Object Detection 01 – Advance Hough Transformation JJCAO.

Slides:



Advertisements
Similar presentations
Fitting: The Hough transform. Voting schemes Let each feature vote for all the models that are compatible with it Hopefully the noise features will not.
Advertisements

Hough Transform Reading Watt, An edge is not a line... How can we detect lines ?
Pedestrian Detection in Crowded Scenes Dhruv Batra ECE CMU.
Edge Detection CSE P 576 Larry Zitnick
Beyond bags of features: Part-based models Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
Fitting: The Hough transform
Lecture 5 Hough transform and RANSAC
CS 558 C OMPUTER V ISION Lecture VIII: Fitting, RANSAC, and Hough Transform Adapted from S. Lazebnik.
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
1 Image Recognition - I. Global appearance patterns Slides by K. Grauman, B. Leibe.
1Ellen L. Walker Segmentation Separating “content” from background Separating image into parts corresponding to “real” objects Complete segmentation Each.
Image alignment.
1 Model Fitting Hao Jiang Computer Science Department Oct 8, 2009.
Object Recognition with Invariant Features n Definition: Identify objects or scenes and determine their pose and model parameters n Applications l Industrial.
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
GENERALIZED HOUGH TRANSFORM. Recap on classical Hough Transform 1.In detecting lines – The parameters  and  were found out relative to the origin (0,0)
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2005 with a lot of slides stolen from Steve Seitz and.
Object Recognition A wise robot sees as much as he ought, not as much as he can Search for objects that are important lamps outlets wall corners doors.
Fitting a Model to Data Reading: 15.1,
Object Recognition Using Geometric Hashing
3-D Computer Vision CSc Feature Detection and Grouping.
Edge Detection Today’s readings Cipolla and Gee –supplemental: Forsyth, chapter 9Forsyth Watt, From Sandlot ScienceSandlot Science.
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2006 with a lot of slides stolen from Steve Seitz and.
Fitting: The Hough transform
Edge Detection.
Robust estimation Problem: we want to determine the displacement (u,v) between pairs of images. We are given 100 points with a correlation score computed.
כמה מהתעשייה? מבנה הקורס השתנה Computer vision.
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean Hall 5409 T-R 10:30am – 11:50am.
October 8, 2013Computer Vision Lecture 11: The Hough Transform 1 Fitting Curve Models to Edges Most contours can be well described by combining several.
Image alignment.
CSE 185 Introduction to Computer Vision
Computer Vision More Image Features Hyunki Hong School of Integrative Engineering.
Segmentation Course web page: vision.cis.udel.edu/~cv May 7, 2003  Lecture 31.
Fitting: The Hough transform. Voting schemes Let each feature vote for all the models that are compatible with it Hopefully the noise features will not.
Fitting & Matching Lecture 4 – Prof. Bregler Slides from: S. Lazebnik, S. Seitz, M. Pollefeys, A. Effros.
HOUGH TRANSFORM Presentation by Sumit Tandon
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
Fitting : Voting and the Hough Transform Monday, Feb 14 Prof. Kristen Grauman UT-Austin.
CS 1699: Intro to Computer Vision Matching and Fitting Prof. Adriana Kovashka University of Pittsburgh September 29, 2015.
Generalized Hough Transform
Lecture 08 Detecting Shape Using Hough Transform Lecture 08 Detecting Shape Using Hough Transform Mata kuliah: T Computer Vision Tahun: 2010.
Class-Specific Hough Forests for Object Detection Zhen Yuan Hsu Advisor:S.J.Wang Gall, J., Lempitsky, V.: Class-specic hough forests for object detection.
CS654: Digital Image Analysis Lecture 25: Hough Transform Slide credits: Guillermo Sapiro, Mubarak Shah, Derek Hoiem.
Fitting: The Hough transform
Edge Detection and Geometric Primitive Extraction Jinxiang Chai.
EECS 274 Computer Vision Model Fitting. Fitting Choose a parametric object/some objects to represent a set of points Three main questions: –what object.
Fitting Thursday, Sept 24 Kristen Grauman UT-Austin.
1 Model Fitting Hao Jiang Computer Science Department Sept 30, 2014.
Object Detection 01 – Basic Hough Transformation JJCAO.
CS 1699: Intro to Computer Vision Detection II: Deformable Part Models Prof. Adriana Kovashka University of Pittsburgh November 12, 2015.
Hough Transform Procedure to find a shape in an image Shape can be described in parametric form Shapes in image correspond to a family of parametric solutions.
Lecture 08 27/12/2011 Shai Avidan הבהרה: החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע / לא מופיע במצגת.
CSE 185 Introduction to Computer Vision Feature Matching.
October 16, 2014Computer Vision Lecture 12: Image Segmentation II 1 Hough Transform The Hough transform is a very general technique for feature detection.
Detecting Image Features: Corner. Corners Given an image, denote the image gradient. C is symmetric with two positive eigenvalues. The eigenvalues give.
On Detection of Multiple Object Instances using Hough Transforms Olga Barinova Moscow State University Victor Lempitsky University of Oxford Pushmeet Kohli.
Hough Transform CS 691 E Spring Outline Hough transform Homography Reading: FP Chapter 15.1 (text) Some slides from Lazebnik.
CS 558 C OMPUTER V ISION Fitting, RANSAC, and Hough Transfrom Adapted from S. Lazebnik.
1 Hough Transform. 2 A Technique to Isolate Features of a Particular Shape within an Image The classical Hough transform is most commonly used for the.
Another Example: Circle Detection
Fitting: Voting and the Hough Transform
Line Fitting James Hayes.
Fitting: The Hough transform
Fitting: Voting and the Hough Transform (part 2)
A special case of calibration
Fitting Curve Models to Edges
Photo by Carl Warner.
Hough Transform.
CSE 185 Introduction to Computer Vision
Presentation transcript:

