object detection
play

Object Detection Sanja Fidler CSC420: Intro to Image Understanding - PowerPoint PPT Presentation

Aug 18, 2023 •249 likes •1.17k views

Object Detection Sanja Fidler CSC420: Intro to Image Understanding 1 / 48 Object Detection The goal of object detection is to localize objects in an image and tell their class Localization: place a tight bounding box around object Most

  1. Object Detection Sanja Fidler CSC420: Intro to Image Understanding 1 / 48

  2. Object Detection The goal of object detection is to localize objects in an image and tell their class Localization: place a tight bounding box around object Most approaches find only objects of one or a few specific classes, e.g. car or cow Sanja Fidler CSC420: Intro to Image Understanding 2 / 48

  3. Type of Approaches Di ff erent approaches tackle detection di ff erently. They can roughly be categorized into three main types: Find interest points , followed by Hough voting Sanja Fidler CSC420: Intro to Image Understanding 3 / 48

  4. Interest Point Based Approaches Compute interest points (e.g., Harris corner detector is a popular choice) Vote for where the object could be given the content around interest points Sanja Fidler CSC420: Intro to Image Understanding 4 / 48

  5. Interest Point Based Approaches Compute interest points (e.g., Harris corner detector is a popular choice) Vote for where the object could be given the content around interest points Sanja Fidler CSC420: Intro to Image Understanding 4 / 48

  6. Interest Point Based Approaches Compute interest points (e.g., Harris corner detector is a popular choice) Vote for where the object could be given the content around interest points Sanja Fidler CSC420: Intro to Image Understanding 4 / 48

  7. Interest Point Based Approaches Compute interest points (e.g., Harris corner detector is a popular choice) Vote for where the object could be given the content around interest points Sanja Fidler CSC420: Intro to Image Understanding 4 / 48

  8. Interest Point Based Approaches Compute interest points (e.g., Harris corner detector is a popular choice) Vote for where the object could be given the content around interest points Sanja Fidler CSC420: Intro to Image Understanding 4 / 48

  9. Type of Approaches Di ff erent approaches tackle detection di ff erently. They can roughly be categorized into three main types: Find interest points , followed by Hough voting Sliding windows : “slide” a box around image and classify each image crop inside a box (contains object or not?) Sanja Fidler CSC420: Intro to Image Understanding 5 / 48

  10. Sliding Window Approaches Slide window and ask a classifier: “Is sheep in window or not?” 0.1 confidence [Slide: R. Urtasun] Sanja Fidler CSC420: Intro to Image Understanding 6 / 48

  11. Sliding Window Approaches Slide window and ask a classifier: “Is sheep in window or not?” -0.2 [Slide: R. Urtasun] Sanja Fidler CSC420: Intro to Image Understanding 6 / 48

  12. Sliding Window Approaches Slide window and ask a classifier: “Is sheep in window or not?” -0.1 [Slide: R. Urtasun] Sanja Fidler CSC420: Intro to Image Understanding 6 / 48

  13. Sliding Window Approaches Slide window and ask a classifier: “Is sheep in window or not?” 0.1 [Slide: R. Urtasun] Sanja Fidler CSC420: Intro to Image Understanding 6 / 48

  14. Sliding Window Approaches Slide window and ask a classifier: “Is sheep in window or not?” . . . 1.5 . . . [Slide: R. Urtasun] Sanja Fidler CSC420: Intro to Image Understanding 6 / 48

  15. Sliding Window Approaches Slide window and ask a classifier: “Is sheep in window or not?” 0.5 [Slide: R. Urtasun] Sanja Fidler CSC420: Intro to Image Understanding 6 / 48

  16. Sliding Window Approaches Slide window and ask a classifier: “Is sheep in window or not?” 0.4 [Slide: R. Urtasun] Sanja Fidler CSC420: Intro to Image Understanding 6 / 48

