Tarik Veli Mumcu

Real object recognition using moment invariants

Moments and functions of moments have been extensively employed as invariant global features of images in pattern recognition. In this study, a flexible recognition system that can compute the good features for high classification of 3-D real objects is investigated. For object recognition, regardless of orientation, size and position, feature vectors are computed with the help of nonlinear moment invariant functions. Representations of objects using two-dimensional images that are taken from different angles of view are the main features leading us to our objective. After efficient feature extraction, the main focus of this study, the recognition performance of classifiers in conjunction with moment-based feature sets, is introduced

Unmanned Aerial Vehicle-Aided Wireless Sensor Network Deployment System for Post-disaster Monitoring

This paper presents design strategies of using unmanned aerial vehicles (UAVs) to deploy wireless sensor networks (WSNs) for post-disaster monitoring. Natural disasters are unforeseeable events which cannot be prevented. But some recovery procedures can be followed to minimize their effects. Post-disaster monitoring is important to estimate the effects of disasters, which in turn is used to determine recovery procedures to be followed. We propose an UAV-aided unattended WSN deployment system. The system is a post-disaster solution which can be used anywhere required. In this study, we mainly evaluate the efficiency of localization and navigation performance of the proposed system. Our simulation studies with an AirRobot quadrotor helicopter in Unified System for Automation and Robot Simulation (USARSim) simulation platform show that UAVs can be used to deploy WSNs after disasters to monitor environmental conditions. Future work includes implementing the system using a hexarotor helicopter.

Design strategies of unmanned aerial vehicle-aided communication for disaster recovery

This paper presents a novel approach of using unmanned aerial vehicles (UA Vs) to establish a communication infrastructure in case of disasters. Due to the collapse of buildings, power systems, and antennas, the collapse of communication infrastructure is the usual effect of disasters. In this study, we propose an emergency communications system established by unmanned aerial vehicles (UA Vs). The system is a post-disaster solution; hence, it can be used anywhere required. In this study, first we briefly explain the details of the system in three aspects: end-to-end communication, localization and navigation, and coordination Then, we evaluate the efficiency of the localization and navigation subsystem. Our simulation studies with Air Robot quadrotor helicopters in Unified System for Automation and Robot Simulation (USARSim) simulation environment show that UAV-aided communications system can be used in case of disasters to establish an emergency communications infrastructure in terms of localization and navigation.

A novel feed-forward controller for PMSMs

In this study, the current tracking problem of PMSM is handled as static feed-forward controller design for Linear Parameter Varying (LPV) system. H infinity controller formulated by means of Linear Matrix inequalities (LMI) with bounded and measurable system parameters is used. Parameter-dependent Lyapunov function is preferred to achieve robust stability against inconstant parameters, throughout the control process. The LPV controller is used in two degrees of freedom (2-DOF), by jointly adding static LPV feed-forward controller on a PI feedback controller. Space vector pulse width modulation (SVPWM) is used to generate switching signals. Overall system is simulated by Matlab/Simulink Software to evaluate the validity of the method in transient and steady state response by computer simulation. Simulation results reveal that proposed method has good dynamic performance and robustness.

Static LPV feedforward controller synthesis for Linear Parameter Varying systems

This paper proposes a new static feedforward controller synthesis for Linear Parameter Varying (LPV) systems. In this approach, the matrices of system are dependent on measurable parameters which have bounded variations. The proposed controller design is based on H infinity controller design and is formulated in terms of Linear Matrix Inequalities (LMIs). Parameter-dependent Lyapunov function is used for the synthesis where the robust stability is guaranteed for all varying parameters during the control. This controller is used by combining on the feedback controller in two degrees of freedom (2-DOF) control system structure. It is assumed that the feedback controller in the generalized system was previously designed in the structure. Afterwards the feedforward controller is designed by imposing on the feedback controller. The controller design can be used for decreasing the reference tracking error or the disturbance attenuation. A numerical example is given to provide the applicability of the controller for decreasing the reference tracking error.

A Performance Analysis of Omnidirectional Vision Based Simultaneous Localization and Mapping

This paper presents a performance analysis of omnidirectional vision based Simultaneous Localization and Mapping (SLAM). In omnidirectional vision based SLAM; robots perform vision based SLAM using only monocular omnidirectional cameras. In this paper, we mainly investigate the use of an omnidirectional camera for Extended Kalman Filter (EKF) based SLAM. To evaluate the success of omnidirectional vision based SLAM, we have also conducted the same simulations using a laser range finder (LRF). Main contributions of this paper are the use of an omnidirectional camera to perform SLAM in the Unified System for Automation and Robot Simulation (USARSim) environment, which is controlled by MATLAB in our study. The results of USARSim simulations show that depending on the environmental conditions omnidirectional cameras can be used as an alternative to other range bearing sensors and stereo cameras.

Exploration strategy related design considerations of WSN-Aided mobile robot exploration teams

This paper presents a novel approach to mobile robot exploration. In this approach, mobile robots send their local maps to the central controller and coordinate with each other using a wireless sensor network (WSN). Different from existing rendezvous point-based exploration strategies, the use of a WSN as the communication media allows quick and cost-effective exploration and mapping of an unknown environment. Overall, this paper introduces WSN-aided mobile robot exploration strategy and shows comparative performance evaluations using the Player/Stage simulation platform. Here, our main goal is to present potential advantages of WSN-aided mobile robot exploration for Simultaneous Localization and Mapping (SLAM).

Autonomous intruder detection system using wireless networked mobile robots

Wireless networked mobile robots pursuing a common objective are envisioned to be an efficient solution for many military, industrial, commercial, and environmental applications. This paper presents the design considerations of an autonomous intruder detection system based on wireless networked robots. Specifically, three critical aspects of these systems, such as coordination and task allocation, communication, and map-based intruder detection, have been investigated and a multi-sensor fusion mechanism has been presented. Performance results show that the fusion of redundant information from different sensors can increase the accuracy of a system and reduce overall uncertainty in intruder detection applications.

WSN aided indoor localization for unmanned vehicles

This paper presents design considerations of an Extended Kalman Filter (EKF) based Wireless Sensor Network (WSN) aided indoor localization for unmanned vehicles (UV). In this approach, we integrate Received Signal Strength Indicator (RSSI) measurements into an EKF based localization system. The localization system primarily uses measurements from a Laser Range Finder (LRF) and keeps track of the current position of the UV using an EKF-based algorithm. The integration of RSSI measurements at predetermined intervals improves the accuracy of the localization system. It may also prevent large drifts from the ground truth, kidnapping, and loop closure errors. Player/Stage based simulation studies were conducted to prove the effectiveness of the proposed system. The results of the comparative simulations show that integrating RSSI measurements into the localization system improves the systems accuracy.

Histogram based color object classification by multi-class support vector machine

This work presents a histogram based color object classification by SVM for laboratory automation. In the laboratory environment, existing problem is the classification of color objects which is understood as blob like pictures by the system via a camera. This automated system is located at hospitals, blood banks where we introduce the system different blood samples for different research purposes. The blood samples for different research purposes are realized with different colors of tube caps. These caps constitute the main problem here since their images are often blob like pictures. The segmented, multi color cap pictures are investigated in this paper by SVM for color object classification. To validate the performance of the system with SVM method, its output also compared to the other classification methods. In the future work different color spaces will be incorporated with SVM for better color classification.