Computer Engineering / Bilgisayar Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/10
Browse
8 results
Search Results
Article Citation - WoS: 3Citation - Scopus: 4Affordable person detection in omnidirectional cameras using radial integral channel features(Springer Verlag, 2019) Demiröz, Barış Evrim; Salah, Albert Ali; Baştanlar, Yalın; Akarun, LaleOmnidirectional 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 different image geometry and formation. In this study, we propose a method for person detection in omnidirectional images, which is based on the integral channel features approach. Features are extracted from various channels, such as LUV and gradient magnitude, and classified using boosted decision trees. Features are pixel sums inside annular sectors (doughnut slice shapes) contained by the detection window. We also propose a novel data structure called radial integral image that allows to calculate sums inside annular sectors efficiently. We have shown with experiments that our method outperforms the previous state of the art and uses significantly less computational resources.Article Citation - WoS: 22Citation - Scopus: 40Correlation of Critical Success Factors With Success of Software Projects: an Empirical Investigation(Springer Verlag, 2019) Garousi, Vahid; Tarhan, Ayça; Pfahl, Dietmar; Coşkunçay, Ahmet; Demirörs, OnurSoftware engineering researchers have, over the years, proposed different critical success factors (CSFs) which are believed to be critically correlated with the success of software projects. To conduct an empirical investigation into the correlation of CSFs with success of software projects, we adapt and extend in this work an existing contingency fit model of CSFs. To archive the above objective, we designed an online survey and gathered CSF-related data for 101 software projects in the Turkish software industry. Among our findings is that the top three CSFs having the most significant associations with project success were: (1) team experience with the software development methodologies, (2) team's expertise with the task, and (3) project monitoring and controlling. A comprehensive correlation analysis between the CSFs and project success indicates positive associations between the majority of the factors and variables, however, in most of the cases at non-significant levels. By adding to the body of evidence in this field, the results of the study will be useful for a wide audience. Software managers can use the results to prioritize the improvement opportunities in their organizations w.r.t. the discussed CSFs. Software engineers might use the results to improve their skills in different dimensions, and researchers might use the results to prioritize and conduct follow-up in-depth studies on those factors.Article Citation - WoS: 5Citation - Scopus: 9Modeling Cultures of the Embedded Software Industry: Feedback From the Field(Springer Verlag, 2021) Akdur, Deniz; Say, Bilge; Demirörs, OnurEngineering of modern embedded systems requires complex technical, managerial and operational processes. To cope with the complexity, modeling is a commonly used approach in the embedded software industry. The modeling approaches in embedded software vary since the characteristics of modeling such as purpose, medium type and life cycle phase differ among systems and industrial sectors. The objective of this paper is to detail the use of a characterization model MAPforES ("Modeling Approach Patterns for Embedded Software"). This paper presents the results of applying MAPforES in multiple case studies. The applications are performed in three sectors of the embedded software industry: defense and aerospace, automotive and transportation, and consumer electronics. A series of both structured and semi-structured interviews with 35 embedded software professionals were conducted as part of the case studies. The characterization model was successfully applied to these cases. The results show that identifying individual patterns provides insight for improving both individual behavior and the behavior of projects and organizations.Article Citation - WoS: 6Citation - Scopus: 6Estimating Software Robustness in Relation To Input Validation Vulnerabilities Using Bayesian Networks(Springer Verlag, 2018) Ufuktepe, Ekincan; Tuğlular, TuğkanEstimating the robustness of software in the presence of invalid inputs has long been a challenging task owing to the fact that developers usually fail to take the necessary action to validate inputs during the design and implementation of software. We propose a method for estimating the robustness of software in relation to input validation vulnerabilities using Bayesian networks. The proposed method runs on all program functions and/or methods. It calculates a robustness value using information on the existence of input validation code in the functions and utilizing common weakness scores of known input validation vulnerabilities. In the case study, ten well-known software libraries implemented in the JavaScript language, which are chosen because of their increasing popularity among software developers, are evaluated. Using our method, software development teams can track changes made to software to deal with invalid inputs.Article Citation - WoS: 16Citation - Scopus: 16Detection and Classification of Vehicles From Omnidirectional Videos Using Multiple Silhouettes(Springer Verlag, 2017) Karaimer, Hakkı Can; Barış, İpek; Baştanlar, YalınTo 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 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 we classify are motorcycle, car (sedan) and van (minibus). The features extracted from the silhouettes are convexity, elongation, rectangularity and Hu moments. We applied two separate methods of classification. First one is a flowchart-based method that we developed and the second is K-nearest neighbour classification. 60% of the samples in the dataset are used for training. To ensure randomization in the experiments, threefold cross-validation is applied. The results indicate that using multiple silhouettes increases the classification performance.Article Citation - WoS: 28Citation - Scopus: 28A Direct Approach for Object Detection With Catadioptric Omnidirectional Cameras(Springer Verlag, 2016) Çınaroğlu, İbrahim; Baştanlar, YalınIn this paper, we present an omnidirectional vision-based method for object detection. We first adopt the conventional camera approach that uses sliding windows and histogram of oriented gradients (HOG) features. Then, we describe how the feature extraction step of the conventional approach should be modified for a theoretically correct and effective use in omnidirectional cameras. Main steps are modification of gradient magnitudes using Riemannian metric and conversion of gradient orientations to form an omnidirectional sliding window. In this way, we perform object detection directly on the omnidirectional images without converting them to panoramic or perspective images. Our experiments, with synthetic and real images, compare the proposed approach with regular (unmodified) HOG computation on both omnidirectional and panoramic images. Results show that the proposed approach should be preferred.Article Citation - WoS: 5Citation - Scopus: 5Instance Detection by Keypoint Matching Beyond the Nearest Neighbor(Springer Verlag, 2016) Uzyıldırım, Furkan Eren; Özuysal, MustafaThe binary descriptors are the representation of choice for real-time keypoint matching. However, they suffer from reduced matching rates due to their discrete nature. 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 variations collected for each keypoint in an off-line training phase. This is a similar approach to those that learn a patch specific keypoint representation. Unlike these approaches, we only use a keypoint specific score 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 sets.Article Citation - WoS: 9Citation - Scopus: 10Fault Domain-Based Testing in Imperfect Situations: a Heuristic Approach and Case Studies(Springer Verlag, 2015) Belli, Fevzi; Beyazıt, Mutlu; Endo, Andre Takeshi; Mathur, Aditya; Simao, AdenilsoModel-based testing (MBT) involves creating an abstraction, called a model, to represent the system and automatically deriving test cases from this model. MBT can be performed using various approaches that generally employ certain assumptions or requirements affecting the test performance in practice. Here, we consider the harmonized state identifiers (HSI) method, which is based on finite state machine (FSM) models and generates test sets that cover all faults in a given domain under certain conditions. We are interested in the application of the HSI method in practical scenarios where some conditions do not hold or are not straightforward to satisfy. Thus, we propose a heuristic extension to the HSI method, called heuristic HSI (HHSI), to consider imperfect situations as they often occur in practice. To analyze the characteristics of HHSI, we empirically compare it to random testing and coverage-based testing using non-trivial case studies. The experiments include model-based mutation analyses over several FSM models.