Sökning: "mask r-cnn"

Visar resultat 1 - 5 av 30 uppsatser innehållade orden mask r-cnn.

1. 1. Instance segmentation using 2.5D data

   Master-uppsats, Linköpings universitet/Institutionen för systemteknik

   Författare :Jonathan Öhrling; [2023]
   Nyckelord :instance segmentation; multi-modality; segmentation; multi-modality fusion; CNN; RGBD; ToF; Mask R-CNN; RTMDet; MMDetection; COCO; NYUDepth;

   Sammanfattning : Multi-modality fusion is an area of research that has shown promising results in the domain of 2D and 3D object detection. However, multi-modality fusion methods have largely not been utilized in the domain of instance segmentation. LÄS MER

3. 2. En analys av strukturellafaktorer inom planlösningar : En metod baserad på djupinlärning, för att extrahera information och bedöma samband med lägenhetspriser.

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen Vi3

   Författare :Michiel David Noback; Sara Morén; [2023]
   Nyckelord :;

   Sammanfattning : The housing market is influenced by various factors that impact the pricing of properties. One such factor is the internal layout and structure of the estate, which is typically represented by a floor plan. Real estate agents commonly use floor plans to provide buyers with a comprehensive overview of the property. LÄS MER

4. 3. Towards Large Scale Façade Parsing: A Deep Learning Pipeline Using Mask R-CNN

   Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

   Författare :MOLA AYENEW; [2022-04-27]
   Nyckelord :pipeline; semi-automated; building facade; parsing; panorama imagery; Google Street view; mapillary; Mask R-CNN; deep learning; inference; rectilinear projection;

   Sammanfattning : This thesis tries to find a methodology that create a working pipeline for building facade parsing, which allows to access large scale panorama imagery from Google Street View (GSV) and implement on deep learning models. We propose a semiautomated pipeline that integrates multiple systems for large-scale building facade parsing. LÄS MER

5. 4. Object Detection via Contextual Information

   Master-uppsats, Linköpings universitet/Institutionen för systemteknik

   Författare :Lovisa Stålebrink; [2022]
   Nyckelord :computer vision; machine learning; object detection; deep learning; contextual information; transformers; document object detection; datorseende; maskininlärning; objektdetektion; djupinlärning; kontextuell information; transformer; detektering av dokumentobjekt;

   Sammanfattning : Using computer vision to automatically process and understand images is becoming increasingly popular. One frequently used technique in this area is object detection, where the goal is to both localize and classify objects in images. Today's detection models are accurate, but there is still room for improvement. LÄS MER

7. 5. Detection of Pests in Agriculture Using Machine Learning

   Master-uppsats, Linköpings universitet/Institutionen för systemteknik

   Författare :Emma Olsson; [2022]
   Nyckelord :machine learning; svm; sliding window; mask r-cnn; yolov5;

   Sammanfattning : Pest inventory of a field is a way of knowing when the thresholds for pest controlis reached. It is of increasing interest to use machine learning to automate thisprocess, however, many challenges arise with detection of small insects both intraps and on plants. LÄS MER