Evaluation of Image Representations for Player Detection in Field Sports Using Convolutional Neural Networks

  • Melike ŞahEmail author
  • Cem Direkoğlu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 896)


Player detection is an important task in sport video analysis. Once players are detected accurately, it can be used for player tracking, player activity/performance analysis as well as team activity recognition. Recently, convolutional Neural Networks (CNN) became the state-of-the-art in computer vision for object recognition. CNN based methods usually use gray or RGB images as an input. It is also possible to use other image representation techniques such as shape information image and polar transformed shape information image for player detection. In this paper, we evaluate various image representation techniques for player detection using CNN. In our evaluation, first the candidate image regions for players are determined using a sliding window technique. Then these regions are input to CNN for player detection. We examine four different types of image representations as an input to CNN: RGB, gray, shape information and polar transformed shape information image. Evaluation is conducted on a field hockey dataset. Results show that CNN based player detection is effective and different image representations yield different performances.


Player detection Field sports Shape information image Polar transformed shape information image Convolutional neural networks 


  1. 1.
    Hamid, R., Kumar, R.K., Grundmann, M., Kihwan, K., Essa, I., Hodgins, J.: Player localization using multiple static cameras for sports visualization. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, USA, pp. 731–738 (2010)Google Scholar
  2. 2.
    Han, B., Davis, L.S.: Density-based multifeature background subtraction with support vector machine. IEEE Trans. Pattern Anal. Mach. Intell. 34(5), 1017–1023 (2012)CrossRefGoogle Scholar
  3. 3.
    Carr, P., Sheikh, Y., Matthews, I.: Monocular object detection using 3D geometric primitives. In: European Conference on Computer Vision, Florence, Italy, vol. 7572, pp. 864–878 (2012)CrossRefGoogle Scholar
  4. 4.
    Xu, M., Orwell, J., Lowey, L., Thirde, D.: Architecture and algorithms for tracking football players with multiple cameras. IEE Vis. Image Signal Process. 152(2), 232–241 (2005)CrossRefGoogle Scholar
  5. 5.
    Direkoglu, C., Sah, M., O’Connor, N.: Player detection in field sports. Mach. Vis. Appl. 29(2), 187–206 (2018)CrossRefGoogle Scholar
  6. 6.
    Lu, K., Chen, J., Little, J.J., He, H.: Light cascaded convolutional neural networks for accurate player detection. In: British Machine Vision Conference (BMVC), London, UK (2017)Google Scholar
  7. 7.
    Lehuger, A., Duffner, S., Garcia, C.: A robust method for automated player detection in sport videos. In: Compression et Representation des Signaux Audievisuels (2007)Google Scholar
  8. 8.
    Acuna, D.: Towards real-time detection and tracking of basketball players using deep neural networks. In: Conference on Neural Information Processing Systems, California, USA (2017)Google Scholar
  9. 9.
    Direkoglu, C., Nixon, M.S.: Moving edge detection via heat flow analogy. Pattern Recogn. Lett. 32(2), 270–279 (2011)CrossRefGoogle Scholar
  10. 10.
    Direkoglu, C., Nixon, M.S.: Image-based multiscale shape description using gaussian filter. In: IEEE Indian Conference on Computer Vision, Graphics and Image Processing, Bhubaneswar, India, pp. 673–678 (2008)Google Scholar
  11. 11.
    Direkoglu, C., Nixon, M.S.: Shape extraction via heat flow analogy. In: International Conference on Advanced Concepts for Intelligent Vision Systems, Delft, Netherlands, pp. 553–564 (2007)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer EngineeringNear East UniversityNicosiaTurkey
  2. 2.Department of Electrical and Electronics EngineeringMiddle East Technical University - Northern Cyprus CampusKalkanli, GuzelyurtTurkey

Personalised recommendations