Object Detection 01 – Advance Hough Transformation JJCAO

Line and curve detection The HTis a standard tool in image analysis that allows recognition of global patterns in an image space by recognition of local patterns in a transformed parameter space. HT: Elegant method for direct object recognition – Edges need not be connected – Complete object need not be visible – Key Idea: Edges VOTE for the possible model 2 Detect partially occluded lines

HT for Lines 3 Parameter space (b,m) Image space y=mx+b (x,y)

Hough_Grd Recall: when we detect an edge point, we also know its gradient direction But this means that the line is uniquely determined! Modified Hough transform: For each edge point (x,y) θ = gradient orientation at (x,y) ρ = x cos θ + y sin θ A(θ, ρ) = A(θ, ρ) + 1 end Θ=[0-360] so there is a conversion

Hough transform for circles x y (x,y) x y r image spaceHough parameter space

6

Generalizing the H.T. (x c,y c ) PiPiPiPi iiii riririri iiii x c = x i + r i cos(  i ) y c = y i + r i sin(  i ) Suppose, there were m different gradient orientations: (m <= n) Suppose, there were m different gradient orientations: (m <= n) 112 mm112 mm... (r 1 1,  1 1 ),(r 1 2,  1 2 ),…,(r 1 n1,  1 n1 ) (r 2 1,  2 1 ),(r 2 2,  1 2 ),…,(r 2 n2,  1 n2 )... (r m 1,  m 1 ),(r m 2,  m 2 ),…,(r m nm,  m nm ) jjjj rjrjrjrj jjjj R-table

Generalized Hough Transform Find Object Center given edges Create Accumulator Array Initialize: For each edge point For each entry in table, compute: Increment Accumulator: Find Local Maxima in Assumption: translation is the only transformation here, i.e., orientation and scale are fixed

Voting schemes Let each feature vote for all the models that are compatible with it Hopefully the noise features will not vote consistently for any single model Missing data doesn’t matter as long as there are enough features remaining to agree on a good model

Application in recognition Instead of indexing displacements by gradient orientation, index by “visual codeword” Combined Object Categorization and Segmentation with an Implicit Shape Model_ECCV04 Object Detection Using a Max-Margin Hough Transform_CVPR09 training image visual codeword with displacement vectors

Application in recognition Instead of indexing displacements by gradient orientation, index by “visual codeword” test image Combined Object Categorization and Segmentation with an Implicit Shape Model_ECCV04 Object Detection Using a Max-Margin Hough Transform_CVPR09

Implicit shape models: Training 1.Build codebook of patches around extracted interest points using clustering (more on this later in the course)

Implicit shape models: Training 1.Build codebook of patches around extracted interest points using clustering 2.Map the patch around each interest point to closest codebook entry

Implicit shape models: Training 1.Build codebook of patches around extracted interest points using clustering 2.Map the patch around each interest point to closest codebook entry 3.For each codebook entry, store all positions it was found, relative to object center

Implicit shape models: Testing 1.Given test image, extract patches, match to codebook entry 2.Cast votes for possible positions of object center 3.Search for maxima in voting space 4.Extract weighted segmentation mask based on stored masks for the codebook occurrences

Implicit shape models: Details Supervised training – Need reference location and segmentation mask for each training car Voting space is continuous, not discrete – Clustering algorithm needed to find maxima How about dealing with scale changes? – Option 1: search a range of scales, as in Hough transform for circles – Option 2: use scale-covariant interest points Verification stage is very important – Once we have a location hypothesis, we can overlay a more detailed template over the image and compare pixel-by-pixel, transfer segmentation masks, etc.

Hough transform: Discussion Pros – Can deal with non-locality and occlusion – Can detect multiple instances of a model – Some robustness to noise: noise points unlikely to contribute consistently to any single bin Cons – Complexity of search time increases exponentially with the number of model parameters – Non-target shapes can produce spurious peaks in parameter space – It’s hard to pick a good grid size Hough transform vs. RANSAC vs. Geometric hashing On Geometric Hashing and the generalized hough transform_tsmc94

Detection of multiple object instances 19 Detection of multiple object instances using Hough transform_cvpr10 Olga Barinova Graphics&Media Lab Moscow State University Victor Lempitsky Yandex company Moscow Visual Geometry Group, University of Oxford – postdoc Pushmeet Kohli Machine Learning and Perception Microsoft Research Cambridge Slides from CVPR 2010 [zip][zip] Talk at CVPR 2010 [link][link] C++ code for pedestrians detection original Visual Studio 2005 solution or Linux Port by Dr. Rodrigo Benenson.Visual Studio 2005 solutionLinux Port C++ code for lines detection the latest version, which is much faster and more accuratethe latest version

Major flaw of HT Lacks a consistent probabilistic model – Does not allow hypotheses to explain away the voting elements Maximum in Hough image corresponds to a correctly detected object The voting elements that were generated by this object also cast votes for other hypotheses The strength of those spurious votes is not inhibited => pseudo maximum Various non-maxima suppression (NMS) heuristics have to be used to localized peaks in the Hough image, which involve specification and tuning of several parameters: – sweep-plane approach (Real-time line detection through an improved Hough transform voting scheme_pr08) – … 20