Iztok Kramberger

DSP acceleration using a reconfigurable FPGA

Programmable logic offers an alternative solution for the computationally-intensive functions found in digital signal processing (DSP). Programmable logic can provide increased DSP system performance at reduced system cost. Programmable logic combines the flexibility of a general purpose DSP plus the speed, density, and low cost of an ASIC implementation. In some applications, programmable logic replaces the DSP processor entirely. In others, programmable logic works in conjunction with the DSP processor, offloading the computationally-intensive function and freeing the processor for other functions. This paper describes an alternative to traditional, general-purpose DSP processors. Programmable logic can implement functions beyond the capabilities of todays DSP processors. Field programmable gate arrays (FPGAs) or complex programmable logic devices (CPLDs) potentially provide performance increases of an order of magnitude over traditional DSPs with the same flexibility.

Mobile device for electronic eye gesture recognition

Based on the fact that there are many challenging cases of infirm persons, who are able to control only their eye muscles, a low-cost mobile device for electronic eye gesture recognition has been designed as a human-machine interface, which enables the control of different applications and home appliances by users eye gestures by the IR and Bluetooth wireless technology. In this paper the embedded system design of the device is presented in detail, including hardware and software design, modes of operation, and used methods for the eye gesture recognition. Beside these, measurements of the used differential amplifier and the achieved eye gesture recognition efficiency are presented within the test results. Furthermore, a newly designed adjustable head mounted EOG acquisition device with the permanent surface electrodes is proposed.

Door phone embedded system for voice based user identification and verification platform

This paper describes the architecture of a door phone embedded system with interactive voice response. Because speech technology is not 100% reliable, the emphasis was on parts that have greater impact on overall performance (audio capture, speech recognition and verification, and power consumption). Using an embedded microphone array increases speech recognition effectiveness in very noisy environments. To increase the speech recognition performance, a null grammar with confidence measure support was used. The speaker verification module was also optimized for nosy environments (using the cepstral mean normalization technique and a universal background model).

A Wearable Device and System for Movement and Biometric Data Acquisition for Sports Applications

This paper presents a miniature wearable device and a system for detecting and recording the movement and biometric information of a user during sport activities. The wearable device is designed to be worn on a wrist and can monitor skin temperature and pulse rate. Furthermore, it can monitor arm movement and detect gestures using inertial measurement unit. The device can be used for various professional and amateur sport applications and for health monitoring. Because of its small size and minimum weight, it is especially appropriate for swing-based sports like tennis or golf, where any additional weight on the arms would most likely disturb the player and have some influence on the player’s performance. Basic signal processing is performed directly on the wearable device but for more complex signal analysis, the data can be uploaded via the Internet to a cloud service, where it can be processed by a dedicated application. The device is powered by a lightweight miniature LiPo battery and has about 6 h of autonomy at maximum performance.

Real-time skin feature identification in a time-sequential video stream

Skin color can be an important feature when tracking skin-colored objects. Particularly this is the case for computer-vision-based human-computer interfaces (HCI). Humans have a highly developed feeling of space and, therefore, it is reasonable to support this within intelligent HCI, where the importance of augmented reality can be foreseen. Joining human-like interaction techniques within multimodal HCI could, or will, gain a feature for modern mobile telecommunication devices. On the other hand, real-time processing plays an important role in achieving more natural and physically intuitive ways of human-machine interaction. The main scope of this work is the development of a stereoscopic computer-vision hardware-accelerated framework for real-time skin feature identification in the sense of a single-pass image segmentation process. The hardware-accelerated preprocessing stage is presented with the purpose of color and spatial filtering, where the skin color model within the hue-saturation-value (HSV) color space is given with a polyhedron of threshold values representing the basis of the filter model. An adaptive filter management unit is suggested to achieve better segmentation results. This enables the adoption of filter parameters to the current scene conditions in an adaptive way. Implementation of the suggested hardware structure is given at the level of filed programmable system level integrated circuit (FPSLIC) devices using an embedded microcontroller as their main feature. A stereoscopic clue is achieved using a time-sequential video stream, but this shows no difference for real-time processing requirements in terms of hardware complexity. The experimental results for the hardware-accelerated preprocessing stage are given by efficiency estimation of the presented hardware structure using a simple motion-detection algorithm based on a binary function.

The design of mobile multimodal communication device - personal navigator

The personal navigator presents a multimodal communication device. To its user it enables visual, tactile and voice communication. Visual and tactile communication between the user and the navigator runs over a graphical LCD display with touch-panel, which in that way serves as an input and output device. Through GSM data communication the personal navigator is connected to a navigation server, which runs on a personal computer and is also a constituent part of the whole personal navigator system. The personal navigator has built-in support for a digital signal processor by which the automatic speech synthesis and recognition are performed. The momentary scheme of the personal navigator enables a wide palette of applications like tourist guide functions (informing the user about his position, presenting tourist sites and guiding), information functions (giving daily news, Internet browser) and communication device (notebook SMS messages, E-mail).

Multi Channel EOG Signal Recognition for an Embedded Eye Movement Tracking Device

In this paper we describe a low cost embedded system for eye movement tracking that supports disabled persons with basic interaction with Bluetooth enabled electronic devices. The method is based on tracking the EOG potential. The device has a built-in 32-bit RISC processor that performs acquisition of multichannel differential EOG signals and signal recognition. Signal recognition is based on cross correlation principle where a simplified triangulated linear model for eye movement is used as a reference signal. The eye movement recognition is more or less user independent, but it takes some time and practice to become familiar with the system for efficient use. The embedded eye movement tracking device communicates with other devices via personal network, which is based on Bluetooth wireless technology. The communication protocol at the application level has been simplified in order to gain plain integration with other devices.

Tennis stroke detection and classification using miniature wearable IMU device

This paper presents work related to tennis stroke detection and classification. For arm movement acquisition a miniature wearable IMU device, positioned on the players forearm (right above the wrist) is proposed and presented. The device uses a MEMS-based accelerometer and gyroscope with 6-DOF. For reliable and accurate tennis stroke detection the information obtained from the accelerometer data is used, and for tennis stroke classification, information from gyroscope data is extracted and processed. The proposed system is able to detect and classify three most common tennis strokes: forehand, backhand, and serve. Because of limited memory and lack of processing power, the proposed algorithms for stroke detection and classification are quite simple, but are nonetheless capable of achieving high classification rate. Overall 98.1% tennis stroke classification accuracy was achieved.

Pulse rate variability and blood oxidation content identification using miniature wearable wrist device

This paper presents the work related to the identification of PRV (pulse rate variability) and SpO2 (blood oxidation content) using miniature wearable wrist device. The extension of currently widely used PPT (photo plethysmography) measuring technique is proposed. Most PPT devices only measure PR (pulse rate), but with minimum adaptations to the sensor, a wider range of parameters can be measured. Two of such parameters are PRV and SpO2. This set of parameters gives a better insight into ones physical and mental state than only PR parameter. In order to develop a device that does not obstruct the user in any way, we propose a miniature non-invasive wearable device, and algorithms that do not need any significant processing power in order to identify the biometric parameters. The device is a lightweight battery powered embedded system, that measures and analyses biometric data for later analysis in correlation with ones activity.

Reflectance Measurement System for Skin Color Modeling in Chromaticity Color Space

Experimental skin reflectance measurement setup is presented to acquire skin color signals under different illuminant conditions directly by an image sensor. To obtain stimulus of varying illuminant conditions an adjustable RGB light source is used. Skin color modeling is an important step for efficient skin color image segmentation, which plays an important role when defining regions of interest in image sequence for a successful hand tracking and gesture recognition within spatially defined vision based interaction. To improve detection accuracy of pixel based skin color segmentation a parametric skin color model can be used, which is able to adapt different illuminant conditions. Therefore skin reflectance under different illuminants plays an important role to obtain such a model. Experimental results of hand skin reflectance measurements within chromaticity space are shown.