31 results about "Fourier descriptor" patented technology

The invention provides an aluminum alloy surface oxidation spot defect identification method and device based on machine vision, and relates to the field of intelligent manufacturing and industrial automation, and the method comprises the steps: obtaining an aluminum alloy surface color image, and carrying out the preprocessing of the image, so as to extract a brightness component image; self-adaptive threshold segmentation of local contrast enhancement is carried out on the brightness component image, a defect area binary mask is generated, morphological connected domains are extracted according to the mask, and three basic feature indexes of the area pixel value, the contour Fourier descriptor complexity and the area gray scale standard deviation contrast of each connected domain are calculated; and extracting and marking a connected domain boundary, verifying a boundary closed topological structure, and dynamically generating a curvature-driven self-adaptive sampling point through multi-scale B-spline curvature extreme value detection. Through optical-algorithm-process three-level collaborative innovation, the curved surface reflection false alarm rate is reduced, the pinhole detection rate is increased, and the boundary precision is + / -0.2 pixel.

The invention discloses a capillary pressure and contact angle synchronous characterization method and device of a microfluidic fluid interface, and relates to the field of interface analysis and multiphase seepage in pore media, and the method comprises the following steps: based on a pre-configured pore, particle and fluid binary image, distinguishing and extracting a fluid-particle contact interface contour and an attack / defense fluid interface contour; fitting and determining the curvature radius of each fluid interface contour through a watershed region division algorithm and reordering smoothing of Fourier descriptors; generating a multi-level size pore space based on the pore binary image, and obtaining a pore overlook radius; calculating a necking angle in combination with the curvature radius and the multi-stage size pore space to obtain an apparent contact angle and an intrinsic contact angle; and calculating the capillary pressure of the attack / defense fluid interface by combining the curvature radius, the pore overlook radius, the chip depth and the interfacial tension. According to the invention, high-precision technical support is provided for micro-fluidic multiphase seepage research.

The invention provides a resistance plate surface flaw real-time detection and positioning method and system, and relates to the technical field of industrial visual detection, and the method comprises the steps: obtaining a reflected light intensity distribution image sequence under different incident angles through a multi-direction light source, calculating the derivative of a light intensity change curve, determining a candidate flaw region according to a mutation point, and carrying out the real-time detection. And establishing a polar coordinate system to extract Fourier descriptors for feature matching, and finally determining the contour, the position and the size of the defect. The method can accurately identify and position the surface flaws of the resistance plate, and improves the detection accuracy and the production efficiency.

The invention discloses an image edge matching degree calculation and inspection point position deviation correction control method and system, and innovatively adopts a semantic segmentation and multi-level feature fusion mechanism to solve the problems of low precision and poor robustness of traditional IMU coarse adjustment, single template matching and SLAM algorithms. The method comprises the following steps of: acquiring an image through a pan-tilt camera, performing de-noising processing, and calculating an initial translation offset by using an RANSAC algorithm; generating a mask matrix in combination with the pre-training model, and extracting the edge gradient direction and strength; region pairing is established based on semantic consistency, and the matching degree is calculated through Fourier descriptor conversion; the control quantity is reversely deduced through the pixel-holder coordinate mapping relation, image acquisition is executed recursively until the matching degree reaches a threshold value, and semantic-level high-precision automatic correction and intelligent control of the target area are achieved.

The invention discloses a rotating machinery shaft system fault identification method, device and equipment and a storage medium, and relates to the technical field of rotating machinery operation safety maintenance, the method comprises the following steps: obtaining vibration displacement data of a shaft system in the X direction and the Y direction of the same cross section under different states of a rotating machinery, and establishing an axis track data set; performing noise reduction and purification on the axis track data set; based on the axis trajectory data set after noise reduction and purification, axis trajectory fusion features are extracted to construct an axis trajectory feature database, and the axis trajectory fusion features comprise axis trajectory depth features, invariant moment features and Fourier descriptor features; newly collected axis trajectory data are matched according to the axis trajectory feature database, and if matching fails, it is judged that an unknown fault occurs, and marking and diagnosis are conducted. Through noise reduction purification, fusion feature extraction and neural network model construction, the shafting fault type can be judged, and safe and stable operation of the rotating mechanical equipment is effectively guaranteed.

