47 results about "Image histogram" patented technology

The invention relates to the technical field of parking lot positioning, in particular to a vehicle positioning management system in a parking lot based on dynamic weight multi-sensor fusion. Comprising a multi-source sensor data acquisition unit; an environment entropy perception and weight pre-adjustment unit; a reinforcement learning weight optimization unit; and an edge end vehicle positioning management unit. According to the method, an image histogram entropy value and a UWB signal RSSI fluctuation variance are calculated in real time through a heterogeneous sensor array in combination with an environment entropy perception and weight pre-adjustment unit, meanwhile, a space correlation matrix is constructed through sensor plane coordinate mapping, and interference space correlation characteristics are extracted. Based on reinforcement learning, a causal correlation model of an environmental entropy change rate, interference characteristics and sensor failure time is established, a sensor failure window can be predicted in advance, the weight of each sensor accessing a fusion filter is dynamically adjusted, and the problems of environmental influence perception deficiency, sensor correlation analysis and failure pre-judgment are solved.

The invention provides a light-SAR image conversion method based on coordinate attention and histogram loss, and relates to the technical field of SAR image data enhancement, and the method comprises the steps: obtaining a to-be-converted optical image; inputting the optical image to be converted into a pre-trained SAR image generator, and converting to obtain a target SAR image; a coordinate attention module is arranged in the pre-trained SAR image generator, and the pre-trained SAR image generator is obtained based on a pre-trained bidirectional conversion framework; the coordinate attention module is used for performing global pooling from the horizontal direction and the vertical direction respectively, and constructing a global feature vector corresponding to the optical image to be converted based on a global pooling result; histogram loss is set in an overall loss function of the pre-training bidirectional conversion framework; histogram losses are constructed based on kernel density estimates and differences between image histograms are determined using square earth motion distances. In combination with the method, the realistic degree of the finally generated target SAR image is improved.

The invention provides a histogram equalization method based on gray scale redistribution. The method comprises the following steps: S1, carrying out statistics on image histogram information; s2, performing Gaussian smoothing filtering on the histogram information; s3, histogram clipping is carried out, the filtered histogram is clipped by adopting a preset parameter clipRatio, a clipped histogram clipped Hist is obtained, and statistics is carried out on a clipped part count; s4, carrying out histogram redistribution; and S5, according to the obtained histogram reHist, calculating a mapping function cdf, and mapping the input brightness image y. The key point of the method is the realization process of brightness image histogram equalization. The statistical brightness image histogram is cut and redistributed to different regions of interest, so that the influence of dominant gray levels on a mapping function in a traditional histogram equalization method is avoided, and the problem of excessive brightness enhancement of the traditional histogram equalization algorithm is solved; wherein the distribution weights and distribution modes of different regions of interest keep more dark region / bright region details for the image after histogram equalization.

The invention discloses a neurosurgery intraoperative lesion recognition system based on an ultrasonic image enhancement technology, and the system comprises an image collection module which is represented as a two-dimensional function I; the self-adaptive median filtering module is used for converting into an output image J; the gray level normalization module is used for generating an output image K; the multi-scale Retinex algorithm enhancement module is used for obtaining an enhanced output image E; the histogram equalization module is used for carrying out histogram equalization on the output image E; the feature extraction module is used for carrying out feature extraction based on a convolutional neural network CNN; and the classification module is used for obtaining an ultrasonic image at the focus. Therefore, noise can be suppressed through adaptive median filtering, contrast and definition can be enhanced through gray level normalization and histogram equalization, lesion features are highlighted through a multi-scale Retinex algorithm, and lesion features are accurately extracted and classified through combination of a convolutional neural network and a support vector machine.

The present invention discloses a lane region segmentation method, system, electronic device, and storage medium, relating to the field of intelligent transportation. The method comprises the following steps: 1) inputting a road image captured by a road monitoring probe and extracting straight lines from the road image using the Hough method; 2) clustering the extracted lines and sorting them by angle and distance to the origin, taking the first and last straight lines l1 and l2 after the sorting; 3) using l1 and l2 to segment the road image to obtain an image of the road surface area; 4) calculating the histogram of the segmented image, using grayscale features to find two grayscale thresholds, and using dual-threshold binarization to segment the lane region; 5) using morphological methods to remove interference from small image holes, and using connected domain detection to remove the median strip, thereby completing the lane region.

