Fast Semantic Segmentation of 3d Point Clouds With Strongly Varying Density

Häckel, Timo; Wegner, Jan Dirk; Schindler, Konrad

doi:10.5194/isprsannals-iii-3-177-2016

Cited by 174 publications

(127 citation statements)

References 22 publications

Supporting

Mentioning

127

Contrasting

Order By: Relevance

“…The set of descriptors computed for each point in 3D space is presented in Table 1. For the computation of geometric features, we adapt the method based on eigenanalyses, which is widely applied in the classification literature [32,33]. The spatial coordinates of the neighboring points are used to compute a local 3D structure covariance tensor, whose eigenvalues of λ max ≥ λ med ≥ λ min together with the eigenvector e min serve as a base for the computation of local geometry features.…”

Section: Data Structure Approximation and Feature Extractionmentioning

confidence: 99%

Supervised Detection of Façade Openings in 3D Point Clouds with Thermal Attributes

2020

View full text Add to dashboard Cite

Targeted energy management and control is becoming an increasing concern in the building sector. Automatic analyses of thermal data, which minimize the subjectivity of the assessment and allow for large-scale inspections, are therefore of high interest. In this study, we propose an approach for a supervised extraction of façade openings (windows and doors) from photogrammetric 3D point clouds attributed to RGB and thermal infrared (TIR) information. The novelty of the proposed approach is in the combination of thermal information with other available characteristics of data for a classification performed directly in 3D space. Images acquired in visible and thermal infrared spectra serve as input data for the camera pose estimation and the reconstruction of 3D scene geometry. To investigate the relevance of different information types to the classification performance, a Random Forest algorithm is applied to various sets of computed features. The best feature combination is then used as an input for a Conditional Random Field that enables us to incorporate contextual information and consider the interaction between the points. The evaluation executed on a per-point level shows that the fusion of all available information types together with context consideration allows us to extract objects with 90% completeness and 95% correctness. A respective assessment executed on a per-object level shows 97% completeness and 88% accuracy.

show abstract

Section: Data Structure Approximation and Feature Extractionmentioning

confidence: 99%

Supervised Detection of Façade Openings in 3D Point Clouds with Thermal Attributes

2020

View full text Add to dashboard Cite

show abstract

“…Several scholars have put effort into road furniture recognition by introducing supervised approaches [18,[30][31][32][33][34][35][36].…”

Section: Introductionmentioning

confidence: 99%

“…Hackel et al [35] described an efficient and effective method for point-wise semantic classification, which can deal with point clouds captured by LiDAR or derived from photogrammetric reconstruction with high-density variations. Instead of computing optimal neighborhoods for each point, they down-sample the entire point cloud to generate a multi-scale pyramid with decreasing point density and compute features for every voxel at every scale level.…”

Section: Introductionmentioning

confidence: 99%

Pole-Like Road Furniture Detection and Decomposition in Mobile Laser Scanning Data Based on Spatial Relations

Elberink

Vosselman

2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:Road furniture plays an important role in road safety. To enhance road safety, policies that encourage the road furniture inventory are prevalent in many countries. Such an inventory can be remarkably facilitated by the automatic recognition of road furniture. Current studies typically detect and classify road furniture as one single above-ground component only, which is inadequate for road furniture with multiple functions such as a streetlight with a traffic sign attached. Due to the recent developments in mobile laser scanners, more accurate data is available that allows for the segmentation of road furniture at a detailed level. In this paper, we propose an automatic framework to decompose road furniture into different components based on their spatial relations in a three-step procedure: first, pole-like road furniture are initially detected by removing ground points and an initial classification. Then, the road furniture is decomposed into poles and attachments. The result of the decomposition is taken as a feedback to remove spurious pole-like road furniture as a third step. If there are no poles extracted in the decomposition stage, these incorrectly detected pole-like road furniture-such as the pillars of buildings-will be removed from the detection list. We further propose a method to evaluate the results of the decomposition. Compared with our previous work, the performance of decomposition has been much improved. In our test sites, the correctness of detection is higher than 90% and the completeness is approximately 95%, showing that our procedure is competitive to state of the art methods in the field of pole-like road furniture detection. Compared to our previous work, the optimized decomposition improves the correctness by 7.3% and 18.4% in the respective test areas. In conclusion, we demonstrate that our method decomposes pole-like road furniture into poles and attachments with respect to their spatial relations, which is crucial for road furniture interpretation.

show abstract

“…The identification of the neighborhood typically employs either the k-nearest-neighborhood (KNN) search [29] or the instance radius search [5]. The former is based on a fixed number of k neighboring points that approximates the density-adaptive search.…”

Section: Region Growing Segmentationmentioning

confidence: 99%

Automating Parameter Learning for Classifying Terrestrial LiDAR Point Cloud Using 2D Land Cover Maps

Feng

Zhou

2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:The automating classification of point clouds capturing urban scenes is critical for supporting applications that demand three-dimensional (3D) models. Achieving this goal, however, is met with challenges because of the varying densities of the point clouds and the complexity of the 3D data. In order to increase the level of automation in the point cloud classification, this study proposes a segment-based parameter learning method that incorporates a two-dimensional (2D) land cover map, in which a strategy of fusing the 2D land cover map and the 3D points is first adopted to create labelled samples, and a formalized procedure is then implemented to automatically learn the following parameters of point cloud classification: the optimal scale of the neighborhood for segmentation, optimal feature set, and the training classifier. It comprises four main steps, namely: (1) point cloud segmentation; (2) sample selection; (3) optimal feature set selection; and (4) point cloud classification. Three datasets containing the point cloud data were used in this study to validate the efficiency of the proposed method. The first two datasets cover two areas of the National University of Singapore (NUS) campus while the third dataset is a widely used benchmark point cloud dataset of Oakland, Pennsylvania. The classification parameters were learned from the first dataset consisting of a terrestrial laser-scanning data and a 2D land cover map, and were subsequently used to classify both of the NUS datasets. The evaluation of the classification results showed overall accuracies of 94.07% and 91.13%, respectively, indicating that the transition of the knowledge learned from one dataset to another was satisfactory. The classification of the Oakland dataset achieved an overall accuracy of 97.08%, which further verified the transferability of the proposed approach. An experiment of the point-based classification was also conducted on the first dataset and the result was compared to that of the segment-based classification. The evaluation revealed that the overall accuracy of the segment-based classification is indeed higher than that of the point-based classification, demonstrating the advantage of the segment-based approaches.

show abstract

Fast Semantic Segmentation of 3d Point Clouds With Strongly Varying Density

Cited by 174 publications

References 22 publications

Supervised Detection of Façade Openings in 3D Point Clouds with Thermal Attributes

Supervised Detection of Façade Openings in 3D Point Clouds with Thermal Attributes

Pole-Like Road Furniture Detection and Decomposition in Mobile Laser Scanning Data Based on Spatial Relations

Automating Parameter Learning for Classifying Terrestrial LiDAR Point Cloud Using 2D Land Cover Maps

Contact Info

Product

Resources

About