Inertial Measurement Unit
PulseAugur coverage of Inertial Measurement Unit — every cluster mentioning Inertial Measurement Unit across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New method improves zero-shot human activity recognition
Researchers have developed a new method to improve zero-shot learning for human activity recognition using inertial measurement unit (IMU) data. Their approach focuses on bridging the gap between sensor data and semanti…
-
New OLIVE framework enables adaptive exoskeleton control
Researchers have developed OLIVE, a novel framework for online learning in wearable exoskeletons. This system efficiently adapts exoskeleton control to individual users and dynamic environments by updating only a low-ra…
-
New methods enhance motion tracking with improved inertial odometry
Researchers have developed two new methods to improve inertial odometry, a technique for tracking motion using only inertial measurement units (IMUs). The first method, MARIO, integrates a learned pose prior based on hu…
-
Ultra Diffusion Poser improves human motion tracking with UWB and IMU data
Researchers have developed Ultra Diffusion Poser, a new diffusion model for human motion tracking that integrates data from sparse inertial sensors and ultra-wideband (UWB) ranging. This model explicitly accounts for th…
-
New IMU-based handwriting recognition model shows improved writer independence
Researchers have developed a new model for writer-independent handwriting recognition using IMU data, addressing the challenge of varying writing styles. The model, which employs a CNN encoder and a BiLSTM-based decoder…
-
New model advances behavioral recognition from AR glasses sensors
Researchers have developed a new method for recognizing complex human behaviors using data from head-mounted Inertial Measurement Units (IMUs), commonly found in AR smart glasses. They created a large dataset and a hier…
-
New AVI-HT method improves 3D hand tracking with vision-IMU fusion
Researchers have developed AVI-HT, a novel approach for 3D hand tracking that adaptively fuses data from on-glove IMU sensors and egocentric cameras. This method significantly enhances accuracy and availability, especia…
-
AnyMo framework enables setup-agnostic human motion modeling
Researchers have developed AnyMo, a novel framework designed to overcome the setup-dependency challenges in modeling human motion from wearable inertial measurement units (IMUs). The system utilizes physics-grounded sim…
-
New benchmark and method tackle low-light, shaky camera action recognition
Researchers have introduced DarkShake-DVS, a new benchmark dataset designed for human action recognition in challenging low-light and high-motion scenarios. The dataset includes over 18,000 real-world clips captured wit…
-
New benchmark tackles UAV detection with event cameras in motion
Researchers have introduced M$^2$E-UAV, a new benchmark and analysis framework designed to tackle the challenge of detecting small UAVs using onboard event cameras, particularly in complex motion-on-motion scenarios. Th…
-
Motion-MLLM enhances 3D scene understanding with egomotion data
Researchers have developed Motion-MLLM, a new framework that integrates egomotion data from Inertial Measurement Units (IMUs) with video to enhance Multimodal Large Language Models (MLLMs) for 3D scene understanding. Th…
-
Autonomous vehicle fuses sonar and GPS for precise seabed mapping
Researchers have developed a new framework for seabed mapping in challenging shallow, turbid waters using autonomous surface vehicles. This system fuses sonar data with GPS and IMU readings, employing Fourier-Mellin tra…
-
TACO pipeline fuses IMU and cross-view geo-localization for precise navigation
Researchers have developed TACO, a new pipeline that tightly integrates Inertial Measurement Unit (IMU) data with fine-grained Cross-View Geo-localisation (CVGL) for precise positioning without continuous GNSS signals. …
-
New HARMES dataset combines motion, environmental, and audio data for activity recognition
Researchers have introduced HARMES, a new multi-modal dataset for wearable human activity recognition. The dataset combines motion sensing, environmental data, and audio from wrist-worn devices, totaling over 80 hours o…