Yalin Bastanlar

Izmir Institute of Technology · Department of Computer Engineering

Advanced driver assistance and automated driving systems should be capable of predicting and avoiding dangerous situations. In this paper, we first discuss the importance of predicting dangerous lane changes and provide its description as a machine learning problem. After summarizing the previous work, we propose a method to predict potentially dan...

Neurodegenerative diseases give rise to irreversible neural damage in the brain. By the time it is diagnosed, the disease may have progressed. Although there is no complete treatment for many types of neurodegenerative diseases, by detecting the disease in its early stages, treatments can be applied to relieve some symptoms or prevent disease progr...

The detection of the maneuvers of the surrounding vehicles is important for autonomous vehicles to act accordingly to avoid possible accidents. This study proposes a framework based on contrastive representation learning to detect potentially dangerous cut-in maneuvers that can happen in front of the ego vehicle. First, the encoder network is train...

Vision based solutions for the localization of vehicles have become popular recently. In this study, we employ an image retrieval based visual localization approach, in which database images are kept with GPS coordinates and the location of the retrieved database image serves as the position estimate of the query image in a city scale driving scena...

Although its origins date a few decades back, contrastive learning has recently gained popularity due to its achievements in self-supervised learning, especially in computer vision. Supervised learning usually requires a decent amount of labeled data, which is not easy to obtain for many applications. With self-supervised learning, we can use inexp...

Omnidirectional cameras are capable of providing \(360^{\circ }\) field-of-view in a single shot. This comprehensive view makes them preferable for many computer vision applications. An omnidirectional view is generally represented as a panoramic image with equirectangular projection, which suffers from distortions. Thus, standard camera approaches...

Any city-scale visual localization system has to overcome long-term appearance changes, such as varying illumination conditions or seasonal changes between query and database images. Since semantic content is more robust to such changes, we exploit semantic information to improve visual localization. In our scenario, the database consists of gnomon...

Advanced driver assistance and automated driving systems should be capable of predicting and avoiding dangerous situations. This study proposes a method to predict potentially dangerous cut-in maneuvers happening in the ego lane. We follow a computer vision-based approach that only employs a single in-vehicle RGB camera, and we classify the target...

Dementia is a type of brain disease that affects the mental abilities. Various studies utilize PET features or some two-dimensional brain perspectives to diagnose dementia. In this study, we have proposed an ensemble approach, which employs volumetric and axial perspective features for the diagnosis of Alzheimer’s disease and the patients with mild...

Vision based solutions for the localization of vehicles have become popular recently. We employ an image retrieval based visual localization approach. The database images are kept with GPS coordinates and the location of the retrieved database image serves as an approximate position of the query image. We show that localization can be performed via...

Vision based solutions for the localization of vehicles have become popular recently. We employ an image retrieval based visual lo-calization approach. The database images are kept with GPS coordinates and the location of the retrieved database image serves as an approximate position of the query image. We show that localization can be performed vi...

Lojistik sektöründe, dijital dönüşüm rekabet açısından büyük önem taşımaktadır. Mevcut durumda konteyner depo giriş / çıkış işlemleri sırasında konteyner hasar tespiti lojistik personeli tarafından elle yürütülen bir süreçlerdir. Konteyner depo giriş / çıkış işlemi sırasında, hasarlı konteynerleri tespit etme işlemi lojistik personeli tarafından ge...

Hyperspectral imaging systems provide dense spectral information on the scene under investigation by collecting data from a high number of contiguous bands of the electromagnetic spectrum. The low spatial resolutions of these sensors frequently give rise to the mixing problem in remote sensing applications. Several unmixing approaches are developed...

Deep learning has become the most popular approach in machine learning in recent years. The reason lies in considerably high accuracies obtained by deep learning methods in many tasks especially with textual and visual data. In fact, Natural Language Processing and Computer Vision are the two research areas that deep learning has demonstrated its i...

Omnidirectional cameras cover more ground than perspective cameras, at the expense of resolution. Their comprehensive field of view makes omnidirectional cameras appealing for security and ambient intelligence applications. Person detection is usually a core part of such applications. Conventional methods fail for omnidirectional images due to diff...

An acknowledgements section was missing in this paper. It should read as follows:

Recently, 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 leopards and zebras. To learn characteristic patt...

To detect and classify vehicles in omnidirectional videos, we propose an approach based on the shape (silhouette) of the moving object obtained by background subtraction. Different from other shape-based classification techniques, we exploit the information available in multiple frames of the video. We investigated two different approaches for this...

In recent years, Deep Learning has shown great performance in different problems of computer vision. Its popularity has increased year by year. A lot of models employing convolutional layers have been proposed which have good performance at image classification task. For instance; AlexNet, VGG19, GoogleNet and ResNet. Camera-traps are photo-cameras...

We propose a method for vehicle detection and classification in traffic scenes using an omnidirectional and a PTZ (pan-tilt-zoom) camera. The proposed method controls the PTZ camera with respect to the location of the object detected by background subtraction with the omnidirectional camera, and classifies the vehicle using the frames of the PTZ ca...

