Editor's Note
Guest Editor
Article List
2024, 22(2):105-113.
DOI: 10.11805/TKYDA2022166
Abstract:
To solve the problem of adaptive detection for distributed targets in partially homogeneous environment with outliers and limited samples, a class of adaptive detectors are designed based on geometric median in this paper. The first step is to construct a data selector based on geometric median generalized inner product and eliminate sample data containing outliers. The second step is to construct detection statistics of the generalized adaptive subspace detector using covariance matrix estimators, which are based on geometric median. The detectors utilize geometric median of the positive definite matrix space without any knowledge of prior probability distribution of sample data. The performance of the proposed two-step detectors is evaluated in terms of the probabilities of correct outliers excision, false alarm, and detection. Experiment results based on simulated and real data show that the proposed approach has better detection performance than the existing ones based on traditional covariance estimator.
To solve the problem of adaptive detection for distributed targets in partially homogeneous environment with outliers and limited samples, a class of adaptive detectors are designed based on geometric median in this paper. The first step is to construct a data selector based on geometric median generalized inner product and eliminate sample data containing outliers. The second step is to construct detection statistics of the generalized adaptive subspace detector using covariance matrix estimators, which are based on geometric median. The detectors utilize geometric median of the positive definite matrix space without any knowledge of prior probability distribution of sample data. The performance of the proposed two-step detectors is evaluated in terms of the probabilities of correct outliers excision, false alarm, and detection. Experiment results based on simulated and real data show that the proposed approach has better detection performance than the existing ones based on traditional covariance estimator.
2024, 22(2):114-121.
DOI: 10.11805/TKYDA2024027
Abstract:
To investigate the application of RF system level chip—Radio Frequency System-on-Chip(RFSoC) in pulse radar system, a radar ranging system with high performance digital-analog hybrid signal processing capability is designed. The high-performance RFSoC development board—IW-RFSoC-49DR(including the design of the background interference filtering algorithm) is adopted, and the test environment is set in a laboratory with narrow space and disturbed multimetallic equipments. The results of the experiments show that the experimental data are significantly disturbed in an untreated, complex indoor environment; after implementing the background interference filtering algorithm, the display resolution of the frequency spectrum map has been significantly improved. As the test target distance increases from 3 m to 12 m, the ranging error decreases from 53 cm to 5 cm. RFSoC technology shows significant advantages in the design of pulsed radar system, realizing the high integration and low power consumption design, and laying a foundation for the subsequent design of portable radar based on RFSoC.
To investigate the application of RF system level chip—Radio Frequency System-on-Chip(RFSoC) in pulse radar system, a radar ranging system with high performance digital-analog hybrid signal processing capability is designed. The high-performance RFSoC development board—IW-RFSoC-49DR(including the design of the background interference filtering algorithm) is adopted, and the test environment is set in a laboratory with narrow space and disturbed multimetallic equipments. The results of the experiments show that the experimental data are significantly disturbed in an untreated, complex indoor environment; after implementing the background interference filtering algorithm, the display resolution of the frequency spectrum map has been significantly improved. As the test target distance increases from 3 m to 12 m, the ranging error decreases from 53 cm to 5 cm. RFSoC technology shows significant advantages in the design of pulsed radar system, realizing the high integration and low power consumption design, and laying a foundation for the subsequent design of portable radar based on RFSoC.
2024, 22(2):122-131.
DOI: 10.11805/TKYDA2023061
Abstract:
The tracking accuracy of conventional Adaptive Interactive Multiple Model(AIMM) algorithm is poor in the process of maneuvering target tracking by passive radar. In combination with the characteristics of passive radar,the improved Adaptive Transition Probability Matrix-Interactive Multiple Model(ATPM-IMM) algorithm is proposed. Based on the ATPM-IMM algorithm, this algorithm uses the adaptive control window to revise the transition probability matrix again. It can automatically switch the maneuvering model according to the maneuvering situation of the target and improve the matching probability of real model. Simulation and experimental results show that the proposed algorithm can effectively improve the tracking accuracy of passive radar to maneuvering targets.
The tracking accuracy of conventional Adaptive Interactive Multiple Model(AIMM) algorithm is poor in the process of maneuvering target tracking by passive radar. In combination with the characteristics of passive radar,the improved Adaptive Transition Probability Matrix-Interactive Multiple Model(ATPM-IMM) algorithm is proposed. Based on the ATPM-IMM algorithm, this algorithm uses the adaptive control window to revise the transition probability matrix again. It can automatically switch the maneuvering model according to the maneuvering situation of the target and improve the matching probability of real model. Simulation and experimental results show that the proposed algorithm can effectively improve the tracking accuracy of passive radar to maneuvering targets.
2024, 22(2):132-141.
DOI: 10.11805/TKYDA2023170
Abstract:
Non-cooperative bistatic radar has a low signal-to-noise ratio in the echo due to its special detection method. In particular, the detection between frames in the radar scanning cycle for maritime moving targets is not stable, which will bring great difficulties for subsequent target tracking. The low threshold Constant False Alarm Rate(CFAR) detector is employed to match the detection results of radar range-Doppler dimension and range-azimuth dimension to obtain the corresponding mask map, and the potential moving targets are found. Then, a Double Backbone-YOLO(DB-YOLO) that fuses multi-dimensional feature information is proposed. The network adopts a dual-trunk structure, extracts the features of the moving target mask map and the same-scale P-display map under its mapping, and uses a deep separable convolution module to reduce the model parameters of the network. Finally, the comparison experiments with Faster RCNN, YOLOv5 and its common variant YOLOv5-ConvNeXt show that DB-YOLO effectively improves the target detection performance and ensures the inference speed, which lays a foundation for target tracking of noncooperative bistatic radar.
Non-cooperative bistatic radar has a low signal-to-noise ratio in the echo due to its special detection method. In particular, the detection between frames in the radar scanning cycle for maritime moving targets is not stable, which will bring great difficulties for subsequent target tracking. The low threshold Constant False Alarm Rate(CFAR) detector is employed to match the detection results of radar range-Doppler dimension and range-azimuth dimension to obtain the corresponding mask map, and the potential moving targets are found. Then, a Double Backbone-YOLO(DB-YOLO) that fuses multi-dimensional feature information is proposed. The network adopts a dual-trunk structure, extracts the features of the moving target mask map and the same-scale P-display map under its mapping, and uses a deep separable convolution module to reduce the model parameters of the network. Finally, the comparison experiments with Faster RCNN, YOLOv5 and its common variant YOLOv5-ConvNeXt show that DB-YOLO effectively improves the target detection performance and ensures the inference speed, which lays a foundation for target tracking of noncooperative bistatic radar.
2024, 22(2):142-151.
DOI: 10.11805/TKYDA2023181
Abstract:
To tackle with the problem of decreased recognition accuracy caused by imbalanced individual data distribution in Specific Emitter Identification(SEI), a dynamic weight model based methodis proposed for individual identification of radiation sources. A Dynamic Class Weight(DCW) model is built. A moderate initial weight value is obtained by using a meta learning algorithm through two-layer calculation with a small amount of sample data. Then, a new cost sensitive loss function is designed to calculate the backward adjustment of the distance between the predicted value and the true value, which gives the minority learning weight, and moderately increases the attention to the minority data. It is more friendly to the minority. It has obvious advantages in the processing of highly unbalanced data, which alleviates the calculation misleading of the majority of samples in the whole recognition process, thus improving the overall recognition accuracy.
To tackle with the problem of decreased recognition accuracy caused by imbalanced individual data distribution in Specific Emitter Identification(SEI), a dynamic weight model based methodis proposed for individual identification of radiation sources. A Dynamic Class Weight(DCW) model is built. A moderate initial weight value is obtained by using a meta learning algorithm through two-layer calculation with a small amount of sample data. Then, a new cost sensitive loss function is designed to calculate the backward adjustment of the distance between the predicted value and the true value, which gives the minority learning weight, and moderately increases the attention to the minority data. It is more friendly to the minority. It has obvious advantages in the processing of highly unbalanced data, which alleviates the calculation misleading of the majority of samples in the whole recognition process, thus improving the overall recognition accuracy.
2024, 22(2):152-159.
DOI: 10.11805/TKYDA2023059
Abstract:
The background noise in the echo spectrum of High Frequency Surface Wave Radar(HFSWR) is complex, the clutter accounts for a small proportion and the ionospheric clutter has different forms and positions, therefore, it is difficult to automatically recognize the clutters. Based on DeeplabV3+ deep learning algorithm, an automatic identification method of ionospheric clutter and sea clutter is proposed for HFSWR. Selecting the lightweight MobileNetV2 backbone feature network, adding the channel attention mechanism module SENet, the focused learning of clutter labels is realized, and the loss weight of various labels in the training set is optimized. The model pre-training transfer method is employed to pre-train the network to tackle with the problem of too small sample space. The experimental results on the measured data set show that the proposed method can realize the automatic recognition of ionospheric clutter and sea clutter in HFSWR, and can obtain more accurate and finer clutter recognition results than the original DeeplabV3+ algorithm. The mean Intersection over Union(mIoU) and Accuracy(ACC) of sea clutter recognition results are increased by 2.9% and 5.1% respectively, and the mIoU and ACC of ionospheric clutter recognition results are increased by 3.0% and 4.9% respectively.
The background noise in the echo spectrum of High Frequency Surface Wave Radar(HFSWR) is complex, the clutter accounts for a small proportion and the ionospheric clutter has different forms and positions, therefore, it is difficult to automatically recognize the clutters. Based on DeeplabV3+ deep learning algorithm, an automatic identification method of ionospheric clutter and sea clutter is proposed for HFSWR. Selecting the lightweight MobileNetV2 backbone feature network, adding the channel attention mechanism module SENet, the focused learning of clutter labels is realized, and the loss weight of various labels in the training set is optimized. The model pre-training transfer method is employed to pre-train the network to tackle with the problem of too small sample space. The experimental results on the measured data set show that the proposed method can realize the automatic recognition of ionospheric clutter and sea clutter in HFSWR, and can obtain more accurate and finer clutter recognition results than the original DeeplabV3+ algorithm. The mean Intersection over Union(mIoU) and Accuracy(ACC) of sea clutter recognition results are increased by 2.9% and 5.1% respectively, and the mIoU and ACC of ionospheric clutter recognition results are increased by 3.0% and 4.9% respectively.
