22 results about "Top-hat transform" patented technology

The invention discloses a star sensor rapid tracking method based on dynamic window blind restoration, and belongs to the field of star sensor algorithms. The method comprises the following steps: estimating a coordinate estimation value of each star in an overlapped view field on a star map at the next moment through a historical star map, and extracting a local window image of a star point corresponding to each star in the overlapped view field; gaussian filtering, top-hat transformation and connected domain processing are carried out on the local window image, star point trailing information is extracted based on a Zernike moment sub-pixel edge extraction method, and a star point area is restored by using a Richardson-Lucy algorithm; then, star point centroids are extracted from the restored image, star points which are tracked successfully are screened out in combination with motion consistency, and initial attitude parameters are calculated through a QUEST method; and finally fusing the star point information newly entering the field of view to obtain attitude parameters of the star sensor under the reference coordinate system. According to the method, the image traversal range is greatly reduced, and the method has important engineering significance.

Methods and systems are provided herein for generating a morphology-based recomposition based on 3-dimensional input image data including an image stack of 2-dimensional (2D) images, the morphology-based recomposition being a final image generated by performing one or more white top hat (WTH) transforms on each 2D image, generating two or more image layers based on two or more WTH transformed images, and scaling adjacent image layers based on one or more scaling factors, each scaling factor being based on an estimated point spread function (PSF), two structure element sizes, and standard deviations of the estimated PSF and image data.

The present application belongs to the technical field of image analysis, and particularly relates to a self-adaptive cleaning control method for a cleaning robot based on image texture analysis, which comprises the following steps: performing top-hat transformation on an original image by using a multi-angle linear structural element to obtain an anisotropic residual texture image and calculate a gray run matrix; constructing a gray run inverse coupling inertia based on a negative correlation mapping relationship between gray and run; obtaining a morphological erosion residual ratio representing stain stability through a morphological erosion operation, and then fusing to generate a sediment consolidation modulus; and adjusting the command marching speed and the command shear torque of the robot accordingly. The present application solves the problems of grid line interference and misjudgment caused by reflection by deeply coupling visual features and physical stability, and realizes accurate matching between cleaning intensity and stain state.

The present invention relates to an automatic tidal creek extraction method based on color space component water index replacement and fusion, comprising the following steps: acquiring a target remote sensing image; calculating the normalized water index NDWI, the improved normalized water index MNDWI, and the multispectral water index MuWI; performing color synthesis to obtain a color image; performing HIS transformation, using the obtained I component as a new water index NWI; performing gray-level co-occurrence matrix (GLCM) calculation on the NWI image to obtain average features; processing the average features through an optimized top-hat transformation; statistically determining an optimal threshold for extracting tidal creeks to generate a binary image; and performing connected component analysis and morphological operations on the binary image to obtain the final result of tidal creek extraction. The present invention has the beneficial effects of reducing the impact of background heterogeneity on tidal creek extraction, effectively enhancing the linear features of tidal creeks, better distinguishing tidal creeks from background, and improving the accuracy of tidal creek extraction.

The present invention discloses a method for enhancing infrared images of the sea surface, including: inputting an infrared image of the sea surface to be enhanced, performing a top-hat transform on the infrared image of the sea surface to be enhanced to obtain a region of interest; adaptively segmenting the region of interest image to obtain a binary labeled image of radiation sources of the infrared image of the sea surface to be enhanced, determining a radiation source region image by using the binary labeled image of radiation sources, and constructing a radiation source suppression image according to the binary labeled image of radiation sources; determining a local illuminance map of the land-air region and a local illuminance map of the sea water region of the infrared image of the sea surface based on the sea horizon; constructing a local guidance map according to the local illuminance map of the land-air region and the local illuminance map of the sea water region to perform background enhancement on the infrared image of the sea surface to be enhanced to obtain a background enhanced image of the infrared image of the sea surface; and superimposing the radiation source region image on the background enhanced image of the infrared image of the sea surface to obtain an enhanced result of the infrared image of the sea surface.

