Contour Detection System Research Articles

Research on Scheme Design and Structure Optimization of High Speed and High Precision Vehicle Contour Detection Platform

To improve road traffic safety and reduce the incidence of unauthorized vehicle modifications, overloading, and oversizing, this study proposed a detection platform structure to support the quick measurement of key dimensions and high-precision reconstruction of local features using the automotive contour size system. Using CAE technology, static and dynamic characteristic analysis was performed on the platform structure, and optimization design was conducted on the column frame and gantry frame separately. The optimized column frame's first-order modal frequency increased by 243% from 5.16 Hz to 17.65 Hz, with an average optimization ratio of 187% for the first six modal frequencies. For the optimized gantry frame, the average optimization ratio of the key node displacement exceeded 46%, with the first-order modal frequency increasing by 13% from 36.43 Hz to 41.33 Hz, and an average optimization ratio of 21% for the first six modal frequencies. Ultimately, the optimized detection platform's key nodes achieved an average optimization ratio of nearly 60%, with the first-order modal frequency increasing by 240% from 5.16 Hz to 17.57 Hz and an average optimization ratio of 185% for the first six modal frequencies. The optimized platform structure provides robust support for the high-speed and high-precision vehicle contour detection system's implementation.

RGB-BASED DEEP SURFACE WATER CONTOUR DETECTION

Abstract. The application of remote monitoring of surface water has focused primarily on the detection of water bodies using expensive multi-spectral IR sensors. However, critical information about surface water bodies, particularly the dynamic behavior, is better derived from water contours. We show that water body detection is inadequate in accurately capturing the contours. Furthermore, we argue that RGB-based detection should be sufficient for accurate water detection. We present a new global dataset of remote sensing images obtained from Sentinel-2 and Landsat-8 missions and contour labeled to assist in this effort. We propose a unique UNet-style contour detection system that utilizes multiscale filters to detect contours accurately. Comparisons between our proposed system, existing water detection, and other segmentation and contour detection systems show the system's effectiveness in detecting water.

Modeling and detection of the prepared tool edge radius.

High-speed and high-efficient machining is the inevitable development direction of machining technology. The tool edge preparation can improve the life, cutting performance, and surface quality of a tool and help to achieve high-speed and efficient machining. Therefore, precise modeling and detection of the micron-level contour of a tool edge are crucial for edge preparation. The aim of this study is to provide the model and detect method of the prepared tool edge radius. The mathematical model of the milling tool trajectory is established through the Matlab. The material removal model by single abrasive particle is established based on the energy conservation principle and energy absorption theory. The material removal model by multiple abrasive grains on the cutting tool edge is constructed using the statistical methods. The mathematical model of the edge radius is established through the geometrical relationship. The milling edge preparation contour detection system is setup based on the machine vision principle through LabVIEW software. Finally, the edge radius at different process parameters is determined by the mathematical model and detection system, and the results are compared with the results of the scanning electron microscopic measurement (SEM). Through the Comparison and analysis of the edge radius measured by the SEM and calculated by the proposed model. The maximum error between the analytical results and SEM measurements is 11.18 μm, while the minimum error is 0.07 μm. Through the comparison and analysis of the edge radius measured by the SEM and the edge detection system. The maximum difference between the two methods is 2.71 μm, and the minimum difference is 0.31 μm. The maximum difference in percentage is 9.2%, and the minimum difference in percentage is 1.2%. The edge preparation mechanisms of a single particle and multiple particles on the tool edge are explained. A mathematical model of the edge radius is established, which provides a basis for a deeper understanding of the edge preparation effect. Based on the machine vision principle, the prepared tool micron-level edge detection method is proposed. The histogram specification method, median filtering, multi-threshold segmentation method, and Canny edge detection operator are adopted to obtain the edge contour. The comparison result shows that the mathematical model of the edge radius is accurate, and the proposed tool edge detection method is feasible, which lays the foundation for edge preparation and realization of high-speed and high-efficient machining.

