Point Extraction Research Articles

Three-dimensional hullform reconstruction from two-dimensional drawings based on image processing techniques

Abstract Repair shipyards sometimes need three-dimensional geometry for repairs and retrofits. However, they often create models manually from two-dimensional drawings provided by ship owners. In this case, human error leads to inaccuracies, making the process time-consuming and laborious. Therefore, there is a need for research on efficient three-dimensional hullform reconstruction from two-dimensional drawings. This study proposed a method to automatically extract points from two-dimensional lines and visualize them in three dimensions. The proposed method consists of three steps. The first step is a point extraction through image processing, which uses a starting point search algorithm to access overlapping or intersection lines and extracts the points on the lines in the drawing by searching for paths between the starting point and the end point entered by the user. The second step is the transformation of the extracted data, which transforms the points based on pixel coordinate into 3D points through coordinate transformation and scaling by utilizing the stored line data and three-dimensional coordinate information. The last step is to visualize the transformed data as a real three-dimensional model with point visualization. This study demonstrates that the proposed method can be effectively utilized by detecting two-dimensional lines and reconstructing the hullform in three dimensions.

Edge Consistency Feature Extraction Method for Multi-Source Image Registration

Multi-source image registration has often suffered from great radiation and geometric differences. Specifically, grayscale and texture from similar landforms in different source images often show significantly different visual features, and these differences disturb the corresponding point extraction in the following image registration process. Considering that edges between heterogeneous images can provide homogeneous information and more consistent features can be extracted based on image edges, an edge consistency radiation-change insensitive feature transform (EC-RIFT) method is proposed in this paper. Firstly, the noise and texture interference are reduced by preprocessing according to the image characteristics. Secondly, image edges are extracted based on phase congruency, and an orthogonal Log-Gabor filter is performed to replace the global algorithm. Finally, the descriptors are built with logarithmic partition of the feature point neighborhood, which improves the robustness of the descriptors. Comparative experiments on datasets containing multi-source remote sensing image pairs show that the proposed EC-RIFT method outperforms other registration methods in terms of precision and effectiveness.

Accurate deformation analysis based on point position uncertainty estimation and adaptive projection point cloud comparison

The accuracy of the scanning scene representation and corresponding points extraction are key factors in deformation analysis based on point cloud. Still, little is known about the influence of terrestrial laser scanner (TLS) survey properties on point cloud. In our study, an accurate deformation analysis method based on point position uncertainty estimation and adaptive projection point cloud comparison is proposed, which consists of two parts: (1) Evaluating the influence of scanning geometry on point cloud quality to gain high accuracy points; (2) an adaptive projection radius and depth point cloud comparison algorithm is constructed for acquiring corresponding points and calculating the deformation. A regular geometry and a landslide point cloud are selected. Results show that the mean error and mean absolute deviation of the distance between corresponding points are –0.3 mm and 16.2 mm, which demonstrates the method can provide an effective solution for the deformation analysis of complex topography.

A monocular visual SLAM system augmented by lightweight deep local feature extractor using in-house and low-cost LIDAR-camera integrated device

ABSTRACT Simultaneous Localization and Mapping (SLAM) has been widely used in emergency response, self-driving and city-scale 3D mapping and navigation. Recent deep-learning based feature point extractors have demonstrated superior performance in dealing with the complex environmental challenges (e.g. extreme lighting) while the traditional extractors are struggling. In this paper, we have successfully improved the robustness and accuracy of a monocular visual SLAM system under various complex scenes by adding a deep learning based visual localization thread as an augmentation to the visual SLAM framework. In this thread, our feature extractor with an efficient lightweight deep neural network is used for absolute pose and scale estimation in real time using the highly accurate georeferenced prior map database at 20cm geometric accuracy created by our in-house and low-cost LiDAR and camera integrated device. The closed-loop error provided by our SLAM system with and without this enhancement is 1.03m and 18.28m respectively. The scale estimation of the monocular visual SLAM is also significantly improved (0.01 versus 0.98). In addition, a novel camera-LiDAR calibration workflow is also provided for large-scale 3D mapping. This paper demonstrates the application and research potential of deep-learning based vision SLAM with image and LiDAR sensors.

