9 results about "Log-polar coordinates" patented technology

The invention relates to the technical field of industrial vision, in particular to an aviation part crack detection and repair method which comprises the following steps: acquiring an aviation part optical image at a reference time point and an aviation part optical image at a to-be-detected time point; according to the method, logarithmic polar coordinate transformation is carried out on different time point images, rotation, scaling and translation parameters are extracted, an image registration relation is established, the structural consistency of time sequence images in a local area is enhanced, a structural tensor is constructed for each pixel neighborhood, the change characteristics of the dual-time-phase tensor are compared, a structural change saliency map is generated, and the structural change saliency map is obtained. Sensitive capture of a tiny deformation area is achieved, the responsiveness to an initial crack is improved, then a crack propagation interval is further refined into a main crack path in a self-adaptive threshold segmentation and skeleton extraction mode, the tip acutance of the crack is calculated in combination with tip contour information of a geometric boundary of the crack, and the initial crack is obtained. And quantitative support is provided for the crack danger degree.

This invention discloses a rotation- and scale-invariant feature extraction method and system based on dual-coordinate system collaboration, belonging to the field of image processing technology. Addressing the poor matching performance of existing image feature extraction methods under rotation and scale changes, this invention employs the following scheme: The input image undergoes a logarithmic polar coordinate transformation to generate a polar coordinate image; a dual-branch network is constructed, where the feature extraction branch extracts keypoint location information in a Cartesian coordinate system, and the feature description branch extracts a polar coordinate feature map in a logarithmic polar coordinate system; the keypoint locations in the Cartesian coordinate system are mapped to their corresponding positions in the polar coordinate feature map using a coordinate mapping function, and interpolation sampling is performed to generate feature descriptors that integrate precise location information and rotation / scale invariance information; based on the feature descriptors, matching point pairs are calculated, and the spatial transformation relationship between images is determined. This invention achieves highly robust feature extraction under rotation and scale changes while maintaining high real-time processing efficiency.

The application discloses a kind of atmospheric environment prediction methods based on neural computing, it is related to meteorology technical field, including the following steps: S1, constructs meteorological physics prior tensor;S2, meteorological physics prior tensor is input improved GMFlow network, utilizes turbulence cascade and physical tensor constraint to construct correlation volume, based on wind field guidance non-local aggregation and logarithm-polar coordinate transformation iterative refinement, output motion vector field;S3, constructs mass conservation physical deviation matrix;S4, outputs physical consistency optical flow field;S5, generates dynamic source increment concentration chart;S6, outputs double physical drive prediction frame;S7, output final atmospheric environment prediction result.The application overcomes the limitation of traditional method physical mechanism missing, high frequency detail fuzzy and transport simulation distortion, provides efficient solution for accurate prediction under complex atmospheric environment.

This invention relates to the field of digital image processing technology, and in particular to a cross-scale image feature field registration method, comprising: extracting the target object shadow regions of a reference image and a floating image respectively, generating a reference topological field and a floating topological field through morphological thinning processing; calculating the sub-image isomorphism similarity between the two to identify matching anchor point pairs, and determining a local target region in the reference image; within the region, mapping the scale scaling and rotation differences between the images to linear displacement in the polar coordinate system through logarithmic polar coordinate transformation; subsequently performing one-dimensional cross-correlation calculation along the polar radial axis, detecting the phase correlation peak offset to obtain the scale scaling coefficient; using this as a reference for initial projection, establishing a composite optimization function that fuses the homography matrix energy term and the dense light flow field energy term; finally, dividing the floating image into a control grid, using an iterative solver to drive node displacement compensation, and completing non-rigid registration.

This invention relates to the field of image recognition technology, specifically to an image recognition-based method for asphalt road quality inspection. The method includes the following steps: acquiring adjacent road surface image frames using an image recognition terminal; mapping the adjacent road surface image frames from a Cartesian coordinate system to a logarithmic polar coordinate system to generate a global transformation parameter set; and performing displacement and angular deflection on the corresponding pixel matrix of the adjacent road surface image frames according to the translation, rotation, and scaling components in the global transformation parameter set to generate a coarsely registered image sequence. In this invention, the fracture and crack density value is calculated using the slope value and the number of nodes, and compared with a preset safety threshold. This elevates the quality inspection result from a simple judgment of crack existence to a graded assessment based on the degree of damage. Therefore, in scenarios with complex road surfaces, fine crack morphology, and significant road surface texture interference, the consistency of the inspection results can be enhanced.

The invention relates to the technical field of photoelectric measurement and machine vision, and discloses a dynamic rotating speed measurement method based on laser speckles, which is suitable for diffuse reflection characteristic-free rotating parts. Projecting a light beam to a measured object to form speckles, and capturing an asynchronous event stream by using an event camera and a self-adaptive mask; mapping the stream data to a dynamic time window, and converting the stream data into a two-dimensional time surface matrix through a time decay model; resolving a physical rotation center based on known parameters or a low-speed accumulation matrix and feeding back the updated mask; performing logarithmic polar coordinate transformation by taking the center as a pole, and obtaining a roughly estimated angular velocity through integral projection and frequency domain calculation; constructing a search space by taking the displacement as a priori, and executing position compensation and similarity evaluation to extract a refinement rotation displacement; based on this, a second-order state model is constructed, and the instantaneous angular velocity is output through adaptive filtering. According to the invention, the radial vibration interference is decoupled, the extreme working condition range is widened, and the speed measurement precision and the anti-interference capability are remarkably improved.

This invention relates to the field of industrial vision technology, specifically to a method for detecting and repairing cracks in aerospace components. The method includes the following steps: acquiring optical images of the aerospace component at a reference time point and optical images of the aerospace component at the time point to be tested. In this invention, by performing logarithmic polar coordinate transformation on images at different time points and extracting rotation, scaling, and translation parameters, an image registration relationship is established, enhancing the structural consistency of the time-series images in local regions. Furthermore, a structural tensor is constructed for the neighborhood of each pixel, and the change characteristics of the bi-temporal tensor are compared to generate a saliency map of structural changes, enabling sensitive capture of areas with minute deformations and improving the response capability to initial cracks. Then, through adaptive threshold segmentation and skeleton extraction, the crack propagation range is further refined into the main crack path. Combined with the tip contour information of the crack geometric boundary, the sharpness of the crack tip is calculated, providing quantitative support for the crack's severity.

This invention provides a Fourier-Melin transform image geometric matching method and system with decoupled logarithmic domain, comprising: estimating the rotation angle using Fourier-Melin transform; rotating the image to be matched in the current frame relative to the template image in the previous frame to obtain an axially aligned image search region; transforming the template image and the image to be matched from Cartesian coordinates to logarithmic polar coordinates to obtain the image search region corresponding to the logarithmic polar coordinates; sequentially segmenting the image search regions corresponding to the image to be matched and the template image along the θ-axis according to a set ratio; stitching the horizontally correlated and vertically correlated image regions into two twin image search regions; calculating the cross power spectrum through phase correlation to obtain the scale factors in the horizontal and vertical directions; and aligning the images to be matched according to the scale factors in the two directions. This invention has the ability to estimate scale and rotation proportionally, and is scale adaptive, and is robust to out-of-plane flipping and rotation of the target object.

The application discloses a kind of local energy response feature transformation multi-modal image matching method and system, system includes image acquisition module, local energy response model establishment module, feature extraction module, feature description module, initial matching set construction module, remove false matching module;Method is: obtaining two multi-modal images to be matched;Establish local energy response model based on log-Gabor filter;On the basis of local energy response model, combined with joint bilateral filter, feature points in two multi-modal images are extracted using FAST algorithm;Log polar coordinate feature descriptor of feature point is established using three-dimensional Gaussian kernel and maximum index strategy;According to the similarity of feature descriptor in two images, establish a group of initial matching set;Affine transformation consistency index is obtained by fast sample consistency algorithm, and the final image matching result is obtained.The scheme of the application can cope with the interference of noise and local nonlinear deformation in multi-modal image, and has rotation invariance.