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
205. Sensor fusion of range and reflectance data for outdoor scene analysis
In So Kweon, M. Hebert, T. Kanade
NASA Workshop on Space Operations, Automation, and Robotics 1988 / 07
204. Perception for rugged terrain
In So Kweon, M. Hebert, T. Kanade
SPIE International Symposium on Intelligent Robots and Computer Vision 1988 / 11
203. CMU sidewalk navigation system: A blackboard-based outdoor navigation system using sensor fusion with colored-range images
Y. Goto, K. Matsuzaki, In So Kweon, T. Obatake
Fall Joint Computer Conference (FJCC) 1986 / 11
202. Automatic Method for Closed Eye Correction
Jean-Charles Bazin, D.Q. Pham, In So Kweon, Kukjin Yoon
ICIP'09 2009 / 11
201. Particle Filter Approach Adapted to Catadioptric Images for Target Tracking Application
Jean-Charles Bazin, Kukjin Yoon, In So Kweon, C. Demonceaux, P. Vasseur
BMVC'09 2009 / 09
200. Contextual Decomposition of Multi-Label Images.
Teng Li, Tao Mei, Shuicheng Yan, In So Kweon, Chilwoo Lee
Accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR2009) 2009 / 06
199. VideoM: Multi-Video Synopsis.
Teng Li, Tao Mei, In So Kweon
In association with IEEE International Conference on Data Mining (ICDM2008) 2008 / 12
198. A Semantic Region Descriptor For Local Feature Based Image Categorization.
Teng Li, In So Kweon
In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2008 / 03
197. Learning Optimal Compact Codebook for Efficient Object Categorization.
Teng Li, Tao Mei, In So Kweon
In IEEE 2008 Workshop on Application of Computer Vision (WACV) 2008 / 01
196. Graph-Based Robust Shape Matching for Robotic Application
Hanbyul Joo, Yekeun Jeong, Olivier Duchenne, In So Kweon
IEEE International Conference on Robotics and Automation (ICRA) 2009 / 05
195. Graph Generation from Over-segmentation for Graph Based Approaches
Hanbyul Joo, Yekeun Jeong, In So Kweon
15th Korea-Japan Joint Workshop on Frontiers of Computer Vision(FCV) 2009 / 02
194. Bottom-Up Segmentation Based Robust Shape Matching in the Presence of Clutter and Occlusion
Hanbyul Joo, Yekeun Jeong, In So Kweon
International Workshop on Advanced Image Technology(IWAIT) 2009 / 01
193. Relative Scale Estimation between Two Camera Motions
Yekeun Jeong, In So Kweon
The 19th International Conference on Pattern Recognition (ICPR) 2008 / 12
192. Capturing Village-level Heritages with a Hand-held Camera-Laser Fusion Sensor
Yunsu Bok, Dong-Geol Choi, Yekeun Jeong, In So Kweon
IEEE Workshop on eHeritage and Digital Art Preservation, In conjunction with ICCV 2009 2009 / 10
191. Support Aggregation via Non-linear Diffusion with Disparity-Dependent Support-Weights for Stereo Matching
Kukjin Yoon, Yekeun Jeong, In So Kweon
Asian Conference on Computer Vision (ACCV), oral presentation 2009 / 09
190. Efficient Color Feature Extraction and Matching for Motion Estimation and Mapping
Hyoseok Hwang, In So Kweon
IEEE/RSJ 2008 International Conference on Intelligent Robots and Systems (IROS) 2008 / 09
189. Spherical Region-Based Matching of Vanishing Points in Catadioptric Images
Jean-Charles Bazin, In So Kweon, Cedric Demonceaux, Pascal Vasseur
OMNIVIS (ECCV) 2008 / 10
188. A Robust Top-Down Approach for Rotation Estimation and Vanishing Points Extraction by Catadioptric Vision 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
187. Robust Vision-based Autonomous Navigation against Environment Changes
Jungho Kim, Yunsu Bok, In So Kweon
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2008 / 09
186. Efficient Feature Tracking for Scene Recognition using Angular and Scale Constraints
Jungho Kim, Ouk Choi, In So Kweon
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2008 / 09
Board Pagination Prev 1 ... 20 21 22 23 24 25 26 27 28 29 ... 35 Next
/ 35