Abstract
We provide an overview of the Intel Distribution of OpenVINO toolkit. The application of the OpenVINO toolkit is represented on the case study of semantic segmentation of on-road images. We provide a step-by-step tutorial for the problem solution based on the Dilation10 model, trained on the Cityscapes dataset. The Inference Engine component of the OpenVINO toolkit is used to implement inference of deep model. We focus on synchronous inference mode. Comparison of on-road semantic segmentation models supported by the OpenVINO toolkit is provided. Performance analysis of the Dilation10 inference implemented using various deep learning tools is carried out.
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
Intel Distribution of OpenVINO toolkit. https://software.intel.com/en-us/openvino-toolkit
Noh, H., et al.: Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE ICCV, pp. 1520–1528 (2015)
Badrinarayanan, V., et al.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. arXiv preprint arXiv:1511.00561 (2015)
Long, J., et al.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on CVPR, pp. 3431–3440 (2015)
Liu, W., Rabinovich, A., Berg, A.C.: ParseNet: looking wider to see better. arXiv preprint arXiv:1506.04579 (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. arXiv preprint arXiv:1505.04597 (2015)
Paszke, A., et al.: ENet: a deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147 (2016)
Zhao, H., et al.: ICNet for real-time semantic segmentation on high-resolution images. arXiv preprint arXiv:1704.08545 (2017)
Chen, L.C., et al.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv preprint arXiv:1412.7062 (2014)
Chen, L.C., et al.: Attention to scale: scale-aware semantic image segmentation. In: Proceedings of the IEEE Conference on CVPR, pp. 3640–3649 (2016)
Lin, G., et al.: Efficient piecewise training of deep structured models for semantic segmentation. In: Proceedings of the IEEE Conference on CVPR, pp. 3194–3203 (2016)
Wu, Z., Shen, C., Hengel, A.: Wider or deeper: revisiting the ResNet model for visual recognition. arXiv preprint arXiv:1611.10080 (2016)
Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1529–1537 (2015)
Cogswell, M., et al.: Combining the best of graphical models and ConvNets for semantic segmentation. arXiv preprint arXiv:1412.4313 (2014)
Liu, Z., et al.: Deep learning Markov random field for semantic segmentation. arXiv preprint arXiv:1606.07230 (2016)
Sidnev, A., et al.: Semantic segmentation review (2018). https://software.intel.com/en-us/download/semantic-segmentation-review
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2015)
The Cityscapes Dataset. https://www.cityscapes-dataset.com
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on CVPR (2016)
TensorFlow. https://www.tensorflow.org
ONNX. Open Neural Network Exchange Format. https://onnx.ai
OpenCV. http://opencv.org
OpenVX. https://www.khronos.org/openvx
Open Model Zoo repository. https://github.com/opencv/open_model_zoo
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2016)
Intel Distribution of OpenVINO toolkit. Documentation. https://docs.openvinotoolkit.org
Deep Learning Deployment Toolkit. https://github.com/opencv/dldt
Overview of Inference Engine Python API. https://docs.openvinotoolkit.org/2019_R1/_inference_engine_ie_bridges_python_docs_api_overview.html
Solving the problem of semantic segmentation using the Inference Engine of Intel Distribution of OpenVINO toolkit. https://github.com/itlab-vision/tutorials/tree/solution/aist2019-openvino-semseg
Mapillary Vistas Dataset. https://www.mapillary.com/dataset/vistas
Mighty AI. https://mighty.ai/blog/tag/open-dataset
Acknowledgements
The research was supported by the Intel Corporation. The authors thank company’s employees for their help and attention to the research.
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
Kustikova, V. et al. (2019). Intel Distribution of OpenVINO Toolkit: A Case Study of Semantic Segmentation. In: van der Aalst, W., et al. Analysis of Images, Social Networks and Texts. AIST 2019. Lecture Notes in Computer Science(), vol 11832. Springer, Cham. https://doi.org/10.1007/978-3-030-37334-4_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-37334-4_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37333-7
Online ISBN: 978-3-030-37334-4
eBook Packages: Computer ScienceComputer Science (R0)