Faculty of Technoscience

Permanent URI for this community

https://dir.muni.ac.ug/handle/20.500.12260/2

Browse

Browsing Faculty of Technoscience by Subject "Classification"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Design a hybrid approach for the classification and recognition of traffic signs using machine learning
    (Wasit Journal of Computer and Mathematics Science, 2023-07) Ali, Guma; Sadıkoğlu, Emre; Abdelhak, Hatim
    Advanced Driver Assistance Systems (ADAS) are a fundamental part of various vehicles, and the automatic classification of traffic signs is a crucial component. A traffic image is classified based on its recognizable features. Traffic signs are designed with specific shapes and colours, along with text and symbols that are highly contrasted with their surroundings. This paper proposes a hybrid approach for classifying traffic signs by combining SIFT with SVM for training and classification. There are four phases to the proposed work: pre-processing, feature extraction, training, and classification. A real traffic sign image is used for classification in the proposed framework, and MATLAB is used to implement the framework
  • Thumbnail Image
    Item
    Reviewing the pertinence of Sentinel-1 SAR for urban land use land cover classification
    (International Journal of Scientific & Engineering Research, 2020-05) Abudu, Dan; Parvin, Nigar Sultana; Andogah, Geoffrey
    Conventional approaches for urban land use land cover classification and quantification of land use changes have often relied on the ground surveys and urban censuses of urban surface properties. Advent of Remote Sensing technology supporting metric to centimetric spatial resolutions with simultaneous wide coverage, significantly reduced huge operational costs previously encountered using ground surveys. Weather, sensor’s spatial resolution and the complex compositions of urban areas comprising concrete, metallic, water, bare- and vegetation-covers, limits Remote Sensing ability to accurately discriminate urban features. The launch of Sentinel-1 Synthetic Aperture Radar, which operates at metric resolution and microwave frequencies evades the weather limitations and has been reported to accurately quantify urban compositions. This paper assessed the feasibility of Sentinel-1 SAR data for urban land use land cover classification by reviewing research papers that utilised these data. The review found that since 2014, 11 studies have specifically utilised the datasets. The reviewed studies demonstrated that, features representing urban topography such as morphology and texture can easily and accurately be extracted from Sentinel-1 SAR and subjected to state-of-the-art classification algorithms such as Support Vector Machine and ensemble Decision Trees for accurate urban land use land cover classification. Development of robust algorithms to deal with the complexities of SAR imagery is still an active research area. Furthermore, augmentation of SAR with optical imagery is required especially for classification accuracy assessments.