Real-time 3D ball tracking with CPU-GPU acceleration using particle filter with multi-command queues and stepped parallelism iteration

Yilin Hou, Xina Cheng, Takeshi Ikenaga

研究成果: Conference contribution

8 被引用数 (Scopus)

抄録

3D ball tracking is a critical function in manyapplications such as game and players behavior analysis, andreal time implementation has become increasingly importantfor it can be used for live broadcast and TV contents. To reacha high accuracy, algorithms usually are time consuming due toa large set of calculations which is challenging to meet realtime demanding. This paper proposes multiple commandqueues, tactical threads allocation and stepped iterativeaddition to empower such a capacity on the CPU-GPUplatform. Multiple command queues achieves a parallelismbetween tasks in the algorithm. Secondly, the tactical threadsallocation helps mapping the algorithm into GPU andenhances synchronism between threads. And this paperproposes stepped iterative addition to achieve partialparallelism in a sequential operation. This work implements inan Intel Core i7-6700 GPU and AMD Radeon R9 FURY GPU.Tracking speed of our work increases 37.8 times from original431ms to 11.7ms while the success rate of the algorithm retainsover 99%. This result fully meets the requirement of 16.6msper frame for 60fps video real-time tracking.

本文言語English
ホスト出版物のタイトルProceedings - 2017 2nd International Conference on Multimedia and Image Processing, ICMIP 2017
出版社Institute of Electrical and Electronics Engineers Inc.
ページ235-239
ページ数5
2017-January
ISBN(電子版)9781509059546
DOI
出版ステータスPublished - 2017 12 15
イベント2nd International Conference on Multimedia and Image Processing, ICMIP 2017 - Wuhan, Hubei, China
継続期間: 2017 3 172017 3 19

Other

Other2nd International Conference on Multimedia and Image Processing, ICMIP 2017
CountryChina
CityWuhan, Hubei
Period17/3/1717/3/19

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Media Technology

フィンガープリント 「Real-time 3D ball tracking with CPU-GPU acceleration using particle filter with multi-command queues and stepped parallelism iteration」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル