Yazar "Galip, Feyza" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim
    Öğe
    A novel approach to obtain trajectories of targets from laser scanned datasets
    (Ieee, 2015) Galip, Feyza; Çaputcu, Mehmet; İnan, Rüveyda Hilal; Sharif, Haidar; Karabayır, Aykut; Kaplan, Sezin; Uyaver, Şahin
    Laser scanner has several bons when compared with video camera. It does not record real world videos except scanned points. As a result, processing of data becomes faster and easier. Over and above, it takes away the problem of private life conservation. This paper proposes a new and competent computer vision based approach for detecting and tracking targets (e.g., pedestrians and vehicles) from laser scanned datasets. Laser scanned data points from each scan have been deemed as a video frame. Blobs are extracted and then computer vision techniques (e.g., Kalman filter, Hungarian algorithms, and etc.) are applied to recognize and track the kind of targets. Scanned datasets, collected from two kinds of laser scanners, were used to conduct experiments. Full trajectories of pedestrians, vehicles, and noises were resulted in three dimensional spaces. Experimental results give evidence of the efficacy of our proposed framework.
  • [ X ]
    Öğe
    A simple approach to count and track underwater fishes from videos
    (Ieee, 2015) Sharif, Haidar; Galip, Feyza; Güler, Adil; Uyaver, Şahin
    Fishes are of great importance to the ecosystem. Behavior of fishes is interesting. Counting and tracking of fishes can provide good knowledge about the behavior of fishes. Counting and behavior quantifying of fishes within a turbulence or trawl environment are challenging tasks. The traditional methods are not only inefficient but also expensive. Thus counting and tracking under water fishes from videos are emerging topic for ichthyologists. This paper addresses a simple method to count and track underwater fishes from videos. It is a hybrid of background subtraction, Hungarian algorithm, and Kalman filter. It enables tracking of fishes whose number can vary over time. Theoretical runtime of the tracking algorithm is O(n(3)) with problem size n. Experimental results demonstrate its effectiveness.
  • Küçük Resim
    Öğe
    Recognition of objects from laser scanned data points using SVM
    (Ieee Computer Soc, 2016) Galip, Feyza; Sharif, Haidar; Çaputcu, Mehmet; Uyaver, Şahin
    Nowadays, laser scanners are operated for data collection instead of video cameras. Laser scanners do not record real world videos except scanned points. Thus it takes away problems of private life conservation. Plus data processing gets very fast and easy. But from laser scanned data points, recognition of objects is a challenging task. This paper points to the usability of SVM to recognize pedestrians and vehicles from laser scanned data points. Data points from each scan are esteemed as a video frame. Moving blobs are extracted and then SVM is used to recognize each blob as either a pedestrian or a vehicle. Experimental results show that SVM can be actually and robustly used to recognize objects from laser scanned data points.