The International Journal of Multimedia & Its Applications (IJMA) Vol.3, No.1, February 2011 DOI : 10.5121/ijma.2011.3110 111           Mahesh Goyani 1 , Shreyash Dutta 2 , Gunvatsinh Gohil 3 and Sapan Naik 4 1 Department of Computer Engineering, Sardar Patel University, Anand, India mgoyani@gmail.com 2 Student Member, IEEE, IEEE CS shreyashdutta@gmail.com 3 Department of Computer Engineering, Gujarat University, Gandhinagar, India gunvantsinh@gmail.com 4 GEC, Gujarat Technological University, Gandhinagar, India sapan_say@yahoo.co.in ABSTRACT In this paper, we propose an algorithm to detect semantic concepts from cricket video. In our previous work, we have proposed key frame detection based approach for semantic event detection and classification. The proposed scheme works in two parts. In first part a top-down event detection and classification is performed using hierarchical tree. In second part, higher level concept is identified by applying A-Priori algorithm. In part 1, key frames are identified based on Hue Histogram difference at level 1. At level 2, logo transitions classify the frames as real-time or replay. At level 3, we classify the real time frames as field view, pitch view or non field view based on thresholds like Dominant Soli Pixel Ration (DSPR) and Dominant Grass Pixel Ration (DGPR). At level 4, we detect close up and crowd frames based upon edge detection. At level 5a, we classify the close up frames into player of team A, player of team B and umpire based upon skin colour and corresponding jersey colour. At level 5b, we classify the crowd frames into spectators, player’s gathering of team A or player’s gathering of team B. In part two, labels are associated with each frame event, which is used as input to A-Priori algorithm for concept mining. Results at the end of paper show the robustness of our approach. KEYWORDS Histogram, Dominant Grass Pixel Ratio, Dominant Soil Pixel Ratio, Concept Mining, A-Priori Algorithm 1. INTRODUCTION Video is the collection of continuous frames, displayed at some specific rate (normally 25 fps). Compared to image, video occupies much more space. And most of the time, much of the portion of Sport videos, security videos is not of one’s interest. The quantity of data produced by recording sports videos need filtration and summarization. Due to long duration of the video, it is quite cumbersome process to index some particular event of the video. One has to go through each frame to find out some specific event from it. In recent years sports video analysis has become a widely research area of digital video processing because of its huge viewership and commercial importance [1], [2]. Because of the enormous difference in sports videos, sport specific methods show successful results and thus constitute the majority of work. Some of the genre specific researches have been done in soccer (football) [3], [4] tennis [5], cricket [6], basketball [7], volleyball [8], etc. less work is observed for genre-independent studies [8], [9]. In viewership and fan following cricket is next to soccer. Major cricket playing nations are India, Australia, Pakistan, South Africa, Zimbabwe, Bangladesh, Sri Lanka, New Zealand, and England. In spite of its huge viewership cricket has not obtained its share in the research community [6], [10]. Cricket video analysis is far more challenging because of the complexities