← Back to all news
arXiv Computer Vision By Dimitrios Bouzoulas, Pyry J\"appinen, Pejman Habibiroudkenar, Eerik Alamikkotervo, Risto Ojala

Stereo LWIR-RGB Automatic Labeling for Low-Light Camera-Based VRU Detection

Read the original on arXiv Computer Vision →

The paper introduces an automated pipeline for labeling vulnerable road users (VRUs) in low-light conditions using stereo LWIR-RGB image pairs. By sourcing labels from LWIR data, which highlights VRUs through body temperature, the method reduces hardware complexity compared to previous setups. Experiments on a Finnish dataset show that models trained on these auto-generated labels outperform off-the-shelf baselines and hand-labeled fine-tuned models on several metrics.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 7

E-RGB-D: Real-Time Event-Based Perception with Structured Light

The paper introduces E‑RGB‑D, a real‑time event‑based perception system that combines a Digital Light Processing projector with a monochrome event camera to produce RGB‑D data. By projecting structured light and capturing asynchronous brightness changes, the system can detect color and depth for each pixel, achieving a color detection speed of 1400 fps and a depth detection rate of 4 kHz. The approach enables frameless RGB‑D sensing and delivers colorful point clouds without compromising spatial resolution.

By Seyed Ehsan Marjani Bajestani, Giovanni Beltrame
computer-visionrobotics
More like this →
Hugging Face Trending Papers
5d ago

3L-D: A Low-Light Level Dataset from a Sensor-Agnostic, Alignment-Preserving Acquisition Framework

The paper introduces 3L-Dataset, a physically calibrated low‑light image and video dataset created with a modular, sensor‑agnostic acquisition framework. The test bench reproduces the Midavaine night‑level scale from full moon to overcast moonless night, covering visible to near‑infrared spectra across varied environments while ensuring sub‑pixel alignment across synchronized image sextuplets. The authors evaluate deep‑learning baselines on this dataset, highlighting trade‑offs between reconstruction fidelity, perceptual quality, and inference latency under severe photon starvation.

roboticsefficiencysafety
More like this →
arXiv Computer Vision
Oct 9

A Camera-Native Stereo VR180 Dataset

The paper introduces a new stereo VR180 dataset captured directly with Blackmagic URSA Cine Immersive cameras, comprising 1,211 samples (636 video clips and 575 stills). Each sample is provided in camera-native Blackmagic RAW, separate-eye fisheye HEVC, and half-equirectangular HEVC formats, along with factory lens calibration and conversion tools. The authors also demonstrate that native-fisheye coding requires significantly more bitrate than half-equirectangular coding for equivalent viewport quality across all tested clips.

By Linxuan Lu
More like this →