Introduction to Recognition CS4670/5670: Intro to Computer Vision Noah Snavely mountain building tree banner vendor people street lamp.

Slides:



Advertisements
Similar presentations
3 Small Comments Alex Berg Stony Brook University I work on recognition: features – action recognition – alignment – detection – attributes – hierarchical.
Advertisements

Lecture 31: Modern object recognition
Many slides based on P. FelzenszwalbP. Felzenszwalb General object detection with deformable part-based models.
Last week... why object recognition is difficult, the template model the feature recognition model, word recognition as a case study Today... Recognition.
CPSC 425: Computer Vision (Jan-April 2007) David Lowe Prerequisites: 4 th year ability in CPSC Math 200 (Calculus III) Math 221 (Matrix Algebra: linear.
Lecture 5 Template matching
Object Detection and Recognition
Recognition of Traffic Lights in Live Video Streams on Mobile Devices
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
How many object categories are there? Biederman 1987.
Lecture 28: Bag-of-words models
Recognition Readings Szeliski Chapter 14 The “Margaret Thatcher Illusion”, by Peter Thompson.
Object Recognition: History and Overview Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and Jean Ponce.
Lecture 17: Parts-based models and context CS6670: Computer Vision Noah Snavely.
Visual Object Recognition Rob Fergus Courant Institute, New York University
Opportunities of Scale, Part 2 Computer Vision James Hays, Brown Many slides from James Hays, Alyosha Efros, and Derek Hoiem Graphic from Antonio Torralba.
Lecture 29: Recent work in recognition CS4670: Computer Vision Noah Snavely.
Lecture 6: Feature matching and alignment CS4670: Computer Vision Noah Snavely.
1 Yacov Hel-Or 2 Administration Pre-requisites / prior knowledge Course Home Page: –
Advanced Computer Vision Devi Parikh Electrical and Computer Engineering.
Learning Visual Similarity Measures for Comparing Never Seen Objects By: Eric Nowark, Frederic Juric Presented by: Khoa Tran.
Internet-scale Imagery for Graphics and Vision James Hays cs195g Computational Photography Brown University, Spring 2010.
Human abilities Presented By Mahmoud Awadallah 1.
Perceptual and Sensory Augmented Computing Visual Object Recognition Tutorial Visual Object Recognition Bastian Leibe & Computer Vision Laboratory ETH.
Face Recognition System By Arthur. Introduction  A facial recognition system is a computer application for automatically identifying or verifying a person.
Lecture 4: Feature matching CS4670 / 5670: Computer Vision Noah Snavely.
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
Marco Pedersoli, Jordi Gonzàlez, Xu Hu, and Xavier Roca
Yao, B., and Fei-fei, L. IEEE Transactions on PAMI(2012)
Visual Scene Understanding (CS 598) Derek Hoiem Course Number: Instructor: Derek Hoiem Room: Siebel Center 1109 Class Time: Tuesday and Thursday.
Computer Science Department Pacific University Artificial Intelligence -- Computer Vision.
Traffic Sign Pattern Recognition Pilho Kim (ECE), Zhaohua Wang, Yichang (James) Tsai (CE)
The University of Texas at Austin Vision-Based Pedestrian Detection for Driving Assistance Marco Perez.
Lecture 31: Modern recognition CS4670 / 5670: Computer Vision Noah Snavely.
80 million tiny images: a large dataset for non-parametric object and scene recognition CS 4763 Multimedia Systems Spring 2008.
Why is computer vision difficult?
School of Engineering and Computer Science Victoria University of Wellington Copyright: Peter Andreae, VUW Image Recognition COMP # 18.
Modeling the Shape of a Scene: Seeing the trees as a forest Scene Understanding Seminar
11/26/2015 Copyright G.D. Hager Class 2 - Schedule 1.Optical Illusions 2.Lecture on Object Recognition 3.Group Work 4.Sports Videos 5.Short Lecture on.
Visual Data on the Internet With slides from Alexei Efros, James Hays, Antonio Torralba, and Frederic Heger : Computational Photography Jean-Francois.
Reconstruction the 3D world out of two frames, based on camera pinhole model : 1. Calculating the Fundamental Matrix for each pair of frames 2. Estimating.
Edmunds’ Safety Conference: Truly Safe?
CS 1699: Intro to Computer Vision Detection II: Deformable Part Models Prof. Adriana Kovashka University of Pittsburgh November 12, 2015.
Context-based vision system for place and object recognition Antonio Torralba Kevin Murphy Bill Freeman Mark Rubin Presented by David Lee Some slides borrowed.
Lecture 8: Feature matching CS6670: Computer Vision Noah Snavely.
Li Fei-Fei, UIUC Rob Fergus, MIT Antonio Torralba, MIT Recognizing and Learning Object Categories ICCV 2005 Beijing, Short Course, Oct 15.
Advanced Computer Vision Devi Parikh Electrical and Computer Engineering.
Recognition Readings – C. Bishop, “Neural Networks for Pattern Recognition”, Oxford University Press, 1998, Chapter 1. – Szeliski, Chapter (eigenfaces)
Using the Forest to see the Trees: A computational model relating features, objects and scenes Antonio Torralba CSAIL-MIT Joint work with Aude Oliva, Kevin.
Adaptable Pattern-Classifier System Applying to Face Recognition Intelligent Technology Lab. B. Battulga.
A Discriminatively Trained, Multiscale, Deformable Part Model Yeong-Jun Cho Computer Vision and Pattern Recognition,2008.
Tentative Future Courses Fall `11 : Computer Vision – emphasis on recognition Spring `11 : Graduate seminar Fall `12 : Computational Photography.
数字视频技术 --- 视觉数据挖掘与内容搜索 数字视频技术. 数据挖掘  The process of extracting patterns from data.  The process of analyzing data from different perspectives and summarizing.
Li Fei-Fei, Stanford Rob Fergus, NYU Antonio Torralba, MIT Recognizing and Learning Object Categories: Year 2009 ICCV 2009 Kyoto, Short Course, September.
Recognizing objects Prof. Noah Snavely CS1114
CS 8803 CVL: Vision and Language
Face Detection and Notification System Conclusion and Reference
Lecture 25: Introduction to Recognition
Opportunities of Scale, Part 2
Lecture 14: Introduction to Recognition
Li Fei-Fei, UIUC Rob Fergus, MIT Antonio Torralba, MIT
An opposition to: Context-Based Vision System for Place and Object Recognition Contextual Models for Object Detection Using BRFs.
Lecture 25: Introduction to Recognition
CS 1674: Intro to Computer Vision Scene Recognition
ICCV 2009 Kyoto, Short Course, September 24
Brief Review of Recognition + Context
Advanced Topics in Computer Vision