This invention relates to the field of image processing technology and discloses a posture deviation recognition method based on image recognition. The method involves acquiring a posture image at the moment a specified rehabilitation movement is completed, preprocessing and segmenting it to obtain a binary contour of the target posture, representing the contour points as a complex sequence, and performing closure processing and arc length resampling to standardize the number of contour points. Based on this, a DC-free and normalized Fourier descriptor is constructed to obtain the frequency domain features of the posture and the standard posture. The global shape deviation intensity and adaptive judgment threshold are calculated through frequency domain comparison, and the residual signal is reconstructed at the resampling point location to obtain the local deviation distribution. Finally, the posture deviation level and structured results are output according to a grading rule, thereby reducing the dependence on sensors and manual thresholding, realizing the quantitative assessment and presentation of posture deviation, and providing a basis for clinical assessment and training adjustment.

A computer-implemented method for classifying road intersections by means of GPS data, in particular from a plurality of vehicles in a fleet. The method includes: using existing GPS data points of vehicle movements, which were captured using GPS sensors of the vehicles at at least one road intersection; converting the captured GPS data points into a 2D contour by determining a center point of the road intersection and creating a polygon that represents a 2D contour of the road intersection; encoding the 2D contour of the road intersection using elliptic Fourier descriptors using a Fourier transform method and classifying the encoded data into different intersection types.

The invention belongs to the technical field of image processing, and relates to a protection method and system for the design copyright of an automobile cushion. The method comprises the following steps of: extracting a digital image contour of an automobile cushion design drawing, calculating a normalized Fourier descriptor of the contour as a shape feature, dividing a drawing area into grid units according to radial sectors and concentric rings, converting a digital image into a CIELAB color space in each grid unit, and for each grid unit, carrying out CIELAB color space conversion on the CIELAB color space; extracting a gradient direction histogram of a brightness L * value taking gradient intensity as a weight and a quantization histogram of statistical a * b * two-dimensional color distribution of pixels in the grid unit, combining the two histograms into a local feature descriptor of the grid unit, serializing and splicing the local feature descriptor from inside to outside, and combining shape features with a local feature sequence to form copyright feature data, and performing digital signature by using an asymmetric encryption private key, and storing the signature and a timestamp in a distributed account book together to realize copyright protection.

Embodiments of the present invention provide a view-based spatial shape recognition method, apparatus, device, and storage medium, relating to the field of appearance recognition technology. This spatial shape recognition method includes S1, obtaining views of a target product from N perspectives. S2, extracting structural contour images of X structures of the target product from N perspectives based on the views from N perspectives. S3, performing feature extraction based on the structural contour images to obtain the Hu moments and Fourier descriptors of the X structures from N perspectives. S4, obtaining feature vectors of the X structures from N perspectives based on the Hu moments and Fourier descriptors. S5, classifying the feature vectors using a classification model to obtain the plane shapes of the X structures from N perspectives. S6, performing recognition based on the plane shapes using multi-image fusion rules to obtain the spatial shapes of each structure of the target product. The spatial shape recognition method of the present invention can obtain spatial shapes based on views, thereby providing a new retrieval basis for image retrieval.

The invention provides a part surface defect detection method which comprises the following steps: extracting a part surface defect contour through an image processing technology, generating frequency domain features by adopting a Fourier descriptor algorithm, and constructing an efficient retrieval database in combination with locality sensitive hashing and a KD tree algorithm; in order to solve the problem of high difficulty in complex defect identification, an energy distribution is utilized to match a preset template, and accurate classification is realized through nearest neighbor search and principal component analysis; meanwhile, the defect types are grouped by adopting K-means clustering, and a management report containing contour and frequency domain information is generated. According to the method, various complex defects can be rapidly and accurately detected and classified, the efficiency and reliability of part quality detection are improved, and powerful support is provided for quality control in the manufacturing industry.

