Technical feasibility

Presentation_Contours_ProjectSECTION I: Testing

1 Has the R & D result been tested?
YES Tested in part

In what mode has the result been tested?

  Pilot Application

  The testing comprises the new algorithms for contours extraction from consecutive TV frames and the creation of new video sequences with contour images only. The video information with the extracted contour images is losslessly compressed and converted into new format. The software player used for the visualization of the compressed information was also created. For the testing was used the software implementation of the new algorithms in C++, Windows environment. Special attention was paid to selection of sign language interpreters’ face and hands contours, which is of highest importance for the interpretation comprehensibility. For the comparison were used Quick time, Pinnacle, MPEG2 and MPEG4 software implementations.
1b Please describe and discuss the testing results

For comparison and evaluation were used English idioms used for training of hearing impaired at the University of Arkansas, Little Rock (UALR) USA.  The original video information was in Quick Time format. It was compressed to a significant degree, which as a rule results into visual quality deterioration in parts with fast movements of interpreter’s hands. For the testing the visual file was decompressed and after that the consecutive TV frames were extracted and processed individually in order to extract the contours of the sign language interpreter’s figure. In a part of the frames the contours of the image were visually significantly deteriorated and the extraction of the main contours was not satisfactory. For this, the successful extraction of the main contours requires to use the original video (without compression) or a video with small compression only. The use of I-frames is a solution also. After separating the video presentation into single frames, the extraction of the main contours is very successful and confirms the efficiency of the specially developed methods.

The new format, which was created for the coding of the compressed video sequences, is very efficient (the new video files are very compact: for example, a video of length 6s, compressed into Quick Time format is of size 1MB, and the corresponding video clip saved in the new format is about 120 KB).

The new method was implemented in C++, Windows environment. A software player for the visualization of the compressed information is also developed.

1c To what extent does the result correspond to the initially defined task?

The testing results proved the method efficiency in compression ratio and comprehensibility: the compression ratio obtained for lossless compression of the extracted contour images is about 8 times smaller than the Quick Time format. The comprehensibility of the contour representations was evaluated by specialists in UALR, USA, who evaluated it as comprehensible.

The testing comprises the developed new algorithms only.

SECTION 2: Current Stage of Development

2a To what extent does the development team have technical resources for supporting the production of a new product[1]? (Researchers, human resources, hardware, etc. )
  The R&D result is a result of collective effort.The development team has technical resources for supporting the production of the new product
2b What are the technical issues that need to be tackled for full deployment, if needed?

The preparation of a product needs the following:

- Performing some experiments, which to establish the conditions, needed for the preparation of the original video presentations – lighting; distance between the TV camera and the sign language interpreter and the color of the sign language interpreter’s dress.

- Development of a software for the automatic processing of the so prepared video presentations;

- Development of software for the contour presentations embedding in live video, containing regular training video courses.

2c What additional technical resources are needed for the production of this new product?
  The special technical resources should provide ability to process video sequences
2d Overall assessment of the current stage of technical development

The new product is technically feasible.

After performing the already described procedures, will be obtained a user-friendly product, which could be used for the development of special training courses for hearing impaired, which to be embedded as additional information in training courses, already used for distance learning in different disciplines. Special attention will be paid to training in mathematics, physics, i.e. in all cases, when the training needs clear representation of formulas of any kind. I this case the formulas should be embedded in the video sequence as separate images of highest quality.

SECTION 3: Deployment

3a Define the demands for large scale production in terms of
  • Materials : kinds , quantities, costs
The demands for large scale production are similar with these any software production.
  • technologies, tools, machineries
     Software for processing of video sequences and for still image processing
  • Staff effort in man/hours or man/months
       6-8 months
SECTION 4: Overall Assessment


What is you overall assessment of the technical feasibility of the research result? 

The research result is technically feasible.



  1 2 3 4 5
Adequacy of testing activity undertaken so far       x  
Adequacy and availability of technical resources of the development team         x
Current development stage     x    
Overall technical feasibility       x  

[1] Throughout this section by “new product” we mean a product or a service or a technology

Bookmark the permalink. Follow any comments here with the RSS feed for this post. Post a comment or leave a trackback: Trackback URL.

Post a Comment

You must be logged in to post a comment.

Visit the other applications of the INTERVALUE Platform: R&D Repository | IP Agreements

© 2009-2010 INTERVALUE Project