Vision Algorithms Research Articles

Mapping multimorbidity progression among 190 diseases

BackgroundCurrent clustering of multimorbidity based on the frequency of common disease combinations is inadequate. We estimated the causal relationships among prevalent diseases and mapped out the clusters of multimorbidity progression among them.MethodsIn this cohort study, we examined the progression of multimorbidity among 190 diseases among over 500,000 UK Biobank participants over 12.7 years of follow-up. Using a machine learning method for causal inference, we analyzed patterns of how diseases influenced and were influenced by others in females and males. We used clustering analysis and visualization algorithms to identify multimorbidity progress constellations.ResultsWe show the top influential and influenced diseases largely overlap between sexes in chronic diseases, with sex-specific ones tending to be acute diseases. Patterns of diseases that influence and are influenced by other diseases also emerged (clustering significance Pau > 0.87), with the top influential diseases affecting many clusters and the top influenced diseases concentrating on a few, suggesting that complex mechanisms are at play for the diseases that increase the development of other diseases while share underlying causes exist among the diseases whose development are increased by others. Bi-directional multimorbidity progress presents substantial clustering tendencies both within and across International Classification Disease chapters, compared to uni-directional ones, which can inform future studies for developing cross-specialty strategies for multimorbidity. Finally, we identify 10 multimorbidity progress constellations for females and 9 for males (clustering stability, adjusted Rand index >0.75), showing interesting differences between sexes.ConclusionOur findings could inform the future development of targeted interventions and provide an essential foundation for future studies seeking to improve the prevention and management of multimorbidity.

A Visual Navigation Algorithm for UAV Based on Visual-Geography Optimization

The estimation of Unmanned Aerial Vehicle (UAV) poses using visual information is essential in Global Navigation Satellite System (GNSS)-denied environments. In this paper, we propose a UAV visual navigation algorithm based on visual-geography Bundle Adjustment (BA) to address the challenge of missing geolocation information in monocular visual navigation. This algorithm presents an effective approach to UAV navigation and positioning. Initially, Visual Odometry (VO) was employed for tracking the UAV’s motion and extracting keyframes. Subsequently, a geolocation method based on heterogeneous image matching was utilized to calculate the geographic pose of the UAV. Additionally, we introduce a tightly coupled information fusion method based on visual-geography optimization, which provides a geographic initializer and enables real-time estimation of the UAV’s geographical pose. Finally, the algorithm dynamically adjusts the weight of geographic information to improve optimization accuracy. The proposed method is extensively evaluated in both simulated and real-world environments, and the results demonstrate that our proposed approach can accurately and in real-time estimate the geographic pose of the UAV in a GNSS-denied environment. Specifically, our proposed approach achieves a root-mean-square error (RMSE) and mean positioning accuracy of less than 13 m.

Colour difference detection algorithm for warp‐knitted fabric based on image colour appearance model

AbstractDetecting colour differences in warp‐knitting fabric is essential to ensure its quality. Machine vision algorithms are commonly used for automatic colour difference detection. However, the current algorithm directly extracts RGB (red, green, blue) colour stimulus values from the image without considering the image's colour attributes, leading to a significant error in colour difference detection. To solve this issue, a colour appearance model is introduced into the field of colour difference detection for warp‐knitted fabric. Initially, a colour appearance model based on CAM16 is established, and the critical parameters are calculated to obtain the colour appearance attribute of the fabric. The colour difference calculation formula is then constructed in the uniform colour space of CAM16‐UCS. A template selection algorithm based on principal component analysis was designed to select warp‐knitted cloth images with standard colours. Subsequently, a cloth colour difference detection algorithm was developed using the cloth colour profile model. The performance of the colour difference formula based on the colour profile model was evaluated using the PF/3 method. To compare the CIELab, CMC(2:1), and CIEDE2000 colour difference formulas, standardised residual sum of squares was used. The results indicated that the colour difference formula based on the colour‐appearance model is about 5.32% different from the visual colour difference perceived by the human eye. However, it can perform as well as the CMC(2:1) colour difference formula, which is widely used in the textile industry.

Gastrointestinal tract disease detection via deep learning based structural and statistical features optimized hexa-classification model.

