Dissertation > Excellent graduate degree dissertation topics show

Spatio-Temporal Interest Points (STIP) Based Method of Recognizing Human Action

Author: MaZuo
Tutor: GuoFeng
School: Xiamen University
Course: Computer technology
Keywords: Human action recognition Spatio-Temporal Interest Points Visualcodebook Motion difference feature
CLC: TP391.41
Type: Master's thesis
Year: 2014
Downloads: 6
Quote: 0
Read: Download Dissertation

Abstract


Human action recognition is an active and challenging area of research in the field of computer vision. It can be applied in many applications, including video surveillance, intelligent vehicles, sport video event analysis and video retrieval. So there is important theoretical and practical value to carry out research on human action recognition.This thesis focus on the local Spatio-Temporal Interest Points (STIP) based method of recognizing human action. For the problems of human action recognition in complex scene, based on a comprehensive survey of the state-of-the-art of human action recognition, the major works and contributions are summarized as follows.1. Summarize existing human action recognition methods. Access to a large literature, existing human action recognition methods based on STIP are outlined. The widely used STIP detector and descriptor have been illustrated in detail.2. Implement visual codebook based on human action recognition Approach. Visual codebook based approach is the primary method of target recognition. First, using clustering algorithm to build visual codebook; and the video is represented as visual codebook feature; finally, use SVM to classify the video. Meanwhile, the work in this thesis compares the performance of different features in a complex dataset.3. Proposed motion difference flow based human action recognition method. Currently in recognizing human action, the motion descriptor is based on the optical flow estimation in video. In complex scene, due to camera motion, object motion and other reasons, the motion estimation has some deviation. To end this, motion difference flow is proposed to represent motion feature of STIP. Experimental results verify that the proposed method is more accurate than existing action recognition methods.

Related Dissertations

  1. Vision-based Human Movement Analysis,TP391.41
  2. Human Action Recognition Based on Delaunay Skeleton Model,TP391.41
  3. The Study of Vision-based Human Action Recognition,TP391.41
  4. Human Pose Estimation and Action Recognition from Image Sequences,TP391.41
  5. Research on Hierarchical Approaches Based Complex Human Action Recognition,TP391.41
  6. Research and Implement of Flame Detection Technology Based on Bag of Features,TP391.41
  7. Human Action Recognition Based on Random Fields,TP391.41
  8. A Human-computer Interaction System Using Single Camera,TP11
  9. Phase Congruency Based Human Action Recognition and Classification,TN919.8
  10. Research on Action Recognition Based on Improved Spatio-temporal Features,TP391.41
  11. Human Action Recognition System in Video Image Sequence,TP391.41
  12. Key Technology Research on Motion Capture Based on Videos,TP391.41
  13. Research on Human Action Recognition Based on Audio-Visual Information,TP391.41
  14. Research on the Tracking Method Based on Meanshift for Human-Object on Video,TP391.41
  15. Research on Unsupervised Activity Recognition Based on Spatio-Temporal Interest Points,TP391.41
  16. Human Action Recognition in Video Surveillances,TP391.41
  17. Video-based Human Action Recognition,TP391.41
  18. Research and Implementation of the Special Population Abnormal Behavior Analysis and Recognition,TP391.41
  19. Human Motion Representation and Recognition Based on Video,TP391.41
  20. Research on Action Recognition Based on Spatio-temporal Features,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