Guided Next Best View for 3D Reconstruction of Large Complex Structures
In this paper, a Next Best View (NBV) approach with a profiling stage and a novel utility function for 3D reconstruction using an Unmanned Aerial Vehicle (UAV) is proposed. The proposed approach performs an initial scan in order to build a rough model of the structure that is later used to improve c...
| Үндсэн зохиолчид: | , , , , |
|---|---|
| Формат: | Өгүүллэг |
| Хэл сонгох: | English |
| Хэвлэсэн: |
MDPI AG
2019-10-01
|
| Цуврал: | Remote Sensing |
| Нөхцлүүд: | |
| Онлайн хандалт: | https://www.mdpi.com/2072-4292/11/20/2440 |
| _version_ | 1828142804586463232 |
|---|---|
| author | Randa Almadhoun Abdullah Abduldayem Tarek Taha Lakmal Seneviratne Yahya Zweiri |
| author_facet | Randa Almadhoun Abdullah Abduldayem Tarek Taha Lakmal Seneviratne Yahya Zweiri |
| author_sort | Randa Almadhoun |
| collection | DOAJ |
| description | In this paper, a Next Best View (NBV) approach with a profiling stage and a novel utility function for 3D reconstruction using an Unmanned Aerial Vehicle (UAV) is proposed. The proposed approach performs an initial scan in order to build a rough model of the structure that is later used to improve coverage completeness and reduce flight time. Then, a more thorough NBV process is initiated, utilizing the rough model in order to create a dense 3D reconstruction of the structure of interest. The proposed approach exploits the reflectional symmetry feature if it exists in the initial scan of the structure. The proposed NBV approach is implemented with a novel utility function, which consists of four main components: information theory, model density, traveled distance, and predictive measures based on symmetries in the structure. This system outperforms classic information gain approaches with a higher density, entropy reduction and coverage completeness. Simulated and real experiments were conducted and the results show the effectiveness and applicability of the proposed approach. |
| first_indexed | 2024-04-11T19:47:27Z |
| format | Article |
| id | doaj.art-c109c4cfd7514de1b3df75e4f9e6e8d2 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-11T19:47:27Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c109c4cfd7514de1b3df75e4f9e6e8d22022-12-22T04:06:25ZengMDPI AGRemote Sensing2072-42922019-10-011120244010.3390/rs11202440rs11202440Guided Next Best View for 3D Reconstruction of Large Complex StructuresRanda Almadhoun0Abdullah Abduldayem1Tarek Taha2Lakmal Seneviratne3Yahya Zweiri4KU Center for Autonomous Robotic Systems (KUCARS), KU Main Campus, Khalifa University of Science and Technology, Abu Dhabi 127788, UAEKU Center for Autonomous Robotic Systems (KUCARS), KU Main Campus, Khalifa University of Science and Technology, Abu Dhabi 127788, UAEAlgorythma, Autonomous Aerial Lab, Abu Dhabi 112230, UAEKU Center for Autonomous Robotic Systems (KUCARS), KU Main Campus, Khalifa University of Science and Technology, Abu Dhabi 127788, UAEKU Center for Autonomous Robotic Systems (KUCARS), KU Main Campus, Khalifa University of Science and Technology, Abu Dhabi 127788, UAEIn this paper, a Next Best View (NBV) approach with a profiling stage and a novel utility function for 3D reconstruction using an Unmanned Aerial Vehicle (UAV) is proposed. The proposed approach performs an initial scan in order to build a rough model of the structure that is later used to improve coverage completeness and reduce flight time. Then, a more thorough NBV process is initiated, utilizing the rough model in order to create a dense 3D reconstruction of the structure of interest. The proposed approach exploits the reflectional symmetry feature if it exists in the initial scan of the structure. The proposed NBV approach is implemented with a novel utility function, which consists of four main components: information theory, model density, traveled distance, and predictive measures based on symmetries in the structure. This system outperforms classic information gain approaches with a higher density, entropy reduction and coverage completeness. Simulated and real experiments were conducted and the results show the effectiveness and applicability of the proposed approach.https://www.mdpi.com/2072-4292/11/20/2440autonomous explorationcoverage planningaerial robotsuavview planningnavigation3d reconstruction |
| spellingShingle | Randa Almadhoun Abdullah Abduldayem Tarek Taha Lakmal Seneviratne Yahya Zweiri Guided Next Best View for 3D Reconstruction of Large Complex Structures Remote Sensing autonomous exploration coverage planning aerial robots uav view planning navigation 3d reconstruction |
| title | Guided Next Best View for 3D Reconstruction of Large Complex Structures |
| title_full | Guided Next Best View for 3D Reconstruction of Large Complex Structures |
| title_fullStr | Guided Next Best View for 3D Reconstruction of Large Complex Structures |
| title_full_unstemmed | Guided Next Best View for 3D Reconstruction of Large Complex Structures |
| title_short | Guided Next Best View for 3D Reconstruction of Large Complex Structures |
| title_sort | guided next best view for 3d reconstruction of large complex structures |
| topic | autonomous exploration coverage planning aerial robots uav view planning navigation 3d reconstruction |
| url | https://www.mdpi.com/2072-4292/11/20/2440 |
| work_keys_str_mv | AT randaalmadhoun guidednextbestviewfor3dreconstructionoflargecomplexstructures AT abdullahabduldayem guidednextbestviewfor3dreconstructionoflargecomplexstructures AT tarektaha guidednextbestviewfor3dreconstructionoflargecomplexstructures AT lakmalseneviratne guidednextbestviewfor3dreconstructionoflargecomplexstructures AT yahyazweiri guidednextbestviewfor3dreconstructionoflargecomplexstructures |