Template Matching Approach Research Articles

Solving Ambiguity in EBSD Indexing of Long-Period Stacking Ordered (LPSO) Phase in Mg with Template Matching Approach

Magnesium (Mg) alloys with long-period stacking ordered (LPSO) phases are receiving increasing interest because of their excellent mechanical performance. The close similarity in atomic stacking sequences between different LPSO polytypes and Mg lattice often leads to ambiguous indexing in electron backscatter diffraction (EBSD), a commonly used material characterization technique. Instead of the Hough transformation approach used in commercial software, an alternative indexing approach, which can catch subtle differences by matching experimental patterns with simulated ones, is explored in this study. Our results, showing ~94% of mapping data being correctly indexed as the target phase, 14H LPSO, demonstrate the capability of not only resolving the LPSO phases but also distinguishing different LPSO polytypes. This approach offers a valuable, if not unique, solution for the microscale characterization of LPSO phases, enabling precise microstructure tuning to further promote the mechanical properties of Mg alloys.

Automatic robotic doppler sonography of leg arteries

PurposeRobot-assisted systems offer an opportunity to support the diagnostic and therapeutic treatment of vascular diseases to reduce radiation exposure and support the limited medical staff in vascular medicine. In the diagnosis and follow-up care of vascular pathologies, Doppler ultrasound has become the preferred diagnostic tool. The study presents a robotic system for automatic Doppler ultrasound examinations of patients’ leg vessels.MethodsThe robotic system consists of a redundant 7 DoF serial manipulator, to which a 3D ultrasound probe is attached. A compliant control was employed, whereby the transducer was guided along the vessel with a defined contact force. Visual servoing was used to correct the position of the probe during the scan so that the vessel can always be properly visualized. To track the vessel’s position, methods based on template matching and Doppler sonography were used.ResultsOur system was able to successfully scan the femoral artery of seven volunteers automatically for a distance of 20 cm. In particular, our approach using Doppler ultrasound data showed high robustness and an accuracy of 10.7 (±3.1) px in determining the vessel’s position and thus outperformed our template matching approach, whereby an accuracy of 13.9 (±6.4) px was achieved.ConclusionsThe developed system enables automated robotic ultrasound examinations of vessels and thus represents an opportunity to reduce radiation exposure and staff workload. The integration of Doppler ultrasound improves the accuracy and robustness of vessel tracking, and could thus contribute to the realization of routine robotic vascular examinations and potential endovascular interventions.

Robust vision detection of pipeline solder joints

PurposeSolder joint inspection plays a critical role in various industries, with a focus on integrated chip (IC) solder joints and metal surface welds. However, the detection of tubular solder joints has received relatively less attention. This paper aims to address the challenges of detecting small targets and complex environments by proposing a robust visual detection method for pipeline solder joints. The method is characterized by its simplicity, cost-effectiveness and ease of implementation.Design/methodology/approachA robust visual detection method based on the characteristics of pipeline solder joints is proposed. With the improved hue, saturation and value (HSV) color space, the method uses a multi-level template matching approach to first segment the pipeline from the background, and then match the endpoint of the pipeline to accurately locate the solder joint. The proposed method leverages the distinctive characteristics of pipeline solder joints and employs an enhanced HSV color space. A multi-level template matching approach is utilized to segment the pipeline from the background and accurately locate the solder joint by matching the pipeline endpoint.FindingsThe experimental results demonstrate the effectiveness of the proposed solder joint detection method in practical detection tasks. The average precision of pipeline weld joint localization exceeds 95%, while the average recall is greater than 90%. These findings highlight the applicability of the method to pipeline solder joint detection tasks, specifically in the context of production lines for refrigeration equipment.Research limitations/implicationsThe precision of the method is influenced by the placement angle and lighting conditions of the test specimen, which may pose challenges and impact the algorithm's performance. Potential avenues for improvement include exploring deep learning methods, incorporating additional features and contextual information for localization, and utilizing advanced image enhancement techniques to improve image quality.Originality/valueThe proposed pipeline solder joint detection method offers a novel and practical approach. The simplicity, cost-effectiveness and ease of implementation make it an attractive choice for detecting pipeline solder joints in different industrial applications.

