An Elevation Ambiguity Resolution Method Based on Segmentation and Reorganization of TomoSAR Point Cloud in 3D Mountain Reconstruction

Tomographic Synthetic Aperture Radar (TomoSAR) is a breakthrough of the traditional SAR, which has the three-dimentional (3D) observation ability of layover scenes such as buildings and high mountains. As an advanced system, the airborne array TomoSAR can effectively avoid temporal de-correlation caused by long revisit time, which has great application in high-precision mountain surveying and mapping. The 3D reconstruction using TomoSAR has mainly focused on low targets, while there are few literatures on 3D mountain reconstruction. Due to the layover phenomenon, surveying in high mountain areas remains a difficult task. Consequently, it is meaningful to carry out the research on 3D mountain reconstruction using the airborne array TomoSAR. However, the original TomoSAR mountain point cloud faces the problem of elevation ambiguity. Furthermore, for mountains with complex terrain, the points located in different elevation periods may intersect. This phenomenon increases the difficulty of solving the problem. In this paper, a novel elevation ambiguity resolution method is proposed. First, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Gaussian Mixture Model (GMM) are combined for point cloud segmentation. The former ensures coarse segmentation based on density, and the latter allows fine segmentation of the abnormal categories caused by intersection. Subsequently, the segmentation results are reorganized in the elevation direction to reconstruct all possible point clouds. Finally, the real point cloud can be extracted automatically under the constraints of the boundary and elevation continuity. The performance of the proposed method is demonstrated by simulations and experiments. Based on the airborne array TomoSAR experiment in Leshan City, Sichuan Province, China in 2019, the 3D model of the surveyed mountain is presented. Moreover, three kinds of external data are applied to fully verify the validity of this method.

Placebo effect unboxed: A Review

As in our body, brain is the most powerful part and our mind could be excellent healing tool when any chance is provided. The idea that our brain can be one of the convincing parts in our body for the fake treatment is the real point this is called as placebo effect [1]. This effect refers to the impact of placebo on any one. However, treatments which are not active also were also demonstrated measurable and positive health response [2]. The ability of placebo effect is reviewed as psychological process [1]. In some cases, placebos can exert an influence powerful enough to mimic the effects of real medical treatments. This effect is more than positive thinking [3]. When this response occurs, many people have no idea they are responding to what is essentially a "sugar pill." Placebos are often utilized in medical research to help doctors and scientists discover and better perceive the physiological and mental effects new medications [2] For exactly understanding the placebo effect importance it is crucial to know more about how and why it works. This article explains how this effect is recognized in modern medicine and elements of placebo effect and suggests few conditions under which making utilization of therapeutic potential of this effect could be ethically acceptable, if not warranted.

Spaced out

What was the real point of the flight of Jeff Bezos’s spacecraft?

Hole Repairing Algorithm for 3D Point Cloud Model of Symmetrical Objects Grasped by the Manipulator

For the engineering application of manipulator grasping objects, mechanical arm occlusion and limited imaging angle produce various holes in the reconstructed 3D point clouds of objects. Acquiring a complete point cloud model of the grasped object plays a very important role in the subsequent task planning of the manipulator. This paper proposes a method with which to automatically detect and repair the holes in the 3D point cloud model of symmetrical objects grasped by the manipulator. With the established virtual camera coordinate system and boundary detection, repair and classification of holes, the closed boundaries for the nested holes were detected and classified into two kinds, which correspond to the mechanical claw holes caused by mechanical arm occlusion and the missing surface produced by limited imaging angle. These two kinds of holes were repaired based on surface reconstruction and object symmetry. Experiments on simulated and real point cloud models demonstrate that our approach outperforms the other state-of-the-art 3D point cloud hole repair algorithms.

SFGAN: Unsupervised Generative Adversarial Learning of 3D Scene Flow from the 3D Scene Self

3D scene flow presents the 3D motion of each point in the 3D space, which forms the fundamental 3D motion perception for autonomous driving and server robots. Although the RGBD camera or LiDAR capture discrete 3D points in space, the objects and motions usually are continuous in the macro world. That is, the objects keep themselves consistent as they flow from the current frame to the next frame. Based on this insight, the Generative Adversarial Networks (GAN) is utilized to self-learn 3D scene flow with no need for ground truth. The fake point cloud of the second frame is synthesized from the predicted scene flow and the point cloud of the first frame. The adversarial training of the generator and discriminator is realized through synthesizing indistinguishable fake point cloud and discriminating the real point cloud and the synthesized fake point cloud. The experiments on KITTI scene flow dataset show that our method realizes promising results without ground truth. Just like a human observing a real-world scene, the proposed approach is capable of determining the consistency of the scene at different moments in spite of the exact flow value of each point is unknown in advance. Corresponding author(s) Email: [email protected]

