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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Hongze, Liu, Rui, Cai, Wuque, Wang, Jun, Wang, Yue, Tang, Huajin, Cui, Yan, Yao, Dezhong, Guo, Daqing
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910662117031936
author Sun, Hongze
Liu, Rui
Cai, Wuque
Wang, Jun
Wang, Yue
Tang, Huajin
Cui, Yan
Yao, Dezhong
Guo, Daqing
author_facet Sun, Hongze
Liu, Rui
Cai, Wuque
Wang, Jun
Wang, Yue
Tang, Huajin
Cui, Yan
Yao, Dezhong
Guo, Daqing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17903
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reliable Object Tracking by Multimodal Hybrid Feature Extraction and Transformer-Based Fusion
Sun, Hongze
Liu, Rui
Cai, Wuque
Wang, Jun
Wang, Yue
Tang, Huajin
Cui, Yan
Yao, Dezhong
Guo, Daqing
Computer Vision and Pattern Recognition
Neurons and Cognition
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.
title Reliable Object Tracking by Multimodal Hybrid Feature Extraction and Transformer-Based Fusion
topic Computer Vision and Pattern Recognition
Neurons and Cognition
url https://arxiv.org/abs/2405.17903