Reliable Object Tracking by Multimodal Hybrid Feature Extraction and Transformer-Based Fusion

TL;DR

This paper introduces a multimodal hybrid tracker (MMHT) that combines frame and event-based data using a hybrid neural network and transformer fusion to improve the reliability of object tracking in challenging scenarios.

Contribution

The paper presents a novel MMHT model that employs a hybrid ANN and SNN backbone with transformer-based feature fusion for enhanced multimodal object tracking.

Findings

MMHT achieves competitive performance against state-of-the-art methods.

Effective multimodal feature extraction improves tracking in low light and cluttered backgrounds.

Transformer-based fusion enhances discriminative feature modeling.

Abstract

Visual object tracking, which is primarily based on visible light image sequences, encounters numerous challenges in complicated scenarios, such as low light conditions, high dynamic ranges, and background clutter. To address these challenges, incorporating the advantages of multiple visual modalities is a promising solution for achieving reliable object tracking. However, the existing approaches usually integrate multimodal inputs through adaptive local feature interactions, which cannot leverage the full potential of visual cues, thus resulting in insufficient feature modeling. In this study, we propose a novel multimodal hybrid tracker (MMHT) that utilizes frame-event-based data for reliable single object tracking. The MMHT model employs a hybrid backbone consisting of an artificial neural network (ANN) and a spiking neural network (SNN) to extract dominant features from different visual modalities and then uses a unified encoder to align the features across different domains. Moreover, we propose an enhanced transformer-based module to fuse multimodal features using attention mechanisms. With these methods, the MMHT model can effectively construct a multiscale and multidimensional visual feature space and achieve discriminative feature modeling. Extensive experiments demonstrate that the MMHT model exhibits competitive performance in comparison with that of other state-of-the-art methods. Overall, our results highlight the effectiveness of the MMHT model in terms of addressing the challenges faced in visual object tracking tasks.