Target Detector Research Articles

Detection of Aerobics Action Based on Convolutional Neural Network.

To further improve the accuracy of aerobics action detection, a method of aerobics action detection based on improving multiscale characteristics is proposed. In this method, based on faster R-CNN and aiming at the problems existing in faster R-CNN, the feature pyramid network (FPN) is used to extract aerobics action image features. So, the low-level semantic information in the images can be extracted, and it can be converted into high-resolution deep-level semantic information. Finally, the target detector is constructed by the above-extracted anchor points so as to realize the detection of aerobics action. The results show that the loss function of the neural network is reduced to 0.2 by using the proposed method, and the accuracy of the proposed method can reach 96.5% compared with other methods, which proves the feasibility of this study.

Dual Position Relationship Transformer for Image Captioning.

Employing feature vectors extracted from the target detector has been shown to be effective in improving the performance of image captioning. However, it is considered that existing framework suffers from the deficiency of insufficient information extraction, such as positional relationships; it is very important to judge the relationship between objects. To fill this gap, we present a dual position relationship transformer (DPR) for image captioning; the architecture improves the image information extraction and description coding steps: it first calculates the relative position (RP) and absolute position (AP) between objects, and integrates the dual position relationship information into self-attention. Specifically, convolutional neural network (CNN) and faster R-CNN are applied to extract image features and target detection, then to calculate the RP and AP of the generated object boxes. The former is expressed in coordinate form, and the latter is calculated by sinusoidal encoding. In addition, to better model the sequence and time relationship in the description, DPR adopts long short-term memory to encode text vector. We conduct extensive experiments on the Microsoft COCO: Common Objects in Context (MSCOCO) image captioning data set that shows that our method achieves superior performance that Consensus-based Image Description Evaluation (CIDEr) increased to 114.6 after training 30 epochs and runs 2 times faster, compared with other competitive methods. The ablation study verifies the effectiveness of our proposed module.

Target Detection in Hyperspectral Imagery Using Atmospheric-Spectral Modeling and Deep Learning

Target detection (TD) in spectral imagery is an evolving analytical perspective with broader application potential. The perceived distinctness of the spectral signatures of the materials of interest is exploited for detecting targets in hyperspectral imagery. Space-time varying atmospheric perturbances on the radiation reaching a remote sensor are major limitations for designing a successful TD framework. Incorporating atmospheric components into a target detection framework is vital for practical applicability. Considered a general approach for flexibility, scalability, and optimal prediction, deep learning (DL) methods are increasingly used in various remote sensing applications. However, their potential for TD is relatively unexplored. Especially, the ability to provide training data sufficient for DL models and maintaining the functional relevance of the sparsely distributed targets in hyperspectral imagery are crucial for TD frameworks. This letter presents a novel method for training of DL architecture, called Deep Spectral Target Detector (DSTD). The proposed method includes a semi-supervised multi-scenario forward radiative transfer modelling (RTM) for the simulation of spectral signatures of various targets as training data suitable for the functional requirements of a typical DL architecture. We implemented the DSTD on a TD application-specific benchmark AVIRIS-NG airborne hyperspectral imagery acquired over a study site near Ooty, India. Compared to state-of-art statistical target detectors, the detection performance of the DSTD is superior to equivalent. Further, RTM-based training yields a robust model, impervious to the atmospheric mismatches between target collection and TD environments, indicating the potential for a similar approach to developing efficient DL-based methods for TD in the future.

Phase-Feature-Based Detection of Small Targets in Sea Clutter

It is known that the challenge for detection of small targets on the sea surface is the low signal-to-clutter ratio (SCR). In particular, for low grazing angles and high sea states, wave shading and sea spikes make the small target detection even more difficult. This letter proposed a novel phase-feature detector of small targets in sea clutter. Three phase features, which correspond to different radar scattering mechanisms between the target and sea surface, are extracted in the phase domain of radar echoes, namely, the number of phase crossing zero points, the maximum value of the phase difference probability density function, and the decorrelation time of the phase difference. A detector with a controllable false alarm rate (FAR) based on phase features is constructed using the fast convex hull learning algorithm. Experimental results on measured databases demonstrate that the proposed phase-feature detector attains better performance than the existing tri-feature detectors.

