Sökning: onr:"swepub:oai:DiVA.org:liu-168856" >
Multi-stream Convol...
Multi-stream Convolutional Networks for Indoor Scene Recognition
-
- Anwer, Rao Muhammad (författare)
- Aalto Univ, Finland; Incept Inst Artificial Intelligence, U Arab Emirates
-
- Khan, Fahad (författare)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Incept Inst Artificial Intelligence, U Arab Emirates
-
- Laaksonen, Jorma (författare)
- Aalto Univ, Finland
-
visa fler...
-
- Zaki, Nazar (författare)
- United Arab Emirates Univ, U Arab Emirates
-
visa färre...
-
(creator_code:org_t)
- 2019-08-22
- 2019
- Engelska.
-
Ingår i: COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2019, PT I. - Cham : SPRINGER INTERNATIONAL PUBLISHING AG. - 9783030298883 - 9783030298876 ; , s. 196-208
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Convolutional neural networks (CNNs) have recently achieved outstanding results for various vision tasks, including indoor scene understanding. The de facto practice employed by state-of-the-art indoor scene recognition approaches is to use RGB pixel values as input to CNN models that are trained on large amounts of labeled data (Image-Net or Places). Here, we investigate CNN architectures by augmenting RGB images with estimated depth and texture information, as multiple streams, for monocular indoor scene recognition. First, we exploit the recent advancements in the field of depth estimation from monocular images and use the estimated depth information to train a CNN model for learning deep depth features. Second, we train a CNN model to exploit the successful Local Binary Patterns (LBP) by using mapped coded images with explicit LBP encoding to capture texture information available in indoor scenes. We further investigate different fusion strategies to combine the learned deep depth and texture streams with the traditional RGB stream. Comprehensive experiments are performed on three indoor scene classification benchmarks: MIT-67, OCIS and SUN-397. The proposed multi-stream network significantly outperforms the standard RGB network by achieving an absolute gain of 9.3%, 4.7%, 7.3% on the MIT-67, OCIS and SUN-397 datasets respectively.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Nyckelord
- Scene recognition; Depth features; Texture features
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas