Ondrej Kainz

Approach to Hand Tracking and Gesture Recognition Based on Depth-Sensing Cameras and EMG Monitoring

In this paper, a new approach for hand tracking and gesture recognition based on the Leap Motion device and surface electromyography (SEMG) is presented. The system is about to process the depth image information and the electrical activity produced by skeletal muscles on forearm. The purpose of such combination is enhancement in the gesture recognition rate. As a first we analyse the conventional approaches toward hand tracking and gesture recognition and present the results of various researches. Successive topic gives brief overview of depth-sensing cameras with focus on Leap motion device where we test its accuracy of fingers recognition. The vision-SEMG-based system is to be potentially applicable to many areas of human computer interaction.

Extended Object Tracking and Stream Control Model Based on Predictive Evaluation Metric of Multiple-Angled Streams

Paper describes the design of extended model for tracking and locating object in multi-cameras environment with controlling the streams from multiple angles in real time. Proposed and experimentally implemented solution is attempting to deliver via streaming technology of the only specific shot from scene that has the best view on tracked object in real time. Measurement of the best shot for the tracking object is based on proposed evaluation metric, consisting of dimensional, locational and reliability parameters gathered from object tracking methods. For latency optimization and accuracy of evaluation the prediction of evaluation metric was outlined. Solution is experimentally tested in standard and mobile environment as well. Approach described in this paper is innovative regarding the content related video stream delivery.

Human face detection in still image using Multilayer perceptron solution based on Neuroph framework

Artificial neural networks (ANN) are one of the dominant learning techniques used in the field of artificial intelligence and have significant assets as their properties imitate the behavior of neurons in human brain. In this paper is presented the research focused on ANN, specifically Multilayer perceptron (MPL) with the aim of detection of human face in the still image. This system was implemented in the Java programming language and its utilizing the software framework called Neuroph, which is primary used precisely for neural networks. Evaluation part presents complex testing procedures and introduces possibilities to modify and set the individual parameters that enhance the overall detection process. Novelty of this research is in the use of ANN for several reasons, one of these being the utilizing of software framework, testing of the parameters and detailed description and evaluation on what influences the detection process. However the principal strength lies in the utilization of ANN for detection of faces rather than for a recognition. Utilization of Neuroph framework is an alternative to the systems that are focused on the detection of faces in still images and are commonly implemented in different programming languages.

Visual system for student attendance monitoring with non-standard situation detection

In this paper we propose a visual system for monitoring of student attendance in seminars and lectures. Basic idea is to estimate the number of people in the room using face detection algorithms and subsequently utilize face recognition algorithms to determine the actual identification of persons (students). Presented approach may be used for multiple purposes. Principal and primary purpose is to monitor attendance, which is possible thanks to university database. When implemented, system is expected to evaluate the attendance automatically or if necessary using collaborative authentication. Non-standard or anomaly detection is another feature that is to be provided by system, subject to tracking are hands, eyes and movement. Proposed solution is expected to improve and facilitate attendance monitoring of students at seminars and lectures. Further it may be used for anomaly prevention (e.g. cheating) and in specific cases for security or legal matters.

On the Extraction of Anthropometric Parameters by Visual and Non-visual Means

In this paper the system for collection of anthropometric data is presented, along with the novel techniques for extraction of such data. System is built on selected open-source platform having developed various plugins as a part of the project. Means for extraction follow two approaches: visual and non-visual. The first presumes the acquiring of data from static 2D image, the latter gets data through the direct measurement. Visual approach utilizes several principles following the image processing and related face recognition algorithms. Moreover known anthropometric relations are utilized to estimate other proportions. The output in the form of data of individual user may serve as for statistical comparison with other users. Further such data is to be used for correlation studies with several diseases and changes of overall health condition.

Kinect as a tool in estimation of selected human body dimensions

The aim of this paper the extraction of human body dimensions using the latest Microsoft Kinect device. Another focus is the analysis of various application of this device in specific branches of science and research and its application in estimation of dimensions. Brief analysis of the device itself is carried out as well. The principal output of this paper the software application that utilizes data from Microsoft Kinect sensor in order to estimate the height of human body as well as the length of its limbs. Further comparison between both generations of Kinect devices is carried out.

Booking solution for video conference planning

In this paper, the solution for interconnecting the videoconference systems into a single videoconference infrastructure is presented. Further its users will be able to make reservations through developed web application. The paper presents complex analysis of technologies related to videoconferencing. Several ways of implementation of the web application while connecting to a central system for videoconference management are outlined. Subsequently, following the proposal, a functional web solution that enables planning of bookings for registered users of the systems is developed and tested in the real environment.

Personal mobile meter for development of human body skeletal model

In this paper, the innovative approach to extraction of the real size of the human body is presented. The prototype device for such extraction process is designed, implemented and tested on larger sample of subjects. The principal goal is the proposal of a solution for creation of exact skeletal human body model. Model dimensions may be further used in numerous use-cases, such as 3D modelling, clothing industry or security. Both, hardware and software, is based on the open-source technologies. The core functionality is enabled by developed hardware module that carries out the measurements of the real scene dimensions. Extracted values may be stored on the device itself or send to another mobile device. The accuracy of the solution proved to be 100 percent in terms of measurement in centimeters.

Adaptive Web-Based System for Examination with Cheating Prevention Mechanism

In this paper, the adaptive web-based system for examination with cheating prevention mechanism is presented. The idea of system was created based on the need to provide impartial evaluation during testing of learners - statistics of cheating during exams from the last decade is rather alarming however not surprising. With the dawn of new technologies cheating is becoming much easier than it used to be, as a natural result certain anti-cheating mechanism has to be deployed. System itself is in nature web-based and thus enables easy and widespread access. Approaches that enable automatic monitoring of learner during an examination were following and enhancing those in previously created systems. As a communication technology over the internet or intranet was utilized WebRTC which enabled to incorporate together various live monitoring capabilities - video, audio, screen of computer. Another feature that is in the center of interest is adaptive selection of questions. This selection is automatically carried out by system and it is based on answers as provided by learner. Deployment in the real environment is expected to be used as a complement that is to enhance education quality and provide automatic impartial evaluation of learner.

System for EKG Monitoring

In this paper the system for the electrocardiogram (EKG) monitoring based on the of Arduino microcontroller is presented. Detailed description of the electrocardiogram itself serves as a ground for building the proposed hardware and software solution. The software implementation is in a form of both, Matlab environment, and own application. Final output enables retrieval of the actual data in real time and further and provide the rudimentary diagnosis. Utilization of such device is for self home diagnosis of arrhythmia.