Fast scene layout estimation via deep hashing

Yi Zhu; Wenbing Luo; Hanxi Li; Mingwen Wang

doi:10.1117/12.2501793

26 July 2018 Fast scene layout estimation via deep hashing

Yi Zhu, Wenbing Luo, Hanxi Li, Mingwen Wang

Proceedings Volume 10828, Third International Workshop on Pattern Recognition; 1082814 (2018) https://doi.org/10.1117/12.2501793
Event: Third International Workshop on Pattern Recognition, 2018, Jinan, China

Abstract

In this work, we propose an efficient method for accurately estimating the scene layout in both outdoor and indoor scenarios. For outdoor scenes, the horizon line in a road image is estimated while for indoor scenes, the wall-wall, wallceiling and wall-floor edges are estimated. A number of image patches are first cropped from the image and then feed into a convolution neural network which is originally trained for object detection. The yielded deep features from three different layers are compared with the features of the training patches, in a spatial-aware hashing fashion. The horizon line is then estimated via a sophisticated voting stage in which different voters are considered differently according to their importances. In particular, for the more complex labels (in indoor scenes), we introduce the structural forest for further enhancing the deep features before learning the hashing function. In practice, the proposed algorithm outperforms the state-of-the-art methods in accuracy for outdoor scenes while achieves the comparable performance to the best indoor scene layout estimators. Further more, the proposed method is real-time speed (up to 25 fps).

Citation Download Citation

Yi Zhu, Wenbing Luo, Hanxi Li, and Mingwen Wang "Fast scene layout estimation via deep hashing", Proc. SPIE 10828, Third International Workshop on Pattern Recognition, 1082814 (26 July 2018); https://doi.org/10.1117/12.2501793

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available