Essays about: "Datorseende"

Showing result 1 - 5 of 237 essays containing the word Datorseende.

  1. 1. Pose Classification of Horse Behavior in Video : A deep learning approach for classifying equine poses based on 2D keypoints

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Michaela Söderström; [2021]
    Keywords : Deep Learning; Computer Visison; Horse behavior; Pose estimation; 2D key- points; Pose classification; DeepLabCut; Djupinlärning; Datorseende; Hästbeteende; Pose-estimering; Nyckelpunkter; Intressepunkter; Pose-klassificering; DeepLabCut;

    Abstract : This thesis investigates whether Computer Vision can be a useful tool in interpreting the behaviors of monitored horses. In recent years, research in the field of Computer Vision has primarily focused on people, where pose estimation and action recognition are popular research areas. READ MORE

  2. 2. Detecting Slag Formation with Deep Learning Methods : An experimental study of different deep learning image segmentation models

    University essay from Linköpings universitet/Datorseende

    Author : Christian von Koch; William Anzén; [2021]
    Keywords : deep learning; deep neural network; computer vision; image segmentation; iron ore pelletising plant; furnace slag-detection; U-Net; PSPNet;

    Abstract : Image segmentation through neural networks and deep learning have, in the recent decade, become a successful tool for automated decision-making. For Luossavaara-Kiirunavaara Aktiebolag (LKAB), this means identifying the amount of slag inside a furnace through computer vision. READ MORE

  3. 3. Image-to-Image Translation for Improvement of Synthetic Thermal Infrared Training Data Using Generative Adversarial Networks

    University essay from Linköpings universitet/Datorseende

    Author : Hanna Hamrell; [2021]
    Keywords : machine learning; deep learning; image-to-image translation; image processing; generative adversarial networks; infrared images; computer vision;

    Abstract : Training data is an essential ingredient within supervised learning, yet time con-suming, expensive and for some applications impossible to retrieve. Thus it isof interest to use synthetic training data. However, the domain shift of syntheticdata makes it challenging to obtain good results when used as training data fordeep learning models. READ MORE

  4. 4. Efficient Recycling Of Non-Ferrous Materials Using Cross-Modal Knowledge Distillation

    University essay from Linköpings universitet/Datorseende

    Author : Sebastian Brundin; Adam Gräns; [2021]
    Keywords : Recycling; Ferrous; Non-Ferrous; Knowledge Distillation; Hallucinogenic; Hyperspectral; HSI ;

    Abstract : This thesis investigates the possibility of utilizing data from multiple modalities to enable an automated recycling system to separate ferrous from non-ferrous debris. The two methods sensor fusion and hallucinogenic sensor fusion were implemented in a four-step approach of deep CNNs. READ MORE

  5. 5. Computer Vision for Camera Trap Footage : Comparing classification with object detection

    University essay from Uppsala universitet/Avdelningen för visuell information och interaktion

    Author : Fredrik Örn; [2021]
    Keywords : computer vision; camera traps; classification; object detection; neural networks; artificial intelligence; machine learning; datorseende; kamerafällor; klassificering; detektering; neurala nätverk; artificiell intelligens; maskininlärning;

    Abstract : Monitoring wildlife is of great interest to ecologists and is arguably even more important in the Arctic, the region in focus for the research network INTERACT, where the effects of climate change are greater than on the rest of the planet. This master thesis studies how artificial intelligence (AI) and computer vision can be used together with camera traps to achieve an effective way to monitor populations. READ MORE