Problem Of Target Recognition Research Articles

A Nuclear detection method Based on improved You Only Look Once v5s Framework

Extracting human cell smear samples through automated scanners, using target detection algorithm to detect its nucleus is an important content in cell detection. Due to the different shapes, different sizes and complex backgrounds of nuclei in the samples, automatic detection of nuclei is a challenging task. In order to solve the problem of complex small target recognition in nuclear detection and improve detection accuracy, based on the YOLOV5S framework of one-stage target detection, make certain improvement, add new residual module to the original network Neck layer, at the same time carry on network widening operation to the subsequent framework. The algorithm visualizes the results of training and testing through Tensorboard. Experimental results show that the accuracy of the improved YOLOV5S network is 1.6% and 4.4% higher than that of the original YOLOV5S network and YOLOV3 network. the improved network has strong real-time performance and high accuracy, which can meet the actual use requirements.

Research on YOLOv3 target detection model in the field of remote sensing

The target recognition problem of high-resolution remote sensing images is marine traffic monitoring, disaster reduction emergency search and rescue, unmanned autonomous systems (UAS) (such as unmanned aerial vehicles, unmanned vehicles, unmanned submersibles, unmanned surface craft and other autonomous robots) and other civilian applications. The core technology of the system is also the key technology of military automatic target recognition (ATR) systems such as military reconnaissance, precision guidance, and maritime monitoring. With the development of high-resolution earth observation systems, more and more industrial applications require the extraction of more valuable target details from high-resolution remote sensing images. Then, due to the complex background of high-resolution remote sensing images and the difference in image quality (factors such as size, resolution, noise, etc.), low target detection accuracy and slow speed are the main bottlenecks that affect the combination of artificial intelligence and remote sensing. In order to solve the technical bottleneck of target detection, this paper focuses on exploring the detection performance of the channel attention module SElayer and YOLOv3 model in the field of high-resolution remote sensing images, providing basic technical support for related research.

Identification of Class number of ship radiated noise based on RK-Means algorithm

Ship radiated noise recognition is one of the basic problems in underwater target recognition. To identify the number of ship types according to ship noise, the ship scale can be predicted in advance and the next step of processing can be carried out. Aiming at the problem of identifying the number of ship types based on ship radiated noise, a RK-Means (Recurrent K-Means) is proposed in this paper. According to the short-time energy characteristics of the target signal, the dimension of the feature data is reduced by principal component analysis; The K-Means algorithm is used to cluster and identify the dimension-reduced signals through cyclic iteration; A single connection algorithm is used to determine the appropriate clustering center, which reduces the similarity value of data objects between classes and makes the difference value between classes large. Furthermore, the algorithm can automatically determine the K value, which is the number of ship types. Verified by the experimental data, compared with the contrast algorithm, the K-value recognition result and clustering effect of the RK-Means clustering algorithm are better.

Combination of Joint Representation and Adaptive Weighting for Multiple Features with Application to SAR Target Recognition

For the synthetic aperture radar (SAR) target recognition problem, a method combining multifeature joint classification and adaptive weighting is proposed with innovations in fusion strategies. Zernike moments, nonnegative matrix factorization (NMF), and monogenic signal are employed as the feature extraction algorithms to describe the characteristics of original SAR images with three corresponding feature vectors. Based on the joint sparse representation model, the three types of features are jointly represented. For the reconstruction error vectors from different features, an adaptive weighting algorithm is used for decision fusion. That is, the weights are adaptively obtained under the framework of linear fusion to achieve a good fusion result. Finally, the target label is determined according to the fused error vector. Experiments are conducted on the moving and stationary target acquisition and recognition (MSTAR) dataset under the standard operating condition (SOC) and four extended operating conditions (EOC), i.e., configuration variants, depression angle variances, noise interference, and partial occlusion. The results verify the effectiveness and robustness of the proposed method.

