2019 - C - Ciliberto - wlcss_cuda_v1.1_cr.pdf (545.13 kB)
WLCSSCuda: a CUDA accelerated template matching method for gesture recognition
conference contribution
posted on 2023-06-09, 18:36 authored by Mathias Ciliberto, Daniel RoggenDaniel RoggenTemplate matching methods can benefit from multi-cores architecture in order to parallelise and accelerate the matching of multiple templates. We present WLCSSCuda: a GPU accelerated implementation of the Warping Longest Common Subsequence (WLCSS) pattern recognition algorithm. We evaluate our method on 4 NVIDIA GPUs and 4 multi-cores CPUs. We observe a 67-times speedup for the GPU implementation in the best case against the multithreaded CPU implementation.
Funding
MinlAttention: Attention Management in Minimal Invasive Surgery; G1830; BUNDESMINISTERIUM F?R VERKEHR, INNOVATION UND TECHNOLOGIE
History
Publication status
- Published
File Version
- Accepted version
Journal
Proceedings of the 2019 International Symposium on Wearable ComputersPublisher
Association for Computing MachineryExternal DOI
Page range
32-34Event name
ISWC 2019: International Symposium on Wearable ComputersEvent location
LondonEvent type
conferenceEvent date
9-13 September 2019ISBN
9781450368704Department affiliated with
- Engineering and Design Publications
Research groups affiliated with
- Sensor Technology Research Centre Publications
Full text available
- Yes
Peer reviewed?
- Yes
Editors
Ozan Cakmakci, Jamie Ward, Lucy DunneLegacy Posted Date
2019-08-08First Open Access (FOA) Date
2019-09-12First Compliant Deposit (FCD) Date
2019-08-07Usage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC