PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 5, 2026International Journal of Advanced Computer Science and Applications0 citationsOpen Access

A Real-Time Multi-Scale Feature Pyramid YOLO Architecture for Accurate and Deployment-Efficient Road Damage Detection

OOOlzhas OlzhayevBKBakhytzhan KulambayevNSNurly Sakenkyzy

Key Points

  • To develop a real-time YOLO architecture that improves accuracy and efficiency in detecting various road damages.
  • Developed a Multi-Scale Feature Pyramid YOLO architecture.
  • Integrated hierarchical feature extraction with bidirectional multi-scale fusion.
  • Employed a decoupled detection head for enhanced classification and localization.
  • Applied focal loss and small-object emphasis to tackle class imbalance and fine-grained detection.
  • Conducted experiments using a multi-class road damage dataset and performed precision-recall analysis.
  • Achieved a mean Average Precision (mAP@0.5) of 0.68 and recall of 0.81.
  • Outperformed several existing real-time detection methods.
  • Confirmed effectiveness of multi-scale feature aggregation through ablation studies.
  • Qualitative results showed robust performance under various environmental conditions.

Abstract

Automated road damage detection has become a critical component of intelligent transportation systems, enabling timely infrastructure maintenance and enhanced traffic safety. However, detecting pavement defects such as cracks, potholes, and surface degradation remains challenging due to significant scale variation, irregular geometries, illumination changes, and class imbalance. This study proposes a real-time Multi-Scale Feature Pyramid YOLO architecture designed to achieve accurate and deployment-efficient multi-class road damage detection. The framework integrates hierarchical feature extraction with bidirectional multi-scale fusion to enhance sensitivity to both small and large defects. A decoupled detection head is employed to improve classification–localization balance, while focal loss and small-object emphasis mechanisms address class imbalance and fine-grained crack detection challenges. Comprehensive experiments conducted on a multi-class road damage dataset demonstrate that the proposed model achieves a mAP@0.5 of 0.68 and a recall of 0.81, outperforming several representative real-time detection approaches. Precision–recall analysis, confusion matrix evaluation, and ablation studies confirm the effectiveness of multi-scale feature aggregation and targeted optimization strategies. Qualitative results further illustrate robust detection performance under diverse environmental conditions. The proposed framework provides a practical trade-off between accuracy and computational efficiency, making it suitable for real-world deployment in intelligent road condition monitoring systems.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Olzhayev et al. (2026) studied this question.

synapsesocial.com/papers/69d1fcc0a79560c99a0a272fhttps://doi.org/10.14569/ijacsa.2026.0170350
Ask AI
Helpful
Bookmark
Share
View Full Paper