引入特征融合和Transformer模型预测器的目标跟踪算法

doi:10.3778/j.issn.1002-8331.2311-0077

摘要/Abstract

摘要： 近年来判别相关滤波器（DCF）在视觉跟踪领域取得了巨大的成功，然而大多数相关滤波跟踪器仅依赖主干网提取的最后一层特征，忽视了低层丰富的目标结构信息。基于此，提出了一种基于特征融合模块和Transformer结构模型预测器的目标跟踪算法。引入了一个金字塔形的特征融合模块，能有效整合低层特征和高层特征。使用采用非对称位置编码方案的Transformer结构预测目标模型权重，以释放模型的表达能力。提出了一个特征优化模块以根据模型权重优化搜索特征。与现有的方法相比，该算法实现了更优的特征表示和更准确的目标定位。在Tracking-Net、LaSOT和UAV123三个主流数据集上的实验结果表明，跟踪器获得了突出性能。

关键词: 特征融合, Transformer, 目标跟踪, 特征优化, 目标分类

Abstract: Discriminative correlation filters (DCF) have achieved much success in visual tracking. However, most of them simply rely on the features extracted by the last layer of the backbone, while ignoring the low-level rich structural information. In view of this, a target tracking algorithm based on the feature fusion module and the Transformer structure model predictor is proposed. Firstly, a feature fusion module is introduced that integrates the low-level feature and high-level feature via a pyramidal structure. Then, a modified Transformer with asymmetric positional encoding scheme is applied to predict the weights of the model, which can effectively release the expressive ability of the model. Finally, a feature refinement module is employed to optimize the search features. Compared with the existing works, the tracker achieves better feature expression and more precise target localization. Extensive experiments on 3 mainstream datasets, TrackingNet, LaSOT and UAV123, demonstrate that the tracker gains prominent tracking results.

Key words: feature fusion, Transformer, object tracking, feature refinement, object classification

龚小梅, 张轶, 胡术. 引入特征融合和Transformer模型预测器的目标跟踪算法[J]. 计算机工程与应用, 2025, 61(6): 254-262.

GONG Xiaomei, ZHANG Yi, HU Shu. Target Tracking Algorithm with Feature Fusion and Transformer Based Model Predictor[J]. Computer Engineering and Applications, 2025, 61(6): 254-262.

