PulseAugur
EN
LIVE 23:20:32

AI models struggle with realistic Earth Observation image distortions

A new research paper introduces an enhanced image simulator to generate realistic Earth Observation (EO) imagery degraded by atmospheric turbulence and satellite pointing errors. The study evaluates the performance of YOLOv8 and RetinaNet models on vessel detection tasks using this simulated data. Results indicate that YOLOv8's recall significantly drops under degraded conditions, while RetinaNet shows greater robustness, maintaining higher recall. AI

IMPACT Highlights the need for more robust AI models trained on realistic environmental conditions for reliable Earth Observation applications.

RANK_REASON The cluster contains an academic paper detailing a new simulation method and evaluating existing AI models.

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 English(EN) · Celia S\'anchez-de-Miguel, Antonio M. Mercado-Mart\'inez, Beatriz Soret, Antonio Jurado-Navas, Miguel Castillo-V\'azquez ·

    Impact of Atmospheric Turbulence and Pointing Error on Earth Observation

    arXiv:2605.22268v1 Announce Type: cross Abstract: Earth Observation (EO) imagery is often degraded by atmospheric turbulence and pointing jitter; yet, these effects are rarely considered in datasets used to train AI-based detection models. Based on prior work, this paper presents…

  2. arXiv cs.CV TIER_1 English(EN) · Miguel Castillo-Vázquez ·

    Impact of Atmospheric Turbulence and Pointing Error on Earth Observation

    Earth Observation (EO) imagery is often degraded by atmospheric turbulence and pointing jitter; yet, these effects are rarely considered in datasets used to train AI-based detection models. Based on prior work, this paper presents an enhanced image simulator that enables the inco…