Background Clutter Research Articles

Patient activity recognition for robust performance under varied illumination and cluttered background in indoor environment

Human Activity Recognition (HAR) holds significant importance in health and human-machine interaction. However, recognizing actions from 2D information faces challenges like occlusion, illumination variation, cluttered backgrounds, and view invariance. These hurdles are particularly pronounced in indoor patient monitoring settings due to fluctuating lighting conditions and cluttered backgrounds, which compromise the accuracy of activity recognition systems. A new architecture named illuminationRevive has been proposed to tackle this issue. Which utilizes an encoder-decoder convolutional neural network and image post-processing blocks to enhance the image's visual appearance. A new dataset comprising seven indoor physical activities has been proposed, created with contributions from thirty individuals aged 20 to 45. A hybrid fusion architecture is proposed to classify activities, integrating motion sequence information and body joint features. The proposed classification model incorporates generated Skeleton Motion History Images (SMHIs), collected human joint motion features from video frames, and novel kinematic and geometric features within window frames as inputs. The model can extract spatial and temporal feature vectors by integrating ResNet50-ViT (Residual Network-50 layers, Vision Transformer) and CNN-BiLSTM (Convolutional Neural Network-Bidirectional Long Short-Term Memory) layers. The suggested classification model was evaluated alongside state-of-the-art models using the LNMIIT-SMD (The LNM Institute of Information Technology-Skelton Motion Dataset) and established NTU-RGBD (Nanyang Technological University's Red Blue Green and Depth information) dataset. The evaluation aimed to assess the effectiveness of the proposed classification model architecture. Results demonstrate the superiority of the proposed model, achieving impressive accuracies of 98.21% on real-time data, 98.45% on the proposed dataset, and 97.12% on the NTU-RGBD dataset.

Framework for abnormal event detection and tracking based on effective sparse factorization strategy

The idea of tracking video objects has evolved to facilitate the area of surveillance systems. However, most current research efforts lie in speedy abnormal event detection and tracking of objects of interest tracking. However, the primary challenge is dealing with complex video structures' inherent redundancy. The existing research models for video tracking are more inclined towards improving accuracy. In contrast, the consideration of a more significant proportion of mobile object dynamics, e.g. abnormal events, in motion over the crowded video frame sequence is mainly overlooked, which is essential to study a specific movement pattern of the object of interest appearing in the frame sequence concerning the cost of computation factors. The study thereby introduces a unique strategy of speedy abnormal event detection and tracking, which facilitates video tracking to assess a specific pattern of object of interest movement over complex and crowded video scenes, considering a unique learning-based approach. The extensive simulation outcome further shows that the proposed tracking model accomplishes better tracking accuracy yet retains an optimized computation cost compared to the baseline studies. The computation of video tracking also accomplishes higher detection rates even in the challenging constraints of partial/complete occlusion, illumination variation and background clutter.

Revolutionizing agricultural efficiency with advanced coconut harvesting automation

<span style="vertical-align: inherit;"><span style="vertical-align: inherit;">The precision coconut harvesting system aims to develop an efficient system for accurately detecting coconuts in agricultural landscapes using advanced image processing techniques. Coconut cultivation is vital to many tropical economies and precise monitoring is essential for optimizing yield and resource utilization. Traditional methods of coconut detection are labor-intensive and time-consuming. The proposed computer vision-based approach automates and enhances coconut detection by analyzing high-resolution images of coconut plantations. Pre-processing techniques improve image quality and object detection algorithms such as convolutional neural networks (CNNs) identify coconut clusters. Challenges like lighting variations and background clutter are addressed using feature extraction and pattern recognition. A user-friendly interface visualizes detection results, aiding farmers in timely decision-making. Extensive testing on diverse datasets evaluates system effectiveness. This model aims to advance precision agriculture, enhancing productivity and informing coconut farmers' decision-making processes. Using a CNN model, the accuracy of coconut detection based on its ripeness was 98.8%.</span></span>

Moving ships detection via the trajectory feature extraction from spatiotemporal slices of infrared maritime videos

In practical application scenarios, maritime infrared videosoften contain different types of sea state scenes, weather conditions, shooting time, shooting distance, etc. In these different types of maritime videos, ship targets have great differences in size, grayscaledistribution and contrast, which brings difficulties to ship target detection.At the same time, the diversity of fluctuation, grayscale distribution and reflected light of the sea surface will bring unpredictable interference noise to ship target detection.How to accurately detect ship targets in complex and changeable maritime infrared videos is a challenging task and research focus.The key to achieving accurate ship detection is to extract robust target features that can effectively distinguish targets from all thebackground noises.In this paper, a novel infrared video ship target detection algorithm based on spatiotemporal slice target trajectory features extraction is proposed. The algorithm is very sensitive to real targets and has excellentanti-noise ability.The main innovation of the algorithm is to extract the target trajectory feature from the spatiotemporal slice of the sequence image and generate the trajectory feature map.We use the trajectory texture formed by the ship target in the spatiotemporal slice to extract the target feature, which can greatly suppress the background noise.The adaptive dilation linear model algorithm can effectively detect the target trajectory line in the spatiotemporal slice. In addition, we also make full use of the gradient of the target trajectory line to distinguish different target trajectory pixels, and propose an adaptive iterative dilation target region localization algorithm combined with gradient consistency.For object segmentation, we calculate the segmentation double-threshold using the adjacent surrounding background pixels of the target, so as to achievetarget segmentationof multiple grayscaledistribution types. Finally, in the comparison experiment, our algorithm shows superior target detection performance, especially when detecting ships from a large number of highlighted sea clutter background, the robust anti-noise ability of the algorithm can be highlighted.

Multitarget CFAR Detection Method Based on Neural Network for HF Hybrid Sky-Surface Wave Radar in Weibull Clutter Background

Multitarget CFAR Detection Method Based on Neural Network for HF Hybrid Sky-Surface Wave Radar in Weibull Clutter Background

Person re-identification transformer with patch attention and pruning

Person re-identification (Re-ID), which is widely used in surveillance and tracking systems, aims to search individuals as they move between different camera views by maintaining identity across various camera views. In the realm of person re-identification (Re-ID), recent advancements have introduced convolutional neural networks (CNNs) and vision transformers (ViTs) as promising solutions. While CNN-based methods excel in local feature extraction, ViTs have emerged as effective alternatives to CNN-based person Re-ID, offering the ability to capture long-range dependencies through multi-head self-attention without relying on convolution and downsampling. However, it still faces challenges such as changes in illumination, viewpoint, pose, low resolutions, and partial occlusions. To address the limitations of widely used person Re-ID datasets and improve the generalization, we present a novel person Re-ID method that enhances global and local information interactions using self-attention modules within a ViT network. It leverages dynamic pruning to extract and prioritize essential image patches effectively. The designed patch selection and pruning for person Re-ID model resulted in a robust feature extractor even in scenarios with partial occlusion, background clutter, and illumination variations. Empirical validation demonstrates its superior performance compared to previous approaches and its adaptability across various domains.

Ground moving target indication of polarimetric interferometric synthetic aperture radar using joint scattering vector

AbstractGround moving target indication (GMTI) plays a critical role in both civilian applications and military applications. The accuracy of complex images coregistration is a major factor for multichannel synthetic aperture radar (SAR) GMTI. Moreover, polarimetric interferometric SAR (PolInSAR) represents a growing strength in multi‐function radar systems. In response to this, we propose a new SAR‐GMTI approach tailored for the PolInSAR system. To address the deterioration in clutter suppression performance caused by the coregistration errors, we construct a joint scattering vector (JSV) for polarimetric SAR (PolSAR) by incorporating the neighbouring vectors of the central pixel. Subsequently, the covariance matrix of JSV is estimated and subjected to eigen‐decomposed. Clutter suppression of the PolInSAR system for GMTI is performed using eigen‐subspace projection, where the JSV is projected onto noise subspace. This method is robust against coregistration errors since all ground moving target information is encapsulated within the JSV. Furthermore, the improvement factors with different clutter backgrounds (by changing the signal‐to‐clutter‐plus‐noise‐ratio, SCNR) are analysed. The effectiveness of the proposed JSV‐based method is validated using simulated PolInSAR data.

