Due to the issues of remote sensing object detection algorithms based on deep learning, such as a high number of network parameters, large model size, and high computational requirements, it is challenging to deploy them on small mobile devices. This paper proposes an extremely lightweight remote sensing aircraft object detection network based on the improved YOLOv5n. This network combines Shufflenet v2 and YOLOv5n, significantly reducing the network size while ensuring high detection accuracy. It substitutes the original CIoU and convolution with EIoU and deformable convolution, optimizing for the small-scale characteristics of aircraft objects and further accelerating convergence and improving regression accuracy. Additionally, a coordinate attention (CA) mechanism is introduced at the end of the backbone to focus on orientation perception and positional information. We conducted a series of experiments, comparing our method with networks like GhostNet, PP-LCNet, MobileNetV3, and MobileNetV3s, and performed detailed ablation studies. The experimental results on the Mar20 public dataset indicate that, compared to the original YOLOv5n network, our lightweight network has only about one-fifth of its parameter count, with only a slight decrease of 2.7% in mAP@0.5. At the same time, compared with other lightweight networks of the same magnitude, our network achieves an effective balance between detection accuracy and resource consumption such as memory and computing power, providing a novel solution for the implementation and hardware deployment of lightweight remote sensing object detection networks.

Siamese networks are one of the most popular directions in the visual object tracking based on deep learning. In Siamese networks, the feature pyramid network (FPN) and the cross-correlation complete feature fusion and the matching of features extracted from the template and search branch, respectively. However, object tracking should focus on the global and contextual dependencies. Hence, we introduce a delicate residual transformer structure which contains a self-attention mechanism called encoder-decoder into our tracker as the part of neck. Under the encoder-decoder structure, the encoder promotes the interaction between the low-level features extracted from the target and search branch by the CNN to obtain global attention information, while the decoder replaces cross-correlation to send global attention information into the head module. We add a spatial and channel attention component in the target branch, which can further improve the accuracy and robustness of our proposed model for a low price. Finally, we detailly evaluate our tracker CTT on GOT-10k, VOT2019, OTB-100, LaSOT, NfS, UAV123 and TrackingNet benchmarks, and our proposed method obtains competitive results with the state-of-the-art algorithms.

The current popular one-shot multi-object tracking (MOT) algorithms are dominated by the joint detection and embedding paradigm, which have high inference speeds and accuracy, but their tracking performance is unstable in crowded scenes. Not only does the detection branch have difficulty in obtaining the accurate object position, but the ambiguous appearance of features extracted by the re-identification (re-ID) branch also leads to identity switches. Focusing on the above problems, this paper proposes a more robust MOT algorithm, named CSMOT, based on FairMOT. First, on the basis of the encoder–decoder network, a coordinate attention module is designed to enhance the information interaction between channels (horizontal and vertical coordinates), which improves its object-detection abilities. Then, an angle-center loss that effectively maximizes intra-class similarity is proposed to optimize the re-ID branch, and the extracted re-ID features are made more discriminative. We further redesign the re-ID feature dimension to balance the detection and re-ID tasks. Finally, a simple and effective data association mechanism is introduced, which associates each detection instead of just the high-score detections during the tracking process. The experimental results show that our one-shot MOT algorithm achieves excellent tracking performance on multiple public datasets and can be effectively applied to crowded scenes. In particular, CSMOT decreases the number of ID switches by 11.8% and 33.8% on the MOT16 and MOT17 test datasets, respectively, compared to the baseline.

Region proposal network (RPN) based trackers employ the classification and regression block to generate the proposals, the proposal that contains the highest similarity score is formulated to be the groundtruth candidate of next frame. However, region proposal network based trackers cannot make the best of the features from different convolutional layers, and the original loss function cannot alleviate the data imbalance issue of the training procedure. We propose the Spatial Cascaded Transformed RPN to combine the RPN and STN (spatial transformer network) together, in order to successfully obtain the proposals of high quality, which can simultaneously improves the robustness. The STN can transfer the spatial transformed features though different stages, which extends the spatial representation capability of such networks handling complex scenarios such as scale variation and affine transformation. We break the restriction though an easy samples penalization loss (shrinkage loss) instead of smooth L1 function. Moreover, we perform the multi-cue proposals re-ranking to guarantee the accuracy of the proposed tracker. We extensively prove the effectiveness of our proposed method on the ablation studies of the tracking datasets, which include OTB-2015 (Object Tracking Benchmark 2015), VOT-2018 (Visual Object Tracking 2018), LaSOT (Large Scale Single Object Tracking), TrackingNet (A Large-Scale Dataset and Benchmark for Object Tracking in the Wild) and UAV123 (UAV Tracking Dataset).

Small-target detection in remote sensing presents three fundamental challenges: limited pixel representation of targets, multi-angle imaging-induced appearance variance, and complex background interference. This paper introduces a dual-component neural architecture comprising Hierarchical Dynamic Refinement Attention (HiDRA) and Densely Connected Dilated Block (DCDBlock) to address these challenges systematically. The HiDRA mechanism implements a dual-phase feature enhancement process: channel competition through bottleneck compression for discriminative feature selection, followed by spatial-semantic reweighting for foreground–background decoupling. The DCDBlock architecture synergizes multi-scale dilated convolutions with cross-layer dense connections, establishing persistent feature propagation pathways that preserve critical spatial details across network depths. Extensive experiments on AI-TOD, VisDrone, MAR20, and DOTA-v1.0 datasets demonstrate our method’s consistent superiority, achieving average absolute gains of +1.16% (mAP₅₀), +0.93% (mAP₉₅), and +1.83% (F1-score) over prior state-of-the-art approaches across all benchmarks. With 8.1 GFLOPs computational complexity and 2.6 ms inference speed per image, our framework demonstrates practical efficacy for real-time remote sensing applications, achieving superior accuracy–efficiency trade-off compared to existing approaches.