Multi-scale feature vector reconstruction for aircraft classification using high range resolution radar signatures

High-Resolution Range Profile (HRRP) is effective in various Radar Automatic Target Recognition problems. Multi-scale techniques have been verified in aircraft target HRRP feature enrichment to achieve aircraft recognition performance optimization. The involvement of multiple training-classification procedures in existing multi-scale methods results in tremendous resource consumption which challenges their real-time classification performance and application significance. This paper introduces a novel method that enables multi-scale HRRP features to be manipulated under a single scale for efficiency enhancement. Numerical analysis indicates that multi-scale intensity variations for particular HRRP scatterers could be modeled as Gaussian noises. Linear Discriminant Analysis and Singular Value Decomposition techniques are applied on reconstructed feature vectors for better separability and noise tolerance capability. Experimental results from dynamic aircraft recognition experiments verify the expected efficiency enhancement of the proposed method while maintaining comparable classification accuracy and better noise tolerance performance.

Fast recognition algorithm for faint targets in complex space background

<p indent="0mm">Imaging characteristics of stars and artificial targets in space are very similar in long-distance space-based observation as they are both light spots described by point spread function with a Gaussian distribution. In the condition of low signal-to-noise ratio, the signal of space artificial targets is faint on the image, which is covered with background and noise signals; thus, it is more difficult to recognize the faint space artificial targets from complex backgrounds. To solve this problem, this paper proposes a fast recognition algorithm for faint targets on the basis of matched filters. First, the imaging model of space artificial targets is built in the star tracking observation mode, wherein space artificial targets and stars appear as streaks and points, respectively. Therefore, the faint point target recognition problem is transferred to faint streak pattern recognition from light spot background. Second, the signal-to-noise ratio is used to define the faint degree of targets to evaluate the recognition limit of the algorithm. Then, a streak element pattern is designed. It is a part of the whole streak pattern; thus, the generation of streak patterns with varying lengths in the progress of matched filter can be avoided, so the calculation is decreased and the recognition speed is increased. Finally, to verify the fast recognition algorithm of faint targets, several images with stars and faint space artificial targets under different signal-to-noise ratios are simulated. The fast recognition algorithm of faint targets is tested using these simulation images; the results reveal that faint targets can be recognized from simulation images using this algorithm when the signal-to-noise ratio is above 0.5.

Anti-interference recognition method of aerial infrared targets based on the Bayesian network

The development of infrared decoy countermeasure technologies has resulted in the complexity of the air combat environment. Therefore, higher requirements are put forward considering the infrared imaging-guided air-to-air missile anti-interference target recognition technology. The release of infrared decoys destroys the completeness, saliency and stability of target features. It is difficult for statistical pattern recognition methods based on feature fusion and matching to cover all of the confrontation conditions. In the present study, a Bayesian probabilistic recognition model is proposed that deals with uncertain information about targets and decoys. The proposed model deals with the interference of the air battlefield with the confrontation environment. Moreover, it simulates some functions of the human visual cognition and improves the target recognition ability when interference exists. Furthermore, numerous simulation data samples are utilized to solve the network structure as well as parameters of the Bayesian recognition model and the probabilistic definitions of the target and interference are achieved. Finally, a new aerial infrared target recognition algorithm is constructed based on prior information and the probability recognition model. Results of simulation experiments indicate that the recognition rate of the anti-interference recognition algorithm based on the Bayesian network reaches 90.73%, which is 6.905% higher than that of the anti-interference recognition algorithm based on Naive Bayes classifier in the tested air combat anti-interference simulation image dataset. Moreover, it can solve the problem of anti-interference target recognition to a certain extent such as false targets and target occlusion.

Time-Frequency Analysis and Target Recognition of HRRP Based on CN-LSGAN, STFT, and CNN

Aiming at the problem of radar target recognition of High-Resolution Range Profile (HRRP) under low signal-to-noise ratio conditions, a recognition method based on the Constrained Naive Least-Squares Generative Adversarial Network (CN-LSGAN), Short-time Fourier Transform (STFT), and Convolutional Neural Network (CNN) is proposed. Combining the Least-Squares Generative Adversarial Network (LSGAN) with the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), the CN-LSGAN is presented and applied to the HRRP denoise. The frequency domain and phase features of HRRP are gained by STFT in order to facilitate feature learning and also match the input data format of the CNN. These experimental results show that the CN-LSGAN has better data augmentation performance and can effectively avoid the model collapse compared to the generative adversarial network (GAN) and LSGAN. Also, the method has better recognition performance than the one-dimensional CNN method and the Long Short-Term Memory (LSTM) network method.

