Behaviour detection in crowded classroom scenes via enhancing features robust to scale and perspective variations

Abstract Detecting human behaviours in images of crowded classroom scenes is a challenging task, due to the large variations of humans in scale and pose perspective. In this paper, two modules are proposed to tackle these two variations. First, an attention‐based RoI (region‐of‐interest) extractor i...

Full description

Saved in:
Bibliographic Details
Main Authors: Mingyu Liu, Fanman Meng, Qingbo Wu, Linfeng Xu, Qianghua Liao
Format: article
Language:EN
Published: Wiley 2021
Subjects:
Online Access:https://doaj.org/article/e18bac49cba44e608faa4e3b7caa524d
Tags: Add Tag
No Tags, Be the first to tag this record!