Master Degree / Yüksek Lisans Tezleri

Permanent URI for this collectionhttps://hdl.handle.net/11147/3008

Browse

Filters

2014 - 20173

Settings

Author: search.filters.author.Baştanlar, YalınSubject: search.filters.subject.Object detection

Search Results

Now showing 1 - 3 of 3
  • Master Thesis
    Localization of Certain Animal Species in Images Via Training Neural Networks With Image Patches
    (Izmir Institute of Technology, 2017) Orhan, Semih; Baştanlar, Yalın
    Object detection is one of the most important tasks for computer vision systems. Varying object size, varying view angle, illumination conditions, occlusion etc. effect the success rate. In recent years, convolutional neural networks (CNNs) have shown great performance in different problems of computer vision including object detection and localization. In this work, we propose a novel training approach for CNNs to localize some animal species whose bodies have distinctive pattern, such as speckles of leopards, black-white lines of zebras, etc. To learn characteristic patterns, small patches are taken from different body parts of animals and they are used to train models. To find object location, in a test image, all locations are visited in a sliding window fashion. Crops are fed to CNN, then classification scores of all patches are recorded. To illustrate object location, heat map is generated by the classification scores of the patches. Afterwards, heat maps are converted to binary images and end up with bounding box estimates of objects. The localization performance of our Patch-based training is compared with Faster R-CNN – a state-of-the-art CNN-based object detection and localization algorithm. While evaluating the performances, in addition to the standard precision-recall metric, we use area-precision and area-recall which represent the potential of Patch-based Model better. Experiment results show that the proposed training method has better performance than Faster R-CNN for most of the evaluated classes. We also showed that Patch-based Model can be used with Faster R-CNN to increase its localization performance.
  • Master Thesis
    Classification and Tracking of Vehicles With Hybrid Camera Systems
    (Izmir Institute of Technology, 2016) Barış, İpek; Baştanlar, Yalın
    The integrated usage of several vision systems is especially important for surveillance applications. In case of a hybrid system combining an omnidirectional and a PTZ (pan-tilt-zoom) camera, the omnidirectional camera provides 360 horizontal FOV (Field of View) with a low resolution per viewing angle whereas the PTZ camera provides high resolution at a certain direction. In this thesis work, we introduce a hybrid system combining the powerful aspects of both camera types and aims a wide angle high resolution surveillance for traffic scenes. The hybrid system provides real-time object classification and high resolution tracking. The omnidirectional camera detects the moving objects and then it performs an initial classification by using shape-based features. Concurrently, the PTZ camera classifies the objects in detail by using HOG (Histogram of Oriented Gradients)+SVM (Support Vector Machine) pair. The object types we worked on are pedestrian, motorcycle, car and van. In the experiments, we compared the classification accuracy of omnidirectional camera, PTZ camera and hybrid system. Aiming high resolution tracking, the PTZ camera tracks the objects belonging to the user defined class and detected by using the omnidirectional camera.
  • Master Thesis
    A Direct Approach for Object Detection With Omnidirectional Cameras
    (Izmir Institute of Technology, 2014) Çınaroğlu, İbrahim; Baştanlar, Yalın
    In this thesis, an object detection system based on omnidirectional camera which has the advantages of detecting a large view-field is introduced. Initially, the traditional camera approach that uses sliding windows and Histogram of Gradients (HOG) features is adopted. Later on, how the feature extraction step of the conventional approach should be modified is described. The aim is an efficient and mathematically correct use of HOG features in omnidirectional images. Main steps are conversion of gradient orientations to compose an omnidirectional sliding window and modification of gradient magnitudes by means of Riemannian metric. Owing to the proposed methods, object detection process can be performed on the omnidirectional images without converting them to panoramic or perspective image. Experiments that are conducted with both synthetic and real images compare the proposed approach with regular (unmodified) HOG computation on both omnidirectional and panoramic images. Results show that the performance of detection has been improved by using the proposed method.