Inaccurate Localization Research Articles

Flame Recognition and Location Algorithm based on YOLO v5s and Binocular Vision

Abstract An improved YOLO v5s framework in conjunction with binocular vision is developed to fulfill the stringent requirements for precise identification and accurate localization of flames. An Efficient Multi-scale Attention (EMA) mechanism is seamlessly integrated into the backbone network of the YOLO v5s model, thereby significantly improving the capacity to focus on and interpret critical target features. To bolster the multi-scale feature fusion capability, the Bidirectional Feature Pyramid Network (BiFPN) is strategically introduced at the fusion layer within the object detection architecture. The Semi-Global Block Matching (SGBM) algorithm is deployed to synchronize the binocular images, complemented by the least squares curve fitting method to adjust location inaccuracies, enhancing the precision of flame positioning. A binocular vision system is meticulously constructed to facilitate a series of rigorous experiments on flame detection and location. The experimental results demonstrate that the improved YOLO v5s network model achieves an exceptional flame recognition rate of 96.25%, which represents a noteworthy increase of 0.98% in accuracy in comparison to the original YOLO v5s model. Additionally, within a distance range of 3 to 10 meters, the flame ranging error is consistently less than 0.1 meters, successfully realizing the objective of high-precision flame detection and localization.

A Feature-Enhanced Small Object Detection Algorithm Based on Attention Mechanism.

With the rapid development of AI algorithms and computational power, object recognition based on deep learning frameworks has become a major research direction in computer vision. UAVs equipped with object detection systems are increasingly used in fields like smart transportation, disaster warning, and emergency rescue. However, due to factors such as the environment, lighting, altitude, and angle, UAV images face challenges like small object sizes, high object density, and significant background interference, making object detection tasks difficult. To address these issues, we use YOLOv8s as the basic framework and introduce a multi-level feature fusion algorithm. Additionally, we design an attention mechanism that links distant pixels to improve small object feature extraction. To address missed detections and inaccurate localization, we replace the detection head with a dynamic head, allowing the model to route objects to the appropriate head for final output. We also introduce Slideloss to improve the model's learning of difficult samples and ShapeIoU to better account for the shape and scale of bounding boxes. Experiments on datasets like VisDrone2019 show that our method improves accuracy by nearly 10% and recall by about 11% compared to the baseline. Additionally, on the AI-TODv1.5 dataset, our method improves the mAP50 from 38.8 to 45.2.

DCFE-YOLO: A novel fabric defect detection method.

Accurate detection of fabric defects is crucial for quality control in the textile industry. However, the task of fabric defect detection remains highly challenging due to the complex textures and diverse defect patterns. To address the issues of inaccurate localization and false positives caused by complex textures and varying defect sizes, this paper proposes an improved YOLOv8-based fabric defect detection method. First, Dynamic Snake Convolution is introduced into the backbone network to enhance sensitivity to elongated and subtle defects, improving the extraction of edge and texture details. Second, a Channel Priority Convolutional Attention mechanism is incorporated after the Spatial Pyramid Pooling layer to enable more precise defect localization by leveraging multi-scale structures and channel priors. Finally, the feature fusion network integrates Partial Convolution and Efficient Multi-scale Attention, optimizing the fusion of information across different feature levels and spatial scales, which enhances the richness and accuracy of feature representations while reducing computational complexity. Experimental results demonstrate a significant improvement in detection performance. Specifically, mAP@0.5 increased by 2.9%, precision improved by 3.5%, and mAP@0.5:0.95 rose by 2.3%, highlighting the model's superior capability in detecting complex defects. The project is available at https://github.com/lilian998/fabric.

LittleFaceNet: A Small-Sized Face Recognition Method Based on RetinaFace and AdaFace.

For surveillance video management in university laboratories, issues such as occlusion and low-resolution face capture often arise. Traditional face recognition algorithms are typically static and rely heavily on clear images, resulting in inaccurate recognition for low-resolution, small-sized faces. To address the challenges of occlusion and low-resolution person identification, this paper proposes a new face recognition framework by reconstructing Retinaface-Resnet and combining it with Quality-Adaptive Margin (adaface). Currently, although there are many target detection algorithms, they all require a large amount of data for training. However, datasets for low-resolution face detection are scarce, leading to poor detection performance of the models. This paper aims to solve Retinaface's weak face recognition capability in low-resolution scenarios and its potential inaccuracies in face bounding box localization when faces are at extreme angles or partially occluded. To this end, Spatial Depth-wise Separable Convolutions are introduced. Retinaface-Resnet is designed for face detection and localization, while adaface is employed to address low-resolution face recognition by using feature norm approximation to estimate image quality and applying an adaptive margin function. Additionally, a multi-object tracking algorithm is used to solve the problem of moving occlusion. Experimental results demonstrate significant improvements, achieving an accuracy of 96.12% on the WiderFace dataset and a recognition accuracy of 84.36% in practical laboratory applications.

The Practical Implications of Re-Referencing in ERP Studies: The Case of N400 in the Picture-Word Verification Task.

Background: The selection of an optimal referencing method in event-related potential (ERP) research has been a long-standing debate, as it can significantly influence results and lead to data misinterpretation. Such misinterpretation can produce flawed scientific conclusions, like the inaccurate localization of neural processes, and in practical applications, such as using ERPs as biomarkers in medicine, it may result in incorrect diagnoses or ineffective treatments. In line with the development and advancement of good scientific practice (GSP) in ERP research, this study sought to address several questions regarding the most suitable digital reference for investigating the N400 ERP component. Methods: The study was conducted on 17 neurotypical participants. Based on previous research, the references evaluated included the common average reference (AVE), mean earlobe reference (EARS), left mastoid reference (L), mean mastoids reference (MM), neutral infinity reference (REST), and vertex reference (VERT). Results: The results showed that all digital references, except for VERT, successfully elicited the centroparietal N400 effect in the picture-word verification task. The AVE referencing method showed the most optimal set of metrics in terms of effect size and localization, although it also produced the smallest difference waves. The most similar topographic dynamics in the N400 window were observed between the AVE and REST referencing methods. Conclusions: As the most optimal regions of interest (ROI) for the picture-word elicited N400 effect, nine electrode sites spanning from superior frontocentral to parietal regions were identified, showing consistent effects across all referencing methods except VERT.

A study on UAV target detection and 3D positioning methods based on the improved deformable DETR model and multi-view geometry

This paper addresses critical challenges in Unmanned Aerial Vehicle (UAV) target detection and 3D positioning, specifically inaccuracies in localization and lack of robustness in complex environments. The objective of this research is to improve UAV detection and positioning accuracy by proposing an enhanced Deformable DETR (Detection Transformer) model integrated with multi-view geometry theory. To achieve this, the study first preprocesses UAV-collected data, then optimizes the convolutional layers of the original DETR model to better handle object occlusion and scale variations. Furthermore, the research incorporates multi-view geometric modeling and multimodal fusion strategies to enhance detection accuracy during the target recognition process. Experimental results demonstrate that the proposed approach achieves over 70% detection accuracy, significantly outperforming traditional methods. The findings underscore the effectiveness of combining the improved Deformable DETR model with multi-view geometry for high-precision detection and 3D localization in complex environments. This research has significant implications for UAV-based applications, such as autonomous navigation, surveillance, and search-and-rescue missions, where precise target detection and 3D positioning are critical for successful operation.

A computed tomography-based evaluation and comparison of ganglionated plexus targeting techniques for cardioneuroablation.

Cardioneuroablation (CNA) targets the ganglionated plexus (GP) to treat neurally mediated syncope, yet a standardized GP identification method is lacking. Postprocessing of cardiac computed tomography (CT) data identifies epicardial fat, thus allowing fat pad identification. Whereas the feasibility of CT-guided CNA is documented, data about GP anatomy and comprehensive evaluations of GP targeting methods remain scarce. This study sought to describe GP anatomy using CT fat pad segmentation and to evaluate the accuracy of different approaches in locating these GPs. The study included 26 CNA or atrial fibrillation ablation patients. GPs were identified through CT-based fat segmentation. CT-derived atrial meshes were merged with corresponding meshes from electroanatomic mapping. Spatial correlation was studied between atrial fractionated electrograms (FEGMs) and epicardial fat pads. Several target areas from the different ablation approaches (FEGM, anatomic, CT-based fat pad identification, and target line) were spatially compared. Correlation between epicardial fat pads and signal fragmentation was weak in the left atrium (ρ = 0.01 ± 0.13 [P=.73]; φ = -0.00 ± 0.10 [P = .94]) and even negative in the right atrium (ρ = 0.11 ± 0.09 [P < .001]; φ = -0.10 ± 0.08 [P< .001]). The FEGM approach was associated with a more extensive ablation area (3.74% vs 17.0% [P < .001] for the anatomic and the FEGM approach for the left atrium and 3.45% vs 9.53% [P < .001] for the anatomic and the FEGM approach for the right atrium). CT-based fat pad segmentation reveals significant interpatient variability in GP anatomy. GPs show low colocalization with signal fragmentation, causing inaccurate localization based on fragmentation alone. An anatomy-focused approach offers a more targeted ablation strategy.

Research on coal gangue recognition method based on SFD-YOLOv5s

ABSTRACT Aiming at the current coal gangue recognition model’s difficulty in recognizing aggregated coal gangue targets, which leads to the problems of misdetections, omissions, and inaccurate localization, we propose a coal gangue recognition method based on the SFD-YOLOv5s model. The SE attention mechanism is improved in incorporating maximum pooling and introduced into the backbone network of the YOLOv5s model to improve the model’s ability to extract the critical feature information of the coal gangue. Furthermore, to improve the recognition ability of the YOLOv5s model for aggregated targets, we introduce the Focal-EIoU loss function and the Dyhead. The experimental results show that the overall performance of the SFD-YOLOv5s model has surpassed other mainstream object detection models of the YOLO series. The SFD-YOLOv5s model has the highest precision, recall, and mean average precision. The precision reaches 97.9%, the recall is 96.2%, and the mean average precision is 94.5%, which is 8.7%, 8.9%, and 9.0% higher compared with the YOLOv5s model, respectively. The FPS is 96.15, which can fully meet the demand for real-time detection of coal gangue. Meanwhile, the SFD-YOLOv5s model has the best recognition effect of aggregated coal gangue targets.

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.

GSEditPro: 3D Gaussian Splatting Editing with Attention‐based Progressive Localization

AbstractWith the emergence of large‐scale Text‐to‐Image(T2I) models and implicit 3D representations like Neural Radiance Fields (NeRF), many text‐driven generative editing methods based on NeRF have appeared. However, the implicit encoding of geometric and textural information poses challenges in accurately locating and controlling objects during editing. Recently, significant advancements have been made in the editing methods of 3D Gaussian Splatting, a real‐time rendering technology that relies on explicit representation. However, these methods still suffer from issues including inaccurate localization and limited manipulation over editing. To tackle these challenges, we propose GSEditPro, a novel 3D scene editing framework which allows users to perform various creative and precise editing using text prompts only. Leveraging the explicit nature of the 3D Gaussian distribution, we introduce an attention‐based progressive localization module to add semantic labels to each Gaussian during rendering. This enables precise localization on editing areas by classifying Gaussians based on their relevance to the editing prompts derived from cross‐attention layers of the T2I model. Furthermore, we present an innovative editing optimization method based on 3D Gaussian Splatting, obtaining stable and refined editing results through the guidance of Score Distillation Sampling and pseudo ground truth. We prove the efficacy of our method through extensive experiments.

Investigating the effect of template head models on Event-Related Potential source localization: a simulation and real-data study.

Event-Related Potentials (ERPs) are valuable for studying brain activity with millisecond-level temporal resolution. While the temporal resolution of this technique is excellent, the spatial resolution is limited. Source localization aims to identify the brain regions generating the EEG data, thus increasing the spatial resolution, but its accuracy depends heavily on the head model used. This study compares the performance of subject-specific and template-based head models in both simulated and real-world ERP localization tasks. Simulated data mimicking realistic ERPs was created to evaluate the impact of head model choice systematically, after which subject-specific and template-based head models were used for the reconstruction of the data. The different modeling approaches were also applied to a face recognition dataset. The results indicate that the template models capture the simulated activity less accurately, producing more spurious sources and identifying less true sources correctly. Furthermore, the results show that while creating more accurate and detailed head models is beneficial for the localization accuracy when using subject-specific head models, this is less the case for template head models. The main N170 source of the face recognition dataset was correctly localized to the fusiform gyrus, a known face processing area, using the subject-specific models. Apart from the fusiform gyrus, the template models also reconstructed several other sources, illustrating the localization inaccuracies. While template models allow researchers to investigate the neural generators of ERP components when no subject-specific MRIs are available, it could lead to misinterpretations. Therefore, it is important to consider a priori knowledge and hypotheses when interpreting results obtained with template head models, acknowledging potential localization errors.

EFMF-pillars: 3D object detection based on enhanced features and multi-scale fusion

As unmanned vehicle technology advances rapidly, obstacle recognition and target detection are crucial links, which directly affect the driving safety and efficiency of unmanned vehicles. In response to the inaccurate localization of small targets such as pedestrians in current object detection tasks and the problem of losing local features in the PointPillars, this paper proposes a three-dimensional object detection method based on improved PointPillars. Firstly, addressing the issue of lost spatial and local information in the PointPillars, the feature encoding part of the PointPillars is improved, and a new pillar feature enhancement extraction module, CSM-Module, is proposed. Channel encoding and spatial encoding are introduced in the new pillar feature enhancement extraction module, fully considering the spatial information and local detailed geometric information of each pillar, thereby enhancing the feature representation capability of each pillar. Secondly, based on the fusion of CSPDarknet and SENet, a new backbone network CSE-Net is designed in this paper, enabling the extraction of rich contextual semantic information and multi-scale global features, thereby enhancing the feature extraction capability. Our method achieves higher detection accuracy when validated on the KITTI dataset. Compared to the original network, the improved algorithm’s average detection accuracy is increased by 3.42%, it shows that the method is reasonable and valuable.

SWiLoc: Fusing Smartphone Sensors and WiFi CSI for Accurate Indoor Localization.

Dead reckoning is a promising yet often overlooked smartphone-based indoor localization technology that relies on phone-mounted sensors for counting steps and estimating walking directions, without the need for extensive sensor or landmark deployment. However, misalignment between the phone's direction and the user's actual movement direction can lead to unreliable direction estimates and inaccurate location tracking. To address this issue, this paper introduces SWiLoc (Smartphone and WiFi-based Localization), an enhanced direction correction system that integrates passive WiFi sensing with smartphone-based sensing to form Correction Zones. Our two-phase approach accurately measures the user's walking directions when passing through a Correction Zone and further refines successive direction estimates outside the zones, enabling continuous and reliable tracking. In addition to direction correction, SWiLoc extends its capabilities by incorporating a localization technique that leverages corrected directions to achieve precise user localization. This extension significantly enhances the system's applicability for high-accuracy localization tasks. Additionally, our innovative Fresnel zone-based approach, which utilizes unique hardware configurations and a fundamental geometric model, ensures accurate and robust direction estimation, even in scenarios with unreliable walking directions. We evaluate SWiLoc across two real-world environments, assessing its performance under varying conditions such as environmental changes, phone orientations, walking directions, and distances. Our comprehensive experiments demonstrate that SWiLoc achieves an average 75th percentile error of 8.89 degrees in walking direction estimation and an 80th percentile error of 1.12 m in location estimation. These figures represent reductions of 64% and 49%, respectively for direction and location estimation error, over existing state-of-the-art approaches.

UAV image object detection based on self-attention guidance and global feature fusion

Unmanned aerial vehicle (UAV) image object detection has garnered considerable attentions in fields such as Intelligent transportation, urban management and agricultural monitoring. However, it suffers from key challenges of the deficiency in multi-scale feature extraction and the inaccuracy when processing complex scenes and small-sized targets in practical applications. To address this challenge, we propose a novel UAV image object detection network based on self-attention guidance and global feature fusion, named SGGF-Net. First, in order to optimizing feature extraction in global perspective and enhancing target localization precision, the global feature extraction module (GFEM) is introduced by exploiting the self-attention mechanism to capture and integrate long-range dependencies within images. Second, a normal distribution-based prior assigner (NDPA) is developed by measuring the resemblance between ground truth and the priors, which improves the precision of target position matching and thus handle the problem of inaccurate localization of small targets. Furthermore, we design an attention-guided ROI pooling module (ARPM) via a deep fusion strategy of multilevel features for optimizing the integration of multi-scale features and improving the quality of feature representation. Finally, experimental results demonstrate the effectiveness of the proposed SGGF-Net approach.

