Eksploitasi Fitur Untuk Peningkatan Kinerja Deteksi Objek Berbasis Pada Pesawat Tanpa Awak

Authors

DOI:

https://doi.org/10.34818/eoe.v9i6.18946

Abstract

Abstrak Teknologi kecerdasan buatan atau Artificial effect of exploitation on the backbone, namely freeze backbone, exploitation of the concat and freeze backbone layers, Intelligence (AI) berkembang pesat seiring dengan perkembangan zaman. Salah satu bagian pada AI yaitu computer vision khususnya Object Detection menjadi teknologi yang terus dikembangkan. Object Detection dapat diimplementasikan pada berbagai sistem, salah satunya Object Detection for Unmanned Aerial Vehicles (UAV). Peningkatan performansi kinerja object detection pada UAV merupakan tantangan bagi para peneliti yang disebabkan oleh beberapa masalah seperti, ketidakseimbangan data, perubahan skala, prediksi yang akurat, keterbatasan memori dan komputasi untuk aplikasi real-time. Pada Tugas Akhir ini dilakukan eksploitasi fitur terhadap algoritma YOLOv5 dalam meningkatkan performansi object detection berbasis pada pesawat tanpa awak. Algoritma ini terdiri dari bagian backbone, neck, dan head. YOLOv5 mengadaptasi CSP network sebagai backbone dan PANet sebagai neck. Beberapa analisis yang dilakukan pada Tugas Akhir ini adalah pengaruh eksploitasi pada backbone yaitu freeze backbone, eksploitasi pada layer concat dan freeze backbone, eksploitasi dengan penambahan layer pada bagian neck dan freeze backbone, dan penggabungan ketiga eksploitasi tersebut. Model dengan performansi terbaik didapatkan pada model penggabungan tiga eksploitasi dengan nilai mAP@.5 sebesar 22,4%. Berdasarkan hasil mAP tersebut, eksploitasi fitur dengan dilakukan freeze backbone dan penambahan layer pada bagian neck juga modifikasi pada layer concat dapat mempengaruhi performansi dan kinerja object detection berbasis pada pesawat tanpa awak. Kata kunci: Eksploitasi, Object Detection, UAV, YOLOv5

Downloads

Download data is not yet available.

References

[1] S. Vaddi, C. Kumar, and A. Jannesari, “Efficient object detection model for real-time UAV applications,” CoRR, vol. abs/1906.00786, 2019. [Online]. Available: http://arxiv.org/abs/1906.00786

[2] G. Jocher, A. Stoken, A. Chaurasia, J. Borovec, NanoCode012, TaoXie, Y. Kwon, K. Michael, L. Changyu, J. Fang, A. V, Laughing, tkianai, yxNONG, P. Skalski, A. Hogan, J. Nadar, imyhxy, L. Mammana, AlexWang1900, C. Fati, D. Montes, J. Hajek, L. Diaconu, M. T. Minh, Marc, albinxavi, fatih, oleg, and wanghaoyang0106, “ultralytics/YOLOv5: v6.0 - YOLOv5n ’Nano’ models, Roboflow integration, TensorFlow export, OpenCV DNN support,” Oct. 2021. [Online]. Available: https://doi.org/10.5281/zenodo.5563715

[3] “Transfer Learning with Frozen Layers,” https://docs.ultralytics.com/tutorials/ transfer-learning-froze-layers/, accessed: 2022-07-06.

[4] R. Padilla, S. L. Netto, and E. A. B. da Silva, “A survey on performance metrics for object-detection algorithms,” 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 237–242, 2020.

[5] P. Zhu, L. Wen, D. Du, X. Bian, H. Fan, Q. Hu, and H. Ling, “Detection and tracking meet drones challenge,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1–1, 2021.

[6] C.-J. Yang, T. Chou, F.-A. Chang, C. Ssu-Yuan, and J.-I. Guo, “A smart surveillance system with multiple people detection, tracking, and behavior analysis,” in 2016 International Symposium on VLSI Design, Automation and Test (VLSI-DAT), 2016, pp. 1–4.

[7] J. Choi, D. Chun, H. Kim, and H.-J. Lee, “Gaussian yolov3: An accurate and fast object detector using localization uncertainty for autonomous driving,” in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 502–511.

[8] J. Lee, J. Wang, D. Crandall, S. Sabanovi ˇ c, and G. Fox, “Real-time, ´ cloud-based object detection for unmanned aerial vehicles,” in 2017 First IEEE International Conference on Robotic Computing (IRC), 2017, pp. 36–43.

[9] P. Zhang, Y. Zhong, and X. Li, “Slimyolov3: Narrower, faster and better for real-time uav applications,” in 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019, pp. 37–45.

[10] X. Zhu, S. Lyu, X. Wang, and Q. Zhao, “Tph-yolov5: Improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios,” ArXiv, vol. abs/2108.11539, 2021.

