RECOGNITION OF 3D OBJECTS FROM UNCONSTRAINED 2D IMAGES BY USING LOCAL APPEARANCE AND AFFINE GEOMETRY

Date

2013-07-19

Author

Soysal, Medeni
Alatan, Abdullah Aydın

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

146
views

0
downloads

This paper introduces a novel method, which utilizes local appearance descriptions in a more efficient way, for 3D object recognition. Geometrically consistent local features are identified using affine 3D and 2D geometric invariants, without any reliance on partial or global planarity. Geometric invariants replace the traditional, highly constrained 2D affine transform estimation/verification step, and provides the ability to directly verify 3D geometric consistency. The accuracy and robustness of the method in highly cluttered scenes are presented in the experiments.

Subject Keywords

Local descriptors, Local detectors, Geometric invariants, Affine geometry, Multi-view object indexing and retrieval

URI

https://hdl.handle.net/11511/54316

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Joint utilization of local appearance and geometric invariants for 3D object recognition Soysal, Medeni; Alatan, Abdullah Aydın (2015-04-01) This article introduces a novel method for 3D object recognition, which utilizes well-known local features in a more efficient way, without any reliance on partial or global planarity. Geometrically consistent local features, which form the crucial basis for object recognition, are identified using affine 3D geometric invariants. The utilization of 3D geometric invariants replaces the classical 2D affine transform estimation/verification step, and provides the ability to directly verify 3D geometric consist...
Estimation of Articulatory Trajectories Based on Gaussian Mixture Model (GMM) With Audio-Visual Information Fusion and Dynamic Kalman Smoothing ÖZBEK, İbrahim Yücel; Hasegawa-Johnson, Mark; Demirekler, Mübeccel (Institute of Electrical and Electronics Engineers (IEEE), 2011-07-01) This paper presents a detailed framework for Gaussian mixture model (GMM)-based articulatory inversion equipped with special postprocessing smoothers, and with the capability to perform audio-visual information fusion. The effects of different acoustic features on the GMM inversion performance are investigated and it is shown that the integration of various types of acoustic (and visual) features improves the performance of the articulatory inversion process. Dynamic Kalman smoothers are proposed to adapt t...
Determination of the position and orientation of rigid bodies by using single camera images Kilic, Varlik; Platin, Bülent Emre (2007-07-04) This study aims to present a new reconstruction method which enables reconstruction of 3D configuration of an object using single camera images. A secondary planar target which is a white circle with two internal black spots, one is located at the center, is used. The proposed reconstruction method is monocular and non-iterative. The elliptical contour and spot center locations of the target in an image is used to determine the 6-DOF configuration parameters of an object, on which the secondary target is ri...
Extraction of 3D transform and scale invariant patches from range scans Akagunduz, Erdern; Ulusoy, İlkay (2007-06-22) An algorithm is proposed to extract transformation and scale invariant 3D fundamental elements from the surface structure of 3D range scan data. The surface is described by mean and Gaussian curvature values at every data point at various scales and a scale-space search is performed in order to extract the fundamental structures and to estimate the location and the scale of each fundamental structure. The extracted fundamental structures can later be used as nodes in a topological graph where the links betw...
Training object detectors by directly optimizing lrp metric Çam, Barış Can; Akbaş, Emre; Kalkan, Sinan; Department of Computer Engineering (2020-9) This thesis focuses on training deep object detection networks by directly optimizing the localisation-recall-precision (LRP) performance metric that can evaluate classification and localisation performance of an object detector in a unified manner (Oksuz et al., 2018). To achieve this goal, unlike the commonly used linear weighting approach, we aim to implicitly optimize the LRP metric first by using a bounded localisation loss from previous works and proposing a loss function that can bound the range ...

Citation Formats

M. Soysal and A. A. Alatan, “RECOGNITION OF 3D OBJECTS FROM UNCONSTRAINED 2D IMAGES BY USING LOCAL APPEARANCE AND AFFINE GEOMETRY,” 2013, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/54316.