High-stage gather-and-distribute branch.

<div><p>Ensuring high accuracy and efficiency in foreign object intrusion detection along railway lines is critical for guaranteeing railway operational safety under limited resource conditions. However, current visual detection methods generally exhibit limitations in effectively handli...

Full description

Saved in:

Bibliographic Details
Main Author:	Xichun Chen (22001791) (author)
Other Authors:	Yu Tian (367745) (author), Ming Li (91180) (author), Bin Lv (551701) (author), Shuo Zhang (30844) (author), Zixian Qu (21568078) (author), Jianqing Wu (163999) (author), Shiya Cheng (6593378) (author)
Published:	2025
Subjects:	Biotechnology Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified wise feature representation varying environmental conditions score also rises sampling positions according network architecture integrates limited resource conditions level feature aggregation irregularly shaped intrusions improve localization robustness experimental results demonstrate context enhancement network 8 %&# 8212 macenet </ p actual object shapes yolo module study proposes specific datasets refine spatial notable increase net ). loss function improving map generalized intersection dynamically adapt dcnv3 allows dcnv3 ). constrained energy automatic detection 200 images 2 %.
Tags:	Add Tag No Tags, Be the first to tag this record!

High-stage gather-and-distribute branch.

Similar Items