Adaptive polarimetric persymmetric detection for distributed subspace targets in lognormal texture clutter

In this paper, the adaptive polarimetric persymmetric detection for distributed subspace targets under the background of compound Gaussian clutter is investigated, where the compound Gaussian clutter exhibits texture that follows a lognormal distribution. Based on the two-step Generalized Likelihood Ratio Test (2S GLRT), two-step maximum a posteriori Generalized Likelihood Ratio Test (2S MAP GLRT), two-step Rao (2S Rao) test and two-step Wald (2S Wald) test, we have proposed four polarimetric persymmetric detectors. Initially, we model the target echo as a distributed subspace signal, assuming known clutter texture and polarization speckle covariance matrix (PSCM), and derive the corresponding test statistics. Then, the estimation of the lognormal texture is obtained through maximum a posteriori (MAP). Conventionally, a set of secondary data, which share the same PSCM as the cells under test (CUTs), is assumed to participate in the estimation of the PSCM, leveraging its inherent persymmetric property during the estimation process. Finally, the estimated values are substituted into the proposed test statistics to obtain fully adaptive polarimetric persymmetric detectors. Numerical experimental results using simulated data and measured sea clutter data demonstrate that the proposed four adaptive polarimetric persymmetric detectors exhibit a constant false alarm rate (CFAR) characteristic relative to the PSCM and satisfactory detection performance for distributed subspace targets.

I-DINO: High-Quality Object Detection for Indoor Scenes

Object Detection in Complex Indoor Scenes is designed to identify and categorize objects in indoor settings, with applications in areas such as smart homes, security surveillance, and home service robots. It forms the basis for advanced visual tasks including visual question answering, video description generation, and instance segmentation. Nonetheless, the task faces substantial hurdles due to background clutter, overlapping objects, and significant size differences. To tackle these challenges, this study introduces an indoor object detection approach utilizing an enhanced DINO framework. To cater to the needs of indoor object detection, an Indoor-COCO dataset was developed from the COCO object detection dataset. The model incorporates an advanced Res2net as the backbone feature extraction network, complemented by a deformable attention mechanism to better capture detailed object features. An upgraded Bi-FPN module is employed to replace the conventional feature fusion module, and SIoU loss is utilized to expedite convergence. The experimental outcomes indicate that the refined model attains an mAP of 62.3%, marking a 5.2% improvement over the baseline model. These findings illustrate that the DINO-based indoor object detection model exhibits robust generalization abilities and practical utility for multi-scale object detection in complex environments.

Adaptive Granularity-Fused Keypoint Detection for 6D Pose Estimation of Space Targets

Estimating the 6D pose of a space target is an intricate task due to factors such as occlusions, changes in visual appearance, and background clutter. Accurate pose determination requires robust algorithms capable of handling these complexities while maintaining reliability under various environmental conditions. Conventional pose estimation for space targets unfolds in two stages: establishing 2D–3D correspondences using keypoint detection networks and 3D models, followed by pose estimation via the perspective-n-point algorithm. The accuracy of this process hinges critically on the initial keypoint detection, which is currently limited by predominantly singular-scale detection techniques and fails to exploit sufficient information. To tackle the aforementioned challenges, we propose an adaptive dual-stream aggregation network (ADSAN), which enables the learning of finer local representations and the acquisition of abundant spatial and semantic information by merging features from both inter-layer and intra-layer perspectives through a multi-grained approach, consolidating features within individual layers and amplifying the interaction of distinct resolution features between layers. Furthermore, our ADSAN implements the selective keypoint focus module (SKFM) algorithm to alleviate problems caused by partial occlusions and viewpoint alterations. This mechanism places greater emphasis on the most challenging keypoints, ensuring the network prioritizes and optimizes its learning around these critical points. Benefiting from the finer and more robust information of space objects extracted by the ADSAN and SKFM, our method surpasses the SOTA method PoET (5.8°, 8.1°/0.0351%, 0.0744%) by 0.5°, 0.9°, and 0.0084%, 0.0354%, achieving 5.3°, 7.2° in rotation angle errors and 0.0267%, 0.0390% in normalized translation errors on the Speed and SwissCube datasets, respectively.

