In this paper, we present a novel method for generating sports video summary highlights. Specifically, our method localizes semantically important events in sport programs by detecting slow motion replays of these events, and then generates highlights of these events at multiple levels. In our method, a hidden Markov model (HMM) is used to model slow motion replays, and an inference algorithm is introduced which computes the probability of a slow motion replay segment, and localizes the boundaries of the segment as well. An effective new feature is used in our HMM, based on a moving measure of the number of zero-crossings and the amplitudes of variations over time of video field differences. Furthermore, the method is capable of filtering out slow motion play segments in commercials. As compared with existing methods for video event detection, our method is more generic (i.e., domain independent), and has the ability to capture inherently important events. 1. INTRODUCTION With the de...

In this paper, we describe a statistical method to detect highlights in a baseball game video. The input video is first segmented into scene shots, within which the camera motion is continuous. Our approach is based on the observations that 1) most highlights in baseball games are composed of certain types of scene shots and 2) those scene shots exhibit special transition context in time. To exploit those two observations, we first build statistical models for each type of scene shots with products of histograms, and then for each type of highlight a hidden Markov model is learned to represent the context of transition in time domain. A probabilistic model can be obtained by combining the two, which is used for highlight detection and classification. Satisfactory results have been achieved on initial experimental results.

We propose a multi-level video event detection methodology and apply it to animal hunt detection in wildlife documentaries. The proposed multi-level approach has three levels. The first level extracts color, texture, and motion features, and detects moving object blobs. The mid-level employs a neural network to verify whether the moving object blobs belong to animals. This level also generates shot descriptors that combine features from the first level and contain results of mid-level, domain specific inferences made on the basis of shot features. The shot descriptors are then used by the domain-specific inference process at the third level to detect the video segments that contain hunts. The proposed approach can be applied to different domains by adapting the mid and high-level inference processes. Event based video indexing, summarization and browsing are among the applications of the proposed approach. Keywords Video content analysis; content-based indexing and retrieval; browsin...

We propose a three-level video event detection algorithm and apply it to animal hunt detection in wildlife documentaries. The \Thetarst level extracts texture, color, and motion features, and detects motion blobs. The mid-level employs a neural network to verify whether the motion blobs belong to objects of interest. This level also generates shot summaries in terms of intermediate-level descriptors which combine low-level features from the \Thetarst level and contain results of mid-level, domain speci\Thetac inferences made on the basis of shot features. The shot summaries are then used by a domain-speci\Thetac inference process at the third level to detect the video segments that contain events of interest, e.g., hunts. Event based video indexing, summarization and browsing are among the applications of the proposed approach. 1. Introduction Existing content-based video indexing and retrieval methods may be classi\Thetaed into the following three categories: (1) syntactic structuri...

This paper aims to extract baseball game highlights based on audio-motion integrated cues. In order to better describe different audio and motion characteristics in baseball game highlights, we propose a novel representation method based on likelihood models. The proposed likelihood models measure the “likeliness ” of low-level audio features and motion features to a set of predefined audio types and motion categories, respectively. Our experiments show that using the proposed likelihood representation is more robust than using low-level audio/motion features to extract the highlight. With the proposed likelihood models, we then construct an integrated feature representation by symmetrically fusing the audio and motion likelihood models. Finally, we employ Hidden Markov Model (HMM) to model and detect the transition of the integrated representation for highlight segments. A series of experiments have been conducted on a 12-hour video database to demonstrate the effectiveness of our proposed method and show that the proposed framework achieves promising results over a variety of baseball game sequences.

This paper will first briefly survey the existing impact of MIR in applications. It will then analyze the current trends of MIR research which can have an influence on future applications. It will then detail the future possibilities and bottlenecks in applying the MIR research results in the main target application areas, such as consumer (e.g. personal video recorders, web information retrieval), public safety (e.g. automated smart surveillance systems) and professional world (e.g. automated meeting capture and summarization). In particular, recommendations will be made to the research community regarding the challenges that need to be met to make the knowledge transfer towards the applications more efficient and effective. It will also attempt to study the trends in the applications which can inform the MIR community on directing intellectual resources towards MIR problems which can have a maximal real-world impact.

To my family and friends ii This thesis investigates semantic analysis of broadcast sports footage. A domain depen-dent sports video model is proposed. Under this model, the game semantics can be derived according to their relationship with the sequence of dynamic events that occur in the sport and the evolution of the spatio-temporal behaviour of a relevant object. Snooker and tennis are targeted as typical broadcast sports footage for the purpose of this research. The prob-lem focus is to automatically extract semantically meaningful events and to convey a useful representation to the user. Access to semantics provides a more natural tool for a user to query a corpus of data than by low-level content based features alone. These semantics are however open to various interpretations by different viewers. Therefore, in order to create a successful semantic based retrieval system it is necessary to consider the user-context. Unconstrained sports footage is generally very complicated in structure, so restricting the domain being addressed enables

This thesis investigates two different, yet related aspects of video indexing: temporal seg-mentation and content classification. Temporal segmentation, often performed by detecting transitions between shots, is required in the early stages of video indexing. This is because a shot can be effectively considered as the smallest indexing unit and higher level concepts are often constructed by combining and analyzing the inter and intra-shot relationships. Automatic video classification, on the other hand, enables efficient cataloging and retrieval with large video collections. We have proposed algorithms for detecting transitions between shots. Hard cuts are detected by recording the peaks in the frame difference curve using an adaptive threshold computed from a local window. Fades and dissolves are detected by inspecting the characteristics of the production models in terms of frame luminance mean and variance. In order to guard against noise and motion which would cause similar effects, constraints derived from the production models are applied. When comparing against two other tools for detecting shot transitions, our algorithms show much better performance. For video classification, we aim at solving the task of automatic identification of video genres,

In this paper, we propose a novel global motion estimation technique based on weighted gradient and Displaced Frame Difference (DFD) associated with Wiener estimation. Then, we apply this technique to parse events of a high level of understanding in a cricket game. A user oriented analysis of the game then reveals a distinct connection between the global motion and specific events. By estimating global motion and analysing the temporal evolution of the estimated motion parameters, we present an effective process for the extraction of cricket events, leading to a succes rate of 88.9%.

Copyright 2001 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. DETECTION OF SLOW-MOTION REPLAY SEGMENTS IN