.png)
MYCD: Integration of YOLO-CNN and DenseNet for Real-Time Road Damage Detection Based on Field Images
Abstract
Road damage such as cracks, potholes, and uneven surfaces poses serious risks to transportation safety, logistics efficiency, and maintenance budgeting in Indonesia. Manual inspection is time consuming, labor intensive, and prone to error, motivating the use of reliable computer vision solutions. This study proposes MYCD, a hybrid and mobile ready architecture that combines the fast detection ability of YOLO with the dense feature reuse of DenseNet, enhanced by the Convolutional Block Attention Module (CBAM) for spatial and channel focus and Spatial Pyramid Pooling (SPP) for multi scale context understanding. The system detects and classifies the severity of road damage into minor, moderate, and severe categories using images captured by standard cameras. MYCD was trained and validated on 1,120 field images using an 80/20 split to simulate realistic deployment. Validation achieved 64 percent accuracy, with the highest per class precision of 0.72 for minor damage and mAP@0.5 = 0.677. The confusion matrix showed that most errors occurred in the moderate category because of visual similarity with minor and severe damage. Unlike earlier studies that extended YOLO with heavy backbones such as ResNet or EfficientNet, MYCD focuses on feature propagation (DenseNet), attention precision (CBAM), and multi scale fusion (SPP) optimized for real time operation on standard hardware. Efficiency profiling confirmed its deployability. After compression, the model size is 46.8 MB and it requires 3.7 GFLOPs per inference at 640×640 resolution. On a mid-range Android device (Snapdragon 778G, 8 GB RAM), MYCD runs at 19 frames per second with 1.2 GB peak memory. Compared with YOLOv8 WD (68 MB; 5.2 GFLOPs), MYCD reduces computation by 31 percent while maintaining similar accuracy. Overall, MYCD achieves a practical balance of speed, accuracy, and efficiency, providing a deployable and reproducible framework for real time road damage detection in resource limited settings.
Keywords
Full Text:
PDFReferences
A. Kurniawan, A. Patriadi, and S. Sajiyo, “Analysis of the Correspondence Between the Type of Road Damage and the Budget Costs Incurred in Handling on Provincial Roads in the Madura Region,” International Journal of Mechanical, Electrical and Civil Engineering, vol. 2, no. 1, pp. 149–156, Jan. 2025, doi: 10.61132/ijmecie.v2i1.140.
Surodjo, V. D. Purnomo, S. A. Kadir, and B. H. C. Handoyo, “Analysis of Traffic Accidents Due to Road Damage,” Formosa Journal of Multidisciplinary Research, vol. 2, no. 1, pp. 17–40, Jan. 2023, doi: 10.55927/fjmr.v2i1.2377.
X. Yang, J. Zhang, W. Liu, J. Jing, H. Zheng, and W. Xu, “Automation in road distress detection, diagnosis and treatment,” Journal of Road Engineering, vol. 4, no. 1, pp. 1–26, Mar. 2024, doi: 10.1016/j.jreng.2024.01.005.
J. Wang et al., “Road defect detection based on improved YOLOv8s model,” Sci Rep, vol. 14, no. 1, pp. 1–21, Dec. 2024, doi: 10.1038/s41598-024-67953-3.
G. Kim and S. Kim, “A Road Defect Detection System Using Smartphones,” Sensors, vol. 24, no. 7, pp. 1–21, Apr. 2024, doi: 10.3390/s24072099.
A. Alrajhi, K. Roy, L. Qingge, and J. Kribs, “Detection of Road Condition Defects Using Multiple Sensors and IoT Technology: A Review,” IEEE Open Journal of Intelligent Transportation Systems, vol. 4, pp. 372–392, 2023, doi: 10.1109/OJITS.2023.3237480.
T. Li and G. Li, “Road Defect Identification and Location Method Based on an Improved ML-YOLO Algorithm,” Sensors, vol. 24, no. 21, pp. 1–15, Nov. 2024, doi: 10.3390/s24216783.
Ö. Kaya and M. Y. Çodur, “Automatic detection and classification of road defects on a global-scale: Embedded system,” Measurement (Lond), vol. 243, pp. 1–19, Feb. 2025, doi: 10.1016/j.measurement.2024.116453.
W. Zhou, Y. Zhan, H. Zhang, L. Zhao, and C. Wang, “Road defect detection from on-board cameras with scarce and cross-domain data,” Autom Constr, vol. 144, pp. 1–12, Dec. 2022, doi: 10.1016/j.autcon.2022.104628.
