Dissertation > Excellent graduate degree dissertation topics show

Near-duplicate Detection in Large Scale Video Dataset

Author: GuoDingYun
Tutor: QiMeiBin
School: Hefei University of Technology
Course: Communication and Information System
Keywords: Near-duplicate video detection Temporal consistency feature Overlapped image blocking SURF K-d tree indexing structure
CLC: TP391.41
Type: Master's thesis
Year: 2013
Downloads: 4
Quote: 0
Read: Download Dissertation

Abstract


In recent years, near-duplicate video detection has become an active researchin video retrieval, and also has broad application prospects in copyright protection,video surveillance and topic detection and tracking. Given its applicationrequirements, it is quite necessary to research a near-duplicate video detectionalgorithm with higher accuracy and faster detection speed. In this thesis, majorwork for the goals and requirements are completed as follows:1. The overview of the research significance, research status at home andabroad of near-duplicate video detection and the existing three algorithms is given.The implement steps of near-duplicate video detection are introduced after the keytechnologies of image similarity detection. Shot boundary detection, key frameextraction, feature extraction and indexing structure are introduced in details.2. A cascaded near-duplicate video detection algorithm with temporalconsistency feature in the shot level is proposed. After a further study based on theanalysis of the existing algorithms, we borrow ideas from combining global andlocal features to get a cascaded detection. We define a new temporal consistencyfeature to represent the shot based on the inherent continuous consistency of videosequences. we first extract the temporal consistency features in the shot levelbefore we extract features of key frames to preliminarily filter out some videosdissimilar with the query video. Then we combine global and local features tofurther accurately detect the remaining videos.3. We use the improved edge contour difference method to detect shotboundaries. An overlapped image blocking method and the SURF algorithm areintroduced to extract global and local features respectively for better accuracy. Wealso use the k-d tree indexing structure to achieve fast nearest neighbor search.Through three forms of experiments, we verify the usefulness and accuracy ofthe proposed method. We experiment the near-duplicate video detection on thelarge scale video dataset CC_WEB_VIDEO. From the performance comparisonswith the existing three commonly used methods and the analysis results, theproposed method can achieve better detection accuracy, especially for the videoswith complex motion scenes and great frame changes.

Related Dissertations

  1. Studies of Technologies and Methods on Image Mosaic,TP391.41
  2. Research on Panorama Stitching Based on Speeded Up Robust Features,TP391.41
  3. Research on Video Forgery Passive Detection Based on Spatial-Temporal Feature,TP391.41
  4. Stereo Vision Based Tracking and Detection System for Serial Robot,TP242
  5. SURF algorithm based on multiple images of three-dimensional model reconstruction method,TP391.41
  6. SURF algorithm based on improved electronic image stabilization technology,TP391.41
  7. The mobile robot based on three-dimensional laser ranging Scene Recognition,TP242
  8. SURF feature based on monocular vision SLAM Research and Implementation,TP242
  9. Missile seeker television image matching algorithm,TP391.41
  10. A class of visual perception and control of mobile robot technology research,TP242
  11. Research on Moving Target Tracking Technology in Video Images,TP391.41
  12. The Study of Target Positioning Technology Based on UAV Image Sequence,TP391.41
  13. Panoramic Image Mosaic Based on SURF Feature Matchning Algorithm,TP391.41
  14. Research and Application on Invariant Feature Points of MMS Image Retrieval,TP391.41
  15. Study on Colored Image Registration Based on Feature,TP391.41
  16. Characteristic Comparison of Fish Larval and Juvenile Assemblages between the Surf Zones of South Branch of Yangtze River Estuary and North Coast of Hangzhou Bay,S931
  17. Mobile Robot Object Recognition and Localization Based on Monocular Vision,TP242.6
  18. Research on Key Technology of Local Blind Image Navigation Based on Scene Matching,TP391.41
  19. Design and Implementation of Parallel Image Matching Algorithm Based on MDSP,TP391.41
  20. Research on Vision Based Odometer for Indoor Mobile Robot,TP242.6
  21. Design and Implementation of Cloud-based Rapid Object Recognition,TP391.41

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile