Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7148

Browse

Filters

2017 - 201912020 - 20242

Settings

COAR Access Rights: search.filters.coarAccessRights.metadata only accessSubject: search.filters.subject.Computer Vision

Search Results

Now showing 1 - 3 of 3
  • Conference Object
    Citation - Scopus: 1
    Open-Source Visual Target-Tracking System Both on Simulation Environment and Real Unmanned Aerial Vehicles
    (Springer Science and Business Media Deutschland GmbH, 2024) Yılmaz,C.; Ozgun,A.; Erol,B.A.; Gumus,A.
    This work presents an investigation into the domain of dynamic target tracking through object detection, particularly emphasizing the context of open-source applications like PX4, ROS, and YOLO. Over the years, achieving real-time object tracking on UAVs in dynamic environments has been a formidable challenge, necessitating offline computations or substantial onboard processing resources. However, contemporary UAVs are now equipped with advanced edge embedded devices, sensors, and cameras, enabling the integration of deep learning-based vision applications. This advancement offers the prospect of directly deploying cutting-edge applications onto UAVs, thereby expanding their utility in areas such as surveillance, search and rescue, and videography. To fully harness the potential of these vision applications, a communication infrastructure interfacing with the UAV’s underneath closed controllers becomes imperative. We’ve developed an integrated visual target-tracking system that connects a flight controller unit with a graphical unit by leveraging ROS tools and open-source deep learning packages. The overall integrated system based on ROS, deep learning applications, and custom PID controllers is shared on GitHub as open-source software package in a way that benefits everyone interested: https://github.com/miralab-ai/vision-ROS. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
  • Article
    Citation - WoS: 1
    Citation - Scopus: 1
    Real-Time Superficial Vein Imaging System for Observing Abnormalities on Vascular Structures
    (Springer, 2024) Altay, A.; Gumus, A.
    Circulatory system abnormalities might be an indicator of diseases or tissue damage. Early detection of vascular abnormalities might have an important role during treatment and also raise the patient’s awareness. Current detection methods for vascular imaging are high-cost, invasive, and mostly radiation-based. In this study, a low-cost and portable microcomputer-based tool has been developed as a Near-Infrared (NIR) superficial vascular imaging device. The device uses NIR Light-Emitting Diode (LED) light at 850 nm along with other electronic and optical components. It operates as a non-contact and safe infrared (IR) imaging method in real-time. Image and video analysis are carried out using OpenCV (Open-Source Computer Vision), a library of programming functions mainly used in computer vision. Various tests were carried out to optimize the imaging system and set up a suitable external environment. To test the performance of the device, the images taken from three diabetic volunteers, who are expected to have abnormalities in the vascular structure due to the possibility of deformation caused by high glucose levels in the blood, were compared with the images taken from two non-diabetic volunteers. As a result, tortuosity was observed successfully in the superficial vascular structures, where the results need to be interpreted by the medical experts in the field to understand the underlying reasons. Although this study is an engineering study and does not have an intention to diagnose any diseases, the developed system here might assist healthcare personnel in early diagnosis and treatment follow-up for vascular structures and may enable further opportunities. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.
  • Conference Object
    Robust Keypoint Matching for Three Dimensional Scenes and Object Recognition
    (IEEE, 2017) Koksal, Ali; Uzyildirim, Furkan Eren; Ozuysal, Mustafa
    In this paper, we adapt a recently proposed keypoint matching approach for binary descriptors and planar objects to three dimensional objects. We also evaluate the performance of this approach for a museum object recognition application containing more than one hundred paintings. Moreover, we quantify the effect of selecting only descriptors with high matching ratio on the success rate of the object recognition application.