Thesis Details

Sharing Local Information for Faster Scanning-Window Object Detection

Ph.D. Thesis Student: Hradiš Michal Academic Year: 2014/2015 Supervisor: Zemčík Pavel, prof. Dr. Ing.
Czech title
Sdílení lokální informace pro rychlejší detekci objektů
Language
English
Abstract

This thesis aims to improve existing scanning-window object detectors by exploiting information shared among neighboring image windows. This goal is realized by two novel methods which are build on the ideas of Wald's Sequential Probability Ratio Test and WaldBoost. Early non-Maxima Suppression moves non-maxima suppression decisions from a post-processing step to an early classification phase in order to make the decisions as soon as possible and thus avoid normally wasted computations. Neighborhood suppression enhances existing detectors with an ability to suppress evaluation at overlapping positions. The proposed methods are applicable to a wide range of detectors. Experiments show that both methods provide significantly better speed-precision trade-off compared to state-of-the-art WaldBoost detectors which process image windows independently. Additionally, the thesis presents results of extensive experiments which evaluate commonly used image features in several detection tasks and scenarios.

Keywords

Object detection, AdaBoost, WaldBoost, EnMS, neighborhood suppression, scanning-window

Department
Degree Programme
Information Technology, Field of Study Information Technology
Files
Status
defended
Date
19 December 2014
Citation
HRADIŠ, Michal. Sharing Local Information for Faster Scanning-Window Object Detection. Brno, 2014. Ph.D. Thesis. Brno University of Technology, Faculty of Information Technology. 2014-12-19. Supervised by Zemčík Pavel. Available from: https://www.fit.vut.cz/study/phd-thesis/257/
BibTeX
@phdthesis{FITPT257,
    author = "Michal Hradi\v{s}",
    type = "Ph.D. thesis",
    title = "Sharing Local Information for Faster Scanning-Window Object Detection",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2014,
    location = "Brno, CZ",
    language = "english",
    url = "https://www.fit.vut.cz/study/phd-thesis/257/"
}
Back to top