Abstract
Embedded video-processing applications are everywhere, and need to be low-energy in order to extend battery life. Convolutional Neural Networks (CNNs), frequently used for this task, fail to explore the intrinsic redundancy present in videos: similarity between sequential frames means that analyzing all frames can be avoided. On top of that, while several hardware solutions for low-energy execution have been proposed, they require extra or dedicated hardware, which makes them non attractive for low cost applications. In this work we propose a technique that uses frame similarity to identify and process only areas that have a significant difference when comparing two subsequent frames. Our technique reduces energy consumption by discarding unneeded operations, and can also be used in low-cost hardware readily available for IoT applications. We obtain up to 12-80x speedup of CNN execution with software-only modifications that require no network retraining while impacting little on accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, T., et al.: DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning. SIGARCH Comput. Archit. News 42(1), 269–284 (2014). https://doi.org/10.1145/2654822.2541967
Chen, Y.H., Krishna, T., Emer, J.S., Sze, V.: Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J. Solid-State Circ. 52(1), 127–138 (2017). https://doi.org/10.1109/JSSC.2016.2616357
Honovich, J.: Average frame rate video surveillance 2011 (2011). https://ipvm.com/reports/recording-frame-rate-whats-actually-being-used
Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221–231 (2013). https://doi.org/10.1109/TPAMI.2012.59
Kang, D., Emmons, J., Abuzaid, F., Bailis, P., Zaharia, M.: Optimizing deep CNN-based queries over video streams at scale. CoRR abs/1703.02529 (2017). http://arxiv.org/abs/1703.02529
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2014
Livingit: average human running speed: broken down age-wise (2018). https://www.iamlivingit.com/running/average-human-running-speed
Redmon, J.: Darknet: open source neural networks in c (2016). http://pjreddie.com/darknet/
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788, June 2016. https://doi.org/10.1109/CVPR.2016.91
Riera, M., Arnau, J., Gonzalez, A.: Computation reuse in DNNs by exploiting input similarity. In: 2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), pp. 57–68, June 2018. https://doi.org/10.1109/ISCA.2018.00016
Robert, F., Santos-Victor, J.C.: CAVIAR: context aware vision using image-based active recognition (2006). http://homepages.inf.ed.ac.uk/rbf/CAVIAR/
Sen, S., Raghunathan, A.: Approximate computing for long short term memory (LSTM) neural networks. IEEE Trans. Comput.-Aided Design Integr. Circ. Syst. 37(11), 2266–2276 (2018). https://doi.org/10.1109/TCAD.2018.2858362
Shafiee, M.J., Chywl, B., Li, F., Wong, A.: Fast YOLO: a fast you only look once system for real-time embedded object detection in video. CoRR abs/1709.05943 (2017). http://arxiv.org/abs/1709.05943
Sze, V., Chen, Y.H., Yang, T.J., Emer, J.S.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295–2329 (2017). https://doi.org/10.1109/JPROC.2017.2761740
Tan, C., Kulkarni, A., Venkataramani, V., Karunaratne, M., Mitra, T., Peh, L.S.: LOCUS: low-power customizable many-core architecture for wearables. ACM Trans. Embed. Comput. Syst. 17(1), 16:1–16:26 (2017). https://doi.org/10.1145/3122786
Teng, Z., Xing, J., Wang, Q., Lang, C., Feng, S., Jin, Y.: Robust object tracking based on temporal and spatial deep networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1153–1162, October 2017. https://doi.org/10.1109/ICCV.2017.130
Yue-Hei Ng, J., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015
Zhu, Y., Samajdar, A., Mattina, M., Whatmough, P.N.: Euphrates: algorithm-SoC co-design for low-power mobile continuous vision. CoRR abs/1803.11232 (2018). http://arxiv.org/abs/1803.11232
Acknowledgements
This work was supported by CAPES, CNPQ and FAPERGS.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Gonçalves, L.R., Draghetti, L.K., Rech, P., Carro, L. (2019). Using Frame Similarity for Low Energy Software-Only IoT Video Recognition. In: Pnevmatikatos, D., Pelcat, M., Jung, M. (eds) Embedded Computer Systems: Architectures, Modeling, and Simulation. SAMOS 2019. Lecture Notes in Computer Science(), vol 11733. Springer, Cham. https://doi.org/10.1007/978-3-030-27562-4_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-27562-4_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27561-7
Online ISBN: 978-3-030-27562-4
eBook Packages: Computer ScienceComputer Science (R0)