Yazar "Yildiz, Tuba Conka" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ X ]
    Öğe
    Deep Learning based Vehicle-To-Vehicle See Through System with Auto-Start Function
    (Institute of Electrical and Electronics Engineers Inc., 2022) Kaya, Mehmet Mucahit; Ozisik, Maide Elif; Baykar, Ali Omer; Yannier, Selim; Yildiz, Tuba Conka
    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. © 2022 IEEE.
  • [ X ]
    Öğe
    Driver fatigue detection with image processing
    (IEEE, 2020) Duman, Mehmet; Erdogdu, Elifnaz; Cogen, Fatih; Yildiz, Tuba Conka
    In recent studies, drowsiness of drivers while driving is seen as one of the most important causes of deaths due to traffic accidents. Therefore, in this study, an algorithm that determines driver fatigue by examining the driver's eye conditions in real-time is proposed. Python versions of OpenCV (Open Source Computer Vision Library) and machine learning libraries were used to create this proposed algorithm. In the study, the face and eyes were detected with the Cascade classifier using Haar features. Detected eyes were classified as open closed or half open with the model trained by the SVM (Support Vector Machine) method according to the HOG (Histogram of Oriented Gradient) feature descriptor. Driver fatigue was decided according to the PERCLOS (Percentage of Eyelid Closure) method, which examines the percentage of eyelid closure over time. In the proposed system, fatigue was detected according to the time the driver's eyes were in the half-open or closed state, and a related user interface was designed and audio and visual warnings were given to the driver.