Master Degree / Yüksek Lisans Tezleri
Permanent URI for this collectionhttps://hdl.handle.net/11147/3008
Browse
10 results
Search Results
Now showing 1 - 10 of 10
Master Thesis Row Following and Altitude Estimation With Uav Images for Agricultural Fields(01. Izmir Institute of Technology, 2023) Yörük, Burak; Baştanlar, YalınTraditional 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 Improvement on Motion-Guided Siamese Object Tracking Networks Using Prioritized Windows(01. Izmir Institute of Technology, 2021) Ünlü, Ünver Can; Baştanlar, YalınIn recent years, there has been significant progress in Visual Object Tracking with evolutions of both computers and learning algorithms, especially in Neural Networks. Therefore, we obtain better results by combining Neural Networks and traditional tracking methods such as Kalman Filter and Correlation Filters. SiamFC is an example of such algorithms because SiamFC combines Siamese Neural Networks and Correlation Filters. SiamFC is open to development because it does not have an online learning process. An example of the improved SiamFC is Kalman-Siam that combines Kalman Filter and Multi-feature SiamFC. Kalman-Siam uses Kalman-Filter to solve the occlusion situation problem by processing the target's previous motion trajectory. Therefore, the tracking can fail in other complex scenarios for Kalman-Siam. One of the methods for solving such problems is detecting this situation and starting the re-tracking process as we used in this research. Also, we used a parameter calculated on the response map after the correlation operation in SiamFC to detect these situations. First, our algorithm generates possible prioritized search windows. Then, it runs in a specific order of priority for these generated search windows surrounding the target's last known location. We named this process Adaptive Window Search that starts from the highest priority search windows and continues until the lowest search windows do not exist. Therefore, we named our algorithm Adaptive-Kalman-Siam. We demonstrated more successful results on commonly used datasets. Adaptive-Kalman-Siam tracks an object better than SiamFC and Kalman-Siam in Background Clutters, Fast Motion, Motion Blur, and Occlusion complex tracking scenarios.Master Thesis Container Damage Detection and Classification Using Container Images(Izmir Institute of Technology, 2019) İmamoğlu, Zeynep; Tuğlular, Tuğkan; Baştanlar, YalınIn the logistics sector, digital transformation is of great importance in terms of competition. In the present case, container warehouse entry / exit operations are carried out manually by the logistics personnel including container damage detection. During container warehouse entry / exit process, the process of detecting damaged containers is carried out by the personnel and several minutes are required to upload to the system. The aim of this thesis is to automate detection of damaged containers. This way, the mistakes made by the personnel in this stage will be eliminated and the process will be accelerated. In this thesis, we propose a machine learning method which detects damaged containers using the container images to perform statistical damaged / undamaged estimation. We modeled the problem as a binary classification problem, which considers a container as damaged or undamaged. The result obtained from the undertaken studies shows that there is no single best method for visual classification. It is shown how the dataset was created and how the parameters used in the layered structure impact the most suitable model could be created for this study.Master Thesis Estimation of Low Sucrose Concentrations and Classification of Bacteria Concentrations With Machine Learning on Spectroscopic Data(Izmir Institute of Technology, 2019) Mezgil, Bahadır; Baştanlar, Yalın; Baştanlar, YalınSpectroscopy can be used to identify elements. In a similar way, there are recent studies that use optical spectroscopy to measure the material concentrations in chemical solutions. In this study, we employ machine learning techniques on collected ultraviolet-visible spectra to estimate the level of sucrose concentrations in solutions and to classify bacteria concentrations. Some metal nanoparticles are very sensitive to refraction index changes in the environment and this helps to detect small refraction index changes in the solution. In our study, gold nanoparticles are used and we benefited from this property to estimate sucrose concentrations. The samples in different low sucrose concentration solutions are obtained by mixing the sucrose measured with precision scales with pure water and then the UV-Vis spectrum of each sample is measured. For the bacteria concentration solutions, spectra for six different bacteria concentrations are captured. Spectra of the same solutions are also captured before adding the bacteria. For each of these solutions, four sets are prepared where gold nanoparticles are not grown (minute 0) and grown for 4 minutes, 10 minutes and 12 minutes. After the dataset preparation, these spectrum measurements are transferred into MATLAB environment as sucrose concentration dataset and bacteria solution dataset. Then the necessary preprocessing steps are performed in order to get the most informative and distinguishing information from these datasets. The raw measurement values and processed spectrum measurements are trained with shallow Artificial Neural Networks (ANN) on MATLAB Deep Learning Toolbox and Support Vector Machine (SVM) on MATLAB Statistics and Machine Learning Toolbox. When the results of the conducted machine learning experiments are examined, success rate is promising for the estimation of sucrose concentrations and very high for classification of bacteria concentrations in pure water solution.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, YalınImage 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 Elimination of Useless Images From Raw Camera-Trap Data(Izmir Institute of Technology, 2018) Tekeli, Ulaş; Baştanlar, YalınA common way to observe animals in nature is to use motion triggered cameras that are called camera-traps. With the expanding usage of camera-trap due to advances in digital technology, the number of images that are collected from camera-traps has increased significantly. Labeling and grouping of animals in these images have put enormous workload on wild-life researchers. We propose a system that frees time for researchers by eliminating useless images-too bright, too dark, too blurred images and images that contain no animals from raw camera-trap data. Firstly, we utilise image histograms to eliminate too bright and too dark images and Fast Fourier Transform to eliminate blurred ones. Secondly, we make use of deep learning techniques and background subtraction to eliminate images without animals and we present the result of our experiments on these subjects. Our approach on eliminating too bright and too dark images have missed very few images and on eliminating blur images we achieve 95.5% success. Finally we show that the technique we propose eliminates more than 50% of images without animals while containing 99% of images with animals.Master Thesis Localization of Certain Animal Species in Images Via Training Neural Networks With Image Patches(Izmir Institute of Technology, 2017) Orhan, Semih; Baştanlar, YalınObject 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, YalınThe 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 Shape Based Detection and Classification of Vehicles Using Omnidirectional Videos(Izmir Institute of Technology, 2015) Karaimer, Hakkı Can; Baştanlar, YalınTo 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 A Direct Approach for Object Detection With Omnidirectional Cameras(Izmir Institute of Technology, 2014) Çınaroğlu, İbrahim; Baştanlar, YalınIn 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.