Analisis Performansi Complex-Yolov4 Menggunakan Pendekatan Upsampling Untuk Objek Deteksi 3-Dimensi (3d) Pada Autonomous Driving

Penulis

DOI:

https://doi.org/10.34818/eoe.v9i6.18909

Abstrak

Abstrak Penggunaan teknologi LiDAR dengan metode Complex-YOLOv4 pada pengujian dengan dataset uji KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) menjadi metode yang baik pada teknologi objek deteksi 3D secara real-time. Namun, hasil pendeteksian untuk kelas pejalan kaki dan pesepeda pada model ini masih kurang akurat dan perlu ditingkatkan. Pada Tugas Akhir ini dilakukan analisis pada backbone CSPDarknet-53 dari model Complex-YOLOv4 dengan menggunakan pendekatan upsample diantaranya yaitu bicubic, bilinear, dan nearest. Parameter yang digunakan untuk perbandingan uji performansi diantaranya precision, recall, average precision (AP), f1-score, dan mean average precision (mAP). Hasil dari tiap pendekatan upsample akan dilakukan perbandingan dengan upsample expand (upsample orisinal). Dari hasil evaluasi, upsample nearest menghasilkan mAP 88,7%. Upsample bilinear menghasilkan mAP 88,5%. Pendekatan upsample terbaik didapatkan dengan menggunakan upsample bicubic. Upsample bicubic menghasilkan mAP terbaik yaitu 88,9% dan lebih tinggi 0.2% dari upsample orisinal yang digunakan pada Complex-YOLOv4. Kata kunci : autonomous driving, ComplexYOLOv4, LiDAR, object detection, point cloud.

Unduhan

Data unduhan tidak tersedia.

Referensi

[1] M. Bhat, S. Han, and F. Porikli, “Fast Polar Attentive 3D Object Detection on LiDAR Point Clouds,” 2021.

[2] M. Simon et al., “Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.

[3] C. R. Qi, W. Liu, C. Wu, H. Su, and L. J. Guibas, “Frustum PointNets for 3D Object Detection From RGB-D Data,” CoRR, abs/1711.08488, 2017.

[4] Y. Zhou and O. Tuzel, “VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection,” CoRR, abs/1711.06396, 2017.

[5] X. Chen, H. Ma, J. Wan, B. Li, and T. Xia, “Multi-View 3D Object Detection Network for Autonomous Driving,” CoRR, abs/1611.07759, 2016.

[6] M. Duggin, “A Review of: Introduction to Remote Sensing,” International Journal of Remote Sensing, vol. 14, no. 3, p. 600, 1993.

[7] R. Wang, J. Peethambaran, and D. Chen, “LiDAR Point Clouds to 3-D Urban Models: A Review,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 11, no. 2, pp. 606–627, 2018.

[8] IEEE Innovation at Work, “LiDAR is the Latest Game-Changing Advancement for Autonomous Vehicles,” Available: https://innovationatwork.ieee.org/lidr-is-the-latest-game-changing-advancement-for-autonomous-vehicles/. Accessed: Dec. 18, 2022.

[9] S. Khan, H. Rahmani, S. A. A. Shah, and M. Bennamoun, A Guide to Convolutional Neural Networks for Computer Vision, Synthesis Lectures on Computer Vision, vol. 8, no. 1, pp. 1–207, 2018. doi: 10.2200/S00822ED1V01Y201712COV015.

[10] V. H. Phung and E. J. Rhee, “A Deep Learning Approach for Classification of Cloud Image Patches on Small Datasets,” Journal of Information and Communication Convergence Engineering, vol. 16, no. 3, pp. 173–178, 2018. doi: 10.6109/jicce.2018.16.3.173.

[11] H. Yingge, I. Ali, and K. Y. Lee, “Deep Neural Networks on Chip: A Survey,” 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), Busan, Korea, 2020, pp. 589–592.

[12] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788, 2016. doi: 10.1109/CVPR.2016.91.

[13] H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese, “Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 658–666, 2019. doi: 10.1109/CVPR.2019.00075.

[14] C. S. Lent, Learning to Program with MATLAB Building GUI Tools, John Wiley & Sons Inc., p. 310, 2013.

[15] Python.org, “What is Python? Executive Summary,” Available: https://www.python.org/doc/essays/blurb/. Accessed: Feb. 18, 2022.

[16] N. Ketkar, “Introduction to PyTorch,” in Deep Learning with Python, Apress, Berkeley, CA, 2017, pp. 195–208. doi: 10.1007/978-1-4842-2766-4_12.

[17] K. Tran, “What is PyTorch?” Towards Data Science, 2020. Available: https://towardsdatascience.com/what-is-pytorch-a84e4559f0e3. Accessed: Feb. 18, 2022.

[18] A. Geiger, “Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012, pp. 3354–3361.

[19] H. Dalianis, “Evaluation Metrics and Evaluation,” in Clinical Text Mining, Springer, Cham, 2018. doi: 10.1007/978-3-319-78503-5_6.

Diterbitkan

2022-12-01

Terbitan

Halaman

2731-2738

Bagian

Program Studi S1 Teknik Telekomunikasi

Cara Mengutip

Ananda, D., Wibowo, S. A., & Pratondo, A. (2022). Analisis Performansi Complex-Yolov4 Menggunakan Pendekatan Upsampling Untuk Objek Deteksi 3-Dimensi (3d) Pada Autonomous Driving. eProceedings of Engineering, 9(6), 2731-2738. https://doi.org/10.34818/eoe.v9i6.18909