Multi-stream CNN based Video Semantic Segmentation for Automated Driving

被引:3
|
作者
Sistu, Ganesh [1 ]
Chennupati, Sumanth [2 ]
Yogamani, Senthil [1 ]
机构
[1] Valeo Vis Syst, Dublin, Ireland
[2] Valeo Troy, Troy, NY USA
关键词
Semantic Segmentation; Visual Perception; Automated Driving;
D O I
10.5220/0007248401730180
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Majority of semantic segmentation algorithms operate on a single frame even in the case of videos. In this work, the goal is to exploit temporal information within the algorithm model for leveraging motion cues and temporal consistency. We propose two simple high-level architectures based on Recurrent FCN (RFCN) and Multi-Stream FCN (MSFCN) networks. In case of RFCN, a recurrent network namely LSTM is inserted between the encoder and decoder. MSFCN combines the encoders of different frames into a fused encoder via 1x1 channel-wise convolution. We use a ResNet50 network as the baseline encoder and construct three networks namely MSFCN of order 2 & 3 and RFCN of order 2. MSFCN-3 produces the best results with an accuracy improvement of 9% and 15% for Highway and New York-like city scenarios in the SYNTHIA-CVPR'16 dataset using mean IoU metric. MSFCN-3 also produced 11% and 6% for SegTrack V2 and DAVIS datasets over the baseline FCN network. We also designed an efficient version of MSFCN-2 and RFCN-2 using weight sharing among the two encoders. The efficient MSFCN-2 provided an improvement of 11% and 5% for KITTI and SYNTHIA with negligible increase in computational complexity compared to the baseline version.
引用
收藏
页码:173 / 180
页数:8
相关论文
共 50 条
  • [1] Multi-stream densely connected network for semantic segmentation
    Jia, Dayu
    Cao, Jiale
    Pan, Jing
    Pang, Yanwei
    IET COMPUTER VISION, 2022, 16 (02) : 180 - 191
  • [2] AMS-CNN: Attentive multi-stream CNN for video-based crowd counting
    Tripathy, Santosh Kumar
    Srivastava, Rajeev
    INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL, 2021, 10 (04) : 239 - 254
  • [3] AMS-CNN: Attentive multi-stream CNN for video-based crowd counting
    Santosh Kumar Tripathy
    Rajeev Srivastava
    International Journal of Multimedia Information Retrieval, 2021, 10 : 239 - 254
  • [4] Multi-stream segmentation of meetings
    Dielmann, A
    Renals, S
    2004 IEEE 6TH WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING, 2004, : 167 - 170
  • [5] Automated Video Monitor Screen Extraction using Semantic Segmentation and CNN
    Belem, Ruan
    Cruz, Caio
    Pimentel, Agemilson
    de Lima Filho, Eddie
    Coimbra, Lucas
    Jesus, Anderson
    Costa, Andre
    Silva, Osmar
    Junior, Wilson
    Paula, Ricardo
    2020 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - TAIWAN (ICCE-TAIWAN), 2020,
  • [6] Driving behaviour recognition from still images by using multi-stream fusion CNN
    Yaocong Hu
    Mingqi Lu
    Xiaobo Lu
    Machine Vision and Applications, 2019, 30 : 851 - 865
  • [7] Driving behaviour recognition from still images by using multi-stream fusion CNN
    Hu, Yaocong
    Lu, Mingqi
    Lu, Xiaobo
    MACHINE VISION AND APPLICATIONS, 2019, 30 (05) : 851 - 865
  • [8] Multi-stream dynamic video Summarization
    Elfeki, Mohamed
    Wang, Liqiang
    Borji, Ali
    2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022), 2022, : 185 - 195
  • [9] A Multi-Stream Approach for Video Understanding
    Kunam, Lutharsanen
    Rossetto, Luca
    Bernstein, Abraham
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022, : 7003 - 7007
  • [10] A multi-stream CNN for deep violence detection in video sequences using handcrafted features
    Mohtavipour, Seyed Mehdi
    Saeidi, Mahmoud
    Arabsorkhi, Abouzar
    VISUAL COMPUTER, 2022, 38 (06): : 2057 - 2072