Ali Ömer Baykar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ali Ömer Baykar has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Ayhan Kural
Istanbul Technical University
2 shared publications - Jens Lambrecht
Technische Universität Berlin
2 shared publications Maide Elif Ozisik
Mercedes Benz Trk A..,Istanbul,Turkey
1 shared publicationMehmet Mucahit Kaya
Siemens Kartal RD Center,Istanbul,Turkey
1 shared publicationSelim Yannier
FEV Turkey,Istanbul,Turkey
1 shared publication- Tuba Çonka Yıldız
European XFEL, Holzkoppel 4, 22869 Schenefeld, Germany
1 shared publication
Latest Publications
- 24 December 2024
- Published by Springer Nature
- p. 41-49
Neuronal Networks for Visual Inspection of Assembly Completeness and Correctness in Manufacturing
- 24 December 2024
- Published by Springer Nature
- p. 41-49
Neuronal Networks for Visual Inspection of Assembly Completeness and Correctness in Manufacturing
- 23 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Evaluation of Feature Detection and Extraction Methods for Landmark Separability in Visual Localization
In this study, the utilization of feature detector methods in landmark-based visual localization research has been evaluated. In contrast to comparative studies of existing feature detection methods, their performance has been assessed in detecting and discerning similarities among environments at distinct locations that pose challenges for perception. Additionally, variables such as varying lighting conditions, camera exposure time, and sensor light sensitivity (ISO value), as well as focus range, have been incorporated into the evaluation. BRISK, Fast, Harris, MinEigen, MSER, ORB, SIFT, SURF feature detector, and descriptor methods have been considered in this assessment. BRISK and MinEigen, notably, have demonstrated superior performance in detecting objects that could serve as landmarks in extremely unambiguous environments compared to other methods. Furthermore, it has been observed that in situations with excessive measurements in camera exposure time, more features can be detected. Additionally, an increase in image sensor light sensitivity has led to a reduction in the number of detected features across all methods. Another noteworthy finding is the dramatic decrease in matched features observed in images captured under varying lighting conditions and the same positions.
- 23 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Evaluation of Feature Detection and Extraction Methods for Landmark Separability in Visual Localization
In this study, the utilization of feature detector methods in landmark-based visual localization research has been evaluated. In contrast to comparative studies of existing feature detection methods, their performance has been assessed in detecting and discerning similarities among environments at distinct locations that pose challenges for perception. Additionally, variables such as varying lighting conditions, camera exposure time, and sensor light sensitivity (ISO value), as well as focus range, have been incorporated into the evaluation. BRISK, Fast, Harris, MinEigen, MSER, ORB, SIFT, SURF feature detector, and descriptor methods have been considered in this assessment. BRISK and MinEigen, notably, have demonstrated superior performance in detecting objects that could serve as landmarks in extremely unambiguous environments compared to other methods. Furthermore, it has been observed that in situations with excessive measurements in camera exposure time, more features can be detected. Additionally, an increase in image sensor light sensitivity has led to a reduction in the number of detected features across all methods. Another noteworthy finding is the dramatic decrease in matched features observed in images captured under varying lighting conditions and the same positions.
- 20 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 8693, 587-590
Deep Learning based Vehicle-to-Vehicle See Through System with Auto-Start Function
Today, with the increasing human population, the need for transportation is also increasing. These increasing transportation needs bring along some problems such as traffic density and traffic accidents. It is known that many of these accidents are caused by incorrect overtaking on single-lane roads and highways. In this research study, a solution proposal for such wrongful overtaking situations is discussed. The most important of these situations is that the vehicle to be overtaken is obstructing the view. In this study, by establishing a WLAN-based communication system between vehicles, it is discussed to eliminate the related loss of vision by image transfer between each vehicles. Unlike existing systems, this image transfer process is equipped with an automatic trigger with artificial intelligence. When overtaking is required, it is determined by means of deep networks whether vision loss occurs or not. As a main essence of this work, If vision loss is detected, the image transfer process between vehicles starts automatically and informs the driver. As a result of the real-time tests, it has been observed that it works successfully within the processing time required for the system to process 20 fps image data at a distance of 100 meters.
- 20 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 8693, 587-590
Deep Learning based Vehicle-to-Vehicle See Through System with Auto-Start Function
Today, with the increasing human population, the need for transportation is also increasing. These increasing transportation needs bring along some problems such as traffic density and traffic accidents. It is known that many of these accidents are caused by incorrect overtaking on single-lane roads and highways. In this research study, a solution proposal for such wrongful overtaking situations is discussed. The most important of these situations is that the vehicle to be overtaken is obstructing the view. In this study, by establishing a WLAN-based communication system between vehicles, it is discussed to eliminate the related loss of vision by image transfer between each vehicles. Unlike existing systems, this image transfer process is equipped with an automatic trigger with artificial intelligence. When overtaking is required, it is determined by means of deep networks whether vision loss occurs or not. As a main essence of this work, If vision loss is detected, the image transfer process between vehicles starts automatically and informs the driver. As a result of the real-time tests, it has been observed that it works successfully within the processing time required for the system to process 20 fps image data at a distance of 100 meters.