We propose to estimate 3D human pose from multi-view images and a few IMUs attached at person's limbs. It operates by firstly detecting 2D poses from the two signals, and then lifting them to the 3D space. We present a geometric approach to reinforce the visual features of each pair of joints based on the IMUs. This notably improves 2D pose estimation accuracy especially when one joint is occluded. We call this approach Orientation Regularized Network (ORN). Then we lift the multi-view 2D poses to the 3D space by an Orientation Regularized Pictorial Structure Model (ORPSM) which jointly minimizes the projection error between the 3D and 2D poses, along with the discrepancy between the 3D pose and IMU orientations. The simple two-step approach reduces the error of the state-of-the-art by a large margin on a public dataset. Our code will be released at https://github.com/CHUNYUWANG/imu-human-pose-pytorch.
Fusing uncalibrated IMUs and handheld smartphone video to reconstruct knee kinematics
Center for Bionic Medicine, Shirley Ryan AbilityLab（雪莉·瑞安能力实验室仿生医学中心）；Department of Biomedical Engineering, Northwestern University（西北大学生物医学工程系）；Department of Physical Medicine and Rehabilitation, Northwestern University（西北大学物理医学与康复系）
FLOW: Fusing and Shuffling Global and Local Views for Cross-User Human Activity Recognition with IMUs
School of Computer Science, University of South China（南华大学计算机学院）；School of Computing, University of Ulster（阿尔斯特大学计算学院）；The University of Auckland（奥克兰大学）；School of Computer Science and Technology, Dalian University of Technology（大连理工大学计算机科学与技术学院）
MARS: Mixed Virtual and Real Wearable Sensors for Human Activity Recognition with Multi-Domain Deep Learning Model
Shanghai Jiao Tong University（上海交通大学）
随着物联网（IoT）的快速发展，使用可穿戴惯性测量单元（IMU）的人体活动识别（HAR）成为许多研究领域的一项有前途的技术。最近，基于深度学习的方法为理解和执行HAR系统中的复杂数据的分析铺平了新的道路。然而，这些方法的性能主要取决于所收集数据的质量和数量。在本文中，我们创新性地提出了建立一个基于虚拟IMU的大型数据库，然后通过引入一个由三个技术部分组成的多域深度学习框架来解决技术问题。在第一部分中，我们提出了学习的单帧人类活动的噪声IMU数据与混合卷积神经网络（CNN）在半监督的形式。第二部分根据不确定性感知一致性原则对提取的数据特征进行融合，通过对特征重要性进行加权来降低不确定性。最后一部分基于最新发布的运动捕捉存档数据集（Archive of Motion Capture as Surface Practice，AMASS）进行迁移学习，该数据集包含丰富的合成人体姿态，增强了训练数据集的多样性，有利于该方法的训练和特征迁移过程。在实际的深惯性波（DIP）数据集上，验证了该方法的有效性。实验结果表明，所提出的方法可以令人惊讶地收敛在几个迭代和优于所有竞争的方法。
HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDAR
Xiamen University（厦门大学）；School of Informatics, Xiamen University（厦门大学信息学院）；Fujian Key Laboratory of Sensing and Computing for Smart Cities（福建省智慧城市感知与计算重点实验室）；School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）
Robotic Classification of Divers' Swimming States using Visual Pose Keypoints as IMUs
Department of Computer Science & Engineering（计算机科学与工程系）；Minnesota Robotics Institute (MnRI)（明尼苏达州机器人研究所）；University of Minnesota–Twin Cities（明尼苏达大学-双城分校）；Department of Computer Science（计算机科学系）；Carnegie Mellon University（卡内基梅隆大学）
Decomposing and Fusing Intra- and Inter-Sensor Spatio-Temporal Signal for Multi-Sensor Wearable Human Activity Recognition
School of Big Data and Software Engineering, Chongqing University（重庆大学大数据与软件学院）；Center for Data Science, Peking University（北京大学数据科学中心）；School of Mathematical Sciences, Peking University（北京大学数学科学学院）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）
A Deep Learning Method for Complex Human Activity Recognition Using Virtual Wearable Sensors
Shanghai Jiao Tong University（上海交通大学）；School of Electrical Information and Electrical Engineering（电子信息与电气工程学院）；Shanghai Key Laboratory of Navigation and Location-based Services（上海市导航与位置服务重点实验室）
GAITEX: Human motion dataset of impaired gait and rehabilitation exercises using inertial and optical sensors
AI for Sensor Data Analytics Research Group（人工智能传感器数据解析研究组）；Ulm University of Applied Sciences（乌尔姆应用科学大学）；Biomechatronic Research Group（生物机械研究组）；Institute of Computer Science（计算机科学研究所）
Spatial-Related Sensors Matters: 3D Human Motion Reconstruction Assisted with Textual Semantics
Beijing Advanced Innovation Center for Materials Genome Engineering（北京材料基因组工程先进创新中心）；University of Science and Technology Beijing（北京科技大学）；Key Laboratory of Intelligent Bionic Unmanned Systems, Ministry of Education（智能仿生无人系统教育部重点实验室）；Institute of Materials Intelligent Technology, Liaoning Academy of Materials（辽宁材料实验室材料智能技术研究所）
AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild
The University of New South Wales（新南威尔士大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）
Sensor Data Augmentation from Skeleton Pose Sequences for Improving Human Activity Recognition
Saarland University（萨尔大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；RPTU Kaiserslautern-Landau（凯撒斯劳滕-兰道莱茵-普法尔茨技术大学）；Seoul National University of Science and Technology（首尔科学技术大学）
HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional Mamba
School of Computer Science, University of South China（南华大学计算机学院）；School of Computer Science and Technology, Dalian University of Technology（大连理工大学计算机科学与技术学院）；Department of Computer & Communication Engineering, University of Science and Technology Beijing（北京科技大学计算机与通信工程学院）；School of Computing, Ulster University（阿尔斯特大学计算学院）
Paving the Way Towards Kinematic Assessment Using Monocular Video: A Preclinical Benchmark of State-of-the-Art Deep-Learning-Based 3D Human Pose Estimators Against Inertial Sensors in Daily Living Activities
