Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : signal and image processing letters

Classification of Road Damage in Sidoarjo Using CNN Based on Inception Resnet-V2 Architecture Zahrah, Fathima; Diyasa, I Gede Susrama Mas; Saputra, Wahyu Syaifullah Jauharis
Signal and Image Processing Letters Vol 7, No 1 (2025)
Publisher : Association for Scientific Computing Electrical and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/simple.v7i1.123

Abstract

Road damage is a serious issue in Sidoarjo Regency, posing risks to road users' safety. This study aims to classify road surface conditions using a Convolutional Neural Network (CNN) model based on the Inception ResNet-V2 architecture. The research develops an image-based classification model by combining secondary data from Kaggle and primary data obtained through Google Street View API scraping, along with training strategies such as data augmentation, class balancing, early stopping, and model checkpointing. A total of 885 images were used, categorized into three classes: potholes, cracks, and undamaged roads. The model was trained over 20 epochs with early stopping triggered at epoch 15, when validation accuracy reached 95.95%. Evaluation on the test set showed a test accuracy of 83%. The undamaged road class achieved the highest performance with an F1-score of 0.89, while the pothole class recorded an F1-score of 0.79. The lowest performance was observed in the cracked road class, with an F1-score of 0.65, indicating the model's limited ability to detect fine crack features. This limitation is likely due to class imbalance and visual similarity between classes. Although the model demonstrated good generalization for the two majority classes, the performance gap between validation and test accuracy highlights the need to improve detection for minority classes. Future work is recommended to explore advanced augmentation techniques, increase the representation of minority class data, and consider alternative architectures or ensemble methods to enhance the model’s sensitivity to subtle road damage features.
Co-Authors Abdillah, Indah Rahma Agus Arifin, Agus Agus Zainal Arifin Ahmad Adiib Aminullah Alfan Rizaldy Pratama Alfath Daryl Alhajir Alyssa Amorita Azzah Amelia, Meisya Vira Amellia Harmaimun Hidayah Aminullah, Ahmad Adiib Amri Muhaimin Andry Syva Maldini Anniswa, Iqbal Ramadhan Anny Yuniarti Aurora Prameswaty, Almira Aviolla Terza Damaliana Aviolla Terza Damaliana Aziz, Rizky Dandi Nur Faizi Diana Novitasari Diyasa, I Gede Susrama Mas Dwi Arman Prasetya Dwi Arman Prasetya Eva Yulia Puspaningrum Faris Nur Tsani Firza Prima Aditiawan Gunawan, Ellexia Leonie Hanif Assalmi, Fityan Herdianti, Rahmalia Anindya I Gede Susrama Mas Diyasa I Gede Susrama Mas Diyasa idhom, Mohammad Indira Iqbal Ramadhan Anniswa Kartika Maulida Hindrayani Kemal Fahreza Jibran Jibran Made Hanindia Prami Swari Mahardhika, Rivaldi Dwi Maulana, Hendra Maulidya Prastita Syah Maurisa Arimbi Putri Meisya Vira Amelia Mohammad Idhom Mohammad Idhom Muhaimin, Amri Muhammad Hakam Fardana Naomi Dwi Anggraini Nashrullah, Ahmad Firqi Ningrum, Lisya Septyo Parlika, Rizky Prismahardi Aji Riyantoko Putra, Chrystia Aji Putri, Milla Akbarany Bakhtiar Renaldy Al Ikhsan Reza Putri Angga Riswanda, Mohammad Nizar Rizkiyah, Selly Rusdiyanto, Nur Rahmat Safira Kusmindasari, Anggun Salsabila, Nada Sefilah Naurah Sabela1 Shindi Shella May War Shindi Shella May Wara Sinthya Putri, Diana Steffany Marcellia Witanto Suprapto, Claudia Millennia Susrama Mas Diyasa, I Gede Taruna Ardianto Tiara Valentina Tresna Maulana Fahrudin Trimono Trimono Trimono, Trimono Yisti Vita Via Zahrah, Fathima