Generic Object Detection using Feature Maps Oscar Danielsson Stefan Carlsson

Slides:



Advertisements
Similar presentations
Jan-Michael Frahm, Enrique Dunn Spring 2013
Advertisements

EE462 MLCV Lecture 5-6 Object Detection – Boosting Tae-Kyun Kim.
EE462 MLCV Lecture 5-6 Object Detection – Boosting Tae-Kyun Kim.
Rapid Object Detection using a Boosted Cascade of Simple Features Paul Viola, Michael Jones Conference on Computer Vision and Pattern Recognition 2001.
Rapid Object Detection using a Boosted Cascade of Simple Features Paul Viola, Michael Jones Conference on Computer Vision and Pattern Recognition 2001.
Face detection Behold a state-of-the-art face detector! (Courtesy Boris Babenko)Boris Babenko.
Classification using intersection kernel SVMs is efficient Joint work with Subhransu Maji and Alex Berg Jitendra Malik UC Berkeley.
Ivan Laptev IRISA/INRIA, Rennes, France September 07, 2006 Boosted Histograms for Improved Object Detection.
Computer Vision for Human-Computer InteractionResearch Group, Universität Karlsruhe (TH) cv:hci Dr. Edgar Seemann 1 Computer Vision: Histograms of Oriented.
Many slides based on P. FelzenszwalbP. Felzenszwalb General object detection with deformable part-based models.
Multi-Local Feature Manifolds for Object Detection Oscar Danielsson Stefan Carlsson Josephine Sullivan
AdaBoost & Its Applications
Face detection Many slides adapted from P. Viola.
Cos 429: Face Detection (Part 2) Viola-Jones and AdaBoost Guest Instructor: Andras Ferencz (Your Regular Instructor: Fei-Fei Li) Thanks to Fei-Fei Li,
EE462 MLCV Lecture 5-6 Object Detection – Boosting Tae-Kyun Kim.
Ghunhui Gu, Joseph J. Lim, Pablo Arbeláez, Jitendra Malik University of California at Berkeley Berkeley, CA
Detecting Pedestrians by Learning Shapelet Features
More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb.
The Viola/Jones Face Detector (2001)
Recognition using Regions CVPR Outline Introduction Overview of the Approach Experimental Results Conclusion.
HCI Final Project Robust Real Time Face Detection Paul Viola, Michael Jones, Robust Real-Time Face Detetion, International Journal of Computer Vision,
Graz University of Technology, AUSTRIA Institute for Computer Graphics and Vision Fast Visual Object Identification and Categorization Michael Grabner,
Robust Real-time Object Detection by Paul Viola and Michael Jones ICCV 2001 Workshop on Statistical and Computation Theories of Vision Presentation by.
Face detection and recognition Many slides adapted from K. Grauman and D. Lowe.
Viola and Jones Object Detector Ruxandra Paun EE/CS/CNS Presentation
Foundations of Computer Vision Rapid object / face detection using a Boosted Cascade of Simple features Presented by Christos Stoilas Rapid object / face.
Face Detection CSE 576. Face detection State-of-the-art face detection demo (Courtesy Boris Babenko)Boris Babenko.
FACE DETECTION AND RECOGNITION By: Paranjith Singh Lohiya Ravi Babu Lavu.
Generic object detection with deformable part-based models
Face Detection using the Viola-Jones Method
Using Statistic-based Boosting Cascade Weilong Yang, Wei Song, Zhigang Qiao, Michael Fang 1.
EADS DS / SDC LTIS Page 1 7 th CNES/DLR Workshop on Information Extraction and Scene Understanding for Meter Resolution Image – 29/03/07 - Oberpfaffenhofen.
“Secret” of Object Detection Zheng Wu (Summer intern in MSRNE) Sep. 3, 2010 Joint work with Ce Liu (MSRNE) William T. Freeman (MIT) Adam Kalai (MSRNE)
Recognition using Boosting Modified from various sources including
Detecting Pedestrians Using Patterns of Motion and Appearance Paul Viola Microsoft Research Irfan Ullah Dept. of Info. and Comm. Engr. Myongji University.
Window-based models for generic object detection Mei-Chen Yeh 04/24/2012.
Lecture 29: Face Detection Revisited CS4670 / 5670: Computer Vision Noah Snavely.
Face detection Slides adapted Grauman & Liebe’s tutorial
Visual Object Recognition
Lecture 31: Modern recognition CS4670 / 5670: Computer Vision Noah Snavely.
Pedestrian Detection and Localization
Supervised Learning of Edges and Object Boundaries Piotr Dollár Zhuowen Tu Serge Belongie.
Combining multiple learners Usman Roshan. Bagging Randomly sample training data Determine classifier C i on sampled data Goto step 1 and repeat m times.
Deformable Part Models (DPM) Felzenswalb, Girshick, McAllester & Ramanan (2010) Slides drawn from a tutorial By R. Girshick AP 12% 27% 36% 45% 49% 2005.
Lecture notes for Stat 231: Pattern Recognition and Machine Learning 1. Stat 231. A.L. Yuille. Fall 2004 AdaBoost.. Binary Classification. Read 9.5 Duda,
Automated Solar Cavity Detection
Adaboost and Object Detection Xu and Arun. Principle of Adaboost Three cobblers with their wits combined equal Zhuge Liang the master mind. Failure is.
Methods for classification and image representation
Lecture 09 03/01/2012 Shai Avidan הבהרה: החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע / לא מופיע במצגת.
The Viola/Jones Face Detector A “paradigmatic” method for real-time object detection Training is slow, but detection is very fast Key ideas Integral images.
Object Detection Overview Viola-Jones Dalal-Triggs Deformable models Deep learning.
Learning to Detect Faces A Large-Scale Application of Machine Learning (This material is not in the text: for further information see the paper by P.
Improved Object Detection
FACE DETECTION : AMIT BHAMARE. WHAT IS FACE DETECTION ? Face detection is computer based technology which detect the face in digital image. Trivial task.
Face detection Behold a state-of-the-art face detector! (Courtesy Boris Babenko)Boris Babenko slides adapted from Svetlana Lazebnik.
More sliding window detection: Discriminative part-based models
Face detection Many slides adapted from P. Viola.
AdaBoost Algorithm and its Application on Object Detection Fayin Li.
Combining Models Foundations of Algorithms and Machine Learning (CS60020), IIT KGP, 2017: Indrajit Bhattacharya.
2. Skin - color filtering.
Cascade for Fast Detection
License Plate Detection
Object detection with deformable part-based models
Lit part of blue dress and shadowed part of white dress are the same color
Asymmetric Gradient Boosting with Application to Spam Filtering
Object detection as supervised classification
Cos 429: Face Detection (Part 2) Viola-Jones and AdaBoost Guest Instructor: Andras Ferencz (Your Regular Instructor: Fei-Fei Li) Thanks to Fei-Fei.
ADABOOST(Adaptative Boosting)
Lecture 29: Face Detection Revisited
Jie Chen, Shiguang Shan, Shengye Yan, Xilin Chen, Wen Gao
Presentation transcript:

