Detection results on the FLIR dataset using different algorithms.

<p>From (a) to (g), the results correspond to Faster R-CNN, SSD, YOLOv5s, YOLOv7, YOLO-IR-Free, YOLO-DeepOC-IR, and ours, respectively.</p>

Saved in:

Bibliographic Details
Main Author:	Weilun Wang (21559389) (author)
Other Authors:	Jian Xu (31545) (author), Ruopeng Zhang (4591987) (author)
Published:	2025
Subjects:	Medicine Sociology Space Science Biological Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified reduced computational cost minimal computational complexity limited texture details layer feature interactions intelligent transportation due improving feature quality hybrid global multi enhancing target focus 32 %, along handle complex backgrounds enhanced yolov8 model world ir applications time detection capabilities div >< p small object detection resolution ir images object detection model ’ complex environments resolution reconstruction resolution ones resolution network suppressing noise sobel module scale variations recall rising optimized approach medical diagnostics lightweight super lightweight c2f integrating super integrate cross industrial monitoring improved sc head attention extensively applied experimental results efficient edge detail extraction bifpn module adverse weather
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items