The power of play-break for automatic detection and browsing of self-consumable sport video highlights

To enable content-based retrieval, highlights extraction from broadcasted sport video has been an active research topic in the last decade. There is a well-known theory that high-level semantic, such as goal in soccer can be detected based on the occurrences of specific audio and visual features that can be extracted automatically. However, there is yet a definitive solution for the scope (i.e. start and end) of the detection for self consumable highlights. Thus, in this paper we will primarily demonstrate the benefits of using play-break for this purpose. Moreover, we also propose a browsing scheme that is based on integrated play-break and highlights (extended from [1]). To validate our approach, we will present the results from some experiments and a user study.

Automatic detection of lung nodule from computer tomography images

Lung nodule refers to lung tissue abnormalities that may become cancerous. An automated system that detects nodules of common sizes within lung images is developed. It consists of acquisition, pre-processing, background removal, nodule detection, and false positives reduction. The system can assist expert radiologists in their decision making.

K-Complex Detection Using a Hybrid-Synergic Machine Learning Method

Sleep stage identification is the first step in modern sleep disorder diagnostics process. K-complex is an indicator for the sleep stage 2. However, due to the ambiguity of the translation of the medical standards into a computer-based procedure, reliability of automated K-complex detection from the EEG wave is still far from expectation. More specifically, there are some significant barriers to the research of automatic K-complex detection. First, there is no adequate description of K-complex that makes it difficult to develop automatic detection algorithm. Second, human experts only provided the label for whether a whole EEG segment contains K-complex or not, rather than individual labels for each subsegment. These barriers render most pattern recognition algorithms inapplicable in detecting K-complex. In this paper, we attempt to address these two challenges, by designing a new feature extraction method that can transform visual features of the EEG wave with any length into mathematical representation and proposing a hybrid-synergic machine learning method to build a K-complex classifier. The tenfold cross-validation results indicate that both the accuracy and the precision of this proposed model are at least as good as a human expert in K-complex detection.

Seasonality of blue and fin whale calls and the influence of sea ice in the Western Antarctic Peninsula

The calling seasonality of blue (Balaenoptera musculus) and fin (B. physalus) whales was assessed using acoustic data recorded on seven autonomous acoustic recording packages (ARPs) deployed from March 2001 to February 2003 in the Western Antarctic Peninsula. Automatic detection and acoustic power analysis methods were used for determining presence and absence of whale calls. Blue whale calls were detected year round, on average 177 days per year, with peak calling in March and April, and a secondary peak in October and November. Lowest calling rates occurred between June and September, and in December. Fin whale calling rates were seasonal with calls detected between February and June (on average 51 days/year), and peak calling in May. Sea ice formed a month later and retreated a month earlier in 2001 than in 2002 over all recording sites. During the entire deployment period, detected calls of both species of whales showed negative correlation with sea ice concentrations at all sites, suggesting an absence of blue and fin whales in areas covered with sea ice. A conservative density estimate of calling whales from the acoustic data yields 0.43 calling blue whales per 1000 n mi² and 1.30 calling fin whales per 1000 n mi², which is about one-third higher than the density of blue whales and approximately equal to the density of fin whales estimated from the visual surveys.

Towards detecting patterns of human behaviour from image sequences

This paper details research that will explore the analysis of human behaviour via video surveillance. Digital computer images will be obtained from video footage of a real world scene, and positions of people in the scene will be identified and tracked through each frame in the sequence.

The noted positions will build into a pattern of motion that can be examined and classified. It is proposed that specific events, such as panic or fight situations, will have unique, and therefore identifying, characteristics that will enable automatic detection of such events.

It is envisaged that active cameras will be used when a situation of interest occurs, to enable more information to be extracted from the scene (e.g., panning to follow action, or zooming to enhance detail.)