Generic Object Detection using Feature Maps Oscar Danielsson Stefan Carlsson

Outline Intro Problem Statement Related Work Famous Object Detectors Our Work Motivation Training Hierarchical Detection Experiments Conclusion

Detect all Instances of an Object Class The classifier needs to be fast (on average). This is typically accomplished by: 1.Using image features that can be computed quickly 2.Using a cascade of increasingly complex classifiers (Viola and Jones IJCV 2004)

Outline Intro Problem Statement Related Work Famous Object Detectors Our Work Motivation Training Hierarchical Detection Experiments Conclusion

Famous Object Detectors (1) Dalal and Triggs (CVPR 05) use a dense Histogram of Oriented Gradients (HOG) representation - the window is tiled into (overlapping) sub-regions and gradient orientation histograms from all sub-regions are concatenated. A linear SVM is used for classification.

Famous Object Detectors (2) Felzenszwalb et. al. (PAMI 10, CVPR 10) extend the Dalal and Triggs model to include high resolution parts with flexible location.

Famous Object Detectors (3) Viola and Jones (IJCV 2004) construct a weak classifier by thresholding the response of a Haar filter (computed using integral images). Weak classifiers are combined into a strong classifier using AdaBoost.

Outline Intro Problem Statement Related Work Famous Object Detectors Our Work Motivation Training Hierarchical Detection Experiments Conclusion

Motivation CornersCorners + BlobsRegionsEdges Different object classes are characterized by different features. So we want to leave the choice of features up to the user. Therefore we construct an object detector based on feature maps. Any feature detectors in any combination can be used to generate feature maps.

Our Object Detector We use AdaBoost to build a strong classifier. We construct a weak classifier by thresholding the distance from a measurement point to the closest occurrence of a given feature.

Outline Intro Problem Statement Related Work Famous Object Detectors Our Work Motivation Training Hierarchical Detection Experiments Conclusion

Extraction of Training Data 1.Feature maps are extracted by some external feature detectors 2.Distance transforms are computed for each feature map 3.(For each training window) Distances from each measurement point to the closest occurrence of the corresponding feature are concatenated into a vector

Training Cascade Strong Learner Weak Learner Decision Stump Learner 1.Require positive training examples and background images 2.Randomly sample background images to extract negative training examples 3.Loop: 1.Train strong classifier 2.Append strong classifier to current cascade 3.Run cascade on background images to harvest false positives 4.If number of false positives sufficiently few, stop { f i }, { I j } { f i }, { c i }, T { f i }, { c i }, { d i } Viola-Jones Cascade Construction

Training Cascade Strong Learner Weak Learner Decision Stump Learner 1.Require positive training examples and background images 2.Randomly sample background images to extract negative training examples 3.Loop: 1.Train strong classifier 2.Append strong classifier to current cascade 3.Run cascade on background images to harvest false positives 4.If number of false positives sufficiently few, stop { f i }, { I j } { f i }, { c i }, T { f i }, { c i }, { d i } Viola-Jones Cascade Construction

