Simplifying Accessibility Without Data Loss: An Exploratory Study on Object Preserving Keyframe Culling

  • Marc RitterEmail author
  • Danny Kowerko
  • Hussein Hussein
  • Manuel Heinzig
  • Tobias Schlosser
  • Robert Manthey
  • Gisela Susanne Bahr
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9739)


Our approach to multimedia big data is based on data reduction and processing techniques for the extraction of the most relevant information in form of instances of five different object classes selected from the TRECVid Evaluation campaign on a shot-level basis on 4 h of video footage from the BBC EastEnders series. In order to reduce the amount of data to be processed, we apply an adaptive extraction scheme that varies in the number of representative keyframes. Still, many duplicates of the scenery can be found. Within a cascaded exploratory study of four tasks, we show the opportunity to reduce the representative data, i.e. the number of extracted keyframes, by up to 84 % while maintaining more than 82 % of the appearing instances of object classes.


Multimedia analysis Duplicate detection Human inspired data reduction algorithms Data reduction strategies Big data Object detection Instance Search Rapid evaluation 



This work was partially accomplished within the project localizeIT (funding code 03IPT608X) funded by the Federal Ministry of Education and Research (BMBF, Germany) in the program of Entrepreneurial Regions InnoProfile-Transfer. Programme material is copyrighted by the BBC.


  1. 1.
    Ritter, M.: Optimierung von Algorithmen zur Videoanalyse: Ein Analyseframework für die Anforderungen lokaler Fernsehsender. In: Wissenschaftliche Schriftenreihe Dissertionen der Medieninformatik (3), TU Chemnitz, 336 pp. (2014)Google Scholar
  2. 2.
    Smeaton, A.F., Over, P., Kraaij, W.: Evaluation campaigns and trecvid. In: ACM International Workshop on Multimedia Information Retrieval, pp. 321–330 (2006)Google Scholar
  3. 3.
    Alvi, M., Khan, M.U.G., Sadiq, M., Aslam, M.: University of Engineering & Technology, Lahore, The University of Sheffield at TRECVID, (2011) Observation of strains: Instance Search. In: TRECVID Workshop 2015, Gaithersburg, Maryland, 5 pp. (2015)Google Scholar
  4. 4.
    Feng, Y., Dong, Y., Wu, Y., Bai, H., Cen, S., Liu, B., Wang, K., Liu, Y.: BUPT & ORANGELABS (OrangeBJ) AT TRECVID 2014: INSTANCE SEARCH. In: TRECVID Workshop 2014, 10–12 November 2014, Orlando, Florida, USA, 9 pp. (2014)Google Scholar
  5. 5.
    Yao, L., Ye, M., Liu, D., Shao, R., Liu, T., Liu, J., Wang, Z., Liang, C.: WHU-NERCMS at TRECVID2015: Instance Search task. In: TRECVID Workshop (2015)Google Scholar
  6. 6.
    Ritter, M., Heinzig, M., Herms, R., Kahl, S., Richter, D., Manthey, R., Eibl, M.: Technische Universität Chemnitz at TRECVID Instance Search 2014. In: TRECVID Workshop 2014, 10–12 November 2014, Orlando, Florida, 8 pp. (2014)Google Scholar
  7. 7.
    Ritter, M., Rickert, M., Juturu Chenchu, L., Kahl, S., Robert, H., Hussein, H., Heinzig, M., Manthey, R., Bahr, G.S., Richter, D., Eibl, M.: Technische Universität Chemnitz at TRECVID Instance Search 2015. In: TRECVID Workshop (2015)Google Scholar
  8. 8.
    Ritter, M., Eibl, M.: An extensible tool for the annotation of videos using segmentation and tracking. In: Marcus, A. (ed.) HCII 2011 and DUXU 2011, Part I. LNCS, vol. 6769, pp. 295–304. Springer, Heidelberg (2011)Google Scholar
  9. 9.
    Storz, M., Ritter, M., Manthey, R., Lietz, H., Eibl, M.: Annotate. Train. Evaluate. A unified tool for the analysis and visualization of workflows in machine learning applied to object detection. In: Kurosu, M. (ed.) HCII/HCI 2013, Part V. LNCS, vol. 8008, pp. 196–205. Springer, Heidelberg (2013)Google Scholar
  10. 10.
    Ritter, M., Storz, M., Heinzig, M., Eibl, M.: Rapid model-driven annotation and evaluation for object detection in videos. In: Antona, M., Stephanidis, C. (eds.) UAHCI 2015 Part I. LNCS, vol. 9175, pp. 464–474. Springer, Heidelberg (2015)CrossRefGoogle Scholar
  11. 11.
    Forsyth, D.A., Malik, J., Fleck, M.M., Greenspan, H., Leung, T., Belongie, S., Carson, C., Bregler, C.: Finding pictures of objects in large collections of images. In: International Workshop on Object Recognition for Computer Vision, pp. 335–360 (1996)Google Scholar
  12. 12.
    Over, P., Awad, G., Michel, M., Fiscus, J., Kraaij, W., Smeaton, A.F., Quenot, G., Ordelman, R.: TRECVID 2015-an overview of the goals, tasks, data, evaluation mechanisms and metrics. In: Proceedings of TRECVID 2015, NIST, USA (2015)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Marc Ritter
    • 1
    Email author
  • Danny Kowerko
    • 1
  • Hussein Hussein
    • 1
  • Manuel Heinzig
    • 1
  • Tobias Schlosser
    • 1
  • Robert Manthey
    • 1
  • Gisela Susanne Bahr
    • 2
  1. 1.Junior Professorship Media ComputingTechnische Universität ChemnitzChemnitzGermany
  2. 2.Department of Biomedical EngineeringFlorida Institute of TechnologyMelbourneUSA

Personalised recommendations