Tracking in UAV scenarios is a complex and important task. Different from target tracking in general scenarios, due to the unique characteristics of the UAV view, the UAV tracking task is faced with many very challenging scenarios such as viewpoint changes and aerial view. Although the Siamese series of trackers have achieved good performance in general scenes, the existing methods of enhancing local features at certain levels may be effective for general scene tracking, but the lack of broad-spectrum relevance will lead to degradation of accuracy, especially in aerial tracking scenarios. In this letter, we propose a broad-spectrum relevance fusion model (SiamBRF) in the Siamese-based tracking framework to efficiently obtain relevance at broad-spectrum levels to enhance the feature representation, thereby enabling our tracker to be more suitable for solving UAV-tracking tasks. Specifically, a coordinate contextual encoder (CCE) is designed to update the saliency representations, and then the transformer cascaded fusion (TCF) structure is used to realize the interbranch information exchange and integration, which could precisely distinguish the target and background in the UAV-tracking scenarios. Finally, we design a spatiotemporal dependency fusion (SDF) network for deep features to better balance the semantic and spatial information. Several experiments demonstrate that our SiamBRF achieves around 3% performance improvement in precision and success rate over the mainstream Siamese-based trackers.

In this paper, we address aerial tracking tasks by designing multi-phase aware networks to obtain rich long-range dependencies. For aerial tracking tasks, the existing methods are prone to tracking drift in scenarios with high demand for multi-layer long-range feature dependencies such as viewpoint change caused by the characteristics of the UAV shooting perspective, low resolution, etc. In contrast to the previous works that only used multi-scale feature fusion to obtain contextual information, we designed a new architecture to adapt the characteristics of different levels of features in challenging scenarios to adaptively integrate regional features and the corresponding global dependencies information. Specifically, for the proposed tracker (SiamMAN), we first propose a two-stage aware neck (TAN), where first a cascaded splitting encoder (CSE) is used to obtain the distributed long-range relevance among the sub-branches by the splitting of feature channels, and then a multi-level contextual decoder (MCD) is used to achieve further global dependency fusion. Finally, we design the response map context encoder (RCE) utilizing long-range contextual information in backpropagation to accomplish pixel-level updating for the deeper features and better balance the semantic and spatial information. Several experiments on well-known tracking benchmarks illustrate that the proposed method outperforms SOTA trackers, which results from the effective utilization of the proposed multi-phase aware network for different levels of features.

For the Siamese network-based trackers utilizing modern deep feature extraction networks without taking full advantage of the different levels of features, tracking drift is prone to occur in aerial scenarios, such as target occlusion, scale variation, and low-resolution target tracking. Additionally, the accuracy is low in challenging scenarios of visual tracking, which is due to the imperfect utilization of features. To improve the performance of the existing Siamese tracker in the above-mentioned challenging scenes, we propose a Siamese tracker based on Transformer multi-level feature enhancement with a hierarchical attention strategy. The saliency of the extracted features is enhanced by the process of Transformer Multi-level Enhancement; the application of the hierarchical attention strategy makes the tracker adaptively notice the target region information and improve the tracking performance in challenging aerial scenarios. Meanwhile, we conducted extensive experiments and qualitative or quantitative discussions on UVA123, UAV20L, and OTB100 datasets. Finally, the experimental results show that our SiamHAS performs favorably against several state-of-the-art trackers in these challenging scenarios.

In recent years, many studies have used Siamese networks (SNs) for UAV tracking. However, there are two problems with SNs for UAV tracking. Firstly, the information sources of the SNs are the invariable template patch and the current search frame. The static template information lacks the perception of dynamic feature information flow, and the shallow feature extraction and linear sequential mapping severely limit the mining of feature expressiveness. This makes it difficult for many existing SNs to cope with the challenges of UAV tracking, such as scale variation and viewpoint change caused by the change in height and angle of the UAV, and the challenges of background clutter and occlusion caused by complex aviation backgrounds. Secondly, the SNs trackers for UAV tracking still struggle with extracting lightweight and effective features. A tracker with a heavy-weighted backbone is not welcome due to the limited computing power of the UAV platform. Therefore, we propose a lightweight spatial-temporal contextual Siamese tracking system for UAV tracking (SiamST). The proposed SiamST improves the UAV tracking performance by augmenting the horizontal spatial information and introducing vertical temporal information to the Siamese network. Specifically, a high-order multiscale spatial module is designed to extract multiscale remote high-order spatial information, and a temporal template transformer introduces temporal contextual information for dynamic template updating. The evaluation and contrast results of the proposed SiamST with many state-of-the-art trackers on three UAV benchmarks show that the proposed SiamST is efficient and lightweight.

Benefiting from the powerful feature extraction capability of deep learning, the Siamese tracker stands out due to its advanced tracking performance. However, constrained by the complex backgrounds of aerial tracking, such as low resolution, occlusion, similar objects, small objects, scale variation, aspect ratio change, deformation and limited computational resources, efficient and accurate aerial tracking is still difficult to realize. In this work, we design a lightweight and efficient adaptive temporal contextual aggregation Siamese network for aerial tracking, which is designed with a parallel atrous module (PAM) and adaptive temporal context aggregation model (ATCAM) to mitigate the above problems. Firstly, by using a series of atrous convolutions with different dilation rates in parallel, the PAM can simultaneously extract and aggregate multi-scale features with spatial contextual information at the same feature map, which effectively improves the ability to cope with changes in target appearance caused by challenges such as aspect ratio change, occlusion, scale variation, etc. Secondly, the ATCAM adaptively introduces temporal contextual information to the target frame through the encoder-decoder structure, which helps the tracker resist interference and recognize the target when it is difficult to extract high-resolution features such as low-resolution, similar objects. Finally, experiments on the UAV20L, UAV123@10fps and DTB70 benchmarks demonstrate the impressive performance of the proposed network running at a high speed of over 75.5 fps on the NVIDIA 3060Ti.

Due to the uniqueness of its perspective and the continuity of tracking, the current utilization of UAV in tracking has demonstrated immense potential in the field of aviation remote sensing. However, constrained by the complexities of the real-world environment during the tracking process and the limited computational capabilities of the onboard computing platform, existing tracking networks struggle to effectively integrate superior tracking performance with efficient computational speed. Addressing this pivotal issue, we proposed the Separation Fusion Transformer and Efficient Reuse Matching Network for Aerial tracking (SFTrack). Specifically, we designed the Separation Fusion Transformer, leveraging a meticulously crafted low-latency Transformer architecture to extract robust feature information of the target, thereby enhancing the algorithm’s ability to distinguish the target from intricate backgrounds. Furthermore, the Efficient Reuse Matching Network efficiently performs feature matching to accurately determine the target’s scale and location. SFTrack exhibits efficient and precise performance in drone tracking tasks. When compared to other drone-to-ground tracking algorithms, SFTrack demonstrates a significant lead in accuracy across multiple datasets, achieving an impressive 54 frames persecond (FPS) on embedded platforms. This validates the feasibility and effectiveness of our tracker in practical drone deployments.