Training Cascade Strong Learner Weak Learner Decision Stump Learner 1.Require labeled training examples and number of rounds 2.Init. weights of training examples 3.For each round 1.Train weak classifier 2.Compute weight of weak classifier 3.Update weights of training examples { f i }, { c i }, T { f i }, { I j } { f i }, { c i }, { d i } AdaBoost

Training Cascade Strong Learner Weak Learner Decision Stump Learner 1.Require labeled training examples and number of rounds 2.Init. weights of training examples 3.For each round 1.Train weak classifier 2.Compute weight of weak classifier 3.Update weights of training examples { f i }, { c i }, T { f i }, { I j } { f i }, { c i }, { d i } AdaBoost

Training Cascade Strong Learner Weak Learner Decision Stump Learner 1.Require labeled and weighted training examples 2.Compute node output 3.Train decision stump 4.Split training examples using decision stump 5.Evaluate stopping conditions 6.Train decision tree on left subset of training examples 7.Train decision tree on right subset of training examples { f i }, { c i }, { d i } { f i }, { I j } { f i }, { c i }, T { f i }, { c i }, { d i } Decision Tree Learner

Training Cascade Strong Learner Weak Learner Decision Stump Learner 1.Require labeled and weighted training examples 2.Compute node output 3.Train decision stump 4.Split training examples using decision stump 5.Evaluate stopping conditions 6.Train decision tree on left subset of training examples 7.Train decision tree on right subset of training examples { f i }, { c i }, { d i } { f i }, { I j } { f i }, { c i }, T { f i }, { c i }, { d i } Decision Tree Learner

Training Cascade Strong Learner Weak Learner Decision Stump Learner 1.Require labeled and weighted training examples 2.For each measurement point 1.Compute a threshold by assuming exponentially distributed distances 2.Compute classification error after split 3.If error lower than previous errors, store threshold and measurement point { f i }, { c i }, { d i } { f i }, { I j } { f i }, { c i }, T { f i }, { c i }, { d i } Feature and Threshold Selection

Outline Intro Problem Statement Related Work Famous Object Detectors Our Work Motivation Training Hierarchical Detection Experiments Conclusion

Hierarchical Detection Evaluate an “optimistic” classifier on regions in search space. Split positive regions recursively.

Hierarchical Detection Evaluate an “optimistic” classifier on regions in search space. Split positive regions recursively.

Hierarchical Detection Evaluate an “optimistic” classifier on regions in search space. Split positive regions recursively.

Hierarchical Detection Evaluate an “optimistic” classifier on regions in search space. Split positive regions recursively.

Hierarchical Detection Evaluate an “optimistic” classifier on regions in search space. Split positive regions recursively.

Hierarchical Detection Evaluate an “optimistic” classifier on regions in search space. Split positive regions recursively.

Hierarchical Detection x y s x y s Search spaceImage space Each point in search space corresponds to a window in the image. In the image is a measurement point.

Hierarchical Detection x y s x y Search spaceImage space A region in search space corresponds to a set of windows in the image. This translates to a set of locations for the measurement point.

Hierarchical Detection x y s x y Search spaceImage space We can then compute upper and lower bounds for the distance to the closest occurrence of the corresponding feature. Based on these bounds we construct an optimistic classifier.

Outline Intro Problem Statement Related Work Famous Object Detectors Our Work Motivation Training Hierarchical Detection Experiments Conclusion

Experiments Detection results obtained on the ETHZ Shape Classes dataset, which was used for testing only Training data downloaded from Google images : 106 applelogos, 128 bottles, 270 giraffes, 233 mugs and 165 swans Detections counted as correct if A intersect / A union ≥ 0.2 Features used: edges, corners, blobs, Kadir-Brady + SIFT + quantization

Results Real AdaBoost slightly better than Dirscrete and Gentle AdaBoost

Results Decision tree weak classifiers should be shallow

Results Using all features are better than using only edges

Results Using the asymmetric weighting scheme of Viola and Jones yields a slight improvement

Results Applelogos Bottles Mugs Swans

Results Hierarchical search yields a significant speed-up

Outline Intro Problem Statement Related Work Famous Object Detectors Our Work Motivation Training Hierarchical Detection Experiments Conclusion

Proposed object detection scheme based on feature maps Used distances from measurement points to nearest feature occurrence in image to construct weak classifiers for boosting Showed promising detection performance on the ETHZ Shape Classes dataset Showed that a hierarchical detection scheme can yield significant speed-ups – Thanks for listening!

Famous Object Detectors (4) Laptev (IVC 09) construct a weak classifier using a linear discriminant on a histogram of oriented gradients (HOG – computed by integral histograms) from a sub-region of the window. Again, weak classifiers are combined into a strong classifier using AdaBoost.