This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Edge Enhanced Traffic Scene Segmentation Algorithm with Deep Neural Network
Technical Paper
2017-01-1967
ISSN: 0148-7191, e-ISSN: 2688-3627
This content contains downloadable datasets
Annotation ability available
Sector:
Language:
English
Abstract
Image segmentation is critical in autonomous driving field. It can reveal essential clues such as objects’ shape or boundary information. The information, moreover, can be leveraged as input information of other tasks: vehicle detection, for example, or vehicle trajectory prediction. SegNet, one deep learning based segmentation model proposed by Cambridge, has been a public baseline for scene perception tasks. It, however, suffers an accuracy deficiency in objects marginal area. Segmentation of this area is very challenging with current models. To alleviate the problem, in this paper, we propose one edge enhanced deep learning based model. Specifically, we first introduced one simple, yet effective Artificial Interfering Mechanism (AIM) which feeds segmentation model manual extracted key features. We argue this mechanism possesses the ability to enhance essential features extraction and hence, ameliorate the model performance. Other modifications of model structures were also designed for further improving model’s feature extraction ability. Besides, one Pixel Alignment Unit (PAU) was presented for pixel level alignment. The unit is designed based on Bidirectional Long Short Term Memory (Bi-LSTM) unit and, according on our design, is able to reconstruct and extract pixel spatial features which is a key clue for the segmentation. Combined with mentioned methods, in the end, an integrated model was proposed. To evaluate our model, CamVid dataset were adopted in experiments. The experiment result showed that our model has the ability to refine objects margin area segmentation results. Our contribution lies in that we attempt to boost model performance through artificially interfered model feature extraction phases and attempt to adopt the Bi-LSTM structure to reconstruct and extract pixels’ spatial features.
Authors
Topic
Citation
Liu, W., Tian, H., Hu, J., Cheng, S. et al., "Edge Enhanced Traffic Scene Segmentation Algorithm with Deep Neural Network," SAE Technical Paper 2017-01-1967, 2017, https://doi.org/10.4271/2017-01-1967.Data Sets - Support Documents
Title | Description | Download |
---|---|---|
Unnamed Dataset 1 | ||
Unnamed Dataset 2 |
Also In
References
- Badrinarayanan , Vijay , Kendall Alex , and Cipolla Roberto SegNet: A Deep Convolutional Encoder-Decoder Architecture for Scene Segmentation IEEE Transactions on Pattern Analysis and Machine Intelligence 2017 10.1109/TPAMI.2016.2644615
- Chen , Liang-Chieh et al. Semantic image segmentation with deep convolutional nets and fully connected crfs arXiv preprint arXiv:1412.7062 2014
- Chen , Liang-Chieh et al. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs arXiv preprint arXiv:1606.00915 2016
- Cho , Kyunghyun et al. On the properties of neural machine translation: Encoder-decoder approaches arXiv preprint arXiv:1409.1259 2014
- Chung , Junyoung et al. Empirical evaluation of gated recurrent neural networks on sequence modeling arXiv preprint arXiv:1412.3555 2014
- Elman , Jeffrey L. Finding structure in time Cognitive science 14 2 1990 179 211
- Girshick , Ross. Fast r-cnn Proceedings of the IEEE International Conference on Computer Vision 2015 10.1109/ICCV.2015.169
- Graves , Alex , and Schmidhuber Jürgen Framewise phoneme classification with bidirectional LSTM and other neural network architectures Neural Networks 18 5 2005 602 610 10.1016/j.neunet.2005.06.042
- Graves , Alex , and Schmidhuber Jürgen Offline handwriting recognition with multidimensional recurrent neural networks Advances in neural information processing systems 2009 10.1007/978-1-4471-4072-6_12
- Graves , Alex , Jaitly Navdeep , and Mohamed Abdel-rahman Hybrid speech recognition with deep bidirectional LSTM Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on IEEE 2013 10.1109/ASRU.2013.6707742
