Remote sensing image object detection and instance segmentation are widely valued research fields. A convolutional neural network (CNN) has shown defects in the object detection of remote sensing images. In recent years, the number of studies on transformer-based models increased, and these studies achieved good results. However, transformers still suffer from poor small object detection and unsatisfactory edge detail segmentation. In order to solve these problems, we improved the Swin transformer based on the advantages of transformers and CNNs, and designed a local perception Swin transformer (LPSW) backbone to enhance the local perception of the network and to improve the detection accuracy of small-scale objects. We also designed a spatial attention interleaved execution cascade (SAIEC) network framework, which helped to strengthen the segmentation accuracy of the network. Due to the lack of remote sensing mask datasets, the MRS-1800 remote sensing mask dataset was created. Finally, we combined the proposed backbone with the new network framework and conducted experiments on this MRS-1800 dataset. Compared with the Swin transformer, the proposed model improved the mask AP by 1.7%, mask AP_S by 3.6%, AP by 1.1% and AP_S by 4.6%, demonstrating its effectiveness and feasibility.

The wide range, complex background, and small target size of aerial remote sensing images results in the low detection accuracy of remote sensing target detection algorithms. Traditional detection algorithms have low accuracy and slow speed, making it difficult to achieve the precise positioning of small targets. This paper proposes an improved algorithm based on You Only Look Once (YOLO)-v3 for target detection of remote sensing images. Due to the difficulty in obtaining the datasets, research on small targets for complex images, such as airplanes and ships, is the focus of research. To make up for the problem of insufficient data, we screen specific types of training samples from the DOTA (Dataset of Object Detection in Aerial Images) dataset and select small targets in two different complex backgrounds of airplanes and ships to jointly evaluate the optimization degree of the improved network. We compare the improved algorithm with other state-of-the-art target detection algorithms. The results show that the performance indexes of both datasets are ameliorated by 1–3%, effectively verifying the superiority of the improved algorithm.

The gradual development of remote sensing object tracking technology based on unmanned aerial vehicles (UAV) videos has become one of the main research directions in the field of visual tracking. However, due to characteristics of the UAV platform, typical visual tracking algorithms currently applied to natural scenes cannot be used directly. Small-scale objects in UAV remote sensing videos are difficult to detect and have the problem of tracking identity switching. In order to solve these problems, we designed the Swin transformer neck YOLOX (STN-YOLOX) object detection algorithm as the detection module, and the G-Byte data association method as the tracking module. We then combined the two into a new multi-object tracking algorithm named STN-Track. We used STN-Track to conduct experiments on the UAVDT and VisDrone MOT datasets. The experimental results show that compared with the current state-of-the-art (SOTA) methods, our STN-Track has improved detection and tracking accuracy of small-scale objects and greatly improved identification capabilities for object tracking. Compared with the SOTA ByteTrack algorithm, MOTA of STN-Track can be improved by up to 3.2%, AP _S can be improved by up to 4.4%, MT can be improved by up to 6.8%, and IDSW can be reduced by up to 28.0%.

Remote sensing object detection has been an important and challenging research hotspot in computer vision that is widely used in military and civilian fields. Recently, the combined detection model of CNN and Transformer has achieved good results, but the problem of poor detection performance of small objects still needs to be solved urgently. This letter proposes a deformable DETR-based framework for object detection in remote sensing images. Firstly, Multi-Scale Split Attention (MSSA) is designed to extract more detailed feature information by grouping. Next, we propose Multi-Scale Deformable Prescreening Attention (MSDPA) mechanism in decoding layer, which achieves the purpose of pre-screening, so that the encoder-decoder structure can obtain attention map more efficiently. Finally, the A-D loss function is applied to the prediction layer, increasing the attention of small objects and optimizing the IOU function. We conduct extensive experiments on the DOTA v1.5 dataset and the HRRSD dataset, which show that the reconstructed detection model is more suitable for remote sensing objects, especially for small objects. The average detection accuracy in DOTA dataset has improved by 4.4% (up to 75.6%), especially the accuracy of small objects has raised by 5%.

The You Only Look Once (YOLO) series has been widely adopted across various domains. With the increasing prevalence of continuous satellite observation, the resulting video streams can be subjected to intelligent analysis for various applications, such as traffic flow statistics, military operations, and other fields. Nevertheless, the signal-to-noise ratio of objects in satellite videos is considerably low, and their size is often smaller, ranging from tens to one percent, when compared to those taken by drones and other equipment. Consequently, the original YOLO algorithm’s performance is inadequate when detecting tiny objects in satellite videos. Hence, we propose an improved framework, named HB-YOLO. To enable the backbone to extract features, we replaced the universal convolution with an improved HorNet that enables higher-order spatial interactions. We replaced all Extended Efficient Layer Aggregation Networks (ELANs) with the BoTNet attention mechanism to make the features fully fused. In addition, anchors were re-adjusted, and image segmentation was integrated to achieve detection results, which are tracked using the BoT-SORT algorithm. The experimental results indicate that the original algorithm failed to learn using the satellite video dataset, whereas our proposed approach yielded improved recall and precision. Specifically, the F1-score and mean average precision increased to 0.58 and 0.53, respectively, and the object-tracking performance was enhanced by incorporating the image segmentation method.