Real-time Object Detection Performance Analysis Using YOLOv7 on Edge Devices
Keywords:
Object detection, YOLOv7, Embedded devicesAbstract
Real-time object detection in images is one of the most important areas in computer vision and finds applications in several fields, such as security systems, protection, independent vehicles, and robotics. Many of these applications need to use edge hardware platforms, and it is vital to know the performance of the object detector on these hardware platforms before developing the system. Therefore, in this work, we executed performance benchmark tests of the YOLOv7-tiny model for real-time object detection using a camera and three embedded hardware platforms: Raspberry Pi 4B, Jetson Nano, and Jetson Xavier NX. We tested and analyzed the NVIDIA platforms and their different power modes. The Raspberry Pi 4B achieved an average of 0.9 FPS. The Jetson Xavier NX achieved 30 FPS, the maximum possible FPS rate, in three power modes. In the tests, it was possible to notice that the maximum CPU clock of the Jetson Xavier NX impacts the FPS rate more than the GPU clock itself. The Jetson Nano achieved 7.4 and 5.2 FPS in its two power consumption modes.
Downloads
References
E. Maiettini, G. Pasquale, L. Rosasco, and L. Natale, “On-line object detection: a robotics challenge,” Autonomous Robots, vol. 44, no. 5, pp.739–757, 2020. doi: https://doi.org/10.3390/pharmaceutics13081318. [Online]. Available: https://www.mdpi.com/1999-4923/13/8/1318
D. Feng, A. Harakeh, S. L. Waslander, and K. Dietmayer, “A review and comparative study on probabilistic object detection in autonomous driving,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 8, pp. 9961–9980, 2021. doi: https://doi.org/10.1109/TITS.2021.3096854. [Online]. Available: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9525313
J. Wu, X. Xu, and J. Yang, “Object detection and x-ray security imaging: A survey,” IEEE Access, 2023. doi: https://doi.org/10.1109/ACCESS.2023.3273736. [Online]. Available: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10120944
X. Zhang, C. Wang, Y. Tang, Z. Zhou, and X. Lu, “A survey of few-shot learning and its application in industrial object detection tasks,” in International Workshop of Advanced Manufacturing and Automation. Springer, 2021. doi: https://doi.org/10.1007/978-981-19-0572-8-81 pp. 637–647. [Online]. Available: https://link.springer.com/chapter/10.1007/978-981-19-0572-8_81
R. C. C. d. M. Santos, M. C. Silva, R. L. Santos, E. Klippel, and R. A. Oliveira, “Towards autonomous mobile inspection robots using edge ai.” in ICEIS (1), 2023. doi: https://www.scitepress.org/Link.aspx?doi=10.5220/0011972200003467 pp. 555–562. [Online]. Available: https://sol.sbc.org.br/index.php/semish/article/view/25073/24894
R. C. C. d. M. Santos, M. C. Silva, and R. A. Oliveira, “A computer vision-based method for collecting ground truth for mobile robot odometry,” Proceedings of the 26th International Conference on Enterprise Information Systems - (Volume 1), pp. 116–127, 2024. doi: http://dx.doi.org/10.5220/0012622900003690. [Online]. Available: https://www.scitepress.org/publishedPapers/2024/126229/pdf/index.html
T. Fukagai, K. Maeda, S. Tanabe, K. Shirahata, Y. Tomita, A. Ike, and A. Nakagawa, “Speed-up of object detection neural network with gpu,” in 2018 25th IEEE International conference on image processing (ICIP). IEEE, 2018. doi: https://doi.org/10.1109/ICIP.2018.8451814 pp. 301–305. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/8451814
L. Chen, J. Hu, X. Li, F. Quan, and H. Chen, “Onboard real-time object detection for uav with embedded npu,” in 2021 IEEE 11th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER). IEEE, 2021. doi: https://doi.org/10.1109/CYBER53097.2021.9588193 pp. 192–197. [Online]. Available: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9588193
B. Kovács, A. D. Henriksen, J. D. Stets, and L. Nalpantidis, “Object detection on tpu accelerated embedded devices,” in Computer Vision Systems: 13th International Conference, ICVS 2021, Virtual Event, September 22-24, 2021, Proceedings 13. Springer, 2021. doi: https://doi.org/10.1007/978-3-030-87156-7-7 pp. 82–92. [Online]. Available: https://link.springer.com/chapter/10.1007/978-3-030-87156-7_7
