Automatic Semantic Video Annotation

Automatic Semantic Video Annotation

Amjad Altadmri, Amr Ahmed*, Andrew Hunter

Poster - Click here to download PDF.
Poster – see link below to download PDF.

 

 

 

(Click Semantic Video Annotation-with Knowledge ” http://amrahmed.blogs.lincoln.ac.uk/files/2013/03/Semantic-Video-Annotation-with-Knowledge.pdf  ,  to download the pdf)

INTRODUCTION

The volume of video data is growing exponentially. This data need to be annotated to facilitate search and retrieval, so that we can quickly find a video whenever needed.

Manual Annotation, especially for such volume, is time consuming and would be expensive. Hence, automated annotation systems are required.

 

AIM

Automated Semantic Annotation of wide-domain videos (i.e. no domain restrictions). This is an important step towards bridging the “Semantic Gap” in video understanding.

 

METHOD

1. Extracting “Video Signature” for each  video.
2. Match signatures to find most similar  videos, with annotations
3. Analyse and process obtained annotations, in consultation with Common-sense knowledge-bases
4. Produce the suggested annotation.

EVALUATION

• Two standard, and challenging  Datasets  were used. TRECVID BBC Rush and UCF.
• Black-box and White-box testing carried out.
•Measures include: Precision, Confusion Matrix.

CONCLUSION

•Developed an Automatic Semantic Video Annotation framework.
•Not restricted to a specific domain videos.
•Utilising Common-sense Knowledge enhances scene understanding and improve semantic annotation.
Publications
  1. A framework for automatic semantic video annotation 
    Altadmri, Amjad and Ahmed, Amr (2013) A framework for automatic semantic video annotation. Multimedia Tools and Applications, 64 (2). ISSN 1380-7501.
  2. Semantic levels of domain-independent commonsense knowledgebase for visual indexing and retrieval applications 
    Altadmri, Amjad and Ahmed, Amr and Mohtasseb Billah, Haytham (2012) Semantic levels of domain-independent commonsense knowledgebase for visual indexing and retrieval applications. Neural Information Processing. Lecture Notes in Computer Science, 7663 . pp. 640-647. ISSN 0302-9743
  3. VisualNet: commonsense knowledgebase for video and image indexing and retrieval application 
    Alabdullah Altadmri, Amjad and Ahmed, Amr (2009) VisualNet: commonsense knowledgebase for video and image indexing and retrieval application. In: IEEE International Conference on Intelligent Computing and Intelligent Systems, 21-22 November 2009, Shanghai, China..
  4. Automatic semantic video annotation in wide domain videos based on similarity and commonsense knowledgebases 
    Altadmri, Amjad and Ahmed, Amr (2009) Automatic semantic video annotation in wide domain videos based on similarity and commonsense knowledgebases. In: The IEEE International Conference on Signal and Image Processing Applications (ICSIPA 2009), 18-19th November 2009, Malaysia.
  5. Video databases annotation enhancing using commonsense knowledgebases for indexing and retrieval 
    Altadmri, Amjad and Ahmed, Amr (2009) Video databases annotation enhancing using commonsense knowledgebases for indexing and retrieval. In: The 13th IASTED International Conference on Artificial Intelligence and Soft Computing., September 7 � 9, 2009, Palma de Mallorca, Spain.

Conference Paper Accepted – DHS virtual training

Another conference paper been accpeted, and will be published in June 2012. This paper reports on the development of the 2 3D tracking prototypes for virtual reality training of surgeons (in vitro / Off patient), especially for the Dynamic Hip Screw surgical procedure (in particular; the insertion of the guide-wire). The aim is to develop the cognitive coordination, in particular the Brain/Hands/Eyes coordination that is crucial for such procedure. But through an affordable system that uses Commercial off-the-shelf (COTs)  components.

This work is in collaboration with Prof. Maqsood, Consultant Trauma and Orthopaedic surgeon in the Lincoln Hospital.

 

Project in the media/press:

More information and images: http://amrahmed.blogs.lincoln.ac.uk/2009/11/04/masterig-dhs/

V&L Network workshop, Brighton

Dr Amr Ahmed attended the Vision & Language Netowork Workshop in Brighton last Thursday 15th September, where 2 posters and oral presentation were presented from the DCAPI group.

DCAPI poster at the V&L Network workshop - Sept'11 - Brighton
DCAPI poster at the V&L workshop

 

Over 40 researchers, from vision and language areas, attended and it was a good opportunity for networking and exchange of contacts and ideas. Posters and sides will be available on the network’s website in the near future

Amr and a keynote speaker
Amr and a keynote speaker
Amr and a keynote speaker
Amr and one of the keynote speaker

 

Mr Amjad Altadmri also attended and presented in the event.

Some nice photos in Brighton,

Amr in Brighton Pier
Amr in Brighton Pier

with some Icereame! 🙂