Vasyl Koval

Smart license plate recognition system based on image processing using neural network

We describe the smart vehicle screening system, which can be installed into a tollbooth for automated recognition of vehicle license plate information using a photograph of a vehicle. An automated system could then be implemented to control the payment of fees, parking areas, highways, bridges or tunnels, etc. There are considered an approach to identify vehicle through recognizing of it license plate using image fusion, neural networks and threshold techniques as well as some experimental results to recognize the license plate successfully

The Local Area Map Building for Mobile Robot Navigation Using Ultrasound and Infrared Sensors

This paper was devoted to improvement of existing and development of the new method for local area map building of mobile robot using sensor fusion techniques. The unstructured environment for navigation of mobile robots is the reason of such task. The offered method provides the local area map building using polar coordinate system and bases on the applications of artificial neural network for fusing of readings from ultrasonic and infrared sensors. Application of the proposed method allows to decrease computational complexity and to increase the accuracy of local area map.

Approach to Face Recognition Using Neural Networks

The paper describes the approach to automatic face recognition for access control application area using wavelet transform and neural networks ensemble. Wavelet transform implements the compression of the face images and thus accelerates the classifiers work, while neural networks ensemble with proposed decision rule provides low recognition error. Proposed ensembles decision rule carries out a high level of unknown peoples access rejection, which is the most significant requirement for the access control systems, and gives a good balance between known and unknown peoples recognition errors.

Mobile Ad Hoc wireless network for pre- and post-emergency situations in nuclear power plant

This paper describes the mobile Ad-Hoc (wireless) network (MANET) for emergency scenarios in nuclear power plant (NPP). Authors proposed the system with such properties as flexibility and a self-forming and self-healing network topology that dynamically adjusts to the moving configuration per each intermediate routing node. It is also proposed to integrate MANET and Bluetooth-like technologies to create an unmanned formation of autonomous quadcopters that provides both indoor and outdoor communications coverage inside and outside of the NPP.

The competitive sensor fusion algorithm for multi sensor systems

The influence of the measurement errors can be reduced using multi-sensor fusion technologies. Competitive algorithms are one of prospective class of sensor fusion (SF) algorithms, which are used in sensor fusion techniques during the processing of sensor measurements to achieve more accurate measurement results than measurement by a each single sensor.

Mobile robot navigation method for environment with dynamical obstacles

The analysis of global and local navigation methods for an autonomous mobile robot allowed to select the main lacks of existent methods of navigation. The improved local navigation method based on the use of potential fields for movement taking into account the gradient of direction to the goal is proposed. Also the round of blocking obstacles is foreseen in a method. That allows to the mobile robot to go out from local minimums (deadlocks) with the control of returning on the previous trajectory of movement. The imitation design and research of the proposed method is conducted on the real base of the mobile robot Amigo.

Predetermined movement of mobile robot using neural networks

We describe the experimental results of neural networks application for mobile robot control on predetermined trajectory of the road. Considered is the formation process of training sets for neural network, their structure and simulating features. Researches have showed robust mobile robot movement on different pans of the road

Infrared sensor data correction for local area map construction by a mobile robot

The construction of local area maps on the based on heterogeneous sensor readings is considered in this paper. The Infrared Sensor Data Correction method is presented for the construction of local area maps. This method displays lower calculation complexity and broader universality compared to existing methods and this is important for on-line robot activity. The simulation results showed the high accuracy of the method.

Criteria to estimate quality of methods selecting contour inflection points

Current study performs a comparison of the contour inflection point selection methods according to the following criteria: probability of the correct selection, probability of the incorrect selection and an error in the coordinate estimation based on the results of model tasks. Results of the interpolation and differential methods and the method based on wavelet analysis of the contour inflection point were analyzed and graphically illustrated. It is shown that for simple geometric shapes the interpolation method has low precision (it shifts the contour inflection points) while differential method has the best precision properties, however it selects redundant inflection points (it has a low noise resistance) and the method based on the wavelet analysis of the curvature function shows the best results under noisy conditions.

A wireless navigation system with no external positions

A wireless navigation system (WNS) is proposed that autonomously coordinates the motions of cooperating robots. The proposed WNS employs both Bluetooth technologies and wireless routing protocols that can discover routes around obstacles and other barriers to communications. A time-slotted, ad hoc on-demand distance vector routing (TAODV) protocol is designed to maintain secure, wireless communication links between cooperating robots that forms a wireless mobile ad hoc network (MANET). A practical application of the WNS is demonstrated as an example.