Dissertation > Excellent graduate degree dissertation topics show

Research on Unsupervised Activity Recognition Based on Spatio-Temporal Interest Points

Author: ZuoYueZuo
Tutor: LiYiBo
School:
Course: Pattern Recognition and Intelligent Systems
Keywords: spatio-temporal interest points region of interest double bags of words probabilistic latent semantic analysis activity recognition
CLC: TP391.41
Type: Master's thesis
Year: 2013
Downloads: 81
Quote: 0
Read: Download Dissertation

Abstract


Human activity recognition is already one of the important research areas in the domainof computer vision and pattern recognition. In recent years, human activity recognitiontechnique has made remarkable progress and has broad application prospects and economicbenefits in the fields of human production, life and scientific research and other high-techfields. Activity recognition is applied to many domains, such as intelligent video surveillance,visual reality, human-computer interface and motion analysis. This paper mainly solve theproblems of activity representation and activity recognition based on spatio-temporal interestpoints, including the detection of spatio-temporal interest points, spatio-temporal interestpoints descriptor, and activity recognition system based on the unsupervised model.In the detection of spatio-temporal interest points, the objective function of the detectionalgorithm is influenced by the change of light intensity easily. Spatio-temporal interest pointsmay be detected in the background by mistake. This paper proposes a novel detectionalgorithm of spatio-temporal interest points based on the region of interest. On the basis offoreground interest region extracted, dense spatio-temporal interest points are obtained by theseparable linear filter method.In terms of the feature description, as bag of words model ignores the spatial andtemporal correlation between features, a novel four-dimensional relative coordinate featuredescriptor is proposed in this paper. The feature is combined with3D-SIFT descriptor torepresent the activity. The method can effectively solve the problem, which is a single bag ofwords cannot reflect the spatial and temporal position relation of the keywords. Then,k-means clustering algorithm is employed to generate double codebooks, which are thefour-dimensional relative coordinate codebook and the3D-SIFT codebook. Finally, theunsupervised probabilistic latent semantic analysis model is used to recognize activity.Experiment results on two activity datasets are provided to demonstrate theeffectiveness.

Related Dissertations

  1. Diffusion Tensor Imaging Study of Idiopathic Epilepsy at 3.0T High Field Magnetic Resonance Scaner,R445.2
  2. The Research of Medical Image Fusion Algorithm Based on Level Set Regions Segmentation,TP391.41
  3. Study on Extraction Methods of Image Interesting Regions,TP391.41
  4. Research on Detection and Recognition of Vision-based Human Activity,TP391.41
  5. Acceleration of X-ray Computed Tomography Reconstruction for Rice Tiller,TP391.41
  6. Multi-Class Object Recognition in High Resolution Remote Sensing Images,TP751
  7. Improved ROI Coding Method Based on SPIHT,TN919.81
  8. Finding Web Services Based on Clustering Probabilistic Semantic Approach,TP393.09
  9. Study and Application of Safety Monitoring System for Smart Home Based on Wireless Sensor Networks,TP273.5
  10. The Study on Multi-Focus Textile Fiber Images Fusion Technology,TP391.41
  11. Research of Image Processing for Seam Track Based on Laser Optical Sensor with Structured Light,TP391.41
  12. Emotional background music for movies Classification Method,TP391.1
  13. Based on the model and features of the package ML_pLSA Target Recognition Algorithm,TP391.41
  14. Research on Human Behavior Identification Technology,TP391.41
  15. Research on Multi-Information Collecting System for Individual Fireman,TP274.2
  16. Research on Mining Techniques of Product Reviews Base on Semantic Analysis,TP391.1
  17. Scenario-based semantic image annotation key technology research,TP391.41
  18. Latent Semantic Analysis in Language Identification,TN912.34
  19. Research on Automatic Construction of Knowledge Tree in Knowledge Management System,G301
  20. Research on Opinion Mining of Automobile Reviews Based on Web,U462
  21. Semantic Analysis of Text Based on Emotional Classification,TP391.1

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