PulseAugur
EN
LIVE 23:29:31

New method enhances crowd counting in low-light conditions · 2 sources tracked

By PulseAugur Editorial · [3 sources] ·

Researchers have developed a new method for counting crowds in low-light conditions, an area that has been underexplored. The approach introduces three new datasets: SHA_Dark, SHB_Dark, and LC-Crowd. It utilizes Retinex-based modeling with depth and edge cues to enhance reflectance representations and proposes a Multi-Modal Hyper-Graph Fusion module to integrate RGB appearance, depth geometry, and edge structure. Additionally, a Deformable Rectangular Sparse Attention module is introduced to optimize computation for dense predictions, leading to a unified Low-Light Counting Network (LCNet) that reportedly outperforms existing state-of-the-art methods. AI

IMPACT This research could improve surveillance and analysis in challenging low-light environments.

RANK_REASON The cluster contains an academic paper detailing a new method and datasets for a computer vision task.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

New method enhances crowd counting in low-light conditions · 2 sources tracked

COVERAGE [3]

  1. arXiv cs.AI TIER_1 English(EN) · Hao-Yuan Ma, Li Zhang, Yushi Qiu, Jie Gao, Yan Zhang, Bangjun Wang ·

    Multi-Modal Hyper-Graph Fusion for Low-Light Crowd Counting

    arXiv:2606.18566v1 Announce Type: cross Abstract: Crowd counting is a fundamental task in computer vision. However, crowd counting in low-light environments remains largely underexplored, despite its practical importance in the real world. Existing methods mainly focus on well-li…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    Multi-Modal Hyper-Graph Fusion for Low-Light Crowd Counting

    Crowd counting is a fundamental task in computer vision. However, crowd counting in low-light environments remains largely underexplored, despite its practical importance in the real world. Existing methods mainly focus on well-lit scenes or rely on single-modality Red-Green-Blue…

  3. arXiv cs.CV TIER_1 English(EN) · Bangjun Wang ·

    Multi-Modal Hyper-Graph Fusion for Low-Light Crowd Counting

    Crowd counting is a fundamental task in computer vision. However, crowd counting in low-light environments remains largely underexplored, despite its practical importance in the real world. Existing methods mainly focus on well-lit scenes or rely on single-modality Red-Green-Blue…

RELATED TOPICS