Conditional Random Field for 3D Point Clouds with Adaptive Data Reduction

Amjoun, Rachida; Straßer, Wolfgang

doi:10.1109/cw.2007.30

Cited by 24 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2005) investigate Mitra and Nguyen's (2003) scale selection algorithm applied to data from different sensors. Lim and Suter (2007) also implement the same approach to determine the support region of the points from a TLS for CRF classification. Pauly et.…”

Section: Local Neighborhood Determinationmentioning

confidence: 99%

“…Regarding the connection between point segmentation and classification, Belton and Lichti (2006) outline a method for point classification by using the variance of the curvature in the local neighborhood of the points followed by a region growing segmentation on terrestrial laser scanning (TLS) point clouds. Lim and Suter, (2007) propose a method employing conditional random fields (CRF) for the classification of 3-D point clouds that are adaptively reduced by omitting geometrically similar features. Niemeyer et.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Min-Cut Based Segmentation of Airborne Lidar Point Clouds

Ural

Shan

2012

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

View full text Add to dashboard Cite

ABSTRACT:Introducing an organization to the unstructured point cloud before extracting information from airborne lidar data is common in many applications. Aggregating the points with similar features into segments in 3-D which comply with the nature of actual objects is affected by the neighborhood, scale, features and noise among other aspects. In this study, we present a min-cut based method for segmenting the point cloud. We first assess the neighborhood of each point in 3-D by investigating the local geometric and statistical properties of the candidates. Neighborhood selection is essential since point features are calculated within their local neighborhood. Following neighborhood determination, we calculate point features and determine the clusters in the feature space. We adapt a graph representation from image processing which is especially used in pixel labeling problems and establish it for the unstructured 3-D point clouds. The edges of the graph that are connecting the points with each other and nodes representing feature clusters hold the smoothness costs in the spatial domain and data costs in the feature domain. Smoothness costs ensure spatial coherence, while data costs control the consistency with the representative feature clusters. This graph representation formalizes the segmentation task as an energy minimization problem. It allows the implementation of an approximate solution by min-cuts for a global minimum of this NP hard minimization problem in low order polynomial time. We test our method with airborne lidar point cloud acquired with maximum planned post spacing of 1.4 m and a vertical accuracy 10.5 cm as RMSE. We present the effects of neighborhood and feature determination in the segmentation results and assess the accuracy and efficiency of the implemented min-cut algorithm as well as its sensitivity to the parameters of the smoothness and data cost functions. We find that smoothness cost that only considers simple distance parameter does not strongly conform to the natural structure of the points. Including shape information within the energy function by assigning costs based on the local properties may help to achieve a better representation for segmentation.

show abstract

Section: Local Neighborhood Determinationmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Min-Cut Based Segmentation of Airborne Lidar Point Clouds

Ural

Shan

2012

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

View full text Add to dashboard Cite

show abstract

“…In the literature review, we also find some techniques, such as [13,14], that segment and label 3D points by employing Markov Random Fields to model their relationship in the local vicinity. These techniques proved to outperform classifiers based only on local features, but at a cost of computational time.…”

Section: Markov Random Fieldsmentioning

confidence: 99%

Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation

2013

View full text Add to dashboard Cite

Segmentation and classification of urban range data into different object classes have several challenges due to certain properties of the data, such as density variation, inconsistencies due to missing data and the large data size that require heavy computation and large memory. A method to classify urban scenes based on a super-voxel segmentation of sparse 3D data obtained from LiDAR sensors is presented. The 3D point cloud is first segmented into voxels, which are then characterized by several attributes transforming them into super-voxels. These are joined together by using a link-chain method rather than the usual region growing algorithm to create objects. These objects are then classified using geometrical models and local descriptors. In order to evaluate the results, a new metric that combines both segmentation and classification results simultaneously is presented. The effects of voxel size and incorporation of RGB color and laser reflectance intensity on the classification results are also discussed. The method is evaluated on standard data sets using different metrics to demonstrate its efficacy.

show abstract

“…Most methods are designed for a much confined scenario, such as focusing on a specific class of objects like roads [6], vehicles [4,10], trees [15,14,9], and buildings [7,3,11]. In these cases, either the scenario is relatively simple that contains only a few objects [8], or the input objects have been segmented from the scene. The theme of these papers is mainly related to recognition and reconstruction of a specific class of objects where object recognition (or classification) techniques play a central role.…”

Section: Introductionmentioning

confidence: 99%

Automatic object segmentation from large scale 3D urban point clouds through manifold embedded mode seeking

Liu

et al. 2011

Proceedings of the 19th ACM International Conference on Multimedia

View full text Add to dashboard Cite

This paper presents a system that can automatically segment objects in large scale 3D point clouds obtained from urban ranging images. The system consists of three steps: The first one involves a ground detection process that can detect relatively complex terrain and separate it from other objects. The second step superpixelizes the remaining objects to speed up the segmentation process. In the final step, a manifold embedded mode seeking method is adopted to segment the point clouds. Even though the segmentation of urban objects is a challenging problem in terms of accuracy and problem scale, our system can efficiently generate very good segmentation results. The proposed manifold learning effectively improves the segmentation performance due to the fact that continuous artificial objects often have manifold-like structures.

show abstract

Conditional Random Field for 3D Point Clouds with Adaptive Data Reduction

Cited by 24 publications

References 16 publications

Min-Cut Based Segmentation of Airborne Lidar Point Clouds

Min-Cut Based Segmentation of Airborne Lidar Point Clouds

Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation

Automatic object segmentation from large scale 3D urban point clouds through manifold embedded mode seeking

Contact Info

Product

Resources

About