Problem Of Low Resolution Research Articles

Long-term tracking for high-frequency surface wave radar based on heading constraint filtering combined ELM

Abstract Aiming at the problem of low measurement resolution and poor tracking accuracy in High-frequency surface wave radar (HFSWR) tracking field, a tracking method that combines the heading constraint filter and Extreme Learning Machine (ELM) is proposed. Compared with the existing research, the innovation of this study lies in proposing a two-stage tracking method based on the short-term stable state of the target, and similarity of long-term trajectory. Firstly, the heading constraint information is introduced into the estimator and improve the estimation accuracy. In multi-target tracking scenarios, many tracklets can be obtained. Then, the ELM learns robust features of tracklets to achieve the trajectory segment classification from the same target. This method can be widely applied to long-term tracking of cargo or passenger ships with fixed destinations, significantly improving tracking performance by utilizing implicit domain knowledge without additional information. The actual data of this paper comes from HFSWR on Bohai Bay. Both the simulation and actual measurement experiments show that the proposed cascaded tracking method achieves long-term continuous tracking, and generates more complete trajectories. Moreover, the proposed Extended Kalman filter based on pseudo-measurement and intercept parameters (IPM-EKF) exhibits better tracking stability and accuracy in limited scan steps. This study provides new ideas and methods for improving the tracking performance of special targets in the HFSWR field by utilizing motion features.

Global sparse attention network for remote sensing image super-resolution

Recently, remote sensing images have become popular in various tasks, including resource exploration. However, limited by hardware conditions and formation processes, the obtained remote sensing images often suffer from low-resolution problems. Unlike the high cost of hardware to acquire high-resolution images, super-resolution software methods are good alternatives for restoring low-resolution images. In addition, remote sensing images have a common nature that similar visual patterns repeatedly appear across distant locations. To fully capture these long-range satellite image contexts, we first introduce the global attention network super-resolution method to reconstruct the images. This network improves the performance but introduces unessential information while significantly increasing the computational effort. To address these problems, we propose an innovative method named the global sparse attention network (GSAN) that integrates both sparsity constraints and global attention. Specifically, our method applies spherical locality sensitive hashing (SLSH) to convert feature elements into hash codes, constructs attention groups based on the hash codes, and computes the attention matrix according to similar elements in the attention group. Our method captures valid and useful global information and reduces the computational effort from quadratic to asymptotically linear regarding the spatial size. Extensive qualitative and quantitative experiments demonstrate that our GSAN has significant competitive advantages in terms of performance and computational cost compared with other state-of-the-art methods.

High-resolution non-confocal non-line-of-sight imaging based on spherical-slice transform from spatial and temporal frequency to space and time.

Current non-confocal non-line-of-sight (NLOS) imaging faces the problems of low resolution and limited scene adaptability. We propose a non-confocal NLOS imaging method based on spherical-slice transform from spatial and temporal frequency to space and time. Simulation and experimental results show that the proposed method has high-resolution reconstruction without artifact interference, shape distortion, and position offset. Furthermore, it has strong scene adaptability. After GPU acceleration, the reconstruction time of the proposed method can be reduced to several hundred milliseconds for the PF32 photon array camera with 32 × 32 detection units. In the future, the proposed method has great potential for application in real-time NLOS imaging systems.

Machine learning-based grayscale analyses for lithofacies identification of the Shahejie Formation, Bohai Bay Basin, China

It is of great significance to accurately and rapidly identify shale lithofacies in relation to the evaluation and prediction of sweet spots for shale oil and gas reservoirs. To address the problem of low resolution in logging curves, this study establishes a grayscale-phase model based on high-resolution grayscale curves using clustering analysis algorithms for shale lithofacies identification, working with the Shahejie Formation, Bohai Bay Basin, China. The grayscale phase is defined as the sum of absolute grayscale and relative amplitude as well as their features. The absolute grayscale is the absolute magnitude of the gray values and is utilized for evaluating the material composition (mineral composition + total organic carbon) of shale, while the relative amplitude is the difference between adjacent gray values and is used to identify the shale structure type. The research results show that the grayscale phase model can identify shale lithofacies well, and the accuracy and applicability of this model were verified by the fitting relationship between absolute grayscale and shale mineral composition, as well as corresponding relationships between relative amplitudes and laminae development in shales. Four lithofacies are identified in the target layer of the study area: massive mixed shale, laminated mixed shale, massive calcareous shale and laminated calcareous shale. This method can not only effectively characterize the material composition of shale, but also numerically characterize the development degree of shale laminae, and solve the problem that difficult to identify millimeter-scale laminae based on logging curves, which can provide technical support for shale lithofacies identification, sweet spot evaluation and prediction of complex continental lacustrine basins.