  17. Sliding Window Approaches Slide window and ask a classifier: “Is sheep in window or not?” 0.3 [Slide: R. Urtasun] Sanja Fidler CSC420: Intro to Image Understanding 6 / 48

  18. Sliding Window Approaches Slide window and ask a classifier: “Is sheep in window or not?” 0.1 confidence- 0.2 -0.1 0.1 . . . 1.5 . . . 0.5 0.4 0.3 [Slide: R. Urtasun] Sanja Fidler CSC420: Intro to Image Understanding 6 / 48

  19. Type of Approaches Di ff erent approaches tackle detection di ff erently. They can roughly be categorized into three main types: Find interest points , followed by Hough voting Sliding windows : “slide” a box around image and classify each image crop inside a box (contains object or not?) Generate region (object) proposals , and classify each region Sanja Fidler CSC420: Intro to Image Understanding 7 / 48

  20. Region Proposal Based Approaches Group pixels into object-like regions Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  21. Region Proposal Based Approaches Group pixels into object-like regions Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  22. Region Proposal Based Approaches Group pixels into object-like regions Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  23. Region Proposal Based Approaches Generate many di ff erent regions Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  24. Region Proposal Based Approaches Generate many di ff erent regions Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  25. Region Proposal Based Approaches Generate many di ff erent regions Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  26. Region Proposal Based Approaches The hope is that at least a few will cover real objects Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  27. Region Proposal Based Approaches The hope is that at least a few will cover real objects Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  28. Region Proposal Based Approaches Select a region Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  29. Region Proposal Based Approaches Crop out an image patch around it, throw to classifier (e.g., Neural Net) Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  30. Region Proposal Based Approaches Do this for every region Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  31. Region Proposal Based Approaches Do this for every region Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  32. Region Proposal Based Approaches Do this for every region Sanja Fidler CSC420: Intro to Image Understanding 8 / 48

  33. Type of Approaches Di ff erent approaches tackle detection di ff erently. They can roughly be categorized into three main types: Find interest points , followed by Hough voting ← Let’s first look at one example method for this Sliding windows : “slide” a box around image and classify each image crop inside a box (contains object or not?) Generate region (object) proposals , and classify each region Sanja Fidler CSC420: Intro to Image Understanding 9 / 48

  34. Object Detection via Hough Voting: Implicit Shape Model B. Leibe, A. Leonardis, B. Schiele Robust Object Detection with Interleaved Categorization and Segmentation IJCV, 2008 Paper: http://www.vision.rwth-aachen.de/publications/pdf/leibe-interleaved-ijcv07final.pdf Sanja Fidler CSC420: Intro to Image Understanding 10 / 48

  35. Start with Simple: Line Detection How can I find lines in this image? [Source: K. Grauman] Sanja Fidler CSC420: Intro to Image Understanding 11 / 48

  36. Hough Transform Idea: Voting (Hough Transform) Voting is a general technique where we let the features vote for all models that are compatible with it. Cycle through features, cast votes for model parameters. Look for model parameters that receive a lot of votes. [Source: K. Grauman] Sanja Fidler CSC420: Intro to Image Understanding 12 / 48

  37. Hough Transform: Line Detection Hough space: parameter space Connection between image ( x , y ) and Hough ( m , b ) spaces A line in the image corresponds to a point in Hough space What does a point ( x 0 , y 0 ) in the image space map to in Hough space? [Source: S. Seitz] Sanja Fidler CSC420: Intro to Image Understanding 13 / 48

  38. Hough Transform: Line Detection Hough space: parameter space Connection between image ( x , y ) and Hough ( m , b ) spaces A line in the image corresponds to a point in Hough space A point in image space votes for all the lines that go through this point. This votes are a line in the Hough space. [Source: S. Seitz] Sanja Fidler CSC420: Intro to Image Understanding 14 / 48

  39. Hough Transform: Line Detection Hough space: parameter space Two points: Each point corresponds to a line in the Hough space A point where these two lines meet defines a line in the image! [Source: S. Seitz] Sanja Fidler CSC420: Intro to Image Understanding 15 / 48