Deep learning detects uncataloged low-frequency earthquakes across regions

Documenting the interplay between slow deformation and seismic ruptures is essential to understand the physics of earthquakes nucleation. However, slow deformation is often difficult to detect and characterize. The most pervasive seismic markers of slow slip are low-frequency earthquakes (LFEs) that allow resolving deformation at minute-scale. Detecting LFEs is hard, due to their emergent onsets and low signal-to-noise ratios, usually requiring region-specific template matching approaches. These approaches suffer from low flexibility and might miss LFEs as they are constrained to sources identified a priori. Here, we develop a deep learning-based workflow for LFE detection and location, modeled after classical earthquake detection with phase picking, phase association, and location. Across three regions with known LFE activity, we detect LFEs from both previously cataloged sources and newly identified sources. Furthermore, the approach is transferable across regions, enabling systematic studies of LFEs in regions without known LFE activity.

Measuring precise radial velocities on individual spectral lines

Context. Radial velocities (RVs) of stars contain both the Doppler reflex motion of potential planetary companions and the drowning and sometimes imitating effect of stellar activity. To separate the two, previous efforts have sought proxies that only trace the activity signals, yet the sub-meter-per-second floor required for the detection of Earth-like planets remains difficult to break. Aims. In this work, we analyze a sample of 12 G- to early M-type stars in order to investigate the feasibility of detecting a differential effect of stellar activity with photospheric depth, as traced by the spectral line-forming temperature, for observations with different sampling and noise levels. Methods. We computed the average line formation temperature for each point in the observed wavelength grids using the spectral synthesis code PySME. The final line selection was curated to exclude blended and poorly synthesized lines. We thereafter computed the convective blueshift (CB) of the line cores of our master spectra (composed of the stacked individual spectra of each star). Finally, we extracted RV time series for certain intervals of formation temperature using a template-matching approach. Results. We find the CB to follow a linear relation with the formation temperature of the line cores, and the CB slope to be steeper with increasing effective temperature. For the RV time series derived for different intervals of formation temperature, we find the RVs of line parts formed at higher temperatures, close to the spectral continuum, to be generally correlated with the S index, and the RVs of line parts formed at cooler temperatures, close to the spectral line cores, to be generally anti-correlated, especially for stars with low noise levels and significant variations over their magnetic cycles. Conclusions. RVs of line parts formed in the coolest 25% of the line-forming temperature range appear to be a strong tracer of stellar activity over the magnetic cycle for several stars. By detrending the total RV time series with a multi-linear combination of residuals of RVs measured at different temperature ranges and the S index, the RV scatter can be decreased to a greater extent than with the S index alone.

A Time-Saving Alternative to "Peak-Picking" Algorithms: A Gaussian Mixture Model Feature Extraction Technique for the Neurodiagnostic Auditory Brainstem Response.

The accurate and efficient analysis of neurodiagnostic auditory brainstem responses (ABR) plays a critical role in assessing auditory pathway function in human and animal research and in clinical diagnosis. Traditional analysis of the neurodiagnostic ABR analysis involves visual inspection of the waveform and manually marking peaks and troughs. Visual inspection is a tedious and time-consuming task, especially in research where there may be hundreds or thousands of waveforms to analyze. "Peak-picking" algorithms have made this task faster; however, they are prone to the same errors as visual inspection. A Gaussian mixture model-based feature extraction technique (GMM-FET) is a descriptive model of ABR morphology and an alternative to peak-picking algorithms. The GMM-FET is capable of modeling multiple waves and accounting for wave interactions, compared with other template-matching approaches that fit single waves. The present study is a secondary analysis applying the GMM-FET to 321 ABRs from adult humans from 2 datasets using different stimuli and recording parameters. Goodness-of-fit of the GMM-FET to waves I and V and surrounding waves, that is, the summating potential and waves IV and VI, was assessed, and latency and amplitude estimations by the GMM-FET were compared with estimations from visual inspection. The GMM-FET had a similar success rate to visual inspection in extracting peak latency and amplitude, and there was low RMS error and high intraclass correlation between the model and response waveform. Mean peak latency differences between the GMM-FET and visual inspection were small, suggesting the two methods chose the same peak in the majority of waveforms. The GMM-FET estimated wave I amplitudes within 0.12 µV of visual inspection, but estimated larger wave V amplitudes than visual inspection. The results suggest the GMM-FET is an appropriate method for extracting peak latencies and amplitudes for neurodiagnostic analysis of ABR waves I and V.

