Pair Of Contours Research Articles

An Improved Product Defect Detection Method Combining Centroid Distance and Textural Information

In order to solve the problems of a high mismatching rate and being easily affected by noise and gray transformation, an improved product defect detection method combining centroid distance and textural information is proposed in this paper. Based on image preprocessing, the improved fuzzy C-means clustering method is used to extract the closed contour features. Then, the contour center distance description operator is used for bidirectional matching, and a robust coarse matching contour pair is obtained. After the coarse matching contour pair is screened, the refined matching result is obtained by using the improved local binary pattern operator. Finally, by comparing whether the number of fine matching pairs is consistent with the number of template outlines, the detection of good and bad industrial products is realized, and the closed contour extraction experiment, the anti-rotation matching experiment, the anti-gray difference matching experiment, and the defect detection experiment of three different products are designed. The experimental results show that the improved product defect detection method has good performance in relation to anti-rotation transformation and anti-gray difference, the detection accuracy can reach more than 90%, and the detection time is up to 362.6 ms, which can meet the requirements of industrial real-time detection.

Analyzing the Relationship between Dose and Geometric Agreement Metrics for Auto-Contouring in Head and Neck Normal Tissues.

This study aimed to determine the relationship between geometric and dosimetric agreement metrics in head and neck (H&N) cancer radiotherapy plans. A total 287 plans were retrospectively analyzed, comparing auto-contoured and clinically used contours using a Dice similarity coefficient (DSC), surface DSC (sDSC), and Hausdorff distance (HD). Organs-at-risk (OARs) with ≥200 cGy dose differences from the clinical contour in terms of Dmax (D0.01cc) and Dmean were further examined against proximity to the planning target volume (PTV). A secondary set of 91 plans from multiple institutions validated these findings. For 4995 contour pairs across 19 OARs, 90% had a DSC, sDSC, and HD of at least 0.75, 0.86, and less than 7.65 mm, respectively. Dosimetrically, the absolute difference between the two contour sets was <200 cGy for 95% of OARs in terms of Dmax and 96% in terms of Dmean. In total, 97% of OARs exhibiting significant dose differences between the clinically edited contour and auto-contour were within 2.5 cm PTV regardless of geometric agreement. There was an approximately linear trend between geometric agreement and identifying at least 200 cGy dose differences, with higher geometric agreement corresponding to a lower fraction of cases being identified. Analysis of the secondary dataset validated these findings. Geometric indices are approximate indicators of contour quality and identify contours exhibiting significant dosimetric discordance. For a small subset of OARs within 2.5 cm of the PTV, geometric agreement metrics can be misleading in terms of contour quality.

Correction for geometric distortion in the flattened representation of pipeline external surface

Conventional cameras often produce external pipeline surface images with significant perspective-projection distortions, making determining the type and size of defects on the pipeline surface difficult. To address this issue, we present a novel approach for correcting the geometric distortion of a constant diameter pipeline (CDP) external surface image based on apparent contour pairs (ACPs). First, the camera is calibrated and the real projection position of ACPs accurately extracted. Second, a single-view perspective projection model of the CDP is adopted to realize a three-dimensional reconstruction of the pipeline. Subsequently, the flattened image of the CDP’s outer surface is obtained by performing equidistant sampling of cross sections, determining the visibility of discrete points, and mapping projection points onto a flat surface. Simulations and real experiments demonstrated the high accurate method in the correction of CDP images. Experiments conducted under different outdoor scenarios confirmed the robustness of the proposed method.

GEC-ESTRO (ACROP)–ABS–CBG Consensus Brachytherapy Target Definition Guidelines for Recurrent Endometrial and Cervical Tumors in the Vagina

