Scholarlink

<p>The use of human damage assessments and expert subjective guilt determinations in modern traffic accident management leads to systemic inefficiencies, which provoke impacted drivers and extend resolution timelines. To overcome these obstacles, this study introduces DeepOntoAccident, an intelligent system that transforms accident reporting by combining semantic reasoning with cutting-edge computer vision. Fundamentally, our system uses an optimized SSD-MobileNet-V2 architecture to identify and categorize vehicle damage into 18 different categories that record location, severity, and impacted components, with remarkable performance (94.7% accuracy, 97.7% mAP). The system’s ontological reasoning architecture, which places visual data within defined traffic norms and environmental variables using SWRL rules, is what truly innovates beyond just recognizing damage. This approach enables culpability reasoning (via a 5-level scale) by integrating contextual factors (weather/environment) and fraudulent driver behaviors, using the identified damage types as evidence. The framework aligns deep learning with ontological reasoning and SWRL rules, producing auditable reasoning chains and nuanced culpability assessments that imitate expert decision-making. The resultant technology addresses major challenges for insurance companies and traffic authorities, such as Saudi Arabia’s Najm services, by cutting processing times from hours to minutes and introducing unprecedented transparency and consistency to accident investigations. Our work establishes a new paradigm for automated accident management, bridging the gap between regulatory-aware reasoning and data-driven pattern recognition while balancing computational efficiency with explainable, legally grounded outcomes.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Towards transparent and efficient accident resolution: a hybrid deep learning–ontology framework for automated damage detection and culpability reasoning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月16日

查看全文
  • Sonia Lajmi

摘要

The use of human damage assessments and expert subjective guilt determinations in modern traffic accident management leads to systemic inefficiencies, which provoke impacted drivers and extend resolution timelines. To overcome these obstacles, this study introduces DeepOntoAccident, an intelligent system that transforms accident reporting by combining semantic reasoning with cutting-edge computer vision. Fundamentally, our system uses an optimized SSD-MobileNet-V2 architecture to identify and categorize vehicle damage into 18 different categories that record location, severity, and impacted components, with remarkable performance (94.7% accuracy, 97.7% mAP). The system’s ontological reasoning architecture, which places visual data within defined traffic norms and environmental variables using SWRL rules, is what truly innovates beyond just recognizing damage. This approach enables culpability reasoning (via a 5-level scale) by integrating contextual factors (weather/environment) and fraudulent driver behaviors, using the identified damage types as evidence. The framework aligns deep learning with ontological reasoning and SWRL rules, producing auditable reasoning chains and nuanced culpability assessments that imitate expert decision-making. The resultant technology addresses major challenges for insurance companies and traffic authorities, such as Saudi Arabia’s Najm services, by cutting processing times from hours to minutes and introducing unprecedented transparency and consistency to accident investigations. Our work establishes a new paradigm for automated accident management, bridging the gap between regulatory-aware reasoning and data-driven pattern recognition while balancing computational efficiency with explainable, legally grounded outcomes.