|
Video cameras are becoming omnipresent. Movies and TVs have made videos very close to us. Processing, analysis and understanding of content present in videos is becoming very important. Bulkiness of the data makes the problem of video processing more complex compared to image analysis.
However, video processing is not just about processing individual frames/images. Video has lot more information than the isolated images. This comes from the spatio temporal continuity of the data. Many of the video data also come with different auxiliary and supplementary information. Thus video processing and analysis necessitates a different class of algorithms. We explore video processing in the larger context of multimedia and multimodal computing. We also investigate the dynamics and articulations associated with popular objects like humans and man made objects.
Since many of the video repositories are continously increasing in size, there is a special need for processing them online and analysing the common and emerging patterns present in them. This requires specific architectures and applications.
Specific activities in this area include:
* Dynamic Scene Analysis
* Aligning Text and Videos (for movies, sports videos etc.)
* Classification of Videos
* Online Video Processing
* Multimedia Mining
Specific activities in this area include:
Related Papers:
* Pramod Sankar K, C.V. Jawahar and Andrew Zisserman "Subtitle-free Movie to Script Alignment" in Proceedings of British Machine Vision Conference (BMVC 09), 7-10 September, 2009, London, UK.
* Mihir Jain, Sreekanth Vempati, Chandrika Pulla and C.V. Jawahar "Example Based Video Filters" in Proceedings of the 8th International Conference on Image and Video Retrieval (CIVR 2009), July . 8-10, 2009, Santorini, Greece.
* Pramod Sankar K. and C.V.Jawahar "Enabling Search over Large Collections of Telugu Document Images-An Automatic Annotation Based Approach" in 5th Indian Conference on Computer Vision, Graphics and Image Processing, Madurai, India, LNCS 4338 pp.837-848, 2006.
* Karteek Alahari and C.V.Jawahar "Dynamic Events as Mixtures of Spatial and Temporal Features" in 5th Indian Conference on Computer Vision, Graphics and Image Processing, Madurai, India, LNCS 4338 pp.540-551, 2006.
* Karteek Alahari and C.V.Jawahar "Discriminative Actions for Recognising Events" in 5th Indian Conference on Computer Vision, Graphics and Image Processing, Madurai, India, LNCS 4338 pp.552-563, 2006.
Related Thesis:
* Modelling and Recognition of Dynamic Events in Video
Karteek Alahari, Year of Completion : 2005
Faculty
- C V Jawahar
- P J Narayanan
(Head)
|