Study on seismic characterization and distribution characteristics of effective reservoirs of granite weathering crust in Dongying Sag, Bohai Bay Basin

To solve the problem of low resolution of seismic data from granite weathering crust and difficulty in predicting effective reservoir distribution. Based on the research idea of combining geology and seismology, seismic facies characteristics and effective reservoir distribution of granite weathering crust are studied by means of frequency division reconstruction processing, seismic facies analysis and sensitive attributes interpretation. This method consists of the following four main processes: (1) Using improved Morlet wavelet function for frequency division and reconstruction processing of seismic data; (2) From the perspective of geological evolution, analyzing the geological origin of seismic facies; (3) Based on the results of well- seismic combination, clarifying the types of effective reservoirs and predicting their distribution; (4) Comprehensive research indicating favorable reservoirs distribution. The results indicate that (1) a considerably improved resolution of seismic data processed by frequency division reconstruction is obtained based on the improved Morlet wavelet function. Thus, granite reservoirs then have clearer internal reflection characteristics. (2) Affected by differences in weathering, the seismic facies in granite weathering crusts can be classified as follows: Strong-amplitude facies with amplitudes of 23,700 − 32,800, corresponding to eluvium, represents the late stage of weathering crust evolution with high-intensity weathering. Medium-amplitude facies with amplitudes of 5,250 − 24,000, corresponding to dissolution layer, represents a middle stage of weathering crust evolution with moderate weathering. And weak-amplitude-blank facies with amplitudes of 0–5,330, corresponding to disintegration layer, represents an early stage of weathering crust evolution with weak weathering. (3) Effective reservoirs can be classified according to well-seismic calibrations and combined with reservoir spaces, porosities and permeabilities, and the logging and oil-bearing characteristics of the reservoirs. Type I effective reservoir comprises medium-amplitude facies, with favorable reservoir conditions and high-yield oil-bearing properties; this type is distributed in the western slopes, with an elevation of 1,300-2,500 m. Type II effective reservoir comprises strong-amplitude facies, with poor oil-bearing properties; this type is mainly distributed in the southeast and north slopes of the study area, with a relatively limited range, and the elevation is mostly below 1,500 m. Type III effective reservoir comprises weak-amplitude-blank facies, with poor reservoir conditions and poor oil-bearing properties; this type is widely distributed at various elevations. (4) The areas where medium-amplitude facies have developed are the most favorable reservoir exploration zones for granite in Dongying Sag, Bohai Bay Basin.

Colorectal Polyp Detection Model by Using Super-Resolution Reconstruction and YOLO

Colorectal cancer (CRC) is the second leading cause of cancer-related deaths worldwide. Colonoscopy is the primary method to prevent CRC. However, traditional polyp detection methods face problems such as low image resolution and the possibility of missing polyps. In recent years, deep learning techniques have been extensively employed in the detection of colorectal polyps. However, these algorithms have not yet addressed the issue of detection in low-resolution images. In this study, we propose a novel YOLO-SRPD model by integrating SRGAN and YOLO to address the issue of low-resolution colonoscopy images. Firstly, the SRGAN with integrated ACmix is used to convert low-resolution images to high-resolution images. The generated high-resolution images are then used as the training set for polyp detection. Then, the C3_Res2Net is integrated into the YOLOv5 backbone to enhance multiscale feature extraction. Finally, CBAM modules are added before the prediction head to enhance attention to polyp information. The experimental results indicate that YOLO-SRPD achieves a mean average precision (mAP) of 94.2% and a precision of 95.2%. Compared to the original model (YOLOv5), the average accuracy increased by 1.8% and the recall rate increased by 5.6%. These experimental results confirm that YOLO-SRPD can address the low-resolution problem during colorectal polyp detection and exhibit exceptional robustness.

Lp-norm relaxation approach for 3D measurement via instantaneous light field of ethylene premixed flames

Optical imaging technology based on flame spontaneous radiation is a promising tool for combustion diagnosis. However, the existing radiation thermometry technology faces the problems of low angular resolution and low efficiency in solving radiative transfer. Therefore, a novel optical imaging model is proposed, which combines light field imaging theory with equation-solving integral equation method based on radiation distribution factor to effectively decouple the radiative properties related to transfer process and the temperature-related source terms. Aiming at the problem that traditional method may cause over-smooth effect, Lp-norm regularization based on non-negative constraint is established. Results show that Lp-norm can improve reconstruction quality and robustness, but p value needs to be reasonably selected according to noise level and flame inhomogeneity. Experimental study of ethylene/air-premixed flames shows that the methodology can realize 3D measurement (900 ∼ 1550 K). Compared with laser absorption spectroscopy and thermocouple, error is better than 3 % at height above burner 15 mm.

Target Image Processing based on Super-resolution Reconstruction and Machine Learning Algorithm

This article proposes a target image processing method based on super-resolution reconstruction and machine learning algorithms, which solves the low-resolution problem in medical images during imaging. This method uses nonlocal autoregressive learning based on a medical image super-resolution reconstruction method. The autoregressive model is introduced into the sparse representation-based medical image super-resolution reconstruction model by utilizing medical image data inherent nonlocal similarity characteristics. At the same time, a clustering algorithm is used to obtain a classification dictionary, improving experimental efficiency. The experimental results show that ten randomly selected CT/MR images are used as test images, and each image's peak signal-to-noise ratio and structural similarity values are calculated separately. Compared with other methods, the method proposed in this paper is significantly better and can achieve ideal results, with the highest value being 31.49. This method demonstrates the feasibility of using super-resolution reconstruction and machine learning algorithms in medical image resolution.

Three-Dimensional Human Pose Estimation from Micro-Doppler Signature Based on SISO UWB Radar

In this paper, we propose an innovative approach for transforming 2D human pose estimation into 3D models using Single Input–Single Output (SISO) Ultra-Wideband (UWB) radar technology. This method addresses the significant challenge of reconstructing 3D human poses from 1D radar signals, a task traditionally hindered by low spatial resolution and complex inverse problems. The difficulty is further exacerbated by the ambiguity in 3D pose reconstruction, as multiple 3D poses may correspond to similar 2D projections. Our solution, termed the Radar PoseLifter network, leverages the micro-Doppler signatures inherent in 1D radar echoes to effectively convert 2D pose information into 3D structures. The network is specifically designed to handle the long-range dependencies present in sequences of 2D poses. It employs a fully convolutional architecture, enhanced with a dilated temporal convolutions network, for efficient data processing. We rigorously evaluated the Radar PoseLifter network using the HPSUR dataset, which includes a diverse range of human movements. This dataset comprises data from five individuals with varying physical characteristics, performing a variety of actions. Our experimental results demonstrate the method’s robustness and accuracy in estimating complex human poses, highlighting its effectiveness. This research contributes significantly to the advancement of human motion capture using radar technology. It presents a viable solution for applications where precision and reliability in motion capture are paramount. The study not only enhances the understanding of 3D pose estimation from radar data but also opens new avenues for practical applications in various fields.

High-Resolution localization of broadband sound sources in a duct using out-duct array measurements

This paper investigates using an Iterated Bayesian Focusing Algorithm and out-duct array measurements to identify multiple broadband sources placed in a cylindrical duct. The problems of large main lobe and low resolution due to localization of sources using conventional methods are investigated in this paper. To solve these problems, an Iterated Bayesian Focusing (IBF) method is utilized to localize the broadband sources. To evaluate and confirm the efficacy of the method, simulation tests and experimental validation are performed. In our experiments, we used a 56-channel dobby spiral array for out-duct measurements and beamforming method, equivalent source method (ESM), deconvolution approach for the mapping of acoustic sources (DAMAS), and Iterated Bayesian Focusing (IBF) method to localize broadband sources inside the duct. Simulation and experimental results demonstrate that the Iterated Bayesian Focusing (IBF) method significantly reduces the main lobe width and minimizes the number of minor lobes. This leads to improved accuracy in localizing double sources.

High‐resolution reservoir prediction method based on data‐driven and model‐based approaches

AbstractThe Jiyang depression in the southeastern part of the Bohai Bay Basin has a relatively large scale set of shale oil in the Paleogene Shahejie Formation, but the complex internal components lead to narrow frequency bands, low resolution and difficulty in reservoir information extraction. Impedance is important information for reservoir characterization, and how to predict high‐resolution impedance using available information is particularly important. Deep learning, known for its effectiveness in addressing non‐linear problems, has found extensive applications in various fields of oil and gas exploration. However, the challenges of overfitting and poor generalization persist due to the limited availability of training datasets. Besides, existing methods often use networks to solve a single problem in fact, deep learning can deal with a series of problems intelligently. In order to partially solve the above problems, an intelligent storage prediction network framework is proposed in this paper. Physical information is introduced to realize data‐driven and model‐based approaches, thus solving the problem of difficult construction of training datasets. The processing part accomplishes the high‐resolution processing of seismic records, thus solving the problems of narrow bandwidth and low resolution. Initial model constraints are introduced so as to obtain more stable inversion results. Finally, the well data is compared and analysed to identify and predict the lithology and complete the intelligent prediction of unconventional reservoirs. The results are compared with the traditional model‐driven inversion method, revealing that the approach presented in this paper exhibits higher resolution in predicting dolomite. This contributes to the establishment of a robust data foundation for reservoir evaluation.

Diverter transformer-based multi-encoder-multi-decoder network model for medical retinal blood vessel image segmentation

The retinal blood vessel is an essential part of the fundus structure. It is important to accurately analyze the structure and distribution of retinal vessels, which can help make accurate medical diagnoses. However, it is still challenging to extract detailed information due to the problems of fuzzy edges, low resolution, and lots of noise in retinal blood vessel medical images. To extract the image detail information effectively, we propose a new diverter transformer-based multi-encoder-multi-decoder network model in this paper. The network model consists of a feature encoder module and a feature decoder module. Among them, the feature encoding module consists of a diverter transformer with a diverter adaptive mechanism, three encoder units with a convolution layer and max-pooling layer, and the two decoder units in the feature decoding module consist of an inverse convolution layer and an up-sampling layer, respectively. The Local Context Module (LCNet Module) in the feature encoding module learns richer local context feature information layer by layer through changing the width of the network while downsampling; the Global Encoder Module1 (G-Encoder Module1) and the Global Encoder Module2 (G-Encoder Module2) extract the global feature representation of retinal blood vessel images by performing a max-pooling operation to transform the input data into a vector of fixed dimensions, thus helping the network model to better understand and extract the global feature representation of retinal blood vessel images. The two decoder units in the feature decoding module receive local and global feature information from three encoder units, LCNet Module, G-Encoder Module1 and G-Encoder Module2, respectively. Decoder Module1 generates segmentation prediction by layer-by-layer up-sampling operation, and Decoder Module2 recovers the feature information by downsampling and decoding operations and fuses the recovered feature information to output, obtaining the final segmentation of the retinal blood vessels. The proposed diverter transformer-based multi-encoder-multi-decoder network model is validated on the DRIVE and STARE datasets with other classical and state-of-the-art network models, and its segmentation accuracy is 97.25% and 97.93%, respectively. Compared with the classical U-Net model, the improvement is 2.24% and 1.42%, respectively. Compared with the state-of-the-art SPNet model, the accuracy is increased by 0.61% on DRIVE and 1.01% on STARE. It indicates that the network model proposed in this paper has a significant competitive advantage in improving the segmentation performance of retinal blood vessel images.

Design and experimental verification of phase-reversal Fresnel lens for contact stress characterization

The accurate characterization of the contact stress on the mating surfaces of assembly components is a key means to ensure the assembly accuracy and operational safety of aero-engines. In this paper, a phase-reversal Fresnel lens for contact stress characterization is designed to solve the problem of low spatial resolution of contact stress characterization by the non water immersion ultrasonic method. The phase-reversal Fresnel lens is used to focus the ultrasonic wave on the mating surface of the assembly components to improve the spatial resolution of the contact stress characterization. The finite element simulation method is used to analyze the influence of the number of lens rings, the piezoelectric plate's diameter, the lens's thickness, and the groove depth on the focusing characteristics of Fresnel lenses. The power spectrum peak is used to analyze the residual reflected wave energy of the mating surface. According to the correlation between the residual reflected wave energy and the contact stress, a correlation model between the two is built to realize the characterization of the contact stress. This study provides a promising method for the characterization of contact stress on the mating surface of aero-engine assembly components by non water immersion focused ultrasound.

Optimizing the temporal and spatial resolutions and light throughput of Fresnel incoherent correlation holography in the framework of coded aperture imaging

Fresnel incoherent correlation holography (FINCH) is a well-established digital holography technique for 3D imaging of objects illuminated by spatially incoherent light. FINCH has a higher lateral resolution of 1.5 times that of direct imaging systems with the same numerical aperture. However, the other imaging characteristics of FINCH, such as axial resolution, temporal resolution, light throughput, and signal-to-noise ratio (SNR), are lower than those of direct imaging systems. Different techniques were developed by researchers around the world to improve the imaging characteristics of FINCH while retaining the inherent higher lateral resolution of FINCH. However, most of the solutions developed to improve FINCH presented additional challenges. In this study, we optimized FINCH in the framework of coded aperture imaging. Two recently developed computational methods, such as transport of amplitude into phase based on the Gerchberg Saxton algorithm and Lucy–Richardson–Rosen algorithm, were applied to improve light throughput and image reconstruction, respectively. The above implementation improved the axial resolution, temporal resolution, and SNR of FINCH and moved them closer to those of direct imaging while retaining the high lateral resolution. A point spread function (PSF) engineering technique has been implemented to prevent the low lateral resolution problem associated with the PSF recorded using pinholes with a large diameter. We believe that the above developments are beyond the state-of-the-art of existing FINCH-scopes.

Unsupervised Domain-Adaptive SAR Ship Detection Based on Cross-Domain Feature Interaction and Data Contribution Balance

Due to the complex imaging mechanism of SAR images and the lack of multi-angle and multi-parameter real scene SAR target data, the generalization performance of existing deep-learning-based synthetic aperture radar (SAR) image target detection methods are extremely limited. In this paper, we propose an unsupervised domain-adaptive SAR ship detection method based on cross-domain feature interaction and data contribution balance. First, we designed a new cross-domain image generation module called CycleGAN-SCA to narrow the gap between the source domain and the target domain. Second, to alleviate the influence of complex backgrounds on ship detection, a new backbone using a self-attention mechanism to tap the potential of feature representation was designed. Furthermore, aiming at the problems of low resolution, few features and easy information loss of small ships, a new lightweight feature fusion and feature enhancement neck was designed. Finally, to balance the influence of different quality samples on the model, a simple and efficient E12IoU Loss was constructed. Experimental results based on a self-built large-scale optical-SAR cross-domain target detection dataset show that compared with existing cross-domain methods, our method achieved optimal performance, with the mAP reaching 68.54%. Furthermore, our method achieved a 6.27% improvement compared to the baseline, even with only 5% of the target domain labeled data.

Supervised-unsupervised combined transformer for spectral compressive imaging reconstruction

To solve the low spatial and/or temporal resolution problem which the conventional hyperspectral cameras often suffer from, spectral compressive imaging systems (SCI) have attracted more attention recently. Recovering a hyperspectral image (HSI) from its corresponding 2D coded image is an ill-posed inverse problem, and learning accurate prior from HSI and 2D coded image is essential to solve this inverse problem. Existing methods only use supervised networks that focus on learning generalized prior from training datasets, or only use unsupervised networks that focus on learning specific prior from 2D coded image, resulting in the inability to learn both generalized and specific priors. Also, when learning the priors, existing methods cannot simultaneously give consideration to both global and local scales, as well as both spatial and spectral dimensions. To cope with this problem, in this paper, we propose a Supervised-Unsupervised Combined Transformer Network (SUCTNet) composed by a supervised Spatio-spectral Transformer network (SSTNet) and an Unsupervised Multi-level Feature Refinement network (UMFRNet). Specifically, we first develop the SSTNet to learn generalized prior and obtain a preliminary HSI. In SSTNet, the proposed spatial encoding and spectral decoding network architecture enables it to simultaneously consider both spatial and spectral dimensions, and a proposed Global and Local Multi head Self Attention block (GL-MSA) enables it simultaneously to consider both global and local scales. Then, the preliminary HSI is fed into the proposed UMFRNet to learn specific prior and obtain the target HSI. In UMFRNet, a proposed multi-level feature refinement mechanism and the physical imaging model of SCI are used to improve reconstruction accuracy and generalization performance. Extensive experiments show that our method significantly outperforms state-of-the-art (SOTA) methods on simulated and real datasets. Codes will be available at https://github.com/Vzhouhan/SUCTNet.

Research on downscaling method of the enhanced TROPOMI solar-induced chlorophyll fluorescence data

Solar-induced chlorophyll fluorescence (SIF) is the release of plant energy during photosynthesis, which is significantly superior to the vegetation index in the characterization of vegetation growth. However, the existing satellite retrieved SIF data have the problems of low spatial resolution and spatial discontinuity. To solve these problems, this paper proposes multiple parameters downscaling method that considers the structural and physiological characteristics of SIF. Multiple linear regression (MLR), random forest (RF), and convolutional neural network (CNN) models were used to construct a downscaling model for the TROPOspheric Monitoring Instrument (TROPOMI) Enhanced SIF (eSIF) data. The theory of spatial scale invariance was applied to invert the 500 m spatial resolution SIF data products for Henan Province from 2012 to 2021 using Moderate-resolution Imaging Spectroradiometer (MODIS) data. The evaluation metrics for assessing downscaling accuracy include the determination coefficient (R 2), mean absolute error (MAE), and root mean squared error (RMSE). The experimental results demonstrate that the RF model outperforms others, achieving R 2, MAE, and RMSE values of 0.935, 0.041 mW/m2/nm2/sr, and 0.061 mW/m2/nm2/sr, respectively. These results successfully meet the downscaling requirements. The downscaling data products have better fitting effect with eSIF and new Global 'OCO-2′ SIF (GOSIF) data both in time and space. The correlation between downscaling SIF data and winter wheat yield is significantly better than that of GOSIF data products and shows strong correlation with Gross Primary Productivity (GPP). By considering the structural and physiological characteristics of SIF, the RF algorithm can effectively retrieve reliable 500 m spatial resolution SIF data, this provides methodological support for the application of SIF data at higher spatial scales.

Fractional-Order Super-Resolution Reconstruction Algorithm for GM-APD Lidar Distance Images Based on Convex Set Projection

The main objective of this paper is to solve the problem of low resolution of target distance images obtained by GM-APD lidar. Towards overcoming this problem, this paper proposes a fractional-order super-resolution reconstruction algorithm for GM-APD lidar distance images based on convex set projection. Firstly, the first low-resolution image is upsampled three times to obtain a high-resolution reference image. Second, starting from the image degradation model, the transformation model between the low-resolution image and the high-resolution reference image is constructed. Then the high-resolution reference image is convolved using the G-L fractional order differential operator, and the estimated low-resolution image is obtained by combining the point spread function. Finally, the difference between the remaining low-resolution images and the estimated low-resolution image is calculated, and the high-resolution reference image is corrected to obtain the final high-resolution distance image. In addition to solving the edge blurring problem of the original convex set projection algorithm, the edge structure of the image is enhanced and the image quality is improved. Simulation and experimental results show that the proposed algorithm improves the information entropy by at least 24.190% and the average gradient by at least 10.812%, and achieves the super-resolution reconstruction of GM-APD LIDAR target distance images.

