Logo image
BRIDGE: Blur Adaptive Disaster Image Analysis by Geometric Transformation
會議論文集

BRIDGE: Blur Adaptive Disaster Image Analysis by Geometric Transformation

Ming Chung Lim 和 Yu-Hsun Lin
Conference proceedings (IEEE Workshop on Advanced Robotics and its Social Impacts.), 頁碼.1-6
17/07/2025
Web of Science ID: WOS:001569371900001

摘要

Adaptation models Analytical models Artificial intelligence Bridges Disasters Image analysis Image restoration Robustness Transformers Transforms
Disaster images are often corrupted by motion blur due to rapid capture during emergency escapes, which can mislead AI models and result in incorrect decisions. To address this challenge, we propose BRIDGE, a blur-adaptive spatial transformation module based on Spatial Transformer Networks (STN), designed to enhance pretrained image classifiers (e.g., SwinV2) without requiring image restoration or structural modification. BRIDGE dynamically transforms blurred inputs to improve classification robustness while preserving modularity. Experiments demonstrate that BRIDGE consistently outperforms existing baselines on both corrupted and restored disaster images across four tasks in the Crisis Image Benchmark dataset. Furthermore, given the growing deployment of rescue robots and UAVs in disaster response, our modular and cost-effective framework provides practical potential for integration into realtime robotic perception systems, since most on-board vision stacks rely on lightweight, plug-and-play modules.

相關連結

指標

1 檢視次數

詳細資料

Logo image