Explore the vast range of titles available.

The looking-down mode of space airship bistatic radars faces complex sea–land clutter, and the mode of wide-range surveillance and the over-sight detection of the satellite platform generates a low SNR and range–Doppler ambiguity. The method traditionally used involves the transmission of multiple Pulse Repetition Frequencies (PRFs) and correlating them to solve the ambiguity. However, with a low SNR, the traditional disambiguation fails due to the large number of false alarms and target omissions. In order to solve this problem, a new algorithm for multi-target joint detection and range–Doppler disambiguation based on an ambiguity matrix is presented. Firstly, all possible state values corresponding to the ambiguous sequence are filled into the ambiguity matrix one by one. Secondly, the state values in the matrix cell are divided into several groups of subsequences according to the PRF. By disambiguating multiple sets of subsequences, performing subsequence fusion, and then undertaking point aggregation, the targets can be effectively detected in scenarios with a strong clutter rate, the false alarms can be suppressed, and the disambiguation of the range and Doppler is completed. The simulation shows that the proposed algorithm has the strong ability to detect targets and perform ambiguity resolution in the scenario of a multi-target and multi-false alarm.

With the widespread deployment of automotive millimeter-wave radars, mutual interference and broadband noise severely degrade the signal-to-noise ratio (SNR) of range–Doppler (RD) maps, leading to the loss of weak targets. Existing deep learning methods rely on difficult-to-obtain paired training samples and often cause excessive target smoothing due to a lack of physical constraints. To address these challenges, this paper proposes RIME-Net, a physics-guided unpaired learning framework designed to jointly achieve radar interference mitigation and weak target enhancement. First, based on a cycle-consistent adversarial architecture, we designed the Interference Mitigation Network (IM-Net). IM-Net integrates spectral consistency loss and identity mapping constraints, learning a robust mapping from the interference domain to the clean domain without paired supervision, effectively suppressing low-rank interference and preserving signal integrity. Second, to recover target details attenuated during denoising, we propose the saliency-aware Target Enhancement Network (TE-Net). TE-Net combines multi-scale residual blocks and channel-spatial attention mechanisms, selectively enhancing weak target features based on saliency priors. Extensive experiments on diverse datasets show that RIME-Net significantly outperforms existing supervised and model-driven methods in terms of SINR, recall, and structural similarity, providing a robust solution for reliable radar perception in complex electromagnetic environments.

Addressing the challenges of inadequate accuracy and limited robustness exhibited by current lightweight object detection networks specifically tailored for low-resolution thermal infrared face detection scenarios, this paper delves into developing an ultra-lightweight thermal infrared face detection algorithm that leverages visual attention mechanisms. To ascertain the optimal neural network complexity, a series of comparative experiments are meticulously conducted. With Yolo-FastestDet serving as the benchmark, this study endeavors to compress the backbone network, striking a delicate balance between network depth and detection speed. Additionally, to bolster the network’s capacity for profound feature extraction and precise discrimination of target edges and small objects, a Transformer-Encoder-based visual attention module is seamlessly integrated. Consequently, a lightweight face detection algorithm, enriched with attention mechanisms, is formulated. Furthermore, to mitigate the scarcity of low-resolution infrared face image data, a self-constructed visible-infrared face dataset is employed for training and evaluation purposes. The experimental outcomes reveal that the proposed algorithm attains an impressive mAP@0.5 score of 0.953 on the test dataset while satisfying the stringent real-time detection criterion of 30 frames per second (FPS) when deployed on an embedded Raspberry Pi CPU.

Aiming at the low observable target detection under sea clutter backgrounds, this paper emphasizes the exploration of distinguishable full-polarization features between target and sea clutter echoes. To overcome the shortcomings of the existing polarization feature-based methods, the full-polarization features of sea clutter are modeled and analyzed in detail by using Van Zyl polarization decomposition. Then, three polarimetric features (the relative surface scattering energy, the relative dihedral scattering energy and the relative diffuse scattering energy) are extracted from the fully polarimetric radar sea clutter echoes, which improve the feature differences between sea clutter and targets. And a tri-polarimetric feature detector with constant false alarm rate (CFAR) is constructed based on the fast convex hull learning algorithm. The experimental results on the real measured IPIX radar datasets prove that the proposed full-polarization feature detector obtains more competitive detection performance and lower computational complexity than the several existing feature-based detectors.

Automatically extract lake water bodies of optical remote sensing images is a very challenging task, because there are many small lakes in such images, these small lakes have the characteristics of weak target information and are easily interfered by noise information. Regarding above problems, this paper proposes an automatic extraction method of lake water based on semantic segmentation. Firstly, a multi-scale information enhancement network is designed based on the encoder-decoder structure, and the deep dilation residual structure is used in the encoder module of the network to improve the network’s ability to mine the deep feature information and the context information of the lake water bodies. Secondly, the two-way channel attention mechanism is introduced into the network, which can reduce the interference of noise information on the lake boundaries and improve the accuracy of the network to the lake boundaries segmentation. Finally, the up-sampling convolution operation is used in the decoder module of the network to reduce the information loss during the up-sampling process. In this paper, the performance of the designed network is tested by using remote sensing images of lakes of different map scales and various evaluation indexes. The experimental results show that the designed network has better segmentation accuracy than other semantic segmentation networks.