Gastrointestinal tract (GIT) diseases impact the entire digestive system, spanning from the mouth to the anus. Wireless Capsule Endoscopy (WCE) stands out as an effective analytic instrument for Gastrointestinal tract diseases. Nevertheless, accurately identifying various lesion features, such as irregular sizes, shapes, colors, and textures, remains challenging in this field. Several computer vision algorithms have been introduced to tackle these challenges, but many relied on handcrafted features, resulting in inaccuracies in various instances. In this work, a novel Deep SS-Hexa model is proposed which is a combination two different deep learning structures for extracting two different features from the WCE images to detect various GIT ailment. The gathered images are denoised by weighted median filter to remove the noisy distortions and augment the images for enhancing the training data. The structural and statistical (SS) feature extraction process is sectioned into two phases for the analysis of distinct regions of gastrointestinal. In the first stage, statistical features of the image are retrieved using MobileNet with the support of SiLU activation function to retrieve the relevant features. In the second phase, the segmented intestine images are transformed into structural features to learn the local information. These SS features are parallelly fused for selecting the best relevant features with walrus optimization algorithm. Finally, Deep belief network (DBN) is used classified the GIT diseases into hexa classes namely normal, ulcer, pylorus, cecum, esophagitis and polyps on the basis of the selected features. The proposed Deep SS-Hexa model attains an overall average accuracy of 99.16% in GIT disease detection based on KVASIR and KID datasets. The proposed Deep SS-Hexa model achieves high level of accuracy with minimal computational cost in the recognition of GIT illness. The proposed Deep SS-Hexa Model progresses the overall accuracy range of 0.04%, 0.80% better than GastroVision, Genetic algorithm based on KVASIR dataset and 0.60%, 1.21% better than Modified U-Net, WCENet based on KID dataset respectively.

An Investigation in to Sports Analytics and Related Tools

This study explores the application of sports analytics and the utilization of various tools in the sports industry. Sports analytics, also known as sports data analytics, is the application of data analysis and statistical approaches to extract important insights. Additionally, it aids in making well-informed judgments and enhancing performance in the realm of sports. Sports data analytics include a diverse array of methods and approaches, such as statistical analysis, machine learning, data visualization, predictive modeling, and optimization algorithms. The objective of sports business analytics is to get practical insights from a dataset in order to enhance decision-making and foster innovation in the sports industry

Automatic Audio and Image Caption Generation with Deep Learning

A novel approach to image caption generation tailored specifically for visually impaired individuals. The proposed system employs advanced computer vision algorithms to analyze images and generate descriptive textual captions. Furthermore, it integrates seamless text-to-speech conversion functionality, allowing for the automatic transformation of these captions into spoken audio, thereby enabling access to visual content for individuals with visual impairments. The goal of this project is to generate descriptive captions for a given photograph or image. We achieve this by employing Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models, both of which are advanced deep learning techniques. Using computer vision, the system identifies the content of the image and generates a relevant caption. This caption is then converted into audio using Natural Language Processing (NLP).

Quantitative determination of SO2 flux from industrial chimney through machine vision with plume model verification

Accurate emission rate data are essential for assessing the environmental impact of industrial emissions and calibrating the effectiveness of desulphurization equipment. However, accurate calculation of SO2 emissions is difficult to realize due to the environmental conditions, the time-varying and spatial non-uniformity of pollution source emissions. In this paper, a Dual TV Plus machine vision algorithm is proposed, calculated and validated with the conventional Farneback optical flow algorithm in terms of industrial stack emission rates. In addition, the effect of turbulence on the inversion of SO2 emission under complex environmental conditions is evaluated by combining simulations and outdoor experiments. The results show that the Dual TV Plus algorithm performs better than the Farnebäck algorithm and the Dual TV-L1 algorithm, with 50% and 30% improvement in accuracy and 5% and 8% improvement in immunity to interference, respectively. This work is important for promoting the engineering applications of remote sensing instruments for environmental monitoring.

A visual security multi-key selection image encryption algorithm based on a new four-dimensional chaos and compressed sensing

In this article, a visual security image encryption algorithm based on compressed sensing is proposed. The algorithm consists of two stages: the compression and encryption stage and the embedding stage. The key streams in the compression and encryption stage are generated by a newly constructed four-dimensional discrete chaotic map, while the Gaussian measurement matrix is generated by a Chebyshev map, and both of their generations are related to the feature code of the carrier image, which enhances the security of the ciphertext. In the compression and encryption stage, a scrambling-cyclic shift-diffusion encryption structure is adopted for the compressed image in which the shift number in the cyclic shift stage and the diffusion key streams are dynamically changed according to each pixel value, so the algorithm can resist chosen plaintext attack. In the embedding stage, the carrier image is first subjected to integer wavelet transform to obtain the high-frequency and low-frequency components of the image, and then the intermediate ciphertext information is embedded into its high-frequency components. Finally, the carrier image is subjected to inverse integer wavelet transform to obtain a visually secure ciphertext image. The experimental results and security analysis indicate that the encryption scheme has a large key space, high decryption key sensitivity, similar histogram distribution between the carrier image and the visual security ciphertext image, and good robustness to noise attacks.

