Analisis Komparatif YOLO11 dan RT-DETR untuk Deteksi Sampah pada Variasi Pencahayaan
DOI:
https://doi.org/10.62712/juktisi.v5i2.1358Keywords:
Deteksi Sampah, YOLO11, RT-DETR, Robustness, Variasi PencahayaanAbstract
Sistem pemilahan sampah berbasis citra memerlukan model deteksi objek yang mampu mempertahankan akurasi ketika kualitas visual berubah. Penelitian ini menganalisis ketahanan visual YOLO11n, YOLO11s, dan RT-DETR-l pada enam kelas objek sampah, yaitu biodegradable, cardboard, glass, metal, paper, dan plastic. Data eksperimen terdiri atas 7.324 citra latih, 2.098 citra validasi, dan 1.042 citra uji dengan anotasi bounding box berformat YOLO. Evaluasi dilakukan pada test set normal dan empat skenario gangguan, yaitu pencahayaan redup 50%, pencahayaan terang 50%, kontras rendah, dan Gaussian noise. Metrik evaluasi meliputi precision, recall, F1-score, mAP@50, mAP@50:95, dan estimasi FPS. Hasil pengujian normal menunjukkan bahwa RT-DETR-l memperoleh performa tertinggi dengan precision 0,5329, mAP@50 0,4484, dan mAP@50:95 0,3576. Pada evaluasi robustness, RT-DETR-l tetap paling stabil, khususnya pada skenario redup 50% dengan mAP@50 0,4463. Sebaliknya, YOLO11n menghasilkan efisiensi inferensi tertinggi dengan 178,32 FPS pada kondisi normal. Temuan ini menegaskan adanya trade-off antara akurasi deteksi, ketahanan visual, dan kecepatan inferensi untuk sistem deteksi sampah real-time.
Downloads
References
[1] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779-788, doi: 10.1109/CVPR.2016.91.
[2] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv preprint arXiv:2004.10934, 2020, doi: 10.48550/arXiv.2004.10934.
[3] C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 7464-7475, doi: 10.1109/CVPR52729.2023.00721.
[4] C.-Y. Wang, I.-H. Yeh, and H.-Y. M. Liao, “YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information,” in Computer Vision - ECCV 2024, 2024, pp. 1-21, doi: 10.1007/978-3-031-72751-1_1.
[5] A. Wang, H. Chen, L. Liu, K. Chen, Z. Lin, J. Han, and G. Ding, “YOLOv10: Real-Time End-to-End Object Detection,” in Advances in Neural Information Processing Systems, 2024, doi: 10.48550/arXiv.2405.14458.
[6] Ultralytics, “Ultralytics YOLO11 Documentation,” 2024. [Online]. Available: https://docs.ultralytics.com/models/yolo11. Accessed: Jul. 3, 2026.
[7] N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, “End-to-End Object Detection with Transformers,” in Computer Vision - ECCV 2020, 2020, pp. 213-229, doi: 10.1007/978-3-030-58452-8_13.
[8] Y. Zhao, W. Lv, S. Xu, J. Wei, G. Wang, Q. Dang, Y. Liu, and J. Chen, “DETRs Beat YOLOs on Real-Time Object Detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 16965-16974, doi: 10.1109/CVPR52733.2024.01605.
[9] T.-Y. Lin et al., “Microsoft COCO: Common Objects in Context,” in Computer Vision - ECCV 2014, 2014, pp. 740-755, doi: 10.1007/978-3-319-10602-1_48.
[10] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, “The Pascal Visual Object Classes (VOC) Challenge,” International Journal of Computer Vision, vol. 88, pp. 303-338, 2010, doi: 10.1007/s11263-009-0275-4.
[11] R. Padilla, S. L. Netto, and E. A. B. da Silva, “A Survey on Performance Metrics for Object-Detection Algorithms,” Electronics, vol. 10, no. 3, p. 279, 2021, doi: 10.3390/electronics10030279.
[12] C. Shorten and T. M. Khoshgoftaar, “A Survey on Image Data Augmentation for Deep Learning,” Journal of Big Data, vol. 6, no. 60, 2019, doi: 10.1186/s40537-019-0197-0.
[13] K. Oksuz, B. C. Cam, S. Kalkan, and E. Akbas, “Imbalance Problems in Object Detection: A Review,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 10, pp. 3388-3415, 2021, doi: 10.1109/TPAMI.2020.2981890.
[14] A. Rahmatulloh, I. Darmawan, A. P. Aldya, and F. M. S. Nursuwars, “WasteInNet: Deep Learning Model for Real-Time Identification of Various Types of Waste,” Cleaner Waste Systems, vol. 10, p. 100198, 2025, doi: 10.1016/j.clwas.2024.100198.
[15] R. G. Girshick, “Fast R-CNN,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015, pp. 1440-1448, doi: 10.1109/ICCV.2015.169.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Juni Ismail, Pangidoan Adventus Ambarita, Renovand Mikael Situmorang, Elida Madona Siburian, Inggrid Ester Erlinda Simarmata
This work is licensed under a Creative Commons Attribution 4.0 International License.
