Automatic Classification of Tennis Video for High-Level Content-Based Retrieval
نویسندگان
چکیده
This paper presen,ts our techniques and results on automatic analysis of t ennis video t o facilitate contentbased retrieval. Our approach is based o n th,e generat ion of a n imuge nlwdel f o r the tennis court-lines. W e derive this model b?j rrsiny the knouile&e about dirriensions arid connectivity ( fo rm) of a tennis court and typical cam era g eo ni e t ry 11s ed uili e n cup t w i n g a i ! e n nis video. We ~ r s e this model to devclop (1:) (I court, line detection algoribiim and ( i i ) a. r.obust player-tracking algorithm to track Me tennis players over the amagcs sequence. W e also present a color-based algorithm to select tennis court claps from a n i n p t raw footo,ge of t ennis video. Automatically extracted tennis court lines and the players' location in format ion are analyzed in a high-level reasoning module o,nd related t o useful high-level tennis play events. Results o n real tennis video data u7.e presented demonstrating tlie validity and perfol-murice of the approach.
منابع مشابه
Semiautomatic Image Retrieval Using the High Level Semantic Labels
Content-based image retrieval and text-based image retrieval are two fundamental approaches in the field of image retrieval. The challenges related to each of these approaches, guide the researchers to use combining approaches and semi-automatic retrieval using the user interaction in the retrieval cycle. Hence, in this paper, an image retrieval system is introduced that provided two kind of qu...
متن کاملCobra: A Content-Based Video Retrieval System
An increasing number of large publicly available video libraries results in a demand for techniques that can manipulate the video data based on content. In this paper, we present a content-based video retrieval system called Cobra. The system supports automatic extraction and retrieval of high-level concepts (such as video objects and events) from raw video data. It benefits from using domain k...
متن کاملAutomatic annotation of tennis games: An integration of audio, vision, and learning
a r t i c l e i n f o Fully automatic annotation of tennis game using broadcast video is a task with a great potential but with enormous challenges. In this paper we describe our approach to this task, which integrates computer vision, machine listening, and machine learning. At the low level processing, we improve upon our previously proposed state-of-the-art tennis ball tracking algorithm and...
متن کاملAutomatic Sports Video Analysis using Audio Clues and Context Knowledge
Sports analysis has recently become popular in research and professional applications. This paper presents a scheme for automatic sports video analysis based on audio clues and specific game context knowledge. We propose a simple, two-step racket-hit detection for achieving accurate event classification for tennis video. To implement the mapping between the sample-level feature space and the se...
متن کاملImage Retrieval and Classification Using Affine Invariant B-spline Representation and Neural Networks
* This work was funded by the National Program “YPER” by the General Secretariat of Research & Development of Greece entitled “Efficient Content-Based Image and Video Query and Retrieval in Multimedia Systems” ABSTRACT In this paper, a system for content-based image retrieval from video databases is introduced, using B-splines for affine invariant object representation. A small number of “keyfr...
متن کامل