Abstract
Nowadays, machine learning algorithms are used intensively for the detection and identification of various entities on an image with high level of accuracy. Deep learning provides even higher performance results in image processing. However, deep learning requires high computing effort for classification and thus limiting the usability of method in AI at the edge especially in the presence of different classes. In this paper, deep learning is applied as a solution to the problem of detecting and identifying more than one entity of different classes in the image in real time at the edge. In the study, a multi-class traffic sign data set was used. The data set consists of six different sign classes and 6000 high resolution images (1280 × 720). Performance of two models, DetectNet and MobileNet (MobiNet) models were compared. MobileNet had better accuracy compared to DetectNet since it has higher number of parameters. But high number of parameters lessens the real time performance of the model at the edge. According to the tests performed on the Nvidia Jetson TX2 embedded system, the DetectNet model can provide 6–7 FPS performance while the MobileNet 160 version of MobileNet model with \( \propto \; = \;0.25 \) has achieved only of 1–2 FPS.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
LeCun, Y.: Backpropagation applied to handwritten zip code recognition (1989)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Kapellmann-Zafra, G.: Design and Development of a FROG Instrument for the Characterization of Femto-second Laser Pulses (2013)
Dumoulin, V., Visin, F.: A Guide to Convolution Arithmetic for Deep (2018)
Kurt, F.: Evrişimli Sinir Ağlarında Hiper Parametrelerin Etkisinin Incelenmesİ (2017)
Tao, A., Barker, J., Sarathy, S.: DetectNet: Deep Neural Network for Object Detection in DIGITS, NVIDIA, 11 Ağustos 2016. https://devblogs.nvidia.com/detectnet-deep-neural-network-object-detection-digits/. [%1 tarihinde erişilmiştir12 Kasım 2018]
Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, T., Adam, H.: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision (2017)
Google, TensorBoard: Graph Visualization, TensorFlow (Google). https://www.tensorflow.org/guide/graph_viz. [%1 tarihinde erişilmiştir 24 12 2018]
Acknowledgment
The authors would like to thank to Open Zeka Information Technologies and PNY for their hardware support.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Sonmez, D., Cetin, A. (2020). Real Time Performance Comparison of Multi-class Deep Learning Methods at the Edge. In: Hemanth, D., Kose, U. (eds) Artificial Intelligence and Applied Mathematics in Engineering Problems. ICAIAME 2019. Lecture Notes on Data Engineering and Communications Technologies, vol 43. Springer, Cham. https://doi.org/10.1007/978-3-030-36178-5_74
Download citation
DOI: https://doi.org/10.1007/978-3-030-36178-5_74
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36177-8
Online ISBN: 978-3-030-36178-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)