Výsledky vyhledávání

Akademický článek

Counting dense object of multiple types based on feature enhancement

Autor: Qiyan Fu, Weidong Min, Weixiang Sheng, Chunjiang Peng

Publikováno v: Frontiers in Neurorobotics, Vol 18 (2024)

IntroductionAccurately counting the number of dense objects in an image, such as pedestrians or vehicles, is a challenging and practical task. The existing density map regression methods based on CNN are mainly used to count a class of dense objects

Externí odkaz: https://doaj.org/article/6682b2e87f9f4adf8cfb2869f2927624

Zobrazit plný text záznamu

Akademický článek

MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting

Autor: Haoyu Zhao, Weidong Min, Xin Wei, Qi Wang, Qiyan Fu, Zitai Wei

Publikováno v: IET Image Processing, Vol 15, Iss 14, Pp 3512-3521 (2021)

Abstract Crowd counting aims to count the number of people in crowded scenes, which is important to the security systems, traffic control and so on. The existing methods typically using local features cannot properly handle the perspective distortion

Externí odkaz: https://doaj.org/article/a5d7c22753c04e09809600b1301edb75

Zobrazit plný text záznamu

Channel Splitting-and-Merging Connection in Neural Networks

Autor: Meng Zhu, Weidong Min, Qing Han, Guowei Zhan, Qiyan Fu, Jiahao Li

Neural networks have achieved success in both computer vision and natural language processing. The existing state-of-the-art neural networks dedicate to increase model complexity for improving performance. However, this causes two problems. One is th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b83d8697152cd9807aee2083df546a4f
https://doi.org/10.21203/rs.3.rs-2205470/v1

Zobrazit plný text záznamu

Scene-adaptive crowd counting method based on meta learning with dual-input network DMNet

Autor: Haoyu Zhao, Weidong Min, Jianqiang Xu, Qi Wang, Yi Zou, Qiyan Fu

Publikováno v: Frontiers of Computer Science. 17

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::59eb1013f457bd9711614f82d0a342f4
https://doi.org/10.1007/s11704-021-1207-x

Zobrazit plný text záznamu

MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting

Autor: Xin Wei, Qiyan Fu, Qi Wang, Zitai Wei, Weidong Min, Haoyu Zhao

Publikováno v: IET Image Processing, Vol 15, Iss 14, Pp 3512-3521 (2021)

Crowd counting aims to count the number of people in crowded scenes, which is important to the security systems, traffic control and so on. The existing methods typically using local features cannot properly handle the perspective distortion and the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e67b1fb5e80da81e5291f5a9e3233dae
https://doi.org/10.1049/ipr2.12175

Zobrazit plný text záznamu

Traffic Police Gesture Recognition Based on Gesture Skeleton Extractor and Multichannel Dilated Graph Convolution Network

Autor: Qiyan Fu, Chunjiang Peng, Weidong Min, Haoyuan Wu, Xin Xiong, Jianqiang Xu

Publikováno v: Electronics, Vol 10, Iss 551, p 551 (2021)
Electronics
Volume 10
Issue 5

Traffic police gesture recognition is important in automatic driving. Most existing traffic police gesture recognition methods extract pixel-level features from RGB images which are uninterpretable because of a lack of gesture skeleton features and m

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ebced7d70d175cbbe86d6b3386519005
https://www.mdpi.com/2079-9292/10/5/551

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání