TY - JOUR
T1 - Contextual object category recognition for RGB-D scene labeling
AU - Ali, H.
AU - Shafait, Faisal
AU - Giannakidou, E.
AU - Vakali, A.I.
AU - Figueroa, N.B.
AU - Varvadoukas, T.
AU - Mavridis, N.
PY - 2014
Y1 - 2014
N2 - Recent advances in computer vision on the one hand, and imaging technologies on the other hand, have opened up a number of interesting possibilities for robust 3D scene labeling. This paper presents contributions in several directions to improve the state-of-the-art in RGB-D scene labeling. First, we present a novel combination of depth and color features to recognize different object categories in isolation. Then, we use a context model that exploits detection results of other objects in the scene to jointly optimize labels of co-occurring objects in the scene. Finally, we investigate the use of social media mining to develop the context model, and provide an investigation of its convergence. We perform thorough experimentation on both the publicly available RGB-D Dataset from the University of Washington as well as on the NYU scene dataset. An analysis of the results shows interesting insights about contextual object category recognition, and its benefits. © 2013 Elsevier B.V. All rights reserved.
AB - Recent advances in computer vision on the one hand, and imaging technologies on the other hand, have opened up a number of interesting possibilities for robust 3D scene labeling. This paper presents contributions in several directions to improve the state-of-the-art in RGB-D scene labeling. First, we present a novel combination of depth and color features to recognize different object categories in isolation. Then, we use a context model that exploits detection results of other objects in the scene to jointly optimize labels of co-occurring objects in the scene. Finally, we investigate the use of social media mining to develop the context model, and provide an investigation of its convergence. We perform thorough experimentation on both the publicly available RGB-D Dataset from the University of Washington as well as on the NYU scene dataset. An analysis of the results shows interesting insights about contextual object category recognition, and its benefits. © 2013 Elsevier B.V. All rights reserved.
U2 - 10.1016/j.robot.2013.10.001
DO - 10.1016/j.robot.2013.10.001
M3 - Article
VL - 62
SP - 241
EP - 256
JO - Robotics and Autonomous Systems
JF - Robotics and Autonomous Systems
SN - 0921-8890
IS - 2
ER -