Generic object recognition
Presentation transcript:

Introduction to Recognition CS4670/5670: Intro to Computer Vision Noah Snavely mountain building tree banner vendor people street lamp

What do we mean by “object recognition”? Next 15 slides adapted from Li, Fergus, & Torralba’s excellent short course on category and object recognitionshort course

Verification: is that a lamp?

Detection: are there people?

Identification: is that Potala Palace?

Object categorization mountain building tree banner vendor people street lamp

Scene and context categorization outdoor city …

Object recognition Is it really so hard? This is a chair Find the chair in this image Output of normalized correlation

Object recognition Is it really so hard? Find the chair in this image Pretty much garbage Simple template matching is not going to make it

Object recognition Is it really so hard? Find the chair in this image A “popular method is that of template matching, by point to point correlation of a model pattern with the image pattern. These techniques are inadequate for three-dimensional scene analysis for many reasons, such as occlusion, changes in viewing angle, and articulation of parts.” Nivatia & Binford, 1977.

Why not use SIFT matching for everything? Works well for object instances Not great for generic object categories

Applications: Computational photography

Applications: Assisted driving meters Ped Car Lane detection Pedestrian and car detection Collision warning systems with adaptive cruise control, Lane departure warning systems, Rear object detection systems,

Applications: image search

How do human do recognition? We don’t completely know yet But we have some experimental observations.

Observation 1 We can recognize familiar faces even in low- resolution images

Observation 2: Jim Carrey Kevin Costner High frequency information is not enough

What is the single most important facial features for recognition?

Observation 4: Image Warping is OK

The list goes on ts_sinha_etal.pdf ts_sinha_etal.pdf

Questions?