Indicator results of the improvement module.

Indicator results of the improvement module.

<div><p>To solve the problem of reduced positioning accuracy caused by changes in scale, background and occlusion in port and dock video images, this research proposes an enhanced model combining YOLOv5s-DeepSORT, integrating target load recognition and trajectory tracking to improve ada...

Full description

Saved in:
Bibliographic Details
Main Author: Chengzhi Wang (2256133) (author)
Other Authors: Donghong Chen (3601139) (author), Zhen Liu (74646) (author), Yuanhao Li (141505) (author), Yifei Wang (95207) (author), Sanglan Zhao (21696099) (author)
Published: 2025
Subjects:
Neuroscience
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
model &# 8217
constructed datasets demonstrated
dock video images
dock image sequence
mean average precision
2 %, offering
scale object detection
deepsort </ p
target tracking accuracy
dock environments
target recognition
detection accuracy
average accuracy
yolov5s improved
xlink ">
valuable reference
trajectory tracking
scale convolution
research proposes
optimization led
network enhanced
mota ).
improve adaptability
findings indicate
experimental results
enhanced using
combined yolov5s
95 increased
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items