Výsledky vyhledávání - "Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision"

Infrared Small Target Detection with YOLO: Performance Analysis and Optimization

Autoři: Atrash, Abdulkarim Uğur, Ömür ERTEKİN BOLELLİ, ŞEYDA a další

Přispěvatelé: Atrash, Abdulkarim Uğur, Ömür ERTEKİN BOLELLİ, ŞEYDA a další

Témata: Single-Frame Infrared Small Target Detection, Moving Target Detection, Small Object Detection, SIRST, YOLO, Arbis Subjects::Engineering and Technology::Computer Sciences, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision::Computer Vision

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/115660

Dostupnost: https://hdl.handle.net/11511/115660

FLAW DETECTION IN ALUMINIUM CASTINGS LEVERAGING SYNTHETIC DATA FOR NON-DESTRUCTIVE TESTING ; TAHRİBATSIZ MUAYENE İÇİN SENTETİK VERİLER KULLANILARAK ALÜMİNYUM DÖKÜM KUSURLARININ TESPİT EDİLMESİ

Autoři: Erkan, Umut Can Sürer, Elif Yaman, Ulaş a další

Přispěvatelé: Erkan, Umut Can Sürer, Elif Yaman, Ulaş a další

Témata: casting defect detection, non-destructive testing, self-supervised learning, synthetic data, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision, Arbis Subjects::Engineering and Technology::Mechanical Engineering::Construction and Manufacturing::NDT Engineering

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/115619

Dostupnost: https://hdl.handle.net/11511/115619

GENERALIZED OUTLIER EXPOSURE FOR ROBUST OUT-OF-DISTRIBUTION DETECTION: A STUDY ON MIXING, FILTERING, AND AUGMENTATION ; SAĞLAM DAĞILIM DIŞI TESPİTİ İÇİN GENELLEŞTİRİLMİŞ AYKIRI VERİYE MARUZ BIRAKMA: KARIŞTIRMA, FİLTRELEME VE VERİ ARTIRMA ÜZERİNE BİR ÇALIŞMA

Autoři: Öztel, Fatma Altan, Koçyiğit Department of Data Informatics

Přispěvatelé: Öztel, Fatma Altan, Koçyiğit Department of Data Informatics

Témata: Out-of-distribution Detection, Outlier Exposure Based OOD Detection, Mixup, Filtering, Augmentation, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/115588

Dostupnost: https://hdl.handle.net/11511/115588

Design and implementation of an object-level indoor navigation algorithm using spherical images ; Küresel görüntüler kullanılarak nesne tabanlı iç mekan navigasyon algoritması tasarımı ve gerçekleştirilmesi

Autoři: Kurt, Umut Koku, Ahmet Buğra Bayar, Gökhan a další

Přispěvatelé: Kurt, Umut Koku, Ahmet Buğra Bayar, Gökhan a další

Témata: Topological Mapping, Spherical Imaging, Object-Level Semantics, Visual SLAM, Hierarchical Map Representation, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision, Arbis Subjects::Engineering and Technology::Information Systems, Communication and Control Engineering::Robotics and Mechatronics Systems::Computer Vision, Communication and Control Engineering::Robotics and Mechatronics Systems::Field and Service Robots

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/116084

Dostupnost: https://hdl.handle.net/11511/116084

Event camera based pose estimation in stereo visual-inertial odometry with multi-state constraint Kalman filter ; Çok durum kısıtlı Kalman filtresi ile stereo görsel-ataletsel odometride olay kamera temelli poz tahmini

Autoři: Keskin, Abdulbaki Alatan, Abdullah Aydın Department of Electrical and Electronics Engineering

Přispěvatelé: Keskin, Abdulbaki Alatan, Abdullah Aydın Department of Electrical and Electronics Engineering

Témata: Visual-inertial odometry, Event-based vision, Motion compensation, High dynamic range, State estimation, Arbis Subjects::Engineering and Technology::Electrical and Electronics Engineering, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision

Popis souboru: 115 pages; application/pdf

Relation: https://hdl.handle.net/11511/116041

Dostupnost: https://hdl.handle.net/11511/116041

Interpretable zero-shot classification with concept bottleneck models ; Kavram dar boğazı modelleriyle yorumlanabilir sıfır örnekli sınıflandırma

Autoři: Özdemir, Onat Akbaş, Emre Department of Computer Engineering

Přispěvatelé: Özdemir, Onat Akbaş, Emre Department of Computer Engineering

Témata: Zero-shot learning, Interpretable machine learning, Concept bottleneck models, Attribute-based classification, Vision-language models, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition

Popis souboru: 63 pages; application/pdf

Relation: https://hdl.handle.net/11511/115995

Dostupnost: https://hdl.handle.net/11511/115995

ADAPTIVE DATA AUGMENTATION THROUGH PROMPT-DRIVEN POLICY OPTIMIZATION WITH LARGE LANGUAGE MODELS ; DİL MODELLERİYLE İSTEM TABANLI POLİTİKA OPTİMİZASYONU KULLANARAK UYARLANABİLİR VERİ ARTIRIMI