Application of Feature Point Matching Technology to Identify Images of Free-Swimming Tuna Schools in a Purse Seine Fishery

Tuna fish school detection provides information on the fishing decisions of purse seine fleets. Here, we present a recognition system that included fish shoal image acquisition, point extraction, point matching, and data storage. Points are a crucial characteristic for images of free-swimming tuna schools, and point algorithm analysis and point matching were studied for their applications in fish shoal recognition. The feature points were obtained by using one of the best point algorithms (scale invariant feature transform, speeded up robust features, oriented fast and rotated brief). The k-nearest neighbors (KNN) algorithm uses ‘feature similarity’ to predict the values of new points, which means that new data points will be assigned a value based on how closely they match the points that exist in the database. Finally, we tested the model, and the experimental results show that the proposed method can accurately and effectively recognize tuna free-swimming schools.

Improved AEB algorithm combined with estimating the adhesion coefficient of road ahead and considering the performance of EHB

This paper proposes an improved autonomous emergency braking (AEB) algorithm intended for intelligent vehicle. Featuring a combination with the estimation of road adhesion coefficient, the proposed approach takes into account the performance of electronic hydraulic brake. In order for the accurate yet fast estimate of road ahead adhesion coefficient, the expectation maximization framework is applied depending on the reflectivity of ground extracted by multiple beams lidar in four major steps, which are the rough extraction of ground points based on 3 σ criterion, the accurate extraction of ground points through principal component analysis (PCA), the main distribution characteristics of ground as extracted using the expectation maximum method (EM) and the estimation of road adhesion coefficient via joint probability. In order to describe the performance of EHB, the response characteristics, as well as the forward and adverse models of both braking pressure and acceleration are obtained. Then, with two typical roads including single homogeneous road and fragment pavement, the safe distance of improved AEB is modeled. To validate the algorithm developed in this paper, various tests have been conducted. According to the test results, the reflectivity of laser point cloud is effective in estimating the road adhesion coefficient. Moreover, considering the performance of EHB system, the improved AEB algorithm is deemed more consistent with the practicalities.

Recommendation of Search Trajectories to Travel Package for Real Time

Ongoing years have seen an expanded interest in recommender frameworks. Notwithstanding huge advancement in this field, there still stay various roads to investigate. Surely, this work gives an investigation of misusing on the web travel data for customized travel bundle suggestion. A basic test along this line is to address the remarkable attributes of movement information, which recognize travel bundles from customary things for proposal. With that in mind, in this work, we initially dissect the qualities of the current travel bundles and build up a traveler region season subject (TAST) model. This TAST model can address travel bundles and sightseers by various subject disseminations, where the point extraction is molded on both the vacationers and the inherent highlights (i.e., areas, travel periods) of the scenes. GPS empowers cell phones to constantly give new freedoms to improve our day by day lives. For instance, the information gathered in applications made by Uber or Public Transport Authorities can be utilized to design transportation courses, gauge limits, and proactively recognize low inclusion zones.

Automated Mosaicking of Medical x-ray Images using SIFT Algorithm

Image registration is a process of joining any number of images that have similar overlapping regions of the same scene in order to make a panoramic image. In the field of medical, multimedia, and image processing applications image registration process stands challenging. The work presented here on medical images can be applicable for long limb operations and scoliosis operations. Traditional x-ray machines produce a single frame of x-ray image containing a portion of the body part, but they can not generate a large view of body x-ray image in a single frame. This problem can be solved by creating panoramic images by combining multiple images. The work proposed in this paper can automatically produce panoramic x-ray images by stitching multiple x-ray images. The proposed work uses scale-invariant feature transform (SIFT) for mosaicking x-ray images as a local feature point extractor which uses the difference of Gaussian (DOG) and invariant to orientation and scale. Based on the location relationship of x-ray images, random sample consensus (RANSAC) is incorporated to remove the effect of mismatched point pairs in x-ray images and to generate the panoramic view. The performance of the system is computed by using structural and time constraint parameters and is compared with different feature detection techniques. The experimental results show that combing SIFT and RANSAC yields less processing time with an increase in similarity measures.