- Hariharan , Bharath et al. Hypercolumns for object segmentation and fine-grained localization Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015 10.1109/CVPR.2015.7298642
- He , Kaiming et al. Mask R-CNN arXiv preprint arXiv:1703.06870 2017
- Hochreiter , Sepp , and Schmidhuber Jürgen Long short-term memory Neural computation 9 8 1997 1735 1780 10.1162/neco.1997.9.8.1735
- Ioffe , Sergey , and Szegedy Christian Batch normalization: Accelerating deep network training by reducing internal covariate shift arXiv preprint arXiv:1502.03167 2015
- Jain , Ashesh et al. Structural-RNN: Deep learning on spatio-temporal graphs Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016 10.1109/CVPR.2016.573
- Jiang , Jiangmin , and Song Xiaonan An Optimized Higher Order CRF for Automated Labeling and Segmentation of Video Objects IEEE Transactions on Circuits and Systems for Video Technology 26 3 2016 506 516 10.1109/TCSVT.2015.2416557
- Karpathy , Andrej , and Fei-Fei Li Deep visual-semantic alignments for generating image descriptions Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015 10.1109/TPAMI.2016.2598339
- Kulkarni , Girish et al. Babytalk: Understanding and generating simple image descriptions IEEE Transactions on Pattern Analysis and Machine Intelligence 35 12 2013 2891 2903 10.1109/TPAMI.2012.162
- Lin , Guosheng et al. Efficient piecewise training of deep structured models for semantic segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016 10.1109/CVPR.2016.348
- Liu , Ziwei et al. Semantic image segmentation via deep parsing network Proceedings of the IEEE International Conference on Computer Vision 2015 10.1109/ICCV.2015.162
- Mehra , Jyotsana , and Neeru Nirvair A brief review: super-pixel based image segmentation methods Imperial Journal of Interdisciplinary Research 2 9 2016
- Mou , Lichao , Ghamisi Pedram , and Zhu Xiao Xiang Deep Recurrent Neural Networks for Hyperspectral Image Classification IEEE Transactions on Geoscience and Remote Sensing 2017 10.1109/TGRS.2016.2636241
- Noh , Hyeonwoo , Hong Seunghoon , and Han Bohyung Learning deconvolution network for semantic segmentation Proceedings of the IEEE International Conference on Computer Vision 2015 10.1109/ICCV.2015.178
- Papandreou , George et al. Weakly-and semi-supervised learning of a DCNN for semantic image segmentation arXiv preprint arXiv:1502.02734 2015
- Pinheiro , Pedro HO , and Collobert Ronan Recurrent Convolutional Neural Networks for Scene Labeling ICML 2014
- Redmon , Joseph , and Farhadi Ali YOLO9000: Better, Faster, Stronger arXiv preprint arXiv:1612.08242 2016
- Richard , Alexander , Kuehne Hilde , and Gall Juergen Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling arXiv preprint arXiv:1703.08132 2017
- Shao , Yan et al. Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF arXiv preprint arXiv:1704.01314 2017
- Shelhamer , Evan , Long Jonathon , and Darrell Trevor Fully convolutional networks for semantic segmentation IEEE transactions on pattern analysis and machine intelligence 2016 10.1109/TPAMI.2016.2572683
- Socher , Richard et al. Convolutional-Recursive Deep Learning for 3D Object Classification NIPS 3 7 2012
- Stewart , Russell , Andriluka Mykhaylo , and Ng Andrew Y. End-to-end people detection in crowded scenes Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016 10.1109/CVPR.2016.255
- Szegedy , Christian et al. Going deeper with convolutions Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015 10.1109/CVPR.2015.7298594
- Szegedy , Christian et al. Inception-v4, inception-resnet and the impact of residual connections on learning arXiv preprint arXiv:1602.07261 2016
- Tripathi , Subarna et al. Context matters: Refining object detection in video with recurrent neural networks arXiv preprint arXiv:1607.04648 2016
- Visin , Francesco et al. Renet: A recurrent neural network based alternative to convolutional networks arXiv preprint arXiv:1505.00393 2015
- Yin, Cho , Kyunghyun et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation arXiv preprint arXiv:1406.1078 2014