3D Model-Based Semantic Categorization of Still Image 2D Objects

Author(s):  
Raluca-Diana Petre ◽  
Titus Zaharia

Automatic classification and interpretation of objects present in 2D images is a key issue for various computer vision applications. In particular, when considering image/video, indexing, and retrieval applications, automatically labeling in a semantically pertinent manner/huge multimedia databases still remains a challenge. This paper examines the issue of still image object categorization. The objective is to associate semantic labels to the 2D objects present in natural images. The principle of the proposed approach consists of exploiting categorized 3D model repositories to identify unknown 2D objects, based on 2D/3D matching techniques. The authors use 2D/3D shape indexing methods, where 3D models are described through a set of 2D views. Experimental results, carried out on both MPEG-7 and Princeton 3D models databases, show recognition rates of up to 89.2%.

Author(s):  
Raluca-Diana Petre ◽  
Titus Zaharia

Automatic classification and interpretation of objects present in 2D images is a key issue for various computer vision applications. In particular, when considering image/video, indexing, and retrieval applications, automatically labeling in a semantically pertinent manner/huge multimedia databases still remains a challenge. This paper examines the issue of still image object categorization. The objective is to associate semantic labels to the 2D objects present in natural images. The principle of the proposed approach consists of exploiting categorized 3D model repositories to identify unknown 2D objects, based on 2D/3D matching techniques. The authors use 2D/3D shape indexing methods, where 3D models are described through a set of 2D views. Experimental results, carried out on both MPEG-7 and Princeton 3D models databases, show recognition rates of up to 89.2%.


Author(s):  
Li Shen ◽  
Fillia Makedon

Recent technological advances in 3D digitizing, noninvasive scanning, and interactive authoring have resulted in an explosive growth of 3D models in the digital world. There is a critical need to develop new 3D data mining techniques for facilitating the indexing, retrieval, clustering, comparison, and analysis of large collections of 3D models. These approaches will have important impacts in numerous applications including multimedia databases and mining, industrial design, biomedical imaging, bioinformatics, computer vision, and graphics. For example, in similarity search, new shape indexing schemes (e.g. (Funkhouser et al., 2003)) are studied for retrieving similar objects from databases of 3D models. These shape indices are designed to be quick to compute, concise to store, and easy to index, and so they are often relatively compact. In computer vision and medical imaging, more powerful shape descriptors are developed for morphometric pattern discovery (e.g., (Bookstein, 1997; Cootes, Taylor, Cooper, & Graham, 1995; Gerig, Styner, Jones, Weinberger, & Lieberman, 2001; Styner, Gerig, Lieberman, Jones, & Weinberger, 2003)) that aims to detect or localize shape changes between groups of 3D objects. This chapter describes a general shape-based 3D data mining framework for morphometric pattern discovery.


Author(s):  
N. Mostofi ◽  
A. Moussa ◽  
M. Elhabiby ◽  
N. El-Sheimy

3D model of indoor environments provide rich information that can facilitate the disambiguation of different places and increases the familiarization process to any indoor environment for the remote users. In this research work, we describe a system for visual odometry and 3D modeling using information from RGB-D sensor (Camera). The visual odometry method estimates the relative pose of the consecutive RGB-D frames through feature extraction and matching techniques. The pose estimated by visual odometry algorithm is then refined with iterative closest point (ICP) method. The switching technique between ICP and visual odometry in case of no visible features suppresses inconsistency in the final developed map. Finally, we add the loop closure to remove the deviation between first and last frames. In order to have a semantic meaning out of 3D models, the planar patches are segmented from RGB-D point clouds data using region growing technique followed by convex hull method to assign boundaries to the extracted patches. In order to build a final semantic 3D model, the segmented patches are merged using relative pose information obtained from the first step.


