Abstract
Modern edge devices are capable of onboard processing of computational heavy tasks, such as artificial intelligence-driven computer vision. An increasing number of deep learning-based object detection networks are frequently proposed with lightweight structures to be deployed on mobile platforms without the need for cloud computing. Comparing these networks is challenging due to the variety in hardware and frameworks and because of different model complexity. This paper investigates models that can be deployed on cross-functional single-board computers without utilizing the power of GPUs. This paves the way towards performing accurate, cheap, and fast object detection, even suited for industrial applications within Industry 4.0. Four state-of-the-art neural networks are trained via transfer learning, then deployed and tested on the Raspberry Pi 4B and the Coral Edge TPU accelerator from Google as a co-processor. The comparison of the models focuses on the inference time, the versatility of the deployment, training, and finally the accuracy of the retrained networks on a selection of datasets with different feature characteristics.
Our code can be found in the following repository: https://github.com/kberci/Deep-Learning-based-Object-Detection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Git repository: https://github.com/ultralytics/yolov5.
References
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)
Dong, H., Song, K., He, Y., Xu, J., Yan, Y., Meng, Q.: PGA-Net: pyramid feature fusion and global context attention network for automated surface defect detection. IEEE Trans. Ind. Inform. 16(12), 7448–7458 (2019)
Ghosh, A., Al Mahmud, S.A., Uday, T.I.R., Farid, D.M.: Assistive technology for visually impaired using tensor flow object detection in raspberry Pi and coral USB accelerator. In: 2020 IEEE Region 10 Symposium (TENSYMP), pp. 186–189. IEEE (2020)
Hosseininoorbin, S., Layeghy, S., Sarhan, M., Jurdak, R., Portmann, M.: Exploring edge TPU for network intrusion detection in IoT. arXiv preprint arXiv:2103.16295 (2021)
Kljucaric, L., Johnson, A., George, A.D.: Architectural analysis of deep learning on edge accelerators. In: 2020 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1–7. IEEE (2020)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Lin, T., Maire, M., et al.: Microsoft COCO: common objects in context. CoRR abs/1405.0312 (2014), http://arxiv.org/abs/1405.0312
Liu, L., et al.: Deep learning for generic object detection: a survey. Int. J. Comput. Vis. 128(2), 261–318 (2020)
Murthy, C.B., Hashmi, M.F., Bokde, N.D., Geem, Z.W.: Investigations of object detection in images/videos using various deep learning techniques and embedded platforms–A comprehensive review. Appl. Sci. 10(9), 3280 (2020)
Nguyen, H.H., Tran, D.N.N., Jeon, J.W.: Towards real-time vehicle detection on edge devices with Nvidia Jetson TX2. In: 2020 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), pp. 1–4. IEEE (2020)
Park, K., et al.: Real-time mask detection on google edge TPU. arXiv preprint arXiv:2010.04427 (2020)
Pedersen, M.R., et al.: Robot skills for manufacturing: from concept to industrial deployment. Robot. Comput-Integ. Manuf. 37(282–291) (2015)
Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520, January 2018
Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection (2020)
Tran, D.N.N., Nguyen, H.H., Pham, L.H., Jeon, J.W.: Object detection with deep learning on drive PX2. In: 2020 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), pp. 1–4. IEEE (2020)
Verucchi, M., et al.: A Systematic assessment of embedded neural networks for object detection. In: 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA). vol. 1, pp. 937–944. IEEE (2020)
Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Scaled-YOLOv4: Scaling Cross Stage Partial Network (2021)
Wu, X., Sahoo, D., Hoi, S.C.: Recent advances in deep learning for object detection. Neurocomputing 396, 39–64 (2020)
Xie, L.: Hardhat (2019). https://doi.org/10.7910/DVN/7CBGOS, https://doi.org/10.7910/DVN/7CBGOS
Xiong, Y., et al.: MobileDets: searching for object detection architectures for mobile accelerators. arXiv preprint arXiv:2004.14525, July 2020
Acknowledgements
The authors would like to thank ProInvent A/S for its support.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Kovács, B., Henriksen, A.D., Stets, J.D., Nalpantidis, L. (2021). Object Detection on TPU Accelerated Embedded Devices. In: Vincze, M., Patten, T., Christensen, H.I., Nalpantidis, L., Liu, M. (eds) Computer Vision Systems. ICVS 2021. Lecture Notes in Computer Science(), vol 12899. Springer, Cham. https://doi.org/10.1007/978-3-030-87156-7_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-87156-7_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87155-0
Online ISBN: 978-3-030-87156-7
eBook Packages: Computer ScienceComputer Science (R0)