Range image segmentation based on function approximation

Maître, Gilbert; Hügli, Heinz; Tièche, François; Amann, Julian

doi:10.1117/12.2294279

Cited by 10 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For that reason, we approximate the surfaces with planar surface patches in 3-D. This polyhedral world assumption may be too strong, but, the region growing algorithm presented can be extended to higher-order surfaces as done in [11]. A planar patch is defined by the equation…”

Section: Surface Representationmentioning

confidence: 99%

See 1 more Smart Citation

Multi-image Region Growing for Integrating Disparity Maps

Leloglu

Halıcı

1999

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

Abstract. In this paper, a multi-image region growing algorithm to obtain planar 3-D surfaces in the object space from multiple dense disparity maps, is presented. A surface patch is represented by a plane equation and a set of pixels in multiple images. The union of back projections of all pixels in the set onto the infinite plane, forms the surface patch. Thanks to that hybrid representation of planar surfaces, region growing (both region aggregation and region merging) is performed on all images simultaneously. Planar approximation is done in object space by linear least square estimation using all data points of the region under question in all images. Linear edge segments detected on colour images are used for constraining the region growing during the region aggregation phase as well as for detection of borders of surface patches. Experimental results on disparity maps obtained from high-resolution aerial images of urban areas demonstrate the performance of the algorithm.

show abstract

Section: Surface Representationmentioning

confidence: 99%

“…Region growing is used frequently for range image segmentation [11], sometimes with the contribution of edge detection [13]. Algorithms for range image segmentation are not always directly applicable to disparity maps.…”

Section: Related Workmentioning

confidence: 99%

Multi-image Region Growing for Integrating Disparity Maps

Leloglu

Halıcı

1999

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

show abstract

“…Pixels are appended to the seed region as long as they do not differ significantly from the average grey level, which of course needs to be updated as new pixels join the region. Though this may be satisfactory for segmentation of many images, it has been argued that a more plausible description of the imaging process is to consider regions as piecewise smooth [1,5,7,8,16]. Thus the homogeneity criterion must be modified, so that pixels are appended to a region as long as their differences to a function (e.g., polynomial) are not larger than a threshold.…”

Section: Introductionmentioning

confidence: 99%

Array algebra polynomial fitting for image segmentation

Wiman

1996

J Math Imaging Vis

View full text Add to dashboard Cite

Segmentation of digital images is a key problem for automation of object recognition and object reconstruction. Area based segmentations, like region growing and split-and-merge, may use similarity with respect to some grey level property as predicate for appending pixels to a region. Regions of particular interest, for example roofs of buildings in aerial photographs, are seldom homogeneous with respect to grey level. There are often position dependent trends in the grey values of a region, that is; the image is piecewise smooth. These trends may be modelled by functional fitting. This turns image segmentation into a computer intensive least squares problem. In this article, a split-and-merge procedure using array algebra is proposed to make polynomial fitting faster. The splitting is two to three times faster than using regular matrix algebra. For 3D images it is four to nine times faster. The merging is performed without accessing the image.

show abstract

“…Early works used range images (e.g. (Maitre et al, 1990), (Lim et al, 1990)) similar to airborne laserscanner data. Recent approaches prefer algorithms on 3d-point clouds.…”

Section: Previous Workmentioning

confidence: 99%

Probabilistic Feasibility of the Reconstruction Process of Russian-Orthodox Churches

Chizhova¹,

Brunn²,

Stilla³

2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:The cultural human heritage is important for the identity of following generations and has to be preserved in a suitable manner. In the course of time a lot of information about former cultural constructions has been lost because some objects were strongly damaged by natural erosion or on account of human work or were even destroyed. It is important to capture still available building parts of former buildings, mostly ruins. This data could be the basis for a virtual reconstruction. Laserscanning offers in principle the possibility to take up extensively surfaces of buildings in its actual status. In this paper we assume a priori given 3d-laserscanner data, 3d point cloud for the partly destroyed church. There are many well known algorithms, that describe different methods of extraction and detection of geometric primitives, which are recognized separately in 3d points clouds. In our work we put them in a common probabilistic framework, which guides the complete reconstruction process of complex buildings, in our case russian-orthodox churches. Churches are modeled with their functional volumetric components, enriched with a priori known probabilities, which are deduced from a database of russian-orthodox churches. Each set of components represents a complete church. The power of the new method is shown for a simulated dataset of 100 russian-orthodox churches.

show abstract

Range image segmentation based on function approximation

Cited by 10 publications

References 6 publications

Multi-image Region Growing for Integrating Disparity Maps

Multi-image Region Growing for Integrating Disparity Maps

Array algebra polynomial fitting for image segmentation

Probabilistic Feasibility of the Reconstruction Process of Russian-Orthodox Churches

Contact Info

Product

Resources

About