Sökning: "Discriminative correlation filter"

Hittade 4 uppsatser innehållade orden Discriminative correlation filter.

  1. 1. Visual Tracking with Deep Learning : Automatic tracking of farm animals

    Master-uppsats, KTH/Radio Systems Laboratory (RS Lab)

    Författare :Biwen Zhu; [2018]
    Nyckelord :Computer vision; Video tracking; Machine learning; Discriminative correlation filter; Compressed video; Bandwidth balancing; Network traffic; Dator vision; Video spårning; Maskininlärning; Diskriminerande korrelationsfilter; Komprimerad video; Bandbredd balansering; Nätverkstrafik;

    Sammanfattning : Automatic tracking and video of surveillance on a farm could help to support farm management. In this project, an automated detection system is used to detect sows in surveillance videos. This system is based upon deep learning and computer vision methods. LÄS MER

  2. 2. Visual Tracking with Deformable Continuous Convolution Operators

    Master-uppsats, Linköpings universitet/Datorseende

    Författare :Joakim Johnander; [2017]
    Nyckelord :Visual Tracking; Discriminative Correlation Filters; DCF; Deformable Filters; Computer Vision; Filter Optimization;

    Sammanfattning : Visual Object Tracking is the computer vision problem of estimating a target trajectory in a video given only its initial state. A visual tracker often acts as a component in the intelligent vision systems seen in for instance surveillance, autonomous vehicles or robots, and unmanned aerial vehicles. LÄS MER

  3. 3. Improving Discriminative Correlation Filters for Visual Tracking

    Master-uppsats, Linköpings universitet/Datorseende

    Författare :Gustav Häger; [2015]
    Nyckelord :Tracking; Computer vision;

    Sammanfattning : Generic visual tracking is one of the classical problems in computer vision. In this problem, no prior knowledge of the target is available aside from a bounding box in the initial frame of the sequence. LÄS MER

  4. 4. Determining Attribute Importance Using an Ensemble of Genetic Programs and Permutation Tests : Relevansbestämning av attribut med hjälp av genetiska program och permutationstester

    Master-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Ivert Annica; [2015]
    Nyckelord :Genetic programming; attribute selection; permutation test; Genetisk programmering; atttribut; relevansbestämning; permutationstest;

    Sammanfattning : When classifying high-dimensional data, a lot can be gained, in terms of both computational time and precision, by only considering the most important features. Many feature selection methods are based on the assumption that important features are highly correlated with their corresponding classes, but mainly uncorrelated with each other. LÄS MER