CS223B Assignment 1 Recap. Lots of Solutions! 37 Groups Many different approaches Let’s take a peek at all 37 results on one image from the test set.

Slides:



Advertisements
Similar presentations
By: Mani Baghaei Fard.  During recent years number of moving vehicles in roads and highways has been considerably increased.
Advertisements

November 12, 2013Computer Vision Lecture 12: Texture 1Signature Another popular method of representing shape is called the signature. In order to compute.
Spatial Filtering (Chapter 3)
Regional Processing Convolutional filters. Smoothing  Convolution can be used to achieve a variety of effects depending on the kernel.  Smoothing, or.
EDGE DETECTION ARCHANA IYER AADHAR AUTHENTICATION.
CS 551 / CS 645 Antialiasing. What is a pixel? A pixel is not… –A box –A disk –A teeny tiny little light A pixel is a point –It has no dimension –It occupies.
Artifact and Textured region Detection - Vishal Bangard.
Introduction to Morphological Operators
Segmentation (2): edge detection
1Ellen L. Walker Edges Humans easily understand “line drawings” as pictures.
CSSE463: Image Recognition Day 6 Yesterday: Yesterday: Local, global, and point operators all operate on entire image, changing one pixel at a time!! Local,
Computer Vision Group Edge Detection Giacomo Boracchi 5/12/2007
Edge detection. Edge Detection in Images Finding the contour of objects in a scene.
Announcements Mailing list: –you should have received messages Project 1 out today (due in two weeks)
EE663 Image Processing Edge Detection 2 Dr. Samir H. Abdul-Jauwad Electrical Engineering Department King Fahd University of Petroleum & Minerals.
Segmentation Divide the image into segments. Each segment:
Canny Edge Detector1 1)Smooth image with a Gaussian optimizes the trade-off between noise filtering and edge localization 2)Compute the Gradient magnitude.
Edge Detection Today’s reading Forsyth, chapters 8, 15.1
CS223B Homework 1 Results. Considered 2 Metrics Raw score –Number of pixels in error Weighted score –Car pixels weighted more heavily than non-car pixels.
CS 223B Assignment 1 Help Session Dan Maynes-Aminzade.
Fitting a Model to Data Reading: 15.1,
Introduction to Computer Vision CS / ECE 181B Thursday, April 22, 2004  Edge detection (HO #5)  HW#3 due, next week  No office hours today.
Lecture 4: Edge Based Vision Dr Carole Twining Thursday 18th March 2:00pm – 2:50pm.
Edge Detection Today’s readings Cipolla and Gee –supplemental: Forsyth, chapter 9Forsyth Watt, From Sandlot ScienceSandlot Science.
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.
Edge detection Goal: Identify sudden changes (discontinuities) in an image Intuitively, most semantic and shape information from the image can be encoded.
Introduction to 3D Graphics John E. Laird. Basic Issues u Given a internal model of a 3D world, with textures and light sources how do you project it.
Edges and Contours– Chapter 7. Visual perception We don’t need to see all the color detail to recognize the scene content of an image That is, some data.
Introduction to Image Processing Grass Sky Tree ? ? Review.
Neighborhood Operations
Object Detection Using the Statistics of Parts Presented by Nicholas Chan – Advanced Perception Robust Real-time Object Detection Henry Schneiderman.
Filtering Robert Lin April 29, Outline Why filter? Filtering for Graphics Sampling and Reconstruction Convolution The Fourier Transform Overview.
Image Processing Edge detection Filtering: Noise suppresion.
Edges. Edge detection schemes can be grouped in three classes: –Gradient operators: Robert, Sobel, Prewitt, and Laplacian (3x3 and 5x5 masks) –Surface.
Detection of nerves in Ultrasound Images using edge detection techniques NIRANJAN TALLAPALLY.
AdeptSight Image Processing Tools Lee Haney January 21, 2010.
CSC508 What You Should Be Doing Code, code, code –Programming Gaussian Convolution Sobel Edge Operator.
CS654: Digital Image Analysis Lecture 25: Hough Transform Slide credits: Guillermo Sapiro, Mubarak Shah, Derek Hoiem.
1 Research Question  Can a vision-based mobile robot  with limited computation and memory,  and rapidly varying camera positions,  operate autonomously.
University of Texas at Arlington
CSSE463: Image Recognition Day 6 Yesterday: Local, global, and point operators use different context, but all Yesterday: Local, global, and point operators.
Lecture 10: Lines from Edges, Interest Points, Binary Operations CAP 5415: Computer Vision Fall 2006.
A New Method for Crater Detection Heather Dunlop November 2, 2006.
Course 5 Edge Detection. Image Features: local, meaningful, detectable parts of an image. edge corner texture … Edges: Edges points, or simply edges,
Lecture 04 Edge Detection Lecture 04 Edge Detection Mata kuliah: T Computer Vision Tahun: 2010.
Digital Image Processing Lecture 17: Segmentation: Canny Edge Detector & Hough Transform Prof. Charlene Tsai.
Machine Vision Edge Detection Techniques ENT 273 Lecture 6 Hema C.R.
Edge Segmentation in Computer Images CSE350/ Sep 03.
TOPIC 12 IMAGE SEGMENTATION & MORPHOLOGY. Image segmentation is approached from three different perspectives :. Region detection: each pixel is assigned.
Computer Vision Computer Vision based Hole Filling Chad Hantak COMP December 9, 2003.
09/23/03CS679 - Fall Copyright Univ. of Wisconsin Last Time Reflections Shadows Part 1 Stage 1 is in.
April 21, 2016Introduction to Artificial Intelligence Lecture 22: Computer Vision II 1 Canny Edge Detector The Canny edge detector is a good approximation.
Chapter 10 Image Segmentation
Fitting: Voting and the Hough Transform
Detection of discontinuity using
Scott Tan Boonping Lau Chun Hui Weng
Computer Vision Lecture 9: Edge Detection II
Lecture 13 Clipping & Scan Conversion
CSSE463: Image Recognition Day 6
Morphological Operators
CSSE463: Image Recognition Day 6
Edge Detection Today’s readings Cipolla and Gee Watt,
CSSE463: Image Recognition Day 6
Midterm Exam Closed book, notes, computer Similar to test 1 in format:
CSSE463: Image Recognition Day 6
Canny Edge Detector Smooth image with a Gaussian
Winter in Kraków photographed by Marcin Ryczek
IT472 Digital Image Processing
IT472 Digital Image Processing
DIGITAL IMAGE PROCESSING Elective 3 (5th Sem.)
Presentation transcript:

