Robotics and Computer Vision Lab


Extra Form
저 자 Sungho Kim
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

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
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
185. Pose Estimation of Unmanned Aerial Vehicle by Catadioptric Vision
Jean-Charles Bazin, In So Kweon
the 13th IEEE Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV ‘07) 2007 / 02
184. UAV Attitude Estimation by Vanishing Points in Catadioptric Images
Jean-Charles Bazin, In So Kweon, Cedric Demonceaux, Pascal Vasseur
IEEE International Conference on Robotics and Automation (ICRA’08) 2008 / 05
183. [Book] Object Identification and Categorization with Visual Context
Sungho Kim, In So Kweon
KAIST 2008 / 05
» Hierarchical Graphical Model-based Methods for Object Identification and Categorization with Visual Context
Sungho Kim
KAIST 2007 / 02
181. Metric reconstruction from images using rank-deficient relations
Jun-sik Kim
KAIST 2006 / 02
180. Robust Correspondence Search under Photometric Variations and Image Ambiguity
Kukjin Yoon
KAIST 2006 / 02
179. Catadioptric vision based localization and mapping for indoor mobile robot
Gijeong Jang
KAIST 2005 / 08
178. Appearance-cloning : Photo-consistent 3D modeling from multi-view images
Howon Kim
KAIST 2004 / 08
177. Shot Detection and Temporal Interest Point for Event-based Clustering and its Application to Golf Videos
Seunghoon Han
KAIST 2004 / 08
176. High-speed automatic edge detection using pixel group statistics and fuzzy-based automatic thresholding
Dongsu Kim
KAIST 2003 / 02
175. Image-based Visual Servoing for Linear Path Control
Jaeseung Cho
KAIST 2002 / 08
174. Chromatic invariant based image retrieval for three dimensional objects
Jiyeun Kim
KAIST 2002 / 02
173. Mobile robot navigation using fuzzy based sensor fusion
Wangheon Lee
KAIST 2001 / 08
172. Robust and direct estimation of camera motion and 3-D structure from stereo image sequence
Seongkee Park
KAIST 2000 / 08
171. A biprism stereo camera system
Doohyun Lee
KAIST 2000 / 08
170. Rectangle Extraction in Catadioptric Images
Jean-Charles Bazin, In So Kweon, Cedric Demonceaux, Pascal Vasseur
(OMNIVIS ‘07) in conjunction with ICCV’07 2007 / 10
169. Robust motion estimation and statistical change detection in image sequences under time-varying illumination
Youngsu Moon
KAIST 2000 / 08
Board Pagination Prev 1 ... 17 18 19 20 21 22 23 24 25 26 ... 31 Next
/ 31