Scholarlink

<p>In order to achieve complex tasks at high speed in robot manipulation, the ability to perform multi-object tracking (MOT), which recognizes the many objects in the surrounding area using camera-based real-time image data processing, is essential. To overcome traditional MOT methods slow tracking speeds challenges, we propose Speed-FairMOT, a deep-learning based real-time multi-class MOT method. We evaluate the Speed-FairMOT on MOT17 dataset and our custom synthetic dataset, achieving over <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11760_2025_4395_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="31" /> </InlineMediaObject> <EquationSource Format="TEX">\(41\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>41</mn> <mo>%</mo> </mrow> </math></EquationSource> </InlineEquation> improvement in speed and slightly decrease of <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11760_2025_4395_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="35" /> </InlineMediaObject> <EquationSource Format="TEX">\(5.9\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>5.9</mn> <mo>%</mo> </mrow> </math></EquationSource> </InlineEquation> in tracking performance as trade-off compared to the original FairMOT. We verified proposed Speed-FairMOT using a camera mounted on a robot manipulator as a hand-eye system. As the result, we were able to achieve MOT at an maximum speed over 58 fps in real-time. This real-time speed is sufficient for feedback control in robotic manipulation system.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Speed-FairMOT: multi-class multi-object tracking for real-time manipulation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月2日

查看全文
  • Cheng Ju,
  • Ziran Li,
  • Koki Terakado,
  • Akio Namiki

摘要

In order to achieve complex tasks at high speed in robot manipulation, the ability to perform multi-object tracking (MOT), which recognizes the many objects in the surrounding area using camera-based real-time image data processing, is essential. To overcome traditional MOT methods slow tracking speeds challenges, we propose Speed-FairMOT, a deep-learning based real-time multi-class MOT method. We evaluate the Speed-FairMOT on MOT17 dataset and our custom synthetic dataset, achieving over \(41\%\) 41 % improvement in speed and slightly decrease of \(5.9\%\) 5.9 % in tracking performance as trade-off compared to the original FairMOT. We verified proposed Speed-FairMOT using a camera mounted on a robot manipulator as a hand-eye system. As the result, we were able to achieve MOT at an maximum speed over 58 fps in real-time. This real-time speed is sufficient for feedback control in robotic manipulation system.