Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Yiming Tang et al.
Summary: With the rapid development of hyperspectral imaging techniques, a novel deep hyperspectral tracker based on Siamese network (SiamHT) is proposed to overcome the limitations of traditional hand-craft features and the challenges of training with limited samples. The proposed method utilizes heterogeneous encoder-decoder (HED) and spectral semantic representation (SSR) modules to extract spatial and spectral semantic features, and employs a two-stage training strategy for parameter learning. The fusion of well-learned spatial and spectral semantic representations enables accurate target state estimation, as demonstrated by extensive comparison experiments on a hyperspectral object tracking dataset.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Environmental Sciences
Jie Lei et al.
Summary: This paper proposes a spatial-spectral cross-correlation embedded dual-transfer network (SSDT-Net) for hyperspectral video object tracking, addressing the challenges of limited annotation data and high-dimensional characteristics. Experimental results show that the SSDT-Net offers satisfactory performance with a similar speed to traditional color trackers.
Article
Environmental Sciences
Chunhui Zhao et al.
Summary: Object tracking using RGB images may fail when the object's color is similar to the background. Hyperspectral images provide more spectral information for RGB-based trackers, but there is currently no fusion tracking algorithm for hyperspectral and RGB images. The proposed reliability-guided aggregation network (RANet) combines hyperspectral and RGB information to improve tracking performance, with the RANet achieving the best performance accuracy among the tested trackers.
Article
Computer Science, Artificial Intelligence
Long Gao et al.
Summary: This paper proposes a Siamese network with non-local correlation attention (SiamNCA) to improve the performance of Siamese-based trackers in challenging scenes. The introduced non-local correlation attention module and bi-directional features fusion module show promising results and achieve state-of-art performance.
KNOWLEDGE-BASED SYSTEMS
(2022)
Proceedings Paper
Remote Sensing
Yifan Zhang et al.
Summary: This paper proposes a fast hyperspectral object tracking method based on channel selection strategy, which takes into account the spatial and spectral changes of local regions and selects a small number of channels for faster tracking.
2022 12TH WORKSHOP ON HYPERSPECTRAL IMAGING AND SIGNAL PROCESSING: EVOLUTION IN REMOTE SENSING (WHISPERS)
(2022)
Proceedings Paper
Remote Sensing
ShiQing Wang et al.
Summary: This paper proposes a hyperspectral video target tracking method based on Band Selection and the Siamese Region Proposal Network. By utilizing an intelligent optimization algorithm to determine bands and performing transfer learning, the method effectively utilizes spectral information and achieves good visual effects and objective evaluation.
2022 12TH WORKSHOP ON HYPERSPECTRAL IMAGING AND SIGNAL PROCESSING: EVOLUTION IN REMOTE SENSING (WHISPERS)
(2022)
Proceedings Paper
Acoustics
Zhuanfeng Li et al.
Summary: This paper introduces a material-guided Siamese fusion network (SiamF) for hyperspectral object tracking. SiamF aims to model the appearance of hyperspectral objects using backbone networks trained on color images, and employs a hyperspectral feature fusion module and online classifiers to improve tracking performance.
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2022)
Article
Computer Science, Artificial Intelligence
Zhenqi Liu et al.
Summary: A dual deep Siamese network framework is proposed for hyperspectral object tracking in this paper, which integrates an RGB tracker, a hyperspectral target-aware module, and a spatial-spectral cross-attention module to train a robust tracker with limited hyperspectral video samples effectively.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Geochemistry & Geophysics
Yiming Tang et al.
Summary: A new background-aware hyperspectral tracking (BAHT) method is designed to improve target recognition in hyperspectral videos through the utilization of material-based information, band selection, and deep semantic features, demonstrating good performance compared to popular color and hyperspectral trackers.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Chunhui Zhao et al.
Summary: This study introduces a fusion tracking framework based on hyperspectral and RGB data, called the transformer-based fusion tracking network (TFTN), to enhance object tracking performance. The framework features a dual-branch structure suitable for different tracking algorithms and a specific branch designed to extract features of hyperspectral data. A fusion module inspired by Transformer is utilized to capture interaction between different modality features.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Dawei Zhang et al.
Summary: Siamese networks have achieved great success in object tracking, but may suffer from performance degradation in difficult scenarios. The proposed CSART framework enhances feature representation by incorporating self-attention mechanism and achieves better performance compared to other state-of-the-art trackers.
Article
Computer Science, Artificial Intelligence
Lianghua Huang et al.
Summary: GOT-10k is a large tracking database that covers over 560 classes of moving objects and 87 motion patterns, providing a unified training and evaluation platform for tracker development. Additionally, the introduction of a one-shot protocol for tracker evaluation avoids biased results towards familiar objects and promotes generalization in tracker development.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhuanfeng Li et al.
Summary: This paper proposes a new method SST-Net for hyperspectral tracking, which combines spatial, spectral, and temporal attention to better select valuable spectral bands for deep tracking. Experimental results show the superior effectiveness of SST-Net in tracking compared to alternative trackers.
2021 11TH WORKSHOP ON HYPERSPECTRAL IMAGING AND SIGNAL PROCESSING: EVOLUTION IN REMOTE SENSING (WHISPERS)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhenqi Liu et al.
Summary: In this paper, an anchor-free Siamese network for hyperspectral video target tracking (HA-Net) is proposed to exploit spectral features and improve tracking performance. By introducing a spectral classification branch, the network's ability to identify objects is enhanced, leading to more discriminative features and better foreground-background discrimination. The experimental results on hyperspectral video demonstrate that HA-Net effectively utilizes spectral information and significantly enhances tracking performance.
2021 11TH WORKSHOP ON HYPERSPECTRAL IMAGING AND SIGNAL PROCESSING: EVOLUTION IN REMOTE SENSING (WHISPERS)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhe Zhang et al.
Summary: This paper proposes a multi-features integration based tracking method over Hyperspectral Videos (HSVs) to distinguish similar targets, utilizing rich spectral information. The method outperforms three existing tracking methods with hyperspectral information, showing better performance in tracking challenging targets with the same appearance in visible videos.
2021 11TH WORKSHOP ON HYPERSPECTRAL IMAGING AND SIGNAL PROCESSING: EVOLUTION IN REMOTE SENSING (WHISPERS)
(2021)
Article
Computer Science, Artificial Intelligence
Kai Yang et al.
KNOWLEDGE-BASED SYSTEMS
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Fei Du et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Computer Science, Artificial Intelligence
Fengchao Xiong et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Geochemistry & Geophysics
Burak Uzkent et al.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2019)
Article
Computer Science, Artificial Intelligence
Martin Danelljan et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Jongwon Choi et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Kaiming He et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Hamed Kiani Galoogahi et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Martin Danelljan et al.
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2015)
Article
Computer Science, Artificial Intelligence
Arnold W. M. Smeulders et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2014)
Article
Geochemistry & Geophysics
Adrian Jon Brown
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2006)