Abstract
Recent research on convolutional neural network (CNN) has seen advances in accuracy improvements of object detection, recognition, tracking, and segmentation applications. Many CNN architectures have been developed in the last five years to achieve good amount of accuracy. To deploy trained CNN models on FPGA, Raspberry Pi and other hardware devices with reduced model size is a key area for research. In this paper, a hybrid approach for pixel level semantic segmentation using SqueezeNet and SegNet is proposed. The hybrid architecture enhances the accuracy to 76%.
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
References
Vijay Badrinarayanan, Alex Kendall and Roberto Cipolla “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation.” PAMI, 2017.
Chunpeng Wu, Hsin-Pai Cheng, Sicheng Li, Hai (Helen) Li, Yiran Chen, “ApesNet: a pixel-wise efficient segmentation network for embedded devices”, IET Cyber-Physical Systems: Theory & Applications, ISSN 2398-3396, ISSN 2398-3396, 2016.
Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, “Squeezenet: alexnet-level accuracy with 50x fewer parameters and < 0.5mb model size”, arXiv:1602.07360, 2016.
Long, J., Shelhamer, E., Darrell, T.: ‘Fully convolutional networks for semantic segmentation’. Int. Conf. on Computer Vision and Pattern Recognition (CVPR), 2015.
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” CoRR, vol. abs/1409.1556, 2014.
Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks”, NIPS’12 Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1, Pages 1097–1105.
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
K. He, X. Zhang, S. Ren, J. Sun, “Deep Residual Learning for Image Recognition”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
Aabhish, sangpilkim, euge@purdue.edu “ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation”, arXiv:1606.02147v1.
https://wiki.tum.de/display/lfdv/Image+Semantic+Segmentation.
A. Garcia-Garcia, S. Orts-Escolano, S.O. Oprea, V. Villena-Martinez, and J. Garcia-Rodriguez, “A Review on Deep Learning Techniques Applied to Semantic Segmentation”, arXiv:1704.06857v1, 2017.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mohanraj, V., Guda, R., V Kameshwar Rao, J. (2019). Hybrid Approach for Pixel-Wise Semantic Segmentation Using SegNet and SqueezeNet for Embedded Platforms. In: Bapi, R., Rao, K., Prasad, M. (eds) First International Conference on Artificial Intelligence and Cognitive Computing . Advances in Intelligent Systems and Computing, vol 815. Springer, Singapore. https://doi.org/10.1007/978-981-13-1580-0_15
Download citation
DOI: https://doi.org/10.1007/978-981-13-1580-0_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-1579-4
Online ISBN: 978-981-13-1580-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)