Computer Vision, Imaging and Computer Graphics Theory and Applications
Computer Vision, Imaging and Computer Graphics Theory and Applications
复制标题
计算机视觉、成像与计算机图形学理论与应用
DOI:
10.1007/978-3-319-29971-6_11
复制
发表时间:
2016
期刊:
影响因子:
--
通讯作者:
Haines O
中科院分区:
文献类型:
--
作者:
Haines O
In this paper we show that combining knowledge of the orientation of a camera with visual information can be used to improve the performance of semantic image segmentation. This is based on the assumption that the direction in which a camera is facing acts as a prior on the content of the images it creates. We gathered egocentric video with a camera attached to a head-mounted display, and recorded its orientation using an inertial sensor. By combining orientation information with typical image descriptors, we show that segmentation of individual images improves in accuracy compared with vision alone, from 61 % to 71 % over six classes. We also show that this method can be applied to both point and line based features from the image, and that these can be combined together for further benefits. Our resulting system would have applications in autonomous robot locomotion and guiding visually impaired humans.
登录
查看更多内容
DOI:
--
发表时间:
2011
期刊:
影响因子:
--
作者:
S. Chikkerur;T. Poggio
通讯作者:
T. Poggio
影响因子:
1.8
作者:
C. Cadieu;Minjoon Kouh;M. Riesenhuber;T. Poggio
通讯作者:
T. Poggio
DOI:
--
发表时间:
2012
期刊:
影响因子:
--
作者:
M. Sharif;Saad Anis;M. Raza;S. Mohsin
通讯作者:
S. Mohsin
DOI:
--
发表时间:
2011
期刊:
影响因子:
--
作者:
Parvesh Kumar;S. Wasan
通讯作者:
S. Wasan