Yazar "Eren, Haluk" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    Classification of Road Curves and Corresponding Driving Profile via Smartphone Trip Data
    (Ieee, 2017) Karaduman, Mucahit; Eren, Haluk
    Smart cities are the new settlement structures formed by new technologies that change human life. Among these technologies, intelligent automobiles have an important place, and many scientific studies on it have been realized. Especially Tesla, Apple, and Google have completed their prototypes of autonomous automobiles. One of the indispensable part of recent automotive technologies is Advanced Driver Assistance System (ADAS). This system has been developed to improve safety and comfort of driver while driving. In this study, we have tried to predict road geometry and driving profile by using sensor data acquired by driver smartphone on steering wheel for a certain trip. Driving profiles are identified as aggressive and safe. GPS, accelerometer and gyroscope sensors are employed in this study. Using smartphone sensor data, road portions are initially determined by the proposed algorithm. Then, road shapes are obtained by a Fuzzy Classifier, which are straight, right curved, and left curved. Afterwards, the acceleration data corresponding road shapes are considered to find acceleration type for the portion of that road. Transitions between straight and curved roads including vehicle speed are determined by Hidden Markov Model (HMM). Thus, speed preference of subject driver for corresponding road shapes are obtained in probabilistic manner. Validation results have shown that the error rate between ground truth and observation data for proposed approach is obtained as 11.81%. Consequently, driving profile have been estimated considering road shapes.
  • Küçük Resim Yok
    Öğe
    Deep Learning based Traffic Direction Sign Detection and Determining Driving Style
    (Ieee, 2017) Karaduman, Mucahit; Eren, Haluk
    Intelligent automobiles and advanced driver assistance systems (ADAS) are some of the major technological developments that affect human daily life. Today, many studies are being generated to develop state of the art transportation systems. The general objective in these studies is to cope with negative effects of traffic. In this work, our aim is to contribute to the development of ADAS by determining driver behavior and traffic direction sign detection. The data employed are acquired by smartphone sensors, which are accelerometer, gyroscope, GPS, and camera, while the subject car moves between two specific points. The proposed method consists of two simultaneously running algorithms. The first one determines driver maneuvers, and the second one is the deep learning based algorithm that detects traffic direction sign using Convolution Neural Network (CNN). Here, the results of these two simultaneously running algorithms are assessed, and driving type is determined. GPS data is used for synchronization. Consequently, it is determined whether riding style is safe or aggressive, involving in traffic direction sign detection.
  • Küçük Resim Yok
    Öğe
    Smart Driving in Smart City
    (Ieee, 2017) Karaduman, Mucahit; Eren, Haluk
    Smart cities have been drawing attention of researchers as seen in recent intensive studies. In associated with this fact, this situation is expected to continue in future works. In other side, smart vehicles are an indispensable part of smart cities. Scientists have been researching vehicles and transportation in order to reach safe and comfortable mobility. Among these vehicles, cars are the first ones that affect human life. In this study, smart cars and their drivers are elaborated in behavioral aspect. Existing works have been discussed to figure out futuristic driving behavior in smart city environment. In order to understand human thought system, additional studies have been given and recommendations have been provided. As seen in the researches conducted in recent years, researchers have been tried to interpret behavior of drivers by examining data taken by smart phones and vehicle OBD output. Evaluations are conducted by result of the specified methods. In recent decade, it has been observed that these behaviors are not only estimations; but also systems mounted on vehicles learn overall driving behavior. Hence, developed systems should work online while drivers on steering wheel. Consequently, this study will enlighten existing trends for different types of learning schemes. Future studies are expected to combine car, driver's biologic, psychological, and environmental data. Thus, in the near future, systems that understand the human thought will be developed.
  • Küçük Resim Yok
    Öğe
    UAV Traffic Patrolling via Road Detection and Tracking in Anonymous Aerial Video Frames
    (Springer, 2019) Karaduman, Mucahit; Cinar, Ahmet; Eren, Haluk
    Unmanned Aerial Vehicles (UAV) have gained great importance for patrolling, exploration, and surveillance. In this study, we have estimated a route UAV to follow, using aerial road images. In the experimental setup, for estimation, test, and validation stages, anonymous aerial road videos have been exploited, meaning a special image database was not produced for this simulation approach. In the proposed study, road portion is initially detected. Two methods are utilized to help road detection, which are k-Nearest Neighbor and Hough transformation. To form a decision loop, both results are matched. If they match each other, they are fused using spatial and spectral schemes for the comparison purpose. Once road area is detected, the road type classification is realized by Fuzzy approach. The resultant image is utilized to estimate route, over which the UAV have to fly towards that direction. In the simulation stage, an anonymous video stream previously captured by UAV is experimented to assess the performance of the underlying system for different roads. According to the implementation results, the proposed algorithm has succeeded in finding all the trial roads in the given aerial images, and the proportion of all the estimated road-portion to actual road pixels for all the images is averagely calculated as %95.40. Eventually, it is shown that UAV has followed the correct route, which is estimated by proposed approach, over the specified road using assigned video frames, and also performances of spatial and spectral fusion results are compared.