J. C. da Silva, M. C. Silva, E. J. Luz, S. Delabrida, and R. A. Oliveira, “Using mobile edge ai to detect and map diseases in citrus orchards,” Sensors, vol. 23, no. 4, p. 2165, 2023. doi: https://doi.org/10.3390/s23042165. [Online]. Available: https://www.mdpi.com/1424-8220/23/4/2165
L. Wenzheng and W. Jie, “A yolov7 forest fire detection system with edge computing,” in 2023 IEEE 13th International Conference on Electronics Information and Emergency Communication (ICEIEC). IEEE, 2023. doi: https://doi.org/10.1109/ICEIEC58029.2023.10200044 pp. 223–227. [Online]. Available: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10200044
R. C. C. d. M. Santos, M. C. Silva, and R. A. R. Oliveira, “Evaluating the effect of audio feedback on the behavior of automotive fatigue and distraction detection system users,” in 2019 IX Brazilian Symposium on Computing Systems Engineering (SBESC). IEEE, 2019. doi: https://doi.org/10.1109/SBESC49506.2019.9046047 pp. 1–8. [Online]. Available: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9046047
F. L. M. de Sousa, M. J. da Silva, R. C. C. de Meira Santos, M. C. Silva, and R. A. R. Oliveira, “Deep-learning-based embedded adas system,” in 2021 XI Brazilian Symposium on Computing Systems Engineering (SBESC). IEEE, 2021. doi: https://doi.org/10.1109/SBESC53686.2021.9628316 pp. 1–8. [Online]. Available: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9628316
G. Liu, Y. Hu, Z. Chen, J. Guo, and P. Ni, “Lightweight object detection algorithm for robots with improved yolov5,” Engineering Applications of Artificial Intelligence, vol. 123, p. 106217, 2023. doi: https://doi.org/10.1016/j.engappai.2023.106217. [Online]. Available: https://dl.acm.org/doi/abs/10.1016/j.engappai.2023.106217
Z. Li, B. Xu, D. Wu, K. Zhao, S. Chen, M. Lu, and J. Cong, “A yolo-ggcnn based grasping framework for mobile robots in unknown environments,” Expert Systems with Applications, vol. 225, p. 119993, 2023. doi: https://doi.org/10.1016/j.eswa.2023.119993. [Online]. Available: https://dl.acm.org/doi/abs/10.1016/j.eswa.2023.119993
G. Xu, A. S. Khan, A. J. Moshayedi, X. Zhang, and Y. Shuxin, “The object detection, perspective and obstacles in robotic: a review,” EAI Endorsed Transactions on AI and Robotics, vol. 1, no. 1, 2022. doi: http://dx.doi.org/10.4108/airo.v1i1.2709. [Online]. Available: https://eudl.eu/doi/10.4108/airo.v1i1.2709
J. Zhu, H. Feng, S. Zhong, and T. Yuan, “Performance analysis of real-time object detection on jetson device,” in 2022 IEEE/ACIS 22nd International Conference on Computer and Information Science (ICIS), 2022. doi: 10.1109/ICIS54925.2022.9882480 pp. 156–161. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9882480
X. Long, K. Deng, G. Wang, Y. Zhang, Q. Dang, Y. Gao, H. Shen, J. Ren, S. Han, E. Ding et al., “Pp-yolo: An effective and efficient implementation of object detector,” arXiv preprint arXiv:2007.12099, 2020. doi: https://ui.adsabs.harvard.edu/link-gateway/2020arXiv200712099L/doi:10.48550/arXiv.2007.12099. [Online]. Available: https://ui.adsabs.harvard.edu/abs/2020arXiv200712099L/abstract
T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft coco: Common objects in context,” in Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 2014. doi: https://doi.org/10.1007/978-3-319-10602-1-48 pp. 740–755. [Online]. Available: https://home.ttic.edu/~mmaire/papers/pdf/coco_eccv2014.pdf
H. Feng, G. Mu, S. Zhong, P. Zhang, and T. Yuan, “Benchmark analysis of yolo performance on edge intelligence devices,” Cryptography, vol. 6, no. 2, p. 16, 2022. doi: https://doi.org/10.3390/cryptography6020016. [Online]. Available: https://www.mdpi.com/2410-387X/6/2/16
Z. Zou, K. Chen, Z. Shi, Y. Guo, and J. Ye, “Object detection in 20 years: A survey,” Proceedings of the IEEE, vol. 111, no. 3, pp. 257–276, 2023. doi: https://doi.org/10.1109/JPROC.2023.3238524. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10028728
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, 2016. doi: https://doi.org/10.1109/CVPR.2016.91 pp. 779–788. [Online]. Available: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780460
J. Terven and D. Cordova-Esparza, “A comprehensive review of yolo: From yolov1 to yolov8 and beyond,” arXiv preprint arXiv:2304.00501, 2023. doi: https://doi.org/10.3390/make5040083. [Online]. Available: https://www.mdpi.com/2504-4990/5/4/83
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, 2023. doi: https://doi.org/10.1109/CVPR52729.2023.00721 pp. 7464–7475. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10204762
