Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 25 for “"YOLOv11"”.

  1. AI-assisted Wheat Spike and Spikelet Detection and Density Mapping Using Multiscale Remote Sensing Data to Support Wheat Grain Yield Forecasting

    … spikelet instances from 4,009 spike images. YOLOv11 and YOLOv12 models were then evaluated for spike and spikelet detection and counting. Pretrained YOLOv11 achieved the highest spike detection performance (mAP@0.5 = 0.958) and counting accuracy (Pearson's r = 0.993), whereas the …

    sdstate Repository record for AI-assisted Wheat Spike and Spikelet Detection and Density Mapping Using Multiscale Remote Sensing Data to Support Wheat Grain Yield Forecasting (opens in a new tab)

  2. Ανίχνευση Γραμμών Κειμένου σε Πολυτονικά Ελληνικά Έγγραφα: Συγκριτική Ανάλυση των CRAFT, EAST, PaddleOCR και YOLO

    … μοντέλων ανίχνευσης αντικειμένων YOLO: YOLOv11-seg και YOLOv11-obb. Χρησιμοποιήθηκε ένα επιμελημένο σύνολο δεδομένων από σαρωμένα πολυτονικά ελληνικά χειρόγραφα και έντυπα, με ετικέτες σε επίπεδο γραμμής. Η διαδικασία περιλαμβάνει προεπεξεργασία, εκπαίδευση των μοντέλων και αξιολόγηση …

    athens Repository record for Ανίχνευση Γραμμών Κειμένου σε Πολυτονικά Ελληνικά Έγγραφα: Συγκριτική Ανάλυση των CRAFT, EAST, PaddleOCR και YOLO (opens in a new tab)

  3. Distilled Few-Shot Object Detection for Truck Equipment: Distilling a few-shot state-of-the-art model for truck equipment detection utilizing stable diffusion for data augmentation

    … recent CD-ViTO architecture, to a lightweight YOLOv11 student model. We use Stable Diffusion 3.5 for synthetic image generation with prompt engineering to augment the limited training data. The study evaluates the impact of this approach on accuracy and inference speed. The results show that …

    chalmers Repository record for Distilled Few-Shot Object Detection for Truck Equipment: Distilling a few-shot state-of-the-art model for truck equipment detection utilizing stable diffusion for data augmentation (opens in a new tab)

  4. Nástroj pro automatickou segmentaci a klasifikaci obrazových dat

    … V rámci výzkumu byly vybrány neuronové sítě YOLOv11 a~Mask2Former pro vzájemnou odlišnost v konstrukci jejich modelů. To umožňuje srovnání konvoluční architektury YOLOv11, která je navržena primárně pro detekci v reálném čase, s architekturou Mask2Former, která představuje transformátorovou …

    brno-tech Repository record for Nástroj pro automatickou segmentaci a klasifikaci obrazových dat (opens in a new tab)

  5. Detekce a analýza pohybu zranitelných účastníků silničního provozu

    … a klasifikace je využit model hlubokého učení YOLOv11, který umožňuje přesnou lokalizaci sledovaných entit v rámci dopravní scény. Práce se dále zaměřuje na zpracování dat o pohybu objektů tak, aby byla využitelná pro digitální komunikaci s okolím. Navržený systém vypočítává reálnou polohu a …

    brno-tech Repository record for Detekce a analýza pohybu zranitelných účastníků silničního provozu (opens in a new tab)

  6. Vizuální detekce parazitických roztočů na včelách

    … zahŕňajú architektúru objektového detektora YOLOv11 a architektúru sémantickej segmentácie U-net, pričom oba dosiahli uspokojivé výsledky. Hlavným problémom zostáva presnosť detekcie klieštikov na okrajoch včiel, ktorý však bude možné riešiť súčasným osvetlením oboch vlnových dĺžok.

    brno-tech Repository record for Vizuální detekce parazitických roztočů na včelách (opens in a new tab)

  7. Analýza videa a vyhledávání málo četných událostí

    … na detekciu objektov, ako je YOLO a jeho verzia YOLOv11. Na rozpoznávanie činností som následne nasadil pokročilý multimodálny model X-CLIP. Pre účely sledovania objektov som skúmal algoritmy, ako SORT, DeepSORT, ByteTrack a BoT-SORT. Dôležitou súčasťou práce bol aj vývoj užívateľského rozhrania …

    brno-tech Repository record for Analýza videa a vyhledávání málo četných událostí (opens in a new tab)

  8. AI-Based Framework for Identifying Wood Burning Appliances through Chimney Recognition

    … rural areas, we trained object detection models (YOLOv11) and integrated them with Vision Language Models (VLMs) for semantic verification. This two-stage pipeline substantially improves detection accuracy over YOLO alone. In the urban Fall Creek neighborhood, the YOLO+VLMs approach achieved an …

    cornell Repository record for AI-Based Framework for Identifying Wood Burning Appliances through Chimney Recognition (opens in a new tab)

  9. Analýza panoramatických rentgenových snímků pomocí hlubokého učení

    … úlohy. Experimenty ukazujú, že model YOLOv11 vo veľkosti medium predtrénovaný na COCO datasete poskytuje najlepšie výsledky. Ďalej sa ukazuje, že predtrénovanie na príbuzných úlohách, ako je detekcia všetkých zubov, môže zlepšiť výsledky na hlavnej úlohe, zatiaľ čo menej príbuzné …

    brno-tech Repository record for Analýza panoramatických rentgenových snímků pomocí hlubokého učení (opens in a new tab)

