SAFETYLIT WEEKLY UPDATE

We compile citations and summaries of about 400 new articles every week.
RSS Feed

HELP: Tutorials | FAQ
CONTACT US: Contact info

Search Results

Journal Article

Citation

Alavianmehr MA, Helfroush MS, Danyali H, Tashk A. J. Real Time Image Proces. 2023; 20(1): e9.

Copyright

(Copyright © 2023, Holtzbrinck Springer Nature Publishing Group)

DOI

10.1007/s11554-023-01273-z

PMID

36748032

PMCID

PMC9894518

Abstract

The detection of multi-scale pedestrians is one of the challenging tasks in pedestrian detection applications. Moreover, the task of small-scale pedestrian detection, i.e., accurate localization of pedestrians as low-scale target objects, can help solve the issue of occluded pedestrian detection as well. In this paper, we present a fully convolutional neural network with a new architecture and an innovative, fully detailed supervision for semantic segmentation of pedestrians. The proposed network has been named butterfly network (BF-Net) because of its architecture analogous to a butterfly. The proposed BF-Net preserves the ability of simplicity so that it can process static images with a real-time image processing rate. The sub-path blocks embedded in the architecture of the proposed BF-Net provides a higher accuracy for detecting multi-scale objective targets including the small ones. The other advantage of the proposed architecture is replacing common batch normalization with conditional one. In conclusion, the experimental results of the proposed method demonstrate that the proposed network outperform the other state-of-the-art networks such as U-Net +  + , U-Net3 + , Mask-RCNN, and Deeplabv3 + for the semantic segmentation of the pedestrians.


Language: en

Keywords

Convolutional neural network; Butterfly network (BF-Net); Pedestrian detection; Semantic segmentation; State-of-the-art U-Nets

NEW SEARCH


All SafetyLit records are available for automatic download to Zotero & Mendeley
Print