GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Presentation
Media
Abstract:

Learn how deep learning algorithms can be used for extracting semantic metadata from video and find out how to take advantage of this metadata for automatic video analysis. We will describe our experience employing deep learning algorithms for face detection, recognition, and anonymization (FaceNet, GANs) and general object recognition (YoloV3). We'll also address practical issues like building and deploying deep learning frameworks on multiple platforms and via GPU-Accelerated Docker containers, both locally and in the cloud. In addition, we'll provide information about several applications for these algorithms such as anonymization of training data, analysis of user-generated content for personalized media services, and automatic camera path generation for 360° video.

Learn how deep learning algorithms can be used for extracting semantic metadata from video and find out how to take advantage of this metadata for automatic video analysis. We will describe our experience employing deep learning algorithms for face detection, recognition, and anonymization (FaceNet, GANs) and general object recognition (YoloV3). We'll also address practical issues like building and deploying deep learning frameworks on multiple platforms and via GPU-Accelerated Docker containers, both locally and in the cloud. In addition, we'll provide information about several applications for these algorithms such as anonymization of training data, analysis of user-generated content for personalized media services, and automatic camera path generation for 360° video.

  Back
 
Topics:
Video & Image Processing, AI Application, Deployment & Inference
Type:
Talk
Event:
GTC Silicon Valley
Year:
2019
Session ID:
S9136
Streaming:
Download:
Share:
 
Abstract:
Basic image processing functions for convolution, morphological, and arithmetic operators are at the heart of many important high-level computer vision algorithms. We'll describe how to implement these routines efficiently on the GPU, using unique GPU capabilities like the texture cache and a large register file. We'll give information about several applications where these routines are employed, like film and video restoration (either locally or in the cloud) or automatic real-time quality assessment and automatic camera path calculation (virtual director) in omnidirectional video.
Basic image processing functions for convolution, morphological, and arithmetic operators are at the heart of many important high-level computer vision algorithms. We'll describe how to implement these routines efficiently on the GPU, using unique GPU capabilities like the texture cache and a large register file. We'll give information about several applications where these routines are employed, like film and video restoration (either locally or in the cloud) or automatic real-time quality assessment and automatic camera path calculation (virtual director) in omnidirectional video.  Back
 
Topics:
Intelligent Video Analytics, Virtual Reality & Augmented Reality, Video & Image Processing
Type:
Talk
Event:
GTC Silicon Valley
Year:
2018
Session ID:
S8111
Streaming:
Download:
Share:
 
Abstract:
Learn how the analysis of large-scale video data sets can be greatly accelerated by taking usage of the power of GPUs. Due to their robustness, SIFT (Scale-Invariant Feature Transform) descriptors are very popular for all sort of video analysis tasks. In this talk, we will first present an efficient GPU implementation of an interest point detector (e.g. using the DoG or LoG operator) and the extraction of SIFT descriptors around these interest points. We will compare the GPU implementation with the reference CPU implementation from the HessSIFT library in terms of runtime and quality. Furthermore, we will talk about the benefits of GPU-accelerated SIFT descriptors for applications such as near-duplicate video detection, which aims at detecting duplicates almost identical video segments in large video data sets, or linking video segments by shooting location or salient object.
Learn how the analysis of large-scale video data sets can be greatly accelerated by taking usage of the power of GPUs. Due to their robustness, SIFT (Scale-Invariant Feature Transform) descriptors are very popular for all sort of video analysis tasks. In this talk, we will first present an efficient GPU implementation of an interest point detector (e.g. using the DoG or LoG operator) and the extraction of SIFT descriptors around these interest points. We will compare the GPU implementation with the reference CPU implementation from the HessSIFT library in terms of runtime and quality. Furthermore, we will talk about the benefits of GPU-accelerated SIFT descriptors for applications such as near-duplicate video detection, which aims at detecting duplicates almost identical video segments in large video data sets, or linking video segments by shooting location or salient object.  Back
 
Topics:
Video & Image Processing, Computer Vision, Media and Entertainment
Type:
Talk
Event:
GTC Silicon Valley
Year:
2014
Session ID:
S4147
Streaming:
Download:
Share:
 
Abstract:
We show how to port a previously proposed algorithm for detection of severe analog and digital video distortions (termed 'video breakup'), efficiently to Fermi Architecture GPUs with CUDA. By porting to a GPU, the runtime of the CPU implementations can be reduced by an order of magnitude. Thus our GPU algorithm is capable of analyzing up to ten Full HD (1920 x 1080) video streams in real-time. The GPU implementation is integrated in the AV-Inspector application, which allows the user to get an automatic assessment of the quality of video and film material in very short time.
We show how to port a previously proposed algorithm for detection of severe analog and digital video distortions (termed 'video breakup'), efficiently to Fermi Architecture GPUs with CUDA. By porting to a GPU, the runtime of the CPU implementations can be reduced by an order of magnitude. Thus our GPU algorithm is capable of analyzing up to ten Full HD (1920 x 1080) video streams in real-time. The GPU implementation is integrated in the AV-Inspector application, which allows the user to get an automatic assessment of the quality of video and film material in very short time.  Back
 
Topics:
Computer Vision
Type:
Poster
Event:
GTC Silicon Valley
Year:
2012
Session ID:
P2389
Download:
Share:
 
Speakers:
Hannes Fassold
Abstract:

Discover how post-production tasks can be accelerated by taking advantage of GPU-based algorithms. In this talk we present computer vision algorithms for corner detection, feature point tracking, image warping and image inpainting, and their efficient implementation on GPUs using CUDA. We also show how to use these algorithms to do real-time stabilization and temporal re-sampling (re-timing) of high definition video sequences, both common tasks in post-production. Benchmarking of the GPU implementations against optimized CPU algorithms demonstrates a speedup of approximately an order of magnitude.

Discover how post-production tasks can be accelerated by taking advantage of GPU-based algorithms. In this talk we present computer vision algorithms for corner detection, feature point tracking, image warping and image inpainting, and their efficient implementation on GPUs using CUDA. We also show how to use these algorithms to do real-time stabilization and temporal re-sampling (re-timing) of high definition video sequences, both common tasks in post-production. Benchmarking of the GPU implementations against optimized CPU algorithms demonstrates a speedup of approximately an order of magnitude.

  Back
 
Topics:
Computer Vision, Video & Image Processing
Type:
Talk
Event:
GTC Silicon Valley
Year:
2010
Session ID:
2029
Streaming:
Download:
Share:
 
 
Previous
  • Amazon Web Services
  • IBM
  • Cisco
  • Dell EMC
  • Hewlett Packard Enterprise
  • Inspur
  • Lenovo
  • SenseTime
  • Supermicro Computers
  • Synnex
  • Autodesk
  • HP
  • Linear Technology
  • MSI Computer Corp.
  • OPTIS
  • PNY
  • SK Hynix
  • vmware
  • Abaco Systems
  • Acceleware Ltd.
  • ASUSTeK COMPUTER INC
  • Cray Inc.
  • Exxact Corporation
  • Flanders - Belgium
  • Google Cloud
  • HTC VIVE
  • Liqid
  • MapD
  • Penguin Computing
  • SAP
  • Sugon
  • Twitter
Next