Representatives from the Gynecologic Groupe European de Curietherapie-European Society for Radiation Therapy and Oncology (GYN GEC-ESTRO), the American Brachytherapy Society (ABS), and the Canadian Brachytherapy Group (CBG) met to develop international consensus recommendations for target definitions for image-guided adaptive brachytherapy for vaginal recurrences of endometrial or cervical cancer. Seventeen radiation oncologists and 2 medical physicists participated. Before an in-person meeting each participant anonymously contoured 3 recurrent endometrial/cervical cancer cases. Participants contoured the residual gross primary tumor volume (GTV-Tres), a high-risk clinical target volume (CTV-THR), and an intermediate-risk clinical target volume (CTV-TIR), on T2-weighted magnetic resonance images (MRIs). All contours were drawn using Falcon EduCase. Contours were reviewed at an in-person meeting during which a consensus document was created defining agreed-upon target definitions (Trial 1). After establishing these definitions, the group was sent one of the cases again (recurrent cervical cancer vaginal recurrence) and asked to contour the targets again (Trial 2). The Computerized Environment for Radiation Research (CERR) software (The Mathworks, Natwick, MA) was used to analyze the contours. Kappa statistics were generated to assess level of agreement between contours. A conformity index (CI), defined as the ratio between the intersection and union volume of a given pair of contours, was calculated. A simultaneous truth and performance level estimation (STAPLE) contour was created for the CTV-THR and CTV-TIR for the postmeeting case. Consensus definitions for GTV-Tres, CTV-THR, and CTV-TIR were established. Kappa statistics (Trial 1/Trial 2) for GTV-Tres, CTV-THR, and CTV-TIR were 0.536/0.583, 0.575/0.743 and 0.522/0.707. Kappa statistics for Trial 2 for the CTV-THR and CTV-TIR showed "substantial" agreement while the GTV-Tres remained at moderate agreement. This consensus provides recommendations to facilitate future collaborations for MRI-guided adaptive brachytherapy target definitions in endometrial/cervical vaginal recurrences.

Visual detection of 3D mirror-symmetry and 3D rotational-symmetry

ABSTRACT Detecting 3D symmetry is important for the human visual system because many objects in our everyday life are 3D symmetrical. Many are 3D mirror-symmetrical and others are 3D rotational-symmetrical. But note that their retinal images are 2D symmetrical only in degenerate views. It has been suggested that a human observer can detect 3D mirror-symmetry even from a 2D retinal image of a 3D mirror-symmetrical pair of contours. There are model-based invariants of the 3D mirror-symmetrical pair of contours in the retinal image and there are additional invariant features when the contours are individually planar. There are also model-based invariants of a 3D rotational-symmetrical pair of contours. These invariant features of 3D mirror-symmetry and rotational-symmetry are analogous to one another but the features of 3D rotational-symmetry are computationally more difficult than the features of 3D mirror-symmetry. Experiment 1 showed that only 3D mirror-symmetry could be detected reliably while the detection of 3D rotational-symmetry was close to chance-level. Experiment 2 showed that the detection of 3D mirror-symmetry is partly based on the model-based invariants of 3D mirror-symmetry and the planarity of the contours. These results show that the visual system has evolved to favour the perception of 3D mirror-symmetry.

Quality assurance for automatically generated contours with additional deep learning

ObjectiveDeploying an automatic segmentation model in practice should require rigorous quality assurance (QA) and continuous monitoring of the model’s use and performance, particularly in high-stakes scenarios such as healthcare. Currently, however, tools to assist with QA for such models are not available to AI researchers. In this work, we build a deep learning model that estimates the quality of automatically generated contours.MethodsThe model was trained to predict the segmentation quality by outputting an estimate of the Dice similarity coefficient given an image contour pair as input. Our dataset contained 60 axial T2-weighted MRI images of prostates with ground truth segmentations along with 80 automatically generated segmentation masks. The model we used was a 3D version of the EfficientDet architecture with a custom regression head. For validation, we used a fivefold cross-validation. To counteract the limitation of the small dataset, we used an extensive data augmentation scheme capable of producing virtually infinite training samples from a single ground truth label mask. In addition, we compared the results against a baseline model that only uses clinical variables for its predictions.ResultsOur model achieved a mean absolute error of 0.020 ± 0.026 (2.2% mean percentage error) in estimating the Dice score, with a rank correlation of 0.42. Furthermore, the model managed to correctly identify incorrect segmentations (defined in terms of acceptable/unacceptable) 99.6% of the time.ConclusionWe believe that the trained model can be used alongside automatic segmentation tools to ensure quality and thus allow intervention to prevent undesired segmentation behavior.

Fuzzy Family Ties

Abstract Melodic contour is one of a melody's defining characteristics. Music theorists such as Michael Friedmann, Robert Morris, Elizabeth West Marvin and Paul Laprade, and Ian Quinn have developed models for evaluating similarities between contours, but only a few compare similarities between pairs of contours with different lengths, and fewer still can measure shared characteristics among an entire family of contours. This article introduces a new method for evaluating familial similarities between related contours, even if the contours have different cardinalities. The model extends theories of contour transformation by using fuzzy set theory and probability, measuring a contour's degree of familial membership by examining the contour's transformational pathway and calculating the probability that each move in the pathway is shared by other family members. Through the potential of differing alignments along these pathways, the model allows for the possibility that pathways may be omitted or inserted within a contour that exhibits familial resemblance, despite its different cardinality. The analytical utility of the model is then demonstrated through an analysis of melodic possibility in phased portions of Steve Reich's The Desert Music. Integrating variable cardinality into contour similarity relations in this way more adequately accounts for familial relationships between contours and can provide new and valuable insights into one of music's most fundamental elements.

Cue selection in the perception of pitch in music and speech

Spectral shape affects pitch perception; sounds with more high energy harmonics sound higher than sounds with low energy in higher harmonics. Flatter spectral slope corresponds to "tenser" voices while steeper spectral slope correlates to "breathier" voices in speech. In string instruments, the spectral slope differentiates sul ponticello and sul tasto. Listeners were found to integrate spectral slope cues in pitch perception in speech; however, work on music focused on cross-instrument differences, glossing over cue integration within instruments with fixed-formant frequencies. Furthermore, spectral cues and F0 co-vary in human pitch production, but are largely independent in instrumental music. It remains unclear whether music processing is as integrative as speech processing. In this study, listeners were given either speech or violin stimuli with identical pitch contour pairs, and were asked to decide whether the second contour was higher or lower in pitch compared to the first. The spectral slope of each sound was manipulated to include all combinations of “breathier”/“sul tasto” and “tenser”/“sul ponticello” sounding pairs. Results show that listeners integrate spectral slope cues in pitch perception in speech and violin stimuli similarly, with similar categoricity and shift. Overall, listeners with higher musicality have more categorical responses but no differences in shift.

Quantitative analysis of fundamental frequency in Spanish (L2) and Brazilian Portuguese (L1)

This paper analyzes the intonation of Spanish and Brazilian Portuguese (BP) produced by monolingual speakers of both languages and bilingual BP speakers that lived in Spain on average for 6 years. Bilinguals produced data in both Spanish L2 (BL2) and BP L1 (BL1). Speech materials are sentences in different modalities (declaratives, yes-no and wh-questions) and reading styles (isolated sentences and storytelling). Fundamental frequency (f0) contours were analyzed to assess learning in Spanish L2 and language attrition in the L1 production of bilinguals. Variability in the f0 contours of the four language conditions was gauged by means of three indices (peak rate, peak range and global standard deviation). Dynamic time warping (DTW) distances between pairs of f0 contours were also measured as a way to measure within- and between-language differences in intonation patterns. The main results are: 1) BL2 and BL1 contours are significantly more variable than the monolingual ones both quantitatively and qualitatively; 2) BL2 contours partially converge towards the patterns of Spanish monolinguals, showing that there is learning; 3) there is evidence for language attrition in the form of transfer of Spanish patterns to BP contours produced by bilinguals; 4) Learning and attrition levels are different depending on sentence modality, such that learning is greater in modalities that differ less between BP and Spanish and attrition is greater in modalities that differ the most.

Synthetic pulmonary perfusion images from 4DCT for functional avoidance using deep learning

Purpose. To develop and evaluate the performance of a deep learning model to generate synthetic pulmonary perfusion images from clinical 4DCT images for patients undergoing radiotherapy for lung cancer. Methods. A clinical data set of 58 pre- and post-radiotherapy 99mTc-labeled MAA-SPECT perfusion studies (32 patients) each with contemporaneous 4DCT studies was collected. Using the inhale and exhale phases of the 4DCT, a 3D-residual network was trained to create synthetic perfusion images utilizing the MAA-SPECT as ground truth. The training process was repeated for a 50-imaging study, five-fold validation with twenty model instances trained per fold. The highest performing model instance from each fold was selected for inference upon the eight-study test set. A manual lung segmentation was used to compute correlation metrics constrained to the voxels within the lungs. From the pre-treatment test cases (N = 5), 50th percentile contours of well-perfused lung were generated from both the clinical and synthetic perfusion images and the agreement was quantified. Results. Across the hold-out test set, our deep learning model predicted perfusion with a Spearman correlation coefficient of 0.70 (IQR: 0.61–0.76) and a Pearson correlation coefficient of 0.66 (IQR: 0.49–0.73). The agreement of the functional avoidance contour pairs was Dice of 0.803 (IQR: 0.750–0.810) and average surface distance of 5.92 mm (IQR: 5.68–7.55). Conclusion. We demonstrate that from 4DCT alone, a deep learning model can generate synthetic perfusion images with potential application in functional avoidance treatment planning.

Estimating electron temperature and density using improved collisional-radiative model in high-density RF argon plasma

It is crucial to measure the electron density (ne) and temperature (Te) for applications such as developing small helicon sources in plasma thrusters. Hence, this study developed a method based on an optical emission spectroscopic (OES) measurement without disturbance or contamination for helicon plasma produced using argon gas. The argon collisional-radiative (CR) model was used to describe the excitation number density in plasma as a function of ne and Te. Each number density ratio was surveyed as a function of ne and Te. From these results, contours of two number densities, i.e., two excitation energy levels, were drawn on an ne–Te plane. By applying various contour pairs, ne and Te were determined from the intersection point of two contours whose values were taken from the experimental intensities. Finally, we compared the new OES measurements with the CR model for various intensity ratios and found a way to select a valid intensity ratio that is in good agreement with the ne and Te derived by the probe method.

Automatic Cone Beam Projection-based Liver Tumor Localization by Deep Learning and Biomechanical Modeling

Accurate on-board liver tumor localization remains a challenge for CBCT-based image-guided radiotherapy, due to tumors’ low-visibility within normal liver tissues. Deformable registration-driven contour propagation from planning CTs may facilitate automatic, accurate tumor localization. We developed a technique combining a population-based liver surface deformation model and a patient-specific, biomechanical modeling-guided algorithm to achieve accurate deformation-driven liver tumor contour propagation and localization. The technique solves the deformation-vector-fields (DVFs) for tumor propagation by three steps: 1. Solving a coarse DVF via 2D-3D deformable registration by intensity-matching DRRs of the deformed planning CT to on-board cone-beam projections; 2. Feeding the DVF into a population-based deep learning model to improve its accuracy around liver surface region; and 3. Applying the accuracy-enhanced liver surface DVF to a patient-specific liver biomechanical model as the boundary condition, to solve intra-liver DVF through finite element analysis. The optimized intra-liver DVF is then applied to the liver tumor contour to propagate it onto the CBCT frame for automatic localization. For step 2, the deep learning model uses a U-net architecture to perform voxel-wise correction to the 2D-3D DVF solved by step 1, especially at the caudal liver surface region where limited tissue contrast diminishes the accuracy of 2D-3D registration. The population-based model was trained on a total of 21 patients through supervised learning, using patient-specific 2D-3D DVF and liver contour pairs as input, and high-accuracy liver surface DVF as ‘gold-standard’ output. The ‘gold-standard’ DVF was obtained by manually contouring, density-overriding, and deform-registering liver organs on corresponding CT-CBCT pairs. We evaluated the technique on 10 liver patients not included in the training list. Each patient had a contrast-enhanced 4D-CT set, of which the 0% phase was used as the planning CT, and phases 10-90% as 4D-CBCTs to simulate 4D cone-beam projections for tumor localization evaluation. Liver tumors were contoured by a radiation oncologist on all 4D-CT phases for propagation (phase 0%) or reference (phases 10-90%). Both DICE similarity index and center-of-mass-error (COME) were calculated between propagated liver tumor contours and physician’s reference contours for quantitative analysis. Using 20 cone-beam projections for each localization, the 2D-3D registration technique, biomechanical modeling technique (without deep learning), and our technique localized the liver tumors to average ± s.d. COMEs of 4.5 ± 1.4 mm, 2.5 ± 0.8 mm, and 1.6 ± 0.5 mm, and DICEs of 0.61 ± 0.23, 0.73 ± 0.16, and 0.80 ± 0.09, respectively. The developed technique enables automatic, accurate liver tumor localization (<2 mm) using few projections (< = 20), which facilitates 4D tumor localization after projection phase sorting.

A marker-less assembly stage recognition method based on segmented projection contour

In man–machine cooperative assembly, assembly recognition that determines the current manual working stage is key information to driving automatic computer-aided assistance. Focused on three features of the assembly scene—movable view, process stage, and CAD model template— a view-free and marker-less assembly stage recognition method is proposed in this paper. By constructing the semantic model for the assembly scene and the stage model for CAD parts, a depth image of assembly and a CAD model can be extracted as point clouds. Then we propose the segmented projection contour descriptor to uniformly express the shape information as a series of contours, so the 3D registration issue is converted to a 2D registration issue. The vertex-to-edge Hausdorff distance is proposed in the partial registration to determine the transformation matrix for each pair of contours. Finally, the overall matching algorithm based on the overlay ratio is given, and the best matching stage model indicates the current assembly stage. The recognition and classification experiments are carried out to verify the proposed method. A comparison with traditional Hausdorff distance proves the proposed algorithm performs better in stage recognition. Our study reveals that the proposed view-free and marker-less method can solve the stage recognition issue based on the assembly’s depth image, so as to connect the on-site assembly with the digital information.

Meeting radiation dosimetry capacity requirements of population-scale exposures by geostatistical sampling.

Accurate radiation dose estimates are critical for determining eligibility for therapies by timely triaging of exposed individuals after large-scale radiation events. However, the universal assessment of a large population subjected to a nuclear spill incident or detonation is not feasible. Even with high-throughput dosimetry analysis, test volumes far exceed the capacities of first responders to measure radiation exposures directly, or to acquire and process samples for follow-on biodosimetry testing. To significantly reduce data acquisition and processing requirements for triaging of treatment-eligible exposures in population-scale radiation incidents. Physical radiation plumes modelled nuclear detonation scenarios of simulated exposures at 22 US locations. Models assumed only location of the epicenter and historical, prevailing wind directions/speeds. The spatial boundaries of graduated radiation exposures were determined by targeted, multistep geostatistical analysis of small population samples. Initially, locations proximate to these sites were randomly sampled (generally 0.1% of population). Empirical Bayesian kriging established radiation dose contour levels circumscribing these sites. Densification of each plume identified critical locations for additional sampling. After repeated kriging and densification, overlapping grids between each pair of contours of successive plumes were compared based on their diagonal Bray-Curtis distances and root-mean-square deviations, which provided criteria (<10% difference) to discontinue sampling. We modeled 30 scenarios, including 22 urban/high-density and 2 rural/low-density scenarios under various weather conditions. Multiple (3-10) rounds of sampling and kriging were required for the dosimetry maps to converge, requiring between 58 and 347 samples for different scenarios. On average, 70±10% of locations where populations are expected to receive an exposure ≥2Gy were identified. Under sub-optimal sampling conditions, the number of iterations and samples were increased, and accuracy was reduced. Geostatistical mapping limits the number of required dose assessments, the time required, and radiation exposure to first responders. Geostatistical analysis will expedite triaging of acute radiation exposure in population-scale nuclear events.

Luminance-contrast properties of texture-shape and texture-surround suppression of contour shape.

Studies have revealed that textures suppress the processing of the shapes of contours they surround. One manifestation of texture-surround suppression is the reduction in the magnitude of adaptation-induced contour-shape aftereffects when the adaptor contour is surrounded by a texture. Here we utilize this phenomenon to investigate the nature of the first-order inputs to texture-surround suppression of contour shape by examining its selectivity to luminance polarity and the magnitude of luminance contrast. Stimuli were constructed from sinusoidal-shaped strings of either "bright" or "dark" elongated Gaussians. Observers adapted to pairs of contours, and the aftereffect was measured as the shift in the apparent shape frequency of subsequently presented test contours. We found that the suppression of the contour-shape aftereffect by a surround texture made of similar contours was maximal when the adaptor's center and surround contours were of the same polarity, revealing polarity specificity of the surround-suppression effect. We also measured the effect of varying the relative contrasts of the adaptor's center and surround and found that the reduction in the contour-shape aftereffect was determined by the surround-to-center contrast ratio. Finally, we measured the selectivity to luminance polarity of the texture-shape aftereffect itself and found that it was reduced when the adaptors and tests were of opposite luminance polarity. We conclude that texture-surround suppression of contour-shape as well as texture-shape processing itself depend on "on-off" luminance-polarity channel interactions. These selectivities may constitute an important neural substrate underlying efficient figure-ground segregation and image segmentation.

Spectrum of flows on discrete pair of contours

We consider a deterministic discrete dynamical system, which is a contour network of Buslaev type. This system contains two contours. The ith contour contains Ni cells, i = 1, 2. There is a cluster of particles on each contour moving in accordance with given rules. The clusters contain 1 ≤ M1 < N1 and 1 ≤ M2 < N2 particles respectively. There is no more than one particle in each cell at any time. There is a common point (node) of the contours. Particles cannot cross the node simultaneously. A set of repeating system states is called a spectral cycle. Average velocities of clusters correspond to spectral cycles. The set of spectral cycles and values of the average velocities have been found.

The effects of presentation time on preference for curvature of real objects and meaningless novel patterns.

Objects with curved contours are generally preferred to sharp-angled ones. In this study, we aim to determine whether different presentation times influence this preference. We used images of real objects (experiment 1) and meaningless novel patterns (experiment 2). Participants had to select one of two images from a contour pair, curved and sharp-angled versions of the same object/pattern. With real objects, the preference for curved versions was greatest when presented for 84ms, and it faded when participants were given unlimited viewing time. Curved meaningless patterns were preferred when presented for 84 and 150ms. However, in contrast to real objects, preference for meaningless patterns increased significantly in the unlimited viewing time condition. Participants discriminated poorly between the two versions (curved and sharp-angled) of the meaningless patterns in the 84- and 150-ms presentations (experiment 3). Therefore, in short times with meaningless patterns, participants selected mostly the curved version without being aware of the difference. In conclusion, presentation time, type of stimulus, and their interaction influence preference for curvature.

Perceiving perpendicular and parallel contours in the frontoparallel plane

The perception of a pair of contours in a retinal image cannot be understood simply by adding up the perceptions of the individual contours, especially when they form a perpendicular junction, or are parallel to one another. It is the relationship among the contours that determines what is perceived. Note that it is hard to actually compare the perception of such configurations quantitatively. We managed to do this by testing the perception of such configurations in three psychophysical experiments in which the perception was characterized by measuring the orientation threshold of a single contour. This threshold was estimated by using a modified Method of Constant Stimuli based on the assumption that contours forming a configuration are perceived individually, and that they are integrated linearly. This assumption made the quantitative comparison of the perceived configurations possible. We found that changes of the estimated threshold depended on the type of the configuration, specifically thresholds estimated from a perpendicular junction were substantially lower than thresholds estimated from a single contour or from a non-perpendicular junction. The lowest thresholds were observed when the threshold was estimated from a pair of parallel contours. These results suggest that the visual system is sensitive to perpendicular junctions and parallel contours in a retinal image.

Local contour symmetry facilitates scene categorization

People are able to rapidly categorize briefly flashed images of real-world environments, even when they are reduced to line drawings. This setting allows for the study of time-limited perceptual grouping processes in the human visual system that are applicable to line drawings. Previous work (Wilder, Dickinson, Jepson, & Walther, 2018) showed that standard local features of individual contours, or junctions between contours, do not account for this rapid classification ability but, rather, the relative placement of these contours appeared to be important. Here we provide strong support for this observation by demonstrating that local ribbon symmetry between neighboring pairs of contours facilitates the categorization of complex real-world environments. To this end, we introduce a novel computational approach, based on the medial axis transform, for measuring the degree of local ribbon symmetry in a line drawing. We use this measure to separate the contour pixels for a given scene into the most ribbon symmetric half and the least ribbon symmetric half. We then show human observers the resulting half-images in a rapid-categorization experiment. Our results demonstrate that local ribbon symmetry facilitates the categorization of complex real-world environments. This is the first study of the role of local symmetry in inter-contour grouping for human scene classification. We conclude that local ribbon symmetry appears to play an important role in jump-starting the grouping of image content into meaningful units, even in flashed presentations.

Exact results for discrete dynamical systems on a pair of contours

The study of discrete model of movement on a single contour, equivalent to CA 184 in terms of Wolfram cellular automata classification, was conducted in the late 1990s and early 2000s. In similar formulations of problems for contour networks, conflicts of movement take place in nodes. These problems have been poorly studied so far. However, they are very interesting for scientific and research applications relating to the flow theory (traffic, development of new materials, energy metabolism in the body). In this paper, results are obtained for the simplest contour network. This network is a pair of contours with common node. The supporter of the system consists of 2 contours with a common point (node). Particles move on their contour in accordance with rule 184 or 240 of Wolfram cellular automata. We consider the system with a common cell (simple node) or common point between 2 cells on each contour (alternating node). We have developed approaches to the study of two‐contour system such that these approaches can be used to the study of contour networks with more complex architecture. We have obtained the following criterion of that the system comes to the state of free movement (self‐organization). The criterion of self‐organization is inequality ρ1+ρ2≤1/2 in the case of rule CA 184 and simple node and inequality ρ1+ρ2≤1 in the case of rule CA 240 and alternating node. In the general case, presence of self‐organization depends on the initial state of the system. Velocities of particles have been found for different rules of movement. Prospects of future research and possible application are outlined.