What question did this study set out to answer?

This research focuses on developing a YOLOv11-based model for automated detection of road damage in real-time.

December 19, 2025bit-TechOpen Access

Real-Time Identification of Potholes and Road Damage Using Yolov11

View Full Paper

Ask AI

Bookmark

Authors

MAMuh Ryamizard AlbasithUniversitas Teknologi Yogyakarta MFMuhammad FachrieUniversitas Tidar

Discussion

Member takes

Implication

Model demonstrates high accuracy and low latency in detecting road defects like potholes and cracks in mobile environments, suggesting efficiency in road maintenance.

Key Points

This research focuses on developing a YOLOv11-based model for automated detection of road damage in real-time.
Developed a detection model using YOLOv11 for Android devices.
Analyzed four defect classes: potholes, cracks, surface waviness, and patched roads.
Collected and annotated 2,989 road images from public datasets for evaluation.
Used evaluation metrics including AP@0.5, confusion matrix, and latency benchmarks.
YOLOv11 achieved high AP@0.5 scores of 0.849 for cracked roads and 0.850 for patched roads.
Real-time inference latency was measured at 2.6 ms per image, outperforming YOLOv8.
Integration into an Android application demonstrated robust real-time performance.

Cite This Study

Albasith et al. (2025) studied this question.

synapsesocial.com/papers/69449a892f0218eca95082c1 https://doi.org/10.32877/bt.v8i2.3371

View Full Paper

Ask AI

Bookmark

Implication

Model demonstrates high accuracy and low latency in detecting road defects like potholes and cracks in mobile environments, suggesting efficiency in road maintenance.

Real-Time Identification of Potholes and Road Damage Using Yolov11

Discussion

Member takes

Implication

Key Points

Cite This Study

Real-Time Identification of Potholes and Road Damage Using Yolov11

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider