Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Zhonghan Chang"'
Publikováno v:
IEEE Access, Vol 7, Pp 77597-77606 (2019)
The state-of-the-art object detection frameworks require the training on large-scale datasets, which is the crux of the present dilemma: overfitting or degrading performance with insufficient samples and time-consuming training process. On the basis
Externí odkaz:
https://doaj.org/article/985f65fc9c2e42e0ba751d2d9ce8d7fd
Publikováno v:
IEEE Transactions on Geoscience and Remote Sensing. 60:1-19
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f3ae01843cb72cd88c1f126f9dfed90c
https://doi.org/10.1109/tgrs.2021.3130174
https://doi.org/10.1109/tgrs.2021.3130174
Publikováno v:
IEEE Transactions on Geoscience and Remote Sensing. 59:4370-4387
Object detection in aerial images is important for a wide range of applications. The most challenging dilemma in this task is the arbitrary orientation of objects, and many deep-learning-based methods are proposed to address this issue. In previous w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a18f3a4ba6ac8a1cf556abab85587f02
https://doi.org/10.1109/tgrs.2020.3020165
https://doi.org/10.1109/tgrs.2020.3020165
Publikováno v:
ISPRS Journal of Photogrammetry and Remote Sensing. 169:268-279
Oriented object detection in remote sensing images is an active yet challenging task. State-of-the-art detectors adopt oriented bounding box as a basic representation of an object. The design of them always multiplies the number of anchor boxes with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::52faa449dff6fac6fac9baebf12c437e
https://doi.org/10.1016/j.isprsjprs.2020.09.022
https://doi.org/10.1016/j.isprsjprs.2020.09.022
Autor:
Yue Zhang, Xian Sun, Hongqi Wang, Tengfei Zhang, Wenhui Diao, Jiangqiao Yan, Zhonghan Chang, Menglong Yan
Publikováno v:
AAAI
Feature pyramid is the mainstream method for multi-scale object detection. In most detectors with feature pyramid, each proposal is predicted based on feature grids pooled from only one feature level, which is assigned heuristically. Recent studies r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6250f950fc5c4cf631e9a3b254423756
https://doi.org/10.1609/aaai.v34i07.6947
https://doi.org/10.1609/aaai.v34i07.6947
Publikováno v:
ISPRS Journal of Photogrammetry and Remote Sensing. 161:294-308
Object detection plays an important role in the field of remote sensing imagery analysis. The most challenging issues in advancing this task are the large variation in object scales and the arbitrary orientation of objects. In this paper, we build a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::04311a7ac255813479a74134ff2b2677
https://doi.org/10.1016/j.isprsjprs.2020.01.025
https://doi.org/10.1016/j.isprsjprs.2020.01.025
Publikováno v:
IEEE Access, Vol 7, Pp 77597-77606 (2019)
The state-of-the-art object detection frameworks require the training on large-scale datasets, which is the crux of the present dilemma: overfitting or degrading performance with insufficient samples and time-consuming training process. On the basis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::079bb93740d821b1e8000144d1f898bd
https://ieeexplore.ieee.org/document/8735792/
https://ieeexplore.ieee.org/document/8735792/
Autor:
Menglong Yan, Wenhui Diao, Yi Zhang, Hao Li, Xin Gao, Xian Sun, Yingchao Feng, Zhonghan Chang
Publikováno v:
IGARSS
The performance of object instance segmentation in remote sensing images has been greatly improved through the introduction of many landmark frameworks based on convolutional neural network. However, the object densely issue still affects the accurac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a284ca72bb61dbb714d0065af82c5663
https://doi.org/10.1109/igarss.2019.8897948
https://doi.org/10.1109/igarss.2019.8897948