The invention relates to an automatic tidal creek extraction method based on color space component water index replacement fusion. The method comprises the following steps: acquiring a target remote sensing image; calculating a normalized water body index NDWI, an improved normalized water body index MNDWI and a multispectral water body index MuWI; performing color synthesis to obtain a color image; carrying out HIS transformation, and taking the obtained I component as a new water body index NWI; performing gray level co-occurrence matrix GLCM calculation on the NWI image to obtain an average feature; the average features are processed through optimized top-hat transformation; carrying out statistics to determine an optimal threshold value for extracting the tidal creek, and generating a binary image; and performing connected component analysis and morphological operation on the binarized image to obtain a final result of tidal creek extraction. The method has the beneficial effects that the influence of background heterogeneity on tidal creek extraction is reduced, the linear features of the tidal creek are effectively enhanced, the tidal creek and the background can be better distinguished, and the precision of tidal creek extraction is improved.

The invention discloses a part interlayer fracture toughness test method, device and equipment and a storage medium, and the method comprises the steps: applying different loading forces to a standard test part based on a mechanical test system, and obtaining test data of each test point at different test moments through a digital image correlation technology DIC; performing top-hat transformation processing on the test image of each test point to obtain a processed test image, and obtaining the size of the precrack according to the processed test image; and calculating according to the precrack size and the loading force of each test point at different test moments to obtain the interlayer fracture toughness of the standard test part. The method comprises the following steps: on the basis of acquiring crack opening displacement and angle of a fiber reinforced composite material I-type interlayer fracture toughness test piece through DIC, synchronizing the dynamic change process of the length of a prefabricated crack extending along with loading of a load at different moments with a real-time load, and meanwhile, optimizing an acquired test image by combining a Top-hat technology, so as to obtain a test result of the I-type interlayer fracture toughness of the fiber reinforced composite material I-type interlayer fracture toughness of the fiber reinforced composite material I-type interlayer fracture toughness test piece. And the measurement precision of the interlayer fracture toughness is improved.

The invention discloses a rock fracture extraction method fusing morphological top-hat transformation, belongs to the field of digital core analysis, and discloses a rock micro-fracture extraction method based on an unsharpened mask and morphological top-hat transformation, which comprises the following steps: extracting rock micro-fractures based on top-hat transformation, and carrying out dynamic weighted fusion on the rock micro-fractures and extracted rock main fractures to obtain a rock micro-fracture extraction result; complete reconstruction of the rock core fracture network is realized; according to the scheme, an interactive processing method and a morphological operation mechanism are integrated, high-precision separation of main and micro cracks of rock and a rock matrix is realized through an unsharpened mask and a morphological-based image processing method, and accurate extraction of microstructure information in a rock core is realized; and support is provided for better serving establishment and application of various rock physical models.

The present application belongs to the technical field of image processing, and particularly relates to a surface oxidation detection method and system for overhead strand, which comprises the following steps: obtaining gradient field data of the overhead strand image; determining the local main direction entropy of the pixel point based on the angle difference between the gradient direction of all neighborhood pixel points of the pixel point and the local main direction, and determining the entropy threshold through clustering to screen anchor points; constructing a gradient profile line along the local main direction of the anchor point, determining the local rust width of the anchor point according to the gradient amplitude change of the pixel points on the gradient profile line; obtaining the adaptive structure element parameters based on the local rust width and the local main direction of the anchor point, and performing morphological top-hat transformation to calculate the response value of the anchor point, and marking the anchor points with a response value greater than the response threshold as oxidation defects. The present application significantly improves the accuracy of overhead strand surface oxidation rust recognition by adaptively matching the local geometric morphology of the rust.

The invention relates to a method and device for counting the penetration number of a target plate, electronic equipment and a storage medium. The method for counting the penetration number of the target plate comprises the following steps: inputting an original image, reading a color image of the penetrated target plate, and realizing image data loading; the method comprises the following steps: preprocessing an original image, converting the original image into a gray-scale image, and smoothing the gray-scale image to realize smoothing and sharpening of the image and reduce noise; extracting features, performing edge detection, adopting a self-adaptive threshold value, performing image preprocessing, and performing row top-hat transformation for enhancing a bright part or bottom-hat transformation for processing a dark part according to the condition of the brightness of a circle displayed by a hole in a target plate photo relative to a background; determining an object needing to be detected, and detecting a circle in the image; and target identification and counting: displaying the number of circles and the positions of the circles on a result image, and outputting the result image and counting. According to the method for counting the penetration number of the target plate, the counting efficiency can be improved, the counting difficulty can be reduced, and the counting accuracy can be improved.

