• Text detection in natural images using convolutional neural networks 

      Grond, Marco Marten (Stellenbosch : Stellenbosch University, 2017-03)
      ENGLISH ABSTRACT : In this study we attempt to solve the problem of text detection in natural images. This requires us to identify regions in a natural image that contain text. Possible applications range from assistive ...
    • Thermal and colour data fusion for people detection and tracking 

      Joubert, Pierre (Stellenbosch : Stellenbosch University, 2014-04)
      ENGLISH ABSTRACT: In this thesiswe approach the problem of tracking multiple people individually in a video sequence. Automatic object detection and tracking is non-trivial as humans have complex and mostly unpredictable ...
    • Time series analysis of data measured in the nearshore area 

      Mphasha, Rosa (Stellenbosch : Stellenbosch University, 2016-03)
      ENGLISH ABSTRACT : Factors that lead to the generation of currents in the nearshore area within the Natal Bight were investigated. The investigation was carried out on data that spans from the 6th June 2012 to the 16th ...
    • Tracking with context 

      Du Toit, Carlo (Stellenbosch : Stellenbosch University, 2016-12-01)
      ENGLISH ABSTRACT : Tracking in an unconstrained environment presents a difficult challenge. Abrupt object motion, appearance changes, non-rigid objects and occlusion are but a few of the trials faced. To overcome these ...
    • Transcriptomic profile based cancer disease prediction and patient survival time differentiation 

      Ofosu Mensah, Samuel (Stellenbosch : Stellenbosch University, 2018-12)
      ENGLISH ABSTRACT : Cancer disease is an abnormal growth of cells, which may be caused by mutations in genes which, as a result, alter the way cells function mainly in the way they grow and divide. Cancer cells are regulated ...
    • Video classification using deep learning 

      Newman, Gregory (Stellenbosch : Stellenbosch University., 2020-03)
      ENGLISH ABSTRACT: To help analyse, classify, and monitor video data we need scalable algorithms that can handle video sequences of various lengths. Existing approaches tend to be both computationally expensive and ...