Fast segmentation of range images into planar regions

Schmitt, Frank; Chen, X.

doi:10.1109/cvpr.1991.139793

Cited by 15 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead of a region growing approach used in the merging stage of the algorithm proposed by Schmitt and Chen (1991), we applied a hierarchical approach proposed by Garland et al (2001), which produces less fragmented surfaces while keeping relevant details. By combining these two approaches a fast detection of dominant planar surfaces is achieved.…”

Section: Detection and Representation Of Surface Segmentsmentioning

confidence: 99%

Place recognition based on matching of planar surfaces and line segments

Cupec

Nyarko

Filko

et al. 2015

The International Journal of Robotics Research

View full text Add to dashboard Cite

This paper considers the potential of using three-dimensional (3D) planar surfaces and line segments detected in depth images for place recognition. A place recognition method is presented that is based on matching sets of surface and line features extracted from depth images provided by a 3D camera to features of the same type contained in a previously created environment model. The considered environment model consists of a set of local models representing particular locations in the modeled environment. Each local model consists of planar surface segments and line segments representing the edges of objects in the environment. The presented method is designed for indoor and urban environments. A computationally efficient pose hypothesis generation approach is proposed that ranks the features according to their potential contribution to the pose information, thereby reducing the time needed for obtaining accurate pose estimation. Furthermore, a robust probabilistic method for selecting the best pose hypothesis is proposed that allows matching of partially overlapping point clouds with gross outliers. The proposed approach is experimentally tested on a benchmark dataset containing depth images acquired in the indoor environment with changes in lighting conditions and the presence of moving objects. A comparison of the proposed method to FAB-MAP and DLoopDetector is reported.

show abstract

Section: Detection and Representation Of Surface Segmentsmentioning

confidence: 99%

Place recognition based on matching of planar surfaces and line segments

Cupec

Nyarko

Filko

et al. 2015

The International Journal of Robotics Research

View full text Add to dashboard Cite

show abstract

“…Depth images acquired by a 3D camera are segmented into sets of 3D points representing approximately planar surface segments using a similar split-and-merge algorithm as in [15], which consists of an iterative Delaunay triangulation method followed by region merging. Instead of a region growing approach used in the merging stage of the algorithm proposed in [15], we applied a hierarchical approach proposed in [16] which produces less fragmented surfaces while keeping relevant details. By combining these two approaches a fast detection of dominant planar surfaces is achieved.…”

Section: A Detection and Representation Of Planar Surface Segmentsmentioning

confidence: 99%

Global Localization Based on 3D Planar Surface Segments Detected by a 3D Camera

Cupec¹,

Nyarko²,

Filko³

et al. 2014

Proceedings of the Croatian Computer Vision Workshop

View full text Add to dashboard Cite

Global localization of a mobile robot using planar surface segments extracted from depth images is considered. The robot's environment is represented by a topological map consisting of local models, each representing a particular location modeled by a set of planar surface segments. The discussed localization approach segments a depth image acquired by a 3D camera into planar surface segments which are then matched to model surface segments. The robot pose is estimated by the Extended Kalman Filter using surface segment pairs as measurements. The reliability and accuracy of the considered approach are experimentally evaluated using a mobile robot equipped by a Microsoft Kinect sensor.

show abstract

“…indoor scenes with large planar surfaces. To generate a triangular mesh from a point cloud we use the algorithm based on recursive triangulation refinement resulting in a Delaunay triangulation proposed in [27]. After the triangulation is completed, each triangle for which the angle between its normal and the optical ray corresponding to one of its vertices is greater than 73° is rejected from the mesh because such triangles mostly represent depth discontinuities rather than an object surface.…”

Section: Segmentation Of 3d Point Clouds Into Approximately Convmentioning

confidence: 99%

Point Cloud Segmentation to Approximately Convex Surfaces for Fruit Recognition

Cupec¹,

Filko²,

Vidović³

et al. 2014

Proceedings of the Croatian Computer Vision Workshop

View full text Add to dashboard Cite

A fruit recognition approach based on segmenting the point cloud acquired by a 3D camera into approximately convex surfaces is considered. A segmentation approach which transforms a depth image into a triangular mesh and then segments this mesh into approximately convex segments is applied to depth images of fruits on trees. An analysis of the results obtained by this approach is performed with the intention to determine how successful the studied method is in detecting fruit as separate objects in a point cloud. The reported analysis gives a valuable insight into the potential applicability of the tested methodology in the preprocessing stage of a fruit recognition system as well as its drawbacks.

show abstract

Fast segmentation of range images into planar regions

Cited by 15 publications

References 6 publications

Place recognition based on matching of planar surfaces and line segments

Place recognition based on matching of planar surfaces and line segments

Global Localization Based on 3D Planar Surface Segments Detected by a 3D Camera

Point Cloud Segmentation to Approximately Convex Surfaces for Fruit Recognition

Contact Info

Product

Resources

About