Title page for etd-0809115-151233


[Back to Results | New Search]

URN etd-0809115-151233
Author Szu-Cheng Shen
Author's Email Address No Public.
Statistics This thesis had been viewed 5359 times. Download 164 times.
Department Computer Science and Engineering
Year 2014
Semester 2
Degree Master
Type of Document
Language English
Title Event Detection and Video Summarization for Parking Lot Surveillance
Date of Defense 2015-07-22
Page Count 52
Keyword
  • Event Detection
  • Video Summarization
  • Video Skimming
  • Abstract Surveillance cameras are around everywhere in public. It is nearly impossible to keep watching over these monitors by human. Thus, detecting abnormal situation automatically is of paramount importance. When an incident happens, it is time consuming and inefficient to watch a whole surveillance video. Thus video summarization is needed for investigating the incident. The shortened length of the video summary and the importance of the content will be significantly influence the efficiency of investigating the incident. In this thesis, we proposed an event detection and video summarization system for parking lot surveillance. The system conducts moving object detection, object tracking, event detection and classification method  to detect, report and record all events in the surveillance video. The definition of basic and advanced events can make the summary video meet a user’s need. According to experimental results, 8 basic events and 4 special events can be correctly detected and recorded. The accuracy of video summarization is 97% based on the experiment.
    Advisory Committee
  • Chiou-Shann Fuh - chair
  • Yi-Wu Chiang - co-chair
  • Jenn-Jier Lien - co-chair
  • Shu-Mei Guo - co-chair
  • Chung-Nan Lee - advisor
  • Files
  • etd-0809115-151233.pdf
  • Indicate in-campus at 2 year and off-campus access at 2 year.
    Date of Submission 2015-09-09

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have more questions or technical problems, please contact eThesys