الفهرس 
AbstractOnly 14 pages are availabe for public view
 |  | from | 141 |  |  |
| | | from | 141 | | |
Abstract
Soccer is the most popular group game; it has a large number of fans all over the world. Although each complete soccer match lasts around one hour and a half, only have very few scenes attracting audiences been perfectly filmed. This filming has usually been done using static (fixed) cameras, and they cannot provide the same level of accuracy or entertainment given by mobile devices. Taking into our consideration that there are no schemes using mobile devices have been proposed to solve this problem till now. As periodic communication generates a huge amount of data; typical storage, computation, and communication resources are required. Hence, this paper aims at introducing a Fog computing mechanism that takes into consideration the requirements of special mobility, low latency and location awareness. Our solution based on controlling the movement of mobile cameras mounted on a fleet of mobile bees. A bee is an autonomous camera-drone, which gives the audience the feeling of being a part of such sports competition. It is a special type of Unmanned Aerial Vehicle (UAV) equipped with a built-in processing unit, memory, high-speed camera and transceiver. The bee has the ability to film the movement of the ball, which has to be followed and filmed via object tracking principle. In fact, detecting and tracking the ball from the broadcast soccer video constitute a major challenge. In soccer matches, the ball moves most of the time and it is frequently occluded while its size and shape appearance vary over the time and between cameras. Moreover, the feature-based tracking methods are used to judge whether or not a sole object is the target as the features of the ball might be changed fast over frames and then we cannot manage to distinguish the ball from other objects by using these methods. Thus, the current study demonstrates an innovative technique for tracking a soccer ball from mobile cameras fixed on multiple ball bees. Sports video analysis has received much attention as it is turned to be a hot research area in the field of image processing. This led to opportunities to develop fascinating applications supported by analysis of different sports especially football. Identifying the ball in soccer images is an essential task for not only goal scoring but also players’ evaluation. However, soccer ball detection suffers from several hurdles such as; occlusions, fast moving objects, shadows, poor lighting, color contrast, and other static background objects. Although several ball detection techniques have been introduced such as; Frame Difference, Mixture of Gaussian (MoG), Optical Flow and etc., ball detection in soccer games is still an open research area. In this paper, a new Fuzzy Based Ball Detection (FB2D) strategy is proposed for identifying the ball through a set of image sequences extracted form a soccer match video. FB2D has the ability to accurately identify the ball even if it is attached to the white lines drawn on the playground or partially occluded behind players. FB2D has been compared to recent ball detection techniques. Experimental results have shown that FB2D outperforms recent detection techniques as it introduced the maximum accuracy and the accuracy of detection in the testing stage is close to 100%. As well as the minimum error.