Automatic labeling of sports video using umpire gesture recognition

We present results on an extension to our approach for automatic sports video annotation. Sports video is augmented with accelerometer data from wrist bands worn by umpires in the game. We solve the problem of automatic segmentation and robust gesture classification using a hierarchical hidden Markov model in conjunction with a filler model. The hierarchical model allows us to consider gestures at different levels of abstraction and the filler model allows us to handle extraneous umpire movements. Results are presented for labeling video for a game of Cricket.

Hierarchical recognition of intentional human gestures for sports video annotation

We present a novel technique for the recognition of complex human gestures for video annotation using accelerometers and the hidden Markov model. Our extension to the standard hidden Markov model allows us to consider gestures at different levels of abstraction through a hierarchy of hidden states. Accelerometers in the form of wrist bands are attached to humans performing intentional gestures, such as umpires in sports. Video annotation is then performed by populating the video with time stamps indicating significant events, where a particular gesture occurs. The novelty of the technique lies in the development of a probabilistic hierarchical framework for complex gesture recognition and the use of accelerometers to extract gestures and significant events for video annotation.

Functional range of movement of the hand : declination angles to reachable space

 The measurement of the range of hand joint movement is an essential part of clinical practice and rehabilitation. Current methods use three finger joint declination angles of the metacarpophalangeal, proximal interphalangeal and distal interphalangeal joints. In this paper we propose an alternate form of measurement for the finger movement. Using the notion of reachable space instead of declination angles has significant advantages. Firstly, it provides a visual and quantifiable method that therapists, insurance companies and patients can easily use to understand the functional capabilities of the hand. Secondly, it eliminates the redundant declination angle constraints. Finally, reachable space, defined by a set of reachable fingertip positions, can be measured and constructed by using a modern camera such as Creative Senz3D or built-in hand gesture sensors such as the Leap Motion Controller. Use of cameras or optical-type sensors for this purpose have considerable benefits such as eliminating and minimal involvement of therapist errors, non-contact measurement in addition to valuable time saving for the clinician. A comparison between using declination angles and reachable space were made based on Hume's experiment on functional range of movement to prove the efficiency of this new approach.

Automatic age estimation based on facial aging patterns

While recognition of most facial variations, such as identity, expression, and gender, has been extensively studied, automatic age estimation has rarely been explored. In contrast to other facial variations, aging variation presents several unique characteristics which make age estimation a challenging task. This paper proposes an automatic age estimation method named AGES (AGing pattErn Subspace). The basic idea is to model the aging pattern, which is defined as the sequence of a particular individual's face images sorted in time order, by constructing a representative subspace. The proper aging pattern for a previously unseen face image is determined by the projection in the subspace that can reconstruct the face image with minimum reconstruction error, while the position of the face image in that aging pattern will then indicate its age. In the experiments, AGES and its variants are compared with the limited existing age estimation methods (WAS and AAS) and some well-established classification methods (kNN, BP, C4.5, and SVM). Moreover, a comparison with human perception ability on age is conducted. It is interesting to note that the performance of AGES is not only significantly better than that of all the other algorithms, but also comparable to that of the human observers.

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.

Integrating kinect and haptics for interactive STEM education in local and distributed environments

Skill shortage is a realistic social problem that Australia is currently facing, especially in the fields of Science, Technology, Engineering and Mathematics (STEM). Various approaches have been proposed to soften this issue. By now the most successful approach is to attract pre-university youth and university freshmen into those fields before they make a decision on future subjects by introducing them with interactive, modifiable and inspiring virtual environments, which incorporates most essential knowledge of STEM. We propose to design a comprehensive virtual reality platform with immersive interactions, pluggable components and flexible configurations. It also involves haptics, motion capture and gesture recognition, and could be deployed in both local and distributed environments. The platform utilizes off the shelf low cost haptics and motion capture products, however the fidelity can be maintained at a good level. The proposed platform has been implemented with different configurations and has been tested on a group of users. Preliminary test results show that the interactivity, flexibility and fidelity of the platform are highly appreciated by users. User surveys also indicate that the proposed platform could help pre-university students and university freshmen build an overview of various aspects of STEM education. Besides, users are also positive on the fact that the platform enabled them to identify the challenges for higher education in STEM by providing them opportunities to interactively modify system configurations and instantly experience the corresponding results both visually and haptically.

