Comparative Analysis of Yolov11 and Mask R-CNN Models for River Water Level Detection

Abiyyu Setrayana; Nurchim; Eko Purwanto

doi:10.47709/cnahpc.v7i3.6622

Authors

Abiyyu Setrayana Universitas Duta Bangsa Surakarta
Nurchim Universitas Duta Bangsa Surakarta
Eko Purwanto Universitas Duta Bangsa Surakarta

DOI:

https://doi.org/10.47709/cnahpc.v7i3.6622

Keywords:

Computer Vision, Detection, Mask R-CNN, Monitoring, Water Level, YOLOv11

Abstract

Flooding is one of the most frequent natural disasters in Indonesia, particularly in densely populated areas such as urban regions. The main cause is the delayed response in anticipating rising river water levels. One contributing factor is the continued use of manual river water monitoring systems. However, these systems often face challenges under various lighting and weather conditions. This study presents a comparison of two segmentation models, YOLOv11 and Mask R-CNN, for river water level detection. These models are evaluated for their application in real-time water level monitoring systems for dams and rivers under diverse lighting conditions. Data was gathered from publicly available sources, including river monitoring CCTV footage and social media content related to river activities, followed by annotation for model training. The YOLOv11 model, implemented using the Ultralytics framework and PyTorch library, achieved a mean Average Precision (mAP) at IoU (Intersection over Union) 50-95 of 99.657% and recall of 99.930%, demonstrating exceptional detection accuracy. The Mask R-CNN model, developed with Detectron2, attained an Average Precision (AP) at IoU 50-95 of 98.620% and a recall of 99.200%, also exhibiting high accuracy. Both models were tested in real-time scenarios, where they accurately detected water-level objects, although challenges arose under complex environmental conditions such as low light or water turbidity. To further enhance model performance, future work will focus on incorporating diverse environmental data and optimizing model parameters. In conclusion, YOLOv11 model offers higher accuracy and better resource efficiency, making it more suitable for real-time water level monitoring applications.

Downloads

Download data is not yet available.

References

Alifta Sulthoni, D. (2023). Pendeteksian Senjata Api pada Manusia dalam Situasi Real-Time Menggunakan Model YOLOv4-Tiny. In JURNAL ILMU KOMPUTER (Vol. 1, Issue 2). Desember.

Alkhalis, N., Haridhi, H. A., Maretna, N., Fadli, N., Haditiar, Y., Nanda, M., Ulfah, M., Handoko, K., Malayana, I., Safitri, A. C., Kuala, S., Aceh, B., Kelautan, K., Perikanan, D., & Korespondensi, P. (2024). IMPLEMENTASI MASK R-CNN PADA PERHITUNGAN TINGGI DAN LEBAR KARANG UNTUK MEMANTAU PERTUMBUHAN TRANSPLANTASI KARANG. 11(3), 603–614. doi: 10.25126/jtiik2024118374

Astanta, T., Saefullah, A., Ardianto, M., Pambudi, R., Ahhari, A., Saputri, H., & Tinggi Ilmu Ekonomi Ganesha, S. (2023). PERAN CLOSED CIRCUIT TELEVISION (CCTV) DALAM MENINGKATKAN KEAMANAN DI KAMPUS STIE GANESHA (Vol. 02, Issue 03).

Bayu Sasongko, T., & Amrullah, A. (2023). ANALISIS EFEK AUGMENTASI DATASET DAN FINE TUNE PADA ALGORITMA PRE-TRAINED CONVOLUTIONAL NEURAL NETWORK (CNN). 10(4), 763–768. doi: 10.25126/jtiik.2023106583

Budi, R., Harianto, R. A., & Setyati, E. (2023). Segmentasi Citra Area Tumpukan Sampah Dengan Memanfaatkan Mask R-CNN. Journal of Intelligent System and Computation, 5(1), 58–64. doi: 10.52985/insyst.v5i1.305

Cholissodin, I., Andy Soebroto, A., & Arif Rahman, M. (2021). Sistem Monitoring Aliran Sungai dan Lingkungan Berbasis Smart Environment di RW 03 Kelurahan Kauman Kota Malang (Monitoring System for River Flow and Environment Based on Smart Environment in RW 03 Kauman Village, Malang City). JAST?: Jurnal Aplikasi Sains Dan Teknologi, 5(1). doi: 10.33366/jast.v5i1

Darmawan, F. E., Khoerotul Magfiroh, S., Hanifah, M. K., & Saman, M. (2024). Examine the effectiveness of the mask R-CNN method, and keypoint R-CNN method in image object detection Menguji keefektifan metode mask R-CNN, dan metode keypoint R-CNN dalam deteksi objek citra. Jurnal Komputer Dan Teknologi Informasi, 2(2), 84–93. doi: 10.26714/jkti.v%vi%i.14084

Diwan, T., Anirudh, G., & Tembhurne, J. V. (2023). Object detection using YOLO: challenges, architectural successors, datasets and applications. Multimedia Tools and Applications, 82(6), 9243–9275. doi: 10.1007/s11042-022-13644-y

He, L., Zhou, Y., Liu, L., & Ma, J. (2024). Research and Application of YOLOv11-Based Object Segmentation in Intelligent Recognition at Construction Sites. Buildings, 14(12). doi: 10.3390/buildings14123777

Huda, M. M., Prasetyo, K. A., Ariel, M., Vieri, R., Wulanningrum, R., Dusea, A., & Dara, W. (2025). Identifikasi Mangga Berdasarkan Tingkat Kematangan Menggunakan Yolo 11 (Vol. 4).

Ilmi, M. A., Komang Somawirata, I., Ardita, M., & Somawirata, I. K. (2025). Water Level Detection and Flood Early Warning System Using Image Processing. Journal Homepage: Journal of Electrical Engineering and Computer (JEECOM), 7(1). doi: 10.33650/jeecom.v4i2

Iskandar Mulyana, D., Adrianto, S., Sutisna, N., & Arif Wahyudi, A. (2025). E-P-Mask R-CNN. In Jurnal Indonesia?: Manajemen Informatika dan Komunikasi (JIMIK) (Vol. 6, Issue 1). Retrieved from https://journal.stmiki.ac.id

Khanam, R., & Hussain, M. (2024). YOLOv11: An Overview of the Key Architectural Enhancements. Retrieved from http://arxiv.org/abs/2410.17725

Li, J., Tong, C., Yuan, H., & Huang, W. (2024). A Complex Environmental Water-Level Detection Method Based on Improved YOLOv5m. Sensors, 24(16). doi: 10.3390/s24165235

Mellasyafa Agustien, C., Zarkasyi Rahman, A., & Sunu Astuti Departemen Administrasi Publik, R. (2023). EVALUASI LAYANAN INFORMASI MITIGASI BENCANA MELALUI WEBSITE PANTAU BANJIR DI KOTA SEMARANG.

Nugroho, D. A., & Handayani, W. (2021). Kajian Faktor Penyebab Banjir dalam Perspektif Wilayah Sungai: Pembelajaran Dari Sub Sistem Drainase Sungai Beringin. Jurnal Pembangunan Wilayah Dan Kota, 17(2), 119–136. doi: 10.14710/pwk.v17i2.33912

Oktafiani, R., Hermawan, A., & Avianto, D. (2023). Pengaruh Komposisi Split data Terhadap Performa Klasifikasi Penyakit Kanker Payudara Menggunakan Algoritma Machine Learning. Jurnal Sains Dan Informatika, 19–28. doi: 10.34128/jsi.v9i1.622

Permana, A. A., Muttaqin, R., & Sunandar, A. (2024). SISTEM DETEKSI API SECARA REAL TIME MENGGUNAKAN ALGORITMA YOU ONLY LOOK ONCE (YOLO) VERSI 8. In Jurnal Mahasiswa Teknik Informatika (Vol. 8, Issue 5). Retrieved from https://universe.roboflow.com/.

Putra, R. R., Maimunah, M., & Sasongko, D. (2024). Implementasi Algoritma YOLO V8 (You Only Look Once) Dalam Deteksi Penyakit Daun Durian. Building of Informatics, Technology and Science (BITS), 6(3). doi: 10.47065/bits.v6i3.6136

Qiao, G., Yang, M., & Wang, H. (2022). A Water Level Measurement Approach Based on YOLOv5s. Sensors, 22(10). doi: 10.3390/s22103714

RAHMAN, A. A., AGUSTIN, S. D., IBRAHIM, N., & KUMALASARI, N. C. (2022). Perbandingan Algoritma YOLOv4 dan Scaled YOLOv4 untuk Deteksi Objek pada Citra Termal. MIND Journal, 7(1), 61–71. doi: 10.26760/mindjournal.v7i1.61-71

Refindha, F., Harianto, A., Alawi, Z., & Sa’ida, I. A. (2025). PENGARUH KOMPOSISI SPLIT DATA PADA AKURASI KLASIFIKASI PENDERITA DIABETES MENGGUNAKAN ALGORITMA MACHINE LEARNING. Jurnal Sistem Informasi Dan Informatika (Simika), 8(1).

Rosidin Rosidin, Rezki Novianti, Kori Puspita Ningsih, Dedi Haryadi, Giatika Chrisnawati, & Nuralfin Anripa. (2024). 31125-Article Text-102718-1-10-20240711. PERAN KECERDASAN BUATAN DALAM PENGEMBANGAN SISTEM OTOMATISASI PROSES BISNIS.

Safitri, D., Putra, R. A. M., & Dewantoro, D. F. (2022). ANALISIS POLA ALIRAN BANJIR PADA SUNGAI CIMADUR, PROVINSI BANTEN DENGAN MENGGUNAKAN HEC-RAS. In Journal of Infrastructural in Civil Engineering (JICE) (Vol. 03, Issue 01). Retrieved from https://ejurnal.teknokrat.ac.id/index.php/jice

Setyaningsih, E. R., & Edy, M. S. (2022). YOLOv4 dan Mask R-CNN Untuk Deteksi Kerusakan Pada Karung Komoditi. Teknika, 11(1), 45–52. doi: 10.34148/teknika.v11i1.419

Su, P., Joutsensaari, J., Dada, L., Zaidan, M. A., Nieminen, T., Li, X., Wu, Y., Decesari, S., Tarkoma, S., Petäjä, T., Kulmala, M., & Pellikka, P. (2022). New particle formation event detection with Mask R-CNN. Atmospheric Chemistry and Physics, 22(2), 1293–1309. doi: 10.5194/acp-22-1293-2022