Small target detection in remote sensing images has considerable significance in practical applications such as military dynamic discrimination and traffic monitoring. However, the limited appearance features of small-scale targets and the widespread false alarm sources make small target detection in remote sensing images a tough challenge. To address these problems, we propose a novel small detection method by employing an adaptive multi-level feature fusion module (AMFFM) and an attention-augmented high-resolution head (AAHRH). Specifically, AMFFM is designed to suppress the interference of false alarm sources in complicated scenes. We upsample the high-level features by the context modeling of semantic information and refine the low-level features for noise removal. Then the enhanced multi-level features are fused based on the spatial and channel significance. After that, AAHRH is put forward to enhance the perception of small targets by embedding cross-dimension interaction with the attention mechanism. The prediction heads are reconstructed with high-resolution layers to improve the detection performance in densely distributed scenes. We conduct dilated and comparison experiments on a constructed small car dataset, a public small ship dataset, and the VEDAI dataset. The experimental results on two datasets verify the effectiveness and robustness of the proposed method with the state-of-the-art performance.

The growing intelligence and prevalence of drones have led to an increase in their disorderly and illicit usage, posing substantial risks to aviation and public safety. This paper focuses on addressing the issue of drone detection through surveillance cameras. Drone targets in images possess distinctive characteristics, including small size, weak energy, low contrast, and limited and varying features, rendering precise detection a challenging task. To overcome these challenges, we propose a novel detection method that extends the input of YOLOv5s to a continuous sequence of images and inter-frame optical flow, emulating the visual mechanisms employed by humans. By incorporating the image sequence as input, our model can leverage both temporal and spatial information, extracting more features of small and weak targets through the integration of spatiotemporal data. This integration augments the accuracy and robustness of drone detection. Furthermore, the inclusion of optical flow enables the model to directly perceive the motion information of drone targets across consecutive frames, enhancing its ability to extract and utilize features from dynamic objects. Comparative experiments demonstrate that our proposed method of extended input significantly enhances the network’s capability to detect small moving targets, showcasing competitive performance in terms of accuracy and speed. Specifically, our method achieves a final average precision of 86.87%, representing a noteworthy 11.49% improvement over the baseline, and the speed remains above 30 frames per second. Additionally, our approach is adaptable to other detection models with different backbones, providing valuable insights for domains such as Urban Air Mobility and autonomous driving.

Aircraft detection in remote sensing images is significant in both military and civilian fields, such as air traffic control and battlefield dynamic monitoring. Deep learning methods can achieve promising detection performance with sufficient and labeled samples. However, current aircraft datasets are mainly from a single data source and lack diverse scenes and targets, making it difficult to train a robust and generalized detector. Therefore, we manually label and construct a complex optical remote sensing aircraft target detection dataset (CORS-ADD) from Google Earth and multiple satellites such as WorldView-2, WorldView-3, Pleiades, Jilin-1, and IKONOS. It contains 7,337 images covering typical airports and various rare scenes, including the aircraft carrier, ocean and land with flying aircraft. The dataset consists of 32,285 civil and military aircraft instances, including bombers, fighters, and early warning aircraft. These targets range from 4×4 pixels to 240×240 pixels and are all labeled with both horizontal bounding box (HBB) and oriented bounding box (OBB) annotations. The various scenes and sufficient instances can fully support the training and evaluation of data-driven algorithms. Meanwhile, based on the constructed dataset, we train and evaluate several detectors to provide a benchmark and help promote the development of aircraft detection techniques.