Detecting indexical signs in film audio for scene interpretation

In this paper, we study the sound tracks in films and their indexical semiotic usage by developing a classification system that detects complex sound scenes and their constituent sound events in cinema. We investigate two main issues in this paper: Determination of what constitutes the presence of a high level sound scene and inferences about the thematic content of the scene that can be drawn from this presence, and classification of environmental sounds in the audio track of the scene, to assist in the automatic detection of the high level scene. Experiments with our classification system on pure sounds resulted in a correct event classification rate of 88.9%. When the audio content of a number of film scenes was examined, though a lower accuracy resulted with sound event detection due to the presence of mixed sounds, the film audio samples were generally classified with the correct high-level sound scene label, enabling correct inferences about the story content of the scenes.

Machine vision system for automatic inspection of surface defects in aluminum die casting

A camera based machine vision system for the automatic inspection of surface defects in aluminum die casting is presented. The system uses a hybrid image processing algorithm based on mathematic morphology to detect defects with different sizes and shapes. The defect inspection algorithm consists of two parts. One is a parameter learning algorithm, in which a genetic algorithm is used to extract optimal structuring element parameters, and segmentation and noise removal thresholds. The second part is a defect detection algorithm, in which the parameters obtained by a genetic algorithm are used for morphological operations. The machine vision system has been applied in an industrial setting to detect two types of casting defects: parts mix-up and any defects on the surface of castings. The system performs with a 99% or higher accuracy for both part mix-up and defect detection and is currently used in industry as part of normal production.

Machine vision system for automatic inspection of surface defects in aluminium die casting

A machine vision system is presented for the automatic inspection of surface defects in aluminium die casting. The system uses a hybrid image processing algorithm based on mathematic morphology to detect defects with different sizes and shapes. The defect inspection algorithm consists of two parts. One is a parameter learning algorithm, in which a genetic algorithm is used to extract optimal structuring element parameters, and segmentation and noise removal thresholds. The second part is a defect detection algorithm, in which the parameters obtained by a genetic algorithm are used for morphological operations. The machine vision system has been applied in an industrial setting to detect two types of casting defects: parts mix-up and any defects on the surface of castings. The system performs with a 99% or higher accuracy for both part mix-up and defect detection and is currently used in industry as part of normal production.

Early detection of depression and associated risk factors in adults with mild/moderate intellectual disability

The aim of this study was to determine the presentation and risk factors for depression in adults with mild/moderate intellectual disability (ID). A sample of 151 adults (83 males and 68 females) participated in a semi-structured interview. According to results on the Beck Depression Inventory II, 39.1% of participants evinced symptoms of depression (2 severe, 14 moderate, and 43 mild). Sadness, self-criticism, loss of energy, crying, and tiredness appeared to be the most frequent indicators of depression or risk for depression. A significant difference was found between individuals with and without symptoms of depression on levels of automatic negative thoughts, downward social comparison and self-esteem. Automatic negative thoughts, quality and frequency of social support, self-esteem, and disruptive life events significantly predicted depression scores in people with mild/moderate ID, accounting for 58.1% of the variance.

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.

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.

Detection and classification of road signs in natural environments

An automatic road sign recognition system first locates road signs within images captured by an imaging sensor on-board of a vehicle, and then identifies the detected road signs. This paper presents an automatic neural-network-based road sign recognition system. First, a study of the existing road sign recognition research is presented. In this study, the issues associated with automatic road sign recognition are described, the existing methods developed to tackle the road sign recognition problem are reviewed, and a comparison of the features of these methods is given. Second, the developed road sign recognition system is described. The system is capable of analysing live colour road scene images, detecting multiple road signs within each image, and classifying the type of road signs detected. The system consists of two modules: detection and classification. The detection module segments the input image in the hue-saturation-intensity colour space, and then detects road signs using a Multi-layer Perceptron neural-network. The classification module determines the type of detected road signs using a series of one to one architectural Multi-layer Perceptron neural networks. Two sets of classifiers are trained using the Resillient-Backpropagation and Scaled-Conjugate-Gradient algorithms. The two modules of the system are evaluated individually first. Then the system is tested as a whole. The experimental results demonstrate that the system is capable of achieving an average recognition hit-rate of 95.96% using the scaled-conjugate-gradient trained classifiers.