Computer Graphics & Visual Computing (CGVC) 2023

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/3543876

Browse

Browsing Computer Graphics & Visual Computing (CGVC) 2023 by Subject "Artificial intelligence"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Automatic Balance Assessment Using Smartphone and AI
    (The Eurographics Association, 2023) Sganga, Magalí; Rozmiarek, Patrycja; Ravera, Emiliano; Akanyeti, Otar; Povina, Federico Villagra; Vangorp, Peter; Hunter, David
    Postural control assessment is essential for understanding human biomechanics in both static and dynamic situations. The relationship between the center of mass (CoM), center of pressure (CoP), and the base of support (BoS) determines whether a person is capable to maintain the balance. Inertial motion units (IMUs) are portable and cost-effective devices capable of measuring acceleration and angular velocity. The integration of IMUs into smartphones provides an accessible means of evaluating postural control in the general population without the need for expensive and time-consuming laboratory setups. A convolutional neural network (CNN) architecture will be employed to predict the difference between the CoM and CoP behavior during different tasks with data from an optoelectronic motion capture system combined with instrumented treadmill. This study aims to establish the foundation for developing an application that assesses postural control and balance in both healthy and pathological populations.
  • No Thumbnail Available
    Item
    Investigating Deep Learning for Identification of Crabs and Lobsters on Fishing Boats
    (The Eurographics Association, 2023) Iftikhar, Muhammad; Tiddeman, Bernard; Neal, Marie; Hold, Natalie; Neal, Mark; Vangorp, Peter; Hunter, David
    This paper describes a collaboration between marine and computer scientists to improve fisheries data collection. We evaluate deep learning (DL)-based solutions for identifying crabs and lobsters onboard fishing boats. A custom made electronic camera systems onboard the fishing boats captures the video clips. An automated process of frame extraction is adopted to collect images of crabs and lobsters for training and evaluating DL networks. We train Faster R-CNN, Single Shot Detector (SSD), and You Only Look Once (YOLO) with multiple backbones and input sizes. We also evaluate the efficiency of lightweight models for low-power devices equipped on fishing boats and compare the results of MobileNet-based SSD and YOLO-tiny versions. The models trained with higher input sizes result in lower frames per second (FPS) and vice versa. Base models are more accurate but compromise computational and run time cost. Lighter versions are flexible to install with lower mAP than full models. The pre-trained weights for training models on new datasets have a negligible impact on the results. YOLOv4-tiny is a balanced trade-off between accuracy and speed for object detection for low power devices that is the main step of our proposed pipeline for automated recognition and measurement of crabs and lobsters on fishing boats.