Accurate Localization of First and Second Heart Sounds via Template Matching in Forcecardiography Signals.

Cardiac auscultation is an essential part of physical examination and plays a key role in the early diagnosis of many cardiovascular diseases. The analysis of phonocardiography (PCG) recordings is generally based on the recognition of the main heart sounds, i.e., S1 and S2, which is not a trivial task. This study proposes a method for an accurate recognition and localization of heart sounds in Forcecardiography (FCG) recordings. FCG is a novel technique able to measure subsonic vibrations and sounds via small force sensors placed onto a subject's thorax, allowing continuous cardio-respiratory monitoring. In this study, a template-matching technique based on normalized cross-correlation was used to automatically recognize heart sounds in FCG signals recorded from six healthy subjects at rest. Distinct templates were manually selected from each FCG recording and used to separately localize S1 and S2 sounds, as well as S1-S2 pairs. A simultaneously recorded electrocardiography (ECG) trace was used for performance evaluation. The results show that the template matching approach proved capable of separately classifying S1 and S2 sounds in more than 96% of all heartbeats. Linear regression, correlation, and Bland-Altman analyses showed that inter-beat intervals were estimated with high accuracy. Indeed, the estimation error was confined within 10 ms, with negligible impact on heart rate estimation. Heart rate variability (HRV) indices were also computed and turned out to be almost comparable with those obtained from ECG. The preliminary yet encouraging results of this study suggest that the template matching approach based on normalized cross-correlation allows very accurate heart sounds localization and inter-beat intervals estimation.

Urban Visual Localization of Block-Wise Monocular Images with Google Street Views

Urban visual localization is the process of determining the pose (position and attitude) of the imaging sensor (or platform) with the help of existing geo-referenced data. This task is critical and challenging for many applications, such as autonomous navigation, virtual and augmented reality, and robotics, due to the dynamic and complex nature of urban environments that may obstruct Global Navigation Satellite Systems (GNSS) signals. This paper proposes a block-wise matching strategy for urban visual localization by using geo-referenced Google Street View (GSV) panoramas as the database. To determine the pose of the monocular query images collected from a moving vehicle, neighboring GSVs should be found to establish the correspondence through image-wise and block-wise matching. First, each query image is semantically segmented and a template containing all permanent objects is generated. The template is then utilized in conjunction with a template matching approach to identify the corresponding patch from each GSV image within the database. Through the conversion of the query template and corresponding GSV patch into feature vectors, their image-wise similarity is computed pairwise. To ensure reliable matching, the query images are temporally grouped into query blocks, while the GSV images are spatially organized into GSV blocks. By using the previously computed image-wise similarities, we calculate a block-wise similarity for each query block with respect to every GSV block. A query block and its corresponding GSV blocks of top-ranked similarities are then input into a photogrammetric triangulation or structure from motion process to determine the pose of every image in the query block. A total of three datasets, consisting of two public ones and one newly collected on the Purdue campus, are utilized to demonstrate the performance of the proposed method. It is shown it can achieve a meter-level positioning accuracy and is robust to changes in acquisition conditions, such as image resolution, scene complexity, and the time of day.

