Object recognition and localization via pose clustering

Stockman, George C.

doi:10.1016/s0734-189x(87)80196-2

Cited by 38 publications

(42 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Projections of 3D points can also be used to represent poses in a traditional pose clustering system such as [10].…”

Section: Resultsmentioning

confidence: 99%

“…Another method known as pose clustering [10] generates many hypothesized poses and detects clusters in pose space under the assumption that these are clusters of poses generated from correct matches. The advantage of this method is that an accurate expensive analysis of the compatibility of pairs of poses does not have to be performed under the assumption that under any reasonable distance metric, clusters of correct poses will be formed.…”

Section: Introduction and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Object recognition using point uncertainty regions as pose uncertainty regions

Shimshoni

Sasporta

2006

Image and Vision Computing

View full text Add to dashboard Cite

“…Projections of 3D points can also be used to represent poses in a traditional pose clustering system such as [10].…”

Section: Resultsmentioning

confidence: 99%

Section: Introduction and Related Workmentioning

confidence: 99%

Object recognition using point uncertainty regions as pose uncertainty regions

Shimshoni

Sasporta

2006

Image and Vision Computing

View full text Add to dashboard Cite

“…Estimating 3D object poses started from a number of seminal works [22,23,24,25,26,27] in the 80s and early 90s. Although the researchers paid close attentions to the 2D-to-3D correspondence, few approaches achieved successes with real-life objects.…”

Section: Related Workmentioning

confidence: 99%

Object spatial recognition for service robots: Where is the front?

Cao

Das

Kobayashi

et al. 2011

2011 IEEE International Conference on Mechatronics and Automation

View full text Add to dashboard Cite

Exactly same objects produce dramatically different images depending on their poses to the camera and result in great ambiguity for spatial recognition. Different poses of same objects also lead to different orientations in the use of intrinsic system. Our current study is focusing on this issue and can be divided into three phases. First, we propose an object pose-estimation model which is capable of recognizing unseen views. We achieve this goal by building a discrete key-pose structure parameterized by an azimuth and using PHOG [20] descriptor to measure the shape correspondence between two images. A large number of instances are learned at the training stage through semi-supervised. Then, we show experimental results on our own dataset. Second, according to the analyzed criteria in the use of intrinsic system, we recognize the frontal orientation of an intrinsic geometry object combining with pose-estimation results (e.g., a LCD screen). Finally, we summarize our integrated model which is able to classify object category, estimate object pose, distinguish intrinsic spatial relations between reference and target objects and locate the target under users' instructions.

show abstract

“…The third approach, pose clustering (Cass 1992;Stockman 1987;Thompson and Mundy 1987), uses the concept of pose consistency to generate hypotheses. An object is projected onto an image under a single transformation acting on all points of the object.…”

Section: Recognition Frameworkmentioning

confidence: 99%

Planar object recognition using projective shape representation

Rothwell

Zisserman

Forsyth

et al. 1995

Int J Comput Vision

118

View full text Add to dashboard Cite

We describe a model based recognition system, called LEWIS, for the identification of planar objects based on a projectively invariant representation of shape. The advantages of this shape description include simple model acquisition (direct from images), no need for camera calibration or object pose computation, and the use of index functions. We describe the feature construction and recognition algorithms in detail and provide an analysis of the combinatorial advantages of using index functions. Index functions are used to select models from a model base and are constructed from projective invariants based on algebraic curves and a canonical projective coordinate frame. Examples are given of object recognition from images of real scenes, with extensive object libraries. Successful recognition is demonstrated despite partial occlusion by unmodelled objects, and realistic lighting conditions.

show abstract

Object recognition and localization via pose clustering

Cited by 38 publications

References 0 publications

Object recognition using point uncertainty regions as pose uncertainty regions

Object recognition using point uncertainty regions as pose uncertainty regions

Object spatial recognition for service robots: Where is the front?

Planar object recognition using projective shape representation

Contact Info

Product

Resources

About