Analisis Perbandingan Antara Model Mask R-CNN dan SSD dalam Mendeteksi Objek Kursi

Elvina Sulistya(1*), Muhammad Munsarif(2)


(1) Universitas Muhammadiyah Semarang
(2) Universitas Muhammadiyah Semarang
(*) Corresponding Author

Abstract


Detection is a process of inspecting or examining an object or image to be studied or understood using a specific method. In this research, a comparison is made between the Mask R-CNN model and the Single Short Detection (SSD) model in detecting an image object. In this case, the goal is to determine which method is better in detecting an image. To achieve a high score, training and testing are required. During testing, it was found that both the Mask R-CNN and SSD models almost have the same score, reaching 0.903. The difference lies in the Intersection over Union (IoU) part, where the Mask R-CNN model obtained an IoU of 0.000, and the SSD model obtained an IoU of 0.577.

Full Text:

PDF

References


R. Y. Sabilla and D. Yendri, “Sistem Monitoring Kondisi dan Posisi Pengemudi Berbasis Internet of things,” Chipset, vol. 2, no. 01, pp. 1–10, 2021, doi: 10.25077/chipset.2.01.1-10.2021.

V. A. Dihni, “Angka Kecelakaan Lalu Lintas di Indonesia Meningkat di 2021,” databoks.katadata.co.id, 2022. .

J. Terven and D. Cordova-Esparza, “A Comprehensive Review of YOLO: From YOLOv1 and Beyond,” pp. 1–27, 2023, [Online]. Available: http://arxiv.org/abs/2304.00501.

E. R. Setyaningsih and M. S. Edy, “YOLOv4 dan Mask R-CNN Untuk Deteksi Kerusakan Pada Karung Komoditi,” Teknika, vol. 11, no. 1, pp. 45–52, 2022, doi: 10.34148/teknika.v11i1.419.

M. Fathur Rahman Haikal et al., “ANALISIS PERBANDINGAN AKURASI DAN PERFORMA ALGORITMA DETEKSI OBJEK PADA YOLO v3 DENGAN SINGLE SHOT MULTIBOX DETECTOR (SSD),” Front. Neurosci., vol. 14, no. 1, pp. 1–13, 2021.

C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable bag of freebies sets new state of th art for real-time object detectors,” pp. 1–17, 2022, [Online]. Available: http://arxiv.org/abs/2207.02696

L. Cao, X. Zheng, and L. Fang, “The Semantic Segmentation of Standing Tree Images Based on the Yolo V7 Deep Learning Algorithm,” 2023.

S. Zhou et al., “An Accurate Detection Model of Takifugu rubripes Using an Improved YOLO-V7 Network,” J. Mar. Sci. Eng., vol. 11, no. 5, 2023, doi: 10.3390/jmse11051051.

C. Y. Wang, A. Bochkovskiy, and H. Y. M. Liao, “Scaled-yolov4: Scaling cross stage partial network,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 13024–13033, 2021, doi: 10.1109/CVPR46437.2021.01283.

X. Ding, X. Zhang, N. Ma, J. Han, G. Ding, and J. Sun, “RepVgg: Making VGG-style ConvNets Great Again,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., no. 2017, pp. 13728–13737, 2021, doi: 10.1109/CVPR46437.2021.01352.

R. Wang and J. Li, “Bayes test of precision, recall, and F1 measure for comparison of two natural language processing models,” ACL 2019 - 57th Annu. Meet. Assoc. Comput. Linguist. Proc. Conf., pp. 4135–4145, 2020, doi: 10.18653/v1/p19-1405.


Article Metrics

Abstract view : 10 times
PDF - 3 times

DOI: https://doi.org/10.26714/jkti.v3i2.14107

Refbacks

  • There are currently no refbacks.


=======================================================================================

Penerbit:

  • JKTI | Jurnal Komputer dan Teknologi Informasi
  • Program Studi S1 Informatika,  Unimus| Universitas Muhammadiyah Semarang
  • Sekretariat: Gedung Kuliah Bersama II (GKB II) Lantai 7,  Jl. Kedungmundu Raya No 18 Semarang
  • email: informatika@unimus.ac.id, Phone: + +62 813 2504 3677
  • e-ISSN: 2986-7592

Paper Template: Download

View My Stats

------------------------------------------------------------------------------------------------------------------------------------------------------