Video Quality Analysis Software Development Kit
(VQA SDK)

Full-reference perceived audio/video quality analysis technologies for third-party applications

Now available for Windows and Linux

 

Video Quality Analysis Software Development Kit (VQA SDK) is a library which contains the perceived video quality measurement and perceived audio quality measurement technologies available in Video Quality Analyzer (VQA).

VQA SDK enables to measure video quality using several video quality metrics:

  • our full-reference metrics dedicated to MPEG-2, MPEG-4/AVC (H.264) and HEVC video encoding formats
  • Netflix's VMAF metric (using the latest version of VMAF)
  • Mean Squared Error (MSE)
  • Peak Signal-to-Noise Ratio (PSNR)
  • VIF
  • PSNR-HVS and PSNR-HVS-M
  • SSIM and MS-SSIM

VQA SDK also enables to measure the synchronization between video and audio (lipsync).

VQA SDK also enables audio quality measurement using PSNR.

VQA SDK enables to:

  • add video quality measurement capabilities in an existing application
  • add audio quality measurement capabilities in an existing application
  • compute video DMOS, VMAF, PSNR, VIF, SSIM values
  • compute values of blockiness, blur, contrast and flatness
  • compute audio PSNR
  • extract video frames from virtually any video file format
  • measure blockiness (sometimes called "blocking effect"), blur (sometimes called "blurring"), contrast and flatness

VQA SDK is a software product which exists for both Windows and Linux.

Overview of VQA SDK

VQA SDK contains the following elements:

  • for Windows: several DLL (dynamic-link libraries) files and one .lib file
  • for Linux: several libraries (.so)
  • one C header file (VQASDK.h) which must be included in your application
  • documentation (developer manual)
  • The C and C++ source code of a sample application which shows how to process audio/video files

Decoding

VQA SDK supports the most popular file formats (*.avi, *.ts, *.mov, *.mp4, *.mxf, *.mp3, *.aac, etc.).

The following pixel formats are supported:

  • YUV 4:2:0 planar (YV12)
  • YUV 4:2:2 packed UYVY
  • YUV 4:2:2 packed YUYV
  • YUV 4:2:2 packed YVYU
  • YUV 4:4:4 YUVA
  • RGB32
  • BGR32
  • Y component only

The following audio sample formats are supported:

  • signed 16 bits
  • signed 32 bits
  • float
  • double

Metrics

VQA SDK contains the following metrics for video:

  • our full-reference metrics, dedicated to MPEG-2, MPEG-4/AVC (H.264) and HEVC video encoding formats
  • Blockiness
  • Blur
  • Contrast (for H.264)
  • Flatness (for HEVC)
  • Netflix's VMAF metric (using the latest version of VMAF)
  • MSE: Mean Squared Error
  • PSNR: Peak Signal-to-Noise Ratio
  • VIF: Visual Information Fidelity
  • PSNR-HVS: Peak Signal-to-Noise Ratio taking into account Contrast Sensitivity Function (CSF) of human vision
  • PSNR-HVS-M: Peak Signal-to-Noise Ratio taking into account Contrast Sensitivity Function (CSF) and contrast masking between DCT coefficients
  • SSIM: Structural Similarity Index Measure
  • MS-SSIM: Multi-Scale Structural Similarity Index Measure
  • Lipsync: measure the skew (in milliseconds) between video and audio

Functioning

VQA SDK automatically aligns the two videos (reference video and measured video) before quality measurement.

You only have to specify the two videos and VQA SDK will take in charge the synchronization and the quality measurement.

You can define your own callback function to receive the measured values during processing.

Conclusion

VQA SDK enables to integrate state-of-the-art perceived audio/video quality measurement or video/audio synchronization technologies in your own application.

Ask for an evaluation version today!