Sparse Representation Classification Method for Active Sonar Target Based on Multi-order Fractional Fourier Domain Feature Fusion

Marine environment noise and reverberation interference are serious, and the poor target separability is the bottleneck problem in active sonar target classification and recognition. In order to solve this problem, based on the echo signal model of active sonar target and the principle of FRactional Fourier Transform (FRFT), this paper deduces the multi-order FRFT domain feature representation form, establishes the FRFT domain sparse representation model, and proposes a method to classify the sparse representation of active sonar targets with multi-order FRFT domain feature fusion. The method achieves the purpose of suppressing noise and reverberation interference through the energy aggregation of FRFT and removing the residual of sparse decomposition; Through the fusion of multi-order FRFT domain features, the separability of targets is improved, and the active sonar target classification with low SNR is realized. Experimental results show that the classification accuracy of the proposed method can reach more than 90% when the SNR is about 0 dB.

Radar Target Classification Based on High Resolution Range Profile Segmentation and Ensemble Classification

Radar target range profile possesses advantages in many target recognition problems. Feature extraction techniques could optimize target recognition performance, but conventional methods neglect specific characters of electromagnetic scattering mechanisms in range profiles. This letter introduces a range profile segmentation algorithm, which decomposes target range profile into segments corresponding to particular electromagnetic scattering mechanisms. Segment type identification and weighing algorithms are also developed for ensemble classification strategy. Results indicate that the proposed method could achieve comparable classification accuracy as advanced neural networks but requires far fewer computational resources to guarantee its application flexibility.

Adaptive target and jamming recognition for the pulse doppler radar fuze based on a time-frequency joint feature and an online-updated naive bayesian classifier with minimal risk

This paper considers the problem of target and jamming recognition for the pulse Doppler radar fuze (PDRF). To solve the problem, the matched filter outputs of the PDRF under the action of target and jamming are analyzed. Then, the frequency entropy and peak-to-peak ratio are extracted from the matched filter output of the PDRF, and the time-frequency joint feature is constructed. Based on the time-frequency joint feature, the naive Bayesian classifier (NBC) with minimal risk is established for target and jamming recognition. To improve the adaptability of the proposed method in complex environments, an online update process that adaptively modifies the classifier in the duration of the work of the PDRF is proposed. The experiments show that the PDRF can maintain high recognition accuracy when the signal-to-noise ratio (SNR) decreases and the jamming-to-signal ratio (JSR) increases. Moreover, the applicable analysis shows that he ONBCMR method has low computational complexity and can fully meet the real-time requirements of PDRF.

Automatic Target Recognition for Low Resolution Foliage Penetrating SAR Images Using CNNs and GANs

In recent years, the technological advances leading to the production of high-resolution Synthetic Aperture Radar (SAR) images has enabled more and more effective target recognition capabilities. However, high spatial resolution is not always achievable, and, for some particular sensing modes, such as Foliage Penetrating Radars, low resolution imaging is often the only option. In this paper, the problem of automatic target recognition in Low Resolution Foliage Penetrating (FOPEN) SAR is addressed through the use of Convolutional Neural Networks (CNNs) able to extract both low and high level features of the imaged targets. Additionally, to address the issue of limited dataset size, Generative Adversarial Networks are used to enlarge the training set. Finally, a Receiver Operating Characteristic (ROC)-based post-classification decision approach is used to reduce classification errors and measure the capability of the classifier to provide a reliable output. The effectiveness of the proposed framework is demonstrated through the use of real SAR FOPEN data.

