Block diagram of YOLOv8 model architecture.

<div><p>An MDCFVit-YOLO model based on the YOLOv8 algorithm is proposed to address issues in nighttime infrared object detection such as low visibility, high interference, and low precision in detecting small objects. The backbone network uses the lightweight Repvit model, improving dete...

Full description

Saved in:

Bibliographic Details
Main Author:	Huiying Zhang (200681) (author)
Other Authors:	Qinghua Zhang (145923) (author), Yifei Gong (18696013) (author), Feifan Yao (20854334) (author), Pan Xiao (3336753) (author)
Published:	2025
Subjects:	Neuroscience Sociology Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified scale contextual information experimental results show capturing complex dependencies infrared target detection improving detection performance reducing model weight recall rates improved lightweight repvit model detecting small objects backbone network uses 7 %, respectively baseline model yolov8 yolo model based yolov8 algorithm yolo model small targets recall rate neural network detection accuracy xlink "> transfer learning training process representation capability reduce losses parameter count map value map increased low visibility low precision high interference feature maps channel dimensions address issues 67 %.
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Block diagram of YOLOv8 model architecture.

Similar Items