Segmentation of Laser Point Clouds in Urban Areas by a Modified Normalized Cut Method

2019 ◽  
Vol 41 (12) ◽  
pp. 3034-3047
Author(s):  
Avishek Dutta ◽  
Johannes Engels ◽  
Michael Hahn
Author(s):  
A. Dutta ◽  
J. Engels ◽  
M. Hahn

Normalized Cut according to (Shi and Malik 2000) is a well-established divisive image segmentation method. Here we use Normalized Cut for the segmentation of laser point clouds in urban areas. In particular we propose an edge weight measure which takes local plane parameters, RGB values and eigenvalues of the covariance matrices of the local point distribution into account. Due to its target function, Normalized Cut favours cuts with “small cut lines/surfaces”, which appears to be a drawback for our application. We therefore modify the target function, weighting the similarity measures with distant-depending weights. We call the induced minimization problem “<i>Distance-weighted Cut</i>” (DWCut). The new target function leads to a slightly more complicated generalized eigenvalue problem than in case of the Normalized Cut; on the other hand, the new target function is easier to interpret and avoids the just-mentioned drawback. DWCut can be beneficially combined with an aggregation in order to reduce the computational effort and to avoid shortcomings due to insufficient plane parameters. <br><br> Finally we present examples for the successful application of the Distance-weighted Cut principle. The method was implemented as a plugin into the free and open source geographic information system SAGA; for preprocessing steps the proprietary SAGA-based LiDAR software LIS was applied.


Author(s):  
Y. Yang ◽  
S. Song ◽  
C. Toth

Abstract. Place recognition or loop closure is a technique to recognize landmarks and/or scenes visited by a mobile sensing platform previously in an area. The technique is a key function for robustly practicing Simultaneous Localization and Mapping (SLAM) in any environment, including the global positioning system (GPS) denied environment by enabling to perform the global optimization to compensate the drift of dead-reckoning navigation systems. Place recognition in 3D point clouds is a challenging task which is traditionally handled with the aid of other sensors, such as camera and GPS. Unfortunately, visual place recognition techniques may be impacted by changes in illumination and texture, and GPS may perform poorly in urban areas. To mitigate this problem, state-of-art Convolutional Neural Networks (CNNs)-based 3D descriptors may be directly applied to 3D point clouds. In this work, we investigated the performance of different classification strategies utilizing a cutting-edge CNN-based 3D global descriptor (PointNetVLAD) for place recognition task on the Oxford RobotCar dataset.


Author(s):  
X.-F. Xing ◽  
M. A. Mostafavi ◽  
G. Edwards ◽  
N. Sabo

<p><strong>Abstract.</strong> Automatic semantic segmentation of point clouds observed in a 3D complex urban scene is a challenging issue. Semantic segmentation of urban scenes based on machine learning algorithm requires appropriate features to distinguish objects from mobile terrestrial and airborne LiDAR point clouds in point level. In this paper, we propose a pointwise semantic segmentation method based on our proposed features derived from Difference of Normal and the features “directional height above” that compare height difference between a given point and neighbors in eight directions in addition to the features based on normal estimation. Random forest classifier is chosen to classify points in mobile terrestrial and airborne LiDAR point clouds. The results obtained from our experiments show that the proposed features are effective for semantic segmentation of mobile terrestrial and airborne LiDAR point clouds, especially for vegetation, building and ground classes in an airborne LiDAR point clouds in urban areas.</p>


Author(s):  
J. Gehrung ◽  
M. Hebel ◽  
M. Arens ◽  
U. Stilla

Abstract. Change detection is an important tool for processing multiple epochs of mobile LiDAR data in an efficient manner, since it allows to cope with an otherwise time-consuming operation by focusing on regions of interest. State-of-the-art approaches usually either do not handle the case of incomplete observations or are computationally expensive. We present a novel method based on a combination of point clouds and voxels that is able to handle said case, thereby being computationally less expensive than comparable approaches. Furthermore, our method is able to identify special classes of changes such as partially moved, fully moved and deformed objects in addition to the appeared and disappeared objects recognized by conventional approaches. The performance of our method is evaluated using the publicly available TUM City Campus datasets, showing an overall accuracy of 88 %.