M. A. Benallal and M. S. Tayeb, “An image-based convolutional neural network system for road defects detection,” IAES International Journal of Artificial Intelligence, vol. 12, no. 2, pp. 577–584, Jun. 2023, doi: 10.11591/ijai.v12.i2.pp577-584.
J. Ren, H. Zhang, and M. Yue, “YOLOv8-WD: Deep Learning-Based Detection of Defects in Automotive Brake Joint Laser Welds,” Applied Sciences (Switzerland), vol. 15, no. 3, pp. 1–18, Feb. 2025, doi: 10.3390/app15031184.
F. X. Ru, M. A. Zulkifley, S. R. Abdani, and M. Spraggon, “Forest Segmentation with Spatial Pyramid Pooling Modules: A Surveillance System Based on Satellite Images,” Forests, vol. 14, no. 2, pp. 1–20, Feb. 2023, doi: 10.3390/f14020405.
G. Lin, F. Chen, Z. Zhang, A. Zhang, X. Wang, and C. Zhou, “DenseNeXt: An Efficient Backbone for Image Classification,” in 2023 15th International Conference on Advanced Computational Intelligence, ICACI 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ICACI58115.2023.10146197.
Y. Hou, Z. Wu, X. Cai, and T. Zhu, “The application of improved densenet algorithm in accurate image recognition,” Sci Rep, vol. 14, no. 1, pp. 1–14, Dec. 2024, doi: 10.1038/s41598-024-58421-z.
J. Zhang et al., “A Low‐Grade Road Extraction Method using SDG‐DenseNet Based on the Fusion of Optical and SAR Images at Decision Level,” Remote Sens (Basel), vol. 14, no. 12, pp. 1–25, Jun. 2022, doi: 10.3390/rs14122870.
A. R. Priambodo and C. Fatichah, “Leveraging Convolutional Block Attention Module (Cbam) For Enhanced Performance In Mobilenetv3-Based Skin Cancer Classification,” Jurnal Teknik Informatika (Jutif), vol. 6, no. 3, pp. 1389–1404, Jun. 2025, doi: 10.52436/1.jutif.2025.6.3.4546.
S. Agac and O. Durmaz Incel, “On the Use of a Convolutional Block Attention Module in Deep Learning-Based Human Activity Recognition with Motion Sensors,” Diagnostics, vol. 13, no. 11, pp. 1–21, Jun. 2023, doi: 10.3390/diagnostics13111861.
Z. Ji et al., “CBAM-DeepConvNet: Convolutional Block Attention Module-Deep Convolutional Neural Network for asymmetric visual evoked potentials recognition,” Brain-Apparatus Communication: A Journal of Bacomics, vol. 4, no. 1, pp. 1–27, Dec. 2025, doi: 10.1080/27706710.2025.2489396.
C. Dewi and H. Juli Christanto, “Combination of Deep Cross-Stage Partial Network and Spatial Pyramid Pooling for Automatic Hand Detection,” Big Data and Cognitive Computing, vol. 6, no. 3, pp. 1–19, Sep. 2022, doi: 10.3390/bdcc6030085.
J. Li et al., “Improved Neural Network with Spatial Pyramid Pooling and Online Datasets Preprocessing for Underwater Target Detection Based on Side Scan Sonar Imagery,” Remote Sens (Basel), vol. 15, no. 2, pp. 1–27, Jan. 2023, doi: 10.3390/rs15020440.
A. Jaikumar and S. C. Sangapu, “Early-Stage Diabetic Retinopathy Diagnosis with Feature Pyramid Networks and Spatial Pyramid Pooling Utilizing Full-Field Optical Coherence Tomography (FF-OCT),” Journal of Computational and Cognitive Engineering, pp. 1–13, May 2025, doi: 10.47852/bonviewjcce52024763.
A. Ashiquzzaman, H. Lee, K. Kim, H. Y. Kim, J. Park, and J. Kim, “Compact spatial pyramid pooling deep convolutional neural network based hand gestures decoder,” Applied Sciences (Switzerland), vol. 10, no. 21, pp. 1–22, Nov. 2020, doi: 10.3390/app10217898.
DOI: https://doi.org/10.47738/jads.v7i1.1040
Refbacks
- There are currently no refbacks.
Journal of Applied Data Sciences
| ISSN | : | 2723-6471 (Online) |
| Publisher | : | Bright Publisher |
| Website | : | http://bright-journal.org/JADS |
| : | taqwa@amikompurwokerto.ac.id (principal contact) | |
| support@bright-journal.org (technical issues) |
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0