Robotics and Computer Vision Lab

Publications

Extra Form
저 자 Kukjin Yoon, In So Kweon
학 회 Computer Vision and Image Understanding
논문일시(Year) 2008
논문일시(Month) 11
vol 112(2) / pp 173-183

The point ambiguity owing to the ambiguous local appearances of image points is one of the main causes making the stereo problem
difficult. Under the point ambiguity, local similarity measures are easy to be ambiguous and this results in false matches in ambiguous
areas.
In this paper, we present a new similarity measure to resolve the point ambiguity problem based on the idea that the distinctiveness,
not the interest, is an appropriate criterion for feature selection under the point ambiguity. Here, the interest of a point represents how
much information a point has for facilitating matching, while the distinctiveness of a point represents how much a point is distinguishable
from other points. The proposed similarity measure named the Distinctive Similarity Measure (DSM) is essentially based on the
distinctiveness of image points and the dissimilarity between them, which are both closely related to the local appearances of image
points; the distinctiveness of an image point is related to the probability of a mismatch while the dissimilarity is related to the probability
of a good match. We verify the efficiency of the proposed DSM by using testbed image sets. Experimental results prove that the proposed
DSM is very effective for both semi-dense and dense stereo matching and considering the point distinctiveness in both images can
improve the performance of stereo methods under the point ambiguity.

List of Articles
225. Robust region boundary tracking in noisy image sequences
Dongjoong Kang, In So Kweon
2nd Japan-Korea Joint Workshop on Computer Vision 1996 / 02
224. Active vision for intelligent vehicles
Dongjoong Kang, In So Kweon
International Workshop on Computer Vision Technology 1996 / 12
223. A visual tracking algorithm by integrating rigid model and snake
Dongjoong Kang, In So Kweon
IEEE International Conference on Intelligent Systems and Robots 1996 / 11
222. A Kalman filter based visual tracking algorithm for an object moving in 3-D
J. Lee, M. Kim, In So Kweon
IEEE International Conference on Intelligent Systems and Robots 1995 / 08
221. A self-localization algorithm for a mobile robot using perspective invariant
Kyoungsig Roh, S. Kim, Wangheon Lee, In So Kweon
International Workshop on Advanced Mechatronics 1995 / 12
220. Active vision algorithms using projective invariants
Dongsu Kim, Kyoungsig Roh, In So Kweon
Annual Conference of Robotics Society in Japan 1994 / 11
219. A new 2-D object recognition algorithm using geometric invariance
Kyoungsig Roh, In So Kweon
International Symposium on Advances in Computer Integrated Manufacturing Systems 1994 / 11
218. Model based color halftoning techniques on perceptually uniform color spaces
C. Kim, S. Kim, Y. Seo, In So Kweon
IST&T/SPIE International Conference on Digital Video Compression and Processing on Personal Computers: Algorithms and Technologies 1994 / 01
217. A behavior-based intelligent robot in dynamic indoor environments
In So Kweon, M. Watanabe, K. Onoguchi, Y. Kuno
IEEE International Conference on Robotics and Automation (ICRA) 1992 / 05
216. behavior-based mobile robot using active sensor fusion
In So Kweon, M. Watanabe, K. Onoguchi, Y. Kuno
IEEE International Conference on Intelligent Robots and Systems (IROS) 1992 / 07
215. A three-layered system architecture for behavior-based mobile robots
M. Watanabe, K. Onoguchi, In So Kweon, Y. Kuno
IEEE International Conference on Robotics and Automation (ICRA) 1992 / 05
214. Vision-based behaviors for indoor mobile robots
In So Kweon, K. Onoguchi, M. Watanabe, Y. Kuno
Information Processing Society of Japan Workshop on Computer Vision 1992 / 01
213. Vehicle control using target tracking
K. Onoguchi, M. Watanabe, In So Kweon, Y. Kuno
Information Processing Society of Japan Workshop on Computer Vision 1991 / 07
212. Extracting topographic terrain features for outdoor mobile robots
In So Kweon, T. Kanade
IEEE International Conference on Robotics and Automation (ICRA) 1991 / 04
211. Behavior-based mobile robot using multiple sensors
In So Kweon, M. Watanabe, K. Onoguchi, Y. Kuno
The 1st Korea-Japan Joint Conference on Computer Vision 1991 / 10
210. High resolution terrain map from multiple sensor data
In So Kweon, T. Kanade
IEEE International Workshop on Intelligent Robots and Systems (IROS) 1990 / 07
209. A mobile robot for lunar surface operations
Bares, In So Kweon, D. Wettegreen, W. Whittaker
NASA Conference on Space Telerobotics 1990 / 03
208. Methods for identifying footfall positions for a legged robot
Caillas, In So Kweon, E. Krotkov, M. Hebert
IEEE International Workshop on Intelligent Robots and Systems (IROS) 1989 / 09
207. Terrain mapping for a roving planetary explorer
M. Hebert, E. Krotkov, In So Kweon, T. Kanade
IEEE International Conference on Robotics and Automation (ICRA) 1989 / 05
206. First results in terrain mapping for a roving planetary explorer
E. Krotkov, M. Hebert, In So Kweon, T.Kanade
NASA Conference on Space Telerobotics 1989 / 01
Board Pagination Prev 1 ... 19 20 21 22 23 24 25 26 27 28 ... 35 Next
/ 35