3D video semantic segmentation for wildfire smoke

被引:0
|
作者
Guodong Zhu
Zhenxue Chen
Chengyun Liu
Xuewen Rong
Weikai He
机构
[1] Shandong University,School of Control Science and Engineering
[2] Shandong University,Research Institute of Shandong University
[3] Shandong Jiaotong University,School of Aeronautics
来源
关键词
Wildfire smoke detection; Semantic segmentation; Natural scene; Real-time;
D O I
暂无
中图分类号
学科分类号
摘要
Wildfires are a serious threat to ecosystems and human life. Usually, smoke is generated before the flame, and due to the diffusing nature of the smoke, we can detect smoke from a distance, so wildfire smoke detection is especially important for early warning systems. In this paper, we propose a 3D convolution-based encoder–decoder network architecture for video semantic segmentation in wildfire smoke scenes. In the encoder stage, we use 3D residual blocks to extract the spatiotemporal features of smoke. The downsampling feature from the encoder is upsampled by the decoder three times in succession. Then, three smoke map prediction modules are, respectively, passed, the output smoke prediction map is supervised by the binary image label, and finally, the final prediction is obtained by feature map fusion. Our model can achieve end-to-end training without pretraining from scratch. In addition, a dataset including 90 smoke videos is tested and trained in this paper. The experimental results of the smoke video show that our model quickly and accurately segmented the smoke area and produced few false positives.
引用
收藏
相关论文
共 50 条
  • [1] 3D video semantic segmentation for wildfire smoke
    Zhu, Guodong
    Chen, Zhenxue
    Liu, Chengyun
    Rong, Xuewen
    He, Weikai
    [J]. MACHINE VISION AND APPLICATIONS, 2020, 31 (06)
  • [2] Joint Semantic Segmentation and 3D Reconstruction from Monocular Video
    Kundu, Abhijit
    Li, Yin
    Dellaert, Frank
    Li, Fuxin
    Rehg, James M.
    [J]. COMPUTER VISION - ECCV 2014, PT VI, 2014, 8694 : 703 - 718
  • [3] 3D Parallel Fully Convolutional Networks for Real-Time Video Wildfire Smoke Detection
    Li, Xiuqing
    Chen, Zhenxue
    Wu, Q. M. Jonathan
    Liu, Chengyun
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2020, 30 (01) : 89 - 103
  • [4] 3D VIDEO PERFORMANCE SEGMENTATION
    Tung, Tony
    Matsuyama, Takashi
    [J]. 2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2010, : 25 - 28
  • [5] Semantic Segmentation and Labeling of 3D garments
    Liu, Li
    Wang, Ruomei
    Zhou, Fan
    Su, Zhuo
    Fu, Xiaodong
    [J]. 2014 5TH INTERNATIONAL CONFERENCE ON DIGITAL HOME (ICDH), 2014, : 299 - 304
  • [6] Segmentation and Semantic Annotation of 3D Objects
    Zhou, Jiang
    Ma, Xinyu
    [J]. MICRO NANO DEVICES, STRUCTURE AND COMPUTING SYSTEMS, 2011, 159 : 124 - 127
  • [7] Deep Projective 3D Semantic Segmentation
    Lawin, Felix Jaremo
    Danelljan, Martin
    Tosteberg, Patrik
    Bhat, Goutam
    Khan, Fahad Shahbaz
    Felsberg, Michael
    [J]. COMPUTER ANALYSIS OF IMAGES AND PATTERNS, 2017, 10424 : 95 - 107
  • [8] Learning Spatiotemporal Features for Video Semantic Segmentation Using 3D Convolutional Neural Networks
    Chen, Jiamin
    Wang, Mingchen
    Jiang, Shang
    Huang, Bin
    Sun, Hongbo
    [J]. 2022 6TH INTERNATIONAL SYMPOSIUM ON COMPUTER SCIENCE AND INTELLIGENT CONTROL, ISCSIC, 2022, : 55 - 62
  • [9] A 3D semantic segmentation network for accurate neuronal soma segmentation
    Ma, Li
    Zhong, Qi
    Wang, Yezi
    Yang, Xiaoquan
    Du, Qian
    [J]. JOURNAL OF INNOVATIVE OPTICAL HEALTH SCIENCES, 2024,
  • [10] Semantic Segmentation and 3D Reconstruction of Concrete Cracks
    Shokri, Parnia
    Shahbazi, Mozhdeh
    Nielsen, John
    [J]. REMOTE SENSING, 2022, 14 (22)