| 注册
首页|期刊导航|太赫兹科学与电子信息学报|基于深度学习的视频序列运动目标自适应跟踪

基于深度学习的视频序列运动目标自适应跟踪

李嘉琪

太赫兹科学与电子信息学报2024,Vol.22Issue(11):1304-1311,8.
太赫兹科学与电子信息学报2024,Vol.22Issue(11):1304-1311,8.DOI:10.11805/TKYDA2024179

基于深度学习的视频序列运动目标自适应跟踪

Adaptive tracking of moving targets in video sequences based on deep learning

李嘉琪1

作者信息

  • 1. 西北大学现代学院 电影学院,陕西 西安 710130
  • 折叠

摘要

Abstract

In response to the issues of low tracking accuracy in video sequences due to factors such as appearance changes,background clutter,and severe occlusions,a novel two-stage adaptive tracking model is proposed.This model includes two phases:target detection and bounding box estimation.In the target detection phase,the model roughly locates the target;in the bounding box estimation phase,the exact position of the target is determined.To address the complexity of video scenes and the challenges of tracking small targets,multi-feature fusion technology is employed to construct a rich target representation.Experimental results show that compared with models such as Simple Online and Realtime Tracking(SORT),Tracktor++,FairMOT,and Transformer,this model demonstrates the best overall performance,effectively balancing the relationship between computational speed and tracking accuracy,and showing good potential for application.

关键词

计算机视觉/目标跟踪/目标检测/边界框估计/判别相关滤波器

Key words

computer vision/target tracking/object detection/bounding box estimation/Discriminant Correlation Filter(DCF)

分类

信息技术与安全科学

引用本文复制引用

李嘉琪..基于深度学习的视频序列运动目标自适应跟踪[J].太赫兹科学与电子信息学报,2024,22(11):1304-1311,8.

太赫兹科学与电子信息学报

OACSTPCD

2095-4980

访问量0
|
下载量0
段落导航相关论文