Implementation of Homographic Transform and YOLO v4-Tiny for Bottle and Can Detection
Abstract
The increasing presence of inorganic waste such as plastic bottles and cans poses a serious environmental threat and demands efficient detection solutions. This study aims to develop a real-time detection and position estimation system for inorganic waste using the YOLO v4-Tiny algorithm combined with homography transformation. A total of 3,388 labeled images were prepared and augmented via the Roboflow platform. The detection model was trained using the Darknet framework, while homography was applied to estimate object positions in real-world coordinates. System performance was evaluated based on precision, recall, F1-score, mean Average Precision (mAP), and Intersection over Union (IoU). The results show a mAP of 86.43%, precision of 77%, recall of 90%, and an average IoU of 62.33%. The system achieved a frame rate of 3–5 FPS, demonstrating its potential for low-power embedded devices. This approach is suitable for real-time waste monitoring using computer vision in constrained environments.
Downloads
References
[2] C. N. Sari, L. H. Al-illahiyah, L. Br Kaban, M. R. Hasibuan, R. H. Nasution, dan W. F. Sari, "Keterbatasan Fasilitas Tempat Pembuangan Sampah dan Tantangan Kesadaran Masyarakat Dalam Pengelolaan Sampah (Studi Kasus di Desa Jandi Meriah Kec. Tiganderket Kab. Karo)," Journal of Human And Education, vol. 3, no. 2, pp. 268–276, 2023.
[3] S. Enggari, A. Ramadhanu, and H. Marfalino, “Peningkatan Digital Image Processing Dalam Mendeskripsikan Tumbuhan Jamur Dengan Segmentasi Warna, Deteksi Tepi Dan Kontur,” Jurnal Teknologi Dan Sistem Informasi Bisnis, vol. 4, no. 1, pp. 70–75, Jan. 2022, doi: 10.47233/jteksis.v4i1.358.
[4] M. D. Pranatha, M. A. Maricar, and G. H. Setiawan, “Implementasi Arsitektural Resnet-34 Dalam Klasifikasi Gambar Penyakit Pada Daun Kentang,” Jurnal Teknologi Dan Sistem Informasi Bisnis, vol. 6, no. 3, pp. 575–580, Jul. 2024, doi: 10.47233/jteksis.v6i3.1431.
[5] F. Marchellyn, F. Y. Suratman, R. Arief, and S. Satyawan, “Realsense Depth Camera Untuk Pengukuran Jarak Pada Mobil Autonom Roda Tiga,” 2024.
[6] N. Indra, K. Dewi, and W. B. Putra, “Pemindaian Ruang pada Bangunan dengan Mobile LiDAR Camera,” Jurnal Arsitektur TERRACOTTA | No.1 |, vol. 4, pp. 80–91, 2022.
[7] U. Ramadhan et al., “Deteksi Sampah Botol Plastik di Perairan Menggunakan YOLO v4-Tiny,” vol. 7, no. 1, 2025, doi: 10.47233/jteksis.v5i1.1744.
[8] T. Sung, H. Jong Lee, and T. Leang Sung, “Images Alignment Using Homography Transformation Matrix,” 2018. [Online]. Available: https://www.researchgate.net/publication/334107601
[9] Y. Luo et al., “A Review of Homography Estimation: Advances and Challenges,” Dec. 01, 2023, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/electronics12244977.
[10] N. Sujana, M. Malik Mutoffar, and A. Azzam Haryanto, “ANALISIS KINERJA YOLOV8 OPTIMALISASI ROBOFLOW UNTUK DETEKSI EKSPRESI WAJAH EMOSIONAL DENGAN MACHINE LEARNING,” vol. 06, 2024.
[11] N. T. Hakiki, F. Shevanie, dan K. N. Ramadhani, "Analisis Metode Augmentasi Data untuk Klasifikasi Objek pada Dataset CIFAR-10," Jurnal Tugas Akhir Fakultas Informatika, Universitas Telkom, Agustus 2023.
[12] P. Y. Putra et al., “JIP (Jurnal Informatika Polinema) DETEKSI KENDARAAN TRUK PADA VIDEO MENGGUNAKAN METODE TINY-YOLO V4”.
[13] A. Ardiansyah, J. Triloka, K. kunci-Pengolahan Citra, D. Kesegaran Buah, and K. Akurasi, “Evaluasi Kinerja Model YOLOv8… 357.”
[14] M. D. Maulana, L. Novamizanti, dan S. A. Wibowo, "Evaluasi Kinerja YOLOv8 dalam Identifikasi Kesegaran Ikan dengan Metode Deteksi Objek," e-Proceeding of Engineering, vol. 11, no. 4, hal. 2864, Agustus 2024.
[15] G. Wölflein and O. Arandjelović, “Determining chess game state from an image,” J Imaging, vol. 7, no. 6, Jun. 2021, doi: 10.3390/jimaging7060094.
[16] P. Prayitno, G. F. Shidiq, A. Z. Fanani, and M. A. Soeleman, “Peningkatan Akurasi Pembacaan Lembar Jawaban Komputer dengan Memperbaiki Ketidaksimetrisan Citra Hasil Pemindaian Menggunakan Transformasi Homografi,” JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 7, no. 4, p. 1635, Oct. 2023, doi: 10.30865/mib.v7i4.6651.
[17] J. Liu, A. Liang, E. Zhao, M. Pang, and D. Zhang, “Homography Matrix-Based Local Motion Consistent Matching for Remote Sensing Images,” Remote Sens (Basel), vol. 15, no. 13, Jul. 2023, doi: 10.3390/rs15133379.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under an Attribution 4.0 International (CC BY 4.0) that allows others to share — copy and redistribute the material in any medium or format and adapt — remix, transform, and build upon the material for any purpose, even commercially with an acknowledgment of the work's authorship and initial publication in this journal.
