BOBBY2: Buffer Based Robust High-Speed Object Tracking

TL;DR

BOBBY2 is a fast, robust object tracker that uses an exemplar buffer to adapt to target changes and maintains high accuracy even with distractors, achieving 85 FPS with a lightweight model.

Contribution

Introduces a novel exemplar buffer module for robust, high-speed object tracking that adapts to target deformation and distractors, with efficient training and competitive performance.

Findings

Achieves 85 FPS with a lightweight AlexNet-based model.

Maintains accuracy even with distractor-filled buffers.

Performs well on GOT-10k and custom UAV datasets.

Abstract

In this work, a novel high-speed single object tracker that is robust against non-semantic distractor exemplars is introduced; dubbed BOBBY2. It incorporates a novel exemplar buffer module that sparsely caches the target's appearance across time, enabling it to adapt to potential target deformation. As for training, an augmented ImageNet-VID dataset was used in conjunction with the one cycle policy, enabling it to reach convergence with less than 2 epoch worth of data. For validation, the model was benchmarked on the GOT-10k dataset and on an additional small, albeit challenging custom UAV dataset collected with the TU-3 UAV. We demonstrate that the exemplar buffer is capable of providing redundancies in case of unintended target drifts, a desirable trait in any middle to long term tracking. Even when the buffer is predominantly filled with distractors instead of valid exemplars, BOBBY2 is capable of maintaining a near-optimal level of accuracy. BOBBY2 manages to achieve a very competitive result on the GOT-10k dataset and to a lesser degree on the challenging custom TU-3 dataset, without fine-tuning, demonstrating its generalizability. In terms of speed, BOBBY2 utilizes a stripped down AlexNet as feature extractor with 63% less parameters than a vanilla AlexNet, thus being able to run at a competitive 85 FPS.