  40. Hough Transform: Line Detection Hough space: parameter space Vote with each image point Find peaks in Hough space. Each peak is a line in the image. [Source: S. Seitz] Sanja Fidler CSC420: Intro to Image Understanding 16 / 48

  41. Hough Transform: Line Detection Issues with usual ( m , b ) parameter space: undefined for vertical lines A better representation is a polar representation of lines [Source: S. Seitz] Sanja Fidler CSC420: Intro to Image Understanding 17 / 48

  42. Example Hough Transform With the parameterization x cos θ + y sin θ = d Points in picture represent sinusoids in parameter space Points in parameter space represent lines in picture Example 0 . 6 x + 0 . 4 y = 2 . 4, Sinusoids intersect at d = 2 . 4, θ = 0 . 9273 [Source: M. Kazhdan, slide credit: R. Urtasun] Sanja Fidler CSC420: Intro to Image Understanding 18 / 48

  43. Hough Transform: Line Detection Hough Voting algorithm [Source: S. Seitz] Sanja Fidler CSC420: Intro to Image Understanding 19 / 48

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

A Review on Salient Object Detection Feng Lin Salient Object Detection Target Detect and

A Review on Salient Object Detection Feng Lin Salient Object Detection Target Detect and

A Review on Salient Object Detection Feng Lin Salient Object Detection Target Detect and segment salient objects in natural scenes a) good detection b) high resolution c) computational efficiency Metric F-score MAE (mean

1.12k views • 39 slides
Detection, Segmentation Overview Object Detection deer cat Object Detection as Classification

Detection, Segmentation Overview Object Detection deer cat Object Detection as Classification

CS6501: Deep Learning for Visual Recognition Detection, Segmentation Overview Object Detection deer cat Object Detection as Classification deer? cat? CNN background? Object Detection as Classification deer? cat? CNN background?

577 views • 28 slides
Lecture 11: Object detection Contains slides from S. Lazebnik, R. Girshick, B. Hariharan 1

Lecture 11: Object detection Contains slides from S. Lazebnik, R. Girshick, B. Hariharan 1

Lecture 11: Object detection Contains slides from S. Lazebnik, R. Girshick, B. Hariharan 1 Object detection with bounding boxes What? Where? Object detection Source: R. Girshick 2 Evaluating an object detector At test time,

2.51k views • 56 slides
From image classification to object detection Image classification Object detection Image source

From image classification to object detection Image classification Object detection Image source

From image classification to object detection Image classification Object detection Image source Slides from L. Lazebnik What are the challenges of object detection? Images may contain more than one class, multiple instances from the same

1.11k views • 57 slides
Object Detection Ujjwal Post-Doc, STARS Team INRIA Sophia Antipolis Outline What is Object

Object Detection Ujjwal Post-Doc, STARS Team INRIA Sophia Antipolis Outline What is Object

Object Detection Ujjwal Post-Doc, STARS Team INRIA Sophia Antipolis Outline What is Object Detection ? Qualitative Definition. Machine Learning Definition. Ingredients of Object Detection. Components of a typical deep

683 views • 55 slides
Deep Neural Networks for Object Detection Paper by C. Szegedy, A. Toshev, D. Erhan [2013]

Deep Neural Networks for Object Detection Paper by C. Szegedy, A. Toshev, D. Erhan [2013]

Deep Neural Networks for Object Detection Paper by C. Szegedy, A. Toshev, D. Erhan [2013] Presentation by Joaqun Ruales The Problem: Object Detection Identifying and locating objects in an image The Problem: Object Detection

449 views • 24 slides
Holistic Scene Understanding for 3D Object Detection with RGB-D cameras Dahua Lin, Sanja Fidler,

Holistic Scene Understanding for 3D Object Detection with RGB-D cameras Dahua Lin, Sanja Fidler,

Holistic Scene Understanding for 3D Object Detection with RGB-D cameras Dahua Lin, Sanja Fidler, Raquel Urtasun TTI Chicago D. Lin, S. Fidler, R. Urtasun 3D detection in RGB-D scenes 1 / 29 3D object detection Goal: Category-level 3D object

516 views • 36 slides
Fusing Generic Objectness and Visual Saliency for Salient Object Detection Yasin KAVAK

Fusing Generic Objectness and Visual Saliency for Salient Object Detection Yasin KAVAK

Fusing Generic Objectness and Visual Saliency for Salient Object Detection Yasin KAVAK 06/12/2012 Citation 1: Salient Object Detection: A Benchmark Fusing for Salient Object Detection INDEX (Related Work) [3] B. Alexe, T. Deselaers, and V.

410 views • 29 slides
Object detection & classification for ADAS Robust for Bad situations Small object sizes

Object detection & classification for ADAS Robust for Bad situations Small object sizes

Object detection & classification for ADAS Robust for Bad situations Small object sizes Robust for occlusion Small model size SVNet @ NVIDIA TX2 Please click Icon for Video 5/19/2017 2 Robust detection for various

123 views • 11 slides
Object detection as supervised classification Tues Nov 10 Kristen Grauman UT Austin Today

Object detection as supervised classification Tues Nov 10 Kristen Grauman UT Austin Today

11/9/2015 Object detection as supervised classification Tues Nov 10 Kristen Grauman UT Austin Today Supervised classification Window-based generic object detection basic pipeline boosting classifiers face detection as case

601 views • 34 slides
An Introduction to Modern Object Detection Gang Yu yugang@megvii.com Visual Recognition A

An Introduction to Modern Object Detection Gang Yu yugang@megvii.com Visual Recognition A

An Introduction to Modern Object Detection Gang Yu yugang@megvii.com Visual Recognition A fundamental task in computer vision Classification Object Detection Semantic Segmentation Instance Segmentation Key point Detection

1.13k views • 83 slides
Object Detection using NVIDIA DIGITS Customization and Modification Deep Learning Institute

Object Detection using NVIDIA DIGITS Customization and Modification Deep Learning Institute

Object Detection using NVIDIA DIGITS Customization and Modification Deep Learning Institute NVIDIA Corporation 1 2 2 Introduction to Object Detection Detection by Combining Deep Learning with Traditional Computer Vision AGENDA Detection by

836 views • 34 slides
Networks for 3D Single-shot Object Detection JunYoung Gwak, Christopher Choy, Silvio Savarese

Networks for 3D Single-shot Object Detection JunYoung Gwak, Christopher Choy, Silvio Savarese

Generative Sparse Detection Networks for 3D Single-shot Object Detection JunYoung Gwak, Christopher Choy, Silvio Savarese Key Challenge of 3D Object Detection Disjoint input and output space: Input 3D scan: surface of the object Output

961 views • 36 slides
Regionlets for Generic Object Detection Xiaoyu W ang , Ming Yang , Shenghuo Zhu and

Regionlets for Generic Object Detection Xiaoyu W ang , Ming Yang , Shenghuo Zhu and

Regionlets for Generic Object Detection Xiaoyu W ang , Ming Yang , Shenghuo Zhu and Yuanqing Lin NEC Labs America, Inc. Cupertino, CA 95014, USA Facebook, Inc. Menlo Park, CA 94025, USA Generic object detection Train

455 views • 20 slides
UFO 2 : A Unified Framework towards Omni-supervised Object Detection Zhongzheng Ren, Zhiding Yu,

UFO 2 : A Unified Framework towards Omni-supervised Object Detection Zhongzheng Ren, Zhiding Yu,

UFO 2 : A Unified Framework towards Omni-supervised Object Detection Zhongzheng Ren, Zhiding Yu, Xiaodong Yang, Ming-Yu Liu, Alexander G. Schwing, Jan Kautz ECCV 2020 Omni-supervised Object Detection unlabeled scribbles tags points

