Real-time robust vision-based hand gesture recognition using stereo images

This paper presents a real-time and robust approach to recognize two types of gestures consisting of seven motional gestures and six finger spelling gestures. This approach utilizes stereo images captured by a stereo webcam to achieve robust recognition under realistic lighting conditions and in various backgrounds. It incorporates several existing computationally efficient techniques and introduces a rule-based approach to merge the information from a pair of stereo images leading to an improved hand detection compared to using single images. The results obtained indicate that high recognition rates under realistic conditions are obtained in real-time on PC platforms at the rate of 30 frames per second. It is shown that its outcome is comparable to two existing approaches while it is computationally more efficient than these approaches.     

Classification of nonstationary narrowband signals using segmented chirp features and hidden Gauss-Markov models

A method is provided for classifying finite-duration signals with narrow instantaneous bandwidth and dynamic instantaneous frequency (IF). In this method, events are partitioned into nonoverlapping segments, and each segment is modeled as a linear chirp, forming a piecewise-linear IF model. The start frequency, chirp rate, signal energy, and noise energy are estimated in each segment. The resulting sequences of frequency and rate features for each event are classified by evaluating their likelihood under the probability density function (PDF) corresponding to each narrowband class hypothesis. The class-conditional PDFs are approximated using continuous-state hidden Gauss-Markov models (HGMMs), whose parameters are estimated from labeled training data. Previous HGMM algorithms are extended by dynamically weighting the output covariance matrix by the ratio of the estimated signal and noise energies from each segment. This covariance weighting discounts spurious features from segments with low signal-to-noise ratio (SNR), making the algorithm more robust in the presence of dynamic noise levels and fading signals. The classification algorithm is applied in a simulated three-class cross-validation experiment, for which the algorithm exhibits percent correct classification greater than 97% as low as -7 dB SNR.     

Automatic Right Ventricular Ejection Fraction Computation from Equilibrium and First-Pass Scintigraphic Cardiac Images

Nakamura, E., Kehtarnavaz, N., Wendt, R. III, and Murphy, P., Automatic Right Ventricular Ejection Fraction Computation from Equilibrium and First-Pass Scintigraphic Cardiac Images,Digital Signal Processing6(1996), 233–239.This paper presents an automatic method for computing the right ventricular ejection fraction (RVEF) by using both equilibrium and first-pass scintigraphic cardiac images. The equilibrium images are used to extract the cardiac activity area. Together with the phase image derived from the right heart first-pass images, the cardiac area is then used to identify the subarea corresponding to the right ventricle. The RVEF is then computed from the regional counts in the end-diastolic and end-systolic frames. The average manually derived RVEFs agreed with the automatically determined RVEFs with anRvalue of 0.81. Using the average of the manually derived RVEFs as the “gold standard,” only one person processing manually had a lower mean squared error than the automatic program. These results suggest that automatic RVEF computation is potentially useful and hence clinical deployment is recommended.     

Skin lesion classification using oblique-incidence diffuse reflectance spectroscopic imaging

We discuss the use of a noninvasive in vivo optical technique, diffuse reflectance spectroscopic imaging with oblique incidence, to distinguish between benign and cancer-prone skin lesions. Various image features were examined to classify the images from lesions into benign and cancerous categories. Two groups of lesions were processed separately: Group 1 includes keratoses, warts versus carcinomas; and group 2 includes common nevi versus dysplastic nevi. A region search algorithm was developed to extract both one- and two-dimensional spectral information. A bootstrap-based Bayes classifier was used for classification. A computer-assisted tool was then devised to act as an electronic second opinion to the dermatologist. Our approach generated only one false-positive misclassification out of 23 cases collected for group 1 and two misclassifications out of 34 cases collected for group 2 under the worst estimation condition.     

Real-time computation of disparity for hand-pair gesture recognition using a stereo webcam

This paper presents an algorithm for the real-time computation of disparity using video stereo images captured by a stereo webcam. This algorithm is designed to provide both real-time throughput and robust disparity estimation for real-world applications where computation is limited to a pre-defined region-of-interest (ROI). More specifically, this algorithm is used as part of a hand-pair gesture recognition application where the disparity is computed for two ROI around a hand-pair identified by the segmentation component of the recognition application. The developed algorithm provides the required relative difference in disparity with background at high frame rates for the hand-pair gesture recognition application. The results obtained with an inexpensive commercial VGA stereo webcam show a robust disparity computation of 20?ms/frame enabling real-time hand-pair gesture recognition at 25?fps with >90% recognition rate for a maximum hand speed of 40?cm/s and for hand distances between 30 and 150?cm away from the camera.     

Fast adaptive termination mode selection for H.264 scalable video coding

Although scalable video coding can achieve coding efficiencies comparable with single layer video coding, its computational complexity is higher due to its additional inter-layer prediction process. This paper presents a fast adaptive termination algorithm for mode selection to increase its computation speed while attempting to maintain its coding efficiency. The developed algorithm consists of the following three main steps which are applied not only to the enhancement layer but also to the base layer: a prediction step based on neighboring macroblocks, a first round check step, and a second round check step or refinement if failure occurs during the first round check. Comparison results with the existing algorithms are provided. The results obtained on various video sequences show that the introduced algorithm achieves about one-third reduction in the computation speed while generating more or less the same video quality.

A fast feature-assisted adaptive early termination approach for multiple reference frames motion estimation in H.264

The multiple reference frames motion estimation approach used in H.264 is computationally intensive. This paper presents a fast or computationally efficient feature-assisted adaptive early termination approach in order to reduce the computational complexity while maintaining more or less the same video quality. The introduced feature-assisted approach consists of three parts: (1) reduction of the number of available reference frames using predicted motion activity, extracted texture information, and skip mode from neighboring macroblocks, (2) the most probable reference frame prediction based on neighboring macroblocks, and (3) an adaptive early termination threshold derived from a theoretical analysis of all zero block detection. Extensive experimental results are performed to demonstrate the computational gain of the introduced approach over the standard approach for the multiple reference frames motion estimation.