Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Qingshan, Hou"'
Publikováno v:
IET Image Processing, Vol 18, Iss 10, Pp 2665-2678 (2024)
Abstract Fires not only cause devastating consequences for human life and property, but also lead to soil erosion in forests. Therefore, it is necessary to design a novel algorithm that can quickly monitor smoke from fires. Most existing smoke segmen
Externí odkaz:
https://doaj.org/article/3e63619606124e6690e6ae62c37265da
Publikováno v:
Fire, Vol 6, Iss 10, p 383 (2023)
To further improve the detection of smoke and small target smoke in complex backgrounds, a novel smoke detection model called RepVGG-YOLOv7 is proposed in this paper. Firstly, the ECA attention mechanism and SIoU loss function are applied to the YOLO
Externí odkaz:
https://doaj.org/article/b6c952e576d94757bc0f5cdde09e77ef
Autor:
Qingshan Hou, Jinsheng Xing
Publikováno v:
IET Image Processing, Vol 14, Iss 15, Pp 3651-3661 (2020)
Considering that the single shot multibox detector (SSD) algorithm will be missed or even false when is used to detect the small‐ and medium‐sized objects, in this study, Kullback–Leibler single shot multibox detection (KSSD) object detection a
Externí odkaz:
https://doaj.org/article/aaa4761ae89d4c90912e1c4e6b9c54c2
Publikováno v:
IEEE Access, Vol 8, Pp 82294-82305 (2020)
In order to further improve the accuracy and real-time performance of the traditional Single Shot Multibox Detector (SSD) object detection model, an improved SSD multi-object detection model is proposed. Firstly, aiming at the defect of weak correlat
Externí odkaz:
https://doaj.org/article/4f266cc97aa64a57b8993f2ff9278e2b
Publikováno v:
Remote Sensing, Vol 14, Iss 20, p 5186 (2022)
For remote sensing image scene classification tasks, the classification accuracy of the small-scale deep neural network tends to be low and fails to achieve accuracy in real-world application scenarios. However, although large deep neural networks ca
Externí odkaz:
https://doaj.org/article/b85862aa52f94eca863576e38aefa56d
Publikováno v:
IEEE Journal of Biomedical and Health Informatics. 27:1455-1466
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::092ad9db524d8685722b8888fb68c75e
https://doi.org/10.1109/jbhi.2022.3231276
https://doi.org/10.1109/jbhi.2022.3231276
Publikováno v:
Complexity, Vol 2020 (2020)
Multiobject detection tasks in complex scenes have become an important research topic, which is the basis of other computer vision tasks. Considering the defects of the traditional single shot multibox detector (SSD) algorithm, such as poor small obj
Externí odkaz:
https://doaj.org/article/e42dcabed89047a68612090345d4bb23
Publikováno v:
Lecture Notes in Electrical Engineering ISBN: 9789819905522
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e76b3e1fc65a42af3824cf0039567566
https://doi.org/10.1007/978-981-99-0553-9_52
https://doi.org/10.1007/978-981-99-0553-9_52
Publikováno v:
IEEE Access, Vol 8, Pp 82294-82305 (2020)
In order to further improve the accuracy and real-time performance of the traditional Single Shot Multibox Detector (SSD) object detection model, an improved SSD multi-object detection model is proposed. Firstly, aiming at the defect of weak correlat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e10ed4e8156c82664be37a426e459e2e
https://doi.org/10.1109/access.2020.2990477
https://doi.org/10.1109/access.2020.2990477
Publikováno v:
Computers in Biology and Medicine. 144:105341
Early detection and treatment of diabetic retinopathy (DR) can significantly reduce the risk of vision loss in patients. In essence, we are faced with two challenges: (i) how to simultaneously achieve domain adaptation from the different domains and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9501241e2918f813d129d93ee6972837
https://doi.org/10.1016/j.compbiomed.2022.105341
https://doi.org/10.1016/j.compbiomed.2022.105341