This invention discloses a two-dimensional contour morphology representation method based on current-round Fourier transform, belonging to the field of geometric morphometrics. It solves the technical problems of contour rotation and misalignment caused by elliptical Fourier descriptors. The key point of its technical solution is to complete the reconstruction and normalization of contour shape through current-round Fourier descriptors, achieving contour shape description effect comparable to elliptical Fourier analysis and contour normalization (alignment) effect comparable to the Pu-style method. It can also avoid the graphic pseudo-rotation problem caused by standardization during the extraction of elliptical Fourier descriptors, without the need for prior standardization of contours using other methods, and quantitatively describes contour features based on current-round Fourier descriptors.

The application provides a lung nodule CT image processing method and system, computer equipment and a storage medium, and belongs to the field of image processing. The method comprises the following steps: collecting a lung nodule CT image; segmenting the lung nodule CT image to obtain a nodule segmentation mask; extracting nodule structure semantic features from the nodule segmentation mask; extracting lung nodule texture features from the nodule segmentation mask based on a gray level co-occurrence matrix; extracting lung nodule shape features from the nodule segmentation mask by a Fourier descriptor; splicing the lung nodule texture features and the lung nodule shape features to obtain hand-crafted features; fusing the nodule structure semantic features and the hand-crafted features based on kernel canonical analysis to obtain fused features; and determining the nodule structure complexity corresponding to the lung nodule CT image according to the fused features. The method retains the powerful pattern recognition capability of the nodule structure semantic features, and also integrates the stable discrimination information of the hand-crafted features in a small sample scene, thereby improving the accuracy and stability of classification.

The present invention relates to the field of navigation and positioning technology, and more specifically to a method for navigating and positioning an unmanned transport platform in a chicken coop based on under-cage feature extraction. The method comprises the following steps: scanning the edge of the feeding trough under the cage using a linear array camera with adjustable pitch angles, extracting continuous geometric features based on Fourier descriptors, and generating a characteristic baseline consistent with the extension direction of the cage; kinematically binding the real-time motion parameters of the transport platform to the characteristic baseline, and dynamically generating a navigation path curvature constraint based on the curvature change of the characteristic baseline; and calculating the platform posture offset based on the feature matching degree at the trough joints between adjacent cages and inversely correcting the motion control parameters to achieve closed-loop posture calibration. The present invention achieves dynamic matching between path curvature and platform steering capability, improving the physical feasibility and stability of path tracking and adapting to the operational requirements of narrow passages and large curvature turns in complex chicken coop scenarios.

The invention provides a landslide deformation identification and early warning method based on video monitoring. The method comprises the following steps of S1, data acquisition, S2, centroid extraction, S3, deformation judgment, construction of a sliding window range envelope line based on a feature point centroid coordinate sequence, and statistics of coordinate extreme values and standard deviations in a window to expand a confidence interval boundary; and when continuous multi-frame centroid coordinates exceed the boundary, a deformation early warning signal is triggered, and multi-modal feature verification is carried out in combination with the change rate of the length-width ratio of the external rectangle and the contour Fourier descriptor difference. And high-precision real-time monitoring and reliability verification of slope deformation are realized. According to the scheme, aiming at the problems of high cost, poor real-time performance, weak anti-interference capability and the like of a traditional monitoring technology, a set of complete software and hardware collaborative solution is provided, and the accuracy and adaptability of landslide early warning are remarkably improved.

The invention relates to a computer-implemented method for encoding a road intersection contour using Elliptic Fourier Descriptors (EFDs), comprising the steps: encoding by calculating Fourier coefficients of a polygonal representation of the road intersection contour using a forward transformation method (20), wherein the number of Fourier coefficients is determined by a complexity of the contour, and thereby a resulting data set is determined.

