ABSTRACT
Real-time objection detection is becoming more important and critical in all application areas, including Smart Transport and Smart City. From safety/security to resource efficiency, real-time image processing approaches are used more than ever. On the other hand, low-latency requirements and available resources present challenges. Edge computing integrated with cloud computing minimizes communication delays but requires efficient use of resources due to its limited resources. For example, although deep learning-based object detection methods give very accurate and reliable results, they require high computational power. This overhead reveals a need to implement deep learning models with less complex architectures for edge deployment. In this paper, the performance of evolving deep learning models with their lightweight versions such as YOLOv5-Nano, YOLOX-Nano, YOLOX-Tiny, YOLOv6-Nano, YOLOv6-Tiny, and YOLOv7-Tiny are evaluated on a commercially available edge device. The results show that YOLOv5-Nano and YOLOv6-Nano with their TensorRT versions can provide real-time applicability in approximately 35 milliseconds of inference time. It is also observed that YOLOv6-Tiny gives the highest average precision while YOLOv5-Nano gives the lowest energy consumption when compared to other models.
- W. Z. Khan, E. Ahmed, S. Hakak, I. Yaqoob, and A. Ahmed, “Edge computing: A survey,” Future Generation Computer Systems, vol. 97, pp. 219–235, 2019.Google ScholarDigital Library
- N. Hassan, K.-L. A. Yau, and C. Wu, “Edge computing in 5G: A Review,” IEEE Access, vol. 7, pp. 127276–127289, 2019.Google ScholarCross Ref
- K. Zhang, S. Leng, Y. He, S. Maharjan, and Y. Zhang, “Mobile edge computing and networking for green and low-latency internet of things,” IEEE Communications Magazine, vol. 56, no. 5, pp. 39–45, 2018.Google ScholarCross Ref
- L. Guo, P.-S. Ge, M.-H. Zhang, L.-H. Li, and Y.-B. Zhao, “Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine,” Expert Systems with Applications, vol. 39, no. 4, pp. 4274–4286, Mar. 2012.Google ScholarDigital Library
- Y. Xiao, Z. Tian, J. Yu, Y. Zhang, S. Liu, S. Du, and X. Lan, “A review of object detection based on Deep Learning,” Multimedia Tools and Applications, vol. 79, no. 33-34, pp. 23729–23791, 2020.Google ScholarDigital Library
- Z.-Q. Zhao, P. Zheng, S.-T. Xu, and X. Wu, “Object detection with deep learning: A Review,” IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 11, pp. 3212–3232, 2019.Google ScholarCross Ref
- W. Rahmaniar and A. Hernawan, “Real-time human detection using deep learning on embedded platforms: A Review,” Journal of Robotics and Control (JRC), vol. 2, no. 6, 2021.Google ScholarCross Ref
- L. Barba-Guaman, J. Eugenio Naranjo, and A. Ortiz, “Deep Learning Framework for vehicle and pedestrian detection in rural roads on an embedded GPU,” Electronics, vol. 9, no. 4, p. 589, 2020.Google ScholarCross Ref
- A. S. Pinto de Aguiar, F. B. Neves dos Santos, L. C. Feliz dos Santos, V. M. de Jesus Filipe, and A. J. Miranda de Sousa, “Vineyard trunk detection using Deep learning – an experimental device benchmark,” Computers and Electronics in Agriculture, vol. 175, p. 105535, 2020.Google ScholarCross Ref
- S. P. Kaarmukilan, S. Poddar, and A. T. K, “FPGA based deep learning models for object detection and recognition comparison of object detection comparison of object detection models using FPGA,” 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC), 2020.Google ScholarCross Ref
- H.-H. Nguyen, D. N.-N. Tran, and J. W. Jeon, “Towards real-time vehicle detection on edge devices with Nvidia Jetson TX2,” 2020 IEEE International Conference on Consumer Electronics - Asia (ICCE-Asia), 2020.Google ScholarCross Ref
- J. Zhu, H. Feng, S. Zhong, and T. Yuan, “Performance analysis of real-time object detection on jetson device,” 2022 IEEE/ACIS 22nd International Conference on Computer and Information Science (ICIS), 2022.Google ScholarCross Ref
