Ana-Maria Sevcenco

Telerehabilitation Using Low-Cost Video Game Controllers

In recent years, advances in motion detection, tracking, and classification have made applications in telerehabilition possible. Monitoring of the elderlies and physically impaired, sports medicine, and physical therapy, are some of the active research areas in telerehabilition. Furthermore, the gaming industry has provided some low-cost devices to track motion with reasonable accuracy, thus, making telerehabilition a reality for patients who need it. This project investigates the feasibility of using the Nintindo Wii Remote Controller as a handheld device that patients can use to perform repetitive motions in physical therapy sessions in a telerehabilitation setting. Patients can use such an instructional (or e-learning) system at home without the cost, effort, and time associated with visiting a medical office. At the same time, the public health care system also benefits from the deployment of these telerehabilitation systems.

Real-Time Classification of Sports Movement Using Adaptive Clustering

Computer-based instructional systems provide an ideal setting for learning certain types of sports. In particular, the sports that require premium space could leverage the widely available computing and Internet facilities to teach individual users anywhere and anytime. An e-learning tennis instruction system is currently being designed and developed. The Nintendo Wii Remote is selected as the input device for its low cost and racket-handle like shape. After the data from motion sensors are captured, they have to be cleansed, normalised clustered and classified. Data of three common swings, backhand, forehand, and overhand, have been recorded from fifty people of various levels of tennis skill. Experiments are carried out to identify the most suitable techniques to classify a tennis swing. The adaptive nature of a prototype system is also introduced.

Perfect histogram matching PCA for face recognition

We present an enhanced principal component analysis (PCA) algorithm for improving rate of face recognition. The proposed pre-processing method, termed as perfect histogram matching, modifies the image histogram to match a Gaussian shaped tonal distribution in the face images such that spatially the entire set of face images presents similar facial gray-level intensities while the face content in the frequency domain remains mostly unaltered. Computationally inexpensive, the perfect histogram matching algorithm proves to yield superior results when applied as a pre-processing module prior to the conventional PCA algorithm for face recognition. Experimental results are presented to demonstrate effectiveness of the technique.

Adaptive Down-Scaling Techniques for JPEG-Based Low Bit-Rate Image Coding

The DCT-based JPEG standard remains to be the most popular compression utility for digital images despite the emerging wavelet-based JPEG-2000 standard. A commonly recognized weak point of the DCT-based transform coding is its blocking effects which become increasingly visible when the bit-rate requirement goes deeper into the low bit-rate territory. There has been a great deal of research endeavors to deal with this problem. Motivated by a recent work of Bruchstein, Elad, and Kimmel (BEK), in this paper we propose two adaptive techniques that can be applied to a BEK type of transform coding system for further performance improvement at a cost of moderate increase in complexity. Here the adaptation is based on the input images local features and statistics, and goes in two ways: either adaptive in terms of the rate of the down-sampling or in terms of the quality factor of each image block. Simulation results are presented to demonstrate the effectiveness of the proposed techniques

Impact of Sensor Sensitivity in Assistive Environment

Advances in motion detection, tracking, and classification have made available many applications in telerehabilition. Monitoring of the elderlies and physically impaired, sports medicine, and physical therapy, are some of the active research areas in telerehabilition. In order to gain acceptance by the general public, a telerehabilition system should have high accuracy in tracking movements and be low in cost. This work investigates the suitability of Leap Motion, a computer input device, for telerehabilition purpose. Its accuracy and tracking reliability are compared to that of Nintendos Wii Remote Controller (Wiimote) that was studies in our prior work. Wiimote can be used as a handheld device for patients to perform repetitive motions in physical therapy sessions in an autonomous remote setting. The Leap Motion, on the other hand, seems to fit physiotherapy sessions that require free motion without any props. Patients can use such an instructional system at home without the effort and time incurred with visiting a medical office. At the same time, the public health care system also benefits from such devices due to reduced cost and broader delivery of programs.

Motion Tracking and Learning in Telerehabilitation Applications

In recent years, advances in motion detection, tracking, and classification have made applications in telerehabiliation possible. Monitoring of the elder lies and physically impaired, sports medicine, and physical therapy, are some of the active research areas in telerehabiliation. Furthermore, the gaming industry has provided some low-cost devices to track motion with reasonable accuracy, thus, making telerehabiliation a reality for most people. This work introduces, presents, and discusses the progress in motion tracking and their application in telerehabiliation.

Design of Optimal Decimation and Interpolation Filters for Low Bit-Rate Image Coding

The DCT-based JPEG standard is certainly one of the most successful applications of transform coding methods for still digital images. A commonly recognized disadvantage of the DCT-based transform coding is its blocking artifacts which become increasingly visible when the bit-rate gets lower. In the past, considerable research endeavors had been made to deal with this problem. Motivated by a recent work of Tsaig, Elad, Milanfar, and Golub (TEMG), in this paper we investigate several techniques for the design of optimal decimation and interpolation filters that can be utilized in a TEMG type system framework for further performance improvement, where the DCT-based JPEG standard is used in conjunction with a decimation filter and an interpolation filter. Simulation results are presented to demonstrate the effectiveness of the proposed techniques

Collection and Classification of Tennis Swings Using a Virtual Racket

Computerized learning systems are popular these days due to the advances in artificial intelligence and decision support. Learning sports using a computer is a new field of research but it requires additional effort in the areas of motion sensing and modeling, and data mining. We are designing a tennis e-learning system using the Nintendo Wii remote as a virtual racket for practicing swings. This work introduces the swing motion data collection process. Classification of the swing data is explored using various techniques such as principal component analysis and K-means clustering. It is evident from the graphical data that different types of tennis swings have dissimilar characteristics in the 3-D space. The distinct envelope shape of the swings can be characterized and differentiated using descriptive statistics. Classification results are presented with emphasis on the swing consistency of tennis learners as well as the similarity of the swing motions which are important in the eventual learning process.

Combined Adaptive and Averaging Strategies for JPEG-Based Low Bit-Rate Image Coding

A commonly recognized weak point of the DCT-based transform coding is its blocking effects which become increasingly visible in the low bit-rate territory. In the first part of this paper, motivated by a recent work of Bruckstein, Elad, and Kimmel (BEK) [1] and by the progress from [3], we propose a combined adaptive technique that can be applied to a BEK type of transform coding system for performance improvement. In the second part of the paper, motivated by a recent work of Tsaig, Elad, Milanfar, and Golub (TEMG) [2], we investigate an averaging technique for the design of optimal interpolation filter that can be utilized in a TEMG type system framework for further performance improvement. Simulation results are presented to demonstrate the effectiveness of the two proposed methods.

A Feasibility Study on Using Low-Cost Gaming Devices for Rehabilitation

Telerehabilitation has become a reality with the advances of communication and sensing technologies. The past decade has seen much research work done in rehabilitation using sophisticated devices and complex computations. A recent research trend has emerged with the proliferation of gaming devices and sensors. This work investigates rehabilitation of wrist and arm using the affordable Nintendo Wii Remote controller with an USB-equipped personal computer. Other gaming devices such as Microsofts Kinect are discussed. The impact of positional displacement of the controller is examined. The sensitive of the controller with respect to prescribed motions is studied. Extensive experiments performed with various controllers, motions, and people are discussed. Conclusions are drawn on the suitability of using the Wii Remote controller in rehabilitation.