Paper Info
Title
A Big-Bang Big-Crunch Type-2 Fuzzy Logic Based System For Soccer Video Scene Classification
Abstract
The recent years have witnessed significant progress in the automation of sports video summarization. The vast majority of the techniques applied to sports video classifications involved black box techniques such as support vector machines (SVMs) and neural networks, which do not provide models that could be easily analysed and understood by human users. Video scenes can be regarded as continuous sequences of images, but the classification problem is much more complicated than single image classification due to the dynamic nature of the video sequence and the associated changes in light conditions, background, camera angle, occlusions, indistinguishable scene features, etc. In order to handle such high levels of uncertainties in video scenes classification, we introduce a system based on Interval Type-2 Fuzzy Logic Classification Systems (IT2FLCS) whose parameters are optimized by the Big Bang-Big Crunch (BB-BC) algorithm which allows for real time scenes classification using optimized rules in broadcasted soccer matches video. The proposed system allows achieving relatively high classification accuracy with a small number of rules, thus increasing the system interpretability.
Year
Venue
Keywords
2016
2016 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ-IEEE)
type-2 fuzzy logic, fuzzy logic classification system, video scene classification, video summarization
Field
DocType
ISSN
Computer science,Fuzzy set,Artificial intelligence,Contextual image classification,Automatic summarization,Computer vision,Neuro-fuzzy,Pattern recognition,Support vector machine,Fuzzy logic,Feature extraction,Video tracking,Machine learning
Conference
1544-5615
Citations 
PageRank 
References 
1
0.35
12
Authors
2
Name
Order
Citations
PageRank
Wei Song110.35
Hani Hagras21747129.26