DeepAI AI Chat
Log In Sign Up

DeepMOT: A Differentiable Framework for Training Multiple Object Trackers

by   Yihong Xu, et al.

Multiple Object Tracking accuracy and precision (MOTA and MOTP) are two standard and widely-used metrics to assess the quality of multiple object trackers. They are specifically designed to encode the challenges and difficulties of tracking multiple objects. To directly optimize a tracker based on MOTA and MOTP is difficult, since both the metrics are strongly rely on the Hungarian algorithm, which are non-differentiable. We propose a differentiable proxy for the MOTA and MOTP, thus allowing to train a deep multiple-object tracker by directly optimizing (a proxy of) the standard MOT metrics. The proposed approximation is based on a bidirectional recurrent network that inputs the object-to-hypothesis distance matrix and outputs the optimal hypothesis-to-object association, thus emulating the Hungarian algorithm. Followed by a differentiable module, the estimated association is used to compute the MOTA and MOTP. The experimental study demonstrates the benefits of this differentiable framework on two recent deep trackers over the MOT17 dataset. Moreover, the code is publicly available from


Multiple Object Tracking with Kernelized Correlation Filters in Urban Mixed Traffic

Recently, the Kernelized Correlation Filters tracker (KCF) achieved comp...

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

Transformer networks have been a focus of research in many fields in rec...

AAA: Adaptive Aggregation of Arbitrary Online Trackers with Theoretical Performance Guarantee

For visual object tracking, it is difficult to realize an almighty onlin...

Improving tracking with a tracklet associator

Multiple object tracking (MOT) is a task in computer vision that aims to...

Real-Time Multiple Object Tracking - A Study on the Importance of Speed

In this project, we implement a multiple object tracker, following the t...

TransFiner: A Full-Scale Refinement Approach for Multiple Object Tracking

Multiple object tracking (MOT) is the task containing detection and asso...

A Framework for Evaluating 6-DOF Object Trackers

We present a challenging and realistic novel dataset for evaluating 6-DO...

Code Repositories


Official implementation of DeepMOT: A Differentiable Framework for Training Multiple Object Trackers.

view repo