Ground Color Customization of Soccer Videos

Ahn, Ilkoo; Kim, Changick

doi:10.1109/acssc.2007.4487260

Cited by 2 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First step in our shot boundary detection algorithm is segmentation of playfield. For this purpose, the method in [19] is used in which the authors assigned N H bins for Hue channel, N S for Saturation channel, and N V for Value channel. In this work, we set N H = 64, N S = 64, N V = 256 experimentally.…”

Section: Playfield Detectionmentioning

confidence: 99%

“…The long shot frames are images captured in a long distance, thus most parts of the shot tend to be occupied by ground. For the other type of frames, the ground color would have little impact on the viewing experience since the viewers' eye gazes are usually drawn by interesting objects [19]. Due to the computational simplicity of our algorithm, we select five frames of the shot, find the class of five frames and assign the shot class to the label of the majority of frames.…”

Section: Shot Classificationmentioning

confidence: 99%

See 1 more Smart Citation

A Low Cost Algorithm for Expected Goal Events Detection in Broadcast Soccer Video

Zameni

Sadri

2010

JDCTA

View full text Add to dashboard Cite

Recently, mining information in sports video data, especially soccer video, has become an active research topic. In this paper, a new algorithm for detection of expected goal events in soccer video is proposed. The proposed algorithm is composed of two main steps. Firstly, video is segmented into its constituent shots and these shots are categorized into two groups, namely long shots and non-long shots. Secondly, long shots are examined to detect expected goal events. Our scheme uses the playfield boundary feature for shot boundary detection, shot classification, and expected goal events detection. Therefore, this feature is extracted only one time and the algorithm is speedy. It is noticeable that the proposed algorithm is robust to blurring and spatial downsampling. Moreover, experimental results on various broadcast soccer videos show that our algorithm can achieve high accuracy and especially high speed.

show abstract

Section: Playfield Detectionmentioning

confidence: 99%

Section: Shot Classificationmentioning

confidence: 99%