Sequential probabilistic grass field segmentation of soccer video images

Authors:
Kaveh Kangarloo;Ehsanollah Kabir
Affiliations:
Dept. of Electrical Eng., Azad University, Central Tehran Branch, Tehran, Iran;Dept. of Electrical Eng., Tarbiat Modarres University, Tehran, Iran
Venue:
IWCIA'04 Proceedings of the 10th international conference on Combinatorial Image Analysis
Year:
2004

Citing 6
Cited 0

Bayesian Classification With Gaussian Processes

IEEE Transactions on Pattern Analysis and Machine Intelligence
Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Colour Model Selection and Adaption in Dynamic Scenes

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
On the Performance Characterisation of Image Segmenation Algorithms: A Case Study

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Where Are the Ball and Players? Soccer Game Analysis with Color Based Tracking and Image Mosaick

ICIAP '97 Proceedings of the 9th International Conference on Image Analysis and Processing-Volume II
Automatic Classification of Tennis Video for High-level Content-based Retrieval

CAIVD '98 Proceedings of the 1998 International Workshop on Content-Based Access of Image and Video Databases (CAIVD '98)

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a method for segmentation of grass field of soccer video images. Since the grass field is observed as a green and nearly soft region, the hue and a feature representing the color dispersion in horizontal and vertical directions are used to model the grass field as a mixture of Gaussian components. At first, the grass field is roughly segmented. On the base of grass field model, the probability density function of non-grass field is estimated. Finally using the Bayes theory, in a recurrent process the grass field is finally segmented.