Computer Vision Method for Automatic Detection of Microstructure Defects of Concrete.

The search for structural and microstructural defects using simple human vision is associated with significant errors in determining voids, large pores, and violations of the integrity and compactness of particle packing in the micro- and macrostructure of concrete. Computer vision methods, in particular convolutional neural networks, have proven to be reliable tools for the automatic detection of defects during visual inspection of building structures. The study's objective is to create and compare computer vision algorithms that use convolutional neural networks to identify and analyze damaged sections in concrete samples from different structures. Networks of the following architectures were selected for operation: U-Net, LinkNet, and PSPNet. The analyzed images are photos of concrete samples obtained by laboratory tests to assess the quality in terms of the defection of the integrity and compactness of the structure. During the implementation process, changes in quality metrics such as macro-averaged precision, recall, and F1-score, as well as IoU (Jaccard coefficient) and accuracy, were monitored. The best metrics were demonstrated by the U-Net model, supplemented by the cellular automaton algorithm: precision = 0.91, recall = 0.90, F1 = 0.91, IoU = 0.84, and accuracy = 0.90. The developed segmentation algorithms are universal and show a high quality in highlighting areas of interest under any shooting conditions and different volumes of defective zones, regardless of their localization. The automatization of the process of calculating the damage area and a recommendation in the "critical/uncritical" format can be used to assess the condition of concrete of various types of structures, adjust the formulation, and change the technological parameters of production.

Collaborative Human-Computer Vision Operative Video Analysis Algorithm for Analyzing Surgical Fluency and Surgical Interruptions in Endonasal Endoscopic Pituitary Surgery: Cohort Study.

The endonasal endoscopic approach (EEA) is effective for pituitary adenoma resection. However, manual review of operative videos is time-consuming. The application of a computer vision (CV) algorithm could potentially reduce the time required for operative video review and facilitate the training of surgeons to overcome the learning curve of EEA. This study aimed to evaluate the performance of a CV-based video analysis system, based on OpenCV algorithm, to detect surgical interruptions and analyze surgical fluency in EEA. The accuracy of the CV-based video analysis was investigated, and the time required for operative video review using CV-based analysis was compared to that of manual review. The dominant color of each frame in the EEA video was determined using OpenCV. We developed an algorithm to identify events of surgical interruption if the alterations in the dominant color pixels reached certain thresholds. The thresholds were determined by training the current algorithm using EEA videos. The accuracy of the CV analysis was determined by manual review, and the time spent was reported. A total of 46 EEA operative videos were analyzed, with 93.6%, 95.1%, and 93.3% accuracies in the training, test 1, and test 2 data sets, respectively. Compared with manual review, CV-based analysis reduced the time required for operative video review by 86% (manual review: 166.8 and CV analysis: 22.6 minutes; P<.001). The application of a human-computer collaborative strategy increased the overall accuracy to 98.5%, with a 74% reduction in the review time (manual review: 166.8 and human-CV collaboration: 43.4 minutes; P<.001). Analysis of the different surgical phases showed that the sellar phase had the lowest frequency (nasal phase: 14.9, sphenoidal phase: 15.9, and sellar phase: 4.9 interruptions/10 minutes; P<.001) and duration (nasal phase: 67.4, sphenoidal phase: 77.9, and sellar phase: 31.1 seconds/10 minutes; P<.001) of surgical interruptions. A comparison of the early and late EEA videos showed that increased surgical experience was associated with a decreased number (early: 4.9 and late: 2.9 interruptions/10 minutes; P=.03) and duration (early: 41.1 and late: 19.8 seconds/10 minutes; P=.02) of surgical interruptions during the sellar phase. CV-based analysis had a 93% to 98% accuracy in detecting the number, frequency, and duration of surgical interruptions occurring during EEA. Moreover, CV-based analysis reduced the time required to analyze the surgical fluency in EEA videos compared to manual review. The application of CV can facilitate the training of surgeons to overcome the learning curve of endoscopic skull base surgery. ClinicalTrials.gov NCT06156020; https://clinicaltrials.gov/study/NCT06156020.

Semihierarchical reconstruction and weak‐area revisiting for robotic visual seafloor mapping

AbstractDespite impressive results achieved by many on‐land visual mapping algorithms in the recent decades, transferring these methods from land to the deep sea remains a challenge due to harsh environmental conditions. Images captured by autonomous underwater vehicles, equipped with high‐resolution cameras and artificial illumination systems, often suffer from heterogeneous illumination and quality degradation caused by attenuation and scattering, on top of refraction of light rays. These challenges often result in the failure of on‐land Simultaneous Localization and Mapping (SLAM) approaches when applied underwater or cause Structure‐from‐Motion (SfM) approaches to exhibit drifting or omit challenging images. Consequently, this leads to gaps, jumps, or weakly reconstructed areas. In this work, we present a navigation‐aided hierarchical reconstruction approach to facilitate the automated robotic three‐dimensional reconstruction of hectares of seafloor. Our hierarchical approach combines the advantages of SLAM and global SfM that are much more efficient than incremental SfM, while ensuring the completeness and consistency of the global map. This is achieved through identifying and revisiting problematic or weakly reconstructed areas, avoiding to omit images and making better use of limited dive time. The proposed system has been extensively tested and evaluated during several research cruises, demonstrating its robustness and practicality in real‐world conditions.

MWIRGas-YOLO: Gas Leakage Detection Based on Mid-Wave Infrared Imaging.

The integration of visual algorithms with infrared imaging technology has become an effective tool for industrial gas leak detection. However, existing research has mostly focused on simple scenarios where a gas plume is clearly visible, with limited studies on detecting gas in complex scenes where target contours are blurred and contrast is low. This paper uses a cooled mid-wave infrared (MWIR) system to provide high sensitivity and fast response imaging and proposes the MWIRGas-YOLO network for detecting gas leaks in mid-wave infrared imaging. This network effectively detects low-contrast gas leakage and segments the gas plume within the scene. In MWIRGas-YOLO, it utilizes the global attention mechanism (GAM) to fully focus on gas plume targets during feature fusion, adds a small target detection layer to enhance information on small-sized targets, and employs transfer learning of similar features from visible light smoke to provide the model with prior knowledge of infrared gas features. Using a cooled mid-wave infrared imager to collect gas leak images, the experimental results show that the proposed algorithm significantly improves the performance over the original model. The segment mean average precision reached 96.1% (mAP50) and 47.6% (mAP50:95), respectively, outperforming the other mainstream algorithms. This can provide an effective reference for research on infrared imaging for gas leak detection.

Fully automated determination of robotic pedicle screw accuracy and precision utilizing computer vision algorithms

Historically, pedicle screw accuracy measurements have relied on CT and expert visual assessment of the position of pedicle screws relative to preoperative plans. Proper pedicle screw placement is necessary to avoid complications, cost and morbidity of revision procedures. The aim of this study was to determine accuracy and precision of pedicle screw insertion via a novel computer vision algorithm using preoperative and postoperative computed tomography (CT) scans. Three cadaveric specimens were utilized. Screw placement planning on preoperative CT was performed according to standard clinical practice. Two experienced surgeons performed bilateral T2–L4 instrumentation using robotic-assisted navigation. Postoperative CT scans of the instrumented levels were obtained. Automated segmentation and computer vision techniques were employed to align each preoperative vertebra with its postoperative counterpart and then compare screw positions along all three axes. Registration accuracy was assessed by preoperatively embedding spherical markers (tantalum beads) to measure discrepancies in landmark alignment. Eighty-eight pedicle screws were placed in 3 cadavers’ spines. Automated registrations between pre- and postoperative CT achieved sub-voxel accuracy. For the screw tip and tail, the mean three-dimensional errors were 1.67 mm and 1.78 mm, respectively. Mean angular deviation of screw axes from plan was 1.58°. For screw mid-pedicular accuracy, mean absolute error in the medial–lateral and superior–inferior directions were 0.75 mm and 0.60 mm, respectively. This study introduces automated algorithms for determining accuracy and precision of planned pedicle screws. Our accuracy outcomes are comparable or superior to recent robotic-assisted in vivo and cadaver studies. This computerized workflow establishes a standardized protocol for assessing pedicle screw placement accuracy and precision and provides detailed 3D translational and angular accuracy and precision for baseline comparison.

Semantic Visual SLAM Algorithm Based on Improved DeepLabV3+ Model and LK Optical Flow

Aiming at the problem that dynamic targets in indoor environments lead to low accuracy and large errors in the localization and position estimation of visual SLAM systems and the inability to build maps containing semantic information, a semantic visual SLAM algorithm based on the semantic segmentation network DeepLabV3+ and LK optical flow is proposed based on the ORB-SLAM2 system. First, the dynamic target feature points are detected and rejected based on the lightweight semantic segmentation network DeepLabV3+ and LK optical flow method. Second, the static environment occluded by the dynamic target is repaired using the time-weighted multi-frame fusion background repair technique. Lastly, the filtered static feature points are used for feature matching and position calculation. Meanwhile, the semantic labeling information of static objects obtained based on the lightweight semantic segmentation network DeepLabV3+ is fused with the static environment information after background repair to generate dense point cloud maps containing semantic information, and the semantic dense point cloud maps are transformed into semantic octree maps using the octree spatial segmentation data structure. The localization accuracy of the visual SLAM system and the construction of the semantic maps are verified using the widely used TUM RGB-D dataset and real scene data, respectively. The experimental results show that the proposed semantic visual SLAM algorithm can effectively reduce the influence of dynamic targets on the system, and compared with other advanced algorithms, such as DynaSLAM, it has the highest performance in indoor dynamic environments in terms of localization accuracy and time consumption. In addition, semantic maps can be constructed so that the robot can better understand and adapt to the indoor dynamic environment.

Autopilot drone in construction: A proof of concept for handling lightweight instruments and materials

Applications of Unmanned Aerial Vehicles (UAVs) in construction have been increased in recent years mainly for purposes of automatically collecting field data. In the market, there is a growing opportunity for using UAVs in material handling. On the other side, vertical transportation in construction sites is a crucial challenge that leads to a drop in productivity efficiency. This paper presents a proof of concept for automating the lifting procedure of lightweight instruments and materials in construction sites. To do so, a platform is developed that could automatically manage material/instrument handling requests via an autopilot drone. The aircraft position is tracked with an onboard GPS module which is not accurate in urban areas. So inaccurate GPS signals could deviate the drone from the predefined path. To tackle this problem, a machine vision algorithm is utilized to calibrate the real-time position of the aircraft. A self-supervised learning algorithm is integrated into the system to handling collision avoidance during the flight. Finally, the developed methods are tested with an UAV in a real world environment to demonstrate the potentials of hiring autopilot drones in construction.

Анализ и документирование требований для программного комплекса по проведению вычислительных экспериментов и численному исследованию системы «расходомерная трубка – жидкость» кориолисова расходомера

&lt;p&gt;Item. This article describes the stages of development of a software package designed to conduct a series of computational experiments on numerical modeling of the &amp;ldquo;flow tube &amp;ndash; liquid&amp;rdquo; system of a Coriolis flow meter and automation of algorithms for subsequent data processing and visualization. The purpose of this article is to formulate and document the requirements for a software package, and its design based on modern approaches to the development of software products. Methods. The structure of requirements for the software package was developed based on the Software Requirements Specification template adopted in the Rational Unified Process software development methodology, in accordance with the classification of requirements for FURPS+ software systems. Python 3 and the interpreted programming language of the MATLAB environment were used to develop the complex routines. Results. A structure of requirements for the software package has been developed, including functional and non-functional requirements. A software package consisting of three subprograms has been developed, its structure, main components and capabilities are described, and examples of use are demonstrated. Conclusions. The software package solves the problems of automating modeling algorithms, processing and visualizing data obtained as a result of experiments. It can be used in engineering and scientific research related to the analysis of the performance of Coriolis flow meters.&lt;/p&gt;

Computer vision-guided open-source active commutator for neural imaging in freely behaving animals.

Recently developed miniaturized neural recording devices that can monitor and perturb neural activity in freely behaving animals have significantly expanded our knowledge of neural underpinning of complex behaviors. Most miniaturized neural interfaces require a wired connection for external power and data acquisition systems. The wires are required to be commutated through a slip ring to accommodate for twisting of the wire or tether and alleviate torsional stresses. The increased trend toward long-term continuous neural recordings has spurred efforts to realize active commutators that can sense the torsional stress and actively rotate the slip ring to alleviate torsional stresses. Current solutions however require the addition of sensing modules. Here, we report on an active translating commutator that uses computer vision (CV) algorithms on behavioral imaging videos captured during the experiment to track the animal's position and heading direction in real time and uses this information to control the translation and rotation of a slip ring commutator to accommodate for accumulated mouse heading orientation changes and position. The CV-guided active commutator has been extensively tested in three separate behavioral contexts. We show reliable cortex-wide imaging in a mouse in an open field with a miniaturized wide-field cortical imaging device. Active commutation resulted in no changes to measured neurophysiological signals. The active commutator is fully open source, can be assembled using readily available off-the-shelf components, and is compatible with a wide variety of miniaturized neurophotonic and neurophysiology devices.

Autonomous Vision-Based Navigation and Stability Augmentation Control of a Biomimetic Robotic Hammerhead Shark

The application potential of robotic fish embedded with intelligent visual navigation algorithms in underwater autonomous operation is on full display recently. However, the existing visual navigation methods are limited by the underwater visual conditions and the motion characteristics of robotic fish. To this end, this paper proposes a novel autonomous navigation framework integrated with visual stabilization control. In practice, a stereo vision-based navigation network is proposed to generate the guidance law. On this basis, a biomimetic robotic hammerhead shark with a controllable cephalofoil is developed, and a nonlinear model predictive controller for cephalofoil stabilization relying on the dynamic model is elaborately designed. Extensive simulations and underwater experiments are conducted to validate the effectiveness and superiority of the proposed methods, which significantly enhance exploration efficiency and reduce image jitter by 26.02% compared to the traditional methods. The obtained results provide a new idea for underwater robots to autonomously explore the ocean. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper is motivated by the problem of vision-based underwater autonomous navigation for a biomimetic robotic fish that possesses underwater visual stability and good maneuverability. The existing visual navigation networks usually generate unexpected navigation instructions when dealing with complex or ambiguous underwater scenes. Additionally, image jitter caused by the rhythmic motion of robotic fish can lead to navigation failure. This paper suggests an integrated navigation framework that includes a biomimetic platform design, a visual stabilization controller, and an intelligent underwater navigation network. Specifically, a novel sphyrnidae-inspired robotic shark is designed as a new platform with superior motion performance. To enhance underwater visual stability, a nonlinear model predictive control-based visual stabilization controller is proposed. Furthermore, a deep stereo attention navigation network based on a parallax attention mechanism is proposed to improve the generalization of vision-based autonomous navigation. A series of underwater search experiments on the robotic shark demonstrate the effectiveness and superiority of the proposed navigation framework. Hopefully, our proposed methods can provide valuable guidance and support for universal underwater robot navigation to accomplish practical marine tasks, such as underwater rescue, resource exploitation, biological observation, and so on.

Snow Depth Extraction From Time‐Lapse Imagery Using a Keypoint Deep Learning Model

AbstractSnow pole time‐lapse photography, in which a snow pole of a known height is installed in front of a camera and photographed repeatedly over the course of a snow season, allows a large network of sites to be established relatively quickly and affordably. However, current approaches for extracting snow depth from snow poles typically relies on time intensive manual photo processing. By integrating computer vision algorithms with snow pole photography, we present a method that uses a keypoint detection model to automatically observe snow height across a network of sites. At 20 snow pole locations from Grand Mesa, CO (n = 9,722 images), our model successfully predicts the top and bottom of the pole with a mean absolute error (MAE) of 1.30 cm. To assess model generalizability, we tested the model on 12 sites in Washington State (n = 1,770 images). When the Colorado trained model was fine‐tuned using a subset of Washington images, the model predicted snow depth with a MAE of 4.0 cm. Best performance was achieved when both data sets were included during training, with a MAE of 2.05 cm for Colorado images and a MAE of 1.14 cm for Washington images. We demonstrate that, especially when trained using a subset of site‐specific data, a keypoint detection model can accelerate snow pole automation. This algorithm brings the hydrology community one step closer to a generalized snow pole detection model, and we call for a future model that integrates across time‐lapse images from additional locations.

Computer Vision Implementation in Computerized Telescope as a Fine Pointing Mechanism

Abstract Optical satellite communication researches have been increasing in recent years. The continuous miniaturization of components, as well as the need for higher bandwidths, has led to higher frequency applications and narrower beams. For these technologies to work properly, it is needed to achieve a precise line-of-sight between transmitters and receivers, thus a strict pointing system. This research shows the use of computer vision as a microradian fine pointing mechanism to achieve the tracking and detection of objects in distances of around 300 m. As a demonstration of the computer vision algorithm, a drone is tracked and correctly detected by a computer, using a computerized telescope as the optical ground station.