Master Degree / Yüksek Lisans Tezleri

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

Browse

Filters

2006 - 200912010 - 201952020 - 20231

Settings

COAR Access Rights: search.filters.coarAccessRights.open accessSubject: search.filters.subject.Computer vision

Search Results

Now showing 1 - 7 of 7
  • Master Thesis
    Row Following and Altitude Estimation With Uav Images for Agricultural Fields
    (01. Izmir Institute of Technology, 2023) Yörük, Burak; Baştanlar, Yalın
    Traditional methods in agriculture involve the use of tractors; however, more than 10\% of the planted fields suffer from harvest losses due to these vehicles. Moreover, tractors cannot enter all agricultural lands, thus reducing the available field for planting. After heavy rainfall, mud and other effects prevent these vehicles from accessing arable field, and processes such as crop spraying take significantly longer. In the past, aerial spraying methods using high altitude aircraft were attempted to overcome these problems; however, this method was banned in many areas due to the insufficient altitude and the harmful effects of chemical dispersion outside the fields. Nowadays, UAVs present a better alternative, and aerial spraying methods are regaining popularity. However, these vehicles can still cause errors when flying with a human operator, and their flight times are limited due to inadequate battery capacity. Therefore, the development of UAVs capable of autonomous flight reduces operator costs. However, during flight, liquid changes in the pesticide tanks hinder the UAV's ability to spray pesticides autonomously at a fixed altitude and prevent unwanted pesticide dispersion in undesirable rows. The thesis study provides following of plant rows on UAV images and making altitude estimation from camera images. In this way, it ensures that the UAVs in agricultural areas can stay at a fixed altitude for appropriate spraying and irrigation and prevents the spread of pesticides to unwanted rows.
  • Master Thesis
    Detection and Localization of Motorway Overhead Directional Signs by Convolutional Neural Networks Trained With Synthetic Images
    (Izmir Institute of Technology, 2019) Hekimgil, Hakan; Baştanlar, Yalın
    Image classification, object detection and recognition have gone a long way in the last decade. The competitions, starting with ImageNet, have shown that various improving implementations of Artificial Neural Networks are the best Machine Learning techniques at the time for such tasks. However, machine learning methods require much training data and the such data for image related tasks come at a cost in terms of time and effort, if it can be obtained at all. When training data is scarce or not representative of the whole target set, synthetic data and data augmentation methods are used to increase the training data using what is already available. This thesis work shows that when the target classification images have a structure, even a loose one, it is still possible to use machine learning methods, deep learning in this case, without any real data to begin with and still produce a good detection model. In this work, a Convolutional Neural Network model is trained to detect and localize informative motorway lane direction signs. Starting with no real samples of the target images, a large computer-generated training set is created to train the model. The resulting detector can detect the required sign types with high accuracy, localizing their position by bounding boxes and categorizing them.
  • Master Thesis
    Keypoint Detection and Description on Image Curves
    (Izmir Institute of Technology, 2017) Köksal, Ali; Özuysal, Mustafa
    Image curves are one of the choices for representing interest points which also provide discriminative information about images. Boundary of regions and contour of shapes are real-time instances of image curves. In this thesis, we propose two approaches for keypoint detection and description on image curves. To extract keypoints on image curves, we compute the extrema curvature of region boundaries. This mechanism improves repeatability of keypoints on 3D data. For the description of image curves, shape contours are used. This is similar to approaches that describe the features based on shapes and image gradients. Unlike these approaches, we combine spatial and directional information of tangent directions to extract a feature vector that leads to improved matching and recognition on several standard computer vision tasks such as character and object recognition.
  • Master Thesis
    Keypoint Matching Based on Descriptor Statistics
    (Izmir Institute of Technology, 2016) Uzyıldırım, Furkan Eren; Uzyıldırım, Furkan Eren; Özuysal, Mustafa; Özuysal, Mustafa
    The binary descriptors are the representation of choice for real-time keypoint matching. However, they suffer from reduced matching rates due to their discrete nature. In this thesis, we propose an approach that can augment their performance by searching in the top K near neighbor matches instead of just the single nearest neighbor one. To pick the correct match out of the K near neighbors, we exploit statistics of descriptor bit variations collected for each keypoint individually in an off-line training phase. This is similar in spirit to approaches that learn a patch specific keypoint representation. Unlike these approaches, we limit the use of a keypoint specific score only to rank the list of K near neighbors. Since this list can be efficiently computed with approximate nearest neighbor algorithms, our approach scales well to large descriptor collections.
  • Master Thesis
    Shape Based Detection and Classification of Vehicles Using Omnidirectional Videos
    (Izmir Institute of Technology, 2015) Karaimer, Hakkı Can; Baştanlar, Yalın