Low-Frequency Blast Detection Using a Large-N Dark Fiber in Noisy Environments: Template Matching and Optimal Channel Selection

Abstract Distributed acoustic sensing (DAS), deployed on dark telecom fiber, is well-positioned to play a significant role in seismic monitoring networks because of the combination of a large aperture, fine spatial resolution, broadband sensitivity, and the ubiquitous presence of unused telecommunication fibers in many areas of the world. In this study, we explore the feasibility of dark-fiber array deployed in a noisy environment for detecting small explosions. We test the effectiveness of template matching for the detection of low-frequency blasts generated by mining activities in the Imperial Valley, California. We first evaluate dark-fiber detection performance by analyzing the relationship between detection threshold (DT) and the number of DAS channels used. We find that although, as expected, increasing the number of channels yields higher detection significance and lowers DT, the gain in performance is far from linear, with local anomalies across the DAS cable associated with zones of higher noise. We focus on investigating the types of noise affecting template matching and practical approaches mitigating anthropogenic noise that lower detection performance. Using median absolute deviation, we identify two types of noise sources affecting detection performance. Next, we design a voting scheme that selects DAS channels contributing to lowering of the DT and ensures improvement in detection when adding sequential channels. Finally, we compare dark-fiber detection performance with nearby conventional seismometers and find that a single station can outperform up to ∼10 DAS channels. However, using the full aperture of our dark-fiber transect allows to obtain ∼10% lower DT and yields fewer false-positive detections than an array of four seismometers. Methodological solutions for noise assessment and channel selection allow us to fully benefit from the large aperture and dense sampling offered by dark fiber. The findings of this study are a step toward incorporating existing telecom fibers into novel explosion-monitoring workflows.

Distinct Yet Adjacent Earthquake Sequences near the Mendocino Triple Junction: 20 December 2021 Mw 6.1 and 6.0 Petrolia, and 20 December 2022 Mw 6.4 Ferndale

Abstract Two earthquake sequences occurred a year apart at the Mendocino Triple Junction in northern California: first the 20 December 2021 Mw 6.1 and 6.0 Petrolia sequence, then the 20 December 2022 Mw 6.4 Ferndale sequence. To delineate active faults and understand the relationship between these sequences, we applied an automated deep-learning workflow to create enhanced and relocated earthquake catalogs for both the sequences. The enhanced catalog newly identified more than 14,000 M 0–2 earthquakes and also found 852 of 860 already cataloged events. We found that deep-learning and template-matching approaches complement each other to improve catalog completeness because deep learning finds more M 0–2 background seismicity, whereas template-matching finds the smallest M < 0 events near already known events. The enhanced catalog revealed that the 2021 Petrolia and 2022 Ferndale sequences were distinct in space and time, but adjacent in space. Though both the sequences happened in the downgoing Gorda slab, the shallower Ferndale sequence ruptured within the uppermost slab near the subduction interface, while the onshore Petrolia sequence occurred deeper in the mantle. Deep-learning-enhanced earthquake catalogs could help monitor evolving earthquake sequences, identify detailed seismogenic fault structures, and understand space–time variations in earthquake rupture and sequence behavior in a complex tectonic setting.

An Enhanced Catalog of Repeating Earthquakes on the 1980 Irpinia Fault System, Southern Italy

A pilot study employing a template-matching approach on the detection of repeating earthquakes (or repeaters) in a small volume of the Irpinia fault (Southern Italy) is presented here. A catalog of repeaters nucleating over about a decade with local magnitudes ranging between ML 0.4 and ML 1.7 is generated. The events nucleate at depths of about 11 km over a fault patch with a size of about 600 m. Assuming a constant stress drop for all repeaters, the yearly coseismic slip rate of the patch is estimated in the range of 1–4.8 mm with a mean value of about 3.4 mm, which is close to the fault slip rate estimated by geodetic approaches. Given the mechanical properties of the medium in the source region of the repeaters revealed by previous tomographic studies, and in particular the high Vp/Vs ratio (close to 1.95), it is postulated that these events are fluid triggered, consistently with the mechanism proposed for the generation of most of the microseismicity in the area. The encouraging outcomes of this study suggest to focus future measurement campaigns on this area and open perspectives to extend this approach to other segments of the Irpinia fault to reveal small-scale frictional properties in an area capable to generate M7 earthquakes.

