Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Yangliu Kuai"'
Publikováno v:
Drones, Vol 8, Iss 9, p 451 (2024)
The use of unmanned aerial vehicles (UAVs) for visible–thermal object detection has emerged as a powerful technique to improve accuracy and resilience in challenging contexts, including dim lighting and severe weather conditions. However, most exis
Externí odkaz:
https://doaj.org/article/8b69908dac3a4469be46fb1b9c7158f7
Publikováno v:
Drones, Vol 7, Iss 9, p 585 (2023)
In the field of drone-based object tracking, utilization of the infrared modality can improve the robustness of the tracker in scenes with severe illumination change and occlusions and expand the applicable scene of the drone object tracking task. In
Externí odkaz:
https://doaj.org/article/57fb45fceb5c4c6ba3ad5399c1230f7f
Publikováno v:
IEEE Access, Vol 7, Pp 25915-25923 (2019)
Convolutional neural networks are powerful models that yield hierarchies of features. In the paper, we present a new approach for general object tracking based on the fully convolutional network with multi-layer feature fusion. The designed network c
Externí odkaz:
https://doaj.org/article/965e6eb1a7a54b1aa1d2821226d8612c
Publikováno v:
IEEE Access, Vol 6, Pp 14357-14366 (2018)
Discriminative correlation filter (DCF) has attracted enormous popularity among the tracking community. Standard DCF based trackers easily achieve real-time tracking speed but significantly suffer from the boundary effects. Recently, spatially regula
Externí odkaz:
https://doaj.org/article/75be9e1ebfd641b88a5ae967374bde29
Publikováno v:
Proceedings of 2022 International Conference on Autonomous Unmanned Systems (ICAUS 2022) ISBN: 9789819904785
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cf1999ebddfac2682ce029762eac41b2
https://doi.org/10.1007/978-981-99-0479-2_318
https://doi.org/10.1007/978-981-99-0479-2_318
Publikováno v:
Neurocomputing. 401:295-307
Recently, the tracking community leads a fashion of end-to-end feature representation learning for visual tracking. Previous works treat all feature channels and training samples equally during training. This ignores channel interdependencies and for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::998aa1ebc219b7d161bd142f019732a2
https://doi.org/10.1016/j.neucom.2019.10.041
https://doi.org/10.1016/j.neucom.2019.10.041
Publikováno v:
Information Sciences. 503:169-182
Visual object tracking is as a critical function for many computer vision tasks such as motion analysis, event detection and action recognition. Recently, Siamese network based trackers gained enormous popularity in the tracking field due to their fa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7ddc50d004cb2de2e3be52c44fba5bd7
https://doi.org/10.1016/j.ins.2019.07.004
https://doi.org/10.1016/j.ins.2019.07.004
Publikováno v:
IEEE Sensors Journal. 19:9522-9531
Recently, the surge of depth sensors makes RGBD data available and facilitates the development of RGBD tracking. Inspired by the popularity of discriminative correlation filter (DCF)-based trackers in RGB tracking, we propose a target-aware framework
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3a9a05da87ebdc66661179fd35772647
https://doi.org/10.1109/jsen.2019.2925821
https://doi.org/10.1109/jsen.2019.2925821
Publikováno v:
IEEE Sensors Journal. 19:1961-1968
Recently, the tracking community leads a fashion of end-to-end feature learning using convolutional neural networks (CNNs) for visual object tracking. Traditional trackers extract feature maps from the last convolutional layer of CNNs for feature rep
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f4dec68cb4421c69385a528effc6f01f
https://doi.org/10.1109/jsen.2018.2883593
https://doi.org/10.1109/jsen.2018.2883593
Publikováno v:
Machine Vision and Applications. 30:519-528
Discriminative correlation filters (DCF) have achieved enormous popularity in the tracking community. Recently, the performance advancement in DCF-based trackers is predominantly driven by the use of convolutional features. In pursuit of extreme trac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e433be4ad827aa06f1a39f8a6c30da88
https://doi.org/10.1007/s00138-019-01009-9
https://doi.org/10.1007/s00138-019-01009-9