Improved Mask RCNN Algorithm and Its Application in Pedestrian Instance Segmentation

In the process of feature extraction, Mask RCNN algorithm will lose semantic information.However, pedestrians in natural scenes have different posture, occlusion and complex background, which lead to poor detection accuracy in pedestrian segmentation.To solve this problem, an improved Mask RCNN algo...

Description complète

Détails bibliographiques

Auteur principal:	YIN Song, CHEN Xueyun, BEI Xueyu
Format:	Artigo
Langue:	Inglês
Publié:	Editorial Office of Computer Engineering 2021-06-01
Collection:	Jisuanji gongcheng
Sujets:	pedestrian instance segmentation|mask rcnn algorithm|feature fusion|object detection|concatenated feature pyramid network(cfpn)
Accès en ligne:	https://www.ecice06.com/fileup/1000-3428/PDF/20210633.pdf
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!