The recent success of deep learning in 3-D data analysis relies upon the availability of large annotated data sets. However, creating 3-D data sets with point-level labels are extremely challenging and require a huge amount of human efforts. This paper presents a novel open-sourced method to extract light detection and ranging point clouds with ground truth annotations from a simulator automatically. The virtual sensor can be configured to simulate various real devices, from 2-D laser scanners to 3-D real-time sensors. Experiments are conducted to show that using additional synthetic data for training can: 1) achieve a visible performance boost in accuracy; 2) reduce the amount of manually labeled real-world data; and 3) help to improve the generalization performance across data sets.

No abstract

Convolutional neural networks (CNNs) for 3-D data analyses require a large size of memory and fast computation power, making real-time applications difficult. This article proposes a novel OctreeNet (a sparse 3-D CNN) to analyze the sparse 3-D laser scanning data gathered from outdoor environments. It uses a collection of shallow octrees for 3-D scene representation to reduce the memory footprint of 3-D-CNNs and performs point cloud classification on every single octree. Furthermore, the smallest non-trivial and non-overlapped kernel (SNNK) implements convolution directly on the octree structure to reduce dense 3-D convolutions to matrix operations at sparse locations. The proposed neural network implements a depthfirst search algorithm for real-time predictions. A conditional random field model is utilized for learning global semantic relationships and refining point cloud classification results. Two public data sets (Semantic3D.net and Oakland) are selected to test the classification performance in outdoor scenes with different spatial sparsity. The experiments and benchmark test results show that the proposed approach can be effectively used in realtime 3-D laser data analyses. Note to Practitioners-This article was motivated by the limitations of existing deep learning technologies for analyzing 3-D laser scanning data. This technology enables robots to infer what the surroundings are, which is closely linked to semantic mapping and navigation tasks. Previous deep neural networks have seldom been used in robotic systems since they require a large amount of memory and fast computation power to apply dense 3-D operations. This article presents a sparse 3-D-Convolutional neural network (CNN) for real-time point cloud classification by exploiting the sparsity of 3-D data. This framework requires no GPUs. The practicality of the proposed method is verified on data sets gathered from different platforms and sensors. The proposed network can be adopted for other classification tasks with laser sensors.

A 3D point cloud is one of the main data sources for robot environmental cognition and understanding. Due to the limited computation and memory capacities of the robotic platform, existing semantic segmentation models of 3D point clouds cannot meet the requirements of real-time applications. To solve this problem, a lightweight, fully convolutional network based on an attention mechanism and a sparse tensor is proposed to better balance the accuracy and real-time performance of point cloud semantic segmentation. On the basis of the 3D-Unet structure, a global feature-learning module and a multi-scale feature fusion module are designed. The former improves the ability of features to describe important areas by learning the importance of spatial neighborhoods. The latter realizes the fusion of multi-scale semantic information and suppresses useless information through the task correlation learning of multi-scale features. Additionally, to efficiently process the large-scale point clouds acquired in real time, a sparse tensor-based implementation method is introduced. It is able to reduce unnecessary computation according to the sparsity of the 3D point cloud. As demonstrated by the results of experiments conducted with the SemanticKITTI and NuScenes datasets, our model improves the mIoU metric by 6.4% and 5%, respectively, over existing models that can be applied in real time. Our model is a lightweight model that can meet the requirements of real-time applications.

With the widespread use of mobile and sensing devices, and the popularity of online map-based services, such as navigation services, the volume of spatio-temporal data is growing rapidly. Conventional big data technologies in existing distributed systems cannot effectively process spatio-temporal big data with temporal continuity and spatial proximity. How to construct an effective index for the application requirements of spatio-temporal data in a distributed environment has become one of the hotspots of spatio-temporal big data research. Many spatio-temporal indexing methods have been proposed to support efficient query processing of spatio-temporal data. In this article, the various spatio-temporal big data indexing methods proposed by domestic and foreign researchers from 2010 to 2020 are classified and summarized according to the distributed environment and application background, and the hot issues that need to be paid attention to in the future are proposed according to the changes in application requirements Index Terms-Big Data, distributed system, spatio-temporal index. I. INTRODUCTION W ITH the maturity and widespread use of perception technology, a large number of records containing temporal and spatial marker information are generated, which are called spatio-temporal data [1]. Spatio-temporal data present multisource, heterogeneous, and multidimensional scale characteristics. Space and time are the basic attributes of spatio-temporal data and the basic characteristics of spatio-temporal data processing. With the rapid development of mobile Internet, location services and other technologies and the popularization of mobile devices, e.g., traffic trajectories [2], social media [3], remote sensing image [4], [5], climate observation [6], and other data containing spatio-temporal information rapidly accumulate, are forming a special kind of spatio-temporal big data [7]. In a general sense, spatio-temporal big data refers to the massive spatio-temporal data collection that is difficult to carry out data management, scientific computing, and value discovery within Manuscript