Text Detection on Industrial Barrel Label with Convolutional Attention and Dual‐Branch Feature Network

Industrial barrel labels generally have low visual contrast, uneven lighting, and cluttered background, making it challenging to accurately locate text regions. This paper proposes a text detection network to solve the inaccurate localization problem based on DBNet. First, a convolutional attention mechanism is applied to the feature extraction network to get more valuable text feature maps. Then, a dual‐branch convolutional feature module is proposed in the feature pyramid to enrich contextual information. Besides, during the probability map generation stage, using a feature remodeling enhancement module to further distinguish text and text boundaries. This paper designs comparative experiments on ILTD, ICDAR2015 and MSRA‐TD500 datasets, achieve F‐measure of 92.3%, 86.0% and 84.1%, which are 2.2%, 2.3%, and 1.9% higher than DBNet, respectively. They demonstrate that our proposed method exhibits competitive performance and strong robustness. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Morphology-Based Feature Extraction Network for Arbitrary-Oriented SAR Vehicle Detection

In recent years, synthetic aperture radar (SAR) vehicle detection has become a research hotspot. However, algorithms using horizontal bounding boxes can lead to redundant detection areas due to the varying aspect ratio and arbitrary orientation of vehicle targets. This paper proposes a morphology-based feature extraction network (MFE-Net), which fully uses the prior shape knowledge of the vehicle targets. Specifically, we adopt rotatable bounding boxes to predict the targets, and a novel rectangular rotation-invariant coordinate convolution (RRICC) is proposed to extract the feature, which can determine more accurately the convolutional sampling location of the vehicles. The adaptive thresholding denoising module (ATDM) is designed to suppress background clutter. Furthermore, inspired by the convolutional neural networks (CNNs) and self-attention, we propose the hybrid representation enhancement module (HREM) to highlight the vehicle target features. The experiment results show that the proposed model obtains an average precision (AP) of 93.1% on the SAR vehicle detection data set (SVDD).

Advanced Object Tracking through Conditional Online Updates and Noise Suppression

Object tracking under complex environmental conditions, such as background clutter, occlusion, and rapid motion, presents significant challenges. This paper addresses these issues by proposing a tracking algorithm integrating background suppression, target region enhancement, and an adaptive online template update mechanism to improve tracking accuracy. The proposed method uses the initial bounding box of the target object as a reference template and selectively updates specific regions online to suppress noise and retain critical features. We evaluated the proposed method using the OTB dataset to validate it. The baseline model without the proposed method showed a success rate of 0.417 and a precision of 0.586, while the algorithm with the proposed method achieved improved values of 0.524 and 0.728, respectively. Qualitative evaluations further confirmed the robustness of the proposed method, demonstrating high performance in scenarios with occlusion and complex backgrounds. Rather than updating all regions indiscriminately, the proposed method selectively updates the template using representative values from the target object's information. This selective update mechanism ensures the incorporation of the most relevant and accurate features, enabling the algorithm to adapt to changes in the target's appearance while minimizing noise integration. Emphasizing the feature regions and suppressing noise are also critical for maintaining a clear and precise representation of the target object, reducing the likelihood of confusion by irrelevant background information. Future research will focus on developing balanced update strategies that integrate new information while maintaining stable and reliable target characteristics.

Underwater Small Target Classification Using Sparse Multi-View Discriminant Analysis and the Invariant Scattering Transform

Sonar automatic target recognition (ATR) systems suffer from complex acoustic scattering, background clutter, and waveguide effects that are ever-present in the ocean. Traditional signal processing techniques often struggle to distinguish targets when noise and complicated target geometries are introduced. Recent advancements in machine learning and wavelet theory offer promising directions for extracting informative features from sonar return data. This work introduces a feature extraction and dimensionality reduction technique using the invariant scattering transform and Sparse Multi-view Discriminant Analysis for identifying highly informative features in the PONDEX09/PONDEX10 datasets. The extracted features are used to train a support vector machine classifier that achieves an average classification accuracy of 97.3% using six unique targets.

Robust Truncated Statistics Constant False Alarm Rate Detection of UAVs Based on Neural Networks

With the rapid popularity of unmanned aerial vehicles (UAVs), airspace safety is facing tougher challenges, especially for the identification of non-cooperative target UAVs. As a vital approach for non-cooperative target identification, radar signal processing has attracted continuous and extensive attention and research. The constant false alarm rate (CFAR) detector is widely used in most current radar systems. However, the detection performance will sharply deteriorate in complex and dynamical environments. In this paper, a novel truncated statistics- and neural network-based CFAR (TSNN-CFAR) algorithm is developed. Specifically, we adopt a right truncated Rayleigh distribution model combined with the characteristics of pattern recognition using a neural network. In the simulation environments of four different backgrounds, the proposed algorithm does not need guard cells and outperforms the traditional mean level (ML) and ordered statistics (OS) CFAR algorithms. Especially in high-density target and clutter edge environments, since utilizing 19 statistics obtained from the numerical calculation of two reference windows as the input characteristics, the TSNN-CFAR algorithm has the best adaptive decision ability, accurate background clutter modeling, stable false alarm regulation property and superior detection performance.

Performance analysis of mean level CFAR detectors in homogeneous gamma-distributed radar clutter

ABSTRACT In this paper, a novel and exact mathematical formulation of three mean level constant false alarm rate (CFAR) detectors has been developed considering a homogeneous gamma-distributed (GM) clutter. These detectors include the cell averaging (CA), the greatest-of (GO), and the smallest-of (SO)-CFAR detection schemes. To do so, we derived closed-form expressions for the probability density function (pdf), and the cumulative distribution function (cdf) of the sum of an exponential fluctuating target submerged in gamma-distributed sea clutter. Then, we developed exact and explicit expressions for the probability of false alarm (P fa ) and probability of detection (P d ) of the optimal fixed threshold detector and the three considered CFAR detectors. The correctness of our expressions is then examined and validated via numerical simulations. Assuming a homogeneous GM background, the detection performance of these three detectors is carried out, discussed, and compared with that of the optimal detector. Experimental results with Sentinel-1 synthetic aperture radar (SAR) data demonstrate the effectiveness of the proposed closed-form expressions and show that the considered CFAR schemes are efficient for ship detection in sea clutter backgrounds.

Grayscale Iterative Star Spot Extraction Algorithm Based on Image Entropy

Star trackers are susceptible to interference from stray light, such as sunlight, moonlight, and Earth atmosphere light, in the space environment, resulting in an overall improvement in the star image grayscale, poor background uniformity, low star extraction rate, and high number of false star spots. In response to these challenges, this paper proposes a grayscale iterative star spot extraction algorithm based on image entropy. The implementation of the algorithm is mainly divided into two steps: (1) The algorithm conducts multiple grayscale iterations, effectively utilizing the prior information on the local contrast of star spots to filter out stray light backgrounds to a certain extent. (2) By establishing an inner–outer template, the image entropy algorithm is employed to obtain the real star targets to be extracted, which further suppresses the background clutter and noise. Numerical simulations and experimental results demonstrate that, compared to traditional detection algorithms, this algorithm can effectively suppress background stray light, enhance star extraction rates, and reduce the number of false star spots, and it exhibits superior detection performance in complex backgrounds across various scenarios.

A multiple x-ray-source array (MXA) system with a planar two-dimensional source distribution for digital breast tomosynthesis.

Digital breast tomosynthesis (DBT) has outpaced digital mammography in clinical adoption in the United States; however, substantial technological limitations remain to image quality in DBT, including undersampling from a one-dimensional (1D) scan geometry, x-ray source motion during acquisition, and patient motion artifacts from long exam times. A thermionic cathode x-ray system employing two-dimensional (2D, planar) multiple x-ray-source arrays (MXA) is proposed to improve DBT image quality. A 1D MXA, consisting of a linear array of thermionic cathodes was used to simulate a 2D MXA. The 1D MXA included 11 focal spots separated by a distance of =23mm. The 11 cathodes were paired with 11 molybdenum 50mm diameter anode disks, mounted on a rotating shaft within a single vacuum enclosure. Image quality was investigated as a function of MXA configuration by integrating the 1D MXA with a 200 × 250 mm2 flat panel detector at a source-to-detector distance of 630mm, resulting in a 20° tomographic arc. To simulate a 2D MXA, the detector (with phantom) was translated orthogonally to the linear array by a distance ( ) ranging from =0mm (conventional 1D) to =57mm. All sources operated at 30kV with 80mA and 4.5 mAs/pulse, yielding ∼100 mAs per DBT dataset. DBT reconstructions involved 22 projections and used filtered backprojection with a ramp and Hann apodization filter. Volumetric reconstructions for each source were weighted by sampling differences between sources, and averaged. Image quality was assessed in terms of contrast-to-noise ratio (CNR), background clutter noise and power spectrum, and slice sensitivity profile (SSP) using a set of physical phantoms, including: (i) contrast-detail signals coupled to spherical clutter (PMMA in air); (ii) an SSP phantom; (iii) a commercial "breast" phantom (CIRS BR3D, Sun Nuclear, Norfolk, VA); and (iv) bovine muscle. Background clutter noise amplitude reduced monotonically from the 1D MXA (σclutter=5.9 A.U., =0mm) and 2D MXA arrays with increasing , with statistical significance between the 1D MXA and 2D MXA with =57mm (σclutter=5.0 A.U., p<0.001). The contrast-detail/clutter phantom demonstrated CNR from the 2D MXA (δ=57mm) outperforming the 1D MXA in all combinations of contrast and detail. 2D power spectrum analysis of clutter demonstrated a pronounced Fourier domain null cone for the 1D MXA in the anterior field-of-view (away from the 1D MXA position), whereas the 2D MXA geometry (δ=57mm) did not exhibit the null cone. The SSP was 15%-50% narrower (FWHM) for the 2D versus the 1D geometry, across all reconstruction setups. The advantages of a 2D source geometry for DBT imaging were demonstrated quantitatively compared to a conventional 1D line of x-ray sources. The improvement in the 2D geometry was attributed both to improved Fourier domain sampling and reduced SSP. We conclude that 2D MXA sources have the potential to substantially improve DBT imaging in comparison to existing commercial DBT systems.

Marine Radar Constant False Alarm Rate Detection in Generalized Extreme Value Distribution Based on Space-Time Adaptive Filtering Clutter Statistical Analysis

The performance of marine radar constant false alarm rate (CFAR) detection method is significantly influenced by the modeling of sea clutter distribution and detector decision rules. The false alarm rate and detection rate are therefore unstable. In order to address low CFAR detection performance and the modeling problem of non-uniform, non-Gaussian, and non-stationary sea clutter distribution in marine radar images, in this paper, a CFAR detection method in generalized extreme value distribution modeling based on marine radar space-time filtering background clutter is proposed. Initially, three-dimensional (3D) frequency wave-number (space-time) domain adaptive filter is employed to filter the original radar image, so as to obtain uniform and stable background clutter. Subsequently, generalized extreme value (GEV) distribution is introduced to integrally model the filtered background clutter. Finally, Inclusion/Exclusion (IE) with the best performance under the GEV distribution is selected as the clutter range profile CFAR (CRP-CFAR) detector decision rule in the final detection. The proposed method is verified by utilizing real marine radar image data. The results indicate that when the Pfa is set at 0.0001, the proposed method exhibits an average improvement in PD of 2.3% compared to STAF-RCBD-CFAR, and a 6.2% improvement compared to STCS-WL-CFAR. When the Pfa is set at 0.001, the proposed method exhibits an average improvement in PD of 6.9% compared to STAF-RCBD-CFAR, and a 9.6% improvement compared to STCS-WL-CFAR.

Road target recognition based on radar range-Doppler spectrum with GS – ResNet

ABSTRACT Road target recognition ability of automotive millimetre-wave (mmWave) radar is crucial in areas such as autonomous driving, advanced driver assistance systems (ADAS), and automated emergency braking systems (AEBS). Current mmWave radar systems are primarily utilized for speed, distance, and angle measurements, with limited capability or unsatisfactory performance in target classification. In response to this limitation, this paper proposes a novel method for road target recognition, using radar range-Doppler spectrum as input data and introducing a global attention mechanism and SCConv module. First, the range-Doppler spectrum is processed by the clutter removal algorithm block to remove background clutter and vibration interference. Second, considering the small features and susceptibility to noise interference in the range-Doppler spectrum, we have devised a deep residual network based on a global attention mechanism, significantly enhancing the model’s accuracy in range-Doppler spectrum classification. Finally, we introduce the SCConv module and improve the downsampling module in ResNet to enhance the model’s classification accuracy. Experimental results demonstrate that the model achieves an average accuracy of 99.79% in classifying six types of road targets, significantly outperforming other methods. This research is of significant importance in advancing the understanding of road traffic conditions by autonomous driving systems and enhancing system safety.