A Computational Learning Theory of Active Object Recognition Under Uncertainty

We present some theoretical results related to the problem of actively searching a 3D scene to determine the positions of one or more pre-specified objects. We investigate the effects that input noise, occlusion, and the VC-dimensions of the related representation classes have in terms of localizing...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of computer vision Ročník 101; číslo 1; s. 95 - 142
Hlavní autoři: Andreopoulos, Alexander, Tsotsos, John K.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Boston Springer US 01.01.2013
Springer
Springer Nature B.V
Témata:
Algorithmics. Computability. Computer arithmetics
Analysis
Applied sciences
Artificial Intelligence
Complexity
Computation
Computer Imaging
Computer Science
Computer science; control theory; systems
Computer vision
Costs
Data processing. List processing. Character string processing
Decision theory
Exact sciences and technology
Image Processing and Computer Vision
Learning
Localization
Machine learning
Memory organisation. Data processing
Noise
Object recognition
Pattern Recognition
Pattern Recognition and Graphics
Pattern recognition. Digital image processing. Computational geometry
Representations
Searching
Sensors
Software
Studies
Theoretical computing
Uncertainty
Vision
Vision systems
Computational complexity of vision
Active vision
Visual search
Object recognition
Attention
Occlusion
Complexity class
Computer vision
Automatic classification
Constraint satisfaction
Pattern recognition
Computational complexity
Modeling
Noise level
Selective attention
Upper bound
Uncertain system
Object detection
Problem solving
Probability learning
Learning algorithm
Artificial intelligence
Occultation
Object location
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 some theoretical results related to the problem of actively searching a 3D scene to determine the positions of one or more pre-specified objects. We investigate the effects that input noise, occlusion, and the VC-dimensions of the related representation classes have in terms of localizing all objects present in the search region, under finite computational resources and a search cost constraint. We present a number of bounds relating the noise-rate of low level feature detection to the VC-dimension of an object representable by an architecture satisfying the given computational constraints. We prove that under certain conditions, the corresponding classes of object localization and recognition problems are efficiently learnable in the presence of noise and under a purposive learning strategy, as there exists a polynomial upper bound on the minimum number of examples necessary to correctly localize the targets under the given models of uncertainty. We also use these arguments to show that passive approaches to the same problem do not necessarily guarantee that the problem is efficiently learnable. Under this formulation, we prove the existence of a number of emergent relations between the object detection noise-rate, the scene representation length, the object class complexity, and the representation class complexity, which demonstrate that selective attention is not only necessary due to computational complexity constraints, but it is also necessary as a noise-suppression mechanism and as a mechanism for efficient object class learning. These results concretely demonstrate the advantages of active, purposive and attentive approaches for solving complex vision problems.
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/s11263-012-0551-6