Synthetic aperture radar automatic target recognition (SAR ATR) with limited data has gained significant attention as practical application requirements change. Despite many proposed methods, key problems caused by the limited SAR data remain under-researched, hindering further performance improvement. In this paper, we establish an SAR ATR model based on causal theory. It compares the causal effect of SAR ATR between cases with ample and limited data, showing that the negative impact of the confounder, which is blocked with ample data, is introduced with limited data, resulting in poor performance of limited-data SAR ATR. To address this, we propose a limited-data SAR ATR causal method via dual invariance intervention, which first derives the causal interventional solution. This solution is transformed into two optimizable objectives: inner-class feature invariance and the independence of features from the confounder. Subsequently, the dual invariance mechanism is designed to filter SAR outlier samples and noise features under limited-data conditions, accurately obtaining the intra-class invariant feature. It also alleviates the need for ample SAR data when optimizing the independence of features from the confounder, achieving the two objectives. Finally, the proposed method not only unravels the key problem caused by limited data but also derives an effective solution with precise recognition performance. Extensive experiments on three benchmark datasets validate the rationality of the causal SAR ATR model, the effectiveness of the solution, and the soundness and recognition performance of the method. The codes and more experimental results will be released at https://github.com/cwwangSARATR/SARATR Causal Dual Invariance.

Panoptic Scene Graph Generation (PSG) translates visual scenes to structured linguistic descriptions, i.e., mapping visual instances to subjects/objects, and their relationships to predicates. However, the annotators' preferences and semantic overlaps between predicates inevitably lead to the semantic mappings of multiple predicates to one relationship, i.e., biased-predicate annotations. As a result, with the contradictory mapping between visual and linguistics, PSG models are struggled to construct clear decision planes among predicates, so as to cause existing poor performances. Obviously, it is essential for the PSG task to tackle this multi-modal contradiction. Therefore, we propose a novel method that utilizes unbiased visual predicate representations for Biased-Annotation Identification (BAI) as a fundamental step for PSG/SGG tasks. Our BAI includes three main steps: predicate representation extraction, predicate representation debiasing, and biased-annotation identification. With flexible biased annotation processing methods, our BAI can act as a fundamental step of dataset debiasing. Experimental results demonstrate that our proposed BAI has achieved state-of-the-art performance, which promotes the performance of benchmark models to various degrees with ingenious biased annotation processing methods. Furthermore, our BAI shows great generalization and effectiveness on multiple datasets. Our codes are released at https://github.com/lili0415/BAI.

Accurate and scalable indoor localization for uncrewed aerial vehicles (UAVs) is essential for Internet of Things (IoT) applications such as autonomous logistics, infrastructure inspection, and emergency response in GPS-denied environments. However, traditional methods often struggle with cost, deployment complexity, and sensitivity to environmental dynamics, limiting their practicality for large-scale IoT scenarios. This article presents a method in which channel state information (CSI) from low-cost IoT sensors enables robust, device-free 3-D UAV localization while optimizing accuracy, sensor adaptability, and data efficiency. We propose CiUAV, leveraging CSI captured by ESP32-S3 sensors, with a robust CSI signal enhancement (RCSE) framework integrating dynamic automatic gain control (AGC) compensation (DAC) and adaptive noise suppression and outlier removal (ANSOR), alongside a sensor-in-sample (SiS) multiobjective optimization (MOO) model for adaptive multisensor fusion. Experimental evaluations in realistic indoor settings achieve a 3-D root-mean-squared error (RMSE) of 0.2659 m, outperforming baselines by up to 35% in accuracy and 50% in data efficiency. CiUAV offers a lightweight, scalable, and infrastructure-compatible solution for future IoT-enabled UAV systems.

Synthetic aperture radar automatic target recognition (SAR ATR) methods often struggle due to inadequate training data. In this letter, we introduce a causal interventional ATR method (CIATR), specifically designed to address the challenges posed by limited synthetic aperture radar (SAR) data. This approach is key in revealing the underlying causal relationships among essential factors in ATR, enabling us to achieve the desired causal effect without altering the imaging conditions (ICs). To address the challenges in SAR ATR with limited data, we developed a structural causal model (SCM) based on causal inference principles. This model helps identify how ICs, as confounders, induce spurious correlations between SAR images and their classifications, which can be solved by standard backdoor adjustment. Our implementation of backdoor adjustment begins with data augmentation, employing a spatial-frequency domain hybrid transformation. This step is crucial in estimating the potential effects of varied ICs on SAR images. Following this, a feature discrimination strategy is introduced to incorporate a hybrid similarity measurement. This technique is essential for assessing and mitigating the impact of changing ICs on the features extracted from SAR images, focusing on both structural and vector angle influences. The CIATR method effectively uncovers the true causal relationships between SAR images and their classes, even with limited data. Tested on MSTAR and OpenSARship datasets, our method shows promising performance in limited data scenarios, achieving 75.05% for ten-way five shots.

Synthetic aperture radar (SAR) imaging plays a crucial role in remote sensing, however, the inherent hardware characteristics, such as limited system bandwidth and the impacts of the synthetic aperture time, inevitably lead to resolution loss of SAR images. Low spatial resolution may lead to decreased image detail and blurred image edge. To enhance spatial resolution and suppress edge blurring in SAR images, this paper proposes a multi-scale edge texture-oriented generative adversarial network-based (METGAN) SAR image super-resolution approach. The proposed METGAN model comprises two phases: the super-resolution phase and the multi-scale edge texture enhancement phase. In the super-resolution phase, attention residual dense block (ARDB) units are designed to enhance spatial resolution without significant loss of edge information. In the multi-scale edge texture enhancement phase, the edge detection operator is incorporated into the texture coarse extraction (TCE) module for coarse extraction of image edges. Subsequently, within the attention multi-scale texture enhancement (AMTE) module, the atrous spatial pyramid pooling is integrated to enhance feature extraction capabilities. Based on the proposed ARDB unit and multi-scale edge texture enhancement stage, super-resolution SAR images with high spatial resolution and image details can be obtained. Experimental results on public datasets SARBuD and RSDD-SAR demonstrate that the proposed METGAN approach offers superior reconstruction performance compared to traditional methods and other GAN-based approaches.

The application of unmanned aerial vehicles (UAVs) in urban environments introduces complex challenges to path planning due to dynamic targets, changing environmental con ditions, and stringent safety requirements. To address these issues, this paper proposes an Evolving Collaborative Differential Evolution (ECDE) algorithm specifically designed for dynamic multi-objective UAV path planning. ECDE integrates an adaptive hyperparameter tuning mechanism, a robust change detection strategy, and a collaborative learning strategy to effectively balance multiple conflicting objectives, such as minimizing path length, energy consumption, noise pollution, and collision risk. Comprehensive experimental evaluations are conducted under various scenarios, including static environments, dynamic targets, and risk-adaptive urban navigation. The results demonstrate that ECDE consistently achieves superior global optimization performance and adaptability compared to state-of-the-art multi objective optimization methods, thereby significantly enhancing UAV operational effectiveness in complex, real-world urban scenarios.