High-precision diameter detector and three-dimensional reconstruction method for oil and gas pipelines

This paper considers the shape detection of the oil and gas-transport pipeline. Currently, deformation of long-distance pipelines has become an urgent problem to the security and capacity of oil and gas transmission, imposing new requirements of a diameter detector of high accuracy and three-dimensional reconstruction functionality. In this paper, high-precision diameter detection technology for use in an oil and gas pipeline is first presented to precisely detect deformation of a pipeline. Next, by detecting the shape of the pipe inner wall and analyzing the attitude and position relationship of the diameter-detector and the pipeline, we developed a three-dimensional reconstruction model of the detected pipeline based on coordinate transformation and the least-squares method. Furthermore, based on the proposed diameter detection technology, a prototype “DN800 diameter-detector” is developed for detecting pipeline in both radial and circumferential directions. Finally, an experimental study was performed to verify the availability and accuracy of the detector. The experimental results show that the developed contour detection system of the pipeline is an effective instrument to detect the deformation of oil and gas pipelines.

Design of Automatic Contour Detection System of Open Arc Welding Workpiece

This paper designs an automatic contour detection system of open arc welding workpiece. The realization of the device is the first step to achieve automatic control system of welding processes. Firstly it summarizes the difficulties must be solved in the design of detection system. According to the requirements, an electromechanical system is designed. The performance has been analyzed by simulation .An experiment has been done to verify the prototype. The results show the design meets the requirements.

Design of Surface Contour Detection System Based on SCM

An automatic surface contour detection system was designed. The detection precision of two sensors and the transmission accuracy of screw were important factors influencing the characteristics of the detection system. A laser displacement sensor and cable-displacement sensor were chosen in this system, which both have high precision and easy work principles. Bluetooth module could realize interaction between SCM and PC reliably and quickly in close range. After programming interaction interface using LabView, the surface contour of measured part could be acquired in real-time.

Increasing the efficiency of systems for the detection of the contours of parts on the basis of Hough’s transformation

Hough’s transformation, which is used in systems for the detection and control of the geometric parameters of parts, along with the complex influence of different sets of filters in a contour detection system are considered. The basic methods of filtration that promote suppression of noise, the elimination of false contours, tapering of the edges of contours, and the removal of residual noise in the form of unconnected points of a contour are described. A quantitative estimate of the efficiency gained with the use of these filters is given from the results of tests.

Multicenter assessment of the reproducibility of volumetric radiofrequency-based intravascular ultrasound measurements in coronary lesions that were consecutively stented

To assess in a multicenter design the between-center reproducibility of volumetric virtual histology intravascular ultrasound (VH-IVUS) measurements with a semi-automated, computer-assisted contour detection system in coronary lesions that were consecutively stented. To evaluate the reproducibility of volumetric VH-IVUS measurements, experienced analysts of 4 European IVUS centers performed independent analyses (in total 8,052 cross-sectional analyses) to obtain volumetric data of 40 coronary segments (length 20.0 ± 0.3 mm) from target lesions prior to percutaneous intervention that were performed in the setting of stable (65%) or unstable angina pectoris (35%). Geometric and compositional VH-IVUS measurements were highly correlated for the different comparisons. Overall intraclass correlation for vessel, lumen, plaque volume and plaque burden was 0.99, 0.92, 0.96, and 0.83, respectively; for fibrous, fibro-lipidic, necrotic core and calcified volumes overall intraclass correlation was 0.96, 0.94, 0.98, and 0.99, respectively. Nevertheless, significant differences for both geometrical and compositional measurements were seen. Of the plaque components, fibrous tissue and necrotic core showed on average the highest measurement reproducibility. A central analysis for VH-IVUS multicenter studies of lesions prior to PCI should be pursued. Moreover, it may be problematical to pool VH-IVUS data of individual trials analyzed by independent centers.

Between-centre reproducibility of volumetric intravascular ultrasound radiofrequency-based analyses in mild-to-moderate coronary atherosclerosis: an international multicentre study

To assess for the first time in a multicentre design the between-centre reproducibility of volumetric virtual histology intravascular ultrasound (VH-IVUS) measurements with a semi-automated, computerassisted contour detection system in mild-to-moderately diseased coronary segments.Analysts of four European IVUS centres performed independent IVUS analyses (in total 7,188 cross-sectional analyses) and obtained volumetric data to evaluate the reproducibility of volumetric VH-IVUS measurements in 36 coronary segments (length 20.0+/-0.4 mm) from patients with stable angina. Geometric and compositional VH-IVUS measurements were highly correlated for the different comparisons. Overall intraclass correlation for vessel, lumen, plaque volume and plaque burden were 0.98, 0.92 0.95, and 0.86, respectively; for fibrous, fibro-lipidic, necrotic core and calcified volumes overall intraclass correlations were 0.95, 0.93, 0.99, and 1.00, respectively. There were significant but small differences for vessel, lumen, fibrous and calcified volumes, and there was no significant difference for plaque volume. Of the plaque components necrotic core and calcified volume showed on average the highest reproducibility.These findings underline the necessity to centrally analyse IVUS data obtained in multicentre studies addressing mild-to-moderately diseased coronary arteries. In addition, pooling VH-IVUS data from different studies, analysed at different centres, may be problematical.

Quantitative measurements in IVUS images.

IntraVascular UltraSound (IVUS) is a catheter-based technique which provides real-time high resolution tomographic images of both the lumen and arterial wall of a coronary segment, this in contrast to X-ray arteriography that provides a shadow image (luminogram) of the entire lumen. Nowadays the lumen and vessel parameters are measured manually, which is very time consuming and suffers from high inter- and intra-obser variability. With the continuing improvement in IVUS imaging, it is now feasible to develop and clinically apply automated methods of three-dimensional quantitative analysis of the coronary vessel morphology in an objective and reproducible way with automated contour detection techniques (QCU). Quantification, in 2D and 3D, as well as volume rendering for visualization of the IVUS images requires segmentation of the images (contour detection). The 3D contour detection system described in this article is based on the combination of contour detection in the transversal and sagital view. This article provides some of the basic principles of IVUS, the IVUS image quantification, the three-dimensional reconstruction and the contour detection and quantification in three-dimensional IVUS images.

Computerized assessment of coronary lumen and atherosclerotic plaque dimensions in three-dimensional intravascular ultrasound correlated with histomorphometry

Intravascular ultrasound (IVUS), which depicts both lumen and plaque, offers the potential to improve on the limitations of angiography for the assessment of the natural history of atherosclerosis and progression or regression of the disease. To facilitate measurements and increase the reproducibility of quantitative IVUS analyses, a computerized contour detection system was developed that detects both the luminal and external vessel boundaries in 3-dimensional sets of IVUS images. To validate this system, atherosclerotic human coronary segments (n = 13) with an area obstruction ≥40% (40% to 61%) were studied in vitro by IVUS. The computerized IVUS measurements (areas and volumes) of the lumen, total vessel, plaque-media complex, and percent obstruction were compared with findings by manual tracing of the IVUS images and of the corresponding histologic cross sections obtained at 2-mm increments (n = 100). Both area and volume measurements by the contour detection system agreed well with the results obtained by manual tracing, showing low mean between-method differences (−3.7% to 0.3%) with SDs not exceeding 6% and high correlation coefficients (r = 0.97 to 0.99). Measurements of the lumen, total vessel, plaque-media complex, and percent obstruction by the contour detection system correlated well with histomorphometry of areas (r = 0.94, 0.88, 0.80, and 0.88) and volumes (r = 0.98, 0.91, 0.83, and 0.91). Systematic differences between the results by the contour detection system and histomorphometry (29%, 13%, −9%, and −22%, respectively) were found, most likely resulting from shrinkage during tissue fixation. The results of this study indicate that this computerized IVUS analysis system is reliable for the assessment of coronary atherosclerosis in vivo.

Features of the angiographic evaluation of the INTACT study

INTACT (International Nifedipine Trial on Antiatherosclerotic Therapy) is a prospective, placebo-controlled, randomized, double-blind, multicenter trial analyzing the influence of 80 mg nifedipine/day on the angiographic progression of early stage coronary atherosclerosis. Coronary angiograms were taken in identical projections before and after a treatment period of 3 years. Quantitative analysis of the angiograms was performed with the computer-assisted contour detection system CAAS. For definition purposes, the coronary artery system was subdivided into 25 different segments, including all anatomic variants. Measurement parameters of segments were mean and minimal diameter, and of stenoses minimal diameter, percentage diameter reduction (at least 20%), length, and plaque area. The variable extent of the changes of these parameters in the different projections analyzed per patient in the two study angiograms was considered by separate computation of the maximal, mean, and minimal changes over these projections; the comparison of the parameter changes between the two treatment groups was performed separately according to these three modes. For all parameters, this comparison was performed on the basis of the individual 25 segments, as well as after aggregation of individual segments to arteries (RCA, LAD, and LCX), to groups of large and small segments, and to the entire coronary artery system. Assessment of changes of the coronary (patho)morphology by quantitative analysis of coronary angiograms is associated with a number of methodical limitations, which may lead to a certain variability of the results. However, due to the double-blind feature of INTACT, this variability should be comparable in the two groups of this study, allowing for a conclusive comparison.

Reproducible uniform coronary vasomotor tone with nitrocompounds: Prerequisite of quantitative coronary angiographic trials

In quantitative analysis of repeated coronary angiograms, a variable vasomotor tone of the epicardial coronary arteries may influence the accuracy of the results. Therefore, we evaluated the extent and reproducibility of coronary artery dilation with nitrocompounds. In 32 patients with coronary artery disease, the vasodilatory response of angiographically normal coronary segments to different nitrocompounds was analyzed with the computer-assisted contour detection system CAAS. Twenty patients received 5 mg or 10 mg of isosorbide dinitrate sublingually. After 10 to 15 min, a maximal diameter increase was measured with an average of 16 +/- 11% (5 mg: P less than 0.01) and 28 +/- 13% (10 mg: P less than 0.001) from control. Another 12 patients received 0.025 mg per kg body weight of SIN-1, the active metabolite of molsidomine, as an intravenous infusion over 5 min. A comparable maximal dilation (29 +/- 5%; P less than 0.001) occurred after 10 to 15 min and could not be enhanced further with 0.8 mg nitroglycerin administered sublingually (28 +/- 7%; n.s.). One hour after square root of Sin-1, coronary dilation was still 24 +/- 8% (P less than 0.001 compared with control), and 0.8 mg of nitroglycerin sublingually reestablished the previous maximal dilation of 28 +/- 8%. We conclude that high doses of nitrocompounds induce a reproducible maximal coronary dilation that eliminates a substantial source of error in quantitative analysis of repeated coronary angiograms. At present, sublingual administrations of either 10 mg isosorbide dinitrate once or 0.8 mg nitroglycerin repeatedly seem to represent the easiest practicable modes to achieve maximal coronary vasodilation for an adequate period.

International nifedipine trial on anti-atherosclerotic therapy (INTACT) — methodologic implications and results of a coronary angiographic follow-up study using computer-assisted film analysis

Animal experiments demonstrated a significant suppressive effect of various calcium channel blockers on the formation of atherosclerotic lesions. Therefore, a prospective, placebo-controlled, randomized, double blind multicenter study was performed to investigate the inhibitory influence of the calcium channel blocker nifedipine (80 mg/day) on the progression of coronary artery disease in man. Study endpoints were changes of coronary morphology documented by coronary angiography with particular respect to the formation of new coronary stenoses. In 348 out of 425 patients included in the study, coronary angiograms were repeated after three years. The angiograms were standardized by induction of a maximal coronary vasodilation with high doses of nitrates and by using absolutely identical angiographic projections. Quantitative analysis of coronary cineangiograms was performed with the computer-assisted contour detection system CAAS. Parameters were mean and minimal diameter of all segments and minimal stenosis diameter, percent diameter stenosis, length and plaque area of all stenoses. Continuous intake of study medication was registered in 282 patients, 134 on nifedipine and 148 patients on placebo. In these patients, a total of 3808 coronary segments with 893 stenoses (greater than or equal to 20% diameter reduction in at least one angiographic projection) were compared on the baseline and follow-up cineangiograms. The changes in all angiographic parameters analyzed averaged over all patients by considering all angiographic projections analyzed, indicated significant progression of the disease (p less than 0.006). The average changes in all parameters were even about three times more profound, when in the individual patients only the respective projections indicating the maximal changes were considered for the calculation (p less than 0.001). However, with neither of these two analysis modes, the differences in progression between the treatment groups were statistically significant. In the follow-up angiograms, a total of 196 new coronary lesions (185 stenoses, 11 occlusions) were found at previously normal arterial sites. In patients on nifedipine, an average of only 0.58 new lesions per patient were detected versus 0.80 lesions per patient on placebo (-27%; p = 0.031). INTACT is the first prospective angiographic trial on the progression of coronary artery disease using computer-assisted quantitative coronary angiography in such a high number of patients. All parameters analyzed indicated significant progression of coronary artery sclerosis. Nifedipine had no influence on the progression of preexisting coronary stenoses, but inhibited significantly the formation of new angiographically recognizable lesions. Further prospective coronary angiographic trials with calcium channel blockers using a comparably exact method are needed to confirm the results of this study.

Coronary vasodilation with dihydropyridines--A pharmacokinetic study

In 26 patients with coronary artery disease, the mean diameters of angiographically 'normal' epicardial coronary arteries were assessed with the aid of a computer-assisted contour detection system (CAAS) before and up to 15 min after onset of a 4-min intravenous-infusion of 2 mg nifedipine (13 patients, group I) or 1 mg nisoldipine (13 patients, group II). Maximal coronary dilation amounted to 20 +/- 9% (4th min) in group I and to 18 +/- 9% (15th min) in group II. In addition, in group II changes of the minimal diameters of 9 coronary obstructions were measured; the maximum increase averaged 28 +/- 15% (7th min). In order to compare the pharmacokinetic properties of these compounds the dilation of the 'normal' coronary segments was correlated with the respective drug plasma levels; maximal plasma concentrations averaged 62 +/- 21 ng ml-1 (7th min) in group I and 17 +/- 7 ng ml-1 (4th min) in group II respectively. A positive, linear correlation between coronary dilation and plasma levels was only found with nifedipine (P less than 0.05); with nisoldipine, however, coronary dilation developed in form of a hysteresis curve, when plotted against plasma levels, probably due to the high receptor affinity of this substance. The prolonged efficacy of nisoldipine could be favourable in oral long-term treatment of patients with coronary artery disease.

Quantitative assessment of regional left ventricular motion using endocardial landmarks

In this study the hypothesis is tested that the motion pattern of small anatomic landmarks, recognizable at the left ventricular endocardial border in the contrast angiocardiogram, reflects the motion of the endocardial wall. To verify this, minute metal markers were inserted in the endocardium of eight pigs with a novel retrograde transvascular approach. Marker motion was subsequently recorded with roentgen cinematography and compared with the motion of the landmarks on the endocardial contours detected from the contrast ventriculogram with an automated contour detection system. Linear regression analysis of the directions of the systolic metal marker and endocardial landmark pathways yielded a correlation coefficient of 0.86 and a standard error of the estimate of 10.3 degrees. Landmark pathways were also measured in 23 normal human left ventriculograms. Normal left ventricular endocardial wall motion during systole, as observed in the 30 degrees right anterior oblique view, is characterized by a dominant inward transverse motion of the opposite anterior and inferoposterior walls and a descent of the base toward the apex. The apex itself is almost stationary. On the basis of these observations, a widely applicable model for the assessment of left ventricular wall motion is described in mathematical terms.