The object detection of unmanned aerial vehicle (UAV) images has widespread applications in numerous fields; however, the complex background, diverse scales, and uneven distribution of objects in UAV images make object detection a challenging task. This study proposes a convolution neural network (CNN)-transformer hybrid model to achieve efficient object detection in UAV images, which has three advantages that contribute to improving the object detection performance. First, the efficient and effective cross-shaped window (CSWin) transformer can be used as a backbone to obtain image features at different levels, and the obtained features can be input into the feature pyramid network (FPN) to achieve multi-scale representation, which will contribute to multi-scale object detection. Second, a hybrid patch embedding module is constructed to extract and utilize low-level information such as the edges and corners of the image. Finally, a slicing-based inference method is constructed to fuse the inference results of the original image and sliced images, which will improve the small object detection accuracy without modifying the original network. Experimental results on public datasets illustrate that the proposed method can improve the performance more effectively than several popular and state-of-the-art object detection methods.

Landslide detection based on remote sensing images is an effective method for rapidly and accurately detecting landslide regions, which can aid in disaster prevention and mitigation. Landslide detection methods based on semantic segmentation can be used to delineate the scope of landslides while detecting their location. Most existing models use multi-temporal or geological data to improve accuracy. However, the large amount of data introduces additional parameters, consuming significant computing resources. Therefore, this study proposes Reg-SA–UNet++, a model for landslide detection, which uses a single-temporal image captured post-landslide. Reg-SA–UNet++ is based on UNet++ with the following modifications: deep supervised pruning is removed for fewer model parameters and increased detection accuracy; RegNet is employed to replace the convolutional blocks in the encoding process to reduce the number of parameters and improve feature acquisition and attention modules are added at the connection of the convolutional blocks of each layer to strengthen the model's attention to landslide features. The overall accuracy and F1 score of the Reg-SA–UNet++ model for the constructed landslide dataset (93.37% and 92.41%, respectively) and landslide mapping (97.09% and 96.10%, respectively) verify the effectiveness of the proposed model in detecting landslides from remote sensing images.

The extensive application of unmanned aerial vehicle (UAV) technology has increased academic interest in object detection algorithms for UAV images. Nevertheless, these algorithms present issues such as low accuracy, inadequate stability, and insufficient pre-training model utilization. Therefore, a high-quality object detection method based on a performance-improved object detection baseline and pretraining algorithm is proposed. To fully extract global and local feature information, a hybrid backbone based on the combination of convolutional neural network (CNN) and vision transformer (ViT) is constructed using an excellent object detection method as the baseline network for feature extraction. This backbone is then combined with a more stable and generalizable optimizer to obtain high-quality object detection results. Because the domain gap between natural and UAV aerial photography scenes hinders the application of mainstream pre-training models to downstream UAV image object detection tasks, this study applies the masked image modeling (MIM) method to aerospace remote sensing datasets with a lower volume than mainstream natural scene datasets to produce a pre-training model for the proposed method and further improve UAV image object detection accuracy. Experimental results for two UAV imagery datasets show that the proposed method achieves better object detection performance compared to state-of-the-art (SOTA) methods with fewer pre-training datasets and parameters.

Synthetic aperture radar automatic target recognition (SAR-ATR) models based on deep neural networks (DNNs) are vulnerable to attacks of adversarial examples. Universal adversarial attack algorithms can help evaluate and improve the robustness of the SAR-ATR models and have become a research hotspot. However, current universal adversarial attack algorithms have limitations. First, considering the difficulty in obtaining information on the attacking SAR-ATR models, there is an urgent need to design a universal adversarial attack algorithm under a black-box scenario. Second, given the difficulty of acquiring SAR images, the effectiveness of attacks under small-sample conditions requires improvement. To address these limitations, this study proposed a black-box universal adversarial attack algorithm: Transferable Universal Adversarial Network (TUAN). Based on the idea of the generative adversarial network, we implemented the game of generator and attenuator to improve the transferability of universal adversarial perturbation (UAP). We designed loss functions for the generator and attenuator respectively, which can effectively improve the success rate of black-box attacks and the stealthiness of attacks. Additionally, U-Net was used as a network structure of generator and attenuator to fully learn the distribution of examples, thereby enhancing the attack success rate under small-sample conditions. TUAN attained a higher black-box attack success rate and superior stealthiness than up-to-date UAP algorithms in non-targeted and targeted attacks.

Synthetic aperture radar (SAR) automatic target recognition (ATR) systems based on deep neural network models are vulnerable to adversarial examples. Existing SAR adversarial attack algorithms require access to the network structure, parameters, and training data, which are often inaccessible in real-world scenarios. To address this problem, this study proposes an intermediate layer feature attack algorithm that does not rely on training data for the adversary model. Electromagnetic simulation is used to obtain the simulated SAR local data domain during the training stage. A lightweight generator, TinyResNet, is introduced to quickly construct adversarial examples through a one-step mapping process. In addition, the transferability of these examples across different models is improved by eliminating the intermediate layer features of the model. Finally, a domain-agnostic feature attention module is utilized to reduce discrepancies between different data domains from a model perspective, further improving the transferability of adversarial examples across domains. Experimental results on five SAR datasets of ground vehicles, ships, and scene types demonstrate that the proposed algorithm outperforms 13 mainstream adversarial attack algorithms in terms of cross-model and cross-data domain transferability. In particular, the proposed method improves the cross-domain attack success rate by 43.74%–48.88% on the MSTAR dataset.

Edge detection is highly susceptible to streaking caused by speckles in polarimetric synthetic aperture radar (PolSAR) imagery. In this article, we address hysteresis thresholding for suppress streaking in PolSAR's edge detection. As an example, an approach is suggested by combining the constant false alarm ratio (CFAR) detector and the hysteresis thresholding. After thinning edges obtained by the CFAR detector, the hysteresis thresholding is employed to reduce edge streaking, which is caused by abundant speckles. A ratio of the high to the low threshold P_fa in the hysteresis thresholding is pointed out for linking edges. Experiments are carried out on both simulated and real PolSAR data sets, and the results reveal that hysteresis thresh- olding obviously promotes the performance of the CFAR detector.