For an automotive pedestrian detection radar system, fast-ramp based 2D range-Doppler Frequency Modulated Continuous Wave (FMCW) radar is effective for distinguishing between moving targets and unwanted clutter. However, when a weak moving target such as a pedestrian exists together with strong clutter, the pedestrian may be masked by the side-lobe of the clutter even though they are notably separated in the Doppler dimension. To prevent this problem, one popular solution is the use of a windowing scheme with a weighting function. However, this method leads to a spread spectrum, so the pedestrian with weak signal power and slow Doppler may also be masked by the main-lobe of clutter. With a fast-ramp based FMCW radar, if the target is moving, the complex spectrum of the range- Fast Fourier Transform (FFT) is changed with a constant phase difference over ramps. In contrast, the clutter exhibits constant phase irrespective of the ramps. Based on this fact, in this paper we propose a pedestrian detection for highly cluttered environments using a coherent phase difference method. By detecting the coherent phase difference from the complex spectrum of the range-FFT, we first extract the range profile of the moving pedestrians. Then, through the Doppler FFT, we obtain the 2D range-Doppler map for only the pedestrian. To test the proposed detection scheme, we have developed a real-time data logging system with a 24 GHz FMCW transceiver. In laboratory tests, we verified that the signal processing results from the proposed method were much better than those expected from the conventional 2D FFT-based detection method.

A small and weak target detection method is proposed in this work that outperforms all other methods in terms of real-time capability. It is the first time that two-dimensional (2D) images are processed using only one-dimensional1D structuring elements in a morphology-based approach, enabling the real-time hardware implementation of the whole image processing method. A parallel image readout and processing structure is introduced to achieve an ultra-low latency time on the order of nanoseconds, and a hyper-frame resolution in the time domain can be achieved by combining the row-by-row structure and the electrical rolling shutter technique. Experimental results suggest that the expected target can be successfully detected under various interferences with an accuracy of 0.1 pixels (1σ) under the worst sky night test condition and that a centroiding precision of better than 0.03 pixels (1σ) can be reached for static tests. The real-time detection method with high robustness and accuracy is attractive for application to all types of real-time small target detection systems, such as medical imaging, infrared surveillance, and target measurement and tracking, where an ultra-high processing speed is required.

Dark-and-weak-target simulators are used as ground-based calibration devices to test and calibrate the performance metrics of star sensors. However, these simulators are affected by full-field-of-view energy nonuniformity. This problem impacts the quality of output images and the calibration accuracy of sensors and inhibits further improvements in navigational accuracy. In the study reported in this paper, we sought to analyze the factors which affect full-field-of-view energy uniformity in dark-and-weak-target simulators. These include uneven irradiation in backlight sources, the leakage of light from LCD display panels, and the vignetting of collimating optical systems. We then established an energy transfer model of a dark-and-weak-target simulator based on the propagation of a point light source and proposed a self-adaptive compensation algorithm based on pixel-by-pixel fitting. This algorithm used a sensor to capture the output image of a dark-and-weak-target simulator and iteratively calculated the response error matrix of the simulator. Finally, we validated the feasibility and effectiveness of the compensation algorithm by acquiring images using a self-built test system. The results showed that, after compensating an output image of the dark-and-weak-target simulator, the grayscale standard display function (SDF) of the acquired sensor image was reduced by about 50% overall, so the acquisition image was more accurately compensated, and the desired level of grayscale distribution was obtained. This study provides a reference for improving the quality of output images from dark-and-weak-target simulators, so that the working environments of star sensors may be more realistically simulated, and their detection performance improved.

In the field of target localization, improving direction-of-arrival (DOA) estimation methods for weak targets in the context of strong interference remains a significant challenge. This paper presents a robust DOA estimator for localizing weak signals of interest in an environment with strong interfering sources that improve passive sonar DOA estimation. The presented estimator combines a multiple-measurement-vector orthogonal matching pursuit (MOMP) algorithm and a dimension-reduced matrix filter with deep nulling (DR-MFDN). Strong interfering sources are adaptively suppressed by employing the DR-MFDN, and the beam-space passband robustness is improved. In addition, Gaussian pre-whitening is used to prevent noise colorization. Simulations and experimental results demonstrate that the presented estimator outperforms a conventional estimator based on a dimension-reduced matrix filter with nulling (DR-MFN) and the multiple signal classification algorithm in terms of interference suppression and localization accuracy. Moreover, the presented estimator can effectively handle short snapshots, and it exhibits superior resolution by considering the signal sparsity.

Due to the interaction between floating weak targets and sea clutter in complex marine environments, it is necessary to distinguish targets and sea clutter from different dimensions by designing universal deep learning models. Therefore, in this paper, we introduce the concept of multimodal data fusion from the field of artificial intelligence (AI) to the marine target detection task. Using deep learning methods, a target detection network model based on the multimodal data fusion of radar echoes is proposed. In the paper, according to the characteristics of different modalities data, the temporal LeNet (T-LeNet) network module and time-frequency feature extraction network module are constructed to extract the time domain features, frequency domain features, and time-frequency features from radar sea surface echo signals. To avoid the impact of redundant features between different modalities data on detection performance, a Self-Attention mechanism is introduced to fuse and optimize the features of different dimensions. The experimental results based on the publicly available IPIX radar and CSIR datasets show that the multimodal data fusion of radar echoes can effectively improve the detection performance of marine floating weak targets. The proposed model has a target detection probability of 0.97 when the false alarm probability is 10−3 under the lower signal-to-clutter ratio (SCR) sea state. Compared with the feature-based detector and the detection model based on single-modality data, the new model proposed by us has stronger detection performance and universality under various marine detection environments. Moreover, the transfer learning method is used to train the new model in this paper, which effectively reduces the model training time. This provides the possibility of applying deep learning methods to real-time target detection at sea.