Dissertation > Excellent graduate degree dissertation topics show

Learning Based Structured Image Model Extraction and Tracking

Author: ZhengDaYu
Tutor: XiongHongKai
School: Shanghai Jiaotong University
Course: Communication and Information System
Keywords: structured graph matching learning-based graphmatching multiple object tracking Gaussian process high dimen-sion feature extraction
CLC: TP391.41
Type: Master's thesis
Year: 2012
Downloads: 130
Quote: 0
Read: Download Dissertation

Abstract


With the rapid development of information technology, most researchers are fo-cused on computer vision which is one of the most popular fields. Object tracking isa major problem in computer vision and also a hard problem to solve. Lots of effortshave been made and plenty of algorithms have been developed according to differentkinds of research background. However, there is no general solution and universaltheory till now.To describe the structure feature is an important problem in image analysis andobject tracking. A lot of related researches only take the local feature of the targetobjects, but not make use of the structure feature (the corresponding relationship ofdifferent objects) in the images. It is the problem this paper focused on.In this paper, structure feature is introduced into the traditional graph model, anda novel structured graph model is defined in the paper. In order to obtain a betterperformance, the proposed approach can make use of the corresponding relationshipof multiple objects, which is the edge feature of the structured graph model. The maincontributions of this paper are in two aspects.First, in the multiple object tracking problem, we define the structure feature ofthe graph model. Therefore, a structured graph matching model is established, and theproblem is regarded as structured node and edge matching between graphs generatedfrom successive frames. In essence, it is formulated as the maximum weighted bipar-tite matching problem to be solved using the dynamic Hungarian algorithm, which isapplicable of optimally solving the assignment problem in situations with changingedge costs or weights. In the proposed graph matching model, the parameters of thestructured graph matching model are determined in a stochastic learning process. Inorder to improve the tracking performance, the bilateral tracking is also used. Secondly, in tubular structure tracking problem, original dataset is transformedto a virtual superellipsoid with non-uniform density where the components of datasetand the local topology of tubular objects are equivalent to the inferred weights of thekernel-based model. Therefore, a structured 3D tubular tracking model is established,and the problem is regarded as maximizing the prediction energy. In order to improvethe performance, Gaussian process (GP) and unscented Kalman Filter (UKF) are in-troduced into the nonlinear prediction phase. GP can provide uncertainty estimatesand learn noise and smoothness parameters from dataset, and UKF can be utilized inthe tubular structure extraction problem.Extensive experimental results demonstrate that the proposed approaches not on-ly take the target feature into account, but also make use of the structure feature inthe images. Different from the traditional approaches, the structured graph model is abetter description of the whole graph. Therefore, the proposed approach gains a betterperformance.

Related Dissertations

  1. The Research of Online Modeling Based on Gaussian Process,TP181
  2. Research on Combination Model for Short-term Load Forecasting Based on EMD and GP Regression Theory,TM715
  3. Karhunen-Loeve Expansions and Positive Definite of Covariance Function of Gaussian Process,O211.6
  4. Study of Soft Sensor Modeling Methods Based on Data Driven and Industrial Applications,TP274
  5. Visual Selective Attention on Sports under Dynamic Multiple Objects Tracking and Multiple Features,G804.2
  6. Design and Implementation of the Multiple Tracking Algorithm for Sperm Analysis,TP391.41
  7. Research on Control of PH Neutralization Process Based on Gauss Process Model,O646.14
  8. KARHUNEN-LOèVE Expansions and Reproducing Kernel Hilbert Spaces of Several Types of Gaussian Processes,O211.6
  9. The Approximation to Rosenblatt Process and Related Analysis,O211.6
  10. Some Applications of Machine Learning Algorithms for the Soft-Sensor Modeling,TP181
  11. Study on Applications of Process Monitoring Based on Multivariate Statistical Methods of Factor Analysis,TP277
  12. The Research on Prediction Model and Prediction Method of Short-term Traffic Flow,TP399-C6
  13. Fast Airfoil Design Based on Gaussian Process Regression,V224
  14. Time Series Analysis Using Gaussian Process,O211.61
  15. Study on Unsupervised and Semi-Supervised Dimensionality Reduction Algorithms,TP181
  16. Bayesian Methods and Its Applications in Chemical Soft-sensor,TP274
  17. Some random process limit theorem,O211
  18. Poincaré Inequality and Log-Sobolev Inequality for Stationary Gaussian Processes,O178
  19. Large and Moderate Deviations for Diffusion Process,O211
  20. The Asymptotic Normality of the Estimation of the Impulse Transfer Function for Two-dimensional Linear Systems,O211.6
  21. Estimation System Storage Reliability by Accelerated Parameter Drifting,O213.2

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