DOC PREVIEW
UIUC CS 543 - Object Category Detection- Parts-based Models

This preview shows page 1-2-3-4-26-27-28-53-54-55-56 out of 56 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 56 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 56 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 56 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 56 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 56 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 56 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 56 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 56 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 56 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 56 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 56 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 56 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

03 30 10 Object Category Detection Parts based Models Computer Vision CS 543 ECE 549 University of Illinois Derek Hoiem Administrative stuff Returning homeworks Administrative stuff Projects next class each group gives 2 minute summary of projects Goal Progress so far If you want to show an image or figure e mail me one image or powerpoint slide by Wed 5pm Deadlines HW 3 due April 6 HW 4 due May 4 should be out April 9 Projects due in 5 weeks Poster session During finals week May 11 12 30 2 30 Tues or May 13 12 30 2 30 Thurs Goal Detect all instances of objects Cars Faces Cats Object model last class Statistical Template in Bounding Box Object is some x y w h in image Features defined wrt bounding box coordinates Image Template Visualization Images from Felzenszwalb Last class sliding window detection Last class statistical template Object model log linear model of parts at fixed positions 3 2 2 1 2 5 0 5 7 5 Non object 4 1 0 5 3 0 5 10 5 7 5 Object When do statistical templates make sense Caltech 101 Average Object Images Object models this class Articulated parts model Object is configuration of parts Each part is detectable Images from Felzenszwalb Deformable objects Images from Caltech 256 Slide Credit Duan Tran Deformable objects Images from D Ramanan s dataset Slide Credit Duan Tran Compositional objects Parts based Models Define object by collection of parts modeled by 1 Appearance 2 Spatial configuration Slide credit Rob Fergus How to model spatial relations One extreme fixed template How to model spatial relations Another extreme bag of words How to model spatial relations Star shaped model Part Part Part Root Part Part How to model spatial relations Star shaped model X X Part Part Part X Root Part Part How to model spatial relations Tree shaped model How to model spatial relations Many others O N6 Fergus et al 03 Fei Fei et al 03 Csurka 04 Vasconcelos 00 O N2 O N3 Leibe et al 04 08 Crandall et al 05 Fergus et al 05 Bouchard Triggs 05 O N2 Crandall et al 05 Felzenszwalb Huttenlocher 05 Carneiro Lowe 06 from Carneiro Lowe ECCV 06 Today s class Part 1 Star shaped model Part Part Root Example ISM Leibe et al 2004 2008 2 Tree shaped model Example Pictorial structures Felzenszwalb Huttenlocher 2005 Part Part ISM Implicit Shape Model Training overview Start with bounding boxes and ideally segmentations of objects Extract local features e g patches or SIFT at interest points on objects Cluster features to create codebook Record relative bounding box and segmentation for each codeword ISM Implicit Shape Model Testing overview Extract interest points in test image Softly match to codebook entries Each matched codeword votes for object bounding box Compute modes of votes using mean shift Check which codewords voted for modes Refine Codebook Representation Extraction of local object features Interest Points e g Harris detector Sparse representation of the object appearance Collect features from whole training set Example K Grauman B Leibe Agglomerative Clustering Algorithm Average Link 1 2 3 Start with each patch as a cluster of its own Repeatedly merge the two most similar clusters X and Y where the similarity between two clusters is defined as the average similarity between their members Until sim X Y Commonly used similarity measures Normalized correlation Euclidean distances K Grauman B Leibe Appearance Codebook Clustering Results Visual similarity preserved Wheel parts window corners fenders Store cluster centers as Appearance Codebook K Grauman B Leibe Voting with Local Features For every feature store possible occurrences Record relative size and scale of object For new image let the matched features vote for possible object positions K Grauman B Leibe Implicit Shape Model Recognition Interest Points Matched Codebook Entries Image Feature Interpretation Codebook match Probabilistic Voting Object Position y s f o x Ci p on x Ci l p Ci f x 3D Voting Space continuous p on x f l p Ci f p on x Ci l i Leibe04 Leibe08 Scale Voting Efficient Computation s s s s y y y y x Scale votes Binned accum array Candidate maxima x Refinement MSME Mean Shift formulation for refinement Scale adaptive balloon density estimator K Grauman B Leibe Implicit Shape Model Recognition Interest Points Matched Codebook Entries Probabilistic Voting y s x 3D Voting Space continuous Backprojected Hypotheses Backprojection of Maxima Leibe04 Leibe08 Example Results on Cows Original image K Grauman B Leibe Example Results on Cows Interest Originalpoints image K Grauman B Leibe Example Results on Cows Matched patches O I K Grauman B Leibe Example Results on Cows Votes I MO Prob K Grauman B Leibe Example Results on Cows 1st hypothesis K Grauman B Leibe Example Results on Cows 2nd hypothesis K Grauman B Leibe Example Results on Cows 3rd hypothesis K Grauman B Leibe ISM Detection Results Qualitative Performance Recognizes different kinds of objects Robust to clutter occlusion noise low contrast K Grauman B Leibe Beyond bounding boxes Interest Points Matched Codebook Entries Probabilistic Voting y s x 3D Voting Space continuous Backprojected codewords can vote Pixel segmentation Part layout Pose Depth values Backprojected Hypotheses Backprojection of Maxima Segmentation Probabilistic Formulation Influence of patch on object hypothesis vote weight p o x C p C p f l o x i n n i p on x i f p f l Backprojection to features f and pixels p p p figure on x p p figure f l o x p f l o x n p f l Segmentation information n Influence on object hypothesis Leibe04 Leibe08 K Grauman B Leibe ISM Top Down Segmentation Interest Points Matched Codebook Entries Probabilistic Voting y s Segmentation p figure Probabilities x 3D Voting Space continuous Backprojected Hypotheses Backprojection of Maxima Leibe04 Leibe08 K Grauman B Leibe Example Results Motorbikes 46K Grauman B Leibe Example Results Chairs Dining room chairs Office chairs 47 B Leibe Inferring Other Information Part Labels Training Test Output 48 Thomas07 Inferring Other Information Part Labels 2 49 Thomas07 Inferring Other Information Depth Maps Depth from a single image 50 Thomas07 Tree shaped model Pictorial Structures Model Part oriented rectangle Spatial model relative size orientation Felzenszwalb and Huttenlocher 2005 Pictorial Structures Model Appearance likelihood Geometry likelihood Pictorial structures model Optimization is tricky but can be efficient Maximization For each l1 find best l2 Remove v2 and repeat with smaller tree until only a single part For n parts


View Full Document
Download Object Category Detection- Parts-based Models
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Object Category Detection- Parts-based Models and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Object Category Detection- Parts-based Models 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?