Scribd Logo
Upload

Welcome to Scribd!

  • 61 views

    Feature Detection and Matching

    Uploaded by

    arya dadhich
    The document discusses feature detection and matching for images. It describes two main approaches: tracking features between nearby images using correlation or least squares, and independently detecting features in each image and then matching based on local appearance. It explains that feature extraction involves finding locations like corners and blobs that can be matched. Feature matching has four stages: detection, description, matching candidates, and tracking. Local features are useful for tasks like image alignment, 3D reconstruction, and object recognition. Good features are distinctive and invariant to transformations. Corners make particularly good features since they are unique and change significantly under shifts.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd

    Feature Detection and Matching

    Uploaded by

    arya dadhich
    61 views50 pages
    The document discusses feature detection and matching for images. It describes two main approaches: tracking features between nearby images using correlation or least squares, and independently detecting features in each image and then matching based on local appearance. It explains that feature extraction involves finding locations like corners and blobs that can be matched. Feature matching has four stages: detection, description, matching candidates, and tracking. Local features are useful for tasks like image alignment, 3D reconstruction, and object recognition. Good features are distinctive and invariant to transformations. Corners make particularly good features since they are unique and change significantly under shifts.

    Original Title

    feature detection

    Copyright

    © © All Rights Reserved

    Available Formats

    PPT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses feature detection and matching for images. It describes two main approaches: tracking features between nearby images using correlation or least squares, and independently detecting features in each image and then matching based on local appearance. It explains that feature extraction involves finding locations like corners and blobs that can be matched. Feature matching has four stages: detection, description, matching candidates, and tracking. Local features are useful for tasks like image alignment, 3D reconstruction, and object recognition. Good features are distinctive and invariant to transformations. Corners make particularly good features since they are unique and change significantly under shifts.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    61 views50 pages

    Feature Detection and Matching

    Uploaded by

    arya dadhich
    The document discusses feature detection and matching for images. It describes two main approaches: tracking features between nearby images using correlation or least squares, and independently detecting features in each image and then matching based on local appearance. It explains that feature extraction involves finding locations like corners and blobs that can be matched. Feature matching has four stages: detection, description, matching candidates, and tracking. Local features are useful for tasks like image alignment, 3D reconstruction, and object recognition. Good features are distinctive and invariant to transformations. Corners make particularly good features since they are unique and change significantly under shifts.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    You are on page 1of 50

    Feature detection and matching

    Points and patches


    Two main approaches to finding
    feature points and their
    correspondences
    • The first is to find features in one image that
    can be accurately tracked using a local search
    technique, such as correlation or least squares
    • The second is to independently detect
    features in all the images under consideration
    and then match features based on their local
    appearance.
    Feature extraction: Corners and blobs
    Motivation: Automatic panoramas

    Credit: Matt Brown


    Motivation: Automatic panoramas

    HD View
    http://research.microsoft.com/en-us/um/redmond/groups/ivm/HDView/HDGigapixel.htm

    Also see GigaPan:


    http://gigapan.org/
    Why extract features?
    • Motivation: panorama stitching
    – We have two images – how do we combine them?
    Why extract features?
    • Motivation: panorama stitching
    – We have two images – how do we combine them?

    Step 1: extract features


    Step 2: match features
    Why extract features?
    • Motivation: panorama stitching
    – We have two images – how do we combine them?

    Step 1: extract features


    Step 2: match features
    Step 3: align images
    • The former approach is more suitable when
    images are taken from nearby viewpoints or in
    rapid succession (e.g., video sequences), while
    the latter is more suitable when a large
    amount of motion or appearance change is
    expected, e.g., in stitching together
    panoramas
    Key point matching
    • Four separate stages
    • [1] During the feature detection (extraction)
    stage, each image is searched for locations that
    are likely to match well in other images.
    • [2]At the feature description stage, each region
    around detected keypoint locations is converted
    into a more compact and stable (invariant)
    descriptor that can be matched against other
    descriptors.
    • [3] The feature matching stage efficiently
    searches for likely matching candidates in
    other images.
    • [4] The feature tracking stage is an alternative
    to the third stage that only searches a small
    neighborhood around each detected feature
    and is therefore more suitable for video
    processing.
    Image matching

    by Diva Sian

    by swashford
    Harder case

    by Diva Sian by scgbt


    Harder still?

    NASA Mars Rover images


    Answer below (look for tiny colored squares…)

    NASA Mars Rover images


    with SIFT feature matches
    Feature Matching
    Feature Matching
    Invariant local features
    Find features that are invariant to transformations
    – geometric invariance: translation, rotation, scale
    – photometric invariance: brightness, exposure, …

    Feature Descriptors
    Advantages of local features
    Locality
    – features are local, so robust to occlusion and clutter
    Quantity
    – hundreds or thousands in a single image
    Distinctiveness:
    – can differentiate a large database of objects
    Efficiency
    – real-time performance achievable
    More motivation…
    Feature points are used for:
    – Image alignment (e.g., mosaics)
    – 3D reconstruction
    – Motion tracking
    – Object recognition
    – Indexing and database retrieval
    – Robot navigation
    – … other
    What makes a good feature?

    Snoop demo
    Want uniqueness
    Look for image regions that are unusual
    – Lead to unambiguous matches in other images

    How to define “unusual”?


    Local measures of uniqueness
    Suppose we only consider a small window of pixels
    – What defines whether a feature is a good or bad
    candidate?

    Credit: S. Seitz, D. Frolova, D. Simakov


    Local measure of feature uniqueness
    • How does the window change when you shift it?
    • Shifting the window in any direction causes a big
    change

    “flat” region: “edge”: “corner”:


    no change in all no change along the significant change in
    directions edge direction all directions
    Credit: S. Seitz, D. Frolova, D. Simakov
    Importance of
    Corners

    Corners are good features


    to match
    Corner Points
    Interpreting the eigenvalues
    Classification of image points using eigenvalues of M:

    2 “Edge”
    2 >> 1 “Corner”
    1 and 2 are large,
    1 ~ 2;
    E increases in all
    directions

    1 and 2 are small;


    E is almost constant “Flat” “Edge”
    in all directions region 1 >> 2

    1
    Eigen Value Computation is Costly
    Corn
    er

    Edge

    Flat

    Image taken
    from Robert
    Collins
    CSE486, Penn
    State
    Thresholding R

    Image taken
    from Robert
    Collins
    CSE486, Penn
    State
    Image taken
    from Robert
    Collins
    CSE486, Penn
    Algorithm State

    𝐼𝑦

    𝐼𝑥 𝐼𝑦
    Harris detector example
    f value (red high, blue low)
    Threshold (f > value)
    Find local maxima of f
    Harris features (in red)

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy