Search

With the rapid development of deep learning, convolutional neural networks have achieved milestones in synthetic aperture radar (SAR) image object detection. However, object detection in SAR images is still a great challenge due to the difficulty in distinguishing targets from complex backgrounds. At the same time, most of the targets in SAR images are small and unevenly distributed, which makes it challenging to extract sufficient feature information. To solve these issues mentioned above, an efficient object detection network for SAR images based on Swin transformer and YOLOv7 is proposed in this article. First, we design a novel feature aggregation module Petty-specialized feature aggregation (PS-FPN) to enrich small targets’ semantic and spatial features while keeping the model lightweight. PS-FPN module uses the fusion of deep and shallow features by using cross-layer feature aggregation and single-branch feature aggregation to enhance the detection of small targets. Second, a novel attention mechanism strategy mix-attention is proposed to find more attention regions. Finally, we add one more prediction head to extract shallow features that effectively preserve small targets’ feature information. To verify the effectiveness of the proposed algorithm, extensive experiments are carried out on several challenging SAR image datasets. The results show that, compared with other state-of-the-art detectors, the proposed method can achieve significant performance based on lightweight detection.

The current methods for lightning risk warnings that are based on atmospheric electric field (AEF) data have a tendency to rely on single features, which results in low robustness and efficiency. Additionally, there is a lack of research on canceling warning signals, contributing to the high false alarm rate (FAR) of these methods. To overcome these limitations, this study proposes a lightning risk warning method that incorporates enhanced empirical Wavelet transform-Adaptive Savitzky–Golay filter (EEWT-ASG) and one-dimensional morphology, using time-frequency domain features obtained through the Wavelet transform (WT). The proposed method achieved a probability of detection (POD) of 77.11%, miss alarm rate (MAR) of 22.89%, FAR of 40.19%, and critical success index (CSI) of 0.51, as evaluated on 83 lightning events. This method can issue a warning signal up to 22 min in advance for lightning processes.

Observational data from the low-frequency electric-field detection array (LFEDA) and radar were used to study the precise location of a fatal accident caused by a lightning in Conghua, Guangzhou, China, 2017. Based on a comprehensive analysis, the lightning was concluded to be a negative “bolt from the blue” ground flash with seven return strokes. The first return stroke was on June 3 at 16:36:49.219 with a peak current intensity of −30.9 kA. The LFEDA system mapped the development of the lightning channel. The horizontal distance from the edge of the cloud anvil area (0 dBz) to the return stroke point was about 0.3 km, the horizontal distance from the edge of the precipitation area (18 dBz) to the return stroke point was about 1.8 km, and the return stroke channel extended as far as 3 km out of the cloud. There was no cloud cover above the head of the victim. The electric field waveform of the return strokes detected by the LFEDA system showed multi-peak characteristics, and all seven return strokes were multiple-termination strokes. The most probable mechanism for the lightning injuries was the side flash.

Aiming at the problem of low accuracy of small target detection in Unmanned Aerial Vehicle (UAV) aerial remote sensing images and limited computing resources of UAV platform, this paper proposes a novel real-time detection algorithm for aerial remote sensing images. Firstly, the Spatial Pyramid Pooling-Fast (SPPF) is used to fuse the global and local features in different receptive fields. Second, we propose the Drone-captured Path Aggregation Network (CPAN) to enrich the semantic features of small targets while keeping the model lightweight. CPAN adds a new detection layer and uses the fusion of deep and shallow feature information to enhance the detection of small targets. At the same time, it uses depthwise separable convolution (DSC) to reduce the number of parameters. Then, Coordinate Attention (CA) is used to capture the cross-channel information with direction-aware and position-aware information. Finally, Decoupled-Head is introduced to make the detection of classification and coordinate regression more robust. We evaluate our model based on the aerial remote sensing dataset. The experimental results show that the proposed method provides a better balance between accuracy and speed than other lightweight networks. [ABSTRACT FROM AUTHOR]