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
  • [21] Multi-Modal Multi-Stream UNET Model for Liver Segmentation
    Elghazy, Hagar Louye
    Fakhr, Mohamed Waleed
    2021 IEEE WORLD AI IOT CONGRESS (AIIOT), 2021, : 28 - 33
  • [22] Multi-stream and multi-scale fusion rib fracture segmentation network based on UXNet
    Liu, Yusi
    Zhang, Liyuan
    Jiang, Zhengang
    QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, 2025, 15 (01) : 230 - 248
  • [23] An automated method for synthesizing a multi-stream heat exchanger network based on stream pseudo-temperature
    Yuan, Dongwen
    Wang, Yao
    Xiao, Wu
    Yao, Pingjing
    Luo, Xing
    Roetzel, Wilfried
    16TH EUROPEAN SYMPOSIUM ON COMPUTER AIDED PROCESS ENGINEERING AND 9TH INTERNATIONAL SYMPOSIUM ON PROCESS SYSTEMS ENGINEERING, 2006, 21 : 919 - 924
  • [24] Multi-Stream CNN for Spatial Resource Allocation: a Crop Management Application
    Barbosa, Alexandre
    Marinho, Thiago
    Martin, Nicolas
    Hovakimyan, Naira
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020), 2020, : 258 - 266
  • [25] Multi-stream CNN for facial expression recognition in limited training data
    Javad Abbasi Aghamaleki
    Vahid Ashkani Chenarlogh
    Multimedia Tools and Applications, 2019, 78 : 22861 - 22882
  • [26] Multi-stream CNN for facial expression recognition in limited training data
    Aghamaleki, Javad Abbasi
    Chenarlogh, Vahid Ashkani
    MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (16) : 22861 - 22882
  • [27] An Automatic Estimation of Arterial Input Function Based on Multi-Stream 3D CNN
    Fan, Shengyu
    Bian, Yueyan
    Wang, Erling
    Kang, Yan
    Wang, Danny J. J.
    Yang, Qi
    Ji, Xunming
    FRONTIERS IN NEUROINFORMATICS, 2019, 13
  • [28] Multi-stream CNN: Learning representations based on human-related regions for action recognition
    Tu, Zhigang
    Xie, Wei
    Qin, Qianqing
    Poppe, Ronald
    Veltkamp, Remco C.
    Li, Baoxin
    Yuan, Junsong
    PATTERN RECOGNITION, 2018, 79 : 32 - 43
  • [29] Multi-stream Deep Learning Framework for Automated Presentation Assessment
    Li, Junnan
    Wong, Yongkang
    Kankanhalli, Mohan S.
    PROCEEDINGS OF 2016 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM), 2016, : 222 - 225
  • [30] MULTI-STREAM SWITCHING FOR INTERACTIVE VIRTUAL REALITY VIDEO STREAMING
    Cheung, Gene
    Liu, Zhi
    Ma, Zhiyou
    Tan, Jack Z. G.
    2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 2179 - 2183