Semantic Segmentation for Traffic Scene Understanding Based on Mobile Networks
Published August 7, 2018 by SAE International in United States
Downloadable datasets for this paper availableAnnotation of this paper is available
Real-time and reliable perception of the surrounding environment is an important prerequisite for advanced driving assistance system (ADAS) and automatic driving. And vision-based detection plays a significant role in environment perception for automatic vehicles. Although deep convolutional neural networks enable efficient recognition of various objects, it has difficulty in accurately detecting special vehicles, rocks, road pile, construction site, fence and so on. In this work, we address the task of traffic scene understanding with semantic image segmentation. Both driveable area and the classification of object can be attained from the segmentation result. First, we define 29 classes of objects in traffic scenarios with different labels and modify the Deeplab V2 network. Then in order to reduce the running time, MobileNet architecture is applied to generate the feature map instead of the original models. After that, the Cityscapes Dataset, which focuses on semantic understanding of urban street scenes, is used to train the network with the modified labels. Finally, we test the network and measure the performance. With the same network (Deeplab V2), VGG-16 and ResNet-101 are also tested. Consequently, we attain similar performance with MobileNet and ResNet-101 models, but using MobileNet requires much fewer operations and time. Compared with VGG-16, MobileNet architecture has better performance and is also more efficient. The using of lightweight mobile models reduce the computation and enable the on-device applications for semantic segmentation in traffic scene understanding.
CitationHao, P., Chen, S., Bai, J., Huang, L. et al., "Semantic Segmentation for Traffic Scene Understanding Based on Mobile Networks," SAE Technical Paper 2018-01-1600, 2018, https://doi.org/10.4271/2018-01-1600.
Data Sets - Support Documents
|[Unnamed Dataset 1]|
- Kang, Y. et al., “Multiband Image Segmentation and Object Recognition for Understanding Road Scenes,” IEEE Transactions on Intelligent Transportation Systems 12(4):1423-1433, 2011.
- Laddha, A. et al., “Map-Supervised Road Detection,” Intelligent Vehicles Symposium IEEE, 2016, 118-123.
- Oliveira, G.L., Burgard, W., and Brox, T., “Efficient Deep Models for Monocular Road Segmentation,” IEEE/RSJ International Conference on Intelligent Robots and Systems IEEE, 2016, 4885-4891.
- Chen, L.C. et al., “DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs,” IEEE Transactions on Pattern Analysis & Machine Intelligence 99:1-1, 2017.
- Sandler, M. et al., “Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation,” 2018.
- Wu, X., “Fully Convolutional Networks for Semantic Segmentation,” Computer Science, 2015.
- Noh, H., Hong, S., and Han, B., “Learning Deconvolution Network for Semantic Segmentation,” IEEE International Conference on Computer Vision, 2016, 1520-1528.
- Badrinarayanan, V., Handa, A., and Cipolla, R., “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling,” Computer Science, 2015.
- Chen, L.C. et al., “Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs,” Computer Science 4:357-361, 2014.
- Peng, C. et al., “Large Kernel Matters-Improve Semantic Segmentation by Global Convolutional Network,” 2017.
- He, K. and Sun, J., “Convolutional Neural Networks at Constrained Time Cost,” IEEE Conference on Computer Vision and Pattern Recognition IEEE, 2015, 5353-5360.
- Szegedy, C. et al., “Going Deeper with Convolutions,” IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, 2015, 1-9.
- Simonyan, K. and Zisserman, A., “Very Deep Convolutional Networks for Large-Scale Image Recognition,” Computer Science, 2014.
- He, K. et al., “Deep Residual Learning for Image Recognition,” IEEE Conference on Computer Vision and Pattern Recognition IEEE, 2016, 770-778.
- Zhang, X. et al., “ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices,” 2017.
- Howard, A.G. et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” 2017.
- Xie, S. et al., “Aggregated Residual Transformations for Deep Neural Networks,” IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, 2017, 5987-5995.