A Novel Bounding Box Regression Method for Single Object Tracking

TL;DR

This paper introduces two novel bounding box regression networks, inception and deformable, demonstrating their effectiveness in improving single object tracking accuracy across multiple benchmarks.

Contribution

The work highlights the importance of receptive field design in bounding box regression and proposes two new networks that outperform existing methods.

Findings

Inception module outperforms deformable on three benchmarks.

Receptive field size significantly impacts bounding box accuracy.

Proposed methods improve tracking performance over state-of-the-art.

Abstract

Locating an object in a sequence of frames, given its appearance in the first frame of the sequence, is a hard problem that involves many stages. Usually, state-of-the-art methods focus on bringing novel ideas in the visual encoding or relational modelling phases. However, in this work, we show that bounding box regression from learned joint search and template features is of high importance as well. While previous methods relied heavily on well-learned features representing interactions between search and template, we hypothesize that the receptive field of the input convolutional bounding box network plays an important role in accurately determining the object location. To this end, we introduce two novel bounding box regression networks: inception and deformable. Experiments and ablation studies show that our inception module installed on the recent ODTrack outperforms the latter on three benchmarks: the GOT-10k, the UAV123 and the OTB2015.