A multivalued representation for view synthesis

Chang, Norman; Zakhor, Avideh

doi:10.1109/icip.1999.822947

Cited by 11 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The low-contrast region processing involves segmenting each image into no overlapping regions based on intensity. A simple linking algorithm starts at every pixel in the image and recursively grows out regions of similar intensity [10]. An input image at the first frame and its resultant low-contrast regions are shown in fig.…”

Section: Feature Detectionmentioning

confidence: 99%

Multi-Hypothesis Outdoor Localization using Multiple Visual Features with a Rough Map

Yun

Miura

2007

Proceedings 2007 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

We describe a method of mobile robot localization based on a rough map using stereo vision, which uses multiple visual features to detect and segment the buildings in the robot's field of view. The rough map is an inaccurate map with large uncertainties in the shapes, the dimensions and the locations of objects so that it can be built easily. The robot fuses odometry and vision information using extended Kalman filters to update the robot pose and the associated uncertainty based on the recognition of buildings in the map. We use multi-hypothesis Kalman filter to generate and track Gaussian pose hypotheses. An experimental result shows the feasibility of our localization method in an outdoor environment.

show abstract

Section: Feature Detectionmentioning

confidence: 99%

Multi-Hypothesis Outdoor Localization using Multiple Visual Features with a Rough Map

Yun

Miura

2007

Proceedings 2007 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

show abstract

“…Examples of such compact form include image-based objects [22], layered depth image (LDI) [23], LDI tree [24], and multivalued representation [25]. However, this approach either requires a careful data-acquisition scheme [22], [25] or a deliberated representation construction procedure [23], [24].…”

Section: B Stereo Compressionmentioning

confidence: 99%

An Efficient Image-Based Telepresence System for Videoconferencing

Lei

Chang

Hendriks

2004

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

“…Typically, our facades are 2 1/2 D objects rather than full 3D objects, and hence we introduce a representation based of multiple depth layers for the street scenery, similar to the one proposed in Chang and Zakhor (1999). Each depth layer is a scan grid, and the scan points of the original grid are assigned to exactly one of the layers.…”

Section: Multi-layer Representationmentioning

confidence: 99%

Data Processing Algorithms for Generating Textured 3D Building Facade Meshes from Laser Scans and Camera Images

Frueh

Jain

Zakhor

2005

International Journal of Computer Vision

186

View full text Add to dashboard Cite

Abstract. In this paper, we develop a set of data processing algorithms for generating textured facade meshes of cities from a series of vertical 2D surface scans and camera images, obtained by a laser scanner and digital camera while driving on public roads under normal traffic conditions. These processing steps are needed to cope with imperfections and non-idealities inherent in laser scanning systems such as occlusions and reflections from glass surfaces. The data is divided into easy-to-handle quasi-linear segments corresponding to approximately straight driving direction and sequential topological order of vertical laser scans; each segment is then transformed into a depth image. Dominant building structures are detected in the depth images, and points are classified into foreground and background layers. Large holes in the background layer, caused by occlusion from foreground layer objects, are filled in by planar or horizontal interpolation. The depth image is further processed by removing isolated points and filling remaining small holes. The foreground objects also leave holes in the texture of building facades, which are filled by horizontal and vertical interpolation in low frequency regions, or by a copy-paste method otherwise. We apply the above steps to a large set of data of downtown Berkeley with several million 3D points, in order to obtain texture-mapped 3D models.

show abstract

A multivalued representation for view synthesis

Cited by 11 publications

References 8 publications

Multi-Hypothesis Outdoor Localization using Multiple Visual Features with a Rough Map

Multi-Hypothesis Outdoor Localization using Multiple Visual Features with a Rough Map

An Efficient Image-Based Telepresence System for Videoconferencing

Data Processing Algorithms for Generating Textured 3D Building Facade Meshes from Laser Scans and Camera Images

Contact Info

Product

Resources

About