The present invention discloses a digital image threshold self-determination algorithm based on pixel neighborhood information, comprising the following steps: (1) selecting a Laplace template of an image, performing convolution calculation to obtain an L‑P grayscale value; (2) marking the L‑P grayscale value obtained in step (1) and replacing the original image grayscale, and performing grayscale value cumulative statistics; (3) drawing a grayscale distribution histogram after replacement and comparing it with the original grayscale image histogram; (4) marking two intersection points generated by the grayscale histogram of the L‑P value after replacement and the grayscale histogram of the original image, obtaining the grayscale value interval of the pixel points corresponding to the two intersection points by calculation, using this interval to cover the original grayscale values ​​of all segmentable boundary pixels, and calculating the maximum value of inter-class variance within this interval; (5) taking the grayscale corresponding to the maximum value of the inter-class variance as the optimal segmentation threshold, which can more accurately and effectively segment the grayscale image of the geotechnical material microscopic image.

Provided is a technique for performing good black balance correction without being affected by color components of an observed image. A microscope system is provided with: a microscope that forms an observation optical image; an imaging device that captures an observation optical image and generates an observation image; a histogram generation unit that generates a pixel value histogram for each color component of the observation image; a correction value determination unit that determines a black balance correction value on the basis of the pixel value histogram for each color component; a correction unit that generates a corrected observation image by subtracting the black balance correction value from a pixel value for each color component of each pixel of the observation image; and an output device that outputs the corrected observation image.

Systems and methods of detecting and recognizing products on product storage structures of a product storage facility include an image capture device that moves about and captures images of the product storage structures at the product storage facility. A computing device processes the obtained images to detect and identify the products on the product storage structure, crops each of the identified individual products from the image to generate a plurality of cropped images and generates an image histogram template, feature vector template and location information template for each of the cropped images. The cropped images are stored in an electronic database and represent a reference model for each of the identified individual products and are stored in association with the generated image histogram template, feature vector template and location information template to facilitate recognition of products subsequently captured on the product storage structure by the image capture device.

The invention discloses a polarization image texture descriptor for representing classification similarity, and belongs to the technical field of polarization spectral imaging and image processing thereof. According to the method, an orthogonal differential polarization image is input, a multi-angle polarization binary pattern (pLBP-MA) is used for locally encoding the polarization image in four different directions in a uniform mode, integral LBP encoding is carried out in a non-uniform mode, a polarization differential image histogram is constructed, and texture classification similarity is measured through histogram intersection. The problem that a simple LBP cannot represent polarization texture information from different polarization angles is solved, and a new technical means is provided for target detection and recognition.

The invention provides a multi-scale adaptive short wave infrared image enhancement method and device. The method comprises the following steps: calculating a cumulative probability density function of an original image histogram; based on the cumulative probability density function and the golden section value, determining a segmentation gray threshold value used for segmenting the original image histogram; segmenting the original image histogram according to the segmentation gray threshold to obtain a first sub-image histogram and a second sub-image histogram; performing multi-scale adaptive correction on the first subimage histogram and the second subimage histogram to obtain a first corrected histogram corresponding to the first subimage histogram and a second corrected histogram corresponding to the second subimage histogram; determining an enhanced histogram of the original image histogram according to the first corrected histogram and the second corrected histogram; and determining an enhanced image of the original image according to the enhanced histogram. The image enhancement effect is improved when image enhancement is carried out.