Automated Analysis of Nano‐Impact Single‐Entity Electrochemistry Signals Using Unsupervised Machine Learning and Template Matching

Nano‐impact (NIE) (also referred to as collision) single‐entity electrochemistry is an emerging technique that enables electrochemical investigation of individual entities, ranging from metal nanoparticles to single cells and biomolecules. To obtain meaningful information from NIE experiments, analysis and feature extraction on large datasets are necessary. Herein, a method is developed for the automated analysis of NIE data based on unsupervised machine learning and template matching approaches. Template matching not only facilitates downstream processing of the NIE data but also provides a more accurate analysis of the NIE signal characteristics and variations that are difficult to discern with conventional data analysis techniques, such as the height threshold method. The developed algorithm enables fast automated processing of large experimental datasets recorded with different systems, requiring minimal human intervention and thereby eliminating human bias in data analysis. As a result, it improves the standardization of data processing and NIE signal interpretation across various experiments and applications.

Predictive Analytics for Sustainable E-Learning: Tracking Student Behaviors

The COVID-19 pandemic has sped up the acceptance of online education as a substitute for conventional classroom instruction. E-Learning emerged as an instant solution to avoid academic loss for students. As a result, educators and academics are becoming more and more interested in comprehending how students behave in e-learning settings. Behavior analysis of students in an e-learning environment can provide vision and influential factors that can improve learning outcomes and guide the creation of efficient interventions. The main objective of this work is to provide a system that analyzes the behavior and actions of students during e-learning which can help instructors to identify and track student attention levels so that they can design their content accordingly. This study has presented a fresh method for examining student behavior. Viola–Jones was used to recognize the student using the object’s movement factor, and a region-shrinking technique was used to isolate occluded items. Each object has been checked by a human using a template-matching approach, and for each object that has been confirmed, features are computed at the skeleton and silhouette levels. A genetic algorithm was used to categorize the behavior. Using this system, instructors can spot kids who might be failing or uninterested in learning and offer them specific interventions to enhance their learning environment. The average attained accuracy for the MED and Edu-Net datasets are 90.5% and 85.7%, respectively. These results are more accurate when compared to other methods currently in use.

Fluid-driven seismic swarms in the Gripp valley (Haute-Pyrénées, France)

SUMMARY An unusual seismic activity has recently occurred in the Gripp valley, located in the central part of the French Pyrenees. Since spring 2020, two new swarms appeared, clearly outside the usual location of the seismicity in this area. On 20 September 2020, almost concomitantly with the activation of the second seismic swarm, a hole suddenly opened in the bed of a local river, the Adour de Payolle. This hole drained the water from the river, which dried up over 500 m. We follow and study the spatial and temporal evolution of these clusters, using four temporary stations deployed a few days or months after the beginning of the crisis to complete the regional network. These additional data lead to the construction of a comprehensive catalogue of more than 4900 earthquakes, using both a template matching approach and a deep-learning based phase picking method to complete and improve the initial catalogue available from the French seismological agency. This allows highlighting a slow and clear migration of the seismicity during 1 yr. Precise absolute and relative event locations reveal a dipping faulting structure, confirmed by the focal mechanism estimated for the highest magnitude event of the sequence (ML 3). We propose to explain the observed migration of the seismicity by deep fluids going up through a newly discovered faulting structure.

Design and Test of a Spatial Nanopositioner for Evaluating the Out-of-Focus-Plane Performance of Micro-Vision

Micro-vision possesses high in-focus-plane motion tracking accuracy. Unfortunately, out-of-focus-plane displacements cannot be avoided, decreasing the in-focus-plane tracking accuracy of micro-vision. In this paper, a spatial nanopositioner is proposed to evaluate the out-of-focus-plane performance of a micro-vision system. A piezoelectric-actuated spatial multi-degree-of-freedom (multi-DOF) nanopositioner is introduced. Three in-plane Revolute-Revolute-Revolute-Revolute (RRRR) compliant parallel branched chains produce in-focus-plane motions. Three out-of-plane RRRR chains generate out-of-focus-plane motions. A typical micro-vision motion tracking algorithm is presented. A general grayscale template matching (GTM) approach is combined with the region of interest (ROI) method. The in-focus-plane motion tracking accuracy of the micro-vision system is tested. Different out-of-focus-plane displacements are generated using the proposed nanopositioner. The accuracy degradation of the in-focus-plane motion tracking is evaluated. The experimental results verify the evaluation ability of the proposed nanopositioner.

Acoustic-Based Machine Anomaly Detection Using Beamforming and Sequential Transform Learning

Acoustic-based analysis has been widely used for the maintenance and operation of industrial machines. However, interferences and background noise highly contaminate the observed acoustic signal. Here, we present a novel two-stage multichannel source separation technique for improved separation and robust anomaly detection. Beamforming is applied in the first stage to provide separation at a coarser level. Sequential transform learning is employed in the second stage to learn the dynamics of the time-varying source signal for more refined source separation. The separated machine sounds are analyzed for anomaly using a simple template matching approach. Results obtained using the MIMII dataset indicate that the proposed two-stage method provides an average improvement of 1.98 dB in signal-to-noise ratio and 19.75 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> in accuracy when compared to the best-performing state-of-the-art methods for source separation and anomaly detection, respectively.

Memory Efficient Local Features Descriptor for Identity Document Detection on Mobile and Embedded Devices

In this paper, we propose a data-driven approach to training a memory-efficient local feature descriptor for identity documents location and classification on mobile and embedded devices. The proposed algorithm for retrieving a dataset of patches is based on the specifics of document detection in smartphone camera-captured images with a template matching approach. The retrieved dataset of patches relevant to the domain, which includes splits for features training, features selection, and testing, is made public. We train a binary descriptor using the retrieved dataset of patches, each bit of the descriptor relies on a single computationally-efficient feature. To estimate the influence of different feature spaces on the descriptor performance, we perform descriptor training experiments using gradient-based and intensity-based features. Extensive experiments in identity document location and classification benchmarks showed that the resulting 128 and 192-bit descriptors which use gradient-based features outperformed a state-of-the-art 512-bit BEBLID descriptor for arbitrary keypoints matching in all cases except the cases of extreme projective distortions, being significantly more efficient in cases of low lighting. The 64-bit gradient-based descriptor obtained within the approach showed better quality than 128 and 256-bit BinBoost descriptors in scanned document images. To evaluate the influence of the descriptor size on the matching speed, we propose a model based on the required number of processor instructions for computing the Hamming distance between a pair of descriptors on various energy-efficient processor architectures.

Automated electrocardiogram signal quality assessment based on Fourier analysis and template matching.

Wedeveloped and tested a novel template matching approach for signal quality assessment on electrocardiogram (ECG) data. A computational method was developed that uses a sinusoidal approximation to the QRS complex to generate a correlation value at every point of an ECG. The strength of this correlation can be numerically adapted into a 'score' for each segment of an ECG, which can be used to stratify signal quality. The algorithm was tested on lead II ECGs of intensive care unit (ICU) patients admitted to the Mount Sinai Hospital (MSH) from January to July 2020 and on records from the MIT BIH arrhythmia database. The algorithm was found to be 98.9% specific and 99% sensitive on test data from the MSH ICU patients. The routine performs in linear O(n) time and occupies O(1) heap space in runtime. This approach can be used to lower the burden of pre-processing in ECG signal analysis. Given its runtime (O(n)) and memory (O(1)) complexity, there are potential applications for signal quality stratification and arrhythmia detection in wearable devices or smartphones.

A new method to solve rotated template matching using metaheuristic algorithms and the structural similarity index

Template matching (TM) is a technique used in computer vision that helps us to identify small pieces of a predefined sub image known as template and a corresponding area inside a large image. There are several approaches in the literature that solve this problem. In spite of their acceptable results, the existing methods fail to detect templates when they are rotated in a large image. On the other hand, the structural similarity (SSIM) index is a resemblance model that allows us to evaluate the affinity between two images. Different from other similarity indexes, SSIM considers important structural information while also incorporating essential elements such as luminance and contrast terms. This paper presents a new approach for template matching when an image is rotated. Our method considers the complete process as an optimization problem where a metaheuristic algorithm is used to find the best resemblance between the template and its rotated or unrotated image. In order to obtain a robust detection, our approach considers the use of the SSIM index as an objective function. Although metaheuristic approaches produce interesting results, there is not an ideal algorithm that can competitively solve all problems. Under such conditions, our study analyzes the performance of five different metaheuristic techniques for solving the problem of TM. In the comparison, several complicated computer experiments have been conducted considering different performance indexes. The results show that the proposed technique solves the problem of TM competitively for rotated instances in terms of accuracy and robustness.

A novel framework for semi-Bayesian radial velocities through template matching

Context. The ability to detect and characterise an increasing variety of exoplanets has been made possible by the continuous development of stable, high-resolution spectrographs and the Doppler radial velocity (RV) method. The cross-correlation function (CCF) method is one of the traditional approaches used to derive RVs. More recently, template matching has been introduced as an advantageous alternative for M-dwarf stars. Aims. We describe a new implementation of the template matching technique for stellar RV estimation within a semi-Bayesian framework, providing a more statistically principled characterisation of the RV measurements and associated uncertainties. This methodology, named the Semi-Bayesian Approach for RVs with Template matching, S-BART, can currently be applied to HARPS and ESPRESSO data. We first validate its performance with respect to other template matching pipelines using HARPS data. We then apply S-BART to ESPRESSO observations, comparing the scatter and uncertainty of the derived RV time series with those obtained using the CCF method. We leave a full analysis of the planetary and activity signals present in the considered datasets for future work. Methods. In the context of a semi-Bayesian framework, a common RV shift is assumed to describe the difference between each spectral order of a given stellar spectrum and a template built from the available observations. Posterior probability distributions are obtained for the relative RV associated with each spectrum using the Laplace approximation, after marginalization with respect to the continuum. We also implemented, for validation purposes, a traditional template matching approach, where a RV shift is estimated individually for each spectral order and the final RV estimate is calculated as a weighted average of the RVs of the individual orders. Results. The application of our template-based methods to HARPS archival observations of Barnard’s star allowed us to validate our implementation against other template matching methods. Although we find similar results, the standard deviation of the RVs derived with S-BART is smaller than that obtained with the HARPS-TERRA and SERVAL pipelines. We believe this is due to differences in the construction of the stellar template and the handling of telluric features. After validating S-BART, we applied it to 33 ESPRESSO GTO targets, evaluating its performance and comparing it to the CCF method as implemented in ESO’s official pipeline. We find a decrease in the median RV scatter of ~10 and ~4% for M- and K-type stars, respectively. Our semi-Bayesian framework yields more precise RV estimates than the CCF method, in particular in the case of M-type stars where S-BART achieves a median uncertainty of ~15 cm s−1 over 309 observations of 16 targets. Further, with the same data we estimated the nightly zero point (NZP) of the instrument, finding a weighted NZP scatter of below ~0.7 m s−1. Given that this includes stellar variability, photon noise, and potential planetary signals, it should be taken as an upper limit on the RV precision attainable with ESPRESSO data.