  10. Image-based Weed Detection in Soybean using Machine Learning Algorithms

    … You Only Look Once (YOLO) architectures (YOLOv8–YOLOv11; nano, small, and medium variants) with 10-fold cross-validation. All models achieved mAP@50 values above 85%, with YOLOv9-small and YOLOv11- medium reaching 88.4%, while YOLOv8-nano provided the fastest inference (6.5 ms per image on an …

    vt Repository record for Image-based Weed Detection in Soybean using Machine Learning Algorithms (opens in a new tab)

  11. Comparative Analysis of Traffic Sign Tracking Methods: From Classical Trackers to Temporal YOLO Extensions and Trajectory Optimization

    … association-based algorithms, and a proposed YOLOv11-based tracker augmented with an appearance-embedding head. Two post-tracking refinement modules—CoTracker for reconnecting fragmented trajectories and a position-based graph smoothing method for identity cleanup—are also evaluated. …

    gatech Repository record for Comparative Analysis of Traffic Sign Tracking Methods: From Classical Trackers to Temporal YOLO Extensions and Trajectory Optimization (opens in a new tab)

  12. Diseño de un Sistema de Selección Automatizada de Granos de Café para el Control de Calidad Postueste Basado en Modelos Avanzados de Visión por Computadora

    … integra modelos avanzados de Deep Learning, YOLOv11 para detección y segmentación, y EfficientNet-B0 para clasificación, desplegados en una plataforma Jetson Nano, junto con un sistema electromecánico de dosificación y separación física de los granos. Se propone además un algoritmo de …

    upc-peru Repository record for Diseño de un Sistema de Selección Automatizada de Granos de Café para el Control de Calidad Postueste Basado en Modelos Avanzados de Visión por Computadora (opens in a new tab)

  13. A Synthetic Image Generation and Deep Learning Framework for Entrained Droplet Detection

    … GeForce RTX 3050 Ti GPU compared the YOLOv8 and YOLOv11 nano segmentation architectures and identified an exclusion threshold of 0.6 as optimal for a 1.0 mm depth-of-field selection. An additional campaign on the Virginia Tech Advanced Research Computing Tinkercliffs cluster trained the YOLOv11 …

    vt Repository record for A Synthetic Image Generation and Deep Learning Framework for Entrained Droplet Detection (opens in a new tab)

  14. WORMML: A UNIVERSAL DEEP LEARNING PIPELINE FOR CROSS-PLATFORM C. ELEGANS DETECTION AND COUNTING

    … pipeline includes camera-specific preprocessing, YOLOv11-L object detection, and comprehensive benchmarking using Hungarian Matching. It was validated on three in-house imaging platforms (OG, custom-built), Tau (dark-field, commercial), and LoopBio (bright-field, commercial) and an external …

    jhu Repository record for WORMML: A UNIVERSAL DEEP LEARNING PIPELINE FOR CROSS-PLATFORM C. ELEGANS DETECTION AND COUNTING (opens in a new tab)

  15. Development and Validation of Low-Cost, High-Frequency Framework for Automated Pavement Monitoring using Deep Learning

    … monitoring. The end-to-end pipeline integrates a YOLOv11-seg model for distress and lane instance segmentation, the ByteTrack algorithm for multi-object tracking, and an Inverse Perspective Mapping (IPM) model for geometric correction and quantification of distress area and location. A new, …

    ttu Repository record for Development and Validation of Low-Cost, High-Frequency Framework for Automated Pavement Monitoring using Deep Learning (opens in a new tab)

  16. Enhancing Infrastructure Monitoring with Calibrated Vision Language Model Ensembles: A Graffiti Detection Case Study

    … automatically defines inspection boundaries, (2) YOLOv11-powered detection optimized for transit infrastructure, and (3) damage assessment using a specialized Vision Language Model (VLM) ensemble. Our ensemble approach employs probability calibration and weight optimization, outperforming …

    unr Repository record for Enhancing Infrastructure Monitoring with Calibrated Vision Language Model Ensembles: A Graffiti Detection Case Study (opens in a new tab)

  17. Using machine learning methods to estimate spruce tree crown and DBH from aerial imagery

    … aerial images. Compared to the second method YOLOv11 that uses instance segmentation to segment the trees. A study is conducted to showcase a relationship between TCD and DBH of the field measurements. This linear relationship can be used to estimate DBH out of TCD and then could futher …

    regina Repository record for Using machine learning methods to estimate spruce tree crown and DBH from aerial imagery (opens in a new tab)

  18. Automated Height Adjustment for Truck-Trailer Coupling

    … detection, locating corners, utilizing the YOLOv11 pose estimation model. We explore two different methods for calculating distance and then utilize this information to calculate the height difference between the trailer and the fifth wheel of the truck. The first method is based on assuming …

    chalmers Repository record for Automated Height Adjustment for Truck-Trailer Coupling (opens in a new tab)

  19. Addressing low-data regimes in Australian wildlife recognition from camera trap images using modern computer vision

    … a state-of-the-art object detection framework, YOLOv11, across varying numbers of training images per class. Results indicated that model performance improvements began to plateau between approximately 250 and 500 images per class, suggesting diminishing returns beyond this threshold. Next, …

    unsw Repository record for Addressing low-data regimes in Australian wildlife recognition from camera trap images using modern computer vision (opens in a new tab)

  20. WEIGHTED EFFECT OF CONCENTRATED CRACKING ON THE STRUCTURAL INTEGRITY OF CONCRETE BRIDGE DECKS

    … and analyzed using deep-learning algorithms, YOLOv11. Then, the Crack Concentration Index (CCI) is calculated for each sample, defined as the ratio of crack areas (length × width) to the boundary area of the cracks. Statistical analysis is conducted to identify the relationships between …

    wvu Repository record for WEIGHTED EFFECT OF CONCENTRATED CRACKING ON THE STRUCTURAL INTEGRITY OF CONCRETE BRIDGE DECKS (opens in a new tab)

Page 1 of 2