The external calibration of a camera system is essential for most of the applications that involve an omnidirectional and a pan-tilt-zoom (PTZ) camera. The methods in the literature fall into two major categories; (1) a complete external calibration of the system which allows all degrees of freedom but highly time consuming, (2) spatial mapping bet...

In this paper, we present an omnidirectional vision based method for object detection.We fi�rst adopt the conventional camera approach that uses sliding windows and Histogram of Gradients (HOG) features. Then, we describe how the feature extraction step of the conventional approach should be modi�ed for a theoretically correct and eff�ective use in...

In this paper, we present our work on vehicle classification with omnidirectional cameras. In particular, we investigate whether the combined use of shape-based and gradient-based classifiers outperforms the individual classifiers or not. For shape-based classification, we extract features from the silhouettes in the omnidirectional video frames, w...

We describe a shape-based method for classification of vehicles from omnidirectional videos. Different from similar approaches, the binary images of vehicles obtained by background subtraction in a sequence of frames are averaged over time. We show with experiments that using the average shape of the object results in a more accurate classification...

This paper describes an approach to detect and classify vehicles in omnidirectional videos. The proposed classification method is based on the shape (silhouette) of the detected moving object obtained by background subtraction. Different from other shape based classification techniques, we exploit the information available in multiple frames of the...

Estimation of camera motion from a given image sequence is a common task for multi-view 3D computer vision applications. Salient features (lines, corners etc.) in the images are used to estimate the motion of the camera, also called egomotion. This estimation suffers from an error built-up as the length of the image sequence increases and this caus...

This paper presents an omnidirectional vision based solution to detect human beings. We first go through the conventional sliding window approaches for human detection. Then, we describe how the feature extraction step of the conventional approaches should be modified for a theoretically correct and effective use in omnidirectional cameras. In this...

This paper presents an approach to detects cars in omnidirectional images. We first go through the conventional method of using Haar-like features and cascaded boosting for conventional camera images. Then, to apply this method for omnidirectional cameras, we generate panoramic images from omnidirectional ones. In this way we perform car detection...

This paper presents an approach to detects cars in omnidirectional images. We first go through the conventional method of using Haar-like features and cascaded boosting for conventional camera images. Then, to apply this method for omnidirectional cameras, we generate panoramic images from omnidirectional ones. In this way we perform car detection...

The machine learning field, which can be briefly defined as enabling computers make successful predictions using past experiences, has exhibited an impressive development recently with the help of the rapid increase in the storage capacity and processing power of computers. Together with many other disciplines, machine learning methods have been wi...

We describe a pipeline for structure-from-motion (SfM) with mixed camera types, namely omnidirectional and perspective cameras. For the steps of this pipeline, we propose new approaches or adapt the existing perspective camera methods to make the pipeline effective and automatic. We model our cameras of different types with the sphere camera model....

In this study, we present a calibration technique that is valid for all single-viewpoint catadioptric cameras. We are able to represent the projection of 3D points on a catadioptric image linearly with a 6×10 projection matrix, which uses lifted coordinates for image and 3D points. This projection matrix can be computed from 3D–2D correspondences (...

A 120 km-long part of the southwestern coast of Turkey, with well-developed karst terrain in contact with the sea, has been investigated by systematic diving surveys to determine the submarine groundwater discharges (SGDs). The physical, chemical and isotopic data have been used to determine the rate of the fresh groundwater end member (FEM) and it...

We describe a pipeline for structure-from-motion with mixed camera types, namely omni directional and perspective cameras. The steps of the pipeline can be summarized as calibration, point matching, pose estimation, triangulation and bundle adjustment. For these steps, we either propose improved methods or modify existing perspective camera methods...

The problems of dense stereo reconstruction and object class segmentation can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are mutually informative, no attempt has been made to j...

The work presented here is on extraction of 3D structure using images of different camera types. For systems with one type of camera, a common way of structure extraction is matching and computing the camera motion between the views, and estimating the 3D location of the points in the scene. Our contribution is proposing and bringing together prope...

When directly applied to images with different scales, scale invariant feature transform (SIFT) matching performance decreases significantly. In this reported work, this phenomenon is demonstrated and a simple method to increase the performance of SIFT matching is proposed. The proposed method includes preprocessing the images before matching and i...

The work presented here is on extraction of D structure using images of different camera types. For systems with one type of camera, a common way of structure extraction is matching and computing the camera motion between the views, and estimating the 3D location of the points in the scene. Our contribution is proposing and bringing together proper...

In this paper, we propose a method to estimate the fundamental matrix for hybrid cameras robustly. In our study a catadioptric omnidirectional camera and a perspective camera were used to obtain hybrid image pairs. For automatic feature point matching, we employed scale invariant feature transform (SIFT) and improved matching results with the propo...

