Thermal Tracking of Sports Players
نویسندگان
چکیده
We present here a real-time tracking algorithm for thermal video from a sports game. Robust detection of people includes routines for handling occlusions and noise before tracking each detected person with a Kalman filter. This online tracking algorithm is compared with a state-of-the-art offline multi-target tracking algorithm. Experiments are performed on a manually annotated 2-minutes video sequence of a real soccer game. The Kalman filter shows a very promising result on this rather challenging sequence with a tracking accuracy above 70% and is superior compared with the offline tracking approach. Furthermore, the combined detection and tracking algorithm runs in real time at 33 fps, even with large image sizes of 1920 × 480 pixels.
منابع مشابه
Monitoring Training Load on Malaysian Rugby 15s Players
Background. In order to minimize overtraining, a reliable method is required to analyze training loads. Objectives. The objective of this study was to see if session Rate of Perceived Exertion (sRPE) is a valuable tool for tracking changes in perceived training load and strain among Malaysia rugby 15-a-side players during preparation for a significant game. Methods. Twenty-eight (n=28) elite ...
متن کاملA Computer Vision Based Tracking System for Indoor Team Sports
This paper presents a video tracking system for tracking players in indoor sports using two high quality digital cameras. The tracking algorithm is based on template matching technique taking into consideration closed world assumptions. The output of the system can be visualized interactively for convenient analysis of player movements. The implementation has been efficiently done as a software...
متن کاملA hierarchical dynamic model for tracking in sports∗
Dynamic models play a crucial role in tracking algorithms. In particle filters, for example, proper modelling of the target dynamics can help achieving the desired tracking accuracy using only a small number of particles and thus reducing the computational complexity of the tracker. We propose a novel hierarchical model for tracking players in sports by combining a conservative and a liberal dy...
متن کاملMulti-target tracking in team-sports videos via multi-level context-conditioned latent behaviour models
Multi-target tracking techniques increasingly exploit contextual information about group dynamics. However, approaches established in pedestrian tracking make assumptions about features and motion models which are often inappropriate to sports team tracking, where motion is erratic and players wear similar uniforms with frequent interplayer occlusions. On the other hand, approaches designed spe...
متن کاملMean Shift Driven Particle Filter for Tracking Players in Sports
This paper proposes a novel Mean Shift driven particle filter algorithm for tracking players in sports. A region of interest (ROI) is specified manually in the initial frame. The color image of the ROI is projected to a brightness and gamma corrected HSV space and the hue component of the HSV space is used to model the probability density function of the ROI, which ensures that the proposed app...
متن کامل