Fast Reconstruction of 3D Point Cloud Model Using Visual SLAM on Embedded UAV Development Platform
In recent years, the rapid development of unmanned aerial vehicle (UAV) technologies has made data acquisition increasingly convenient, and three-dimensional (3D) reconstruction has emerged as a popular subject of research in this context. These 3D models have many advantages, such as the ability to...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/20/3308 |
| _version_ | 1797551283937214464 |
|---|---|
| author | Fang Huang Hao Yang Xicheng Tan Shuying Peng Jian Tao Siyuan Peng |
| author_facet | Fang Huang Hao Yang Xicheng Tan Shuying Peng Jian Tao Siyuan Peng |
| author_sort | Fang Huang |
| collection | DOAJ |
| description | In recent years, the rapid development of unmanned aerial vehicle (UAV) technologies has made data acquisition increasingly convenient, and three-dimensional (3D) reconstruction has emerged as a popular subject of research in this context. These 3D models have many advantages, such as the ability to represent realistic scenes and a large amount of information. However, traditional 3D reconstruction methods are expensive, and require long and complex processing. As a result, they cannot rapidly respond when used in time-sensitive applications, e.g., those for such natural disasters as earthquakes, debris flow, etc. Computer vision-based simultaneous localization and mapping (SLAM) along with hardware development based on embedded systems, can provide a solution to this problem. Based on an analysis of the principle and implementation of the visual SLAM algorithm, this study proposes a fast method to quickly reconstruct a dense 3D point cloud model on a UAV platform combined with an embedded graphics processing unit (GPU). The main contributions are as follows: (1) to resolve the contradiction between the resource limitations and the computational complexity of visual SLAM on UAV platforms, the technologies needed to compute resource allocation, communication between nodes, and data transmission and visualization in an embedded environment were investigated to achieve real-time data acquisition and processing. Visual monitoring to this end is also designed and implemented. (2) To solve the problem of time-consuming algorithmic processing, a corresponding parallel algorithm was designed and implemented based on the parallel programming framework of the compute unified device architecture (CUDA). (3) The visual odometer and methods of 3D “map” reconstruction were designed using under a monocular vision sensor to implement the prototype of the fast 3D reconstruction system. Based on preliminary results of the 3D modeling, the following was noted: (1) the proposed method was feasible. By combining UAV, SLAM, and parallel computing, a simple and efficient 3D reconstruction model of an unknown area was obtained for specific applications. (2) The parallel SLAM algorithm used in this method improved the efficiency of the SLAM algorithm. On the one hand, the SLAM algorithm required 1/6 of the time taken by the structure-from-motion algorithm. On the other hand, the speedup obtained using the parallel SLAM algorithm based on the embedded GPU on our test platform was 7.55 × that of the serial algorithm. (3) The depth map results show that the effective pixel with an error less than 15cm is close to 60%. |
| first_indexed | 2024-03-10T15:42:23Z |
| format | Article |
| id | doaj.art-67caf3bb04fd4d4aa0b7fb90dc2450d6 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T15:42:23Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-67caf3bb04fd4d4aa0b7fb90dc2450d62023-11-20T16:41:38ZengMDPI AGRemote Sensing2072-42922020-10-011220330810.3390/rs12203308Fast Reconstruction of 3D Point Cloud Model Using Visual SLAM on Embedded UAV Development PlatformFang Huang0Hao Yang1Xicheng Tan2Shuying Peng3Jian Tao4Siyuan Peng5School of Recourses and Environment, University of Electronic Science and Technology of China (UESTC), Chengdu 611731, ChinaSchool of Recourses and Environment, University of Electronic Science and Technology of China (UESTC), Chengdu 611731, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, ChinaSchool of Recourses and Environment, University of Electronic Science and Technology of China (UESTC), Chengdu 611731, ChinaTexas A&M Engineering Experiment Station (TEES), Texas A&M University, College Station, TX 77843, USASchool of Recourses and Environment, University of Electronic Science and Technology of China (UESTC), Chengdu 611731, ChinaIn recent years, the rapid