- 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.Google ScholarCross Ref
- J. Lee, P. Wang, R. Xu, V. Dasari, N. Weston, Y. Li, S. Bagchi, and S. Chaterji, “Benchmarking video object detection systems on embedded devices under resource contention,” Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning, 2021.Google ScholarDigital Library
- A. Bailly, C. Blanc, É. Francis, T. Guillotin, F. Jamal, B. Wakim, and P. Roy, “Effects of dataset size and interactions on the prediction performance of logistic regression and deep learning models,” Computer Methods and Programs in Biomedicine, vol. 213, Jan. 2022.Google ScholarDigital Library
- Z. Ge, S. Liu, F. Wang, Z. Li, and J. Sun, “YOLOX: Exceeding YOLO Series in 2021,” arXiv preprint, Jul. 2021.Google Scholar
- D. Snegireva and A. Perkova, “Traffic sign recognition application using Yolov5 Architecture,” 2021 International Russian Automation Conference (RusAutoCon), 2021.Google ScholarCross Ref
- C. Li, L. Li, H. Jiang, K. Weng, Y. Geng, L. Li, Z. Ke, Q. Li, M. Cheng, W. Nie , "YOLOv6: a single-stage object detection framework for industrial applications," arXiv preprint, Sep. 2022.Google Scholar
- 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,” arXiv preprint, Jul. 2022.Google Scholar
- G. Verma, Y. Gupta, A. M. Malik, and B. Chapman, “Performance evaluation of deep learning compilers for Edge Inference,” 2021 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2021.Google ScholarCross Ref
- “Jetson Nano Developer Kit,” NVIDIA Developer, 28-Sep-2022. [Online]. Available: https://developer.nvidia.com/embedded/jetson-nano-developer-kit. [Accessed: 08-Nov-2022].Google Scholar
- O. Shafi, C. Rai, R. Sen, and G. Ananthanarayanan, “Demystifying tensorrt: Characterizing neural network inference engine on Nvidia Edge Devices,” 2021 IEEE International Symposium on Workload Characterization (IISWC), 2021.Google ScholarCross Ref
- H. Song, H. Liang, H. Li, Z. Dai, and X. Yun, “Vision-based vehicle detection and counting system using deep learning in highway scenes,” European Transport Research Review, vol. 11, no. 1, 2019.Google ScholarCross Ref
- 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,” Computer Vision – ECCV 2014, pp. 740–755, 2014.Google Scholar
- Y. Liu, P. Sun, N. Wergeles, and Y. Shang, “A survey and performance evaluation of deep learning methods for small object detection,” Expert Systems with Applications, vol. 172, p. 114602, 2021.Google ScholarCross Ref
Index Terms
- Performance Evaluation of Recent Object Detection Models for Traffic Safety Applications on Edge
Recommendations
Safety Helmet Detection Based on YOLOv7
CSAE '22: Proceedings of the 6th International Conference on Computer Science and Application EngineeringFrequent safety accidents have posed a significant risk to workers' lives recently. In particular, the risk of head injury is significantly increased by workers not wearing helmets. However, manual supervision is inefficient and costly. Even though ...
Object detection through edge behavior modeling
AVSS '11: Proceedings of the 2011 8th IEEE International Conference on Advanced Video and Signal Based SurveillanceThe detection of moving objects depends on the accuracy of the model used to represent the background. Common pixel-based and naive edge-based approaches have many drawbacks in dynamic environments, e.g., false detections with noise. We propose a novel ...
Edge Assisted Object Detection for Mobile Application
ICIT '19: Proceedings of the 2019 7th International Conference on Information Technology: IoT and Smart CityObject detection for mobile devices is meaningful especially in the field of IoT. Limited by computing power and network transmission, it's challenging to get high accuracy in mobile object detection. To solve this question, this article designs a ...
Comments