Active Foreground Region Extraction and Tracking for Sports Video Annotation
- 296 Downloads
- 6 Citations
Abstract
Automatic video segmentation plays a vital role in sports videos annotation. This paper presents a fully automatic and computationally efficient algorithm for analysis of sports videos. Various methods of automatic shot boundary detection have been proposed to perform automatic video segmentation. These investigations mainly concentrate on detecting fades and dissolves for fast processing of the entire video scene without providing any additional feedback on object relativity within the shots. The goal of the proposed method is to identify regions that perform certain activities in a scene. The model uses some low-level feature video processing algorithms to extract the shot boundaries from a video scene and to identify dominant colours within these boundaries. An object classification method is used for clustering the seed distributions of the dominant colours to homogeneous regions. Using a simple tracking method a classification of these regions to active or static is performed. The efficiency of the proposed framework is demonstrated over a standard video benchmark with numerous types of sport events and the experimental results show that our algorithm can be used with high accuracy for automatic annotation of active regions for sport videos.
Keywords
Background subtraction Object detection Spatial correlation Parametric and non-parametric approaches Sports video Dominant color ClusteringReferences
- 1.Assfalg J, Bertini M, Colombo C, Del Bimbo A, Nunziat W (2005) Semantic annotation of soccer videos: automatic highlights identification. Comput Vis Image Underst 2:619–628Google Scholar
- 2.Belongie S, Carson C, Greenspan H, Malik J (1998) Color- and texture-based segmentation using EM and its application to content-based image retrieval, IEEE international conference computer vision, pp 675–682Google Scholar
- 3.Bouwmans T, El Baf F (2009) Modeling of dynamic backgrounds by type-2 fuzzy Gaussians mixture models, MASAUM. J Basic Appl Sci 1(2):265–277Google Scholar
- 4.Bouwmans T, El Baf F, Vachon B (2008) Background modeling using mixture of Gaussians for foreground detection: a survey. Recent Pat Comput Sci 1(3):219–237CrossRefGoogle Scholar
- 5.Duan L, Xu M, Chua T, Tian Q, Xu C (2003) A mid-level representation framework for semantic sports video analysis. In Proceedings of ACM MM 2003 pp 33–44Google Scholar
- 6.El Baf F, Bouwmans T, Vachon B (2008) Type-2 fuzzy mixture of Gaussians model: application to background modeling, intelligent symposium visual, computingGoogle Scholar
- 7.Ekin A, Murat Tekalp A (2003) Robust dominant color region detection and color-based applications for sports video, IEEE international conference on image processing (ICIP), pp I21–I24Google Scholar
- 8.Ekin A, Murat Tekalp A, Mehrota R (2003) Automatic soccer video analysis and summarization. IEEE Trans Image Process 12:796–807CrossRefGoogle Scholar
- 9.Fan J, Gao Y, Luo H (2004) Multi-level annotation of natural scenes using dominant image components and semantic concepts, ACM Multimedia (ACM MM 2004) pp 540–547Google Scholar
- 10.Herrero-Jaraba E, Orrite-Uru\(\tilde{n}\)uela C, Senar J (2003) Detected motion classification with a double-background and a neighbourhood-based difference, pattern recognition letters 24:2079–2092Google Scholar
- 11.Jiang S, Ye Q, Gao W, Huang T (2004) A new method to segment playfield and its applications in match analysis in sports videos, ACM MM, 292–295Google Scholar
- 12.Jodoin P, Konrad J, Saligrama V, Veilleux-Gaboury V (2008) Motion detection with an unstable camera. In: Proceedings of IEEE Signal International Conference on Image Processing, pp 229–232Google Scholar
- 13.Langmann B, Ghobadi SE, Hartmann K, Loffeld O (2010) Multi-modal background subtraction using gaussian mixture models, in ISPRS technical commission III symposium on photogrammetry computer vision and image analysis (PCV 2010), pp 61–66Google Scholar
- 14.Lanza A, Tombari F, Di Stefano L (2010) Robust and efficient background subtraction by quadratic polynomial fitting, IEEE international conference on image processing (ICIP), pp 1537–1540Google Scholar
- 15.Liu C, Yuen PC, Qiu G (2008) Generating novel information salient maps for foreground object detection in video, in congress on image and signal processing (IEEE), pp 196–200Google Scholar
- 16.M. Mentzelopoulos, A Psarrou (2004) Key-frame extraction algorithm using entropy difference. In: Proceedings of the 6th ACM international workshop on multimedia information retrieval (MIR 04), 39–45 2004Google Scholar
- 17.Okuma K, Little J, Lowe D (2003) Automatic acquisition of motion trajectories: tracking hockey players. SPIE Proc 5304:202–213CrossRefGoogle Scholar
- 18.Piccardi M (2004) Background subtraction techniques: a review. In: Proceedings of the IEEE international 286 conference on systems, man and cybernetics 4, pp 3099–3104Google Scholar
- 19.Pers J, Kristan M, Perse M and Kovacic S (2008) Analysis of player motion in sport matches, computer science in sport: mission and methodsGoogle Scholar
- 20.Rissanen J (1999) Hypothesis selection and testing by the mdl principle. Comput J 42(4):260–269MathSciNetMATHCrossRefGoogle Scholar
- 21.Smith J (1999) Image classification and querying using composite region templates. Comput Vis Image Underst 75:165–174CrossRefGoogle Scholar
- 22.Tong X, Liu Q, Duan L, Lu H, Xu C, Tian Q (2005) A unified framework for semantic shot representation of sports video, ACM multimedia information retrieval MIR, pp 127–134Google Scholar
- 23.Yan F, Christmas W, Kittle J (2005) A tennis ball tracking algorithm for automatic annotation of tennis match, BMVC 2, pp. 619–628Google Scholar