Robotics and Computer Vision Lab

Publications

Extra Form
저 자 Sungho Kim
학 회 KAIST
논문일시(Year) 2007
논문일시(Month) 02
김성호, 영상 문맥 정보를 이용한 계층적 그래피컬 모델 기반 물체 인식 및 분류 기법, 한국과학기술원, 2007 2월.


The goal of object recognition is to label objects from images and
to estimate the poses of the labeled objects. The field of object
recognition has seen tremendous progress with successful
applications in some specific domains such as face recognition.
However, the current state-of-the-art methods show unsatisfactory
results for more general object domains in complex natural
environments with visual ambiguities. In this dissertation, we aim
to enhance the object identification and categorization with the
guide of visual context and graphical model.

In this dissertation, we propose a general framework for the
cooperative object identification and object categorization.
Examplars used in identification provide useful information of
similarity in categorization. Conversely, novel objects are rejected
in identification but the proposed object categorization can label
the novel objects and segment them out for database update in
identification.

In the first part of the work, we propose a hierarchical graphical
model (HGM) for the disambiguation of blurred objects. We define
three types of visual context such as spatial, hierarchical, and
temporal context, which provide powerful disambiguation. To handle
both the visual relation and uncertainty, we model them by the HGM.
It consists of part layer, object layer, and a place node. Pose
information in part and object layer is inserted into nodes for the
utilization of part-object context. Due to the complexity of
graphical model, we apply the piecewise learning which gives
practical learning of the HGM, and propose a context-guided sample
generation and pruning for the variable graph estimation and
distribution estimation. The bidirectional interaction in the HGM
can discriminate ambiguous objects and places simultaneously in real
environment. Large scale experiments for building guidance validate
the robustness. As a direct extension, the HGM is adapted for the
video interpretation by incorporating additional temporal context.

In the second part of the work, we propose a directed graphical
model, a variant of the HGM, for the simultaneous segmentation and
categorization in cluttered environments. Conventional methods show
weak performance due to the ambiguity of figure-ground. We enhance
the categorization by the proposed online boost based on the
part-part and part-object context. It can provide robust bottom-up
proposal for the clutter reduction. The boosted MCMC (Markov Chain
Monte Carlo) optimizes the simultaneous categorization and
segmentation. Samples from bottom-up boost provide fast and accurate
results. The proposed system shows upgraded enhancement for
cluttered environments.

List of Articles
265. Automatic Calibration of Catadioptric Cameras In Urban Environment
Jean-Charles Bazin, In So Kweon, Cedric Demonceaux, Pascal Vasseur
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2008 / 09
264. Improvement of Feature Matching in Catadioptric Images Using Gyroscope Data
Jean-Charles Bazin, In So Kweon, Cedric Demonceaux, Pascal Vasseur
International Conference on Pattern Recognition (ICPR) 2008 / 12
263. Dynamic Programming and Skyline Extraction in Catadioptric Infrared Images
Jean-Charles Bazin, In So Kweon, Cedric Demonceaux, Pascal Vasseur
IEEE International Conference on Robotics and Automation (ICRA) 2009 / 05
262. Image Warping for View-invariant Object Matching using Stereo Camera
Jiyoung Jung, Yekeun Jeong, Joon-Young Lee, In So Kweon
16th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV) 2010 / 02
261. Detecting Small Objects in Natural Scene using Depth Cue
Jaesik Park, Yekeun Jeong, Chaehoon Park, In So Kweon
16th Korea-Japan Joint Workshop on Frontiers of Computer Vision(FCV) 2010 / 02
260. A Camera Calibration Method using Concentric Circles for Vision Applications
Jun-sik Kim, Howon Kim, In So Kweon
The 5th Asian Conference on Computer Vision (ACCV) 2002 / 01
259. Optimal Photo Hull Recovery for the Image-based Modeling
Howon Kim, In So Kweon
The 6th Asian Conference on Computer Vision (ACCV) 2004 / 01
258. Robust Background Maintenance for Dynamic Scenes with Global Intensity Level Change
Kapje Sung, Youngbae Hwang, In So Kweon
5th International Conference on Ubiquitous Robots and Ambient Intelligence(URAI) 2008 / 11
257. Foreground Extraction Using Blur Information
Kapje Sung, Seong-Heum Kim, In So Kweon
15th Korea-Japan Joint Workshop on Frontiers of Computer Vision(FCV) 2009 / 02
256. Local-Driven Semi-Supervised Learning with Multi-Label
Teng Li, Shuicheng Yan, Tao Mei, In So Kweon
IEEE Conference on Multimedia and Expo (ICME2009) 2009 / 06
255. Measuring Conceptual Relation of Visual Words for Visual Categorization
Teng Li, In So Kweon
IEEE Conference on Image Processing (ICIP2009) 2009 / 11
254. Contextual Bag-of-Words for Visual Categorization
Teng Li, Tao Mei, In So Kweon, Xian-Sheng Hua
IEEE Transactions on Circuits and Systems for Video Technology (CSVT) 2010 / 01
253. An Efficient Structure from Motion for 3D Reconstruction of Large-scale Scene
Yekeun Jeong, In So Kweon
Korea Robotics Society Annual Conference (KROC) 2007 2007 / 06
252. 다중반사특성을 이용한 새로운 초음파 거리 센서
Wangheon Lee, In So Kweon
ICASE논문집 2002 / 04
251. 이동 로봇을 위한 컬러 표식 기반 자기 위치 추정 기법
Kukjin Yoon, Gijeong Jang, Sungho Kim, In So Kweon
Journal of Automation and System Engineering 2001 / 09
250. 3차원 형상복원을 위한 새로운 시각장치
Doohyun Lee, In So Kweon
제어자동화시스템공학회지 2000 / 05
249. 투사영상 불변량을 이용한 장애물 검지 및 자기위치 인식
Kyoungsig Roh, Wangheon Lee, Joonwoong Lee, In So Kweon
제어자동화시스템공학회논문지 1999 / 02
248. 영상변형을 이용한 선행차량과의 충돌시간 및 법선벡터의 예측
Jaeyong Lee, Seongkee Park, Kyoungsig Roh, In So Kweon
제어자동화시스템공학회논문지 1998 / 06
247. 지배주파수도를 이용한 미소표면 결함추출을 위한 영상처리 알고리즘
Sangwon Kim, In So Kweon
Journal of the Institute of Control, Automation and Systems Engineer 1996 / 03
246. 이동로봇주행을 위한 영상처리 기술
Kyoungsig Roh, Dongsu Kim, Wangheon Lee, In So Kweon
전자공학회지 1996 / 12
Board Pagination Prev 1 ... 17 18 19 20 21 22 23 24 25 26 ... 35 Next
/ 35