Back to Search
Start Over
Fast feature matching for detailed point cloud generation
- Source :
- Proceedings of 6th International Conference on Image Processing Theory Tools and Applications (IPTA), 2016 | 6th International Conference on Image Processing Theory, Tools and Applications, IPTA2016 | 12/12/2016-15/12/2016 | Oulu, Finlandia, IPTA, Archivo Digital UPM, instname
- Publication Year :
- 2016
- Publisher :
- E.T.S.I. Telecomunicación (UPM), 2016.
-
Abstract
- Structure from motion is a very popular technique for obtaining three-dimensional point cloud-based reconstructions of objects from un-organised sets of images by analysing the correspondences between feature points detected in those images. However, the point clouds stemming from usual feature point extractors such as SIFT are frequently too sparse for reliable surface recovery. In this paper we show that alternate feature descriptors such as A-KAZE, which provide denser coverage of images, yield better results and more detailed point clouds. Unfortunately, the use of a dramatically increased number of points per image poses a computational challenge. We propose a technique based on epipolar geometry restrictions to significantly cut down on processing time and an efficient implementation thereof on a GPU.
- Subjects :
- Informática
Telecomunicaciones
Computer science
business.industry
Epipolar geometry
Feature extraction
Point cloud
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Scale-invariant feature transform
020207 software engineering
02 engineering and technology
Iterative reconstruction
Feature (computer vision)
0202 electrical engineering, electronic engineering, information engineering
Structure from motion
020201 artificial intelligence & image processing
Computer vision
Point (geometry)
Electrónica
Artificial intelligence
business
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- Proceedings of 6th International Conference on Image Processing Theory Tools and Applications (IPTA), 2016 | 6th International Conference on Image Processing Theory, Tools and Applications, IPTA2016 | 12/12/2016-15/12/2016 | Oulu, Finlandia, IPTA, Archivo Digital UPM, instname
- Accession number :
- edsair.doi.dedup.....fe05d785365c85c1d4a312d8b9e40b7b