Deep Learning Seminar  /  28. November 2019

Unsupervised Multiple Object Tracking Using Regularized Triplet Loss for Graph Partitioning

Abstract:

[nur in Englisch verfügbar]

Multiple Object Tracking is a long-standing task in computer vision. Current approaches based on the tracking by detection paradigm are either requiring some sort of domain knowledge or supervision to associate data correctly into tracks. In this work, we present an unsupervised multiple object tracking approach based on visual features and minimum cost lifted multicuts. Our method is based on straight-forward spatio-temporal cues that can be extracted from neighboring frames in an image sequence without supervision.

From these cues, we learn an object instance appearance model using a new, regularized Triple Loss. We provide evidence for its superiority over the standard Triplet Loss formulation in the context of minimum cost multicuts. Thus, the resulting embedding representations can serve as robust appearance cues for tracking even over large temporal distances where no reliable spatio-temporal features could be extracted. We show that, despite being trained without using the provided annotations, our model provides competitive results on the challenging MOT Benchmark for pedestrian tracking.

  • Mechatronics in Mechenical and Automotive Engineering (Dep. of Mechanical and Process Engineering)
  • Automation Control (Dep. of Electrical and Computer Engineering)
  • Electromobility (Dep. of Electrical and Computer Engineering)

The seminar takes place at the ITWM every 1st Tuesday of a month (besides holidays and summer break). Aims are broadening of experiences and exchange of scientific views – also beyond the organizing groups.

Typical subjects of talks are:

  • ongoing or recently finished graduations and doctoral theses
  • current research and projects

The topics vary from mathematical methods to technical implementations. Usually, the talks present research results. However, some show open issues for brainstorming and inputs from the audience.

The seminar »KL-Regelungstechnik« (Kaiserslautern – Control Theory and Control Engineering) is organized by our department as well as several research groups of the TU Kaiserslautern:

  • Technomathematics (Dep. of Mathematics)
  • Mechatronics in Mechenical and Automotive Engineering (Dep. of Mechanical and Process Engineering)
  • Automation Control (Dep. of Electrical and Computer Engineering)
  • Electromobility (Dep. of Electrical and Computer Engineering)

The seminar takes place at the ITWM every 1st Tuesday of a month (besides holidays and summer break). Aims are broadening of experiences and exchange of scientific views – also beyond the organizing groups.

Typical subjects of talks are:

  • ongoing or recently finished graduations and doctoral theses
  • current research and projects

The topics vary from mathematical methods to technical implementations. Usually, the talks present research results. However, some show open issues for brainstorming and inputs from the audience.

The seminar »KL-Regelungstechnik« (Kaiserslautern – Control Theory and Control Engineering) is organized by our department as well as several research groups of the TU Kaiserslautern:

  • Technomathematics (Dep. of Mathematics)
  • Mechatronics in Mechenical and Automotive Engineering (Dep. of Mechanical and Process Engineering)
  • Automation Control (Dep. of Electrical and Computer Engineering)
  • Electromobility (Dep. of Electrical and Computer Engineering)

The seminar takes place at the ITWM every 1st Tuesday of a month (besides holidays and summer break). Aims are broadening of experiences and exchange of scientific views – also beyond the organizing groups.

Typical subjects of talks are:

  • ongoing or recently finished graduations and doctoral theses
  • current research and projects

The topics vary from mathematical methods to technical implementations. Usually, the talks present research results. However, some show open issues for brainstorming and inputs from the audience.