Global-Local and Occlusion Awareness Network for Object Tracking in UAVs
Multiobject tracking in unmanned aerial vehicle (UAV) scenes is a crucial task with numerous applications across various domains. The goal of this task is to track multiple objects such as people and vehicles over time as they move through the scene, often captured by cameras mounted on UAV. However...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10227510/ |
| _version_ | 1827803691414978560 |
|---|---|
| author | Lukui Shi Qingrui Zhang Bin Pan Jun Zhang Yuanchao Su |
| author_facet | Lukui Shi Qingrui Zhang Bin Pan Jun Zhang Yuanchao Su |
| author_sort | Lukui Shi |
| collection | DOAJ |
| description | Multiobject tracking in unmanned aerial vehicle (UAV) scenes is a crucial task with numerous applications across various domains. The goal of this task is to track multiple objects such as people and vehicles over time as they move through the scene, often captured by cameras mounted on UAV. However, tracking objects in UAV scenes can be challenging due to several factors, including the scale variance of objects as they move through the scene and the frequent occlusions caused by complex scenes. To address these issues, we propose a global-local and occlusion awareness (GLOA) tracking network for UAVs. It comprises two main components: global-local awareness detector (GLA-D) and the occlusion awareness data association (OADA). The GLA-D uses our specially designed global-local awareness block to extract scale variance feature information from the input frames. It then outputs more discriminative identity information by adding identity embedding branches to the prediction head. The GLA-D is designed to better handle scale variance issues and improve object tracking accuracy. The OADA method used different metrics for high- and low-scoring detection frames was to alleviate occlusion problems in tracking scenarios. By combining these two components, the GLOA provides a more robust and effective solution for multiobject tracking in UAV scenes. Experiments on two public datasets may indicate the effectiveness of the proposed method. |
| first_indexed | 2024-03-11T20:59:06Z |
| format | Article |
| id | doaj.art-c408a4e110b8469d8eedebe7ba6ae5c2 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-11T20:59:06Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-c408a4e110b8469d8eedebe7ba6ae5c22023-09-29T23:00:20ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-01168834884410.1109/JSTARS.2023.330804210227510Global-Local and Occlusion Awareness Network for Object Tracking in UAVsLukui Shi0https://orcid.org/0000-0002-7906-6349Qingrui Zhang1https://orcid.org/0009-0007-9726-3366Bin Pan2https://orcid.org/0000-0003-3063-1762Jun Zhang3https://orcid.org/0000-0003-4345-454XYuanchao Su4https://orcid.org/0000-0002-4776-0862School of Artificial Intelligence, Hebei University of Technology, Tianjin, ChinaSchool of Artificial Intelligence, Hebei University of Technology, Tianjin, ChinaSchool of Statistics and Data Science, KLMDASR, LEBPS, and LPMC, Nankai University, Tianjin, ChinaSchool of Artificial Intelligence, Hebei University of Technology, Tianjin, ChinaDepartment of Remote Sensing, College of Geomatics, Xi'an University of Science and Technology, Xi'an, ChinaMultiobject tracking in unmanned aerial vehicle (UAV) scenes is a crucial task with numerous applications across various domains. The goal of this task is to track multiple objects such as people and vehicles over time as they move through the scene, often captured by cameras mounted on UAV. However, tracking objects in UAV scenes can be challenging due to several factors, including the scale variance of objects as they move through the scene and the frequent occlusions caused by complex scenes. To address these issues, we propose a global-local and occlusion awareness (GLOA) tracking network for UAVs. It comprises two main components: global-local awareness detector (GLA-D) and the occlusion awareness data association (OADA). The GLA-D uses our specially designed global-local awareness block to extract scale variance feature information from the input frames. It then outputs more discriminative identity information by adding identity embedding branches to the prediction head. The GLA-D is designed to better handle scale variance issues and improve object tracking accuracy. The OADA method used different metrics for high- and low-scoring detection frames was to alleviate occlusion problems in tracking scenarios. By combining these two components, the GLOA provides a more robust and effective solution for multiobject tracking in UAV scenes. Experiments on two public datasets may indicate the effectiveness of the proposed method.https://ieeexplore.ieee.org/document/10227510/Multiobject trackingocclusion awarenessunmanned aerial vehicle (UAV) |
| spellingShingle | Lukui Shi Qingrui Zhang Bin Pan Jun Zhang Yuanchao Su Global-Local and Occlusion Awareness Network for Object Tracking in UAVs IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Multiobject tracking occlusion awareness unmanned aerial vehicle (UAV) |
| title | Global-Local and Occlusion Awareness Network for Object Tracking in UAVs |
| title_full | Global-Local and Occlusion Awareness Network for Object Tracking in UAVs |
| title_fullStr | Global-Local and Occlusion Awareness Network for Object Tracking in UAVs |
| title_full_unstemmed | Global-Local and Occlusion Awareness Network for Object Tracking in UAVs |
| title_short | Global-Local and Occlusion Awareness Network for Object Tracking in UAVs |
| title_sort | global local and occlusion awareness network for object tracking in uavs |
| topic | Multiobject tracking occlusion awareness unmanned aerial vehicle (UAV) |
| url | https://ieeexplore.ieee.org/document/10227510/ |
| work_keys_str_mv | AT lukuishi globallocalandocclusionawarenessnetworkforobjecttrackinginuavs AT qingruizhang globallocalandocclusionawarenessnetworkforobjecttrackinginuavs AT binpan globallocalandocclusionawarenessnetworkforobjecttrackinginuavs AT junzhang globallocalandocclusionawarenessnetworkforobjecttrackinginuavs AT yuanchaosu globallocalandocclusionawarenessnetworkforobjecttrackinginuavs |