Shape-Based Individual/Group Detection for Sport Videos Categorization

Abstract

We present a shape based method for automatic people detection and counting without any assumption or knowledge of camera motion. The proposed method is applied to athletic videos in order to classify them to videos of individual and team sports. Moreover, in the case of team (multi-agent) sport, we propose a shape deformations based method for running/hurdling discrimination (activity recognition). Robust, adaptive and independent from the camera motion, the proposed features are combined within the Transferable Belief Model (TBM) framework providing a two level (frames and shot) video categorization. The TBM allows to take into account imprecision, uncertainty and conflict inherent to the features into the fusion process. We have tested the proposed scheme into a big variety of athletic videos like pole vault, high jump, triple jump, hurdling, running, etc. The experimental results of 97% individual/team sport categorization accuracy, using a dataset of 252 real videos of athletic meetings acquired by moving cameras under varying view angles, indicate the stability and the good performance of the proposed scheme.

The contribution of pattern recognition techniques in geomorphology and geology: the case study of Tinos Island (Cyclades, Aegean, Greece)

“…It corresponds to the angle between the horizontal axis and the major axis of the ellipse having the same second-order moments (Panagiotakis, Ramasso, Tziritas, Rombaut, & Pellerin, 2008) as the detected topographic high region.…”

Human Motion Analysis and Simulation Tools

“…In order to facilitate an efficient access and an accurate search to those contents, several solutions for an automatic video annotation have been developed. An example is presented in (Panagiotakis, Ramasso, Tziritas, Rombaut, & Pellerin, 2008) where it is proposed a method to classify sport videos as team sports or as individual sports, or in (Y. Ke, Sukthankar, & Hebert, 2007) where it is proposed a method that can detect a wide range of actions in video, as demonstrated by results on a long tennis match video.…”

Lymphocyte Segmentation Using the Transferable Belief Model

“…The TBM is an alternative to probability measure for knowledge modelling and the main advantage and power of the TBM is the capacity to explicitly model doubt and conflict. TBM has been successfully applied on object detection and tracking problems [7] combined with shape and motion based features. The mean value and the variance can be adequately converted into beliefs (symbolic representation).…”

“…Finally, the area (A i ) and the eccentricity (E i ) [7] are used in the decision of splitting a detected region to more than one regions plausibly corresponding to lymphocyte nuclei.…”