Bayesian Detection for Radar Targets in Compound-Gaussian Sea Clutter

We consider the detection problem of maritime radar targets in the training-sample-starved and non-Gaussian sea clutter environment. The performance of conventional detectors for radar targets is seriously degraded due to both the starvation of training samples for estimating the clutter covariance matrix and the non-Gaussianity of sea clutter. In this letter, we adopt the inverse Gaussian distribution and the inverse complex Wishart distribution to model the texture and speckle covariance matrix of sea clutter, respectively. Then an adaptive Bayesian detector is developed based on the two-step generalized likelihood ratio test and the maximum posterior estimates of clutter parameters. Finally, the experimental results on simulated and measured data demonstrate the performance superiority of the proposed detector over its competitors, especially when the training samples are starved.

Wald- and Rao-Based Detection for Maritime Radar Targets in Sea Clutter With Lognormal Texture

Non-Gaussian sea clutter causes conventional detectors designed in Gaussian clutter to suffer detection performance degradation, and some nuisance parameters cause the uniformly most powerful test to be unavailable. To improve the detection performance of maritime radar targets, we investigate the design of adaptive detectors in correlated non-Gaussian sea clutter via using suboptimal tests. The non-Gaussian sea clutter is modelled as a product of lognormal-distributed texture and complex Gaussian speckle. Two adaptive radar target detectors are developed by using the suboptimal two-step Wald and Rao tests. Specifically, a non-adaptive detector is derived by the Wald or Rao test when the clutter texture and speckle covariance matrix are assumed to be known in the first step; then the clutter parameters known in the first step are estimated, and the true parameters of the detector obtained in the first step are replaced with the estimated values. Theoretical proof and experimental verification indicate that the two proposed detectors have the constant false alarm property with regard to the clutter speckle covariance matrix and the clutter average power. Numerical results on simulated and measured radar data show that the proposed Rao-based detector outperforms its competitors, and has the stronger robustness to the signal mismatch compared to the proposed Wald-based detector.

Target-to-Anomaly Conversion for Hyperspectral Anomaly Detection

A known target detection assumes that the target to be detected is provided <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a priori</i> , while an anomaly detection is an unknown target detection without any prior knowledge. As a result, the known target detection generally performs search-before-detect detection in an active mode, referred to as active target detection as opposed to anomaly detection which performs throw-before-detect detection in a passive mode, referred to as passive target detection. Accordingly, techniques designed for these two types of detection are completely different. This paper shows that there is indeed a mechanism, called target-to-anomaly conversion which can convert hyperspectral target detection (HTD) to hyperspectral anomaly detection (HAD) via a novel idea, called dummy variable trick (DVT). By virtue of such target-to-anomaly conversion many well-known target detection techniques, such as likelihood ratio test (LRT), constrained energy minimization (CEM) and orthogonal subspace projection (OSP), spectral angle mapper (SAM) and adaptive cosine estimator (ACE) can be converted to their corresponding anomaly detector, referred to as target-to-anomaly conversion-derived anomaly detector (TAC-AD). Since a target detector requires target knowledge while TAC-AD does not, a direct use of RAC-AD is not effective. To make TAC-AD work, a newly developed approach to effective anomaly space (EAS) is implemented in conjunction with TAC-AD so that anomalies can be retained in EAS and interference and noise including background (BKG) can be removed from EAS. The experiments demonstrate that TAC-AD operating in EAS performs better than many existing anomaly detection approaches including model-based methods.

Target Detection With Unconstrained Linear Mixture Model and Hierarchical Denoising Autoencoder in Hyperspectral Imagery.

Hyperspectral imagery with very high spectral resolution provides a new insight for subtle nuances identification of similar substances. However, hyperspectral target detection faces significant challenges of intraclass dissimilarity and interclass similarity due to the unavoidable interference caused by atmosphere, illumination, and sensor noise. In order to effectively alleviate these spectral inconsistencies, this paper proposes a novel target detection method without strict assumptions on data distribution based on an unconstrained linear mixture model and deep learning. Our proposed detector firstly reduces interference via a specifically designed deep-learning-based hierarchical denoising autoencoder, and then carries out accurate detection with a two-step subspace projection, aiming at background suppression and target enhancement. Additionally, to generate representative background and reliable target samples required in the detection procedure, an efficient spatial-spectral unified endmember extraction method has been developed. Performance comparison with several state-of-the-art detection methods and further analysis on four real-world hyperspectral images demonstrate the effectiveness and efficiency of our proposed target detector.

