[an error occurred while processing this directive] [an error occurred while processing this directive]
RUSSIAN VERSION

MSU Scene Change Detector
(SCD)

MSU Graphics & Media Lab (Video Group)

Take a look at this article on the new site! Follow the link
https://videoprocessing.ai/vqmt/plugins-scd.html

About Metrics Python Online help Changelog Screenshots Plugins & SDK

Project, Ideas: Dr. Dmitriy Vatolin, Alexander Parshin
Implementation: Ivan Glazistov
Updating and additions: Sergey Grishin
 [an error occurred while processing this directive]

Common Description

[an error occurred while processing this directive]


Scene Change Detector is made to automatic identification of scene boundaries in video sequence. [an error occurred while processing this directive]

Change Log

[an error occurred while processing this directive]

[!] - Known bug
[+] - New Feature
[*] - Other

Version 1.2
[*] Windows Vista & Windows 7 support implemented

Version 1.1
[*] Visualization bug fixed for non-stadard resolution video

Version 1.0
[+] First plugin release

[an error occurred while processing this directive]

Usage

[an error occurred while processing this directive]


The plugin implements four algorithms of similarity measurements between two adjacency frames in video sequence:

  1. Pixel-level frames comparison
  2. Global Histogram comparison
  3. Block-Based Histogram comparison
  4. Motion-Based similarity measure
The choice of the algorithm can be made in Settings. Numbers from 1 up to 4 corresponds to each algorithm.

Default and recommended value is 3 (Block-Based Histogram).

[an error occurred while processing this directive]

Visualisation

[an error occurred while processing this directive]


Y-plane is drawing during the visualization. Brightness of scene boundary frames is increased.

Example of visualization:

[an error occurred while processing this directive]
[an error occurred while processing this directive] [an error occurred while processing this directive]

Plots

[an error occurred while processing this directive]

Metric's plot is making after all measurements. "One" value means that current frame is the first frame in scene, other frames have "zero" values. Sequence average value is the number of detected scene changes.

Plot's example
Plot's example
[an error occurred while processing this directive]

Algorithm

[an error occurred while processing this directive]


Pixel-level comparison

Similarity measure of two frames is the sum of absolute differences (SAD) between corresponding pixels values.

Global Histogram

The histogram is obtained by counting the number of pixels in frame with specified brightness level. The difference between two histograms is then determined calculating SAD of number of pixels on each brightness level.

Block-Based Histogram

Each frame is divided into 16x16 pixel blocks. Brightness distribution histogram is constructed for each block. Then similarity measure for each block is obtained. Average value of these measures is accepted as a frames similarity measure.

Motion-Based

Motion Estimation algorithm with block size 16x16 pixels is performed for two adjacency frames at the first stage. After that average value of motion vector errors is accepted as a finally similarity measure. [an error occurred while processing this directive]

Download

[an error occurred while processing this directive] [an error occurred while processing this directive]

MSU Video Quality Measurement Tools

[an error occurred while processing this directive]

e-mail: 

[an error occurred while processing this directive]

Other resources

[an error occurred while processing this directive] [an error occurred while processing this directive] [an error occurred while processing this directive] [an error occurred while processing this directive]