The invention discloses a rapid adaptive SAR image correction method based on a human vision system. The method comprises the following steps: S1, normalizing an original SAR image and calculating a pixel concentration ratio; s2, judging whether the pixel concentration ratio exceeds a threshold value or not: if the pixel concentration ratio does not exceed the threshold value, assigning the normalized original SAR image to the low-concentration-ratio SAR image, and entering S4; otherwise, entering S3; s3, mapping the histogram peak value of the normalized original SAR image to a set histogram peak value position through a power function, and calculating a low-concentration SAR image; s4, constructing a reference histogram based on a human visual system theory, and mapping the histogram of the low-concentration SAR image into the reference histogram to obtain a mapped SAR image; and S5, obtaining a detail enhanced image based on partition control. The multi-source SAR image self-adaptive correction method has wide applicability and self-adaptive processing capacity, after parameter setting is completed, multi-source SAR images can be corrected in a self-adaptive mode, and histograms of the corrected images are basically consistent.

The invention discloses a medical X-ray perspective grayscale adaptive control method based on histogram features, and relates to the technical field of medical X-ray imaging and medical image processing, and the method comprises the steps: extracting image histogram features, and adjusting a high-voltage generator and parameters in combination with an ABC curve to maintain the image grayscale stable; the method further comprises the following steps: constructing a multi-dimensional correction-real-time calibration contrast agent photon attenuation-histogram feature nonlinear mapping model, performing synchronous coupling control on real-time photon counting-histogram features, and completing parameter self-calibration by using a contrast agent attenuation critical threshold effect; according to the invention, through a nonlinear mapping model, an FPGA parallel architecture, physiological signal correction and one-frame pre-injection calibration, a contrast agent gray abrupt change time sequence difference is eliminated, overexposure and underexposure are avoided, and high-frequency clinical real-time accurate requirements are met; meanwhile, contrast agent concentration quantification and flow evaluation are achieved, trinity diagnosis and treatment assistance is formed, the missed diagnosis rate is reduced, and the clinical value of medical X-ray fluoroscopy equipment is remarkably improved.

The present invention discloses a shipborne video defogging method based on dual histogram equalization, comprising the following steps: S1: performing mean normalization processing on the histogram of the input image; S2: performing gamma correction on the part of the normalized histogram that is less than 1, and limiting the larger histogram data by setting an over-enhancement threshold T, reducing the influence of the largest number of pixels in the histogram, and preventing over-enhancement; S3: calculating the median pixel of the histogram of the input image, and dividing the original histogram into left and right sub-histograms according to the median pixel; S4: respectively calculating the grayscale distribution probability histogram of the left and right sub-histograms; S5: calculating the cumulative distribution histogram of the left and right sub-histograms; S6: merging the left and right mapping tables to obtain the final mapping table, and mapping the original image according to the mapping table to obtain the defogging shipborne video image. The present invention has the characteristics of strong defogging ability and high fidelity, and is suitable for shipborne video defogging.

The present invention is a video contrast enhancement method and system, especially a video contrast enhancement algorithm based on self-supervised learning. The unsupervised image quality evaluation model is used to guide the training of the video contrast enhancement algorithm model. The present invention can achieve real-time video contrast enhancement on the CPU. Inspired by the image histogram equalization algorithm, the present invention designs an adaptive gray mapping mechanism, uses the unsupervised image quality evaluation model as a guide, and regresses to obtain the Map mapping matrix; different Map mapping matrices will be obtained for different images for video contrast enhancement, without human intervention, which is particularly user-friendly in the use of the algorithm.

The invention belongs to the technical field of machine vision, and particularly relates to a flexible printed circuit (FPC) image rapid segmentation method and an FPC image segmentation system. According to the method, FPC image segmentation can be rapidly and accurately realized. Comprising the following steps: S1, carrying out layer-by-layer downsampling processing on an FPC image by using a Gaussian pyramid, and gradually reducing the resolution of the image; s2, calculating a grey level histogram of each layer of the downsampled FPC image, and comparing the grey level histogram with the grey level histogram of the original FPC image; evaluating the difference between the image histograms of different levels and the original FPC image histogram by using the chi-square distance as a measurement standard; and according to a result of the chi-square distance, determining a stop layer number of down-sampling. S3, for the selected stop layer image, calculating an optimal segmentation threshold value by using an OTSU algorithm, and taking the optimal segmentation threshold value as a final segmentation threshold value of the original FPC image; therefore, the time required for determining the segmentation threshold is greatly reduced while the effectiveness of the segmentation threshold is guaranteed.

