Semantic Segmentation of Video Sequences with Convolutional LSTMs

@article{Pfeuffer2019SemanticSO,
  title={Semantic Segmentation of Video Sequences with Convolutional LSTMs},
  author={Andreas Pfeuffer and K. Schulz and K. Dietmayer},
  journal={2019 IEEE Intelligent Vehicles Symposium (IV)},
  year={2019},
  pages={1441-1447}
}
  • Andreas Pfeuffer, K. Schulz, K. Dietmayer
  • Published 2019
  • Computer Science
  • 2019 IEEE Intelligent Vehicles Symposium (IV)
    • Most of the semantic segmentation approaches have been developed for single image segmentation, and hence, video sequences are currently segmented by processing each frame of the video sequence separately. The disadvantage of this is that temporal image information is not considered, which improves the performance of the segmentation approach. One possibility to include temporal information is to use recurrent neural networks. However, there are only a few approaches using recurrent networks… CONTINUE READING
    View on IEEE
    arxiv.org
    17 Citations
    Background Citations
    9
    Methods Citations
    6
    Results Citations
    2
    17 Citations
    Citation Type

    Citation Type

    Separable Convolutional LSTMs for Faster Video Segmentation
    • 4
    • PDF
    Robust Semantic Segmentation in Adverse Weather Conditions by means of Fast Video-Sequence Segmentation
    • Andreas Pfeuffer, K. Dietmayer
    • Computer Science, Engineering
    • 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)
    • 2020
    • 1
    • PDF
    Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation
    • PDF
    Real-time pedestrian video segmentation using memory network
    • F. Zhao, J. Liu
    • Engineering
    • International Symposium on Multispectral Image Processing and Pattern Recognition
    • 2020
    A Survey on Deep Learning Methods for Semantic Image Segmentation in Real-Time
    • 1
    • PDF
    A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images.
    • 8
    • PDF
    A SURVEY ON DEEP LEARNING-BASED ARCHITECTURES
    • 2019
    Gated Recurrent Networks for Video Super Resolution
    • PDF
    Video scene parsing: An overview of deep learning methods and datasets
    • 1
    Sequential vessel segmentation via deep channel attention network
    • PDF

    References

    SHOWING 1-10 OF 23 REFERENCES
    Scene labeling with LSTM recurrent neural networks
    • 264
    • PDF
    Recurrent Fully Convolutional Networks for Video Segmentation
    • 56
    • PDF
    SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
    • 5,475
    • PDF
    Semantic Segmentation of RGBD Videos with Recurrent Fully Convolutional Neural Networks
    • 9
    • Highly Influential
    • PDF
    Fully Convolutional Networks for Semantic Segmentation
    • 9,026
    • Highly Influential
    • PDF
    End-to-End Instance Segmentation and Counting with Recurrent Attention
    • 59
    • PDF
    Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
    • 2,564
    • PDF
    DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
    • 6,198
    • Highly Influential
    • PDF
    Large-Scale Video Classification with Convolutional Neural Networks
    • 4,379
    • PDF
    ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
    • 853
    • PDF