Vehicle Detection Based on Semantic-Context Enhancement for High-Resolution SAR Images in Complex Background

Small-scale target detection (such as vehicles) in complex synthetic aperture radar (SAR) image scenes has always been a pain point for the advanced convolutional neural network (CNN)-based target detectors because of the downsampling operations and the local receptive field characteristics of CNNs. To tackle these limitations, a vehicle detector named SCEDet for the small-scale vehicles in SAR images is proposed to improve the detection performance in this letter. SCEDet mainly consists of two parts: subaperture semantic feature extraction and subaperture semantic-context enhancement (SCE) with SCE module. First, ResNet34 with subaperture decomposition is used to efficiently exploit the latent subaperture semantic features. Then, the SCE module is proposed to balance the multiscale semantic information as well as aggregate the global context information for vehicle detection with a small number of parameters and computation costs. The experimental results on the FARAD dataset (0.1 m <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times0.1$ </tex-math></inline-formula> m, Ka-band) demonstrate that both the detection performance and the speed are much better than other detection methods under the same hardware conditions.

An SAR Target Detector Based on Gradient Harmonized Mechanism and Attention Mechanism

In this letter, a target detector based on gradient harmonized mechanism (GHM) and attention mechanism is proposed to realize synthetic aperture radar (SAR) target detection in complex scenes. Considering the imbalance of positive and negative examples in SAR target detection, we use RefineDet as our backbone network. RefineDet can mitigate this imbalance problem by introducing the idea of two-step classification and regression into the one-stage detector. However, RefineDet only selects a part of examples for training and does not make full use of the information of all examples. Therefore, we apply GHM to the classification loss function of RefineDet, so that the network can make full use of all examples and increase the weights of hard examples adaptively in the loss function to reduce the false alarms and the missing alarms. In addition, to achieve a better detection performance in SAR images with complex scenes, a multiscale feature attention module (MFAM) is embedded into the network. By applying channel and spatial attention mechanisms to the multiscale feature maps, the MFAM can highlight the significant information and suppress the interference caused by clutter. The extensive experimental results based on the measured SAR dataset verify the effectiveness of the proposed method.

SETR-YOLOv5n: A Lightweight Low-Light Lane Curvature Detection Method Based on Fractional-Order Fusion Model

End-to-end automatic driving requires the identification of lane curvature. We proposed a lightweight detection method for the low-light lane curvature based on the Fractional-Order Fusion Model (FFM) to assure real-time performance and increase the reliability of automatic driving in low-light conditions. To begin, the FFM method is introduced to enhance images with low average brightness, fuzzy detail, and a high signal-to-noise ratio. Under low-light conditions, these images cannot clearly express information (such as rainy, snowy, foggy, and other harsh external environments). Then, aiming at the problems of complex network structure, high hardware configuration required for training, and low transmission Frames Per Second (FPS) of real-time detection in the previously proposed YOLOv5, the SETR-C3Block module is proposed. The YOLOv5n is improved by optimizing the configuration of the target detector head and the network’s structure, which solves the problems of low efficiency and redundancy parameters in feature extraction in the network. According to the experimental results on the lane curvature dataset, the mAP@.5:.95 of SETR-YOLOv5n is 87.22%, the transmission FPS of real-time detection is 70.4, and the number of model parameters is only 1.8M. It shows that the SETR-YOLOv5n can meet the lightweight and accuracy requirements of target detection by the mobile terminal or embedded device.

Adaptive Moving Target Detection Without Training Data for FDA-MIMO Radar

This paper deals with the problem of adaptive moving target detection, embedded in homogeneous Gaussian noise with unknown covariance matrix, for frequency diverse array multiple-input multiple-output (FDA-MIMO) radar operating in interference-dominant environment. Unlike traditional adaptive moving target detectors that need training data to estimate the jamming covariance matrix (JCM), we present the Rao and Wald test based adaptive detector, which requires no training data. Furthermore, we proposed a two-stage approach to obtain maximum likelihood estimate (MLE) of the joint range, angle and Doppler, respectively. The corresponding signal-to-jamming-plus-noise ratio (SJNR) is derived to evaluate the FDA-MIMO radar performance. All proposed methods are validated by numerical results, which show that the proposed detector outperforms the existing generalized likelihood ratio test (GLRT).

Dynamic Selection of Optional Feature for Object Detection

To obtain the most intuitive pedestrian target detection results and avoid the impact of motion pose uncertainty on real-time detection, a pedestrian target detection system based on a convolutional neural network was designed. Dynamic Selection of Optional Feature (DSOF) module and a center branch were proposed in this paper, and the target was detected by an anchor-free method. Although almost all the most advanced target detectors use pre-defined anchor boxes to run through the possible positions, scales, and aspect ratios of search targets, their effectualness, and generalization ability are also limited by the anchor boxes. Most anchor-based detectors use heuristically guided anchor frames. Such a design is difficult to detect objects of different types and sizes, especially objects with highly overlapping boundaries. To solve this problem, the DSOF module is proposed in this paper, which selects for each instance the most appropriate feature layer through automatic feature selection. After using multi-level prediction, stacks of low-grade prediction bounding boxes will be generated far away from the target center. To eliminate these low-grade detections, we introduce a new center branch to predict the deviation of a pixel from its corresponding bounding box. This score is used to reduce the weight of the low-grade detection bounding box and merge the detection sequences into the Non-Maximum Suppression (NMS).

YOLO-G: A Lightweight Network Model for Improving the Performance of Military Targets Detection

Military target detection technology is the foundation and key to perceive and analyze the battlefield situation, and it is also the premise of target tracking technology. Aiming at the task of military target detection, the detection performance of traditional detection algorithms is poor in complex environment. We realize automatic detection of military targets in complex environment through deep learning. In this research, we improve the components of YOLOv3 and propose a novel military target detection algorithm (YOLO-G). We have built a military target dataset composed of armed men with different weapons, which provides a test environment for various object detection algorithms. In the YOLOv3 network structure, by introducing the lightweight convolutional neural network GhostNet as the feature extraction network, the accuracy and speed of military target detection are improved. Then, the attention mechanism based on the coordinate attention block is introduced to enhance the representation ability of target features, suppress interference and improve the detection accuracy. Finally, the loss function of the target detector is redesigned by using DIOU loss function and Focal loss function, which further improves the detection accuracy of our detection model for military targets. We tested YOLO-G on the military target dataset. Experimental results show that our method improves the mAP by 2.9% and the detection speed by 25.9 frames/s compared with the original YOLOv3 algorithm, and the size of the proposed model is reduced to 1/6 of that of YOLOv3. In addition, we also compare our method with state-of-the-art object detection algorithms. The results show that YOLO-G also has superior detection performance, and the mAP index obtained by our method is 1.2% higher than that of the latest YOLOv5 on the premise of meeting the application requirements, which plays an important auxiliary role in the generation and analysis of battlefield situation.

Band Sampling of Kernel Constrained Energy Minimization Using Training Samples for Hyperspectral Mixed Pixel Classification

Constrained energy minimization (CEM) has been extended to several generalized versions, iterative CEM (ICEM), Nystrom method-based kernel CEM (NKCEM), and iterative training sampling-based NKCEM (ITS-NKCEM) for hyperspectral image classification (HSIC). Since CEM is a subpixel target detector that specifies a target signature to detect its target abundance fractions present in data samples, this article takes the advantage of CEM’s ability in subpixel detection to consider NKCEM as a nonlinear mixed pixel classifier for hyperspectral mixed pixel classification (HMPC). Recently, a new concept of band sampling (BSam) was proposed by utilizing random signal sampling derived from compressive sensing (CS) to show its performance better than band selection (BSel) for HSIC. Thus, incorporating BSam into NKCEM and ITS-NKCEM yields two new versions for HPMC, called band sampling NKCEM (BSam-NKCEM) and band sampling ITS-NKCEM (BSam-ITS-NKCEM). Interestingly, despite that BSam-ITS-NKCEM uses sampled bands as well as training samples, extensive experiments demonstrate that it can perform better than all other CEM and KCEM versions using full bands and ground truth. Specifically, it also shows that BSam-ITS-NKCEM can do better than spectral–spatial HSIC techniques using BSel.

Semantic Segmentation and Defect Detection of Aerial Insulators of Transmission Lines

Aiming at the problems of low accuracy and poor generalization ability of insulator defect detection in complex aerial images by existing insulator defect detection algorithms, the possibility of using semantic segmentation technology to simplify insulator features in complex images is explored. The semantic segmentation model DeepLabv3 is cascaded with the target detector yolov3 to realize the semantic segmentation of insulators in aerial images and the detection of defects. The experimental results show that the use of the strategy of semantic segmentation and target detection can increase the accuracy of insulator defect detection by 12.58%, which effectively improves the performance of the detection model.

Parallelized Nonlinear Target Detection for Asbestos Identification in Large-Scale Remote Sensing Data

Due to the side effects of asbestos on human health and environments, many countries have banned the use of asbestos-containing materials, but there are still illegal products with asbestos in daily life. In order to investigate the distributions of asbestos to facilitate its removal, this paper studies the feasibility of asbestos identification with HyperSpectral (HS) and panchromatic (PAN) data, taking images captured by the PRISMA and ZY1E 2D satellites over Pavia, Italy as examples. In this work, a pansharpening method with guided filter was used to improve HS image quality in terms of spectral fidelity and spatial details. Then, the possible location of asbestos could be obtained by a nonlinear target detector named BSTD. Considering high computational cost for large-scale remote sensing data processing, we further develop BSTD to its parallelized version (denoted as PBSTD). Given the groundtruth of asbestos over Pavia by the Regional Environmental Protection Agency-ARPA Lombardia, our PBSTD and several popular methods are evaluated from both qualitative and quantitative perspectives, showing that most algorithms could correctly detect large-size asbestos roofs, and the nonlinear PBSTD and MSDinter perform better in small-size asbestos identification than other linear detectors. However, the detection accuracy on small-size asbestos is insufficient in practical applications, which indicates that there are still issues to achieve accurate small-size asbestos identification using coarse-spatial-resolution spaceborne remote sensing.

MmHRV: Contactless Heart Rate Variability Monitoring Using Millimeter-Wave Radio

Heart rate variability (HRV), which measures the fluctuation of heartbeat intervals, has been considered as an important indicator for general health evaluation. To alleviate the user burden and explore the usability for long-term health monitoring, noncontact methods for HRV monitoring have drawn tremendous attention. In this article, we present mmHRV, the first contact-free multiuser HRV monitoring system using commercial millimeter-wave (mmWave) radio. The design of mmHRV consists of two key components. First, we develop a calibration-free target detector to identify each user’s location. Second, a heartbeat signal extractor is devised, which can optimize the decomposition of the phase of the channel information modulated by the chest movement and, thus, estimate the heartbeat signal. The exact time of heartbeats is estimated by finding the peak location of the heartbeat signal while the interbeat intervals (IBIs) can be further derived for evaluating the HRV metrics of each target. We evaluate the system performance and the impact of different settings, including the distance between human and the device, user orientation, incidental angle, and blockage. Experimental results show that mmHRV can measure the HRV accurately with a median IBI estimation error of 28 ms (with respect to 96.16% accuracy). In addition, the root-mean-square error (RMSE) measured in the nonline-of-sight (NLOS) scenarios is 31.71 ms based on the experiments with 11 participants. The performance of the multiuser scenario is slightly degraded compared with the single-user case; however, the median error of the 3-user case is within 52 ms for all three tested locations.

ERF-YOLO: A YOLO algorithm compatible with fewer parameters and higher accuracy

Research shows that theoretical receptive field and effective receptive field are very important to target detection results. The effective receptive field determines the contribution of different positions in the theoretical receptive field. Therefore, the main purpose of this work is to increase the effective receptive field area and reduce the number of parameters. This idea obtains a high-precision and high-speed target detector. First, the algorithm needs to optimize the activation function to improve the efficiency of feature extraction. Second, the model structure needs to select the backbone network and improve the convolutional layer structure. Then, the enhanced network requires increasing the number of the residual structures and the “Concat” to improve feature extraction performance. Finally, the network needs to combine the optimized convolutional layer and the anchor box loss function to improve the performance of the anchor box. The project designed a YOLO algorithm (ERF-YOLO) with a larger effective receptive field. The training and testing of the experiment use PASCAL VOC data set and MS COCO data set respectively. Experimental results show that the parameter of ERF-YOLO is close to half of YOLO v4. In terms of detection accuracy, ERF-YOLO is superior to many current algorithms.

An End-to-End Anti-Jamming Target Detection Method Based on CNN

Target detection in the presence of main-lobe deception jamming has received intensive attention. Generally, traditional target detection with additive jamming can be regarded as an adjacent process of jamming suppression and target detection. Since target information can be lost in jamming suppression, the detection performance can degrade severely. Aiming at this issue, an end-to-end anti-jamming target detector is proposed based on convolutional neural network (CNN) in the presence of interrupted-sampling repeater jamming. The CNN method first converts the single-pulse compression filter into a series of feature extraction filters, accumulating the energy of various features in various dimensions and on multiple scales. Then, a feature fusion filter added after the feature extraction stage is utilized to suppress jamming features while simultaneously retaining the actual target features. The two stages can be achieved in the CNN structure, and all the filters in this method are obtained by training the CNN. Numerical simulations show the efficiency of the proposed method.