DeepAI AI Chat
Log In Sign Up

Strong-TransCenter: Improved Multi-Object Tracking based on Transformers with Dense Representations

by   Amit Galor, et al.
Tel Aviv University

Transformer networks have been a focus of research in many fields in recent years, being able to surpass the state-of-the-art performance in different computer vision tasks. A few attempts have been made to apply this method to the task of Multiple Object Tracking (MOT), among those the state-of-the-art was TransCenter, a transformer-based MOT architecture with dense object queries for accurately tracking all the objects while keeping reasonable runtime. TransCenter is the first center-based transformer framework for MOT, and is also among the first to show the benefits of using transformer-based architectures for MOT. In this paper we show an improvement to this tracker using post processing mechanism based in the Track-by-Detection paradigm: motion model estimation using Kalman filter and target Re-identification using an embedding network. Our new tracker shows significant improvements in the IDF1 and HOTA metrics and comparable results on the MOTA metric (70.9 and 75.8 on all 3 metrics (67.5 tracker is currently ranked first among transformer-based trackers in these datasets. The code is publicly available at:


page 3

page 5

page 7

page 8


BoT-SORT: Robust Associations Multi-Pedestrian Tracking

The goal of multi-object tracking (MOT) is detecting and tracking all th...

Efficient Visual Tracking with Exemplar Transformers

The design of more complex and powerful neural network models has signif...

TransCenter: Transformers with Dense Queries for Multiple-Object Tracking

Transformer networks have proven extremely powerful for a wide variety o...

Motion-based Post-Processing: Using Kalman Filter to Exclude Similar Targets in Underwater Object Tracking

Visual tracker includes network and post-processing. Despite the color d...

EnsembleMOT: A Step towards Ensemble Learning of Multiple Object Tracking

Multiple Object Tracking (MOT) has rapidly progressed in recent years. E...

DeepMOT: A Differentiable Framework for Training Multiple Object Trackers

Multiple Object Tracking accuracy and precision (MOTA and MOTP) are two ...

Immortal Tracker: Tracklet Never Dies

Previous online 3D Multi-Object Tracking(3DMOT) methods terminate a trac...

Code Repositories


Multiple Object Tracking framework based on transformers for the MOT Challenge

view repo