Double Mask R-CNN for Pedestrian Detection in a Crowd
Aiming at the difficulty of feature extraction and the limitation of NMS (nonmaximum suppression) in crowded pedestrian detection, a new detection network named Double Mask R-CNN based on Mask R-CNN with FPN (Feature Pyramid Network) is proposed in this article. The algorithm has two improvements: F...
Main Authors: | Liu, C. (Author), Wang, H. (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2022
|
Subjects: | |
Online Access: | View Fulltext in Publisher |
Similar Items
-
Pedestrian as Points: An Improved Anchor-Free Method for Center-Based Pedestrian Detection
by: Jiawei Cai, et al.
Published: (2020-01-01) -
MR-FPN: Multi-Level Residual Feature Pyramid Text Detection Network Based on Self-Attention Environment
by: Hamdulla, A., et al.
Published: (2022) -
Texture classification using Steerable Pyramid based Laws’ Masks
by: Sonali Dash, et al.
Published: (2017-05-01) -
A New Region Proposal Network for Far-Infrared Pedestrian Detection
by: Zhiwei Cao, et al.
Published: (2019-01-01) -
Large-scale tissue histopathology image segmentation based on feature pyramid
by: Pinle Qin, et al.
Published: (2018-08-01)