In this thesis, a pipeline for structure-from-motion with mixed camera types is described and methods for the steps of this pipeline to make it effective and automatic are proposed. These steps can be summarized as calibration, feature point matching, epipolar geometry and pose estimation, triangulation and bundle adjustment. We worked with catadio...

We developed a method to validate and filter a large set of previously obtained corner points. We derived the necessary relationships between image derivatives and estimates of corner angle, orientation and contrast. Commonly used cornerness measures of the auto-correlation matrix estimates of image derivatives are expressed in terms of these estim...

In this study, we present a calibration technique that is valid for all single-viewpoint catadioptric cameras. We are able to represent the projection of 3D points on a catadioptric image linearly with a 6 × 10 projection matrix, which uses lifted coordinates for image and 3D points. This projection matrix can be computed with enough number of 3D-2...

An efficient 3D reconstruction technique based on robust camera motion estimation and an improved version of the space-sweeping stereo reconstruction approach is presented. The proposed approach is focused on generation of usable and fully automatic reconstruction of wide-area scenes with the computational resources of a conventional PC. The aim is...

In this study, the principle that any single-viewpoint catadioptric projection is equivalent to a spherical projection followed by a point projection is explained. Applicability of Gaussian smoothing, line detection and interest point detection using this principle and stereographic projection is investigated. Particularly, Scale Invariant Feature...

zetçe Bu çalışmada, tek görüş noktalı katadioptrik sistemlerin görüntü oluşumunun, önce bir küre üzerine izdüşüm, ardından imge üzerine izdüşüm olarak tanımlanabilmesi [8] esası açıklanmış, buradan hareketle stereografik projeksiyon kullanılarak Gaussian yumuşatma, kenar tespiti ve ilgi noktası tespiti (özel olarak SIFT) işlemlerinin yapılabilirliğ...

The aim of this study is to build a Web-based virtual tour system, focused at the presentation of archaeological sites. The proposed approach is comprised of powerful techniques such as multiview 3D reconstruction, omnidirectional viewing based on panoramic images, and their integration with GIS technologies. In the proposed method, the scene is ca...

In this work, user behaviour characteristics were investigated for a Web-based virtual tour application in which 360deg panoramic images were used. There exist several options for the user to navigate in the museum (interactive floor plan, links in the images and pull-down menu). Written and audio information about the sections visited, detailed in...

In this work, effects of stereoscopic view on object recognition and navigation performance of the participants are examined in an indoor desktop virtual reality environment, which is a two-floor virtual museum having different floor plans and 3D object models inside. This environment is used in two different experimental settings: 1) color-multipl...

We developed a method to obtain corner points for healthier point matching using corner properties such as corner angle, corner orientation and contrast. A large corner point set, obtained by a common corner detector (Harris, Tomasi-Kanade etc.) is given to our algorithm as input Then, the corner properties are extracted for this point set in terms...

A Web-based system-consisting of data entrance, access and retrieval modules-is constructed for museums. Internet users that visit the e-museum, are able to view the written and visual information, belonging to the artworks in the museum, are able to follow the virtual tour prepared for the different sections of the museum, are able to browse the a...

Bu çalışmada, katadioptrik (mercek-ayna sistemli) tümyönlü kameraların görüntüleme sistemleri ve oluşan görüntüler incelenmiş ve elde edilen tümyönlü imgelerden sistem parametrelerinin çıkarılması üzerinde durulmuştur. Hiperbolik aynalı sistemlerde, cisimlerin gerçek dünya koordinatları ve tümyönlü imge üzerindeki eşlenikleri kullanılarak bilinmeye...

Not Available

In this paper, we aimed to enhance the panoramic images (panoramas) that are generated from omnidirectional images (ODI). The blurring problem encountered in these images is defined and the effects of standard interpolation methods (bilinear, bicubic, nearest neighbor, cubic spline) are evaluated first. Then, several feature-based techniques are de...

In this thesis, catadioptric omnidirectional imaging systems are analyzed in detail. Omnidirectional image (ODI) formation characteristics of different camera-mirror configurations are examined and geometrical relations for panoramic and perspective image generation with common mirror types are summarized. A method is developed to determine the unk...

Tel: (312) 2977740, E-posta: serdar@hacettepe.edu.tr Özet Bu çalışmada Batı Toroslar'ın Patara-Kekova bölümü, tatlı su boşalımları ve kıyı-denizaltı mağaraları açısından incelenmiştir. Disiplinler arası bir yaklaşımla yürütülen çalışmada uydu görüntüleri ile jeolojik, tektonik, morfolojik ve topografik veriler kullanılmış, 0m-30m derinlik aralığınd...

MADAG (Mağara Dalışı ve Araştırmaları Grubu; Sualtı Araştırmaları Derneği, ODTÜ-SAT) Özet: Mağara dalışı, içerdiği risklerin fazlalığı nedeniyle çok yetkin ve disiplinli eğitim gerektiren bir dalış türüdür. Dünyada kabul gören eğitim sistemlerinden de yararlanılarak, araştırma projelerine katılacak dalıcılar için geliştirilen "MADAG Mağara Dalışı E...