Faculty/Research

Research Groups

컴퓨터비젼 연구실

Computer Vision Lab.

Prof. : Prof. Lee, Kyoung Mu

Research Area : 제어계측 및 자동화



  • About the Laboratory & Research Area
  • Computer Vision Lab. was founded at Seoul National University in 2003. Under supervision of Prof. Kyoung Mu Lee, various topics in computer vision field have been researched and developed.

    We mainly focus on developing algorithms to extract, reconstruct and recognize the information of object, person and 3D environments from digital images which may be used by computers, helping to have artificial intelligence close to human.
  • Research Interests & Projects
  • Specific topics we are interested in and researching currently are

    - Object Recognition / Object Segmentation
    - Object Tracking / Action Recognition
    - SLAM (Simultaneous Localization And Mapping)
    - Stereo Matching
    - Optimization
  • Journals & Patents
  • - Hoyub Jung, Koung Mu Lee, and Sang Uk Lee, "Window Annealing for Pixel-Labeling Problems," Computer Vision and Image Understanding (CVIU). to appear.
    - Tae Hoon Kim, Koung Mu Lee, and Sang Uk Lee, "Learning Full Pairwise Affinities for Spectral Segmentation," IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI). to appear.
    - Junseok Kwon and Kyoung Mu Lee, "Wang-Landau Monte Carlo-based Tracking Methods for Abrupt Motions," IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI).
    - Yong Seok Heo, Kyoung Mu Lee, and Sang Uk Lee, "Joint Depth Map and Color Consistency Estimation for Stereo Images with Different Illuminations and Cameras," IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI).
    - Sangdon Park, Wonsik Kim, and Kyoung Mu Lee, "Abnormal Object Detection by Canonical Scene-based Contextual Model," Proc. European Conference on Computer Vision (ECCV), 2012.
    - Yumin Suh, Minsu Cho, and Kyoung Mu Lee, "Graph Matching via Sequential Monte Carlo," Proc. European Conference on Computer Vision (ECCV), 2012.
    - Minsu Cho and Kyoung Mu Lee, "Progressive Graph Matching: Making a Move of Graphs via Probabilistic Voting," Proc. Computer Vision and Pattern Recognition (CVPR), 2012. (ORAL presentation, 2.5% acceptance rate)
    - Minsu Cho and Kyoung Mu Lee, "Mode-Seeking on Graphs via Random Walks," Proc. Computer Vision and Pattern Recognition (CVPR), 2012. (24.0% acceptance rate)
    - Junseok Kwon and Kyoung Mu Lee, "A Unified Framework for Event Summarization and Rare Event Detection," Proc. Computer Vision and Pattern Recognition (CVPR), 2012. (24.0% acceptance rate)
    - Heesoo Myeong, Ju Yong Chang, and Kyoung Mu Lee, "Learning Object Relationships via Graph-based Context Model," Proc. Computer Vision and Pattern Recognition (CVPR), 2012. (24.0% acceptance rate)
    - Dong Woo Park, Junseok Kwon, and Kyoung Mu Lee, "Robust Visual Tracking using Autoregressive Hidden Markov Model," Proc. Computer Vision and Pattern Recognition (CVPR), 2012. (24.0% acceptance rate)

    [C105] Yumin Suh, Minsu Cho, and Kyoung Mu Lee, "Graph Matching via Sequential Monte Carlo," Proc. European Conference on Computer Vision (ECCV), 2012. [PDF][Project Page]

    [C104] Minsu Cho and Kyoung Mu Lee, "Progressive Graph Matching: Making a Move of Graphs via Probabilistic Voting," Proc. Computer Vision and Pattern Recognition (CVPR), 2012. (ORAL presentation, 2.5% acceptance rate)[PDF][Project Page]

    [C103] Minsu Cho and Kyoung Mu Lee, "Mode-Seeking on Graphs via Random Walks," Proc. Computer Vision and Pattern Recognition (CVPR), 2012. (24.0% acceptance rate) [PDF][Project Page]

    [C102] Junseok Kwon and Kyoung Mu Lee, "A Unified Framework for Event Summarization and Rare Event Detection," Proc. Computer Vision and Pattern Recognition (CVPR), 2012. (24.0% acceptance rate) [PDF]

    [C101] Heesoo Myeong, Ju Yong Chang, and Kyoung Mu Lee, "Learning Object Relationships via Graph-based Context Model," Proc. Computer Vision and Pattern Recognition (CVPR), 2012. (24.0% acceptance rate) [PDF]

    [C100] Dong Woo Park, Junseok Kwon, and Kyoung Mu Lee, "Robust Visual Tracking using Autoregressive Hidden Markov Model," Proc. Computer Vision and Pattern Recognition (CVPR), 2012. (24.0% acceptance rate) [PDF]

TOP