SQE: a Self Quality Evaluation Metric for Parameters Optimization in Multi-Object Tracking

TL;DR

This paper introduces SQE, a ground-truth-free metric for optimizing parameters in multi-object tracking, based on internal trajectory characteristics, enabling self-optimization and improved performance.

Contribution

The paper proposes a novel self quality evaluation metric (SQE) that assesses trajectory quality without ground truth, facilitating parameter optimization in real-world scenarios.

Findings

SQE correlates well with existing metrics.

SQE enables effective parameter self-optimization.

Improved tracking performance on MOT16 datasets.

Abstract

We present a novel self quality evaluation metric SQE for parameters optimization in the challenging yet critical multi-object tracking task. Current evaluation metrics all require annotated ground truth, thus will fail in the test environment and realistic circumstances prohibiting further optimization after training. By contrast, our metric reflects the internal characteristics of trajectory hypotheses and measures tracking performance without ground truth. We demonstrate that trajectories with different qualities exhibit different single or multiple peaks over feature distance distribution, inspiring us to design a simple yet effective method to assess the quality of trajectories using a two-class Gaussian mixture model. Experiments mainly on MOT16 Challenge data sets verify the effectiveness of our method in both correlating with existing metrics and enabling parameters self-optimization to achieve better performance. We believe that our conclusions and method are inspiring for future multi-object tracking in practice.