Automatic player detection and identification for sports entertainment applications

Abstract

In this paper, we develop an augmented reality sports broadcasting application for automatic detection, recognition of players during play, followed by display of personal information of players. The proposed application can be divided into four major steps. In first step, each player in the image is detected. In the second step, a face detection algorithm detects face of each player. In third step, we use a face recognition algorithm to match the faces of players with a database of players' faces which also stores personal information of each player. In step four, personal information of each player is retrieved based on the face matching result. This application can be used to show the viewers' information about players such as name of the player, sports record, age, highest score, and country of belonging. We develop this system for baseball game, however, it can be deployed in any sports where the audience can take a live video or images using smart phones. For the task of player and subsequent face detection, we use AdaBoost algorithm with haar-like features for both feature selection and classification while player face recognition system uses AdaBoost algorithm with linear discriminant analysis for feature selection and nearest neighbor classifier for classification. Detailed experiments are performed using 412 diverse images taken using a digital camera during baseball match. These images contain players in different sizes, facial expressions, lighting conditions and pose. The player and face detection accuracy is high in all situations, however, the face recognition module requires detected players' faces to be frontal or near frontal. In general, restricting the head rotation to ±30°gives a high accuracy of overall system

EAR: Enhanced Augmented Reality System for Sports Entertainment Applications

“…Standard implementation of the Viola and Jones face detector is available in various programming languages among which the one in OpenCV 1 is the most popular. This approach is based on Adaptive Boosting [8,9,25,26,38] (AdaBoost) and Haar-like features [32]. For a set of training images (x i , y i ), the AdaBoost selects combination of several weak classifiers (h j (x)) from Haar-like features and pools into a robust classifier that gives better classification accuracy [31].…”

A Comparative Study of Baseline Algorithms of Face Recognition

“…Therefore, an interesting finding of our work is that AdaBoost based FR system surpasses PCA based system on LR images. A huge number of potential applications need completely reliable FR system [22], [24], and [25]. Therefore, the FR technology has to mature more to be deployed more in common practice.…”

“…These features are then compared with the features of the probe image and a similarity score is computed for a given comparison. Larger the similarity scores, the more similar images are in the given pair of images [22]. The rest of the paper is organised as follows.…”

A mobile augmented reality system to enhance live sporting events

“…Baseball's heavy dependency on a player's field location limits its applicability to other sports. In [7], Mahmood et. al.…”