Hybrid Inference Network for Few-Shot SAR Automatic Target Recognition

Synthetic aperture radar (SAR) automatic target recognition (ATR) plays an important role in SAR image interpretation. However, at least hundreds of training samples are usually required for each target type in the existing SAR ATR algorithms. In this article, a novel few-shot learning framework named hybrid inference network (HIN) is proposed to tackle the problem of SAR target recognition with only a few training samples. The recognition procedure of HIN consists of two main stages. In the first stage, an embedding network is utilized to map the SAR images into an embedding space. In the second stage, a hybrid inference strategy that combines the inductive inference and the transductive inference is adopted to classify the samples in the embedding space. In the inductive inference section, each sample is recognized independently according to a metric based on Euclidean distance. In the transductive inference section, all samples are recognized as a whole according to their manifold structures by label propagation. Finally, in the hybrid inference section, the classification result is obtained by combining the above two inference methods. To train the framework more effectively, a novel loss function named enhanced hybrid loss is proposed to constrain samples to gain better interclass separability in the embedding space. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) benchmark data set illustrate that HIN performs well in few-shot SAR image classification.

Target Recognition Algorithm Based on Optical Sensor Data Fusion

Optical sensor data fusion technology is a research hotspot in the field of information science in recent years, which is widely used in military and civilian fields because of its advantages of high accuracy and low cost, and target recognition is one of the important research directions. Based on the characteristics of small target optical imaging, this paper fully utilizes the frontier theoretical methods in the field of image processing and proposes a small target recognition algorithm process framework based on visible and infrared image data fusion and improves the accuracy as well as stability of target recognition by improving the multisensor information fusion algorithm in the photoelectric meridian tracking system. A practical guide is provided for the solution of the small target recognition problem. To facilitate and quickly verify the multisensor fusion algorithm, a simulation platform for the intelligent vehicle and the experimental environment is built based on Gazebo software, which can realize the sensor data acquisition and the control decision function of the intelligent vehicle. The kinematic model of the intelligent vehicle is firstly described according to the design requirements, and the camera coordinate system, LiDAR coordinate system, and vehicle body coordinate system of the sensors are established. Then, the imaging models of the depth camera and LiDAR, the data acquisition principles of GPS and IMU, and the time synchronization relationship of each sensor are analyzed, and the error calibration and data acquisition experiments of each sensor are completed.

Entity Recognition Based on Knowledge Graph in Air Defense Domain

Air defense safety refers to the state in which the civil air transportation system is free from the threat or damage of illegal interference or disruptive behavior. It forms two important parts of aviation safety together with flight safety. It is an important part of civil aviation safety This paper proposes an entity recognition algorithm based on knowledge graph, which aims to solve the problem of target recognition in the air defense field by combining pattern recognition and inconsistency verification methods based on knowledge graph. The effectiveness of the method is proved by verifying the air defense data in the simulation scenario. This method provides new research ideas for threat discovery in our country’s air defense field.

SAR Target Recognition via Meta-Learning and Amortized Variational Inference.

The challenge of small data has emerged in synthetic aperture radar automatic target recognition (SAR-ATR) problems. Most SAR-ATR methods are data-driven and require a lot of training data that are expensive to collect. To address this challenge, we propose a recognition model that incorporates meta-learning and amortized variational inference (AVI). Specifically, the model consists of global parameters and task-specific parameters. The global parameters, trained by meta-learning, construct a common feature extractor shared between all recognition tasks. The task-specific parameters, modeled by probability distributions, can adapt to new tasks with a small amount of training data. To reduce the computation and storage cost, the task-specific parameters are inferred by AVI implemented with set-to-set functions. Extensive experiments were conducted on a real SAR dataset to evaluate the effectiveness of the model. The results of the proposed approach compared with those of the latest SAR-ATR methods show the superior performance of our model, especially on recognition tasks with limited data.

Multi-scale spectral feature extraction for underwater acoustic target recognition

In this work, we proposed a multi-scale spectral (MSS) feature set for underwater acoustic target recognition problem, whose main difficulty lies in the fact that the acoustic signal is often submerged by intense environmental noise. With explicit physical meaning, the proposed MSS feature set fits better with traditional machine learning algorithms, presenting accuracies around 98% for static targets and 90% for moving targets, respectively. The baseline features and algorithm, MFCCs and CNN, show accuracies of only 77.18% and 83.31% for static and moving targets. Thus, the MSS features exhibit “fingerprint” characters of underwater acoustic targets, and are robust in highly noisy and constantly changing environment. MSS features also only need very low computational complexity, thus present great advantages in underwater acoustic target recognition.

