Multidirection Object Detection in Aerial View of Traffic Target under Complex Scenes
Focusing on DOTA, the multidirectional object dataset in aerial view of vehicles, CMDTD has been proposed. The reason why it is difficult for applying the general object detection algorithm in multidirectional object detection has been analyzed in this paper. Based on this, the detection principle o...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/5597168 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832566493269721088 |
|---|---|
| author | Zeqing Zhang Weiwei Lin Yuqiang Zheng |
| author_facet | Zeqing Zhang Weiwei Lin Yuqiang Zheng |
| author_sort | Zeqing Zhang |
| collection | DOAJ |
| description | Focusing on DOTA, the multidirectional object dataset in aerial view of vehicles, CMDTD has been proposed. The reason why it is difficult for applying the general object detection algorithm in multidirectional object detection has been analyzed in this paper. Based on this, the detection principle of CMDTD including its backbone network and multidirectional multi-information detection end module has been studied. In addition, in view of the complexity of the scene faced by aerial view of vehicles, a unique data expansion method is proposed. At last, three datasets have been experimented using the CMDTD algorithm, proving that the cascaded multidirectional object detection algorithm with high effectiveness is superior to other methods. |
| format | Article |
| id | doaj-art-973546378e0a4fbe8fb556ca76c44f58 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-973546378e0a4fbe8fb556ca76c44f582025-02-03T01:03:58ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/55971685597168Multidirection Object Detection in Aerial View of Traffic Target under Complex ScenesZeqing Zhang0Weiwei Lin1Yuqiang Zheng2School of Information Science and Engineering, Xiamen University, Xiamen, ChinaSchool of Electronic and Information Engineering, Fujian Polytechnic Normal University, Fuqing, ChinaSchool of Information Science and Engineering, Xiamen University, Xiamen, ChinaFocusing on DOTA, the multidirectional object dataset in aerial view of vehicles, CMDTD has been proposed. The reason why it is difficult for applying the general object detection algorithm in multidirectional object detection has been analyzed in this paper. Based on this, the detection principle of CMDTD including its backbone network and multidirectional multi-information detection end module has been studied. In addition, in view of the complexity of the scene faced by aerial view of vehicles, a unique data expansion method is proposed. At last, three datasets have been experimented using the CMDTD algorithm, proving that the cascaded multidirectional object detection algorithm with high effectiveness is superior to other methods.http://dx.doi.org/10.1155/2021/5597168 |
| spellingShingle | Zeqing Zhang Weiwei Lin Yuqiang Zheng Multidirection Object Detection in Aerial View of Traffic Target under Complex Scenes Complexity |
| title | Multidirection Object Detection in Aerial View of Traffic Target under Complex Scenes |
| title_full | Multidirection Object Detection in Aerial View of Traffic Target under Complex Scenes |
| title_fullStr | Multidirection Object Detection in Aerial View of Traffic Target under Complex Scenes |
| title_full_unstemmed | Multidirection Object Detection in Aerial View of Traffic Target under Complex Scenes |
| title_short | Multidirection Object Detection in Aerial View of Traffic Target under Complex Scenes |
| title_sort | multidirection object detection in aerial view of traffic target under complex scenes |
| url | http://dx.doi.org/10.1155/2021/5597168 |
| work_keys_str_mv | AT zeqingzhang multidirectionobjectdetectioninaerialviewoftraffictargetundercomplexscenes AT weiweilin multidirectionobjectdetectioninaerialviewoftraffictargetundercomplexscenes AT yuqiangzheng multidirectionobjectdetectioninaerialviewoftraffictargetundercomplexscenes |