1 / 42

Object Detect

Object Detect. 报 告 人: 郭立君 日 期: 2007 年 11 月. Contents. Introduction Rigid Object Detect Human Detect Introduction Histograms of Oriented Gradients for Human Detection Dressed Human Modeling,Detection Conclution. Introduction. Some Background on Object Detection.

Download Presentation

Object Detect

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Object Detect 报 告 人: 郭立君 日 期: 2007年11月

  2. Contents • Introduction • Rigid Object Detect • Human Detect Introduction • Histograms of Oriented Gradients for Human Detection • Dressed Human Modeling,Detection • Conclution

  3. Introduction • Some Background on Object Detection As mentioned earlier an object detector can be viewed as a combination of an image feature set and a detection algorithm. 1.The image descriptors or feature vectors that they use 2.The detection framework that is built over these descriptors

  4. Introduction • Descriptors or Feature Vectors Sparse Local Representations Point Detectors (SIFT etc) Part or Limb Detectors Dense Representation of Image Regions Regions and Fragments Based on Image Intensity Edge and Gradient Based Detectors Wavelet Based Detectors

  5. Introduction • Classfication Method Generative Approaches: Typically generative approaches use Bayesian graphical models with Expectation-Maximisation (EM) to characterise these parts and to model their co-occurrences. Such as Bayesian and Graphical Models Discriminative Approaches: Discriminative approaches use machine learning techniques to classify each feature vector as belonging to the object or not. Such as Support Vector Machine (SVM) Classifiers and Cascaded AdaBoost

  6. Rigid Object Detection • Roberts’ Method

  7. Rigid Object Detection • Model Based Vehicle Motion(Tieniu Tan)

  8. Human Detect Introduction Challenges • Wide variety of articulated poses • Variable appearance/clothing • Complex backgrounds • Unconstrained illumination • Occlusions, different scales

  9. Human Detect Introduction Applications • Pedestrian detection for smart cars • Film & media analysis • Visual surveillance • Mobile robot navigation • Human motion capture

  10. Note Two approaches to object detection One approach is to search the whole image at multi-scales for objects. This is a time consuming procedure and may result in multiple responses from a single object. Another approach is to first segment fore-ground objects from the background,then classify each segmented object as human or non-human.

  11. Dressed Human Modeling,Detection --Liang Zhao CMU-RI-TR-01-19 • Backgroud

  12. Dressed Human Modeling,Detection • Backgroud

  13. Dressed Human Modeling,Detection • Goal • initial contour detection (b) body parts identification • (c) contour prediction (d) contour alignment

  14. Dressed Human Modeling,Detection • Goal focuses on how to classify a previously segmented object as human or non-human • Idea Rrecognition scheme is based on the shapes of body parts and the relationships between them. Then the questions left are how to decompose a silhouette into parts, and how to represent the shapes and the relationships between the parts

  15. Dressed Human Modeling • Requirements for a Good Object Class Model 1. It should not depend on scale, orientation, and position of objects; 2. It should handle view-dependent shape variation; 3. It should be robust to shape distortions resulting from digitization noise and foreground/background segmentation errors; 4. It should be robust to partial occlusions of an object; 5. It should allow for articulated moving parts; 6. It should not be influenced by the shape variations allowed within the class; 7. It should support efficient shape recognition/classification.

  16. Dressed Human Modeling • Shape Decomposition for Part-Based Representation

  17. Dressed Human Modeling • Shape Decomposition for Part-Based Representation

  18. Dressed Human Modeling • Shape Decomposition for Part-Based Representation

  19. Dressed Human Modeling • Shape Decomposition for Part-Based Representation Problems and Solutions: (a) Smooth the boundary of a silhouette. (b) Remove noise or small local deformations (c) Exploit high level information(RCR)

  20. Dressed Human Modeling • Human body model TRS-invariant probabilistic model: For the purpose of human detection and model learning, a TRS-invariant representation of the shapes of parts and the relationships between them is developed. For the purpose of modeling the shape variations between individuals and due to viewpoint changes, probability distributions are employed to encode the variations of the model parameters.

  21. Dressed Human Modeling • Human body model

  22. Dressed Human Modeling • Human body model A body part is parameterized with a vector (a; l; x; y;Ө), where a = w/l is the aspect ratio that captures the general shape of a ribbon, (x; y) are the coordinates of the origin in the coordinate frame of the parent part, and Ө is the intersection angle between the major axes of this part and its parent part.

  23. Dressed Human Modeling • Human body model Three TRS-invariant matrices: A; S; U,

  24. Dressed Human Modeling • Human body model TRS-invariant probabilistic model:

  25. Dressed Human Modeling • Dressed Human Modeling

  26. Dressed Human Modeling • Dressed Human Modeling 1.Merged body parts(dynamic) 2.An evaluation function( Bayesian similarity measure-Shape Similarity Measure) 3.A coarse to fine procedure( RCR algorithm-recursive context reasoning)

  27. Dressed Human Modeling • Dressed Human Modeling TRS BSM

  28. Dressed Human Modeling • Bayesian Similarity Measure and Body Part Identification Problem Formulation:

  29. Dressed Human Modeling • Bayesian Similarity Measure and Body Part Identification Problem Formulation:

  30. Dressed Human Modeling • Bayesian Similarity Measure for Human Detection Decision Rule:

  31. Dressed Human Modeling • Bayesian Similarity Measure for Human Detection Resule:

  32. Histograms of Oriented Gradients for Human Detection INRIA Rhˆone-Alpes Background 1. Focus on building robust feature sets 2. Classifier is just linear SVM on normalized image windows, is reliable & fast 3. Moving window based detector with non-maximum suppression over scale-space

  33. Histograms of Oriented Gradients for Human Detection Background

  34. Histograms of Oriented Gradients for Human Detection Feature Sets

  35. Histograms of Oriented Gradients for Human Detection Processing Chain

  36. Histograms of Oriented Gradients for Human Detection HOG Descriptors

  37. Histograms of Oriented Gradients for Human Detection Performance

  38. Histograms of Oriented Gradients for Human Detection Descriptor Cues

  39. Histograms of Oriented Gradients for Human Detection Conclusions

  40. Histograms of Oriented Gradients for Human Detection Demo

  41. the question should be:y = arg max h(a1,a2,...,an)for example: if ai maximizes h, y = ai

More Related