Omni-directional wavenumber dictionary modified imaging method for orthotropic composites damage detection using ultrasonic guided waves

The sparse reconstruction imaging method is promising for detecting damage in isotropic and quasi-isotropic materials. However, its effectiveness relies on an accurate dictionary. When applied to orthotropic materials without accounting for wavenumber directionality, the accuracy of the dictionary degrades, leading to inaccurate damage localization. To address this limitation, this paper presents an omnidirectional wavenumber dictionary modified imaging method for orthotropic composites damage detection. The omni-directional wavenumber dispersion curve of ultrasonic guided waves is calculated numerically by converting of elastic stiffness coefficient of orthotropic composites at various propagation angles. A modified propagation model, informed by the omni-directional wavenumber dispersion curve, enhances the precision of the acoustic field dictionary. Utilizing a coherent matched field processor, the method compares the scattered signal's envelope with the acoustic field dictionary's envelope to generate an ambiguity function, which in turn forms a damage image. Simulation and experimental results confirm the method's superiority in resolving damage localization inaccuracies and artifacts typically associated with orthotropic composites. The proposed method exhibits enhanced signal-to-noise ratio and lower positioning error, facilitating precise multi-damage detection in orthotropic composites compared to existing methods.

Research on improved YOLOV7-SSWD digital meter reading recognition algorithms.

Meter reading recognition is an important link for robots to complete inspection tasks. To solve the problems of low detection accuracy and inaccurate localization of current meter reading recognition algorithms, the YOLOV7-SSWD (YOLOV7-SiLU-SimAM-Wise-IoU-DyHeads) model is proposed, a novel detection model based on the multi-head attention mechanism, which is improved on the YOLOV7-Tiny model. First, the Wise-IoU loss function is used to solve the problem of sample quality imbalance and improve the model's detection accuracy. Second, a new convolutional block is constructed using the SiLU activation function and applied to the YOLOV7-Tiny model to enhance the model's generalization ability. The dynamic detection header is then built as the header of YOLOV7-Tiny, which realizes the fusion of multi-scale feature information and improves the target recognition performance. Finally, we introduce SimAM to improve the feature extraction capability of the network. In this paper, the importance of each component is fully verified by ablation experiments and comparative analysis. The experiments showed that the mAP and F1-scores of the YOLOV7-SSWD model reached 89.8% and 0.84. Compared with the original network, the mAP increased by 8.1% and the F1-scores increased by 0.1. The YOLOV7-SSWD algorithm has better localization and recognition accuracy and provides a reference for deploying inspection robots to perform automatic inspections.

FBDPN: CNN-Transformer hybrid feature boosting and differential pyramid network for underwater object detection

Despite advancements in underwater object detection (UOD) from optical underwater images in recent years, the task still poses significant challenges due to the chaotic underwater environment, as well as the substantial variations in scale and contour of objects. Existing deep learning-based schemes generally overlook the enhancement and refinement between multi-scale features of densely distributed underwater objects, leading to inaccurate localization and classification predictions with excessive information redundancy. To tackle the above issues, this article presents a novel feature boosting and differential pyramid network (FBDPN) for precise and efficient UOD. The salient properties of our paper are: (1) a heuristic feature pyramid network (FPN)-inspired architecture is constructed, which employs a convolutional neural network (CNN)-Transformer hybrid strategy to simultaneously facilitate the learning of multi-scale features and the capture of long-distance dependencies among pixels. (2) A neighborhood-scale feature boosting module (NSFBM) is developed to enhance contextual information between features of neighborhood scales. (3) A cross-scale feature differential module (CSFDM) is designed further to achieve effective information redundancy between features of different scales. Extensive experiments are conducted to reveal that our proposed FBDPN can outperform other state-of-the-art methods in both UOD performance and computational complexity. In addition, sufficient ablation studies are also performed to demonstrate the effectiveness of each component in our FBDPN. The source code is available at https://github.com/jixun-dmu/FBDPN.