Author(s):  
J. Schachtschneider ◽  
C. Brenner

Abstract. The development of automated and autonomous vehicles requires highly accurate long-term maps of the environment. Urban areas contain a large number of dynamic objects which change over time. Since a permanent observation of the environment is impossible and there will always be a first time visit of an unknown or changed area, a map of an urban environment needs to model such dynamics.In this work, we use LiDAR point clouds from a large long term measurement campaign to investigate temporal changes. The data set was recorded along a 20 km route in Hannover, Germany with a Mobile Mapping System over a period of one year in bi-weekly measurements. The data set covers a variety of different urban objects and areas, weather conditions and seasons. Based on this data set, we show how scene and seasonal effects influence the measurement likelihood, and that multi-temporal maps lead to the best positioning results.


Author(s):  
Han Hu ◽  
Chongtai Chen ◽  
Bo Wu ◽  
Xiaoxia Yang ◽  
Qing Zhu ◽  
...  

Textureless and geometric discontinuities are major problems in state-of-the-art dense image matching methods, as they can cause visually significant noise and the loss of sharp features. Binary census transform is one of the best matching cost methods but in textureless areas, where the intensity values are similar, it suffers from small random noises. Global optimization for disparity computation is inherently sensitive to parameter tuning in complex urban scenes, and must compromise between smoothness and discontinuities. The aim of this study is to provide a method to overcome these issues in dense image matching, by extending the industry proven Semi-Global Matching through 1) developing a ternary census transform, which takes three outputs in a single order comparison and encodes the results in two bits rather than one, and also 2) by using texture-information to self-tune the parameters, which both preserves sharp edges and enforces smoothness when necessary. Experimental results using various datasets from different platforms have shown that the visual qualities of the triangulated point clouds in urban areas can be largely improved by these proposed methods.


Author(s):  
Y.-H. Lu ◽  
J.-Y. Han

Abstract. Global Navigation Satellite System (GNSS) is a matured modern technique for spatial data acquisition. Its performance has a great correlation with GNSS receiver position. However, high-density building in urban areas causes signal obstructions and thus hinders GNSS’s serviceability. Consequently, GNSS positioning is weakened in urban areas, so deriving proper improvement resolutions is a necessity. Because topographic effects are considered the main factor that directly block signal transmission between satellites and receivers, this study integrated aerial borne LiDAR point clouds and a 2D building boundary map to provide reliable 3D spatial information to analyze topographic effects. Using such vector data not only reflected high-quality GNSS satellite visibility calculations, but also significantly reduced data amount and processing time. A signal obstruction analysis technique and optimized computational algorithm were also introduced. In conclusion, this paper proposes using superimposed column method to analyze GNSS receivers’ surrounding environments and thus improve GNSS satellite visibility predictions in an efficient and reliable manner.


2020 ◽  
Vol 171 ◽  
pp. 02008
Author(s):  
Krzysztof Pyszny ◽  
Mariusz Sojka ◽  
Rafał Wróżyński

Planning green infrastructure in the cities is a challenging task for planners and city managers. Developing multifunctional green space systems provide many benefits including: increasing water retention, mitigating urban heat island effect, microclimate regulation, reducing air, water and noise pollution and conservation biodiversity. The greenery in the city also have an impact on human health. The paper presents the possibilities of using LiDAR data mapping vegetation density in urban areas on the example of Gorzów Wielkopolski (Poland). Maps made as a result of processing the point clouds obtained from airborne laser scanning represents the most accurate, comprehensive and detailed assessment of Gorzów Wielkopolski vegetation cover to date and establishes the baseline for greenery governance and planning of green infrastructure in the city.


2013 ◽  
Vol 373-375 ◽  
pp. 583-586
Author(s):  
De Yong Wang ◽  
Ji Fan

In this paper an improved image segmentation algorithm based on watershed transform is presented. Firstly the normalized cut method and watershed transform are explained and analyzed. Secondly the idea of the improved algorithm and the main formula are explained. We consider the area and perimeter when we merge adjacent regions. We define a new weight value and discuss the value of the parameter αand β. Finally the experiment result is presented. The new algorithm reduces the nodes and the computational demand of the common normalized cut technique.


Sign in / Sign up

Export Citation Format

Share Document