This invention discloses a method and apparatus for traffic light shape detection, relating to the fields of computer vision and intelligent transportation technology. The method includes: acquiring an image to be detected; determining the preliminary boundary region of the traffic light based on color and position information; determining whether the size of the preliminary boundary region meets preset size conditions; if not, performing adaptive size enlargement processing on the preliminary boundary region to obtain an enlarged target region; extracting the outline of the traffic light from the target region and calculating multiple coefficients using Fourier descriptors; determining the preliminary shape type of the traffic light based on the Fourier descriptor coefficients; and performing secondary confirmation of the preliminary shape type based on the geometric features of the target region to obtain the final detection result. This invention effectively compensates for the feature loss of small-sized or deformed targets through adaptive size processing, and significantly improves the accuracy and robustness of traffic light shape recognition by utilizing the invariance characteristics of Fourier descriptors and a multi-stage judgment strategy.

The invention discloses a method for optimizing the robustness of a microwave device through reinforcement learning of a Fourier descriptor reward function. The method comprises the following steps: firstly, carrying out matrix processing on structural parameters of the microwave device; secondly, establishing an environment based on a deep reinforcement learning framework, adding disturbance to matrix parameters, and inputting the matrix parameters as a state space; thirdly, designing interaction between the intelligent agent and the environment, and designing a reward function in combination with a Fourier descriptor; then, by adjusting the proportion of the reward function, the robustness of different microwave devices can be optimized without redesign; and finally, analyzing and evaluating the robustness of the device by utilizing Monte Carlo (MC). Experiments show that the robustness of the device is adjusted along with the weight change of the reward function. The method has the characteristics of strong generalization ability and wide applicability, breaks through the limitation of the traditional single device design, can effectively cope with the influence of the manufacturing process tolerance and the device type difference on the performance, and provides a brand new solution for the optimization design of low-cost and high-performance microwave devices.

The invention discloses a trash holding net anomaly detection method, system and device and a storage medium, and the method comprises the steps: carrying out the analysis of a monitoring image through a semantic segmentation model, and extracting a binary segmentation mask of a trash holding net main rope; performing skeleton extraction on the segmentation mask to generate a skeleton image of the main rope; extracting a main rope curve in the skeleton image, and aligning the curve through principal component analysis; calculating a Fourier descriptor module value of the curve, and extracting morphological characteristics of the main rope; and comparing the curve feature vectors of the main rope in different time periods, calculating curve similarity, and judging whether the main rope is abnormal or not according to a similarity threshold value. The method has the advantages of high efficiency, automation, low cost, high robustness and the like, can be widely applied to monitoring the state of the trash holding net in a large-range water area, and provides reliable technical support for safe operation of water area facilities.

This invention relates to the field of computer vision and image recognition technology, and discloses a method and system for visually identifying the authenticity of cards based on floral anti-counterfeiting features. The method includes: macro imaging and adaptive preprocessing of the floral area, extraction of the floral line skeleton based on curvature flow analysis, hierarchical encoding of floral features and construction of multidimensional fingerprints, depth comparison based on Fourier descriptors and KL divergence, and counterfeit detection and comprehensive judgment based on generative adversarial networks. The accuracy rate of floral anti-counterfeiting feature recognition reaches 99.2%, the detection rate of high-quality counterfeit products reaches 98.5%, and the identification time per card is less than 3 seconds.

The application discloses an image edge matching degree calculation and patrol point rectification control method and system, aiming at the low precision and poor robustness problems existing in traditional IMU coarse adjustment, single template matching and SLAM algorithm, and innovatively adopting a semantic segmentation and multi-level feature fusion mechanism.After the image is collected by a holder camera, denoising processing is carried out, and the RANSAC algorithm is used to calculate the initial translation offset; a mask matrix is generated in combination with a pre-trained model, and the edge gradient direction and intensity are extracted; region pairing is established based on semantic consistency, and the matching degree is calculated through Fourier descriptor conversion.The control quantity is inversely deduced through the pixel-hold coordinate mapping relationship, the image collection is recursively executed until the matching degree reaches the threshold, and the high-precision automatic rectification and intelligent control of the target region at the semantic level are realized.

