A 3D U-Net Based on a Vision Transformer for Radar Semantic Segmentation.

Radar target recognition is an important research direction in the field of radar information processing. Low resolution radar ground target classification and recognition still has broad application prospects in modern military and civil fields. Convolutional neural network (CNN) has attracted more and more attention in the field of radar automatic target recognition, because it does not need Feature Engineering and has superior classification performance. The optimization algorithm of neural network is proposed, and the effects of different network structures on the recognition effect are compared, in this paper. The results show that the multi-scale wide residual network multi-target classification algorithm based on optimized auto-encoder has better recognition effect in low resolution radar target recognition.

High resolution range profile (HRRP) has the advantages of low complexity in imaging and processing. These features make HRRP widely adopted in radar automatic target recognition technology. Template matching is a representative technique for radar target recognition using HRRP. To overcome the attitude sensitivity problem of HRRP data, it is necessary to subdivide the training database according to attitude domain, and construct corresponding templates for matching. However, templates from traditional methods usually cause the loss of details due to the smoothing process, with limited classification performance. This paper is motivated by proposing a template generation approach based on maximum information profile, which retains the detailed information in templates for accuracy optimization. The proposed method is verified by the recognition experiments of three types of aircraft targets. The experimental results indicate that the maximum information profile outperform the mean range profile contributed by the angle domain template.

Abstract. Semantic instance segmentation from scenes, serving as a crucial role for 3D modelling and scene understanding. Conducting semantic segmentation before grouping instances is adopted by the existing state-of-the-art methods. However, without additional refinement, semantic errors will fully propagate into the grouping stage, resulting in low overlap with the ground truth instance. Furthermore, the proposed methods focused on indoor level scenes, which are limited when directly applied to large-scale outdoor Airborne Laser Scanning (ALS) point clouds. Numerous instances, significant object density and scale variations make ALS point clouds distinct from indoor data. In order to address the problems, we proposed a geometric characterization-aware semantic instance segmentation network, which utilized both semantic and objectness score to select potential points for grouping. And in point cloud feature learning stage, hand-craft geometry features are taken as input for geometric characterization awareness. Moreover, to address errors propagated from previous modules after grouping, we have additionally designed a per-instance refinement module. To assess semantic instance segmentation, we conducted experiments on an open-source dataset. Additionally, we performed semantic segmentation experiments to evaluate the performance of our proposed point cloud feature learning method.

Polarimetric radar systems play a crucial role in enhancing microwave remote sensing and target identification by providing a refined understanding of electromagnetic scattering mechanisms. This study introduces the concept of polarization scattering regions as a novel tool for describing the polarization characteristics across three spectral regions: the polarization Rayleigh region, the polarization resonance region, and the polarization optical region. By using ellipsoidal models, we simulate and analyze scattering across varying electrical sizes, demonstrating how these sizes influence polarization characteristics. The research leverages Cameron decomposition to reveal the distinctive scattering behaviors within each region, illustrating that at higher-frequency bands, scattering approximates spherical symmetry, with minimal impact from the target shape. This classification provides a comprehensive view of polarization-based radar cross-section regions, expanding upon traditional single-polarization radar cross-section regions. The results show that polarization scattering regions are practical tools for interpreting polarimetric radar data across diverse frequency bands. The applications of this research in radar target recognition, weather radar calibration, and radar polarimetry are discussed, highlighting the importance of frequency selection for accurately capturing polarization scattering features. These findings have significant implications for advancing weather radar technology and target recognition techniques, particularly as radar systems move towards higher frequency bands.

Accurate organ-level segmentation is essential for achieving high-throughput, non-destructive, and automated plant phenotyping. To address the challenge of intelligent acquisition of phenotypic parameters in tomato plants, we propose TSINet, an end-to-end dual-task segmentation network designed for effective and precise semantic labeling and instance recognition of tomato point clouds, based on the Pheno4D dataset. TSINet adopts an encoder–decoder architecture, where a shared encoder incorporates four Geometry-Aware Adaptive Feature Extraction Blocks (GAFEBs) to effectively capture local structures and geometric relationships in raw point clouds. Two parallel decoder branches are employed to independently decode shared high-level features for the respective segmentation tasks. Additionally, a Dual Attention-Based Feature Enhancement Module (DAFEM) is introduced to further enrich feature representations. The experimental results demonstrate that TSINet achieves superior performance in both semantic and instance segmentation, particularly excelling in challenging categories such as stems and large-scale instances. Specifically, TSINet achieves 97.00% mean precision, 96.17% recall, 96.57% F1-score, and 93.43% IoU in semantic segmentation and 81.54% mPrec, 81.69% mRec, 81.60% mCov, and 86.40% mWCov in instance segmentation. Compared with state-of-the-art methods, TSINet achieves balanced improvements across all metrics, significantly reducing false positives and false negatives while enhancing spatial completeness and segmentation accuracy. Furthermore, we conducted ablation studies and generalization tests to systematically validate the effectiveness of each TSINet component and the overall robustness of the model. This study provides an effective technological approach for high-throughput automated phenotyping of tomato plants, contributing to the advancement of intelligent agricultural management.

As one of the most important components of urban space, an outdated inventory of road-side trees may misguide managers in the assessment and upgrade of urban environments, potentially affecting urban road quality. Therefore, automatic and accurate instance segmentation of road-side trees from urban point clouds is an important task in urban ecology research. However, previous works show under- or over-segmentation effects for road-side trees due to overlapping, irregular shapes and incompleteness. In this paper, a deep learning framework that combines semantic and instance segmentation is proposed to extract single road-side trees from vehicle-mounted mobile laser scanning (MLS) point clouds. In the semantic segmentation stage, the ground points are filtered to reduce the processing time. Subsequently, a graph-based semantic segmentation network is developed to segment road-side tree points from the raw MLS point clouds. For the individual tree segmentation stage, a novel joint instance and semantic segmentation network is adopted to detect instance-level roadside trees. Two complex Chinese urban point cloud scenes are used to evaluate the individual urban tree segmentation performance of the proposed method. The proposed method accurately extract approximately 90% of the road-side trees and achieve better segmentation results than existing published methods in both two urban MLS point clouds. Living Vegetation Volume (LVV) calculation can benefit from individual tree segmentation. The proposed method provides a promising solution for ecological construction based on the LVV calculation of urban roads.

Automatic target recognition has been one of the hottest research in synthetic aperture radar (SAR) data processing. Noticing that popular recognition methods cannot utilize multiple features of SAR complex data, a method fused scattering center feature and deep convolutional neural network (CNN) feature is proposed in this letter. This method contains three key parts, namely, scattering center extraction and reconstruction block, CNN feature extraction block, and final feature fusion and classification block. In this process, the scattering center feature and CNN feature are fused at the level of feature maps, which retain the space information of 2-D feature maps. What is more, the proposed half end-to-end strategy realizes the automatic update of weighting parameters in feature extraction network and subnetwork, which promotes a better recognition efficiency. Experimental results on measured SAR data show that the proposed method can achieve better accuracy than other single feature-based methods and feature fusion methods.

A Unified Architecture of Semantic Segmentation and Hierarchical Generative Adversarial Networks for Expression Manipulation

This paper proposes a low-resolution ground surveillance radar automatic target recognition(ATR) method based on onedimensional convolutional neural network (1D-CNN), which solves the problem of overfitting using complex CNN for data classification. First, the target recognition algorithm combines the time-domain waveform, power spectrum, and power transform spectrum into the three channels of the established 1D-CNN input. After that, the autoencoder is used to reduce the feature dimension and improve the classifier's ability to select parameters autonomously. Finally, the Bayesian hyperparameter optimization method is used to optimize hyperparameters, which not only simplifies the network structure, but also reduces the parameter calculation scale. We tested our method with the collected data to classify people and cars, and the results showed that the recognition accuracy rate has reached 99%. Compared with the traditional artificial feature extraction target recognition method, our model has better recognition performance and adaptability.

Semantic segmentation has been proposed as a tool to accelerate the processing of natural history collection images. However, developing a flexible and resilient segmentation network requires an approach for adaptation which allows processing different datasets with minimal training and validation. This paper presents a cross-validation approach designed to determine whether a semantic segmentation network possesses the flexibility required for application across different collections and institutions. Consequently, the specific objectives of cross-validating the semantic segmentation network are to (a) evaluate the effectiveness of the network for segmenting image sets derived from collections different from the one in which the network was initially trained on; and (b) test the adaptability of the segmentation network for use in other types of collections. The resilience to data variations from different institutions and the portability of the network across different types of collections are required to confirm its general applicability. The proposed validation method is tested on the Natural History Museum semantic segmentation network, designed to process entomological microscope slides. The proposed semantic segmentation network is evaluated through a series of cross-validation experiments designed to test using data from two types of collections: microscope slides (from three institutions) and herbarium sheets (from seven institutions). The main contribution of this work is the method, software and ground truth sets created for this cross-validation as they can be reused in testing similar segmentation proposals in the context of digitization of natural history collections. The cross-validation of segmentation methods should be a required step in the integration of such methods into image processing workflows for natural history collections.

Automatic target recognition (ATR) is of increasing importance for the modern radar system, where the high-resolution range profile (HRRP) is essential. However, the recognition accuracy and sensitivity to dataset should be optimized for practical applications. Herein, we proposed a novel algorithm for HRRP target recognition based on a convolutional capsule network rather than neurons in conventional deep neural networks. The capsules were vectors trained to learn latent features from input HRRP, with the length of the vector representing the confidential probability. The convolution dynamic routing mechanism was applied between capsule layers by shared transformation matrices and constrained routing procedures in local kernels, reducing the size of parameters and computational expense. Experiments on measured data proved that the proposed algorithm outperforms other existing methods with higher recognition accuracy and less sensitivity to training size. This study provided a promising and effective approach for HRRP target recognition.

Synthetic aperture radar (SAR) target recognition under extended operating conditions (EOCs) is a challenging problem due to the complex application environment, especially for insufficient target variations and corrupted SAR images in the training samples. This paper proposes a new strategy to solve these problems for target recognition. The SAR images are firstly characterized by multi-scale components of monogenic signal. The generated monogenic features are decomposed to learn a class dictionary and a shared dictionary, which represent the possible intraclass variations information and the common information, respectively. Moreover, a sparse representation of the class dictionary and a dense representation of the shared dictionary are jointly employed to represent a query sample for classification. The validity of the proposed strategy is demonstrated with multiple comparative experiments on moving and stationary target acquisition and recognition (MSTAR) database.

Point cloud segmentation is essential for scene understanding, which provides advanced information for many applications, such as autonomous driving, robots, and virtual reality. To improve the accuracy and robustness of point cloud segmentation, many researchers have attempted to fuze camera images to complement the color and texture information. The common fusion strategy is the combination of convolutional operations with concatenation, element-wise addition or element-wise multiplication. However, conventional convolutional operators tend to confine the fusion of modal features within their receptive fields, which can be incomplete and limited. In addition, the inability of encoder–decoder segmentation networks to explicitly perceive segmentation boundary information results in semantic ambiguity and classification errors at object edges. These errors are further amplified in point cloud segmentation tasks, significantly affecting the accuracy of point cloud segmentation. To address the above issues, we propose a novel self-attention multi-modal fusion semantic segmentation network for point cloud semantic segmentation. Firstly, to effectively fuze different modal features, we propose a self-cross fusion module (SCF), which models long-range modality dependencies and transfers complementary image information to the point cloud to fully leverage the modality-specific advantages. Secondly, we design the salience refinement module (SR), which calculates the importance of channels in the feature maps and global descriptors to enhance the representation capability of salient modal features. Finally, we propose the local-aware anisotropy loss measure the element-level importance in the data and explicitly provide boundary information for the model, which alleviates the inherent semantic ambiguity problem in segmentation networks. Extensive experiments on two benchmark datasets demonstrate that our proposed method surpasses current state-of-the-art methods.

In the radar automatic target recognition (RATR) community, high-resolution range profile (HRRP) obtained from the target has been widely utilized for many recognition techniques. The information provided by one single HRRP is limited and unstable, utilizing multiple HRRPs for recognition is a better choice. However, common method such as the hidden Markov model (HMM) is not good at modeling high dimensional data and can only capture local dependencies. In this paper, a multi-scale temporal model is developed from the conditional restricted Boltzmann machine (CRBM). The proposed model can efficiently discover stochastic patterns in high dimensional data just as RBMs generally do. Besides that, it can capture multiple scales of temporal dependencies, which is especially beneficial when the angular sampling rate at testing phase is different from that at training phase. Experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) database validate the efficiency and robustness of the proposed method under various conditions.

Radar target automatic recognition is a comprehension problem. We have researched the practical radar data and concluded some valuable viewpoint. With it we put forward a whole scheme to achieve radar automatic target recognition. First the OS CAFR and binary accumulation algorithm is taken to accurately detect target. Here we lower self-adapt threshold to get more targets which maybe be false target. Then we use target trace management to remove the illusion target. The novel algorithm, called as endpoint detection based on moving window, can get more valuable data to classification. For 3D target we must build more templets in classification. So we use Neural Net as classification algorithm to reduce memory space. The simulation results prove that this scheme can get better recognition results.