参考文献

[1] WANG G, LUO C, SUN X, et al. Tracking by instance detection: a meta-learning approach[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 6288-6297.
[2] DANELLJAN M, GOOL L V, TIMOFTE R. Probabilistic regression for visual tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 7183-7192.
[3] ZHANG Z, LIU Y, WANG X, et al. Learn to match: automatic matching network design for visual tracking[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 13339-13348.
[4] DANELLJAN M, BHAT G, KHAN F S, et al. Atom: accurate tracking by overlap maximization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 4660-4669.
[5] ZHENG L, TANG M, CHEN Y, et al. Learning feature embeddings for discriminant model based tracking[C]//Proceedings of the 16th European Conference on Computer Vision (ECCV 2020), Glasgow, UK, 2020: 759-775.
[6] WANG N, ZHOU W, WANG J, et al. Transformer meets tracker: exploiting temporal context for robust visual tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 1571-1580.
[7] PAUL M, DANELLJAN M, MAYER C, et al. Robust visual tracking by segmentation[C]//Proceedings of the European Conference on Computer Vision, 2022: 571-588.
[8] LI S, ZHAO S, CHENG B, et al. Part-aware framework for robust object tracking[J]. IEEE Transactions on Image Processing, 2023, 32: 750-763.
[9] MAYER C, DANELLJAN M, PAUDEL D P, et al. Learning target candidate association to keep track of what not to track[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 13444-13454.
[10] BHAT G, DANELLJAN M, VAN GOOL L, et al. Know your surroundings: exploiting scene information for object tracking[C]//Proceedings of the 16th European Conference on Computer Vision (ECCV 2020), Glasgow, UK, 2020: 205-221.
[11] MAYER C, DANELLJAN M, BHAT G, et al. Transforming model prediction for tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 8731-8740.
[12] FAN H, LIN L, YANG F, et al. LaSOT: a high-quality benchmark for large-scale single object tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 5374-5383.
[13] HUANG L, ZHAO X, HUANG K. GOT-10k: a large high-diversity benchmark for generic object tracking in the wild[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 43(5): 1562-1577.
[14] MULLER M, BIBI A, GIANCOLA S, et al. TrackingNet: a large-scale dataset and benchmark for object tracking in the wild[C]//Proceedings of the European Conference on Computer Vision (ECCV), 2018: 300-317.
[15] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//Proceedings of the 13th European Conference on Computer Vision (ECCV 2014), Zurich, Switzerland, 2014: 740-755.
[16] MUELLER M, SMITH N, GHANEM B. A benchmark and simulator for UAV tracking[C]//Proceedings of the 14th European Conference on Computer Vision (ECCV 2016), Amsterdam, The Netherlands, 2016: 445-461.
[17] CHEN X, YAN B, ZHU J, et al. Transformer tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 8126-8135.
[18] YU B, TANG M, ZHENG L, et al. High-performance discriminative tracking with transformers[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 9856-9865.
[19] XIE F, WANG C, WANG G, et al. Learning tracking representations via dual-branch fully transformer networks[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 2688-2697.
[20] ZHOU Z, PEI W, LI X, et al. Saliency-associated object tracking[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 9866-9875.
[21] FU Z, LIU Q, FU Z, et al. Stmtrack: template-free visual tracking with space-time memory networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 13774-13783.
[22] GUO D, SHAO Y, CUI Y, et al. Graph attention tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 9543-9552.
[23] CHENG S, ZHONG B, LI G, et al. Learning to filter: siamese relation network for robust tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 4421-4431.
[24] ZHAO H, YAN B, WANG D, et al. Effective local and global search for fast long-term tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(1): 460-474.
[25] PAN S, ZHANG C, LI Z, et al. SiamCA: siamese visual tracking with customized anchor and target-aware interaction[J]. Expert Systems with Applications, 2024, 238: 121763.
[26] YAN B, PENG H, WU K, et al. Lighttrack: finding lightweight neural networks for object tracking via one-shot architecture search[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 15180-15189.
[27] ZHAO J, DAI K, ZHANG P, et al. Robust online tracking with meta-updater[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(5): 6168-6182.
[28] YU Y, XIONG Y, HUANG W, et al. Deformable siamese attention networks for visual object tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 6728-6737.
[29] CAO Z, HUANG Z, PAN L, et al. Towards real-world visual tracking with temporal contexts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023: 261049377.
[30] ZHANG Y, PAN H, WANG J, et al. Facing completely occluded short-term tracking based on correlation filters[J]. IEEE Transactions on Instrumentation Measurement, 2023, 72: 3317483.
[31] 谌海云, 王海川, 黄忠义, 等. 引入轻量级Transformer的无人机视觉跟踪[J]. 计算机工程与应用, 2024, 60(2): 244-253.
SHEN H Y, WANG H C, HUANG Z Y, et al. UAV visual tracking with lightweight Transformer[J]. Computer Engineering and Applications, 2024, 60(2): 244-253.
[32] HU W, WANG Q, ZHANG L, et al. SiamMask: a framework for fast online object tracking and segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(3): 3072-3089.
[33] YANG K, HE Z, PEI W, et al. SiamCorners: siamese corner networks for visual tracking[J]. IEEE Transactions on Multimedia, 2021, 24: 1956-1967.
[34] PANG H, SU J, MA R, et al. Multiple templates transformer for visual object tracking[J]. Knowledge-Based Systems, 2023, 280: 111025.
[35] 王淑贤, 葛海波, 李文浩. 多尺度通道注意与孪生网络的目标跟踪算法[J]. 计算机工程与应用, 2023, 59(14): 142-150.
WANG S X, GE H B, LI W H. Object tracking algorithm for multi-scale channel attention and siamese network[J]. Computer Engineering and Applications, 2023, 59(14): 142-150.

编辑推荐 0

Metrics

阅读次数

全文

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	0	0	0	70

	来源	本网站

	次数	70
	比例	100%

摘要

最新录用	在线预览	正式出版

0	0	49

	来源	本网站

	次数	49
	比例	100%