Cargando…
Scale-Sensitive Feature Reassembly Network for Pedestrian Detection
Serious scale variation is a key challenge in pedestrian detection. Most works typically employ a feature pyramid network to detect objects at diverse scales. Such a method suffers from information loss during channel unification. Inadequate sampling of the backbone network also affects the power of...
Autores principales: | Yang, Xiaoting, Liu, Qiong |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8234486/ https://www.ncbi.nlm.nih.gov/pubmed/34207219 http://dx.doi.org/10.3390/s21124189 |
Ejemplares similares
-
Multi-Scale Feature Pyramid Network: A Heavily Occluded Pedestrian Detection Network Based on ResNet
por: Shao, Xiaotao, et al.
Publicado: (2021) -
Reassembly of BEBC
Publicado: (1974) -
Delving Deep into Multiscale Pedestrian Detection via Single Scale Feature Maps
por: Fu, Xinchuan, et al.
Publicado: (2018) -
Contour Information-Guided Multi-Scale Feature Detection Method for Visible-Infrared Pedestrian Detection
por: Xu, Xiaoyu, et al.
Publicado: (2023) -
Detecting Multi-Resolution Pedestrians Using Group Cost-Sensitive Boosting with Channel Features †
por: Zhu, Chao, et al.
Publicado: (2019)