Sökning: id:"swepub:oai:DiVA.org:kth-105314" >
Multi view registra...
Multi view registration for novelty/background separation
-
- Aghazadeh, Omid (författare)
- KTH,Datorseende och robotik, CVAP
-
- Sullivan, Josephine (författare)
- KTH,Datorseende och robotik, CVAP
-
- Carlsson, Stefan (författare)
- KTH,Datorseende och robotik, CVAP
-
(creator_code:org_t)
- IEEE Computer Society, 2012
- 2012
- Engelska.
-
Ingår i: Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. - : IEEE Computer Society. - 9781467312264 ; , s. 757-764
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- We propose a system for the automatic segmentation of novelties from the background in scenarios where multiple images of the same environment are available e.g. obtained by wearable visual cameras. Our method finds the pixels in a query image corresponding to the underlying background environment by comparing it to reference images of the same scene. This is achieved despite the fact that all the images may have different viewpoints, significantly different illumination conditions and contain different objects cars, people, bicycles, etc. occluding the background. We estimate the probability of each pixel, in the query image, belonging to the background by computing its appearance inconsistency to the multiple reference images. We then, produce multiple segmentations of the query image using an iterated graph cuts algorithm, initializing from these estimated probabilities and consecutively combine these segmentations to come up with a final segmentation of the background. Detection of the background in turn highlights the novel pixels. We demonstrate the effectiveness of our approach on a challenging outdoors data set.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Nyckelord
- Automatic segmentations
- Background environment
- Data sets
- Graph cut
- Illumination conditions
- Multi-view registration
- Multiple image
- Multiple reference images
- Multiple segmentation
- Query images
- Reference image
- Computer vision
- Pixels
- Image segmentation
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas