Robust Long-Term Object Tracking via Improved Discriminative Model Prediction

TL;DR

This paper introduces RLT-DiMP, a robust long-term object tracker that enhances a pre-trained short-term tracker with uncertainty reduction, spatio-temporal constrained random search, and background augmentation, achieving competitive results.

Contribution

The paper presents a novel long-term tracking method that improves upon SuperDiMP by integrating uncertainty estimation, constrained random search, and background augmentation techniques.

Findings

Achieves comparable performance to state-of-the-art long-term trackers on VOT-LT2020.

Demonstrates robustness through uncertainty reduction and background augmentation.

Improves tracking stability with spatio-temporal constrained random search.

Abstract

We propose an improved discriminative model prediction method for robust long-term tracking based on a pre-trained short-term tracker. The baseline pre-trained short-term tracker is SuperDiMP which combines the bounding-box regressor of PrDiMP with the standard DiMP classifier. Our tracker RLT-DiMP improves SuperDiMP in the following three aspects: (1) Uncertainty reduction using random erasing: To make our model robust, we exploit an agreement from multiple images after erasing random small rectangular areas as a certainty. And then, we correct the tracking state of our model accordingly. (2) Random search with spatio-temporal constraints: we propose a robust random search method with a score penalty applied to prevent the problem of sudden detection at a distance. (3) Background augmentation for more discriminative feature learning: We augment various backgrounds that are not included in the search area to train a more robust model in the background clutter. In experiments on the VOT-LT2020 benchmark dataset, the proposed method achieves comparable performance to the state-of-the-art long-term trackers. The source code is available at: https://github.com/bismex/RLT-DIMP.