fall experiments. First, unmarked 3D motion capture technology is employed to reconstruct human movements. Subsequently, utilizing the biomechanical simulation platform Opensim and forward kinematic methods, an ample amount of training data from various body segments can be custom generated. Synthetic IMU data was then used to train a machine learning model, achieving testing accuracies of 91.99% and 86.62% on two distinct datasets of actual fall-related IMU data. Building upon the simulation framework, this paper further optimized the single IMU attachment position and multiple IMU combinations on fall detection. The proposed method simplifies fall detection data acquisition experiments, provides novel venue for generating low cost synthetic data in scenario where acquiring data for machine learning is challenging and paves the way for customizing machine learning configurations.
15 July 2024 in IEEE Transactions on Instrumentation and Measurement
Recently, with the rapid progress of solid-state light detection and ranging (LiDAR), the issues of establishing a robust transformation between solid-state LiDAR (SSL) and other sensors have attracted considerable attention. However, the inconsistency of the ranging error distribution and the trailing phenomenon of SSL pose great challenges to calibration. To address this issue, this article proposes an automatic calibration method based on pseudovisual images obtained from SSL and multiple targets with distinguished patterns. For feature refinement, by utilizing adaptive pseudovisual image restoration algorithms, the precise detection of checkerboard corners in point clouds brings reliable initial values for coarse registration. The biplanar fitting and hollow fillment algorithms are invented to efficiently extract the ideal planes from noisy point clouds for precise registration. For registration, the 2-D–3-D corner mapping table is established to estimate the initial rigid-body transformation. After coarse registration, the loss function based on multiplanar distances and normal vectors is introduced to obtain the final extrinsic parameters in precise registration. Our proposed method has been tested in real-world and synthetic environments with extensive qualitative and quantitative analyses, respectively, to verify its excellent accuracy and robustness compared with other state of the arts (SOTAs).
28 February 2025 in IEEE Robotics and Automation Letters
Keyframe insertion is critical for the performance and robustness of SLAM systems. However, traditional heuristic-based methods often lead to suboptimal keyframe selection, compromising the accuracy of localization and mapping. To address this, we propose KINND, a lightweight neural network-based framework for real-time keyframe insertion. The framework introduces a novel foundational paradigm for learning-based keyframe insertion, encompassing the model architecture and training methodology. A neural network model is designed using a hierarchical weighted self-attention mechanism to encode real-time SLAM state information into high-dimensional representations, producing keyframe insertion decisions. To overcome the absence of ground truth for keyframe insertion, a composite loss function is developed by integrating pose error and system state information, providing a metric for this task. Additionally, a novel training mode enhances the model's real-time decision-making capabilities. Experimental results on public and private datasets demonstrate that KINND operates in real time without requiring a GPU and, with a single training session on a public dataset, achieves superior generalization performance on other datasets.
27 November 2025 in IEEE Transactions on Intelligent Transportation Systems
Simultaneous localization and mapping (SLAM) is a fundamental technology of autonomous vehicle, yet its deployment in large-scale, low-texture indoor environments remains highly challenging. The paper introduces PillarSLAM, a multimodal, pillar-based semantic SLAM framework designed to address the limitations of conventional feature-driven approaches. First, a dynamic pillar modeling strategy is proposed to continuously refine pillar dimensions without singularity. Second, a geometry-driven data association method is developed, utilizing distance and pose constraints to uniquely identify individual pillar faces. Third, an object-centric multi-view loop closure is introduced, leveraging pillar positions instead of viewpoint-dependent keypoints to achieve robust long-range corrections. Finally, a topology-based relocalization method is designed, where subgraph of observed pillars are matched to the global map via graph isomorphism, enabling reliable place recognition independent of visual appearance. Experiments in both simulated and real-world environments demonstrate that PillarSLAM significantly outperforms state-of-the-art SLAM systems in mapping accuracy and relocalization robustness under challenging conditions.