Data augmentation before-and-after comparison.

<div><p>Fires are characterized by their sudden onset, rapid spread, and destructive nature, often causing irreversible damage to ecosystems. To address the challenges in forest fire detection, including the varying scales and complex features of flame and smoke, as well as false positiv...

Full description

Saved in:

Bibliographic Details
Main Author:	Diansheng Zhang (22640973) (author)
Other Authors:	Yueyuan Zhang (10025813) (author), Leilei Dong (8044145) (author), Shifeng Ruan (22640976) (author), Zhiwei Liu (151279) (author)
Published:	2025
Subjects:	Biological Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> fires missed detections caused incomplete data collected feature extraction structure effectively mitigating issues missed detection rates forest fire detection model &# 8217 key fire features experimental results demonstrate ssd backbone network improved ssd algorithm smoke texture along cbam </ p ssd model time detection results indicate complex features world scenarios varying scales sudden onset substantially improving spatial dimension significantly enhances rapid spread lower false increase compared false positives environmental interference destructive nature deep learning color transformations channel dimension cbam module accurate solution 80 %. 61 %, 49 %, 40 %;
Tags:	Add Tag No Tags, Be the first to tag this record!

Data augmentation before-and-after comparison.

Similar Items