The application relates to a three-dimensional model classification method based on feature fusion and a voting mechanism. The application first pre-processes training models and test models in a three-dimensional model data set to obtain a group of two-dimensional views representing the three-dimensional models, and obtains low-level shape features of the views, namely D1, D2, D3, Zernike moments, Fourier descriptors and KSP features, through calculation. RegNet design space is used to realize extraction of high-level semantic features of the views. Concat is used to fuse the low-level shape features and the high-level semantic features of the views obtained from the training models to obtain training data. Concat is used to fuse the low-level shape features and the high-level semantic features of the views obtained from the test models to obtain test data. Then, the RegNet design space and LSTM are optimized by using the training data, discriminative features are extracted from the fused features of the test data by using the optimized RegNet design space and LSTM, and the discriminative features are input into Softmax, a voting algorithm is used to vote the probability distribution output by Softmax, and the classification result of the test data is obtained. The application realizes good classification of the three-dimensional models and more accurately predicts the real categories of the three-dimensional models.

This invention belongs to the field of forensic image processing and pattern recognition technology, and discloses a method and system for image comparison and analysis of morphological features of forensic blunt force trauma wounds. The method includes: acquiring wound images using standardized macro photography with an orthophoto perspective and performing geometric correction; parameterizing the wound contour using an elliptical Fourier descriptor and extracting local geometric parameters; constructing a tissue retraction deformation compensation model based on elasticity mechanics for inverse correction; and matching the wounding tool cross-section with a cosine similarity database and outputting a recommended ranking of the wounding tools. This invention realizes the transformation of wound morphology from qualitative description to quantitative analysis.

The invention provides a pulmonary nodule CT image processing method and system, computer equipment and a storage medium, and belongs to the field of image processing, and the method comprises the steps: collecting a pulmonary nodule CT image; segmenting the pulmonary nodule CT image to obtain a nodule segmentation mask; extracting nodule structure semantic features from the nodule segmentation mask; extracting pulmonary nodule texture features from the nodule segmentation mask based on a gray level co-occurrence matrix, and extracting pulmonary nodule shape features from the nodule segmentation mask through a Fourier descriptor; splicing the pulmonary nodule texture features and the pulmonary nodule shape features to obtain manual features; and fusing the nodule structure semantic features and the manual features based on kernel canonical analysis to obtain fusion features, and determining the nodule structure complexity corresponding to the pulmonary nodule CT image according to the fusion features. According to the method, the powerful mode recognition capability of nodule structure semantic features is reserved, stable discrimination information of manual features in a small sample scene is fused, and the classification accuracy and stability are improved.

The application provides a landslide deformation identification and early warning method based on video monitoring, which comprises the following steps: S1: data acquisition, S2: centroid extraction, S3: deformation judgment, a sliding window range envelope is constructed based on a feature point centroid coordinate sequence, and the coordinate extreme value and standard deviation in the window are counted to expand the confidence interval boundary; when the centroid coordinates of continuous multiple frames exceed the boundary, a deformation early warning signal is triggered, and multi-modal feature verification is carried out in combination with the change rate of the length-width ratio of the circumscribed rectangle and the difference of the Fourier descriptor of the contour. The application realizes high-precision real-time monitoring and reliability verification of the slope deformation by combining an automatic image processing algorithm with a high-fidelity indoor scale physical model test. The scheme provides a complete software and hardware cooperative solution scheme for the problems of high cost, poor real-time performance and weak anti-interference ability of the traditional monitoring technology, and significantly improves the accuracy and adaptability of the landslide early warning.

The invention relates to a method and a device for classifying road junctions. The invention relates to a computer-implemented method for classifying road junctions by means of GPS data, in particular by means of GPS data of a plurality of vehicles of a vehicle fleet, the method comprising the following steps: using existing GPS data points (10, 11) of a vehicle movement, which have been detected in particular at at least one road junction by means of a GPS sensor of the vehicle; converting the detected GPS data points into a 2D contour by determining a center point (13) of the road junction and creating a polygon (12) representing the 2D contour of the road junction; encoding the 2D contour of the road junction by means of a Fourier transform method in the case of using Elliptic Fourier Descriptors (EFDs) and classifying the encoded data into different junction types.

The invention relates to a computer-implemented method for classifying road intersections using GPS data, in particular from several vehicles of a vehicle fleet, comprising the following steps: using existing GPS data points (10, 11) of vehicle movements, which were recorded in particular by means of GPS sensors of the vehicles at at least one road intersection, Converting the recorded GPS data points into a 2D contour by determining a center point (13) of the road intersection and creating a polygon (12) which represents a 2D contour of the road intersection, Encoding the 2D contour of the road intersection using Elliptic Fourier Descriptors (EFDs) via a Fourier transformation procedure and classifying the encoded data into different intersection types.

The application provides a kind of aluminum alloy surface oxidation spot defect identification method and device based on machine vision, it is related to intelligent manufacturing and industrial automation field, the method comprises: obtaining aluminum alloy surface color image, pre-processing image to extract luminance component image;Local contrast enhancement is carried out to luminance component image, and adaptive threshold segmentation is generated, and the area binary mask of defect region is extracted, and the area binary mask is extracted according to mask morphological connected domain, and the area pixel value of each connected domain, the complexity of profile fourier descriptor and the contrast of area gray standard deviation three basic feature indexes are calculated;Extract the boundary of marked connected domain, verify the closed topological structure of boundary, and dynamically generate curvature driven adaptive sampling point by multi-scale B spline curvature extreme detection.The application realizes the breakthrough of detection such as the decrease of curved surface reflection false alarm rate, the increase of pinhole detection rate and the boundary accuracy of ±0.2 pixels through optical-algorithm-technology three-level collaborative innovation.

The invention discloses a small target detection method based on an adaptive Fourier descriptor bounding box regression loss function, and solves the problem of low detection precision caused by a drift sensitive phenomenon in small target detection in the prior art. According to the method, the small target detection model based on the YOLO11 model and the adaptive Fourier descriptor regression loss function is constructed, the frequency domain information is introduced through the adaptive Fourier descriptor regression loss function value, the offset sensitivity problem of the bounding box in the small target detection process is improved, the detection performance of the small target detection model is effectively improved finally, and the detection accuracy of the small target detection model is improved. And thus, the small target detection precision and efficiency are improved.

The application discloses a capillary pressure and contact angle synchronous characterization method and device of a micro-fluidic interface, relates to the field of interface analysis in a porous medium and multiphase seepage, and comprises the following steps: based on a pre-configured pore, particle and fluid binary image, distinguishing and extracting a fluid-particle contact interface contour and an attack / defense fluid interface contour, fitting and determining the curvature radius of each fluid interface contour through watershed region division algorithm and reordering smoothing of a Fourier descriptor; generating a multi-level size pore space based on the pore binary image, and obtaining a pore apparent radius; combining the curvature radius and the multi-level size pore space, calculating a necking angle, and obtaining an apparent contact angle and an intrinsic contact angle; and combining the curvature radius, the pore apparent radius, a chip depth and an interface tension, calculating the capillary pressure of the attack / defense fluid interface. The application provides high-precision technical support for micro-fluidic multiphase seepage research.

The present application relates to a kind of multi-view three-dimensional model classification methods of fusing ResNet and CoTNet.The present application is first projected to three-dimensional model, obtains two-dimensional view set.CBAM attention module and SENet attention module are added in 2DResNet model to enhance the learning ability of network.2DResNet-CoTNet network is constructed based on 2DResNet model, and 2DResNet is combined with 2DCoTNet in parallel, view feature is extracted from two-dimensional view.Shape descriptor D1, D2, D3, Zernike moment and Fourier descriptor are used to describe two-dimensional view, and 1DResNet is used to extract shape feature.View feature and shape feature are fused, and finally Softmax function is used to determine the category of three-dimensional model.The present application has good three-dimensional model classification effect, can more accurately solve three-dimensional model classification problem.