Autoři: Duru, Ant Temizel, Alptekin Department of Modeling and Simulation

Přispěvatelé: Duru, Ant Temizel, Alptekin Department of Modeling and Simulation

Témata: Automated Data Augmentation, Large Language Models, Model Training Optimization, Deep Learning, Image Classification, Arbis Subjects::Engineering and Technology::Computer Sciences, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/115992

Dostupnost: https://hdl.handle.net/11511/115992

Semi supervised orientation estimation of honeybees ; Bal arılarının yarı denetimli yönelim tahmini

Autoři: Gündeğer, bilal yağız Şahin, Erol Department of Computer Engineering

Přispěvatelé: Gündeğer, bilal yağız Şahin, Erol Department of Computer Engineering

Témata: Markerless tracking, Orientation estimation, Lifelong learning, Honeybee, Behavior, Semi-supervised learning, Arbis Subjects::Engineering and Technology, Arbis Subjects::Engineering and Technology::Computer Sciences, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition, Computer Learning and Pattern Recognition::Computer Learning, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision::Computer Vision

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/115538

Dostupnost: https://hdl.handle.net/11511/115538

Incorporating piecewise linear functions with constant regions in backpropagation ; Sabit bölgeli parçalı doğrusal fonsi̇yonların geri yayılım algoritmasina dahil edilmesi

Autoři: Doğan, Adnan Harun Kalkan, Sinan Akbaş, Emre a další

Přispěvatelé: Doğan, Adnan Harun Kalkan, Sinan Akbaş, Emre a další

Témata: Gradients of Piecewise Linear Functions with Constant Regions, Combinatorial Optimization, Optimal Transport, Error-driven Update, Identity Update, Bipartite Matching in Object Detection, Arbis Subjects::Engineering and Technology::Computer Sciences, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/113504

Dostupnost: https://hdl.handle.net/11511/113504

UTILIZATION OF GAUSSIAN SPLATTING IN VISUAL SLAM ; GÖRSEL E¸S ZAMANLI KONUMLANDIRMA VE HAR˙ITALAMADA GAUSS SIÇRAMASININ KULLANIMI

Autoři: Sarıkamış, Furkan Aykut Alatan, Abdullah Aydın Computational Design and Fabrication Technologies in Department of Architecture

Přispěvatelé: Sarıkamış, Furkan Aykut Alatan, Abdullah Aydın Computational Design and Fabrication Technologies in Department of Architecture

Témata: Gaussian Splatting, Neural Radiance Fields, Visual SLAM, 3D reconstruction, Arbis Subjects::Engineering and Technology, Arbis Subjects::Engineering and Technology::Electrical and Electronics Engineering::Other, Arbis Subjects::Engineering and Technology::Electrical and Electronics Engineering, Arbis Subjects::Engineering and Technology::Computer Sciences, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision::Computer Vision

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/113440

Dostupnost: https://hdl.handle.net/11511/113440

Fiducial marker detection and identification for individual honey bee tracking using cascaded deep learning models ; Ardışık derin öğrenme modelleri kullanarak bireysel arı takibi için güvenilir işaretçi tespiti ve çözümlenmesi

Autoři: Kara, Mustafa Yavuz Alemdar, Hande Department of Computer Engineering

Přispěvatelé: Kara, Mustafa Yavuz Alemdar, Hande Department of Computer Engineering

Témata: Visual recognition, Object detection, Data generation, Visual fiducial marker, Bee tracking, Arbis Subjects::Engineering and Technology, Arbis Subjects::Engineering and Technology::Computer Sciences, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition, Computer Learning and Pattern Recognition::Neural Networks

Popis souboru: 62 pages; application/pdf

Relation: https://hdl.handle.net/11511/113487

Dostupnost: https://hdl.handle.net/11511/113487

Cross-modal semi-dense image matching ; Çapraz-modlu yarı-yoğun görüntü eşleştirme

Autoři: Tuzcuoğlu, Önder Alatan, Abdullah Aydın Kalkan, Sinan a další

Přispěvatelé: Tuzcuoğlu, Önder Alatan, Abdullah Aydın Kalkan, Sinan a další

Témata: Image matching, Cross-modal image matching, Feature matching, Visible-thermal image matching, Arbis Subjects::Engineering and Technology, Arbis Subjects::Engineering and Technology::Electrical and Electronics Engineering, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/111012

Dostupnost: https://hdl.handle.net/11511/111012

Prediction of Covid-19 risk of a person by analyzing computed tomography images using convolutional neural networks ; Kişilerin Covid-19 riskinin, bilgisayarlı tomografi görüntülerinin evrişimli sinir ağları kullanılarak tahminlenmesi

Autoři: Topçu, Kaan Acar, Aybar Can Department of Information Systems

Přispěvatelé: Topçu, Kaan Acar, Aybar Can Department of Information Systems

Témata: Convolutional neural network, Covid-19, Image classification, Computed tomography, Arbis Subjects::Engineering and Technology::Information Systems, Communication and Control Engineering, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision

Popis souboru: 56 pages; application/pdf

Relation: https://hdl.handle.net/11511/108466

Dostupnost: https://hdl.handle.net/11511/108466

3D pose uncertainty estimation for visual aided navigation ; Görüntü yardımlı navigasyonda 3B poz belirsizlik kestirimi

Autoři: Temür, Ramazan Alatan, Abdullah Aydın Department of Electrical and Electronics Engineering

Přispěvatelé: Temür, Ramazan Alatan, Abdullah Aydın Department of Electrical and Electronics Engineering

Témata: Computer vision, Uncertainty, Navigation, 3D pose estimation, Arbis Subjects::Engineering and Technology::Electrical and Electronics Engineering::Other, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/112931

Dostupnost: https://hdl.handle.net/11511/112931

Exploiting spatial redundancy in feature maps to accelerate convolutional neural networks ; Evrişimli sinir ağlarını hızlandırmak için özellik haritalarındaki uzamsal fazlalıktan yararlanma

Autoři: Ulaş, Muhammed Yasin Akbaş, Emre Yarman Vural, Fatoş Tunay a další

Přispěvatelé: Ulaş, Muhammed Yasin Akbaş, Emre Yarman Vural, Fatoş Tunay a další

Témata: Deep learning, Convolutional neural networks, Spatial redundancy, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/110919

Dostupnost: https://hdl.handle.net/11511/110919

Self-supervised learning for unsupervised image classification and supervised localization tasks ; Denetimsiz görüntü sınıflandırma ve denetimli yer saptama görevleri için öz-denetimli öğrenme

Autoři: Baydar, Melih Akbaş, Emre Department of Computer Engineering

Přispěvatelé: Baydar, Melih Akbaş, Emre Department of Computer Engineering

Témata: Self-supervised learning, Contrastive learning, Non-contrastive learning, Instance discrimination task, Semantic segmentation, Object detection, Unsupervised image classification, Deep clustering, Arbis Subjects::Engineering and Technology, Arbis Subjects::Engineering and Technology::Computer Sciences, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition

Popis souboru: 86 pages; application/pdf

Relation: https://hdl.handle.net/11511/110517

Dostupnost: https://hdl.handle.net/11511/110517

Transformer Based Sensor Fusion and Pose Estimation in End-to-End Supervised Learning of Visual Inertial Odometry ; Denetemeli Uçtan Uca Öğrenme ile Görsel Ataletsel Odometride Dönüştürücü Temelli Algılayıcı Füzyonu ve Poz Tahmini

Autoři: Kurt, Yunus Bilge Alatan, Abdullah Aydın Department of Electrical and Electronics Engineering

Přispěvatelé: Kurt, Yunus Bilge Alatan, Abdullah Aydın Department of Electrical and Electronics Engineering

Témata: Visual inertial odometry, End-to-end odometry learning, Transformer, Arbis Subjects::Engineering and Technology, Arbis Subjects::Engineering and Technology::Electrical and Electronics Engineering, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/111293

Dostupnost: https://hdl.handle.net/11511/111293

The effect of language input in semantic segmentation and grading of colorectal cancer with language-vision models. ; Kolorektal kanser görüntülerinden segmentasyon ve kanser derecesi teşhisi yapan dil-görme modellerinde dil girdisinin etkisi.

Autoři: Şehlaver, Sina Akbaş, Emre Acar, Ahmet a další

Přispěvatelé: Şehlaver, Sina Akbaş, Emre Acar, Ahmet a další

Témata: Deep Learning, Semantic Segmentation, Colorectal Cancer, Vision-language models, Histopathology, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/110567

Dostupnost: https://hdl.handle.net/11511/110567

ON DISENTANGLED REPRESENTATION LEARNING ; AYRIŞIK GÖSTERİM ÖĞRENME ÜZERİNE

Autoři: MOĞULTAY ÖZCAN, HAZAL Yarman Vural, Fatoş Tunay Kalkan, Sinan a další

Přispěvatelé: MOĞULTAY ÖZCAN, HAZAL Yarman Vural, Fatoş Tunay Kalkan, Sinan a další

Témata: Disentanglement, Representation learning, Disentanglement measure, Hyperparameter optimization, Arbis Subjects::Engineering and Technology::Computer Sciences, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/110813

Dostupnost: https://hdl.handle.net/11511/110813

Real-time joint multi-camera multi-person tracking ; Gerçek zamanlı bütünleşik çoklu kamera çoklu insan takibi

Autoři: Temür, Abdussamet Tarık Akbaş, Emre Department of Computer Engineering

Přispěvatelé: Temür, Abdussamet Tarık Akbaş, Emre Department of Computer Engineering

Témata: Tracking, Multi-Camera, Real-Time, Multi-Object, Re-Id, Arbis Subjects::Engineering and Technology, Arbis Subjects::Engineering and Technology::Computer Sciences, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision

Popis souboru: application/pdf

Relation: https://hdl.handle.net/11511/109774

Dostupnost: https://hdl.handle.net/11511/109774