Comparison of local image descriptors for full 6 degree-of-freedom pose estimation

Viksten, Fredrik; Forssén, Per-Erik; Johansson, Björn; Moe, Anders

doi:10.1109/robot.2009.5152360

Cited by 48 publications

(22 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The choice of datasets for this task that allow comparison with existing methods is limited, here again. We use the "3D pose Volvo car" of Viksten et al [62,63] (Fig. 14).…”

Section: Volvo Car: Continuous 3d Pose Estimation and Synthesis Of Nomentioning

confidence: 99%

Multiview feature distributions for object detection and continuous pose estimation

Teney

Piater

2014

Computer Vision and Image Understanding

View full text Add to dashboard Cite

This paper presents a multiview model of object categories, generally applicable to virtually any type of image features, and methods to efficiently perform, in a unified manner, detection, localization and continuous pose estimation in novel scenes. We represent appearance as distributions of low-level, fine-grained image features. Multiview models encode the appearance of objects at discrete viewpoints, and, in addition, how these viewpoints deform into one another as the viewpoint continuously varies (as detected from optical flow between training examples). Using a measure of similarity between an arbitrary test image and such a model at chosen viewpoints, we perform all tasks mentioned above with a common method. We leverage the simplicity of low-level image features, such as points extracted along edges, or coarse-scale gradients extracted densely over the images, by building probabilistic templates, i.e. distributions of features, learned from one or several training examples. We efficiently handle these distributions with probabilistic techniques such as kernel density estimation, Monte Carlo integration and importance sampling. We provide an extensive evaluation on a wide variety of benchmark datasets. We demonstrate performance on the "ETHZ Shape" dataset, with single (hand-drawn) and multiple training examples, well above baseline methods, on par with a number of more task-specific methods. We obtain remarkable performance on the recognition of more complex objects, notably the cars of the "3D Object" dataset of Savarese et al. with detection rates of 92.5% and an accuracy in pose estimation of 91%. We perform better than the state-of-the-art on continuous pose estimation with the "rotating cars" dataset of Ozuysal et al. . We also demonstrate particular capabilities with a novel dataset featuring non-textured objects of undistinctive shapes, the pose of which can only be determined from shading, captured here by coarse scale intensity gradients.

show abstract

“…The choice of datasets for this task that allow comparison with existing methods is limited, here again. We use the "3D pose Volvo car" of Viksten et al [62,63] (Fig. 14).…”

Section: Volvo Car: Continuous 3d Pose Estimation and Synthesis Of Nomentioning

confidence: 99%

Multiview feature distributions for object detection and continuous pose estimation

Teney

Piater

2014

Computer Vision and Image Understanding

View full text Add to dashboard Cite

show abstract

“…3. A car image from [23] reconstructed from CCFMs, clipped to 512 × 256. Left: reconstruction from direct CCFM encoding.…”

Section: Convergence Behaviormentioning

confidence: 99%

“…The images are taken from [23], size 512 × 512. We have reproduced the experiment from [6], generating CCFMs with a resolution of 66×66×10 channels, and reconstructing images with a resolution of 512 × 512 using the method from [6].…”

Section: Image Reconstructionmentioning

confidence: 99%

See 1 more Smart Citation

Incremental Computation of Feature Hierarchies

Felsberg

2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Feature hierarchies are essential to many visual object recognition systems and are well motivated by observations in biological systems. The present paper proposes an algorithm to incrementally compute feature hierarchies. The features are represented as estimated densities, using a variant of local soft histograms. The kernel functions used for this estimation in conjunction with their unitary extension establish a tight frame and results from framelet theory apply. Traversing the feature hierarchy requires resampling of the spatial and the feature bins. For the resampling, we derive a multi-resolution scheme for quadratic spline kernels and we derive an optimization algorithm for the upsampling. We complement the theoretic results by some illustrative experiments, consideration of convergence rate and computational efficiency.

show abstract

“…We consider several sequences: the CMU 'house' and 'hotel' sequences (used in [6,20]), as well as two new sequences from [24], which are advantageous in that their changes in rotation/azimuth are known.…”

Section: -D Models From Different Viewpointsmentioning

confidence: 99%

Unified graph matching in Euclidean spaces

McAuley

Campos

Caetano

2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Graph matching is a classical problem in pattern recognition with many applications, particularly when the graphs are embedded in Euclidean spaces, as is often the case for computer vision. There are several variants of the matching problem, concerned with isometries, isomorphisms, homeomorphisms, and node attributes; different approaches exist for each variant. We show how structured estimation methods from machine learning can be used to combine such variants into a single version of graph matching. In this paradigm, the extent to which our datasets reveal isometries, isomorphisms, homeomorphisms, and other properties is automatically accounted for in the learning process so that any such specific qualification of graph matching loses meaning. We present experiments with real computer vision data showing the leverage of this unified formulation.

show abstract

Comparison of local image descriptors for full 6 degree-of-freedom pose estimation

Cited by 48 publications

References 22 publications

Multiview feature distributions for object detection and continuous pose estimation

Multiview feature distributions for object detection and continuous pose estimation

Incremental Computation of Feature Hierarchies

Unified graph matching in Euclidean spaces

Contact Info

Product

Resources

About