Weak moving target detection in space by fusing deep and statistical features from intensity temporal profiles

this paper presents the concept of using the low-frequency array (LOFAR) radio telescope receiver for passive detection of air and space targets using illuminators of opportunity. The LOFAR radio telescope operates in a 110-250 MHz band, thus the focus is on VHF illuminators, such as DAB (digital radio) and DVB-T (digital television). For the detection of air targets, such as aircraft, illuminators of opportunity that are relatively close to the radio telescope are considered. Due to the Earth's surface curvature, the detection of space targets, such as orbital debris, requires the use of transmitters that are far away from the receiver. The paper presents a theoretical study of the detection range for aerial and space targets and preliminary results of the detection of air targets using nearby transmitters.

Space target extraction and detection for wide-field surveillance

Space target detection under the background of stars is one of the key techniques in space based optical measurement. In this paper, we proposed a space target detection algorithm based on star identification. First, the centroid of stars and space target is extracted by FPGA. Then, DSP accomplish space target detection based on the centroid data. Result shows that this method have a good effect on the space target detection.

Long exposure time and wide field can effectively improve the ability of a space surveillance telescope to detect faint space targets. However, complicated situations pose challenges for space target detection. Background star images usually manifest a rotated streak, and target trajectories can be crossed, discontinuous, or nonlinear. This paper presents an accurate and robust space target detection method, namely, spatiotemporal pipeline multistage hypothesis testing (SPMHT), to overcome the issues. Specifically, the method includes the following two stages: First, in the spatiotemporal pipeline filtering step, Spatiotemporal-related Intersection over Union (SrIoU) is used to calculate the IoU score instead of the traditional method. Benefiting from the differences between motion characteristics of targets and stars and the insensitivity of the SrIoU score to the noise, the spatiotemporal pipeline filtering can effectively remove the streak images of background stars and obtain candidate points. Second, a series of candidate points is further organized into a tree structure. We pruned in the tree structure combined with these candidate trajectories by using velocity and direction feature of moving objects. Furthermore, in the search step, fast adaptive sequence region search is used to reduce the computational cost. The experimental results for two datasets, simulated image datasets and real captured image datasets, demonstrate the effectiveness in addressing the difficulties of space target detection in complicated situations.

In bearing fault diagnosis, statistical features and deep representation features reflect the signal characteristics from different perspectives and demonstrate tremendous diagnostic potential. Nevertheless, previous studies have paid little attention to the heterogeneousity between statistical and deep representation features. Besides, directly combining these two kinds of features may also lead to redundancy and conflict, which may negatively affect the diagnostic performance. To address this issue, an enhanced random subspace method with coupled LASSO (RS-CL) is proposed in this paper to jointly optimize statistical and deep representation features. In the feature extraction stage, statistical features are constructed from the time-domain, frequency-domain and time-frequency domain, while deep representation features are extracted by bidirectional long short-term memory. In the model construction stage, an enhanced RS-CL method is developed to generate more efficient and diverse base classifiers. To verify the performance of the proposed RS-CL method, experiments were conducted on a bearing fault diagnosis data set provided by the University of Paderborn. The experimental results verify the effectiveness and feasibility of the proposed method.

People strive to make sense of the complex electroencephalography (EEG) data generated by the brain. This study uses a prepared dataset to examine how easily people with alcohol use disorder (AUD) could be distinguished from healthy people. The signals from each electrode are connected to one another and are first represented as a single signal. The signal is then denoised through variation mode decomposition (VMD) during the preprocessing stage. The statistical and deep feature extraction phases are the two subsequent phases. The crucial step in the suggested strategy is to classify data using a combination of these two unique qualities. Deep and statistical feature performance was evaluated independently. Then, using the eigenvectors created by merging all of the collected features, classification was carried out using our DSFC (Deep - Statistical Features Classification) model. Although the classification accuracy rate using only statistical features was 81.2 percent and the classification accuracy rate using only deep learning was 95.71 percent, the classification accuracy rate utilizing hybrid features created using the suggested DSFC technique was 99.2%. Therefore, it can be proven that combining statistical and deep features can produce beneficial results.

In view of the fact that the technology of polarization detection performs better at identifying targets through clouds and fog, the recognition ability of the space target detection system under haze conditions will be improved by applying the technology. However, due to the low ambient brightness and limited target radiation information during space target detection, the polarization information of space target is seriously lost, and the advantages of polarization detection technology in identifying targets through clouds and fog cannot be effectively exerted under the condition of haze detection. In order to solve the above problem, a dehazing enhancement strategy specifically applied to polarization images of space targets is proposed. Firstly, a hybrid multi-channel interpolation method based on regional correlation analysis is proposed to improve the calculation accuracy of polarization information during preprocessing. Secondly, an image processing method based on full polarization information inversion is proposed to obtain the degree of polarization of the image after inversion and the intensity of the image after dehazing. Finally, the image fusion method based on discrete cosine transform is used to obtain the dehazing polarization fusion enhancement image. The effectiveness of the proposed image processing strategy is verified by carrying out simulated and real space target detection experiments. Compared with other methods, by using the proposed image processing strategy, the quality of the polarization images of space targets obtained under the haze condition is significantly improved. Our research results have important practical implications for promoting the wide application of polarization detection technology in the field of space target detection.

Intelligent motor fault diagnosis in industrial applications requires identifying key characteristics to differentiate various fault types effectively. Solely relying on statistical features cannot guarantee high classification accuracy, while complex feature extraction techniques can pose challenges for industry practitioners. Conversely, advanced feature extraction may not ensure that the model effectively learns these features for classification. A feature fusion approach that combines statistical and deep learning features to address these challenges is proposed. Since statistical features form the foundation for general feature extraction, statistical and deep learning features are combined using Extreme Gradient Boosting (XGBoost) algorithm with Particle Swarm Optimization (PSO). The PSO algorithm automates parameter tuning for XGBoost. A deep neural network (DNN) adaptively extracts hidden features, improving bearing fault classification precision using t‐SNE representation. Results successfully prove the DNN's ability to classify diverse motor faults using deep learning features. Thus, integrating statistical features with XGBoost further enhances DNN's performance. To ensure robustness, the proposed method has been compared with different motor fault classification methods and validated across different motor fault datasets, showcasing improved classification accuracy and robust performance, even amidst varying noise levels. This approach represents a promising advancement in intelligent fault diagnosis within industrial contexts.

A wide-field surveillance system with a long exposure time has a stronger detection capability for faint space targets. However, some of the complexities it generates also pose difficulties for space target detection; a large amount of image data, numberless object points, some stars manifesting as streak-like sources, and possible discontinuous or nonlinear target trajectories. This paper presents a high precision and low computational-cost space target detection method to overcome these obstacles. Firstly, the minimum external rectangle method is implemented to effectively remove stars and noise. Secondly, the motion velocity of the targets is calculated as the basis for predicting the allowed state transition region in each image of the frame set. Finally, a dynamic programming sliding window method is proposed to detect space targets with continuous, discontinuous, linear or nonlinear trajectories. The experimental results show that this method can effectively detect faint space targets in wide-field surveillance under a long exposure time. This method also has the advantage of a low computational cost.

A mathematical model of space target illumination characteristics is established based on the basic theory of radiation by considering geometry, background, and material characteristics of the space target. Using the model, the spatial distribution of scattering light intensity from the space target is calculated with the modeling and blanking technique of target when being illuminated by the sun. The relations of specular reflection with the position, geometry, materials and other attributes of the space target are analyzed. Furthermore, the effect of specular reflection on space target detecting is discussed. A method of characteristic simulation of space target is presented. The simulation result indicates that polyhedral structure, mirror surface, or solar sail is easy to cause specular reflection. It shows the effect of specular reflection is helpful for space target detection and identification.

Deep space exploration is one of the hot techniques currently. The small and dim point target detection is one of the key technologies for space surveillance. In order to detect the small and dim point target without background compensation, we proposed a new method to realize the target detection in the feature space which we special designed. This method makes the centroid location to denote each of all the stars and targets separately, when the reference stars are chosen, the images could be mapping in the feature space which gets from the changing distance from all stars and potential targets to the reference stars, then the stars and potential targets can be divided by comparability measurement function with different motion characteristics, finally by trajectory conjunction the target detection be realized. The method we present here can be widely used in the visible light space surveillance system and infrared systems, and employed not only ground based surveillance system but also space based surveillance systems, which can also play an important role in space debris surveillance. The experimental result shown that the algorithm can fully take into account the characteristics of the fixed star, dim point moving target and noise, and can be effective to detect the moving dim and small in moving background with low SNR.

Two phenomena that degrade the performance of ground moving target detection (GMTI) capabilities of space based radars (SBR) are (i) range foldover effects associated with multiple data points originating from different range bins due to the radar pulse stream and (ii) Earth's rotational effect on clutter Doppler frequency. The degradation in performance due to these phenomena is quantified in this paper and methods to minimize their effect are discussed. In this context, transmit pulsing schemes involving waveform diversity is proposed for improved target detection capabilities

Terahertz wave has recently become a promising technology in detection and tracking of space targets, such as missiles and debris, where higher detection performance are required. In this paper, the advantages of terahertz radar applied in space targets detection are firstly exploited over the microwave-band radar. Although simulation results of micro-Doppler effect and SAR imaging have shown the advantages of terahertz wave in target detections, the narrow beam-width of terahertz wave also limits the application of target searching in vast area. This disadvantage, however, can be overcome by radar netting technology, which can make full use of detection resource by combing multi-radars in different locations, different types and different frequencies together. Therefore, we present a scheme of cooperative space targets detection based on terahertz and traditional microwave radars. Simulation results have demonstrated the usefulness of terahertz technology in space targets detection.

Polarization detection of space targets is one of the most important research directions in the field of space target recognition. In view of the fact that there are problems such as strong background noise and inconspicuous details of contour features in the polarization image of space targets, an image denoising and enhancement strategy is proposed. To solve the problem of high intensity of Gaussian noise in degree of polarization (DoP) images, a denoising method named adaptive noise template prediction (ANTP) is proposed to eliminate the noise. Compared to the existing methods, the ANTP algorithm performs better at reducing noise and improving image quality. Aiming at the difficulty of separating the background noise from angle of polarization (AoP) images, a denoising method named gray analysis of local area (GALA) is proposed. Compared to traditional methods, the GALA algorithm can effectively extract the contour features of targets and improve the contrast of AoP images. An image fusion method based on discrete cosine transform and local spatial frequency (LSF) is used to fuse the denoised DoP image and AoP image. The experimental results of the simulated and real space target polarization detection confirm the effectiveness of our proposed strategy.

Semi-random subspace with Bi-GRU: Fusing statistical and deep representation features for bearing fault diagnosis