Sökning: "objektigenkänning"

Visar resultat 1 - 5 av 13 uppsatser innehållade ordet objektigenkänning.

  1. 1. Latent Space Growing of Generative Adversarial Networks

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Erik Sandström; [2019]
    Nyckelord :Generative models; GAN; Generative Adversarial Networks; Artificial Intelligence; CelebA; Latent Space; Deep Learning; Computer Vision; Machine Learning; Mathematics and Statistics;

    Sammanfattning : This thesis presents a system, which builds on the Generative Adversarial Network (GAN) framework, with the focus of learning interpretable representations of data. The system is able to learn representations of data that are ordered in regards to the saliency of the attributes, in a completely unsupervised manner. LÄS MER

  2. 2. Comparing normal estimation methods for the rendering of unorganized point clouds

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Ingemar Markström; [2019]
    Nyckelord :;

    Sammanfattning : Surface normals are fundamental in computer graphics applications such as computer vision, object recognition, and lighting calculations. When working with unorganized point clouds of surfaces, there exists a need for fast and accurate normal estimation methods. LÄS MER

  3. 3. Evaluating rain removal image processing solutions for fast and accurate object detection

    Master-uppsats, KTH/Mekatronik; KTH/Mekatronik

    Författare :Tugay Köylüoglu; Lukas Hennicks; [2019]
    Nyckelord :object detection; failure modes; autonomous vehicles; objektigenkänning; felmodell; autonoma fordon;

    Sammanfattning : Autonomous vehicles are an important topic in modern day research, both for the private and public sector. One of the reasons why self-driving cars have not yet reached consumer market is because of levels of uncertainty. This is often tackled with multiple sensors of different kinds which helps gaining robust- ness in the vehicle’s system. LÄS MER

  4. 4. Mobile Object Detection using TensorFlow Lite and Transfer Learning

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Oscar Alsing; [2018]
    Nyckelord :cnn; convolutional neural networks; transfer learning; mobile object detection;

    Sammanfattning : With the advancement in deep learning in the past few years, we are able to create complex machine learning models for detecting objects in images, regardless of the characteristics of the objects to be detected. This development has enabled engineers to replace existing heuristics-based systems in favour of machine learning models with superior performance. LÄS MER

  5. 5. A Combined Approach for Object Recognition and Localisation for an Autonomous Racecar

    Master-uppsats, KTH/Maskinkonstruktion (Inst.); KTH/Maskinkonstruktion (Inst.)

    Författare :Jonathan Cressell; Isac Törnberg; [2018]
    Nyckelord :;

    Sammanfattning : With autonomous vehicles being a hot topic for research it has also become an interest in theworld of motor sport. To be able to run a vehicle autonomously it needs to know what the currentpose of the vehicle is and what the environment looks like. LÄS MER