Localizing Mobile Target using Kalman Filtering and Least Square Boosting Ensemble Learning based Approach

Trilateration-based target localization using received signal strengths (RSS) within wireless sensor networks (WSN) often results in inaccurate location estimates due to the considerable fluctuations in RSS measurements encountered in indoor environments. Enhancing the precision of RSS-based localization systems has been a primary area of interest in extensive research efforts. This study introduces two range-free algorithms, Ensemble Learning (EL) and EL+KF, which leverage RSS measurements for localization. In contrast to trilateration, the EL- based localization approach enables the direct estimation of target locations based on field measurements, eliminating the need for distance calculations. Notably, unlike other cutting-edge localization and tracking (L&amp;T) scheme like the support vector regression (SVR), the LSBoost (Least Squares Boosting) EL based localization architecture can be trained very quickly using RSS measurements to determine the mobile target's position. Furthermore, the proposed EL-based localization scheme incorporates the Kalman filter (KF) to achieve additional refinement in target location estimates. To assess the localization effectiveness of these proposed algorithms in the presence of noisy RF channels and dynamic target motion models, rigorous simulations were conducted. Thanks to the robust generalization capabilities of EL, the simulation results reveal that the presented EL-based localization algorithms exhibit superior performance compared to trilateration and the SVR-based localization scheme, particularly in terms of indoor localization accuracy.

Augmented reality navigation method based on image segmentation and sensor tracking registration technology

With the rapid development of modern science and technology, navigation technology provides great convenience for people's life, but the problem of inaccurate localization in complex environments has always been a challenge that navigation technology needs to be solved urgently. To address this challenge, this paper proposes an augmented reality navigation method that combines image segmentation and multi-sensor fusion tracking registration. The method optimizes the image processing process through the GA-OTSU-Canny algorithm and combines high-precision multi-sensor information in order to achieve accurate tracking of positioning and guidance in complex environments. Experimental results show that the GA-OTSU-Canny algorithm has a faster image edge segmentation rate, and the fastest start speed is only 1.8 s, and the fastest intersection selection time is 1.2 s. The navigation system combining the image segmentation and sensor tracking and registration techniques has a highly efficient performance in real-world navigation, and its building recognition rates are all above 99%. The augmented reality navigation system not only improves the navigation accuracy in high-rise and urban canyon environments, but also significantly outperforms traditional navigation solutions in terms of navigation startup time and target building recognition accuracy. In summary, this research not only provides a new framework for the theoretical integration of image processing and multi-sensor data, but also brings innovative technical solutions for the development and application of practical navigation systems.

Guided Ultrasonic Wave Monitoring of Damage in Anisotropic Composites

Lightweight, carbon fibre reinforced composites are often employed for the manufacture of aerospace components due to their good strength to weight ratio. However, due to poor interlaminar strength, composite components are prone to barely visible impact damage, caused by low velocity impacts, during aircraft operation. Guided-wave-based structural health monitoring (SHM) techniques, using a network of distributed sensors, is an important Structural Health Monitoring (SHM) tool for the detection and localization of in-service impact damage in composite structures. However, the material anisotropy of composite laminates influences guided wave propagation and scattering. These anisotropic effects, if unaccounted for, could lead to inaccurate localization of damage, and potential regions of the structure where guided waves cannot propagate with sufficient amplitude, reducing damage sensitivity. Defect characterization can be improved by considering the scattering characteristics of various damage types for the sparse array signal processing. Guided wave scattering (A0 Lamb wave mode) was investigated around an artificial insert delamination in a quasi-isotropic CFRP panel. Permanent magnets, mounted on an undamaged region of the plate, were also used as scattering targets and compared to the delamination case. Full 3D Finite Element (FE) simulations were performed for both the delamination and magnet cases and compared to wavefield data obtained from non-contact laser Doppler vibrometer (LDV) measurements. Individual ply layers were modelled using unidirectional composite material properties to accurately capture the anisotropy effects. Good agreement was found between the experimental measurements and simulations. Scattered guided wave amplitudes around each damage type show strong directional dependency with energy focusing along the fiber directions of the outer ply layers of the laminate. Distinct scattering behavior was observed for each damage type. Implications of anisotropy and angular scattering on sparse array SHM of different defect types are discussed.