This application belongs to the field of target detection and relates to a method for detecting small infrared targets, comprising: acquiring an infrared image, preprocessing the infrared image to obtain a preprocessed image; performing a multi-directional top-hat transform on the preprocessed image, and simultaneously performing multi-directional weighting to obtain a filtered image; constructing a sliding window structure on the preprocessed image to obtain a preliminary local contrast for each pixel in the preprocessed image; obtaining a final local contrast for each pixel in the filtered image based on the preliminary local contrast of each pixel in the filtered image and the preprocessed image; and obtaining a small infrared target in the infrared image based on the final local contrast of each pixel in the filtered image. This method can improve robustness in irregular, highly undulating, and cluttered backgrounds.

The present invention discloses an infrared small target adaptive detection method based on FPGA and DSP, belonging to the field of infrared real-time detection technology. The method comprises the following steps: first, the FPGA caches an input original infrared grayscale image, and filters the image by using curvature filtering and top-hat transformation to obtain a filtered image; second, the FPGA performs adaptive threshold segmentation on the filtered image to generate a binary image, and compresses the image into a single-bit image data stream to transmit to the DSP; third, the DSP performs connected domain detection on the single-bit image data stream to obtain a connected domain detection result; finally, the DSP dynamically adjusts the adaptive threshold segmentation coefficient of the FPGA according to the connected domain detection result, and uses the coefficient for threshold segmentation of the next frame of image.

The invention belongs to the technical field of radiation detection, and particularly relates to a synthetic aperture radiometer target detection method and device under a high dynamic condition based on continuous frame image processing. Utilizing a synthetic aperture radiometer to continuously obtain millimeter wave signals of a target scene, and obtaining visibility functions of a plurality of continuous frames according to preset integral time; performing background subtraction, Gaussian low-pass filtering and Fourier transform on the visibility function sequence to obtain a plurality of frames of brightness temperature maps; solving a rotation matrix of the current frame image according to the attitude angle at the current moment, and performing registration fusion on the brightness temperature image according to the rotation matrix to obtain a preliminary result image; a convolution kernel is set according to antenna array arrangement and platform motion imaging properties, the preliminary result image is enhanced, then the image is further enhanced by adopting multi-scale white top-hat transform, and a final result image is obtained; and setting a target detection window, screening candidate target points according to pixels in the window, and finally setting a threshold value according to a full-image pixel mean value and variance to determine the positions of the target points.

This invention discloses an infrared small target detection method based on adaptive multi-scale filtering, belonging to the field of infrared target detection technology. The steps include: image preprocessing, multi-scale top-hat transformation, adaptive threshold binarization, multi-dimensional screening of candidate targets, and IoU-based cross-frame matching and target validity determination. This invention employs a three-scale elliptical structuring element to enhance target robustness, achieves adaptive binarization based on global statistics, and suppresses false alarms through noise-sensing parameter switching and temporal verification. The entire process has low computational complexity and high real-time performance, enabling stable and accurate infrared small target detection under complex backgrounds, strong noise, and low signal-to-noise ratio conditions. It is suitable for scenarios such as military reconnaissance, security monitoring, infrared guidance, and low-altitude target detection.

The application discloses an infrared small target detection method based on an elliptical ring Top-Hat, and comprises the following steps: constructing a structure element of four angles of a detection target, wherein the structure element comprises an external structure element, an internal structure element and an elliptical structure element; defining an open operation and a closed operation according to the structure element; obtaining a top-hat transformation operation and a bottom-hat transformation operation through morphological transformation based on the open operation and the closed operation; obtaining a first detection result through fusion based on the top-hat transformation operation and the bottom-hat operation; and segmenting the first detection result based on an adaptive threshold to obtain an infrared small target detection result. The elliptical structure element obtained by constructing the structure element of four angles of the detection target can fully acquire contrast information, and the problem of serious false alarm in the case of a complex background is solved, so that the application can be widely applied to the field of infrared detection technology.

The present application relates to a welding seam image processing method based on line structured light, which performs top-hat transformation on the welding seam image to eliminate the phenomenon of uneven background illumination; performs image enhancement on the welding seam image after top-hat transformation; performs smoothing processing on the welding seam image after image enhancement to blur the edges of sharp gray scale changes, suppress noise, and obtain a clear welding seam image; performs binarization on the welding seam image to clearly separate the target from the background; dynamically extracts the ROI region of the binary image to remove interference and improve speed; performs isolated point filtering to remove small isolated blocks in the binary image to obtain a target laser stripe; performs thinning processing on the laser stripe and removes burrs to obtain the center point coordinates of the laser stripe, thereby laying a solid foundation for subsequent extraction of welding seam features. The present application can realize online, real-time and automatic welding seam image processing based on line structured light, has high speed and high precision, is not constrained by the type of welding seam, and is robust to noise interference such as arc light, spatter, smoke and dust, and workpiece reflection during the welding process.

The invention belongs to the technical field of image analysis, and particularly relates to a cleaning robot self-adaptive cleaning control method based on image texture analysis, which comprises the following steps of: performing top-hat transformation on an original image by using a multi-angle linear structure element to obtain an anisotropic residual error texture image and calculate a gray scale run length matrix; constructing a gray scale run length reverse coupling inertia based on a negative correlation mapping relation between the gray scale and the run length; obtaining a morphological erosion residual ratio representing the stain stability through morphological corrosion operation, and fusing to generate a sediment consolidation degree modulus; therefore, the instruction advancing speed and the instruction shearing moment of the robot are adjusted. Through deep coupling of visual features and physical stability, the problems of grid line interference and reflection misjudgment are solved, and accurate matching of the cleaning intensity and the stain state is achieved.

The invention belongs to the technical field of image processing, and particularly relates to a surface oxidation detection method and system for an overhead stranded conductor, and the method comprises the steps: obtaining the gradient field data of an overhead stranded conductor image; based on the included angle difference between the gradient direction and the local main direction of all neighborhood pixel points of the pixel points, determining the local main direction entropy of the pixel points, and determining an entropy threshold through clustering to screen anchor points; a gradient section line is constructed in the local main direction of the anchor point, and the local rust width of the anchor point is determined according to gradient amplitude changes of pixel points on the gradient section line; and on the basis of the local rust widths and the local main directions of the anchor points, self-adaptive structure element parameters are obtained, morphological top-hat transformation is executed to calculate response values of the anchor points, and the anchor points with the response values larger than a response threshold value are marked as oxidation defects. According to the method, the accuracy of identifying the oxidation rust on the surface of the overhead stranded wire is remarkably improved through self-adaptive matching of the local geometric morphology of the rust.

The invention provides a small target detection method, an infrared imaging system and computer equipment, and the method comprises the steps: obtaining an infrared image, recognizing a target frame in the infrared image through a target detection model, and recording a corner coordinate of the target frame; cutting the image according to the target frame and filtering noisy points to obtain a first image; carrying out white top hat transformation and adaptive threshold segmentation on the first image to obtain a binary image; carrying out Hamming window weighting processing on the binary image and carrying out two-dimensional discrete Fourier transform to obtain a corresponding frequency domain image; constructing a multi-scale frequency domain filter, performing frequency domain calculation on the frequency domain graph by using the multi-scale frequency domain filter, and performing inverse Fourier transform to convert the frequency domain graph into a spatial domain to obtain a response graph; and traversing the response diagram to obtain a peak position coordinate, and adding the peak position coordinate and the corner coordinate to obtain a target coordinate of the small target. According to the scheme, the detection effect of the small target under the complex background can be improved, the calculation precision is higher, the operation time is shorter, and the calculation resource occupation is lower.

Methods and systems are provided herein for generating a morphology-based recomposition based on 3-dimensional input image data including an image stack of 2-dimensional (2D) images, the morphology-based recomposition being a final image generated by performing one or more white top hat (WTH) transforms on each 2D image, generating two or more image layers based on two or more WTH transformed images, and scaling adjacent image layers based on one or more scaling factors, each scaling factor being based on an estimated point spread function (PSF), two structure element sizes, and standard deviations of the estimated PSF and image data.

The present invention discloses a grayscale morphological quantum image segmentation method, characterized by obtaining an original NEQR quantum image; performing a cyclic shift operation on the original NEQR quantum image according to a neighborhood window to obtain a quantum image set; performing a bottom-hat transformation or a top-hat transformation on the quantum image set to obtain a result image; and performing a binarization operation on the result image obtained by the bottom-hat transformation or the top-hat transformation to obtain a binary image. The quantum version of morphological theory is used for image segmentation, and quantum images containing uneven illumination are well segmented. Unlike classical methods, the method of the present invention, which utilizes quantum computing, can process the quantum state superposition of pixels in the quantum image, thereby significantly accelerating the speed of the classical method.