Search

The success of deep learning in synthetic aperture radar (SAR) automatic target recognition (ATR) relies on a large number of labeled samples, however, there are often wrong (noisy) labels in a large-scale dataset. In this paper, we propose a loss curve fitting-based method, which can identify the noisy labels and train the classification network effectively. We propose to model label noise by unsupervised clustering via fitting loss curve to identify whether the sample’s label is clean or noisy. Then, we train the network using augmented samples with clean labels to correct noisy labels further. The experiments on the MSTAR dataset prove that our proposed method can deal with the situation when training a network with different ratios of noisy labels, and correct noisy labels effectively. When the noise ratio is small (40%) in the training dataset, our method can correct 97.9% of noisy labels and train the classification network with 98.8% classification accuracy. While the noise ratio is large (80%), our method can correct 78.1% of noisy labels and train the classification network with 79.6% classification accuracy.

This paper deals with the real-time recognition from multiple spatial angles of concealed human motions with ultra wide band (UWB) through-the-wall radar (TWR). To conquer the performance loss incurred by diverse human motion in a single view, a multi-view real-time human motion recognition model based on ensemble learning is proposed. Specifically, we first proposes a multi-view human motion recognition model based on Stacking parallel ensemble learning algorithm, which is used to realize the real-time human motion recognition based on UWB TWR. Secondly, in order to address the irrationality of the existing accuracy evaluation criteria to evaluate the real-time motion recognition algorithm, a real-time model evaluation criterion based on normalized harmonic weighted intersection over union (NHW-IOU) is proposed. Finally, the collected multi-view human motion data are used to verify the effectiveness of the proposed algorithm. The actual measurement results show that the average recognition performance of the proposed Stacking model has improved by 14.76% compared with the single-view model, which is of great significance for using multi-view data to improve network performance. Moreover, compared with the bi-directional long short-term memory (Bi-LSTM) and Gated Recurrent Unit (GRU) models, the proposed model has better performance in accuracy and time delay.

In synthetic aperture radar (SAR) automatic target recognition, it is expensive and time-consuming to annotate the targets. Thus, training a network with a few labeled data and plenty of unlabeled data attracts attention of many researchers. In this article, we design a semisupervised learning framework including self-consistent augmentation rule, mixup-based mixture, and weighted loss, which allows a classification network to utilize unlabeled data during training and ultimately alleviates the demand of labeled data. The proposed self-consistent augmentation rule forces the samples before and after augmentation to share the same labels to utilize the unlabeled data, which can ensure the prominent effect of supervised learning part of the framework for training by balancing amounts of labeled and unlabeled samples in a minibatch, and makes the network achieve better performance. Then, a mixture method is introduced to mix the labeled, unlabeled, and augmented samples for the better involvement of label information in the mixed samples. By using cross-entropy loss for the mixed-labeled mixtures and mean-squared error loss for the mixed-unlabeled mixtures, the total loss is defined as the weighted sum of them. The experiments on the MSTAR data set and OpenSARShip data set show that the performance of the method is not only far better than the state of the art among current semisupervised-based classifiers but also near to the state of the art among the supervised learning-based networks.

Automatically detecting dangerous concealed objects in the millimeter-wave images is important for imaging-aided security systems. In this paper, we proposed a normalized accumulation map-based training mechanism for concealed object detection network. The proposed normalized accumulation map, calculated as the average of binary masks representing the object location for each image, can reveal the positions of frequently-appeared concealed objects, which offers different weights for different locations when computing confidence loss. Experiments on a millimeter-wave security image dataset demonstrate the effectiveness of our proposed normalized accumulation map-based training mechanism. By introducing our training mechanism to YOLO-v2, the object detection network can achieve a 4.43% performance improvement in mean average precision.

Clustering, a class of unsupervised learning methods, has been extensively studied and applied in machine learning. By designing the training process, we are able to impose the CNN with the ability of clustering. In this paper, we propose a binary clustering framework by implementing the deep network in the clustering process, instead of barely acting as a feature extractor. The proposed training strategy consists of five stages: feature elimination, feature seeding, feature germination, feature growing and feature grafting. Feature elimination works to eliminate the impact of random weights initialization and leave the network unbiased. Feature seeding, feature germination and feature growing altogether realize similarity generation, while feature grafting filters and strengthens the generated similarity. Because of the uncertainty of clustering, we take genres into consideration as evaluation metrics. Only performance analysis is considered while the first and the second samples selected during feature training belong to different genres. Compared with DEC and DEC-DA, our proposed training strategy is shown to achieve the state-of-the-art performance, with clustering accuracy of up to 0.996 for dataset fashion MNIST 4/5 -full and outperforms other methods in terms of stability.

