scholarly journals OPTIMAL INFORMATION EXTRACTION OF LASER SCANNING DATASET BY SCALE-ADAPTIVE REDUCTION

Author(s):  
Y. Zang ◽  
B. Yang

3D laser technology is widely used to collocate the surface information of object. For various applications, we need to extract a good perceptual quality point cloud from the scanned points. To solve the problem, most of existing methods extract important points based on a fixed scale. However, geometric features of 3D object come from various geometric scales. We propose a multi-scale construction method based on radial basis function. For each scale, important points are extracted from the point cloud based on their importance. We apply a perception metric Just-Noticeable-Difference to measure degradation of each geometric scale. Finally, scale-adaptive optimal information extraction is realized. Experiments are undertaken to evaluate the effective of the proposed method, suggesting a reliable solution for optimal information extraction of object.

Sensors ◽  
2019 ◽  
Vol 19 (8) ◽  
pp. 1852 ◽  
Author(s):  
Junjie Zhou ◽  
Hongqiang Wei ◽  
Guiyun Zhou ◽  
Lihui Song

The separation of leaf and wood points is an essential preprocessing step for extracting many of the parameters of a tree from terrestrial laser scanning data. The multi-scale method and the optimal scale method are two of the most widely used separation methods. In this study, we extend the optimal scale method to the multi-optimal-scale method, adaptively selecting multiple optimal scales for each point in the tree point cloud to increase the distinctiveness of extracted geometric features. Compared with the optimal scale method, our method achieves higher separation accuracy. Compared with the multi-scale method, our method achieves more stable separation accuracy with a limited number of optimal scales. The running time of our method is greatly reduced when the optimization strategy is applied.


Author(s):  
R. Blomley ◽  
M. Weinmann

In this paper, we present a novel framework for the semantic labeling of airborne laser scanning data on a per-point basis. Our framework uses collections of spherical and cylindrical neighborhoods for deriving a multi-scale representation for each point of the point cloud. Additionally, spatial bins are used to approximate the topography of the considered scene and thus obtain normalized heights. As the derived features are related with different units and a different range of values, they are first normalized and then provided as input to a standard Random Forest classifier. To demonstrate the performance of our framework, we present the results achieved on two commonly used benchmark datasets, namely the <i>Vaihingen Dataset</i> and the <i>GML Dataset A</i>, and we compare the results to the ones presented in related investigations. The derived results clearly reveal that our framework excells in classifying the different classes in terms of pointwise classification and thus also represents a significant achievement for a subsequent spatial regularization.


2019 ◽  
Vol 11 (23) ◽  
pp. 2846 ◽  
Author(s):  
Tong ◽  
Li ◽  
Zhang ◽  
Chen ◽  
Zhang ◽  
...  

Accurate and effective classification of lidar point clouds with discriminative features expression is a challenging task for scene understanding. In order to improve the accuracy and the robustness of point cloud classification based on single point features, we propose a novel point set multi-level aggregation features extraction and fusion method based on multi-scale max pooling and latent Dirichlet allocation (LDA). To this end, in the hierarchical point set feature extraction, point sets of different levels and sizes are first adaptively generated through multi-level clustering. Then, more effective sparse representation is implemented by locality-constrained linear coding (LLC) based on single point features, which contributes to the extraction of discriminative individual point set features. Next, the local point set features are extracted by combining the max pooling method and the multi-scale pyramid structure constructed by the point’s coordinates within each point set. The global and the local features of the point sets are effectively expressed by the fusion of multi-scale max pooling features and global features constructed by the point set LLC-LDA model. The point clouds are classified by using the point set multi-level aggregation features. Our experiments on two scenes of airborne laser scanning (ALS) point clouds—a mobile laser scanning (MLS) scene point cloud and a terrestrial laser scanning (TLS) scene point cloud—demonstrate the effectiveness of the proposed point set multi-level aggregation features for point cloud classification, and the proposed method outperforms other related and compared algorithms.


Author(s):  
F. Poux ◽  
R. Neuville ◽  
R. Billen

Reasoning from information extraction given by point cloud data mining allows contextual adaptation and fast decision making. However, to achieve this perceptive level, a point cloud must be semantically rich, retaining relevant information for the end user. This paper presents an automatic knowledge-based method for pre-processing multi-sensory data and classifying a hybrid point cloud from both terrestrial laser scanning and dense image matching. Using 18 features including sensor’s biased data, each tessera in the high-density point cloud from the 3D captured complex mosaics of Germigny-des-prés (France) is segmented via a colour multi-scale abstraction-based featuring extracting connectivity. A 2D surface and outline polygon of each tessera is generated by a RANSAC plane extraction and convex hull fitting. Knowledge is then used to classify every tesserae based on their size, surface, shape, material properties and their neighbour’s class. The detection and semantic enrichment method shows promising results of 94% correct semantization, a first step toward the creation of an archaeological smart point cloud.


Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6969
Author(s):  
Xiangda Lei ◽  
Hongtao Wang ◽  
Cheng Wang ◽  
Zongze Zhao ◽  
Jianqi Miao ◽  
...  

Airborne laser scanning (ALS) point cloud has been widely used in various fields, for it can acquire three-dimensional data with a high accuracy on a large scale. However, due to the fact that ALS data are discretely, irregularly distributed and contain noise, it is still a challenge to accurately identify various typical surface objects from 3D point cloud. In recent years, many researchers proved better results in classifying 3D point cloud by using different deep learning methods. However, most of these methods require a large number of training samples and cannot be widely used in complex scenarios. In this paper, we propose an ALS point cloud classification method to integrate an improved fully convolutional network into transfer learning with multi-scale and multi-view deep features. First, the shallow features of the airborne laser scanning point cloud such as height, intensity and change of curvature are extracted to generate feature maps by multi-scale voxel and multi-view projection. Second, these feature maps are fed into the pre-trained DenseNet201 model to derive deep features, which are used as input for a fully convolutional neural network with convolutional and pooling layers. By using this network, the local and global features are integrated to classify the ALS point cloud. Finally, a graph-cuts algorithm considering context information is used to refine the classification results. We tested our method on the semantic 3D labeling dataset of the International Society for Photogrammetry and Remote Sensing (ISPRS). Experimental results show that overall accuracy and the average F1 score obtained by the proposed method is 89.84% and 83.62%, respectively, when only 16,000 points of the original data are used for training.


2020 ◽  
Vol 12 (6) ◽  
pp. 960
Author(s):  
Xingyu Yang ◽  
Yuchun Huang ◽  
Qiulan Zhang

With the rapid increase of power supply demand, a large amount of stockpiles of coal have been formed during the process of coal excavation and transportation between the mines, ports, power plants and etc. Quantitative parameters, especially the volume of stockpile are important for the planning of coal production and consumption. Although laser scanning can collect the dense 3D coordinates of the stockpile surface for its quantification, stockpiles of coal have irregular shape, size, height, and base conditions, and may be overlapped with each other, which makes it hard to measure the different stockpiles automatically and accurately. This paper proposes an algorithm to extract and measure the stockpiles from the 3D point cloud data using the multi-scale directional curvature. Firstly, the second-order directional curvature analysis along multiple directions and at multiple scales is proposed to extract the distinctive ridge of crest in the point cloud of stockpiles. Then, starting with the crest points, a competitive growing strategy is proposed to accurately locate the points of slope in the stockpile. Finally, the stockpile’s volume is calculated by reconstructing the complete points of crest and slope with many meshes and triangular prisms through the subsurface fitting and surface reconstruction. Experiments on both the synthetic and real point cloud of stockpiles demonstrate that the proposed algorithm can extract the stockpiles with the average accuracy over 93.5% and measure the volume of stockpiles with the average precision over 93.7%. It is promising for automatically measuring the stockpiles like sand, soybean, etc., and facilitating the scientific storage and transportation management, as well as the maintenance of safety inventory during operation.


Author(s):  
W. Ao ◽  
L. Wang ◽  
J. Shan

<p><strong>Abstract.</strong> Point cloud classification is quite a challenging task due to the existence of noises, occlusion and various object types and sizes. Currently, the commonly used statistics-based features cannot accurately characterize the geometric information of a point cloud. This limitation often leads to feature confusion and classification mistakes (e.g., points of building corners and vegetation always share similar statistical features in a local neighbourhood, such as curvature, sphericity, etc). This study aims at solving this problem by leveraging the advantage of both the supervoxel segmentation and multi-scale features. For each point, its multi-scale features within different radii are extracted. Simultaneously, the point cloud is partitioned into simple supervoxel segments. After that, the class probability of each point is predicted by the proposed SegMSF approach that combines multi-scale features with the supervoxel segmentation results. At the end, the effect of data noises is supressed by using a global optimization that encourages spatial consistency of class labels. The proposed method is tested on both airborne laser scanning (ALS) and mobile laser scanning (MLS) point clouds. The experimental results demonstrate that the proposed method performs well in terms of classifying objects of different scales and is robust to noise.</p>


2016 ◽  
Vol 136 (8) ◽  
pp. 1078-1084
Author(s):  
Shoichi Takei ◽  
Shuichi Akizuki ◽  
Manabu Hashimoto

2020 ◽  
Vol 961 (7) ◽  
pp. 47-55
Author(s):  
A.G. Yunusov ◽  
A.J. Jdeed ◽  
N.S. Begliarov ◽  
M.A. Elshewy

Laser scanning is considered as one of the most useful and fast technologies for modelling. On the other hand, the size of scan results can vary from hundreds to several million points. As a result, the large volume of the obtained clouds leads to complication at processing the results and increases the time costs. One way to reduce the volume of a point cloud is segmentation, which reduces the amount of data from several million points to a limited number of segments. In this article, we evaluated effect on the performance, the accuracy of various segmentation methods and the geometric accuracy of the obtained models at density changes taking into account the processing time. The results of our experiment were compared with reference data in a form of comparative analysis. As a conclusion, some recommendations for choosing the best segmentation method were proposed.


Sign in / Sign up

Export Citation Format

Share Document