Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Accelerating local feature extraction using OpenCL on heterogeneous platforms

: Moren, Konrad; Perschke, Thomas; Göhringer, Diana

Volltext urn:nbn:de:0011-n-3113162 (639 KByte PDF)
MD5 Fingerprint: d6addb9bc494c65d2a71215cf02742e8
Erstellt am: 5.11.2014

Pinzari, A. ; Institute of Electrical and Electronics Engineers -IEEE-; European Electronic Chips & Systems design Initiative -ECSI-, Gieres:
DASIP 2014, Conference on Design & Architectures for Signal & Image Processing. Proceedings : Madrid, Spain, October 8-10, 2014
Piscataway, NJ: IEEE, 2014
ISBN: 979-10-92279-05-4 (Print)
ISBN: 979-10-92279-06-1 (Online)
8 S.
Conference on Design & Architectures for Signal & Image Processing (DASIP) <2014, Madrid>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()
OpenCL; SIFT; Many-core GPU; Multi-core CPU; heterogeneous computing; platform specific optimizations

Local feature extraction is one of the most important steps in image processing applications such as image matching and object recognition. The Scale Invariant Feature Transformation (SIFT) algorithm is one of the most robust as well as one of the most computation intensive algorithms to extract local features. Recent implementations of the algorithm focus on homogeneous processors like multi-core CPUs or many-core GPUs. In this paper, we introduce an OpenCL-based implementation, which can be used in homogeneous and heterogeneous CPU/GPU environments. We analyze possible coarse-grained and fine-grained parallelization solutions of the SIFT algorithm. Using a set of optimizations we implement a high-performance SIFT implementations for very different CPU/GPU architectures. The scalable implementation allows for a fast processing, more than 40 FPS for Full-HD images.