AN EXTRACTION METHOD FOR ROOF POINT CLOUD OF ANCIENT BUILDING USING DEEP LEARNING FRAMEWORK

Chinese ancient architecture is a valuable heritage wealth, especially for roof that reflects the construction age, structural features and cultural connotation. Point cloud data, as a flexible representation with characteristics of fast, precise, non-contact, plays a crucial role in a variety of applications for ancient architectural heritage, such as 3D fine reconstruction, HBIM, disaster monitoring etc. However, there are still many limitations in data editing tasks that need to be worked out manually, which is time-consuming, labor-intensive and error-prone. In recent years, the theoretical advance on deep learning has stimulated the development of various domains, and digital heritage is not in exception. Whenever, deep learning algorithm need to consume a huge amount of labeled date to achieve the purpose for segmentation, resulting a actuality that high labor costs also be acquired. In this paper, inspired by the architectural style similarity between mimetic model and real building, we proposed a method supported by deep learning, which aims to give a solution for the point cloud automatic extraction of roof structure. Firstly, to generate real point cloud, Baoguang Temple, unmanned Aerial Vehicle (UAV) is presented to obtain image collections that are subsequently processed by reconstruction technology. Secondly, a modified Dynamic Graph Convolutional Neural Network (DGCNN) which can learn local features with taking advantage of an edge attention convolution is trained using simulated data and additional attributes of geometric attributes. The mimetic data is sampled from 3DMAX model surface. Finally, we try to extract roof structure of ancient building from real point clouds scenes utilizing the trained model. The experimental results show that the proposed method can extract the rooftop structure from real scene of Baoguang, which illustrates not only effectiveness of approach but also a fact that the simulated source perform potential value when real point cloud datasets are scarce.

GENERATING SYNTHETIC 3D POINT SEGMENTS FOR IMPROVED CLASSIFICATION OF MOBILE LIDAR POINT CLOUDS

Mobile lidar point clouds are commonly used for 3d mapping of road environments as they provide a rich, highly detailed geometric representation of objects on and around the road. However, raw lidar point clouds lack semantic information about the type of objects, which is necessary for various applications. Existing methods for the classification of objects in mobile lidar data, including state of the art deep learning methods, achieve relatively low accuracies, and a primary reason for this under-performance is the inadequacy of available 3d training samples to sufficiently train deep networks. In this paper, we propose a generative model for creating synthetic 3d point segments that can aid in improving the classification performance of mobile lidar point clouds. We train a 3d Adversarial Autoencoder (3dAAE) to generate synthetic point segments that exhibit a high resemblance to and share similar geometric features with real point segments. We evaluate the performance of a PointNet-like classifier trained with and without the synthetic point segments. The evaluation results support our hypothesis that training a classifier with training data augmented with synthetic samples leads to significant improvement in the classification performance. Specifically, our model achieves an F1 score of 0.94 for vehicles and pedestrians and 1.00 for traffic signs.

IMAGE TO POINT CLOUD TRANSLATION USING CONDITIONAL GENERATIVE ADVERSARIAL NETWORK FOR AIRBORNE LIDAR DATA

This study introduces a novel image to a 3D point-cloud translation method with a conditional generative adversarial network that creates a large-scale 3D point cloud. This can generate supervised point clouds observed via airborne LiDAR from aerial images. The network is composed of an encoder to produce latent features of input images, generator to translate latent features to fake point clouds, and discriminator to classify false or real point clouds. The encoder is a pre-trained ResNet; to overcome the difficulty of generating 3D point clouds in an outdoor scene, we use a FoldingNet with features from ResNet. After a fixed number of iterations, our generator can produce fake point clouds that correspond to the input image. Experimental results show that our network can learn and generate certain point clouds using the data from the 2018 IEEE GRSS Data Fusion Contest.

Is there Any Possibility of Reconciliation between Erasmus and Luther?

After five centuries, would it be possible to see any chance of reconciliation between Erasmus and Luther? Looking at this question from the point of view of the three dimensions of the doctrine of grace, we might say some hopeful words. As to the first (1) dimension of grace, at many points even Erasmus admits that human choice must be empowered by God’s grace in order to move in the direction willed by God. But here the real difference is that, for Erasmus, free choice is enabled by the grace given in the creation and it is still naturally efficient in the sinners, whereas Luther sees that there is no freedom because of the human being’s enslavement by unfaith —there is a need for the efficient prevenient movement of the Holy Spirit which alone can create faith. As to the second (2) dimension of grace, following the Catholic tradition, Erasmus knows the conception of (2a) the forensic-juridical forgiveness of sins based on the atonement by the cross of Christ—in this respect there is no real point of controversy between the two. But Erasmus knows nothing about (2b) the union of the sinner with Christ in the Holy Spirit, the Trinitarian participatory conception of justification, central for Luther. In respect to the third (3) dimension of grace, both see possible the cooperation of the believer with God, the difference being Erasmus’ more anthropocentric concept of sanctification if compared with Luther’s emphasis of growth in love enabled by the Holy Spirit.