Search

Copyright of Acta Infologica is the property of Acta Infologica and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this paper, a new hybrid stereovision-based distance-estimation approach is proposed for indoor mobile robot platforms. To calculate the distances between the robot and object, triangulation method is used first. However, this technique is insufficient for objects located on the left or right side of the robot or the case of the stereo camera pair fixed to the robot with an angle down to the floor. Therefore, a new approach is proposed by adding a look-up table and curve-fitting methods to the triangulation technique. In this approach, the stereo camera pair is located on the robot with an angle down to the floor. In the experimental studies, an average accuracy rate of 97.69% is obtained. The Manhattan and Euclidean distances of objects that are not in the same line as the robot are also calculated. Average accuracy rates of 98.24% for Manhattan and 98.03% for Euclidean distances are achieved. [ABSTRACT FROM AUTHOR]

In this study, the objects found in the environment are detected and classified in real time, the results obtained are presented. Hazelnut fruit is used in the experimental studies of the proposed method. The image belongs to hazelnut that is in a work environment is taken with the camera, it is processed by using image processing techniques. The size and area data of hazelnut on the image plane is calculated. By evaluating the obtained data, the hazelnut is divided into three classes as small (K1), medium (K2) and big (K3) in real time application. This process is performed using mean-based classification and K-means clustering methods. Detection and classification of cluster centers is provided by using the information database obtained from the data of hazelnut fruit. Hazelnut fruits found in the experimental environment are determined with 100% accuracy using image processing techniques. The classification of hazelnut fruits using the mean-based and K-means clustering methods has been compared. As a result of the comparison, it is observed that the two methods realized are similar ratio of 90% to 100%. [ABSTRACT FROM AUTHOR]

A web-based virtual and remote laboratory environment is developed, realized and proposed for real time control and monitoring of a mobile robot in an indoor environment. In this laboratory, a real time and continuous video stream of indoor laboratory environment is viewed by wireless IP camera mounted to the ceiling. The localization of the robot is also implemented using this IP camera. In this environment, a virtual target and virtual obstacles are located anywhere on the video image taken by the user. The robot is guaranteed to arrive at the virtual target avoiding virtual obstacles using the shortest path. The video stream of the robot's navigation is monitored through the web environment. The robot is controlled by a BeagleBoard-xM single board computer. The PC web server symmetrically communicates with the other web server on the BeagleBoard-xM, executing developed application software. Since genetic algorithms generate alternative solutions, it is utilized as a path planning algorithm. Parameters such as population size and maximum generation of genetic algorithms applied to get the shortest path for the robot are tuned via the web-based virtual laboratory environment. The robot is also controlled manually through the web environment. At the conclusion of the experiments, the results are monitored on the web-based virtual laboratory environment. A low-cost mobile robot virtual remote laboratory is designed and implemented for engineering education in this paper. Consequently, survey and some experimental works, of the usability and performance of the RRC-Lab (remote robot control-laboratory) system are confirmed by students. [ABSTRACT FROM AUTHOR]

In this study, nuts are determined using image processing techniques and classified by k‐means and k‐means++ methods in rapid time. Firstly, pixel area (PA) and square area (SA) features are extracted by an image processing technique. Then, the obtained data are classified by the k‐means and k‐means++ clustering methods. We present a new method called the pixel area and square area method (PASAM), which is realized by clustering feature selection of PA and SA values. Our proposed method is applied on numerous real RGB images of nuts for different cases. Experimental results show that k‐means++ clustering based on PASAM is more efficient than other techniques such as k‐means and k‐means++ clustering based on PA and SA. The nuts in the working environment are determined and classified with 100% accuracy by PASAM. Practical applications: The proposed research distinguishes small, medium and big nuts based on image processing and PASAM. This method is appropriate to use to separate all vegetables and fruits for which classification is important. [ABSTRACT FROM AUTHOR]