Active Object Recognition Integrating Attention and Viewpoint Control

Dickinson, Sven; Christensen, Henrik I.; Tsotsos, John K.; Olofsson, Göran

doi:10.1006/cviu.1997.0532

Cited by 95 publications

(59 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Bayes rule is used for updating the probabilities of nodes having a particular label, given that successor nodes have particular labels. Dickinson et al [56] use a variant of a Bayes net for their recognition system (Rimey and Brown [25]. use Bayes nets for scene analysis), while Hutchinson and Kak [55] use the Dempster-Shafer theory to represent uncertainty.…”

Section: Methods For Representing Uncertaintymentioning

confidence: 99%

“…Existing part-based recognition systems usually use information from only a single view. The works of Dickinson et al [56], and our work [59] are examples of active recognition systems using a part-based representation. Here, we look at two part-based representations namely, geons and appearance-based parts:…”

Section: Part-based Representationsmentioning

confidence: 96%

“…Many active object recongition schemes are based on aspect graphs [55], [56], [14], [57], [58] (Section 2.3 describes these in detail). The aspect graph-based approach is more general than the other two approaches in that appearance-based information may be used to construct an aspect graph.…”

Section: Aspect Graphsmentioning

confidence: 99%

“…Dickinson and co-workers [44], [45] use an augmented aspect hierarchy using geons as the basic volumetric primitives. They use this augmented aspect hierarchy for active 3-D object recognition in [56].…”

Section: Geonsmentioning

confidence: 99%

“…Dickinson and co-workers [56] present an active object recognition scheme which integrates attention and viewpoint control. Their representation scheme is similar to that of Biederman [60].…”

Section: Dickinson Et Almentioning

confidence: 99%

See 4 more Smart Citations

Active recognition through next view planning: a survey

Roy

Chaudhury

Banerjee

2004

Pattern Recognition

View full text Add to dashboard Cite

Abstract3-D object recognition involves using image-computable features to identify 3-D object. A single view of a 3-D object may not contain sufficient features to recognize it unambiguously. One needs to plan different views around the given object in order to recognize it. Such a task involves an active sensor -one whose parameters (external and/or internal) can be changed in a purposive manner. In this paper, we review two important applications of an active sensor. We first survey important approaches to active 3-D object recognition. Next, we review existing approaches towards another important application of an active sensor namely, that of scene analysis and interpretation.

show abstract

Section: Methods For Representing Uncertaintymentioning

confidence: 99%

Section: Part-based Representationsmentioning

confidence: 96%

Section: Aspect Graphsmentioning

confidence: 99%

Section: Geonsmentioning

confidence: 99%

Section: Dickinson Et Almentioning

confidence: 99%

See 3 more Smart Citations

Active recognition through next view planning: a survey

Roy

Chaudhury

Banerjee

2004

Pattern Recognition

View full text Add to dashboard Cite

show abstract

Multiple human tracking on image sequence under hierarchical attention control

Satake¹,

Shakunaga²

2006

Systems & Computers in Japan

View full text Add to dashboard Cite

SUMMARYThe authors aim to implement flexible human visionlike processing on a computer by automatically switching the focus of attention to perform stable and efficient image sequence processing. To do so, they first introduce a hierarchical attention control model that divides high-order processing into five layers in this paper according to the object or role of each layer. By using this model, the authors implement attention control that uses not only simple image information, but also high-order information such as the various objects or relations between objects. Next, they take the problem of stably and efficiently tracking multiple people in a sequence of images to show the effectiveness of hierarchical attention control. In other words, by using this model, they determine the conditions of each person in an image based on the distance between the people or the way in which the people overlap and switch to suitable tracking processing or control the focus of attention. They use actual images to perform tracking experiments and verify the stability of tracking multiple people according to the proposed technique and the attention control processing contents of each layer during state transitions to show the effectiveness of the proposed technique.

show abstract