From Images to Shape Models for Object Detection

We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models directly from images, and can localize novel instances in the presence of intra-class variations, clutter, and scale changes....

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of computer vision Ročník 87; číslo 3; s. 284 - 303
Hlavní autoři: Ferrari, Vittorio, Jurie, Frederic, Schmid, Cordelia
Médium: Journal Article
Jazyk:angličtina
Vydáno: Boston Springer US 01.05.2010
Springer
Springer Nature B.V
Springer Verlag
Témata:
Algorithms
Analysis
Applied sciences
Artificial Intelligence
Boundaries
Clutter
Computer Imaging
Computer Science
Computer science; control theory; systems
Computer vision
Computer Vision and Pattern Recognition
Detectors
Exact sciences and technology
Image Processing and Computer Vision
Learning
Mathematical models
Pattern Recognition
Pattern Recognition and Graphics
Pattern recognition. Digital image processing. Computational geometry
Studies
Vision
Voting
Object class detection
Local contour features
Learning category models
Shape matching
Image processing
Cluttered environment
Object recognition
Shape detection
Clutter
Modeling
Voting
Object detection
Pattern matching
ISSN:0920-5691, 1573-1405
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models directly from images, and can localize novel instances in the presence of intra-class variations, clutter, and scale changes. Like a shape matcher, it finds the boundaries of objects, rather than just their bounding-boxes. This is achieved by a novel technique for learning a shape model of an object class given images of example instances. Furthermore, we also integrate Hough-style voting with a non-rigid point matching algorithm to localize the model in cluttered images. As demonstrated by an extensive evaluation, our method can localize object boundaries accurately and does not need segmented examples for training (only bounding-boxes).
Bibliografie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-009-0270-9