15 results about "Image moment" patented technology

The invention discloses an anti-counterfeiting printed matter preparation and identification method and system based on halftone frequency compensation, and the method comprises the steps: determining the compensation frequency of an embedded texture needed to be embedded into an original digital image according to the frequency of macroscopic moire patterns induced when an input anti-counterfeiting printed matter is copied; designing an embedded texture based on halftone frequency compensation according to the compensation frequency, and generating a digital image hidden with the embedded texture; and outputting the digital image hidden with the embedded texture to a printing material through printing equipment to obtain an anti-counterfeiting printed matter. The invention aims to utilize the active induction mechanism of the moire to actively induce the moire characteristics excited in the frequency domain and the micro texture at the moment of imaging of the copy, the discrimination of the copy is converted from searching a weak signal to detecting significant interference, and the stability of anti-counterfeiting printed matter discrimination in the application scene of complex media and cross-brand equipment is improved.

The utility model discloses a kind of photo albums with video function, including cover, top plate, magnetic attraction piece, T type support pole, T type support foot, cover side is connected with bottom cover by cover spine, top plate is connected by folding portion between bottom cover, top plate top is equipped with mounting groove and is equipped with display screen in mounting groove, lithium battery and video storage chip are equipped in top plate, magnetic attraction piece is located in cover and top plate, photo album is innovatively integrated with display screen, not only can play the photo in video storage chip, can also play video, when user peruses photo album, not only can see familiar paper photo on inner page, can also review dynamic image moment through display screen, and photo album still retains the cover, bottom cover and inner page structure of traditional photo album, user can continue to place paper photo therein, give consideration to the emotional dependence of people to traditional photo album;While incorporating modern electronic technology, the display of dynamic image is realized, greatly enrich the use experience of viewer.

The application relates to the technical field of machine vision measurement, and discloses a workpiece visual measurement method, device, equipment and storage medium, the workpiece visual measurement method comprises the following steps: collecting an original image, performing gray scale processing on the original image, performing edge detection processing based on the gray scale image, and obtaining a workpiece image; obtaining a direction gradient histogram of the workpiece image to obtain contour information of a workpiece to be measured; determining an image moment of the workpiece to be measured according to the gray scale image, and matching the workpiece to be measured with a template workpiece according to the image moment and the contour information to judge whether the workpiece to be measured is rotated; if the workpiece to be measured is rotated, fitting an edge straight line of the workpiece to be measured according to edge information of the workpiece to be measured; and determining a rotation angle of the workpiece to be measured relative to a placement state of the template workpiece according to the edge straight line of the workpiece to be measured. The application is simple in operation in the workpiece measurement process, easy to maintain, can save labor cost, and ensures the stability of product quality.

The disclosure provides a document image reading order arrangement method and system based on a convolutional neural network, relating to the technical field of image processing, comprising obtaining document image data to be sorted and preprocessing; inputting the preprocessed document image data into a global sequence positioning model of a deep convolutional neural network to obtain a global sequence positioning arrangement result; then performing heuristic local sorting on the text area inside the global sequence positioning arrangement result, calculating the image moment of the string instance in the text area to obtain the center point coordinates of the string instance, sorting the center point coordinates of the string instance according to a set heuristic rule, and outputting the final sequence arrangement result in combination with the text area reading order.

The invention relates to the technical field of shooting, and provides a shooting anti-shake method, electronic equipment, a storage medium and a program product, which are applied to the electronic equipment, and the electronic equipment comprises a camera module and an inertial measurement unit. The method comprises the following steps: for a preview image which is acquired by a camera module at a first image moment and needs to be sent and displayed, the electronic equipment carries out anti-shake processing on the preview image based on a first equipment pose before smoothing and a target equipment pose after smoothing at the same image acquisition moment and then sends and displays the preview image; wherein the target equipment pose is smoothed in combination with the predicted second equipment pose. Thus, more and richer equipment pose change information is included between the first equipment pose and the target equipment pose, and more equipment pose change information can be referred to by performing anti-shake processing on the preview image based on the first equipment pose and the target equipment pose, so that the anti-shake effect of the preview image can be improved, and the user experience is improved. And the stability of the preview image and the operation mirror smoothness are ensured.

The invention discloses a space target instantaneous attitude estimation method and device based on bistatic inverse synthetic aperture radar imaging, and the method comprises the steps: obtaining an ISAR image in a current CPI of a space target obtained by a single-base / bistatic ISAR observation system, and obtaining the position information of the target and a radar; determining an expression of a mapping relation between a projection matrix and attitude parameters of the single-base / double-base ISAR observation system based on the position information; selecting feature points from the two ISAR images, and solving an expression of a mapping relation between a projection matrix and attitude parameters of the single-base / double-base ISAR observation system to obtain two mapping relation matrixes; and estimating the attitude parameters of the space target at the imaging moment based on the two mapping relation matrixes and the relation between the mapping relation and the attitude parameters. According to the method, high-reliability and low-cost instantaneous attitude estimation of the space target can be realized without selecting the same features in two images.

The invention provides a galvanometer calibration method and device, electronic equipment and a storage medium, and the method comprises the steps: transmitting a voltage signal to a galvanometer point by point based on a voltage sampling grid, so as to drive the galvanometer to perform angle deflection according to each voltage value, and transmitting a laser starting signal to a laser based on the angle deflection action of the galvanometer, the laser outputs a laser beam; the monocular camera is controlled to capture a laser spot image frame formed by the laser beam on the target surface, and a target local image area is cut with the maximum brightness point in the laser spot image frame as the center; performing binarization processing and image moment calculation on the basis of the target local image region to obtain a mass center pixel coordinate of the laser spot; and performing cubic strip sample interpolation based on the mass center pixel coordinate and the galvanometer driving voltage value thereof, constructing a mapping relation, and performing galvanometer calibration based on the mapping relation to obtain a final galvanometer driving voltage and a final light spot coordinate. According to the invention, the precision of galvanometer calibration is improved.

The invention discloses a target attitude estimation method based on unmanned aerial vehicle visual servo. The method comprises the following steps: setting feature points on a target; the unmanned aerial vehicle obtains an image of a ground target at an expected position, extracts feature points of the target, and obtains image moment features as initial image features based on the feature points; the unmanned aerial vehicle shoots a target in real time, extracts feature points of the target at the current position, fits an ellipse based on the feature points, and obtains image moment features of the current position based on the fitted ellipse; and taking a difference value between the image moment characteristic and the initial moment characteristic as an error, and based on the error, controlling the aircraft to fly towards the target by adopting a PID method. According to the method disclosed by the invention, the target attitude estimation is more accurate, and the tracking error is remarkably reduced.

The application discloses an intelligent breeding system and method based on Internet of Things, and relates to the technical field of big data analysis.The application realizes efficient management of intelligent breeding manure through multi-dimensional analysis.The image sensor collects manure images at a preset period and stores them according to time stamps, thereby constructing a data set and realizing dynamic monitoring of the manure.The image data is extracted to construct a ground cleaning image moment curve, a time series prediction model is used, color and texture feature analysis is combined, cleaning time is predicted, manure change rules are mined, and environmental problems are avoided.The color features of the manure images are quantified in HSV space to form a judgment standard, a trend graph is constructed based on color changes of adjacent time stamps, the predicted cleaning time is compared in real time, and two prediction results are fused by weighting, and the weight is dynamically adjusted according to the deviation, so that the decision is scientific and accurate, the manure treatment is refined and intelligent, and the breeding environment management is optimized.

This invention proposes a method for calibrating a cross-shaped structured light based on a planar target. The method includes acquiring images of intersecting laser stripes projected onto a planar target, extracting the center points of the laser stripes, removing center points of laser stripes located at the edges of feature points on the planar target, extracting the positions of the intersection points of the intersecting laser stripes in the image using image moments, incorporating these intersection points into a line fitting process, and performing line fitting to remove laser stripe center points that deviate significantly from the fitted line. Finally, the internal and external parameters of the camera target are obtained through camera calibration, the three-dimensional coordinates of the laser stripe center points on multiple images are calculated, and light plane fitting is performed to complete the calibration of the cross-shaped structured light. This invention effectively improves the calibration accuracy of the cross-shaped structured light by removing laser stripe center points close to the edges of feature points on the planar target and incorporating the intersection points of the intersecting laser stripes into the cross-shaped structured light calibration process.

This invention discloses a robust control method for an aerial contact operation robot, comprising: constructing a contact dynamics model of the aerial contact operation robot; constructing a visual servo controller based on image moments; constructing a visual impedance controller, which outputs a desired image moment based on the error vector between the tracked contact force and the desired contact force; the visual servo controller outputting a generalized control force generated by the aerial contact operation robot based on the desired image moment and the actual contact force; calculating a generalized torque generated by the aerial contact operation robot based on the generalized control force and the desired rotation matrix of the aerial contact operation robot using an attitude controller; and controlling the aerial contact operation robot based on the generalized control force and the generalized torque. This control method effectively improves the robot's operational stability and enables contact operations in areas with weak or absent outdoor GPS signals.

The glass defect detection method comprises the following steps: shooting glass to be detected to obtain an original image; processing the original image by using a pre-trained deep learning model to obtain a basic defect area and a defect type; generating a key image based on the basic defect area, and preprocessing the key image; generating a self-adaptive segmentation threshold value through a histogram smoothing algorithm and a double-peak average value algorithm, and segmenting the preprocessed key image based on the self-adaptive segmentation threshold value to obtain at least one accurate defect area; performing moment operation on the accurate defect area to obtain an image moment, and generating defect characteristics based on the image moment; and fusing the defect type and the defect characteristic to obtain a defect detection result. According to the method, firstly, the defect type in the original image can be accurately detected by using the deep learning model, the basic defect area containing the defect is extracted, and then the key image is processed, so that an accurate defect detection result can be obtained.

The invention relates to the field of flower data processing, in particular to a flower data measurement method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining initial pose data of a to-be-measured flower at a plurality of imaging moments and initial mask data of a flower imaging region; performing orthographic imaging coordinate system transformation according to the initial pose data to obtain orthographic pose data at a plurality of times of imaging moments; according to the initial pose data and the orthographic pose data, carrying out orthographic imaging coordinate system transformation on the initial mask data of the flower imaging area at the corresponding imaging moment to obtain orthographic mask data of the flower imaging area at a plurality of times of imaging moments; performing target orthographic mask pixel point extraction on the orthographic mask data of the flower imaging area to obtain target orthographic mask pixel point data at a plurality of times of imaging moments; and performing flower data measurement according to the orthographic pose data and the target orthographic mask pixel point data to obtain the flower height and the flower crown breadth of the to-be-measured flower.

This invention discloses a method for locating flexible ton bag lifting lugs based on a neural network model, relating to the field of computer systems based on specific computational models. It includes simultaneously acquiring and aligning color and depth images; inputting the CLAHE-enhanced color image into a neural network model, which introduces a depth-guided attention module into the backbone network to generate an attention weight map by fusing depth gradient information, and then performing element-wise multiplication with the color feature map to output the first 2D bounding box of the lifting lug; extracting depth pixel regions from the bounding box and converting them into point cloud data; denoising, calculating normal vectors and curvature of the point cloud, and using a clustering algorithm to remove bag body interference to obtain a second 2D bounding box; further analyzing image moments and depth gradients to generate grasping instructions for a robotic arm. This invention effectively solves the challenges of weak texture recognition, flexible deformation positioning, and real-time edge calculation against a background of the same color, significantly improving the robustness and efficiency of grasping.