Real-time video breakup detection for multiple HD video streams on a single GPU

Real-Time Image and Video Processing Pub Date : 2012-06-01 DOI:10.1117/12.921529

Jakub Rosner, Hannes Fassold, M. Winter, P. Schallauer

{"title":"Real-time video breakup detection for multiple HD video streams on a single GPU","authors":"Jakub Rosner, Hannes Fassold, M. Winter, P. Schallauer","doi":"10.1117/12.921529","DOIUrl":null,"url":null,"abstract":"An important task in film and video preservation is the quality assessment of the content to be archived or reused out of \nthe archive. This task, if done manually, is a straining and time consuming process, so it is highly recommended to \nautomate this process as far as possible. In this paper, we show how to port a previously proposed algorithm for detection \nof severe analog and digital video distortions (termed \"video breakup\"), efficiently to NVIDIA GPUs of the Fermi \nArchitecture with CUDA. By parallizing of the algorithm massively in order to take usage of the hundreds of cores on a \ntypical GPU and careful usage of GPU features like atomic functions, texture and shared memory, we achive a speedup \nof roughly 10-15 when comparing the GPU implementation with an highly optimized, multi-threaded CPU \nimplementation. Thus our GPU algorithm is able to analyze nine Full HD (1920 × 1080) video streams or 40 standard \ndefinition (720 × 576) video streams in real-time on a single inexpensive Nvidia Geforce GTX 480 GPU. Additionally, \nwe present the AV-Inspector application for video quality analysis where the video breakup algorithm has been \nintegrated.","PeriodicalId":369288,"journal":{"name":"Real-Time Image and Video Processing","volume":"40 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Real-Time Image and Video Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1117/12.921529","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

Abstract

An important task in film and video preservation is the quality assessment of the content to be archived or reused out of the archive. This task, if done manually, is a straining and time consuming process, so it is highly recommended to automate this process as far as possible. In this paper, we show how to port a previously proposed algorithm for detection of severe analog and digital video distortions (termed "video breakup"), efficiently to NVIDIA GPUs of the Fermi Architecture with CUDA. By parallizing of the algorithm massively in order to take usage of the hundreds of cores on a typical GPU and careful usage of GPU features like atomic functions, texture and shared memory, we achive a speedup of roughly 10-15 when comparing the GPU implementation with an highly optimized, multi-threaded CPU implementation. Thus our GPU algorithm is able to analyze nine Full HD (1920 × 1080) video streams or 40 standard definition (720 × 576) video streams in real-time on a single inexpensive Nvidia Geforce GTX 480 GPU. Additionally, we present the AV-Inspector application for video quality analysis where the video breakup algorithm has been integrated.

查看原文本刊更多论文

实时视频分解检测多个高清视频流在一个单一的GPU

电影和录像保存的一项重要任务是对存档或从存档中重新使用的内容进行质量评估。如果手动完成此任务，则是一个紧张且耗时的过程，因此强烈建议尽可能将此过程自动化。在本文中，我们展示了如何将先前提出的用于检测严重模拟和数字视频失真(称为“视频分解”)的算法有效地移植到具有CUDA的费米架构的NVIDIA gpu上。通过大规模并行化算法，以利用典型GPU上的数百个内核，并仔细使用GPU特性(如原子函数、纹理和共享内存)，当将GPU实现与高度优化的多线程CPU实现进行比较时，我们实现了大约10-15的加速。因此，我们的GPU算法能够在一个便宜的Nvidia Geforce GTX 480 GPU上实时分析9个全高清(1920 × 1080)视频流或40个标准清晰度(720 × 576)视频流。此外，我们还提出了AV-Inspector应用程序，用于视频质量分析，其中集成了视频分解算法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Real-Time Image and Video Processing

自引率

0.00%

发文量