Recognition of 3D textured objects by mixing view-based and model-based representations

Allezard, Nicolas; Dhome, Michel; Jurie, Frédéric

doi:10.1109/icpr.2000.905614

Cited by 8 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown 1 The training scales of the synthetically generated positive training images for the different object classes are given in the experimental sections of Chapter 3, Chapter 4, and Chapter 5. 2 In Chapter 3 and Chapter 4 respectively, we propose two different approaches for automatically determining suitable part positions within the synthetically generated positive training images instead of choosing them manually.…”

Section: Part Appearancementioning

confidence: 99%

See 1 more Smart Citation

Object class detection using part-based models trained from synthetically generated images

Schels¹

2013

SIGMultimedia Rec.

View full text Add to dashboard Cite

This thesis presents part-based approaches to object class detection in single 2D images, relying on pre-built CAD models as a source of synthetic training data.Part-based models, representing an object class as a deformable constellation of object parts, have demonstrated state-of-the-art results with respect to object class detection. Typically, the majority of part-based approaches rely on real training images of publicly available image data sets and consequently, the positive output of those detectors is restricted to the viewpoints which are represented by those real training images. However, progress in the domain of computer graphics enables the generation of photo-realistic renderings on demand from a database of CAD models, which can serve as training source for learning an object class detection approach. In this thesis, we present part-based object class detection methods which are based on synthetically generated positive training images and real negative training images, thereby combining the advantages of the two domains described above. More specifically, photo-realistic object parts, representing the object class being trained, are learnt in an unsupervised way without requiring any manual bounding box, object part, or viewpoint annotations during the training process. The established object parts are efficiently combined into an object class detection framework relying on two part-based models with different learning paradigms. In addition, we outline an extension of our detection framework which is able to cope with multiple object classes.The approaches to object class detection are evaluated on standard benchmark data sets and achieve state-of-the-art results with respect to object class detection in single 2D images.

show abstract

Section: Part Appearancementioning

confidence: 99%

“…Create an initial training set consisting of all positive samples and randomly selected negative samples from a set of background images. 2. Train a linear SVM classifier based on the current training set.…”

Section: Preliminariesmentioning

confidence: 99%

Object class detection using part-based models trained from synthetically generated images

Schels¹

2013

SIGMultimedia Rec.

View full text Add to dashboard Cite

show abstract

“…He also gives an algorithm to remove stretch and skew and obtain an affine invariant characterization. Allezard et al [1] represent the key point neighbourhood by a hierarchical sampling, and rotation invariance is obtained by starting the circular sampling with respect to the gradient direction.…”

Section: Automatic Initializationmentioning

confidence: 99%

“…The object to be recognized is represented by a set of key points characterized by their local appearances. The object 3D model may be known [1], or not [14]. Feature points are extracted from the images, and characterized in order to be matched against the set of keypoints.…”

Section: Automatic Initializationmentioning

confidence: 99%

“…Given an image of the scene, the camera can then be registered online by matching the feature points present in the image against the database. This approach is inspired by recent work on object recognition [14,1] and wide-baseline matching, but our method goes much further towards reducing the computational burden, thus making it suitable for AR applications.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fully automated and stable registration for augmented reality applications

Lepetit

Vacchetti

Thalmann

et al.

The Second IEEE and ACM International Symposium on Mixed and Augmented Reality, 2003. Proceedings.

View full text Add to dashboard Cite

show abstract

Vision-Based 3D Object Localization Using Probabilistic Models of Appearance

Plagemann

Müller²,

Burgard

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The ability to accurately localize objects in an observed scene is regarded as an important precondition for many practical applications including automatic manufacturing, quality assurance, or human-robot interaction. A popular method to recognize three-dimensional objects in two-dimensional images is to apply so-called view-based approaches. In this paper, we present an approach that uses a probabilistic viewbased object recognition technique for 3D localization of rigid objects. Our system generates a set of views for each object to learn an object model which is applied to identify the 6D pose of the object in the scene. In practical experiments carried out with real image data as well as rendered images, we demonstrate that our approach is robust against changing lighting conditions and high amounts of clutter.

show abstract

Recognition of 3D textured objects by mixing view-based and model-based representations

Cited by 8 publications

References 14 publications

Object class detection using part-based models trained from synthetically generated images

Object class detection using part-based models trained from synthetically generated images

Fully automated and stable registration for augmented reality applications

Vision-Based 3D Object Localization Using Probabilistic Models of Appearance

Contact Info

Product

Resources

About