Proceedings ArticleDOI
Combining multiple evidence for video classification
S. Vakkalanka,C. Krishna Mohan,R. Kumaraswamy,B. Yegnanarayana +3 more
- pp 187-192
Reads0
Chats0
TLDR
The efficacy of the performance based fusion method is demonstrated by applying it to classification of short video clips into six popular TV broadcast genre, namely cartoon, commercial, news, cricket, football, and tennis.Abstract:
In this paper, we investigate the problem of video classification into predefined genre, by combining the evidence from multiple classifiers. It is well known in the pattern recognition community that the accuracy of classification obtained by combining decisions made by independent classifiers can be substantially higher than the accuracy of the individual classifiers. The conventional method for combining individual classifiers weighs each classifier equally (sum or vote rule fusion). In this paper, we study a method that estimates the performances of the individual classifiers and combines the individual classifiers by weighing them according to their estimated performance. We demonstrate the efficacy of the performance based fusion method by applying it to classification of short video clips (20 seconds) into six popular TV broadcast genre, namely cartoon, commercial, news, cricket, football, and tennis. The individual classifiers are trained using different spatial and temporal features derived from the video sequences, and two different classifier methodologies, namely hidden Markov models (HMMs) and support vector machines (SVMs). The experiments were carried out on more than 3 hours of video data. A classification rate of 93.12% for all the six classes and 97.14% for sports category alone has been achieved, which is significantly higher than the performance of the individual classifiers.read more
Citations
More filters
Journal ArticleDOI
Parallel neural networks for multimodal video genre classification
TL;DR: This article proposes in this article a methodology for classifying the genre of television programmes, which reaches a classification accuracy rate of 95% and is used for training a parallel neural network system able to distinguish between seven video genres.
Journal ArticleDOI
A study on video data mining
TL;DR: The objective of video data mining is to discover and describe interesting patterns from the huge amount ofVideo data as it is one of the core problem areas of the data-mining research community.
Journal ArticleDOI
Sport Type Classification of Mobile Videos
Francesco Cricri,Mikko J. Roininen,Jussi Leppänen,Sujeet Shyamsundar Mate,Igor Danilo Diego Curcio,Stefan Uhlmann,Moncef Gabbouj +6 more
TL;DR: This work extracts domain knowledge about sport events recorded by multiple users, by classifying the sport type into soccer, American football, basketball, tennis, ice-hockey, or volleyball, by using a multi-user and multimodal approach.
Proceedings ArticleDOI
HMM Based Automatic Video Classification Using Static and Dynamic Features
M.K. Geetha,S. Palanivel +1 more
TL;DR: This paper inspects the problem of automatic video classification using static and dynamic features using hidden Markov model (HMM) as the classifier and demonstrates the efficiency of the system by applying it on a broad range of video data.
Book ChapterDOI
Video Structure Analysis and Content-Based Indexing in the Automatic Video Indexer AVI
TL;DR: Experimental results show good performance of the scheme of video scene detection of a given sport discipline in TV sports news, using the Automatic Video Indexer.
References
More filters
Proceedings ArticleDOI
Video classification using spatial-temporal features and PCA
Li-Qun Xu,Yongmin Li +1 more
TL;DR: This work investigates the problem of automated video classification by analysing the low-level audio-visual signal patterns along the time course in a holistic manner using a novel statistically based approach comprising two important ingredients designed for implicit semantic content characterisation and class identities modelling.
Proceedings ArticleDOI
Sports video classification using HMMS
TL;DR: This paper addresses the problem of sports video classification using hidden Markov models (HMMs) by constructing two HMMs representing motion and color features respectively for each sports genre.
Proceedings ArticleDOI
Sports video categorizing method using camera motion parameters
TL;DR: A content based video categorizing method focusing broadcasted sports videos using camera motion parameters, which designs a sports video categorization algorithm for identifying 6 major different sports types based on the characteristics.
Book ChapterDOI
Content-Based Video Classification Using Support Vector Machines
TL;DR: This paper proposes an optimized multi-class classification method based on spatial and temporal descriptors derived from short video sequences based on support vector machines (SVMs) and achieves accuracy of 92.5%.
Proceedings ArticleDOI
Edge-based semantic classification of sports video sequences
TL;DR: This paper proposes an algorithm for edge detection, and illustrates the usage of edges for semantic analysis of video content, and shows how an audio feature can be used as a filter to enhance edge-based semantic classification.