Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 31, 2025

YOLO-ROC: A High-Precision and Ultra-Lightweight Model for Real-Time Road Damage Detection

View Full Paper
Ask AI
Bookmark
Share

Authors

ZLZicheng LinPeking UniversityWPWeichao PanShandong Jianzhu University

Discussion

Loading...

Member takes

Implication

YOLO-ROC improves road damage detection accuracy in various targets, reducing complexity and enhancing performance.

Key Points

  • YOLO-ROC addresses road damage detection challenges with enhanced multi-scale feature extraction.
  • The model reduces parameter count from 3.01M to 0.89M, optimizing computational efficiency.
  • BMS-SPPF module boosts detection of small-scale damage, improving mAP50 by 2.11% over YOLOv8n.
  • YOLO-ROC's effectiveness is validated through benchmarking on RDD2022 China Drone dataset and others.

Cite This Study

Lin et al. (2025) studied this question.

synapsesocial.com/papers/689a094be6551bb0af8cf4a0https://doi.org/10.21203/rs.3.rs-7221917/v1
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Feature Pyramid Networks for Object Detection2017 · 30,017 citations
  2. 2A Deep Learning-Based Approach for Road Surface Damage Detection2022 · 31 citations
  3. 3ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices2018 · 9,327 citations
  4. 4You Only Look Once: Unified, Real-Time Object Detection2016 · 51,579 citations