SPAM-Net: A CNN-Based SAR Target Recognition Network With Pose Angle Marginalization Learning

Recently, deep convolutional neural networks (CNNs) have started to be applied for automatic target recognition (ATR) problems of synthetic aperture radar (SAR) images. In conventional SAR-ATR algorithms, the pose angle information of the target has been importantly used. However, recent deep learning-based SAR-ATR algorithms often only utilize the intensity information. In this paper, based on the prior works that the pose angle is an important latent variable for boosting target recognition performance, we propose a CNN-based SAR target recognition network with pose angle marginalization learning, called SPAM-Net that marginalizes the conditional probabilities of SAR targets over their pose angles to precisely estimate the true class probabilities. The proposed SPAM-Net consists of two sub-nets: (i) a sub-net for class-conditional probability estimation, called CP sub-net, and (ii) a sub-net for pose angle probability estimation, called PP sub-net. The two sub-nets are jointly learned via an end-to-end manner in a Bayesian framework so that the SPAM-Net incorporates the pose angle information into target recognition task effectively. The SPAM-Net outperforms our baseline network that does not utilize the pose angle information. In the experiments, we intensively analyze the effectiveness of pose angle information for SAR-ATR, revealing that more accurate pose angle information helps the SPAM-Net precisely estimate target classes for the misclassified target groups that are obtained by the baseline network. Furthermore, our method also outperforms the other state-of-the-art SAR-ATR algorithms, yielding the correct target recognition rate with average 99.61%.

Research on Super-Resolution Image Reconstruction Based on Low-Resolution Infrared Sensor

Due to the limitation of the pixel size in the focal plane, the low-resolution(LR) infrared sensor has a very low image resolution when sampling and imaging scenes with slightly rich spatial frequencies, and aliasing is sometimes very serious. This paper uses a new technique base on sub-pixel displacement to reconstruct high-resolution(HR) images,with reduced aliasing, from a sequence of under-sampled rotated frames of the same object. First, this paper presents an image degradation model, based on the under-sampling model of the infrared image and the infrared radiation distribution on the focal plane. Second, an image reconstruction algorithm based on image micro rotation is proposed and implemented to solve the problems of inaccurate temperature measurement and target recognition caused by low resolution. Finally, the experiments results are provided to test our algorithm, and we can obtain the image whose resolution is four or five times higher than the under-sampled frames, as well as improve the temperature measurement accuracy by more than 10%. The experimental results also show that the image reconstruction algorithm is very robust, efficient and has a good reconstruction effect.

Continuously Adaptive Mean-shift Tracking Algorithm Based on Improved Gaussian Model

In complex scenes with light changes, deformations, and occlusions, target tracking easily contains a large amount of background color information when building a target color model. Thus, the tracking effect is reduced. To improve the accuracy of the traditional continuously adaptive mean-shift algorithm (CAMShift) in complex scenarios, a target tracking algorithm based on an improved Gaussian mixture model was proposed. Using the Gaussian mixture model, the tracking image was divided into the foreground and background superposition. The histograms of the hue component were respectively established in the foreground and background of the target area. By suppressing the same hue as the background color in the tracking image, the target color model was established. The target position was iteratively obtained by implementing the CAMShift algorithm using the enhanced target color model. The Bhattacharyya distance between the candidate target and the target template was used as basis for updating the target model. Simulation analysis under benchmark data sets and actual monitoring scenarios verified the accuracy of the proposed algorithm. Results show that the distance precision and overlap success rate of the proposed algorithm are 0.88 and 0.625, respectively. The proposed algorithm effectively solves long-term target tracking problems with complex scenes, such as occlusion, background clutters, and illumination variation. This study eliminates the problem of target recognition caused by environmental changes and provides references for real-time monitoring of abnormal traffic conditions.