Researchers Release Multi-View In-Cabin Monitoring Dataset for Public Transport Vehicles
Computer scientists have introduced a new dataset for monitoring the interiors of public transportation vehicles, featuring synchronized RGB and depth images from multiple cameras and LiDAR sensors installed in a German city bus. The dataset contains over 9,000 annotated samples with 3D human pose estimates and bounding boxes for occupants, along with calibration tools and benchmarks for detection models. The resource aims to support development of perception systems for automated public transport monitoring and safety applications.
Researchers have created a multi-view in-cabin monitoring dataset designed to advance computer vision systems for public transportation vehicles. The dataset was collected from a digitalized German city bus equipped with four inward-facing RGB and depth cameras plus a rotating LiDAR system, capturing 9,136 synchronized samples with full annotations. The accompanying infrastructure includes a calibration pipeline, pseudo-labeling methods for generating 3D human pose estimates and oriented 3D bounding boxes for vehicle occupants, and conversion tools to the nuScenes format for standardized benchmarking. The authors evaluated representative multi-view 3D detection models including Lift-Splat-Shoot and BEVFusion to establish performance baselines. The dataset and associated tools have been made publicly available to support comparative evaluation and training of multi-view in-cabin perception models for the transportation sector.
What different sources said
- arXiv cs.AICenter
Multi-View In-Cabin Monitoring System for Public Transport Vehicles
Related
Genetic Drift, Not Selection, Drives Rapid Feather Color Evolution in Island Bird Radiation
A new study of an island bird radiation found that rapid evolution of feather coloration is driven primarily by genetic drift in small populations rather than sexual or ecological selection. The research integrated whole-genome data with detailed plumage measurements across complete species sampling to test whether signaling trait evolution correlates with speciation rates. The findings suggest that neutral demographic processes play a central role in generating phenotypic diversity during island radiations, challenging assumptions about the mechanisms driving rapid evolution.
New AI Model Improves Prediction of Therapeutic Peptide Function from Protein Sequences
Researchers developed a lightweight CNN classifier that predicts whether peptide sequences have therapeutic properties, trained on a database of 54,655 peptides across 48 functional categories. The model uses a novel negative sampling strategy to reduce false positive rates from over 60% in previous approaches to 2.1%. This advancement could accelerate drug discovery by enabling faster computational screening of peptide candidates before expensive experimental testing.
Study Shows Different Metabolic Stress Models Produce Distinct Effects on Human Neuronal Networks
Researchers tested three common in vitro metabolic stress models on human-derived neuronal networks and found each produced different patterns of neuronal activity and cell damage. The models tested were hypoxia alone, oxygen-glucose deprivation (OGD), and hypoxia combined with glutamate exposure. The findings suggest that choice of experimental model significantly affects results and that combining electrophysiological and structural analyses is important for accurately assessing metabolic stress in stroke research.