Z
ZuWhan Kim
Researcher at University of California, Berkeley
Publications - 38
Citations - 2204
ZuWhan Kim is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Object detection & Vehicle tracking system. The author has an hindex of 20, co-authored 38 publications receiving 2064 citations. Previous affiliations of ZuWhan Kim include University of Southern California & University of California.
Papers
More filters
Journal ArticleDOI
Robust Lane Detection and Tracking in Challenging Scenarios
TL;DR: A robust lane-detection-and-tracking algorithm to deal with challenging scenarios such as a lane curvature, worn lane markings, lane changes, and emerging, ending, merging, and splitting lanes is presented.
Journal ArticleDOI
Autonomous UAV path planning and estimation
J. Tisdale,ZuWhan Kim,J. Hedrick +2 more
TL;DR: This work proposes a tightly coupled approach, in which sensor models and estimation objectives are used online for path planning, and seeks to develop decentralized, autonomous control strategies that can account for a wide variety of sensing missions.
Proceedings ArticleDOI
Vision-based road-following using a small autonomous aircraft
Eric W. Frew,Timothy G. McGee,ZuWhan Kim,Xiao Xiao,S. Jackson,M. Morimoto,Sivakumar Rathinam,J. Padial,Raja Sengupta +8 more
TL;DR: In this paper, the authors describe the vision-based control of a small UAV following a road, using only the vision measurements and onboard inertial sensors, using a control strategy stabilizing the aircraft and following the road.
Proceedings Article
Fast Vehicle Detection with Probabilistic Feature Grouping and its Application to Vehicle Tracking
ZuWhan Kim,Jitendra Malik +1 more
TL;DR: A new tracking approach which uses model-based 3-D vehicle detection and description algorithm based on a probabilistic line feature grouping, and it is faster and more flexible than previous image-based algorithms.
Proceedings ArticleDOI
Real time object tracking based on dynamic feature grouping with background subtraction
TL;DR: This work introduces an object detection and tracking approach that combines the background subtraction algorithm and the feature tracking and grouping algorithm that can be used in real time applications and also provides high-quality trajectories.