Acoustic features extraction for emotion recognition

In the last decade, the efforts of spoken language processing have achieved significant advances, however, the work with emotional recognition has not progressed so far, and can only achieve 50% to 60% in accuracy. This is because a majority of researchers in this field have focused on the synthesis of emotional speech rather than focusing on automating human emotion recognition. Many research groups have focused on how to improve the performance of the classifier they used for emotion recognition, and few work has been done on data pre-processing, such as the extraction and selection of a set of specifying acoustic features instead of using all the possible ones they had in hand. To work with well-selected acoustic features does not mean to delay the whole job, but this will save much time and resources by removing the irrelative information and reducing the high-dimension data calculation. In this paper, we developed an automatic feature selector based on a RF2TREE algorithm and the traditional C4.5 algorithm. RF2TREE applied here helped us to solve the problems that did not have enough data examples. The ensemble learning technique was applied to enlarge the original data set by building a bagged random forest to generate many virtual examples, and then the new data set was used to train a single decision tree, which selects the most efficient features to represent the speech signals for the emotion recognition. Finally, the output of the selector was a set of specifying acoustic features, produced by RF2TREE and a single decision tree.

Online context recognition in multisensor systems using Dynamic Time Warping

In this paper, we present our system for online context recognition of multimodal sequences acquired from multiple sensors. The system uses Dynamic Time Warping (DTW) to recognize multimodal sequences of different lengths, embedded in continuous data streams. We evaluate the performance of our system on two real world datasets: 1) accelerometer data acquired from performing two hand gestures and 2) NOKIA's benchmark dataset for context recognition. The results from both datasets demonstrate that the system can perform online context recognition efficiently and achieve high recognition accuracy.

Visual mouse : SIFT detection and PCA recognition

The paper presents the Visual Mouse (VM), a novel and simple system for interaction with displays via hand gestures. Our method includes detecting bare hands using the fast SIFT (Scale-Invariant Feature Transform) algorithm saving long training time of the Adaboost algorithm, tracking hands based on the CAMShift algorithm, recognizing hand gestures in cluttered background via Principle Components Analysis (PCA) without extracting clear-cut hand contour, and defining simple and robustly interpretable vocabularies of hand gestures, which are subsequently used to control a computer mouse. The system provides a fast and simple interaction experience without the need for more expensive hardware and software.

Glucose enhancement of recognition memory: differential effects on effortful processing but not aspects of 'remember-know' responses

The administration of a glucose drink has been shown to enhance cognitive performance with effect sizes comparable with those from pharmaceutical interventions in human trials. In the memory domain, it is currently debated whether glucose facilitation of performance is due to differential targeting of hippocampal memory or whether task effort is a more important determinant. Using a placebo-controlled, double-blind, crossover 2(Drink: glucose/placebo) × 2(Effort: ± secondary task) design, 20 healthy young adults' recognition memory performance was measured using the 'remember-know' procedure. Two high effort conditions (one for each drink) included secondary hand movements during word presentation. A 25 g glucose or 30 mg saccharine (placebo) drink was consumed 10 min prior to the task. The presence of a secondary task resulted in a global impairment of memory function. There were significant Drink × Effort interactions for overall memory accuracy but no differential effects for 'remember' or 'know' responses. These data suggest that, in some circumstances, task effort may be a more important determinant of the glucose facilitation of memory effect than hippocampal mediation. This article is part of a Special Issue entitled 'Cognitive Enhancers'.

Using data mining for digital ink recognition: dividing text and shapes in sketched diagrams

The low accuracy rates of textshape dividers for digital ink diagrams are hindering their use in real world applications. While recognition of handwriting is well advanced and there have been many recognition approaches proposed for hand drawn sketches, there has been less attention on the division of text and drawing ink. Feature based recognition is a common approach for textshape division. However, the choice of features and algorithms are critical to the success of the recognition. We propose the use of data mining techniques to build more accurate textshape dividers. A comparative study is used to systematically identify the algorithms best suited for the specific problem. We have generated dividers using data mining with diagrams from three domains and a comprehensive ink feature library. The extensive evaluation on diagrams from six different domains has shown that our resulting dividers, using LADTree and LogitBoost, are significantly more accurate than three existing dividers.

Learning feature trajectories using Gabor Filter Bank for human activity segmentation and recognition

We describe a novel method for human activity segmentation and interpretation in surveillance applications based on Gabor filter-bank features. A complex human activity is modeled as a sequence of elementary human actions like walking, running, jogging, boxing, hand-waving etc. Since human silhouette can be modeled by a set of rectangles, the elementary human actions can be modeled as a sequence of a set of rectangles with different orientations and scales. The activity segmentation is based on Gabor filter-bank features and normalized spectral clustering. The feature trajectories of an action category are learnt from training example videos using Dynamic Time Warping. The combined segmentation and the recognition processes are very efficient as both the algorithms share the same framework and Gabor features computed for the former can be used for the later. We have also proposed a simple shadow detection technique to extract good silhouette which is necessary for good accuracy of an action recognition technique. © 2008 IEEE.