PulseAugur
EN
LIVE 20:23:49

New system enables real-time aerial person tracking on low-power hardware

Researchers have developed a novel system called EMTS-Det for real-time aerial person tracking on low-power hardware. This five-stage system estimates ego-motion, normalizes frame data, and uses a small, efficient network to detect and track individuals. The system achieves significantly higher frame rates and accuracy on resource-constrained devices like the Raspberry Pi Zero 2W compared to standard models like YOLOv8n, demonstrating its effectiveness in challenging real-world UAV video scenarios. AI

IMPACT Enables real-time AI-powered tracking on low-power drones, potentially for surveillance or autonomous navigation.

RANK_REASON Academic paper detailing a new computer vision system and its performance evaluation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New system enables real-time aerial person tracking on low-power hardware

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari ·

    Moving Like a Human: Ego-Motion-Normalized Temporal Signatures for Real-Time Aerial Person Tracking on Milliwatt-Class Hardware

    arXiv:2607.16282v1 Announce Type: new Abstract: Follow-me person tracking must run on the drone itself, where affordable companion computers offer only a few effective int8 GFLOP/s. At typical follow distances a person spans 10-60 pixels, indistinguishable from clutter and beyond…