Joint utilization of local appearance and geometric invariants for 3D object recognition

Date

2015-04-01

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

214
views

0
downloads

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 consistency. The main contribution of the proposed approach lies in this ability of incorporating highly discriminative affine invariant 3D information much earlier in the process of matching in comparison with its counterparts. The accuracy and robustness of the method in highly cluttered scenes, without any prior segmentation or post 3D reconstruction requirements, are presented in the experiments.

Subject Keywords

Local features, Geometric descriptors, Geometric invariants, Multi-view object recognition

URI

https://hdl.handle.net/11511/33254

Journal

MULTIMEDIA TOOLS AND APPLICATIONS

DOI

https://doi.org/10.1007/s11042-013-1622-6

Collections

Department of Electrical and Electronics Engineering, Article

Suggestions

OpenMETU
Core

Geospatial Object Recognition From High Resolution Satellite Imagery Ergul, Mustafa; Alatan, Abdullah Aydın (2013-01-01) In this paper, a novel automatic geo-spatial object recognition algorithm from high resolution satellite imagery is proposed. The proposed algorithm consists of two main steps; the generation of hypothesis with a local feature based algorithm and verification step with a shape based approach. The superiority of this method is the ability of minimization of false alarm number in the recognition and this is because object shape includes more characteristic and discriminative information about object identity ...
RECOGNITION OF 3D OBJECTS FROM UNCONSTRAINED 2D IMAGES BY USING LOCAL APPEARANCE AND AFFINE GEOMETRY Soysal, Medeni; Alatan, Abdullah Aydın (2013-07-19) 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 meth...
Joint Utilization of Appearance and Geometry for Determining Correspondences Soysal, Medeni; Alatan, Abdullah Aydın; Karadeniz, Talha (2009-09-16) A novel approach, which is based on combining the competence of interest point detectors to capture primitives and the capability of geometric constraints to discriminate between spatial configurations of these primitives is presented. In the proposed approach, the geometric constraints are enforced by means of barycentric coordinates, a mathematical tool that has been utilized in the relevant literature as a neighborhood constraint. In the context of our research, however, these coordinates are utilized as...
Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery Sumbul, Gencer; Cinbiş, Ramazan Gökberk; Aksoy, Selim (2018-02-01) Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional fully supervised algorithms fail to handle this problem where there is low betweenclass variance and high within-class variance for the classes of interest with small sample sizes. We study an even more extreme scenario named zero-shot learning (ZSL) in which no training example exists f...
E3D-D2D: EMBEDDING IN 3D, DETECTION IN 2D THROUGH PROJECTIVE INVARIANTS Yasaroglu, Yagiz; Alatan, Abdullah Aydın (2014-10-30) A novel watermarking method is presented in which the data embedded into a 3D model is extracted from an arbitrary 2D view by using a perspective projective invariant. The data is embedded into 3D positions of selected interest points on a 3D mesh. Determining the interest point modification vectors for ensuring watermark detection constitutes an important part of the proposed method. Different watermark embedding schemes based on optimization of the watermark function are implemented and evaluated. Another...

Citation Formats

M. Soysal and A. A. Alatan, “Joint utilization of local appearance and geometric invariants for 3D object recognition,” MULTIMEDIA TOOLS AND APPLICATIONS, pp. 2611–2637, 2015, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/33254.