417 views • 16 slides
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation Authors: Ross

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation Authors: Ross

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation Authors: Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik Presented by Huihuang Zheng Problem: Object Detection Regionlets SegDPM (2013) Selective

499 views • 19 slides
Numerical Methods for LargeScale Eigenvalue Problems Patrick K urschner Max Planck

Numerical Methods for LargeScale Eigenvalue Problems Patrick K urschner Max Planck

Summer School in Trogir, Croatia Oktober 12, 2011 Numerical Methods for LargeScale Eigenvalue Problems Patrick K urschner Max Planck Institute for Dynamics of Complex Technical Systems Computational Methods in Systems and Control Theory

298 views • 17 slides
' $ r r r r INSTITUT F UR INF ORMA TIK r r r r r r r r r r r r r

' $ r r r r INSTITUT F UR INF ORMA TIK r r r r r r r r r r r r r

' $ r r r r INSTITUT F UR INF ORMA TIK r r r r r r r r r r r r r Ulrich R ude r r r ' $ Multilevel Eigenvalue Solvers fo r the Multigroup Diusion Equations U. R ude and W. Schmid T

862 views • 13 slides
Overview of the CMD-3 recent results at e+e- collider VEPP-2000 Fedotovich G.V. On behalf of CMD-3

Overview of the CMD-3 recent results at e+e- collider VEPP-2000 Fedotovich G.V. On behalf of CMD-3

Overview of the CMD-3 recent results at e+e- collider VEPP-2000 Fedotovich G.V. On behalf of CMD-3 collaboration Budker Institute of Nuclear Physics Novosibirsk State University MESON 2016, 2 7 June, Krakow 1 Outline Motivation

554 views • 32 slides
Inverse Free Preconditioned Krylov Subspace Method for Symmetric Generalized Eigenvalue Problems

Inverse Free Preconditioned Krylov Subspace Method for Symmetric Generalized Eigenvalue Problems

Existing Methods Inverse-free Preconditioned Krylov Subspace Method Block Generalization Blackbox Implementation Numerical Inverse Free Preconditioned Krylov Subspace Method for Symmetric Generalized Eigenvalue Problems Qiang Ye University

743 views • 73 slides
IMplicit-EXplicit schemes for BGK kinetic equations Sandra Pieraccini, Gabriella Puppo

IMplicit-EXplicit schemes for BGK kinetic equations Sandra Pieraccini, Gabriella Puppo

IMplicit-EXplicit schemes for BGK kinetic equations Sandra Pieraccini, Gabriella Puppo Politecnico di Torino Dipartimento di Matematica HYP06, Lyon, July 17-21 p.1/22 Boltzmann equation Rarefied gas flow obeys Boltzmann equation which

745 views • 45 slides
Predicting implicit and explicit questions Matthijs Westera COLT kick-off workshop Predicting

Predicting implicit and explicit questions Matthijs Westera COLT kick-off workshop Predicting

Predicting implicit and explicit questions Matthijs Westera COLT kick-off workshop Predicting implicit and explicit questions Matthijs Westera COLT kick-off workshop = Computational Linguistics & Linguistic Theory The data of

801 views • 59 slides
Links visited in class implied volatility of asset from call option value artificial data plot

Links visited in class implied volatility of asset from call option value artificial data plot

14.0 Implied volatility Links visited in class implied volatility of asset from call option value artificial data plot Newton iter- ates.html 1

612 views • 6 slides
Optimal Portfolio under Fractional Stochastic Environment Ruimeng Hu Joint work with Jean-Pierre

Optimal Portfolio under Fractional Stochastic Environment Ruimeng Hu Joint work with Jean-Pierre

Introduction Fractional Stochastic Volatility under Power Utility General Utility Optimal Portfolio under Fractional Stochastic Environment Ruimeng Hu Joint work with Jean-Pierre Fouque Department of Statistics and Applied Probability

445 views • 33 slides

More recommend