A Comparative Study about Data Structures Used for Efficient Management of Voxelised Full-Waveform Airborne LiDAR Data during 3D Polygonal Model Creation

In this paper, we investigate the performance of six data structures for managing voxelised full-waveform airborne LiDAR data during 3D polygonal model creation. While full-waveform LiDAR data has been available for over a decade, extraction of peak points is the most widely used approach of interpreting them. The increased information stored within the waveform data makes interpretation and handling difficult. It is, therefore, important to research which data structures are more appropriate for storing and interpreting the data. In this paper, we investigate the performance of six data structures while voxelising and interpreting full-waveform LiDAR data for 3D polygonal model creation. The data structures are tested in terms of time efficiency and memory consumption during run-time and are the following: (1) 1D-Array that guarantees coherent memory allocation, (2) Voxel Hashing, which uses a hash table for storing the intensity values (3) Octree (4) Integral Volumes that allows finding the sum of any cuboid area in constant time, (5) Octree Max/Min, which is an upgraded octree and (6) Integral Octree, which is proposed here and it is an attempt to combine the benefits of octrees and Integral Volumes. In this paper, it is shown that Integral Volumes is the more time efficient data structure but it requires the most memory allocation. Furthermore, 1D-Array and Integral Volumes require the allocation of coherent space in memory including the empty voxels, while Voxel Hashing and the octree related data structures do not require to allocate memory for empty voxels. These data structures, therefore, and as shown in the test conducted, allocate less memory. To sum up, there is a need to investigate how the LiDAR data are stored in memory. Each tested data structure has different benefits and downsides; therefore, each application should be examined individually.

A New Enrichment Method for Quantification of 5-Hydroxymethylfurfural by Indirect Flame Atomic Absorption Spectrometry in Honey and Jam Samples.

Because of increasing amounts of 5-hydroxymethylfurfural (5-HMF) in processed foods and the complexity of the matrix, monitoring of trace 5-HMF requires accurate and reliable methods. Hence, an efficient sample pretreatment procedure is necessary for extraction and preconcentration of 5-HMF from the matrix. In this study, a new and efficient sample preparation method utilizing ultrasound-assisted-cloud point extraction (UA-CPE), indirectly followed by flame atomic absorption spectrometry (FAAS), was introduced for the monitoring of trace amounts of 5-HMF in honey and jam samples. With this method, hydroxylamine was used as a derivatizing agent in the presence of Mn(II) and an anionic surfactant, SDS for extraction of 5-HMF at pH 9.0. For dispersing reagents in sample solution, low amounts of mixed surfactant, triton X-45 and SDS were mixed and fast-injected into the extraction media. A cloudy solution formed, and after reaction of 5-HMF with reagents, the cloudy solution was centrifuged. The extracted 5-HMF in the surfactant-rich phase was dissolved in acidic acetone and indirectly analyzed by FAAS. The method showed a detection limit of 1.27 μg/L in linear working range of 4-240 μg/L, good precision (2.3-6.5%), and recovery rates (93.5-97%) after preconcentration of 70-fold. Within this study, an accurate and reliable method for the indirect quantification of 5-HMF in selected samples was successfully developed with a sensitivity improvement factor of 30.6. The figures of merit for the developed indirect method were appropriate. The applicability of the method for the analysis of 5-HMF in processed foods was excellent.

Automated Tax Mapping from UAV Multispectral Imagery

Tax mapping is an essential element for efficient management of real estate property and tax management, paving the way for effective implementation of g-governance practices in India. Conventional mapping of individual buildings and their attributes involves large effort and is time-consuming. The use of high-resolution UAV imagery facilitates the process of automatic extraction of land parcel, roof area and height by providing accurate and latest building and landuse information for improved tax assessment and collection. Image segmentation has been performed on UAV imagery applied to differentiate rooftop surfaces from other features such as roads and vegetation using gray level thresholding. An example-based feature extraction algorithm was adopted to extract the land parcel and rooftop surfaces from the segmented image. Further, DSM and DTM derived from UAV imagery were used to determine the height of the buildings by extraction of terrain points and rooftop points. The extracted building height was used to estimate the numbers of floors in the building using thresholding. The number of floors and rooftop area were used to derive the total floor area of each building. The property tax to be levied for each building was calculated automatically using total floor area in efficient and scientific manner. The UAV imagery used in the study enabled rapid mapping of buildings parcels for tax assessment compared to conventional mapping methods.

Small Moving Target Recognition in Star Image with TRM

Recognition of small moving targets in space has become one of the frontier scientific researches in recent decade. Most of them focus on detection and recognition in star image with sidereal stare mode. However, in this research field, few researches are about detection and recognition in star image with track rate mode. In this paper, a novel approach is proposed to recognize the moving target in single frame by machine learning method based on elliptical characteristic extraction of star points. The technical path about recognition of moving target in space is redesigned instead of traditional processing approaches. Elliptical characteristics of each star point can be successfully extracted from single image. Machine learning can achieve the classification goal in order to make sure that all moving targets can be extracted. The experiments show that our proposed approach can have better performance in star images with different qualities.

Use of new polymeric composites for preconcentration of trace Ag+ ions from the selected mushroom/vegetables by ultrasound-assisted cloud-point extraction coupled to microvolume UV-Vis spectrophotometry

ABSTRACT The magnetic nano-composites based on the tris(hydroxymethlmethyl)aminomethane-modified maleic anhydride-co-styrene copolymers and Fe3O4 nano-particles were prepared as new potential chelating agents for ultrasound-assisted-cloud point extraction (UA-CPE) and pre-concentration of trace levels of Ag+ ions from aqueous solutions. The structures of the nano-composites were characterised via FT-IR, 1H-NMR and XRD analysis. After structural characterisation of composites, Ag+ ions were detected by micro-volume UV-vis spectrophotometry at 347 nm. The variables affecting complex formation and extraction efficiency for separation/pre-concentration of the Ag+ ions from various food matrices were evaluated and optimised in detail. Under the optimised conditions, the method shows a good sensitivity with linearity range from 10 to 350 µg L−1 and 4 to 160 µg L−1 for amidic and imidic composites, respectively, with a better correlation coefficient than 0.9825. The limits of detection, intra- and inter-day precision (as RSDs%) and recovery rates for six replicate determinations of Ag+ ions at levels of 25 and 100 μg L−1 were 4.28/1.21 μg L−1, 2.4–4.1% and 92–98% for the modified copolymers, respectively. The pre-concentration factor for Ag+ ion from pre-concentration of 35-mL sample was 70. A significant matrix effect was not observed for the triplicate measurements of 100 µg L−1 Ag+ in the presence of various interfering species below their maximum concentrations allowed in this method, for Ag+ ions. The accuracy of the method was confirmed by analysis of the two certified samples. The method was successfully applied to determine low levels of Ag+ ions in mushroom and vegetable samples, and satisfactory recoveries were obtained in the range of 91-97% with lower RSD than 5.1% for the spiked samples.

Automatic Extraction of Structural and Non-Structural Road Edges from Mobile Laser Scanning Data.

Accurate road information is important for applications involving road maintenance, intelligent transportation, and road network updates. Mobile laser scanning (MLS) can effectively extract road information. However, accurately extracting road edges based on large-scale data for complex road conditions, including both structural and non-structural road types, remains difficult. In this study, a robust method to automatically extract structural and non-structural road edges based on a topological network of laser points between adjacent scan lines and auxiliary surfaces is proposed. The extraction of road and curb points was achieved mainly from the roughness of the extracted surface, without considering traditional thresholds (e.g., height jump, slope, and density). Five large-scale road datasets, containing different types of road curbs and complex road scenes, were used to evaluate the practicality, stability, and validity of the proposed method via qualitative and quantitative analyses. Measured values of the correctness, completeness, and quality of extracted road edges were over 95.5%, 91.7%, and 90.9%, respectively. These results confirm that the proposed method can extract road edges from large-scale MLS datasets without the need for auxiliary information on intensity, image, or geographic data. The proposed method is effective regardless of whether the road width is fixed, the road is regular, and the existence of pedestrians and vehicles. Most importantly, the proposed method provides a valuable solution for road edge extraction that is useful for road authorities when developing intelligent transportation systems, such as those required by self-driving vehicles.

Cloud point extractors for simultaneous determination of Pd and Pt in water samples by ICP OES with multivariate optimisation

- Palladium and platinum preconcentration in water samples prior to ICP OES determination. - Friendly solvents extraction for noble's metals investigation in aquatic compartments. - The use of the labilising agents for reduction the inertia of the chlorocomplexes in CPE methods. - Multivariate optimisation in cloud point extraction. Catalysts used in the combustion process inside vehicles, palladium (Pd) and platinum (Pt), can be released to the atmosphere and deposited in aquatic environments. Thus, a simple and environmentally friendly method was developed for simultaneous Pd and Pt determination by ICP OES in aqueous samples. Cloud point extractions (CPE) combined with a factorial design were employed to achieve method accuracy. The extraction was facilitated based on the interaction between a reducing (labilising) agent in hydrochloric acid medium together with the analytes. The cloud point solution (CPS) was composed of the non-ionic surfactant (Triton X-114), the chelating agent 2-mercaptobenzothiazole (2-MBT), the labilising agent tin chloride (SnCl 2 ) or potassium iodide (KI) as well as HCl. The analytical curves were linear in the range of 5–100 μg L −1 with detection limits of 0.525 and 0.752 μg L −1 for Pd and Pt, respectively. Factorial design, considering the concentration of Triton X-114, 2-MBT, HCl, SnCl 2 and KI, was used to optimise the analytical protocol. The proposed method was successfully applied in samples of tap, fresh, and saline waters.

Remote Sensing Image Registration Based on Dynamic Threshold Calculation Strategy and Multiple-Feature Distance Fusion

Remote sensing image registration is widely used in civilian and military applications such as target recognition, environmental transformation monitoring, and military damage assessment. The severe outliers in the extraction of feature points caused by nonrigid transformation and viewpoint changes in the process of capturing remote sensing images increase the difficulty of registration. Therefore, we present a remote sensing image registration method based on dynamic threshold calculation strategy (DTCS) and multiple-feature distance fusion. The main idea of our approach is to maximize inliers while ensuring the optimal correspondence. First, DTCS gradually screens reliable inliers to reduce the negative effect of outliers over the iterations. The multiple-feature distance fusion Gaussian mixture model is then introduced to compensate for the defect of a single feature, and DTCS acting as the prior probability combines with the deterministic annealing to achieve the optimal mapping from local to global scale. Moreover, structure constraint based on local applying force is added into the global constraint to control the alignment of feature points more accurately in the overlapping area, so as to guide the subsequent image transformation. Extensive experiments show that our method performs better in most cases compared with nine state-of-the-art methods.

Simultaneous Determination of Brilliant Green and Basic Fuchsin by Cloud Point Extraction–scanometry

In this study, cloud point extraction‒scanometry as a new, simple and inexpensive method was developed for the separation, preconcentration and determination of trace amounts of brilliant green (BG) and basic fuchsin (BF) in mixture. The method is based on the extraction of analytes simultaneously from aqueous solution using a non-ionic surfactant Triton X-114 as a cloud point extractor. After phase separation, the surfactant-rich phase was diluted with ethanol, digital image of the solution taken with a flatbed scanner and RGB parameters of the enriched analytes were calculated by special software written in visual basic (VB 6). The influence of analytical parameters including pH of system, the concentration of the surfactant, equilibration temperature and time were optimized. The method was linear in the concentration ranges of 0.025‒1.00 and 0.05‒2.50 mg/L with limits of detection of 0.008 and 0.019 mg/L for BG and BF, respectively. The preconcentration factors were 29 for BG and 28 for BF. The enrichment factors were found to be 34 and 16, precision (RSD, %) of the method, 1.9 and 1.3% for BG and BF, respectively. The effects of interfering ions and dyes were investigated. Finally, the proposed method was applied for the determination of BG and BF in real water samples with satisfactory results.

Chronic wound assessment and infection detection method

BackgroundNumerous patients suffer from chronic wounds and wound infections nowadays. Until now, the care for wounds after surgery still remain a tedious and challenging work for the medical personnel and patients. As a result, with the help of the hand-held mobile devices, there is high demand for the development of a series of algorithms and related methods for wound infection early detection and wound self monitoring.MethodsThis research proposed an automated way to perform (1) wound image segmentation and (2) wound infection assessment after surgical operations. The first part describes an edge-based self-adaptive threshold detection image segmentation method to exclude nonwounded areas from the original images. The second part describes a wound infection assessment method based on machine learning approach. In this method, the extraction of feature points from the suture area and an optimal clustering method based on unimodal Rosin threshold algorithm that divides feature points into clusters are introduced. These clusters are then merged into several regions of interest (ROIs), each of which is regarded as a suture site. Notably, a support vector machine (SVM) can automatically interpret infections on these detected suture site.ResultsFor (1) wound image segmentation, boundary-based evaluation were applied on 100 images with gold standard set up by three physicians. Overall, it achieves 76.44% true positive rate and 89.04% accuracy value. For (2) wound infection assessment, the results from a retrospective study using confirmed wound pictures from three physicians for the following four symptoms are presented: (1) Swelling, (2) Granulation, (3) Infection, and (4) Tissue Necrosis. Through cross-validation of 134 wound images, for anomaly detection, our classifiers achieved 87.31% accuracy value; for symptom assessment, our classifiers achieved 83.58% accuracy value.ConclusionsThis augmentation mechanism has been demonstrated reliable enough to reduce the need for face-to-face diagnoses. To facilitate the use of this method and analytical framework, an automatic wound interpretation app and an accompanying website were developed.Trial registration201505164RIND, 201803108RSB.

High-Precision Extraction of Segment Points of 2D Profiles Based on a Dynamic Grid Method

In order to improve the reconstruction precision and performance of 2D profiles, this paper presents a new high-precision extraction method of segment points of 2D profile features. Firstly, we extract the intervals which include initial segment points based on the curvature information of data points. Secondly, a grid is dynamically constructed in the interval and all the nodes of the grid are considered as candidate segment points for an optimization process. Thirdly, the optimization model of each feature curve is constructed on the basis of boundary constraints. Selection of the optimal segment point is related to two factors: the number of control points of B-spline and the total approximation error of all collected points to the fitted curves. Numerical experiments were conducted and the results demonstrate the efficacy of our method in capturing design intent and in industrial applications, compared to existing methods.

Determination of solubilization isotherm in micelles of non-ionic surfactant L62 for butanol extraction

Earlier studies with extractive butanol fermentation using non-ionic surfactant L62 showed significant increase in butanol titer by 50–125%. Butanol was further separated from fermentation broth using L62 in a cloud point extraction system. The present work was undertaken to determine the solubilization of butanol in L62-water system. Experiments were conducted to study the effect of different parameters on butanol extraction efficiency. Optimum conditions i.e. 3% L62 (v/v) with 4% (v/v) butanol concentration at 45 °C for 30 min resulted into extraction efficiency of 40.8% (w/w). The Langmuir isotherm was fitted and isotherm parameters were found to be m = 129.87 (mol/mol) and n = 0.308 (L/mol). Langmuir isotherm with estimated parameters was used to predict the surfactant concentration to extract butanol with desired efficiency. Predicted and experimental results were in close agreement (96% accuracy). Thus, Langmuir model can be successfully used to design the cloud point extractor and predict the extraction efficiency/surfactant concentration for L62-butanol-water system with great accuracy.