Abstract | ||
---|---|---|
A currently popular trend in object detection and pattern recognition is usage of statistical classifiers, namely AdaBoost and its modifications. The speed performance of these classifiers largely depends on the low level image features they are using: both on the amount of information the feature provides and the processor time of its evaluation. Local Rank Differences is an image feature that is alternative to commonly used haar wavelets. It is suitable for implementation in programmable (FPGA) or specialized (ASIC) hardware, but -as this paper shows -it performs very well on graphics hardware (GPU) used in general purpose manner (GPGPU, namely CUDA in this case) as well. The paper discusses the LRD features and their properties, describes an experimental implementation of the LRD in graphics hardware using CUDA, presents its empirical performance measures compared to alter native approaches, suggests several notes on practical usage of LRD and proposes directions for future work. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-642-02345-3_37 | ICCVG |
Keywords | Field | DocType |
lrd feature,paper shows,speed performance,image feature,gp-gpu implementation,experimental implementation,graphics hardware,local rank differences,empirical performance,practical usage,low level image,image features,pattern recognition | Computer vision,Object detection,AdaBoost,Graphics hardware,Computer science,CUDA,Feature (computer vision),Field-programmable gate array,Artificial intelligence,General-purpose computing on graphics processing units,Haar wavelet | Conference |
Volume | ISSN | Citations |
5337 | 0302-9743 | 3 |
PageRank | References | Authors |
0.47 | 9 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Adam Herout | 1 | 248 | 35.39 |
Radovan Josth | 2 | 3 | 0.47 |
Pavel Zemcik | 3 | 66 | 7.58 |
Michal Hradis | 4 | 132 | 14.19 |