For the reason of target multipaths ambiguities, localization for hidden moving target due to lack of line of sight (LOS) path in urban environments is a hard task. To handle this problem we propose a localization algorithm based on the internal connection of these multipaths in this paper. First, we establish an electromagnetic (EM) propagation model based on the characters of the measured signal received by an L-band single-input single-output (SISO) ultra-wideband (UWB) radar. After that, the model-based target localization algorithm is proposed based on a times-of-arrival (TOAs) association method, which is able to match the measured TOAs with the corresponding EM propagation paths correctly. The proposed method can cope with the case while some missing detections of TOAs happen. Simulation and experimental results ultimately validate the robustness and the state-of-the-art performance of the proposed algorithm.

Motivated by the intrinsic dynamics of physical motion as well as establishment of target motion model, this article addresses the problem of human motion recognition with ultra wide band (UWB) through-the-wall radar (TWR) in a novel view of range profile serialization. Specifically, we first convert the original radar echoes into range profiles. Then, an auto-encoder network (AEN) with three dense layers is adopted to reduce the dimension and extract the features of each range profile. After that, a gated recurrent unit (GRU) network with two hidden layers is employed to deal with the features of each time-range slice and output the recognition results at each slice in real time. Finally, experimental data with respect to four different behind-wall human motions is collected by self-developed UWB TWR to validate the effectiveness of the proposed model. The results show that the proposed model can validly recognize the human motion serialization and achieve 93% recognition accuracy within the initial 20% duration of the activities (the average durations are 4s, 5.5s, 3s and 4.5s), which is of great significance for real-time human motion recognition.

In the problem of geospatial object detection, the quality and amount of reference boxes significantly impact the detection performance and prediction speed of object detection networks. Nowadays, most of the popular detection methods adopt the anchor mechanism to generate reference boxes. This paper proposed an anchor-free and sliding-window-free deconvolutional region proposal network and constructed a two-stage deconvolutional object detection network. Instead of using an anchor mechanism, we proposed to use a deconvolutional neural network followed by a connected region generation module to generate reference boxes. The comparison experiments and quantitative analysis with NWPU VHR-10 dataset demonstrate that DeRPN can vastly reduce the number of reference boxes and improve the precision of the reference box coordinates. The experiments also suggest that our proposed two-stage object detection network can not only obtain the nearly state-of-the-art detection results but also achieve the prediction speed close to that of the one-stage detection network.

The recoverability for peripheral nerve lesions with a long segment defect is much challenging. Conventional methods for sciatic nerve repair excepted for autografts are bridged with nerve guidance conduit (NGC). Herein, the chitin-based NGC (ChT NGC) is firstly reported by facile dissolution, molding and regeneration process, performed excellent nerve regeneration and neuroma inhibition after deposited with anti-inflammatory polydopamine (ChT-PDA NGC). In 10 mm sciatic nerve defect rat model, the restorative effects of ChT-PDA NGC groups are similar to autografts. That is mainly ascribed to the high activity of Schwann cells and claimed by immunofluorescence staining and Western blot analysis. Interestingly, ChT-PDA NGC presents outstanding neuroma inhibition during the nerve regeneration as for the anti-inflammatory activity of PDA. This work provides a facile and novel approach to prepare hollow chitin hydrogel tube, which presents well nerve regeneration and neuroma inhibition, improving the potential high-value application of chitin in biomedical fields.

Convolutional neural network (CNN) has become the mainstream method in the field of image recognition for its excellent ability to feature extraction. Most of the CNNs increase the classification accuracy for the rotational objects by imposing the network with rotation invariance or equivariance property, which causes the loss of the target's orientation information. In this work, a rotation-mapping network (RM-Net) that can achieve objects recognition and angle or orientation estimation simultaneously without additional network training is constructed. Besides, an octagona convolutional kernel is introduced to improve the network's performance. The experiments on the simulation SAR datasets show that the proposed RM-CNN can achieve state-of-the-art results in target recognition and angle estimation.

The nerve guidance conduit (NGC) is a promising clinical strategy for regenerating the critical-sized peripheral nerve injury. In this study, the polysaccharide chitin is used to fabricate the hydrogel film for inducing the impaired sciatic nerve regeneration through incorporating the conductive poly(3,4-ethylenedioxythiophene) nanoparticles (PEDOT NPs) and modifying with cell adhesive tetrapeptide Cys-Arg-Gly-Asp (CRGD) (ChT-PEDOT-p). The partial deacetylation process of chitin for exposing the amino groups is performed to (i) improve the electrostatic interaction between chitin and the negatively charged PEDOT for enhancing the composite hydrogel strength and (ii) offer the active sites for peptide modification. The as-prepared hydrogel remarkably promotes the in vitro RSC-96 cell adhesion and proliferation, as well as the Schwann cell activity-related gene S100, NF-200, and myelin basic protein (MBP) expression. Function of gastrocnemius muscle and thickness of myelinated axon in chitin/PEDOT groups are analogous to the autograft in 10 mm rat sciatic nerve defect. Immunofluorescence, immunohistochemistry, western blotting, and toluidine blue staining analyses on the regenerated sciatic nerve explain that the attachment and proliferation enhancement of Schwann cells and angiogenesis are the vital factors for the chitin/PEDOT composite to facilitate the nerve regeneration. This work provides an applicable chitin-based NGC material for accelerating the peripheral nerve restoration.

Convolutional neural network (CNN) has become the mainstream method in the field of image recognition for its excellent ability to feature extraction. Most of the CNNs increase the classification accuracy for the rotational objects by imposing the network with rotation invariance or equivariance property, which causes the loss of the targets orientation information. This paper attempts to achieve objects recognition and angle or orientation estimation simultaneously without additional network training. To this end, we propose the matching criterion and the kernel-mapping convolutional neural network (KM-CNN). It has been shown that when the kernel satisfies the matching criterion, the output remains the same. Based on this study, we apply rotation transformation to the KM-CNN. Besides, the KM-CNN with the rotation by shifting pixel method and octagonal convolutional kernels can solve the mismatching problem caused by the rotations. The KM-CNN with the kernel sharing central weights gives the near state-of-art results in target recognition and angle estimation on benchmark datasets MNIST, GTSRB and Caltech-256.

Background Reconstruction of chronic lower extremity wounds remains challenging. These wounds are mainly associated with diabetes mellitus, infections, and osteomyelitis. Although several reconstructive techniques are available, the peroneal artery perforator flap has unique advantages. Methods In this study, we discuss our experiences with peroneal artery perforator flaps in 55 patients who had suffered from chronic lower limb wounds. The size of the defect, comorbidities, etiology, flap size, and complications were recorded and analyzed based on a retrospective chart review. Results All 55 flaps survived. In two cases, small superficial necrosis occurred, one of which healed with conservative treatment and the other was reconstructed with split thickness skin grafts. Partial necrosis was observed in nine cases, seven of which were covered with split thickness skin grafts and the remaining two sutured directly after adequate debridement. Vascular compromise was observed in one patient, which was salvaged successfully by performing an exploratory procedure and releasing a few sutures. No complications were seen in the remaining 44 cases. Conclusion The peroneal artery perforator flap is a reliable option for reconstruction of chronic lower extremity wounds.

SAR automatic object classification plays an important role in many SAR-based applications. Currently, the research about SAR automatic object classification focuses on supervised learning, which needs a large amount of annotated data for training the network. We find that clustering can achieve object classification based on unsupervised learning. Considering time consumption and expensive cost of manual labeling, unsupervised learning method has a prominent advantage since it does not need manually annotated data. In this paper, we introduce an unsupervised learning method to achieve SAR object classification with no labeled data. The introduced method models object clustering as a recurrent process, in which data samples are gradually clustered together according to their similarity, and feature representation of them is obtained simultaneously. The experiments on MSTAR dataset and quantitative analysis demonstrate the effectiveness of the introduced method.

Deep learning networks are widely being applied to remote sensing image recognition and have achieved promising results. In this paper, we researched the influence of background with different scattering characteristics for synthetic aperture radar (SAR) target recognition based on convolutional neural network (CNN). Firstly, a two-parameter CFAR image segmentation method based on Weibull distribution was used to extracted SAR target and its shadow. And then, SAR datasets with road, farmland and grassland background environment is synthesized to analyze the CNN classifier. Experiments results show that the method by mixing training sets with different background together can improve the recognization rate when the backgrounds are complex.

Due to finite of information dimension of single bistatic synthetic aperture radar (SAR), to expand more information about ground objects we research multistatic SAR which can be decomposed into groups of bistatic SAR. It is known that scattering properties of the different viewing angles is different. In this paper, we focus on system of single transmitter and triple receivers and use polar format algorithm(PFA) to obtain images of ground objects for the triple receivers. A geometric distortion correction method is proposed due to elevation of ground objects. After the distortion correction, the three SAR images are registrated, then we put images into red, green, blue(RGB) channels respectively to realize fake color synthesis, and thus realize information fusion.

For the existence of speckles, many standard optical image processing methods, such as classification, segmentation, and registration, are restricted to synthetic aperture radar (SAR) images. In this work, an end-to-end deep multi-scale recurrent network (MSR-net) for SAR image despeckling is proposed. The multi-scale recurrent and weights sharing strategies are introduced to increase network capacity without multiplying the number of weights parameters. A convolutional long short-term memory (convLSTM) unit is embedded to capture useful information and helps with despeckling across scales. Meanwhile, the sub-pixel unit is utilized to improve the network efficiency. Besides, two criteria, edge feature keep ratio (EFKR) and feature point keep ratio (FPKR), are proposed to evaluate the performance of despeckling capacity for SAR, which can assess the retention ability of the despeckling algorithm to edge and feature information more effectively. Experimental results show that our proposed network can remove speckle noise while preserving the edge and texture information of images with low computational costs, especially in the low signal noise ratio scenarios. The peak signal to noise ratio (PSNR) of MSR-net can outperform traditional despeckling methods SAR-BM3D (Block-Matching and 3D filtering) by more than 2 dB for the simulated image. Furthermore, the adaptability of optical image processing methods to real SAR images can be enhanced after despeckling.