Vision based target tracking using robust linear filtering

The use of perspective projection in tracking a target from a video stream involves nonlinear observations. The target dynamics, however, are modeled in Cartesian coordinates and result in a linear system. In this paper we provide a robust version of a linear Kalman filter and perform a measurement conversion technique on the nonlinear optical measurements. We show that our linear robust filter significantly outperforms the Extended Kalman Filter. Moreover, we prove that the state estimation error is bounded in a probabilistic sense.

Distance-driven fusion of gait and face for human identification in video

Gait and face are two important biometrics for human identification. Complementary properties of these two biometrics suggest fusion of them. The relationship between gait and face in the fusion is affected by the subject-to-camera distance. On the one hand, gait is a suitable biometric trait for human recognition at a distance. On the other hand, face recognition is more reliable when the subject is close to the camera. This paper proposes an adaptive fusion method called distance-driven fusion to combine gait and face for human identification in video. Rather than predefined fixed fusion rules, distance-driven fusion dynamically adjusts its rule according to the subject-to-camera distance in real time. Experimental results show that distance-driven fusion performs better than not only single biometric, but also the conventional
static fusion rules including MEAN, PRODUCT, MIN, and MAX.

Multi-level semantic analysis for sports video

There has been a huge increase in the utilization of video as one of the most preferred type of media due to its content richness for many significant applications including sports. To sustain an ongoing rapid growth of sports video, there is an emerging demand for a sophisticated content-based indexing system. Users recall video contents in a high-level abstraction while video is generally stored as an arbitrary sequence of audio-visual tracks. To bridge this gap, this paper will demonstrate the use of domain knowledge and characteristics to design the extraction of high-level concepts directly from audio-visual features. In particular, we propose a multi-level semantic analysis framework to optimize the sharing of domain characteristics.

A statistical-driven approach for automatic classification of events in AFL video highlights

Due to the repetitive and lengthy nature, automatic content-based summarization is essential to extract a more compact and interesting representation of sport video. State-of-the art approaches have confirmed that high-level semantic in sport video can be detected based on the occurrences of specific audio and visual features (also known as cinematic). However, most of them still rely heavily on manual investigation to construct the algorithms for highlight detection. Thus, the primary aim of this paper is to demonstrate how the statistics of cinematic features within play-break sequences can be used to less-subjectively construct highlight classification rules. To verify the effectiveness of our algorithms, we will present some experimental results using six AFL (Australian Football League) matches from different broadcasters. At this stage, we have successfully classified each play-break sequence into: goal, behind, mark, tackle, and non-highlight. These events are chosen since they are commonly used for broadcasted AFL highlights. The proposed algorithms have also been tested successfully with soccer video.

Extraction and classification of self-consumable sport video highlights using generic HMM

This paper aims to automatically extract and classify self-consumable sport video highlights. For this purpose, we will emphasize the benefits of using play-break sequences as the effective inputs for HMMbased classifier. HMM is used to model the stochastic pattern of high-level states during specific sport highlights which correspond to the sequence of generic audio-visual measurements extracted from raw video data. This paper uses soccer as the domain study, focusing on the extraction and classification of goal, shot and foul highlights. The experiment work which uses183 play-break sequences from 6 soccer matches will be presented to demonstrate the performance of our proposed scheme.

Towards universal and statistical-driven heuristics for automatic classification of sports video events

Researchers worldwide have been actively seeking for the most robust and powerful solutions to detect and classify key events (or highlights) in various sports domains. Most approaches have employed manual heuristics that model the typical pattern of audio-visual features within particular sport events To avoid manual observation and knowledge, machine-learning can be used as an alternative approach. To bridge the gaps between these two alternatives, an attempt is made to integrate statistics into heuristic models during highlight detection in our investigation. The models can be designed with a modest amount of domain-knowledge, making them less subjective and more robust for different sports. We have also successfully used a universal scope of detection and a standard set of features that can be applied for different sports that include soccer, basketball and Australian football. An experiment on a large dataset of sport videos, with a total of around 15 hours, has demonstrated the effectiveness and robustness of our
aIlgorithms.

Extensible detection and indexing of highlight events in broadcasted sports video

Content-based indexing is fundamental to support and sustain the ongoing growth of broadcasted sports video. The main challenge is to design extensible frameworks to detect and index highlight events. This paper presents: 1) A statistical-driven event detection approach that utilizes a minimum amount of manual knowledge and is based on a universal scope-of-detection and audio-visual features; 2) A semi-schema-based indexing that combines the benefits of schema-based modeling to ensure that the video indexes are valid at all time without manual checking, and schema-less modeling to allow several passes of instantiation in which additional elements can be declared. To demonstrate the performance of the events detection, a large dataset of sport videos with a total of around 15 hours including soccer, basketball and Australian football is used.

Using decision-tree to automatically construct learned-heuristics for events classification in sports video

Automatic events classification is an essential requirement for constructing an effective sports video summary. It has become a well-known theory that the high-level semantics in sport video can be “computationally interpreted” based on the occurrences of specific audio and visual features which can be extracted automatically. State-of-the-art solutions for features-based event classification have only relied on either manual-knowledge based heuristics or machine learning. To bridge the gaps, we have successfully combined the two approaches by using learning-based heuristics. The heuristics are constructed automatically using decision tree while manual supervision is only required to check the features and highlight contained in each training segment. Thus, fully automated construction of classification system for sports video events has been achieved. A comprehensive experiment on 10 hours video dataset, with five full-match soccer and five full-match basketball videos, has demonstrated the effectiveness/robustness of our algorithms.

Coastal marine habitat mapping using multi-beam acoustics, video data and a decision tree classifier on the temperate south-east Australian continental shelf

In this habitat mapping study, multi-beam acoustic data are integrated with extensive, precisely geo-referenced video validation data in a GIS environment to classify benthic substrates and biota at a 33km2 site in the near shore waters of Victoria, Australia. Using an automated decision-tree classification method, 5 representative biotic groups were identified in the Cape Nelson survey area using a combination of multi-beam bathymetry, backscatter and derivative products. Rigorous error assessment of derived, classified maps produced high overall accuracies (>85%) for all mapping products. In addition, a discrete multivariate analysis technique (kappa analysis) was used to assess classification accuracy. High-resolution (2.5m cell-size) representation of sea floor morphology and textural characteristics provided by multi-beam bathymetry and backscatter datasets, allowed the interpretation of benthic substrates of the Cape Nelson site and the communities of sessile organisms that populate them. Non-parametric multivariate statistical analysis (ANOSIM) revealed a significant difference in biotic composition between depth strata, and between substrate types. Incorporated with other descriptive measures, these results indicate that depth and substrate are important factors in the distributional ecology of the biotic communities at the Cape Nelson study site. BIOENV analysis indicates that derivatives of both multi-beam datasets (bathymetry and backscatter) are correlated with distribution and density of biotic communities. Results from this study provide new tools for research and management of the coastal zone.

History, memory, and the politics of programming : the video work of Richard Fung

Richard Fung, a Toronto-based video artist and cultural critic, was born in Trinidad in 1954, and attended school in Ireland before immigrating to Canada to study at the University of Toronto. Richard Fung has taught at the Ontario College of Art and Design, and has been a visiting professor in the Department of Media Study at the State University of New York in Buffalo. He is currently the coordinator of the Centre for Media and Culture in Education, Ontario Institute for Studies in Education, University of Toronto.