    To detect and classify vehicles in omnidirectional videos, an approach based on the shape (silhouette) of the moving object obtained by background subtraction is proposed. Different from other shape based classification techniques, the information available in multiple frames of the video is exploited. Two different approaches were investigated for this purpose. One is combining silhouettes extracted from a sequence of frames to create an average silhouette, the other is making individual decisions for all frames and use consensus of these decisions. Using multiple frames eliminates most of the wrong decisions which are caused by a poorly extracted silhouette from a single video frame. The vehicle types which are classified are motorcycle, car (sedan) and van (minibus). The features extracted from the silhouettes are convexity, elongation, rectangularity, and Hu moments. Three separate methods of classification is applied. The first one is a flowchart based (i.e. rule based) method, the second one is K nearest neighbor classification, and the third one is using a Deep Neural Network. 60% of the samples in the dataset are used for training. To ensure randomization, the procedure is repeated three times with the whole dataset split each time differently into training and testing samples (i.e. three-fold cross validation). The results indicate that using silhouettes in multiple frames performs better than using single frame silhouettes.
  • Master Thesis
    Vision-Based Monitoring and Control of Fiber Laser Welding
    (Izmir Institute of Technology, 2014) Tavkaya, Emre; Dede, Mehmet İsmet Can
    Laser welding is an advanced emission process that applies the converted laser beam energy to join pieces by melting and welding them together. Fiber lasers, with their high efficiency, continuous wave and shorter wavelength, are mostly useful for deep penetration welding of materials. To avoid the defects in an automated fiber laser welding process such as pores, cracks or blow-out holes and to make the welding process controllable, off-line pre-process is required. Tuning welding parameters is critical during this stage since modeling of the process is hard and parameters change with respect to material and thickness. Therefore, real-time control of the laser welding becomes a challenge due to uncertainties in the process. A solution to such problem could be a vision-based monitoring and control system, which uses a path modification algorithm that matches CAD-based (Computer Aided Design-based) path data to target path before welding. In this thesis, a vision-based path modification algorithm is developed to determine the orientation of target welding path. Two subsystems are used in this developed technique including; a machine vision system and a CNC system. These subsystems are integrated through developed vision algorithm and subroutine logic of CNC system by calculating laser spot position on workpiece during operation. As a result of implemented technique, welding path modification data is stored as a CNC subprogram (file) under the CNC main program so that operational modification is made without the need of any change on the main CNC program. The proposed method is experimentally tested to assess the performance of the monitoring and control technique on line and curve welding paths for mild steel and stainless steel materials with two different material thicknesses. The accuracy of the measurements is carried out by comparing the measured and computed offset values that are exported from the vision algorithm with reference to effective laser beam diameter. The results of tests indicate that the vision system accuracy varies between %85 and %95 for 600 micron effective laser beam size. For thinner materials less than 1 millimeter, due to smaller effective laser beam size requirements, system performance is found to be decreased down to %58-70 as a result of 400 micron effective laser beam size.
  • Master Thesis
    An Automatic Vision Guided Position Controller in a Conveyor Belt Pick and Place System
    (Izmir Institute of Technology, 2006) Çelikdemir, Özgür; Aytaç, İsmail Sıtkı
    An automatic vision guided position controller system is developed as for possible applications such as handling and packaging that require position and orientation control. The aim here is to minimize the production cycle time, and to improve the economic performance and system productivity. The system designed can be partitioned into five major parts: vision module, pneumatic automation module, manipulator, conveyor-belt and a software that manages and integrates these modules. The developed software captures raw image data from a camera that is connected to a PC via usb port. Using image processing methods, this software determines the proper coordinates and pose of the moving parts on the conveyor belt in real time. The pick and place system locates the parts to the packaging area as part.s predefined orientation. The software communicates with a controller card via serial port, manages and synchronizes the peripherals (conveyor belt stepper motors- pneumatic valves,etc) of the system. C programming language is used in the implementation. OpenCV library is utilized for image acquisition. The system has the following characteristics: The Conveyor belt runs with a constant speed and objects on the conveyor belt may have arbitrary position and orientation. The vision system detects parts with their position and orientation on the moving conveyor belt based on a reference position. The manipulator picks the part and then corrects its position comparing the information obtained by vision system with predefined position, and it places the object to the packaging area. System can be trained for the desired position of the object .