The application discloses a low-distortion reversible contrast enhancement method based on RDH, which comprises the following steps: 1, a contrast-enhanced gray level mapping is obtained by histogram specification processing of an original image; a globally enhanced image is obtained by transformation according to the gray level mapping; data structures A and B of one-to-one and one-to-many gray mapping inversion are respectively calculated according to the gray level mapping; global recovery data information is extracted from the original image; the global recovery data information is encoded as embedded data; the embedded data is embedded into the globally enhanced image to obtain a reversible globally contrast-enhanced image; a locally contrast-enhanced image is obtained by using a fuzzy mean clustering algorithm for local contrast enhancement; and local recovery data information is extracted from the reversible globally contrast-enhanced image and embedded into the locally contrast-enhanced image to obtain a reversible locally contrast-enhanced image. The application introduces local contrast enhancement on the basis of global contrast enhancement, thereby reducing image distortion.

The invention relates to the technical field of image processing and data acquisition, and discloses a financial bill intelligent identification and archiving method of an embedded hardware terminal, and the method comprises the steps: firstly obtaining a global low-resolution image, and generating an acquisition instruction queue containing heterogeneous ISP parameters; then controlling the image sensor to execute hardware-level asynchronous serialization acquisition by utilizing vertical blanking interval configuration to obtain heterogeneous local image slices; and eliminating view field displacement between the slice and the global image by using gradient domain registration, and executing logic consistency verification on the identified and extracted service data. And if the verification is passed, generating a layered archived file, otherwise, based on the image histogram, generating a correction parameter and triggering hardware feedback recollection. According to the invention, through a heterogeneous acquisition strategy and a business logic closed loop, the problems of high delay of high-resolution acquisition of a mobile terminal and difficult alignment of handheld shooting are effectively solved, and the bill identification accuracy and filing efficiency are significantly improved.

The invention relates to a method and system for screening crop growth images, and the method comprises the steps: obtaining a plurality of continuous growth images of crops, and carrying out the preprocessing of the growth images through a bilateral filtering method and a contrast-limited adaptive histogram equalization method; the preprocessing comprises denoising, contrast enhancement, brightness enhancement and saturation enhancement; on the basis of feature point matching and an image histogram, comparing the preprocessed continuous growth images, and screening and storing a plurality of images of which the image difference values are greater than a preset value within a preset time; based on a Laplacian operator and an image entropy, performing quality evaluation on the plurality of screened images; and filtering the image with the quality lower than the preset quality according to the evaluation result. Through the image comparison and screening method, the storage efficiency, the monitoring accuracy and the image quality of the crop growth image are improved, and the adaptability is high.

The application provides a histogram equalization method for protecting details, comprising the following steps: S1, dividing an input luminance image into blocks; S2, counting a histogram of the image; calculating an average gray level of a current block; S3, histogram redistribution, comprising the following steps: calculating a clipping threshold; histogram clipping and redistribution; S4, calculating a mapping function; S5, adjusting the mapping function; and S6, enhancing the input image. The histogram equalization method solves the problem of over-enhancement in bright areas and dark areas, and ensures that low-contrast images will not lose the details of bright areas and dark areas after being enhanced.

Methods and systems are described for estimating an optimal pupil binarization threshold using adaptive binarization thresholding. The disclosed methods and systems are designed to determine a pupil binarization threshold from a histogram of an eye image. An eye image is obtained and an eye image histogram is computed from the eye image. A pupil region and an iris region are identified in the eye image histogram and the second derivative of the eye image histogram is computed. The pupil binarization threshold is determined based on the second derivative of the eye image histogram, the identified pupil region and the identified iris region and then used to generate a binarized eye image. A pupil contour may be determined from the binarized eye image. The disclosed system may help to overcome challenges associated with robust and precise detection of a pupil contour, for example, in images of varying quality.

The present invention relates to the field of image processing technology. Specifically, the present invention relates to a high-definition medical image processing method. The present invention performs noise reduction processing on the ileocecal image through a guided filtering algorithm, obtains the histogram of the ileocecal image, calculates the potential secretion index of each pixel point in the ileocecal image according to the ileocecal histogram, extracts the pixel points exceeding the potential secretion index by setting a segmentation threshold, connects the pixel points to highlight the diseased area of the ileocecal part, and uses an edge detection algorithm to extract the edge features of the diseased area image, obtains the resolution of the edge pixel points, then uses Fourier transform analysis to obtain the blur degree coefficient of the edge pixel points, obtains the enhancement coefficient of the diseased area image according to the resolution and blur degree coefficient of the edge pixel points, and realizes the enhancement of the diseased area image of the ileocecal part by adjusting the enhancement coefficient of the diseased area image.

The invention discloses a remote sensing image nonlinear simulation method and system and a readable storage medium. The method comprises the following steps: inputting a panchromatic image and a multispectral band image; registering the multispectral image and the panchromatic image, and resampling according to a high-spatial-resolution wave band; counting the mean value, mean square error and correlation coefficient matrix of the panchromatic image and the multispectral image; constructing an intermediate wave band I by using the low-resolution multispectral image; constructing an image simulation operator by utilizing remote sensing image histogram feature matching; and solving a feature fusion coefficient kE and a feature extraction coefficient kI, determining an image simulation scheme, and carrying out image simulation on wave bands one by one. The method is not limited by the number of image wavebands, and the remote sensing image simulation result can be predicted. According to the method, two image simulation modes of injecting the panchromatic wave band image into the multispectral wave band image and injecting the multispectral wave band image into the panchromatic wave band image are provided, and high-fidelity simulation of ground object spectrum and space information of the remote sensing image can be realized.

The application provides an image histogram smoothing device, method, electronic equipment and storage medium, relates to the technical field of image processing, and the device comprises an initialization module, a weight curve determination module, a smoothing module and a construction module, wherein: the initialization module is used for determining an initial image histogram corresponding to a target image and a reference brightness; the weight curve determination module is used for determining a weight curve corresponding to each bar in the initial image histogram based on the reference brightness; the smoothing module is used for traversing each bar, determining a target statistical value of the current bar based on each target weight curve extending to the current bar, and the target statistical value is used for representing the mutual influence relationship between each bar; and the construction module is used for determining a smoothed image histogram based on the target statistical value of each bar. The application can realize the smoothing of the image histogram, and improve the anti-interference and stability of the image histogram.

The invention relates to a vegetation identification method and device based on an unmanned aerial vehicle image, a readable medium and a program, and the method comprises the steps: obtaining the unmanned aerial vehicle image of a to-be-identified region, and calculating a constructed RGBSI vegetation index based on the brightness values or reflectivity of the red light wave band, the green light wave band and the blue light wave band of the image, and extracting a vegetation region from the image of which the RGBSI vegetation index is calculated by using a threshold segmentation method. The RGBSI vegetation index constructed by the method combines the strong reflection of green vegetation in a green light wave band and the absorption characteristics of the green vegetation in red and blue wave bands, when the method is used for vegetation identification, an image histogram of a vegetation index grey-scale map image calculated by RGBSI has a good double-peak form under the condition of medium and high vegetation coverage, a threshold can be rapidly determined by using a maximum entropy threshold method, and the method can be applied to vegetation identification. And the threshold value is generally close to 0. The overall extraction precision of identifying the vegetation-containing image by using the RGBSI index is more than 90%, the extraction precision is high, and the extraction effect of vegetation with medium and high vegetation coverage is better.

This invention belongs to the field of digital image preprocessing technology and discloses an adaptive enhancement method for underground utility tunnel fire images, comprising: Step 1, receiving a fire image and preprocessing it to obtain a grayscale histogram; Step 2, calculating a grayscale histogram segmentation threshold; Step 3, using the grayscale histogram threshold, segmenting the original image histogram into three sub-block arrays: a low grayscale area, a middle grayscale area, and a high grayscale area, and marking the pixel range corresponding to each sub-historical array; Step 4, performing enhancement processing on the three sub-block arrays to obtain an enhanced and reconstructed fire image, and transmitting the enhanced fire image data to a remote control center. This invention can effectively improve the clarity and contrast of fire images in complex environments such as low light and low contrast, thereby achieving rapid and accurate identification of fire features.

The present application discloses a method for predicting blast furnace conditions based on flame images of charge surfaces and related equipment, the prediction method comprising obtaining an in-furnace image of the blast furnace to be predicted, and determining a dynamic boundary threshold corresponding to the in-furnace image based on an image histogram of the in-furnace image; determining a flame region in the in-furnace image based on the dynamic boundary threshold; obtaining regional parameters of the flame region and image parameters of the in-furnace image; and predicting the blast furnace condition of the blast furnace to be predicted through a trained classification model based on the regional parameters and the image parameters. The present application improves the prediction accuracy of the blast furnace condition by obtaining an in-furnace image, determining the flame region corresponding to the in-furnace image based on a dynamic boundary threshold, and then predicting the blast furnace condition through a classification model based on the regional parameters of the flame region and the image parameters of the in-furnace image.

The embodiment of the invention discloses a digital image detection method and device based on OpenCV, electronic equipment and a storage medium, the method is applied to a computer, the method is applied to the computer, and the method comprises the steps that a first image is collected through a camera; calling a preprocessing algorithm of OpenCV to preprocess the first image to obtain a second image; the preprocessing algorithm comprises one or a combination of more of the following algorithms: gray processing, Gaussian blur processing and image histogram equalization processing; calling a Sobel operator of OpenCV to carry out edge detection on the second image to obtain position information of a digital region in the second image; and calibrating the number area in the first image according to the position information, thereby efficiently and accurately identifying the number from the image.

The invention relates to a visual SLAM front-end processing method based on fuzzy clustering contrast enhancement, and belongs to the technical field of visual synchronous positioning and mapping, and the method comprises the following steps: S1, obtaining an original image collected by a camera, and carrying out the preprocessing of the original image; s2, performing image quality evaluation on the preprocessed image, making a decision according to an evaluation result, and if enhancement is skipped, directly turning to a front-end processing flow; if enhancement is started, executing a fuzzy C-means clustering enhancement algorithm; s3, analyzing the intensity distribution of the image through fuzzy C-means clustering, and adaptively stretching an image histogram according to a membership relationship to enhance the image; and S4, carrying out feature extraction, feature matching and pose estimation on the enhanced image and the preprocessed unenhanced image to realize visual SLAM front-end processing.

The invention provides a method and system for enhancing a Mura defect image in an OLED display panel, and relates to the field of defect detection and quality control, and the method comprises the steps: obtaining an original image of the OLED display panel, the original image having a Mura defect; performing histogram image conversion and pseudo-infrared image conversion on the original image by adopting a dual-channel preprocessing strategy to obtain two complementary histogram enhanced images and pseudo-infrared images; wherein the histogram image conversion process comprises color image graying, local histogram statistics, equalization mapping and smooth fusion, and the pseudo infrared image conversion process comprises contrast and brightness adjustment and pseudo infrared color mapping; and performing three-mode feature fusion on the original image, the histogram enhanced image and the pseudo-infrared image to obtain a defect integrated image. According to the method, a complementary information fusion image preprocessing mode is adopted, histogram equalization and pseudo-thermal imaging transformation are combined, and the visibility of low-contrast defects can be enhanced.

The embodiment of the invention relates to the field of image detection, and discloses a tunnel surface crack image automatic detection method, device and equipment and a storage medium, and the method comprises the steps: carrying out the image preprocessing of a tunnel surface image, and obtaining a binary image, the image preprocessing comprises the filtering processing, the local image histogram stretching processing and the binary processing, the filtering processing comprises the steps of judging whether the image contains salt-and-pepper noise or not, and if the image contains the salt-and-pepper noise, sequentially performing median filtering processing and bilateral filtering processing on the image; removing residual noise in the binarized image to obtain a crack image by analyzing crack characteristics of a connected region in the binarized image; and carrying out crack refining processing on the crack image to obtain a crack skeleton image. According to the tunnel surface crack image automatic detection method disclosed by the invention, the problem that the accuracy of crack detection is influenced by noise existing in the tunnel surface image is solved, and the effect of eliminating the noise existing in the tunnel surface image can be effectively improved.