development of unmanned aerial vehicle (UAV) technologies has made data acquisition increasingly convenient, and three-dimensional (3D) reconstruction has emerged as a popular subject of research in this context. These 3D models have many advantages, such as the ability to represent realistic scenes and a large amount of information. However, traditional 3D reconstruction methods are expensive, and require long and complex processing. As a result, they cannot rapidly respond when used in time-sensitive applications, e.g., those for such natural disasters as earthquakes, debris flow, etc. Computer vision-based simultaneous localization and mapping (SLAM) along with hardware development based on embedded systems, can provide a solution to this problem. Based on an analysis of the principle and implementation of the visual SLAM algorithm, this study proposes a fast method to quickly reconstruct a dense 3D point cloud model on a UAV platform combined with an embedded graphics processing unit (GPU). The main contributions are as follows: (1) to resolve the contradiction between the resource limitations and the computational complexity of visual SLAM on UAV platforms, the technologies needed to compute resource allocation, communication between nodes, and data transmission and visualization in an embedded environment were investigated to achieve real-time data acquisition and processing. Visual monitoring to this end is also designed and implemented. (2) To solve the problem of time-consuming algorithmic processing, a corresponding parallel algorithm was designed and implemented based on the parallel programming framework of the compute unified device architecture (CUDA). (3) The visual odometer and methods of 3D “map” reconstruction were designed using under a monocular vision sensor to implement the prototype of the fast 3D reconstruction system. Based on preliminary results of the 3D modeling, the following was noted: (1) the proposed method was feasible. By combining UAV, SLAM, and parallel computing, a simple and efficient 3D reconstruction model of an unknown area was obtained for specific applications. (2) The parallel SLAM algorithm used in this method improved the efficiency of the SLAM algorithm. On the one hand, the SLAM algorithm required 1/6 of the time taken by the structure-from-motion algorithm. On the other hand, the speedup obtained using the parallel SLAM algorithm based on the embedded GPU on our test platform was 7.55 × that of the serial algorithm. (3) The depth map results show that the effective pixel with an error less than 15cm is close to 60%.https://www.mdpi.com/2072-4292/12/20/3308fast 3D reconstructionunmanned aerial vehiclecomputer visionembedded system developingROSparallel computing |
| spellingShingle | Fang Huang Hao Yang Xicheng Tan Shuying Peng Jian Tao Siyuan Peng Fast Reconstruction of 3D Point Cloud Model Using Visual SLAM on Embedded UAV Development Platform Remote Sensing fast 3D reconstruction unmanned aerial vehicle computer vision embedded system developing ROS parallel computing |
| title | Fast Reconstruction of 3D Point Cloud Model Using Visual SLAM on Embedded UAV Development Platform |
| title_full | Fast Reconstruction of 3D Point Cloud Model Using Visual SLAM on Embedded UAV Development Platform |
| title_fullStr | Fast Reconstruction of 3D Point Cloud Model Using Visual SLAM on Embedded UAV Development Platform |
| title_full_unstemmed | Fast Reconstruction of 3D Point Cloud Model Using Visual SLAM on Embedded UAV Development Platform |
| title_short | Fast Reconstruction of 3D Point Cloud Model Using Visual SLAM on Embedded UAV Development Platform |
| title_sort | fast reconstruction of 3d point cloud model using visual slam on embedded uav development platform |
| topic | fast 3D reconstruction unmanned aerial vehicle computer vision embedded system developing ROS parallel computing |
| url | https://www.mdpi.com/2072-4292/12/20/3308 |
| work_keys_str_mv | AT fanghuang fastreconstructionof3dpointcloudmodelusingvisualslamonembeddeduavdevelopmentplatform AT haoyang fastreconstructionof3dpointcloudmodelusingvisualslamonembeddeduavdevelopmentplatform AT xichengtan fastreconstructionof3dpointcloudmodelusingvisualslamonembeddeduavdevelopmentplatform AT shuyingpeng fastreconstructionof3dpointcloudmodelusingvisualslamonembeddeduavdevelopmentplatform AT jiantao fastreconstructionof3dpointcloudmodelusingvisualslamonembeddeduavdevelopmentplatform AT siyuanpeng fastreconstructionof3dpointcloudmodelusingvisualslamonembeddeduavdevelopmentplatform |