RGB cameras
PulseAugur coverage of RGB cameras — every cluster mentioning RGB cameras across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
Kineo pipeline enables calibration-free metric motion capture from sparse RGB cameras
Researchers have developed Kineo, a new pipeline for markerless motion capture that eliminates the need for precise camera calibration. This system uses sparse RGB cameras to simultaneously calibrate cameras and reconst…
-
New WorkIng Dataset Enhances AV Navigation in Highway Work Zones
Researchers have introduced WorkIng, a new benchmark dataset designed to improve autonomous vehicle navigation in highway work zones. This dataset includes both real-world and synthetic data, addressing the limitations …
-
Vision-language models struggle with fine-grained thermal activity recognition for robots
A new study published on arXiv investigates the performance of vision-language models (VLMs) when applied to thermal imagery for human activity understanding in human-robot interaction (HRI). The research found that whi…
-
Vision-language models struggle with fine-grained thermal activity recognition for robots
A new study evaluated seven vision-language models (VLMs) for their effectiveness in understanding human activities using thermal imagery for human-robot interaction (HRI). The research found that while these models can…
-
LiFR v2 framework enhances dense prediction with event camera fusion
Researchers have introduced LiFR v2, a novel framework designed for high-rate dense prediction using a combination of RGB cameras and event cameras. This system addresses the limitations of RGB cameras by leveraging the…
-
LICOA system treats projected light as embodied action for spatial AR
Researchers have developed LICOA, a system that treats projected light as an embodied action for mobile spatial augmented reality. LICOA uses a differential-drive chassis and a steerable mirror to control the projection…
-
New mmHRI framework uses radar for privacy-preserving robot interaction
Researchers have developed mmHRI, a novel framework for privacy-preserving human-robot interaction (HRI) that utilizes millimeter-wave (mmWave) radar instead of traditional RGB cameras. This approach addresses privacy c…
-
New markerless video analysis quantifies mouse tremor
Researchers have developed a novel, non-invasive method for quantifying pathological tremor in mouse models using only standard RGB cameras. This approach aims to overcome the limitations of existing methods like electr…
-
Gated Fusion Leads Multi-modal Activity Recognition on HARMES Dataset
Researchers have conducted a comparative study of seven sensor fusion techniques for multi-modal human activity recognition using the HARMES dataset. The study found that Gated Multi-modal Fusion achieved the highest pe…
-
New FEMOT dataset and FEMOTR framework advance multi-object tracking
Researchers have introduced FEMOT, a new dataset designed to advance multi-object tracking using both standard RGB cameras and bio-inspired event cameras. This dataset aims to overcome limitations of traditional cameras…
-
New compact model integrates multiple autonomous driving perception tasks
Researchers have developed a new compact deep learning model for autonomous driving that can perform multiple perception tasks simultaneously. This model integrates semantic segmentation, depth estimation, LiDAR segment…
-
New methods tackle 2D-3D cross-modal gait recognition
Two new research papers introduce novel approaches to cross-modal gait recognition, aiming to improve the identification of individuals across different sensing modalities like 2D cameras and 3D LiDAR. DiffCrossGait uti…
-
RadarSim uses camera data to improve radar simulation accuracy
Researchers have developed RadarSim, a novel differentiable renderer that simulates Doppler radar range images by utilizing the high angular resolution of RGB cameras. This approach initializes a neural field from camer…
-
Event-based cameras improve batting impact estimation accuracy
Researchers have developed a new framework using event-based cameras to accurately estimate the timing of batting impacts. This method addresses the limitations of traditional RGB cameras and IMUs by offering microsecon…
-
Event cameras detect liveness with 95% accuracy using eye dynamics
Researchers have explored using event cameras for face liveness detection, focusing on temporal ocular dynamics. Unlike traditional RGB cameras, event cameras capture asynchronous brightness changes with high temporal r…
-
New dataset 'ParkingScenes' released for autonomous parking research
Researchers have introduced ParkingScenes, a new multimodal dataset designed to improve autonomous parking systems. Built using the CARLA simulator, the dataset includes structured parking trajectories and synchronized …