[11] A. Zhang, Z. C. Lipton, M. Li, and A. J. Smola, “Dive into deep learning,” 2021.

[12] M. Carranza-Garc´ıa, J. Torres-Mateo, P. Lara-Ben´ıtez, and J. Garc´ıa-Gutierrez, “On the performance of one-stage and two-stage ´ object detectors in autonomous vehicles using camera data,” Remote. Sens., vol. 13, p. 89, 2021.

[13] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. E. Reed, C.-Y. Fu, and A. C. Berg, “Ssd: Single shot multibox detector,” in ECCV, 2016.

[14] R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, “Convolutional neural networks: an overview and application in radiology,” Insights into Imaging, vol. 9, pp. 611 – 629, 2018.

[15] “Convolutional Neural Network (CNN),” https://medium.com/@raycad. seedotech/convolutional-neural-network-cnn-8d1908c010ab, accessed: 2022-07-13.

[16] J. Redmon, S. K. Divvala, R. B. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788, 2016.

[17] J. Redmon and A. Farhadi, “Yolo9000: Better, faster, stronger,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6517–6525, 2017.

[18] J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” ArXiv, vol. abs/1804.02767, 2018.

[19] A. Bochkovskiy, C.-Y. Wang, and H.-y. Liao, “Yolov4: Optimal speed and accuracy of object detection,” ArXiv, vol. abs/2004.10934, 2020.

[20] D. Thuan, D. Thuan, “Evolution of yolo algorithm and yolov5: The state-of-the-art object detention algorithm,” https://www.theseus.fi/handle/10024/452552, accessed: 2021-11-12.

[21] D. Lema, O. Pedrayes, R. Usamentiaga, F. D. Garcia, and A. Alonso, “Cost-performance evaluation of a recognition service of livestock activity using aerial images,” Remote Sensing, vol. 13, p. 2318, 06 2021.

[22] R. Padilla, W. Lobato Passos, T. Dias, S. Netto, and E. da Silva, “A comparative analysis of object detection metrics with a companion open-source toolkit,” Electronics, vol. 10, pp. 279–306, 01 2021.

[23] M. Everingham, L. Van Gool, C. Williams, J. Winn, and A. Zisserman, “The pascal visual object classes (voc) challenge,” International Journal of Computer Vision, vol. 88, pp. 303–338, 06 2010.

[24] “Metrics,” https://cocodataset.org/#detection-eval, accessed: 2021-12-08.

[25] D. Du, P. Zhu, L. Wen, X. Bian, H. Lin, Q. Hu, T. Peng, J. Zheng, X. Wang, Y. Zhang, L. Bo, H. Shi, R. Zhu, A. Kumar, A. Li, A. Zinollayev, A. Askergaliyev, A. Schumann, B. Mao, B. Lee, C. Liu, C. Chen, C. Pan, C. Huo, D. Yu, D. Cong, D. Zeng, D. R. Pailla, D. Li, D. Wang, D. Cho, D. Zhang, F. Bai, G. Jose, G. Gao, G. Liu, H. Xiong, H. Qi, H. Wang, H. Qiu, H. Li, H. Lu, I. Kim, J. Kim, J. Shen, J. Lee, J. Ge, J. Xu, J. Zhou, J. Meier, J. W. Choi, J. Hu, J. Zhang, J. Huang, K. Huang, K. Wang, L. Sommer, L. Jin, L. Zhang, L. Huang, L. Sun, L. Steinmann, M. Jia, N. Xu, P. Zhang, Q. Chen, Q. Lv, Q. Liu, Q. Cheng, S. S. Chennamsetty, S. Chen, S. Wei, S. S. S. Kruthiventi, S. Hong, S. Kang, T. Wu, T. Feng, V. A. Kollerathu, W. Li, W. Dai, W. Qin, W. Wang, X. Wang, X. Chen, X. Chen, X. Sun, X. Zhang, X. Zhao, X. Zhang, X. Zhang, X. Chen, X. Wei, X. Zhang, Y. Li, Y. Chen, Y. H. Toh, Y. Zhang, Y. Zhu, Y. Zhong, Z. Wang, Z. Wang, Z. Song, and Z. Liu, “Visdrone-det2019: The vision meets drone object detection in image challenge results,” in 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019, pp. 213–226

Downloads

Published

2022-12-01

Issue

Pages

2943-2950

Section

Program Studi S1 Teknik Telekomunikasi

How to Cite

Jannah, N., Wibowo, S. A., & Siadari, T. S. (2022). Eksploitasi Fitur Untuk Peningkatan Kinerja Deteksi Objek Berbasis Pada Pesawat Tanpa Awak. EProceedings of Engineering, 9(6), 2943-2950. https://doi.org/10.34818/eoe.v9i6.18946