Intelligent Gangue Sorting System Based on Dual-Energy X-ray and Improved YOLOv5 Algorithm

Intelligent gangue sorting with high precision is of vital importance for improving coal quality. To tackle the challenges associated with coal gangue target detection, including algorithm performance imbalance and hardware deployment difficulties, in this paper, an intelligent gangue separation system that adopts the elevated YOLO-v5 algorithm and dual-energy X-rays is proposed. Firstly, images of dual-energy X-ray transmission coal gangue mixture under the actual operation of a coal mine were collected, and datasets for training and validation were self-constructed. Then, in the YOLOv5 backbone network, the EfficientNetv2 was used to replace the original cross stage partial darknet (CSPDarknet) to achieve the lightweight of the backbone network; in the neck, a light path aggregation network (LPAN) was designed based on PAN, and a convolutional block attention module (CBAM) was integrated into the BottleneckCSP of the feature fusion block to raise the feature acquisition capability of the network and maximize the learning effect. Subsequently, to accelerate the rate of convergence, an efficient intersection over union (EIOU) was used instead of the complete intersection over union (CIOU) loss function. Finally, to address the problem of low resolution of small targets leading to missed detection, an L2 detection head was introduced to the head section to improve the multi-scale target detection performance of the algorithm. The experimental results indicate that in comparison with YOLOv5-S, the same version of the algorithm proposed in this paper increases by 19.2% and 32.4% on mAP @.5 and mAP @.5:.95, respectively. The number of parameters decline by 51.5%, and the calculation complexity declines by 14.7%. The algorithm suggested in this article offers new ideas for the design of identification algorithms for coal gangue sorting systems, which is expected to save energy and reduce consumption, reduce labor, improve efficiency, and be more friendly to the embedded platform.

Measurement of Submicron Particle Size Using Scattering Angle-Corrected Polarization Difference with High Angular Resolution

The particle size of submicron particles significantly affects their properties; thus, the accurate measurement of submicron particle size is essential to ensure its excellent properties. Polarized light scattering is an important tool for measuring the particle size of the ensemble of particles in suspension. However, in the existing measurement systems, the polarized scattered light is detected using a CCD detector or an array of single-point detectors. The CCD detector misses a large part of the polarized scattered light due to its narrow detection range of scattering angles, and the array of single-point detectors has the problem of low angular resolution due to the limited number of detectors. According to the above problems, this paper designs a submicron particle size measurement method based on the polarization difference in polarized scattered light with high angular resolution. The vertically and horizontally polarized scattered light was acquired with high angular resolution (angular separation = 2°) over a scattering angle range of 50°–110° using a photomultiplier coupled with a turntable. The scattering angle of the acquired vertically and horizontally polarized scattered light were corrected to eliminate the scattering angle deviations caused by obliquely incident light, and then the polarization difference in the vertically and horizontally polarized scattered light was computed, from which the submicron particle size distribution was inverted subsequently. Experiments were performed using polystyrene microsphere standard particles with particle sizes of 350 nm, 200 nm, and 100 nm. The experimental results show that (1) the Pearson correlation coefficient of the linearly fitted curve of the corrected polarization difference to the theoretical polarization difference is larger than 0.997, and the slope and intercept of the linearly fitted curve are, respectively, close to 1 and 0, indicating that the corrected polarization difference is highly consistent with the theoretical polarization difference; (2) the mean relative error and coefficient of variation of the particle size distribution parameter D50 obtained from the polarization difference with high angular resolution (angular separation = 2°) are better than those of the parameter D50 obtained from the polarization difference with low angular resolution (angular separation = 12°), indicating better accuracy and repeatability of the particle size distribution inverted from the polarization difference with high angular resolution; and (3) for the particle size distribution parameters D10, D50, and D90 obtained from the scattering angle-corrected polarization difference with high angular resolution, the deviation of the measured values from the average value are all smaller than the thresholds given in the international standard, indicating a good repeatability of the proposed method.