2011 ◽  
Author(s):  
Raluca-Diana Petre ◽  
Titus Zaharia

1996 ◽  
Author(s):  
Vikrant Kobla ◽  
David Doermann ◽  
King-Ip Lin ◽  
Christos Faloutsos

Author(s):  
Newton Spolaôr ◽  
Huei Diana Lee ◽  
Weber Shoity Resende Takaki ◽  
Leandro Augusto Ensina ◽  
Antonio Rafael Sabino Parmezan ◽  
...  

Author(s):  
M. Abdelaziz ◽  
M. Elsayed

<p><strong>Abstract.</strong> Underwater photogrammetry in archaeology in Egypt is a completely new experience applied for the first time on the submerged archaeological site of the lighthouse of Alexandria situated on the eastern extremity of the ancient island of Pharos at the foot of Qaitbay Fort at a depth of 2 to 9 metres. In 2009/2010, the CEAlex launched a 3D photogrammetry data-gathering programme for the virtual reassembly of broken artefacts. In 2013 and the beginning of 2014, with the support of the Honor Frost Foundation, methods were developed and refined to acquire manual photographic data of the entire underwater site of Qaitbay using a DSLR camera, simple and low cost materials to obtain a digital surface model (DSM) of the submerged site of the lighthouse, and also to create 3D models of the objects themselves, such as statues, bases of statues and architectural elements. In this paper we present the methodology used for underwater data acquisition, data processing and modelling in order to generate a DSM of the submerged site of Alexandria’s ancient lighthouse. Until 2016, only about 7200&amp;thinsp;m<sup>2</sup> of the submerged site, which exceeds more than 13000&amp;thinsp;m<sup>2</sup>, was covered. One of our main objectives in this project is to georeference the site since this would allow for a very precise 3D model and for correcting the orientation of the site as regards the real-world space.</p>


Author(s):  
D. Einaudi ◽  
A. Spreafico ◽  
F. Chiabrando ◽  
C. Della Coletta

Abstract. Rebuilding the past of cultural heritage through digitization, archiving and visualization by means of digital technology is becoming an emerging issue to ensure the transmission of physical and digital documentation to future generations as evidence of culture, but also to enable present generation to enlarge, facilitate and cross relate data and information in new ways. In this global effort, the digital 3D documentation of no longer existing cultural heritage can be essential for the understanding of past events and nowadays, various digital techniques and tools are developing for multiple purposes.In the present research the entire workflow, starting from archive documentation collection and digitization to the 3D models metrically controlled creation and online sharing, is considered. The technical issues to obtain a detail 3D model are examined stressing limits and potentiality of 3D reconstruction of disappeared heritage and its visualization exploiting three complexes belonging to 1911 Turin World’s Fair.


Author(s):  
Ryuji Nakada ◽  
Masanori Takigawa ◽  
Tomowo Ohga ◽  
Noritsuna Fujii

Digital oblique aerial camera (hereinafter called “oblique cameras”) is an assembly of medium format digital cameras capable of shooting digital aerial photographs in five directions i.e. nadir view and oblique views (forward and backward, left and right views) simultaneously and it is used for shooting digital aerial photographs efficiently for generating 3D models in a wide area. &lt;br&gt;&lt;br&gt; For aerial photogrammetry of public survey in Japan, it is required to use large format cameras, like DMC and UltraCam series, to ensure aerial photogrammetric accuracy. &lt;br&gt;&lt;br&gt; Although oblique cameras are intended to generate 3D models, digital aerial photographs in 5 directions taken with them should not be limited to 3D model production but they may also be allowed for digital mapping and photomaps of required public survey accuracy in Japan. &lt;br&gt;&lt;br&gt; In order to verify the potency of using oblique cameras for aerial photogrammetry (simultaneous adjustment, digital mapping and photomaps), (1) a viewer was developed to interpret digital aerial photographs taken with oblique cameras, (2) digital aerial photographs were shot with an oblique camera owned by us, a Penta DigiCAM of IGI mbH, and (3) accuracy of 3D measurements was verified.


Sign in / Sign up

Export Citation Format

Share Document