Zobrazeno 1 - 10
of 225
pro vyhledávání: '"Suh, Il Hong"'
In this paper, we present an autonomous navigation system for goal-driven exploration of unknown environments through deep reinforcement learning (DRL). Points of interest (POI) for possible navigation directions are obtained from the environment and
Externí odkaz:
http://arxiv.org/abs/2103.07119
For a robotic grasping task in which diverse unseen target objects exist in a cluttered environment, some deep learning-based methods have achieved state-of-the-art results using visual input directly. In contrast, actor-critic deep reinforcement lea
Externí odkaz:
http://arxiv.org/abs/2002.11903
Estimating accurate depth from a single image is challenging because it is an ill-posed problem as infinitely many 3D scenes can be projected to the same 2D scene. However, recent works based on deep convolutional neural networks show great progress
Externí odkaz:
http://arxiv.org/abs/1907.10326
We present a novel feature matching algorithm that systematically utilizes the geometric properties of features such as position, scale, and orientation, in addition to the conventional descriptor vectors. In challenging scenes with the presence of r
Externí odkaz:
http://arxiv.org/abs/1701.05676
Kinect skeleton tracker is able to achieve considerable human body tracking performance in convenient and a low-cost manner. However, The tracker often captures unnatural human poses such as discontinuous and vibrated motions when self-occlusions occ
Externí odkaz:
http://arxiv.org/abs/1604.04528
Publikováno v:
In Information Sciences May 2017 388-389:84-98
Publikováno v:
In Physica A: Statistical Mechanics and its Applications 15 August 2015 432:16-23
Publikováno v:
In Image and Vision Computing May 2015 37:1-11
Autor:
Kwon, Woo Young, Suh, Il Hong
Publikováno v:
In Knowledge-Based Systems December 2014 72:81-95
Autor:
Park, Youngbin, Suh, Il Hong
Publikováno v:
In Information Sciences 20 August 2014 276:80-103