A Time-Efficient Complementary Kalman Gain Filter Derived From Extended Kalman Filter and Used for Magnetic and Inertial Measurement Units

Rong, Hailong; Peng, Cuiyun; Chen, Yang; Lv, Jidong; Zou, Ling

doi:10.1109/jsen.2022.3217058

Cited by 3 publications

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The module extrapolates the orientation of the IMU linked to the body segment 𝐴𝐵, 𝑂𝑅𝐼 𝐼 𝑀𝑈 𝐴𝐵 = 𝜙 𝐼 𝑀𝑈 𝐴𝐵 , 𝜃 𝐼 𝑀𝑈 𝐴𝐵 , 𝜓 𝐼 𝑀𝑈 𝐴𝐵 by employing a complementary filter [12] on the acceleration and angular velocity concerning the world reference system. To prevent interference in indoor settings, the magnetometer signal is disregarded (𝜓 𝐼 𝑀𝑈 𝐴𝐵 = 0).…”

Section: A Feature Extractionmentioning

confidence: 99%

Combining 3-D Human Pose Estimation and IMU Sensors for Human Identification and Tracking in Multiperson Environments

Marchi,

Turetta,

Pravadelli

et al. 2024

IEEE Sens. Lett.

View full text Add to dashboard Cite

Human pose estimation (HPE) based on deep neural networks (DNN) aims to predict the poses of human body in videos without needing markers. One of the main limitations in its applicability is consistently identifying and tracking the keypoints of an individual in multi-person scenarios. Despite various solutions based on image analysis being attempted, challenges such as model accuracy, occlusions, or individuals exiting the camera's field of view often result in the loss of the association between humans and their keypoints across video frames. In this article, we propose a human identification and tracking methodology in multi-person environments based on data fusion between HPE software and wearable IMU sensors. We demonstrate how to align the data generated by these two sensor categories (camera-based HPE and IMUs) and assess the alignment between each skeleton of keypoints and IMU pair using a scoring system. Additionally, we illustrate how to combine different metrics, such as orientation, acceleration, and velocity, to address alignment problems caused by inaccuracies in sensor data.

show abstract

Section: A Feature Extractionmentioning

confidence: 99%