Edge-based Object Detection using Optimized Tiny YOLO on Embedded Systems
محورهای موضوعی : شبکه های عصبی و یادگیری عمیق
1 - Department of Computer Engineering, West Tehran Branch, Islamic Azad University, Tehran, Iran.
کلید واژه: Tiny YOLO, Model optimization, Model Deployment, Quantization, Pruning, Weight Clustering, Embedded Systems.,
چکیده مقاله :
Object detection at the edge has gained considerable attention for enabling real-time, low-latency, and privacy-preserving solutions by processing data locally on resource-constrained devices. This paper explores using Tiny YOLO, a lightweight variant of the YOLO architecture, for object detection on embedded systems. Tiny YOLO is specifically designed for edge devices to run efficiently on constrained devices by utilizing a reduced architecture with fewer parameters while maintaining good performance for real-time object detection. The study examines the deployment of optimized Tiny YOLO models on embedded systems, incorporating techniques like quantization, pruning, and clustering to reduce model size, enhance speed, and lower power consumption. Optimization methods show significant improvements, with quantization speeding up inference, pruning eliminating redundant parameters, and clustering enhancing accuracy. Specifically, the study compares the performance of Tiny YOLO under these optimization techniques, presenting results for both Pascal VOC and COCO datasets. The results demonstrate that optimized Tiny YOLO models are effective for real-time object detection on microcontrollers. These methods enable the efficient deployment of deep learning models for edge computing, without relying on cloud infrastructure.
Object detection at the edge has gained considerable attention for enabling real-time, low-latency, and privacy-preserving solutions by processing data locally on resource-constrained devices. This paper explores using Tiny YOLO, a lightweight variant of the YOLO architecture, for object detection on embedded systems. Tiny YOLO is specifically designed for edge devices to run efficiently on constrained devices by utilizing a reduced architecture with fewer parameters while maintaining good performance for real-time object detection. The study examines the deployment of optimized Tiny YOLO models on embedded systems, incorporating techniques like quantization, pruning, and clustering to reduce model size, enhance speed, and lower power consumption. Optimization methods show significant improvements, with quantization speeding up inference, pruning eliminating redundant parameters, and clustering enhancing accuracy. Specifically, the study compares the performance of Tiny YOLO under these optimization techniques, presenting results for both Pascal VOC and COCO datasets. The results demonstrate that optimized Tiny YOLO models are effective for real-time object detection on microcontrollers. These methods enable the efficient deployment of deep learning models for edge computing, without relying on cloud infrastructure.
[1] Kotha, H.D. and Gupta, V.M., 2018. IoT application: a survey. Int. J. Eng. Technol, 7(2.7), pp.891-896.
[2] Dian, F.J., Vahidnia, R. and Rahmati, A., 2020. Wearables and the Internet of Things (IoT), applications, opportunities, and challenges: A Survey. IEEE access, 8, pp.69200-69211.
[3] Asghari, P., Rahmani, A.M. and Javadi, H.H.S., 2019. Internet of Things applications: A systematic review. Computer Networks, 148, pp.241-261.
[4] Li, H., Ota, K. and Dong, M., 2018. Learning IoT in edge: Deep learning for the Internet of Things with edge computing. IEEE network, 32(1), pp.96-101.
[5] Liangzhen Lai and Naveen Suda. 2018. Enabling Deep Learning at the IoT Edge. In Proceedings of the International Conference on Computer-Aided Design (San Diego, California) (ICCAD ’18). ACM, New York, NY, USA, Article 135, 6 pages.
[6] Singh, R. and Gill, S.S., 2023. Edge AI: a survey. Internet of Things and Cyber-Physical Systems, 3, pp.71-92.
[7] Wang, X., Han, Y., Leung, V.C., Niyato, D., Yan, X. and Chen, X., 2020. Edge AI: Convergence of edge computing and artificial intelligence (pp. 3-149). Singapore: Springer.
[8] David, R., Duke, J., Jain, A., Janapa Reddi, V., Jeffries, N., Li, J., Kreeger, N., Nappier, I., Natraj, M., Wang, T. and Warden, P., 2021. Tensorflow lite micro: Embedded machine learning for tinyml systems. Proceedings of Machine Learning and Systems, 3, pp.800-811.
[9] Rashidi, M., 2022. Application of TensorFlow lite on embedded devices: A hands-on practice of TensorFlow model conversion to TensorFlow Lite model and its deployment on Smartphone to compare model’s performance.
[10] Mamtha, G.N., Sharma, S. and Sing, N., 2023, December. Embedded Machine Learning with Tensorflow Lite Micro. In 2023 International Conference on Power Energy, Environment & Intelligent Control (PEEIC) (pp. 1480-1483).
[11] Berthelier, A., Chateau, T., Duffner, S., Garcia, C. and Blanc, C., 2021. Deep model compression and architecture optimization for embedded systems: A survey. Journal of Signal Processing Systems, 93(8), pp.863-878.
[12] TensorFlow Lite, TensorFlow, 2021. Available online: https://www.tensorflow.org/lite
[13] Hua, H., Li, Y., Dong, N., Li, W. and Cao, J., 2023. Edge computing with artificial intelligence: A machine learning perspective. ACM Computing Surveys, 55(9), pp.1-35.
[14] Deng, S., Zhao, H., Fang, W., Yin, J., Dustdar, S. and Zomaya, A.Y., 2020. Edge intelligence: The confluence of edge computing and artificial intelligence. IEEE Internet of Things Journal, 7(8), pp.7457-7469.
[15] Grzesik, P. and Mrozek, D., 2024. Combining Machine Learning and Edge Computing: Opportunities, Challenges, Platforms, Frameworks, and Use Cases. Electronics, 13(3), p.640.
[16] Li, H., Ota, K. and Dong, M., 2018. Learning IoT in edge: Deep learning for the Internet of Things with edge computing. IEEE network, 32(1), pp.96-101.
[17] Chang, Z., Liu, S., Xiong, X., Cai, Z. and Tu, G., 2021. A survey of recent advances in edge-computing-powered artificial intelligence of things. IEEE Internet of Things Journal, 8(18), pp.13849-13875.
[18] Sivaganesan, D., 2019. Design and development ai-enabled edge computing for intelligent-iot applications. Journal of trends in Computer Science and Smart technology (TCSST), 1(02), pp.84-94.
[19] Jain, S., Dash, S. and Deorari, R., 2022, October. Object detection using coco dataset. In 2022 International Conference on Cyber Resilience (ICCR) (pp. 1-4). IEEE.
[20] Shetty, S., 2016. Application of convolutional neural network for image classification on Pascal VOC challenge 2012 dataset. arXiv preprint arXiv:1607.03785.
[21] Li, C., Wang, J., Wang, S. and Zhang, Y., 2024. A review of IoT applications in healthcare. Neurocomputing, 565, p.127017.
[22] Afzal, B., Umair, M., Shah, G.A. and Ahmed, E., 2019. Enabling IoT platforms for social IoT applications: Vision, feature mapping, and challenges. Future Generation Computer Systems, 92, pp.718-731.
[23] Dian, F.J., Vahidnia, R. and Rahmati, A., 2020. Wearables and the Internet of Things (IoT), applications, opportunities, and challenges: A Survey. IEEE access, 8, pp.69200-69211.
[24] Tripathi, A., Gupta, M.K., Srivastava, C., Dixit, P. and Pandey, S.K., 2022, December. Object detection using YOLO: A survey. In 2022 5th International Conference on Contemporary Computing and Informatics (IC3I) (pp. 747-752). IEEE.
[25] Hussain, M., 2024. Yolov1 to v8: Unveiling each variant–a comprehensive review of yolo. IEEE Access, 12, pp.42816-42833.
[26] Babaei, P., 2024, March. Convergence of Deep Learning and Edge Computing using Model Optimization. In 2024 13th Iranian/3rd International Machine Vision and Image Processing Conference (MVIP) (pp. 1-6). IEEE.
[27] Gholami, A., Kim, S., Dong, Z., Yao, Z., Mahoney, M.W. and Keutzer, K., 2022. A survey of quantization methods for efficient neural network inference. In Low-Power Computer Vision (pp. 291-326). Chapman and Hall/CRC.
[28] Rokh, B., Azarpeyvand, A. and Khanteymoori, A., 2023. A comprehensive survey on model quantization for deep neural networks in image classification. ACM Transactions on Intelligent Systems and Technology, 14(6), pp.1-50.
[29] Liang, T., Glossner, J., Wang, L., Shi, S. and Zhang, X., 2021. Pruning and quantization for deep neural network acceleration: A survey. Neurocomputing, 461, pp.370-403.
[30] Madnur, P.V., Dabade, S.H., Khanapure, A., Rodrigues, S., Hegde, S. and Kulkarni, U., 2023, November. Enhancing Deep Neural Networks through Pruning followed by Quantization Pipeline: A Comprehensive Review. In 2023 2nd International Conference on Futuristic Technologies (INCOFT) (pp. 1-8). IEEE.
[31] Choudhary, T., Mishra, V., Goswami, A. and Sarangapani, J., 2020. A comprehensive survey on model compression and acceleration. Artificial Intelligence Review, 53, pp.5113-5155.