CS223B Assignment 1 Recap

Lots of Solutions! 37 Groups Many different approaches Let’s take a peek at all 37 results on one image from the test set

Possible Things to Look For Symmetry Color Shadow Corners Edges Texture Taillights

Road Finding Tactic 1 Run adaptive flood fill on the image starting at the pixels near the bottom Everything that gets filled in is considered road Holes inside the road are likely car candidates

Road Finding Tactic 2 Run an edge detector (such as Prewitt or Canny) and a Hough transform, and then look for lines with the right approximate angle and position.

Road Finding Tactic 3 Sample the color from some pixels directly in front of car (bottom of image) Generate a difference map using this color Run an edge detector on this difference map, followed by a Hough transform

Road Finding Tactic 4 Assume the road is in pretty much the same place in every image and hard code it in

Edge Approach 1 Detect edges with Canny detector Dilate image to join nearby edges Fill in closed regions

Edge Approach 2 Custom edge mask that considers vertical and horizontal edges in likely configurations

Shadow Finding Use a mask that enhances horizontal edges Look for several adjacent rows of dark pixels in the road region

Corner Approach Compute strong corners Cluster them with kmeans Find the densest clusters and compute their convex hulls

Texture Approach Look for regions of high frequency –Find density of edges in rectangular regions –Mask or sum the derivative across rectangular regions –Take FFT of image and set magnitudes to 1, leaving only phase info; inverse FFT then enhances portions with many frequencies

Taillight Detection Transforming the color space can help spot the reddest pixels Groups of these pixels are good candidates for taillights If there’s a horizontal pair of taillights, even better Or, use a mask with the pair built in

Going from Pixels to Regions Count the number of “car pixels” in square regions; if above a threshold, consider it a car region

Statistical Classifier More stages mean many fewer false positives (and only slightly fewer missed cars)

Multiple Classifiers

Filtering Classifier Output Tactics Check number of corners in the rectangle. If too low, reject. Check position and size of rectangle. If it doesn’t make sense given perspective, then reject. Run an edge detector on the rectangular region and then sum the pixels inside. If below threshold, reject. Look at the average derivative of image intensity. If below threshold, reject.

Consider Geometry of Scene

Combining Results from Different Detectors Many of the best solutions used some weighted combination of several heuristics to verify the strength of hypotheses …

Building a Better Bounding Box Get the strong corners in the box, and then trace the convex hull of these corners to eliminate some of the road. Alternatively, make a 2D or 3D model of car shape based on image position and replace rectangle with appropriate polygon. Or, segment the rectangle by colors and keep only the inner segments.

Common Mistakes Strange ways of drawing car regions Don’t use anti-aliased lines or flood fill, just draw filled polygons with cvPolyLine

Common Mistakes Stray Pixels Could be fixed with image close operation