Alignment invariant image comparison implemented on the GPU
- Authors: Roos, Hans , Roodt, Yuko , Clarke, Willem A.
- Date: 2008
- Subjects: Distance transform , Binary image , Graphics processing units , Parallel processing
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/15593 , uj:15681 , Roos, H., Roodt, Y. & Clarke, W.A. 2008. Alignment invariant image comparison implemented on the GPU. Pattern Recognition Association of South Africa (PRASA), 27-28 Nov. 2008.
- Description: Abstract: This paper proposes a GPU implemented algorithm to determine the differences between two binary images using Distance Transformations. These differences are invariant to slight rotation and offsets, making the technique ideal for comparisons between images that are not perfectly aligned...
- Full Text:
Binary image features designed towards vision-based localization and environment mapping from micro aerial vehicle (MAV) captured images
- Authors: Cronje, Jaco
- Date: 2012-10-24
- Subjects: Binary image , Micro aerial vehicle captured images , Remote sensing - Data processing , Micro air vehicles , Mobile geographic information systems , Imaging systems
- Type: Thesis
- Identifier: http://ujcontent.uj.ac.za8080/10210/387081 , uj:10415 , http://hdl.handle.net/10210/7881
- Description: M.Phil. , This work proposes a fast local image feature detector and descriptor that is im- plementable on a GPU. The BFROST feature detector is the first published GPU implementation of the popular FAST detector. A simple but novel method of feature orientation estimation which can be calculated in constant time is proposed. The robustness and reliability of the orientation estimation is validated against rotation invariant descriptors such as SIFT and SURF. Furthermore, the BFROST feature descriptor is robust to noise, scalable, rotation invariant, fast to compute in parallel and maintains low memory usage. It is demonstrated that BFROST is usable in real-time applications such as vision-based localization and mapping of images captured from micro aerial platforms.
- Full Text: