Utilizing semantic interpretation of junctions for 3D-2D pose estimation

Pilz, Florian
Shi, Yan
Grest, Daniel
Pugeault, Nicolas
Kalkan, Sinan
Krüger, Norbert
In this paper we investigate the quality of 3D-2D pose estimates using hand labeled line and point correspondences. We select point correspondences from junctions in the image, allowing to construct a meaningful interpretation about how the junction is formed, as proposed in e.g. [1], [2], [3]. We make us of this information referred as the semantic interpretation, to identify the different types of junctions (i.e. L-junctions and T-junctions). T-junctions often denote occluding contour, and thus do not designate a point in space. We show that the semantic interpretations is useful for the removal of these T-junction from correspondence sets, since they have a negative effect on motion estimates. Furthermore, we demonstrate the possibility to derive additional line correspondences from junctions using the semantic interpretation, providing more constraints and thereby more robust estimates. © Springer-Verlag Berlin Heidelberg 2007.
3rd International Symposium on Visual Computing, ISVC 2007


A MAP-Based Approach for Hyperspectral Imagery Super-Resolution
IRMAK, Hasan; Akar, Gözde; Yuksel, Seniha Esen (Institute of Electrical and Electronics Engineers (IEEE), 2018-06-01)
In this paper, we propose a novel single image Bayesian super-resolution (SR) algorithm where the hyperspectral image (HSI) is the only source of information. The main contribution of the proposed approach is to convert the ill-posed SR reconstruction problem in the spectral domain to a quadratic optimization problem in the abundance map domain. In order to do so, Markov random field based energy minimization approach is proposed and proved that the solution is quadratic. The proposed approach consists of f...
Direct Reconstruction of Pharmacokinetic-Rate Images of Optical Fluorophores From NIR Measurements
Alacam, Burak; Yazici, Birsen (Institute of Electrical and Electronics Engineers (IEEE), 2009-09-01)
In this paper, we present a new method to form pharmacokinetic-rate images of optical fluorophores directly from near infra-red (NIR) boundary measurements. We first derive a mapping from spatially resolved pharmacokinetic rates to NIR boundary measurements by combining compartmental modeling with a diffusion based NIR photon propagation model. We express this mapping as a state-space equation. Next, we introduce a spatio-temporal prior model for the pharmacokinetic-rate images and combine it with the state...
An Experimental Study on the Reliability of COSMIC Measurement Results
Ungan, Erdir; Demirörs, Onur; Top, Ozden Ozcan; Ozkan, Baris (2009-11-06)
In this paper, we present the results of a functional software size measurement experiment. We have conducted this experiment to analyze variances in functional software size measurement results among individuals. We aimed to isolate the factors that cause these variances. At the end of the study, statistical results are displayed. Common measurement problems were presented including their causes. And finally factors leading to discrepancies were identified based on these findings.
Extraction of target poles from electromagnetic scatter signals by using page distribution for target recognition Hedef tanima amaci ile page daǧilimi kullanarak elektromanyetik saçilim sinyallerinden kutup çikarimi
Seçmen, Mustafa; Sayan, Gönül; Hizal, Altunkan (2005-12-01)
In this paper, we work on the electromagnetic target recognition problem based on the scattered field measurements. These measurements were obtained both in frequency and time domains by using two 0.8-12 GHz horn antennas in bistatic position and HP8720D vector network analyzer. First, the theory of electromagnetic scattering from a target and singularity expansion method (SEM) are summarized. The importance of complex natural resonance frequencies (CNR) in identification problem is discussed in this part. ...
A shape deformation algorithm for constrained multidimensional scaling
Sahillioğlu, Yusuf (2015-12-01)
We present a new Euclidean embedding technique based on volumetric shape registration. Extrinsic representation of the intrinsic geometry of a shape is preferable in various computer graphics applications as it poses only a small degrees of freedom to deal with during processing. A popular Euclidean embedding approach to achieve such a representation is multidimensional scaling (MDS), which, however, distorts the original geometric details drastically. Our method introduces a constraint on the original MDS ...
Citation Formats
F. Pilz, Y. Shi, D. Grest, N. Pugeault, S. Kalkan, and N. Krüger, “Utilizing semantic interpretation of junctions for 3D-2D pose estimation,” Lake Tahoe, NV, Amerika Birleşik Devletleri, 2007, vol. 4841 LNCS, Accessed: 00, 2022. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=38149123380&origin=inward.