Current Search:   3D reconstruction (x)

View All Items

  • CSV Spreadsheet
(1 - 4 of 4)
MULTI-VIEW APPROACHES TO TRACKING, 3D RECONSTRUCTION AND OBJECT CLASS DETECTION
Title
MULTI-VIEW APPROACHES TO TRACKING, 3D RECONSTRUCTION AND OBJECT CLASS DETECTION.
Creator
khan, saad, Shah, Mubarak, University of Central Florida
Abstract / Description
Multi-camera systems are becoming ubiquitous and have found application in a variety of domains including surveillance, immersive visualization, sports entertainment and movie special effects amongst others. From a computer vision perspective, the challenging task is how to most efficiently fuse information from multiple views in the absence of detailed calibration information and a minimum of human intervention. This thesis presents a new approach to fuse foreground likelihood information...
Show moreMulti-camera systems are becoming ubiquitous and have found application in a variety of domains including surveillance, immersive visualization, sports entertainment and movie special effects amongst others. From a computer vision perspective, the challenging task is how to most efficiently fuse information from multiple views in the absence of detailed calibration information and a minimum of human intervention. This thesis presents a new approach to fuse foreground likelihood information from multiple views onto a reference view without explicit processing in 3D space, thereby circumventing the need for complete calibration. Our approach uses a homographic occupancy constraint (HOC), which states that if a foreground pixel has a piercing point that is occupied by foreground object, then the pixel warps to foreground regions in every view under homographies induced by the reference plane, in effect using cameras as occupancy detectors. Using the HOC we are able to resolve occlusions and robustly determine ground plane localizations of the people in the scene. To find tracks we obtain ground localizations over a window of frames and stack them creating a space time volume. Regions belonging to the same person form contiguous spatio-temporal tracks that are clustered using a graph cuts segmentation approach. Second, we demonstrate that the HOC is equivalent to performing visual hull intersection in the image-plane, resulting in a cross-sectional slice of the object. The process is extended to multiple planes parallel to the reference plane in the framework of plane to plane homologies. Slices from multiple planes are accumulated and the 3D structure of the object is segmented out. Unlike other visual hull based approaches that use 3D constructs like visual cones, voxels or polygonal meshes requiring calibrated views, ours is purely-image based and uses only 2D constructs i.e. planar homographies between views. This feature also renders it conducive to graphics hardware acceleration. The current GPU implementation of our approach is capable of fusing 60 views (480x720 pixels) at the rate of 50 slices/second. We then present an extension of this approach to reconstructing non-rigid articulated objects from monocular video sequences. The basic premise is that due to motion of the object, scene occupancies are blurred out with non-occupancies in a manner analogous to motion blurred imagery. Using our HOC and a novel construct: the temporal occupancy point (TOP), we are able to fuse multiple views of non-rigid objects obtained from a monocular video sequence. The result is a set of blurred scene occupancy images in the corresponding views, where the values at each pixel correspond to the fraction of total time duration that the pixel observed an occupied scene location. We then use a motion de-blurring approach to de-blur the occupancy images and obtain the 3D structure of the non-rigid object. In the final part of this thesis, we present an object class detection method employing 3D models of rigid objects constructed using the above 3D reconstruction approach. Instead of using a complicated mechanism for relating multiple 2D training views, our approach establishes spatial connections between these views by mapping them directly to the surface of a 3D model. To generalize the model for object class detection, features from supplemental views (obtained from Google Image search) are also considered. Given a 2D test image, correspondences between the 3D feature model and the testing view are identified by matching the detected features. Based on the 3D locations of the corresponding features, several hypotheses of viewing planes can be made. The one with the highest confidence is then used to detect the object using feature location matching. Performance of the proposed method has been evaluated by using the PASCAL VOC challenge dataset and promising results are demonstrated.
Show less
Date Issued
2008
Identifier
CFE0002073, ucf:47593
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0002073
HEURISTIC 3D RECONSTRUCTION OF IRREGULAR SPACED LIDAR
Title
HEURISTIC 3D RECONSTRUCTION OF IRREGULAR SPACED LIDAR.
Creator
Shorter, Nicholas, Kasparis, Takis, University of Central Florida
Abstract / Description
As more data sources have become abundantly available, an increased interest in 3D reconstruction has emerged in the image processing academic community. Applications for 3D reconstruction of urban and residential buildings consist of urban planning, network planning for mobile communication, tourism information systems, spatial analysis of air pollution and noise nuisance, microclimate investigations, and Geographical Information Systems (GISs). Previous, classical, 3D reconstruction...
Show moreAs more data sources have become abundantly available, an increased interest in 3D reconstruction has emerged in the image processing academic community. Applications for 3D reconstruction of urban and residential buildings consist of urban planning, network planning for mobile communication, tourism information systems, spatial analysis of air pollution and noise nuisance, microclimate investigations, and Geographical Information Systems (GISs). Previous, classical, 3D reconstruction algorithms solely utilized aerial photography. With the advent of LIDAR systems, current algorithms explore using captured LIDAR data as an additional feasible source of information for 3D reconstruction. Preprocessing techniques are proposed for the development of an autonomous 3D Reconstruction algorithm. The algorithm is designed for autonomously deriving three dimensional models of urban and residential buildings from raw LIDAR data. First, a greedy insertion triangulation algorithm, modified with a proposed noise filtering technique, triangulates the raw LIDAR data. The normal vectors of those triangles are then passed to an unsupervised clustering algorithm – Fuzzy Simplified Adaptive Resonance Theory (Fuzzy SART). Fuzzy SART returns a rough grouping of coplanar triangles. A proposed multiple regression algorithm then further refines the coplanar grouping by further removing outliers and deriving an improved planar segmentation of the raw LIDAR data. Finally, further refinement is achieved by calculating the intersection of the best fit roof planes and moving nearby points close to that intersection to exist at the intersection, resulting in straight roof ridges. The end result of the aforementioned techniques culminates in a well defined model approximating the considered building depicted by the LIDAR data.
Show less
Date Issued
2006
Identifier
CFE0001315, ucf:47017
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0001315
CONTRIBUTIONS TO AUTOMATIC PARTICLE IDENTIFICATION IN ELECTRON MICROGRAPHS: ALGORITHMS, IMPLEMENTATION, AND APPLICATIONS
Title
CONTRIBUTIONS TO AUTOMATIC PARTICLE IDENTIFICATION IN ELECTRON MICROGRAPHS: ALGORITHMS, IMPLEMENTATION, AND APPLICATIONS.
Creator
Singh, Vivek, Marinescu, Dan, University of Central Florida
Abstract / Description
Three dimensional reconstruction of large macromolecules like viruses at resolutions below 8 \AA~ - 10 \AA~ requires a large set of projection images and the particle identification step becomes a bottleneck. Several automatic and semi-automatic particle detection algorithms have been developed along the years. We present a general technique designed to automatically identify the projection images of particles. The method utilizes Markov random field modelling of the projected images and...
Show moreThree dimensional reconstruction of large macromolecules like viruses at resolutions below 8 \AA~ - 10 \AA~ requires a large set of projection images and the particle identification step becomes a bottleneck. Several automatic and semi-automatic particle detection algorithms have been developed along the years. We present a general technique designed to automatically identify the projection images of particles. The method utilizes Markov random field modelling of the projected images and involves a preprocessing of electron micrographs followed by image segmentation and post processing for boxing of the particle projections. Due to the typically extensive computational requirements for extracting hundreds of thousands of particle projections, parallel processing becomes essential. We present parallel algorithms and load balancing schemes for our algorithms. The lack of a standard benchmark for relative performance analysis of particle identification algorithms has prompted us to develop a benchmark suite. Further, we present a collection of metrics for the relative performance analysis of particle identification algorithms on the micrograph images in the suite, and discuss the design of the benchmark suite.
Show less
Date Issued
2005
Identifier
CFE0000705, ucf:46610
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0000705
DIGITIZATION PROTOCOLS AND APPLICATIONS FOR LASER SCANNING HUMAN BONE IN FORENSIC ANTHROPOLOGY
Title
DIGITIZATION PROTOCOLS AND APPLICATIONS FOR LASER SCANNING HUMAN BONE IN FORENSIC ANTHROPOLOGY.
Creator
Filiault, Matthew, Schultz, John, University of Central Florida
Abstract / Description
In medico-legal investigations involving unidentified skeletal remains, forensic anthropologists commonly assist law enforcement and medical examiners in their analysis and identification. The traditional documentation techniques employed by the forensic anthropologist during their analysis include notes, photographs, measurements and radiographic images. However, relevant visual information of the skeleton can be lacking in morphological details in 2D images. By creating a 3D representation...
Show moreIn medico-legal investigations involving unidentified skeletal remains, forensic anthropologists commonly assist law enforcement and medical examiners in their analysis and identification. The traditional documentation techniques employed by the forensic anthropologist during their analysis include notes, photographs, measurements and radiographic images. However, relevant visual information of the skeleton can be lacking in morphological details in 2D images. By creating a 3D representation of individual bones using a laser-scanner, it would be possible to overcome this limitation. Now that laser scanners have become increasingly affordable, this technology should be incorporated in the documentation methodologies of forensic anthropology laboratories. Unfortunately, this equipment is rarely used in forensic anthropology casework. The goal of this project is to investigate the possible visualization applications that can be created from digitized surface models of bone for use in medico-legal investigations. This research will be achieved in two phases. First, examples of human bone as well as replicas of bone will be scanned using a NextEngine™ laser scanner. In conjunction with this will be the exploration and documentation of protocols for scanning different bone types and processing the scan data for creating a 3D model. The second phase will investigate how the resulting 3D model can be used in lieu of the actual remains to achieve improved documentation methodologies through the use of several commercial computer graphics programs. The results demonstrate that an array of visual applications can be easily created from a 3D file of bone, including virtual curation, measurement, illustration and the virtual reconstruction of fragmented bone. Based on the findings of this project, the implementation of laser scanning technology is recommended for forensic anthropology labs to enhance documentation, analysis and presentation of human bone.
Show less
Date Issued
2012
Identifier
CFH0004287, ucf:44907
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFH0004287