Fast and accurate object detection in high resolution 4K and 8K video using GPUs
source link: https://www.tuicool.com/articles/hit/qiAb2ei
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
Computer Science > Computer Vision and Pattern Recognition
Title: Fast and accurate object detection in high resolution 4K and 8K video using GPUs
(Submitted on 24 Oct 2018)
Abstract: Machine learning has celebrated a lot of achievements on computer vision tasks such as object detection, but the traditionally used models work with relatively low resolution images. The resolution of recording devices is gradually increasing and there is a rising need for new methods of processing high resolution data. We propose an attention pipeline method which uses two staged evaluation of each image or video frame under rough and refined resolution to limit the total number of necessary evaluations. For both stages, we make use of the fast object detection model YOLO v2. We have implemented our model in code, which distributes the work across GPUs. We maintain high accuracy while reaching the average performance of 3-6 fps on 4K video and 2 fps on 8K video.
Comments: 6 pages, 12 figures, Best Paper Finalist at IEEE High Performance Extreme Computing Conference (HPEC) 2018; copyright 2018 IEEE; (DOI will be filled when known) Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG) Cite as: arXiv:1810.10551 [cs.CV] (or arXiv:1810.10551v1 [cs.CV] for this version)Submission history
From: Vít Růžička [view email]
[v1] Wed, 24 Oct 2018 18:00:06 UTC (7,085 KB)
Which authors of this paper are endorsers? |( What is MathJax? )
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK