Shahed Shojaeipour

Vision-Based Mobile Robot Navigation Using Image Processing and Cell Decomposition

In this paper, we present a method to navigate a mobile robot using a webcam. This method determines the shortest path for the robot to transverse to its target location, while avoiding obstacles along the way. The environment is first captured as an image using a webcam. Image processing methods are then performed to identify the existence of obstacles within the environment. Using the Cell Decomposition method, locations with obstacles are identified and the corresponding cells are eliminated. From the remaining cells, the shortest path to the goal is identified. The program is written in MATLAB with the Image Processing toolbox. The proposed method does not make use of any other type of sensor other than the webcam.

Optimization of the Performance Face Recognition Using AdaBoost-Based

In this paper, using the results of classifier composition is one of the methods of increasing efficiency of face recognition systems that many researchers paid attention to it in recent years. However AdaBoost algorithm is as one of the efficient boosting algorithm that has been used as to decrease the dimensions of characteristic space extracted from face recognition systems, it hasn’t been used as classifier in face recognition systems. In this paper paid attention to how to use this algorithm in classifying face recognition systems. At first the methods evaluated of classifier composition. Then, the result is presented of several composition methods in comparison with singular classifying methods; therefore, database has correct recognition of 96.4% and improved the results of KNN method with PCA specification. AdaBoost method is used according to weak learning, as proposed classifier system with the aim of identification validate.

Efficient Genetic Algorithm for Flexible Job-Shop Scheduling Problem Using Minimise Makespan

The aim of this paper is to minimise the makespan. The flexible job-shop scheduling is very common in practice and parallel machine is used in job-shop environment as flexibility. These flexibilities could be used for increasing the throughput rate, avoiding the production stop, removing bottleneck problems and finally achieving competitive advantages in economical environments. In opposition to classic job-shop where there is one machine in each stage, in this problem production system consists of multistage which in each stage there are one or several parallel machines with different speeds. The flexible job-shop scheduling with parallel machines problem consists of two sub-problems for solving: assigning and sequencing sub-problem.

A Novel Method for Rural Road Construction Planning Using Quad-Tree Decomposition on the Satellite Image

Rural roads construction projects are expensive, this has led to difficulties in developing accurate construction plans and modeling the construction operation using a novel simulation system. In this field, the aim of this research is to create a knowledge driven rural road construction simulation system to assist satellite image in generating s and reliable road construction plans. Road construction operations of the resources have been identified, developed, classified and modeled through a comprehensive analysis of a Simulink road construction projects. For every road construction operation a GIS-based template for little models was defined and developed. The models abridge distance of the path on the roads construction between villages and automating the optimizing of works. Also, the models provide a roadmap for evaluating several shortest paths on road construction via Quad-tree decomposition of the satellite image. A simulation case study was modeled to identify applicability, usefulness and accuracy of the developed simulation system and results are presented in this paper. The study fulfilled that the system generated for fast marching.

Path Planning for Two-Link Navigation in an Unknown Environment Using Webcam

In this article, we used image processing by a webcam connected on top of the arm robot. The robot navigation is in an unknown environment. Then start point and target point were determined for the robot, so the robot needs to have a program for path planning using Voronoi diagrams to find the path. After the possible path for moving the robot was found, the route information obtained was sent to the arm robot. The arm robot moves in the workspace and any time new information was processed via the webcam. The program was written using MATLAB software which at controls the robot’s movement the unknown environment.

A Novel Method for Automated Tool Path Optimisation for CNC Machining Operations

In this article, a new method for rapid tool movement in CNC machines is presented. Firstly, a single digital camera, installed on the Z-axis, captures the image of the workpiece on the work table. Image processing techniques, implemented using MATLAB, are then used to convert the image into a binary black and white image. This allows the locations of protruding edge sections on the workpiece, which could impede tool movement, to be identified. Quadtree decomposition is then performed on the binary image, and possible paths from the tool current location to its target location are found. These paths are then analysed based on the tool diameter clearance and the distance to the goal, and the shortest path with sufficient tool clearance is selected. A Visual Basic program then converts the selected path into G-code commands that provides instructions to the CNC machine tool such that this path is followed. With this method, the workpiece fixture location would not have to be precise as the imaging system would be able to automatically identify the target location with respect to the tool current location, along with the optimal path to reach it.

Laser-Pointer Rangefinder between Mobile Robot and Obstacles via Webcam Based

In this paper, we present a method to measurement a distance using a laser-pointer. This method calculated the distance from obstacles for the robot to transverse to its target location, while avoiding obstacles along the way. The environment is first captured as an image using a webcam. Image processing are then calculate to identify the existence of obstacles within the environment. Using the laser-pointer, ditance locations with obstacles are identified which laser-pointer consist of the webcam and the laser-pointer. It measure the distace mobile robot to the obstacles is identified. The program is written in MATLAB with the Image processing toolbox.

Modeling of Hysteretic Damper in Three-Story Steel Frame Subjected to Earthquake Load

This paper presents the nonlinear time-history and response spectrum analysis for a three-story steel moment frame and a braced frame by hysteretic damper against earthquake load which analyzed by SAP2000 software. The mentioned frames were analyzed by Eigenvalue method for linear analysis and Ritz-vector method for nonlinear analysis. Simulation results were presented as a time-displacement graph based on dynamic analysis, the dynamic base shear force is also calculated.

Vision-Based Trajectory Generation for a Two-Link Robotic Arm Using Quadtree Decomposition and Curve Smoothing

In this article, the development of an autonomous robot trajectory generation system based on a single eye-in-hand webcam, where the workspace map is not known a priori, is described. The system makes use of image processing methods to identify locations of obstacles within the workspace and the Quadtree Decomposition algorithm to generate collision free paths. The shortest path is then automatically chosen as the path to be traversed by the robot end-effector. The method was implemented using MATLAB running on a PC and tested on a two-link SCARA robotic arm. The tests were successful and indicate that the method could be feasibly implemented on many practical applications.