157 results about "Corner detection" patented technology

The invention discloses a two-stage infrared and visible light image registration method, system and device. The method comprises the following steps of image preprocessing, contour extraction, angular point detection, feature description and matching, affine transformation estimation, multi-scale optical flow estimation, optical flow constraint and loss function, reverse resampling and fusion and error evaluation. According to the invention, rough registration is carried out by using contour angular point features, so that a preliminary alignment result can be quickly obtained; refined alignment is carried out in combination with an unsupervised optical flow network, and sub-pixel-level registration precision is achieved. The contour angular points are based on shape information of an image target, are natural and are not influenced by spectral differences, and the matching stability is enhanced through main direction and angle features. The unsupervised depth optical flow model estimates a pixel displacement field by learning consistency characteristics of an input image, and does not need to depend on annotation data. The combination can effectively eliminate the difference between infrared light and visible light, and improves the robustness and adaptability of registration.

The present invention relates to the field of rock structure measurement, and disclosed are a three-dimensional pore reconstruction method and system based on a rock image, for use in solving the problem that using a machine learning method to reconstruct pores in a rock image requires relatively high mathematical or computer science expertise, involves high labor and economic costs, and is difficult to apply to small-scale rock pore reconstruction projects. The method comprises: step 1: grouping slice images of each rock sample into one set, and performing preprocessing; step 2: performing grayscale processing, histogram equalization and normalization processing on an image; step 3: using a Harris corner detection algorithm to perform corner detection, sorting Harris response values, selecting key points by setting the number of key points, and using a non-maximum suppression method to screen the selected key points; step 4: segmenting the boundaries of pores in the image by means of an adaptive threshold selection method, and extracting pore features; and step 5: using a marching cubes algorithm to construct a three-dimensional pore reconstruction model. The present invention is used for three-dimensional reconstruction of pores in a rock image.

The invention discloses an image processing method and device, equipment and a storage medium, and is applied to the technical field of image processing. According to the scheme, the method comprises the following steps: detecting angular points in a target image to be interpolated based on an angular point detection algorithm to obtain feature points in the target image; for the texture complexity of the neighborhood image of each feature point, selecting a target interpolation algorithm for processing the feature point; and performing interpolation processing on the feature points based on a target interpolation algorithm to generate an interpolation result image. For angular points with complex textures, a high-precision interpolation algorithm is adopted to ensure that image details are finely restored; and for the angular points with slightly simple textures, a low-calculation-amount algorithm is used to reduce resource occupation, so that the limitation that a single algorithm is uniformly adopted for the whole image in the prior art is avoided, and the redundant calculation amount is remarkably reduced while the interpolation precision of the key feature region is ensured and the quality of the whole image is maintained.

The invention discloses a coal cutter roller cutting interference state identification method based on an infrared image, and the method employs an infrared camera to shoot the surrounding environment, effectively prevents the recognition precision from being limited by complex illumination environments, such as underground low illumination, high dust, and strong water mist, and guarantees the stability and definition of a target contour. Then analyzing and processing the infrared image through a deep learning network, determining four corner points of the hydraulic support face guard in the area from the infrared image by adopting a Shii-Tomasi corner point detection algorithm, further accurately calculating the spatial attitude of the hydraulic support face guard, and constructing a three-dimensional trajectory model of the coal mining machine roller; the Kalman filtering is adopted to obtain the predicted poses of the two, and then the cutting interference state is judged through early warning grading, so that the response speed and the safety guarantee capability of the fully-mechanized coal mining system are remarkably improved, the dynamic prediction and real-time response of the cutting interference state are realized, and the efficiency and the precision of cutting interference state recognition are ensured.

The invention relates to the technical field of ultrasonic medical robots, and discloses a superficial ultrasonic scanning path planning method and device based on an SVD-improved RRT algorithm. The superficial ultrasonic scanning path planning method is applied to ultrasonic medical robot equipment, and specifically comprises the following steps: S101, receiving a data acquisition request sent by a main control end, controlling a Kinect camera to acquire a superficial depth image, processing 20 groups of calibration board images through a Matlab calibration tool box, and executing a corner detection algorithm to identify checkerboard corners, and optimizing and solving the internal reference matrix of the infrared camera. According to the method, SVD plane fitting and an improved RRT algorithm are fused, the precision and efficiency of an ultrasonic scanning path are remarkably improved, in the point cloud processing stage, statistical filtering and voxel gravity center down-sampling synergistically act, point cloud noise is reduced by 90%, meanwhile, more than 95% of three-dimensional features are reserved, a high-fidelity data basis is provided for path planning, and the method has good application prospects. SVD plane fitting forcibly passes through the center of mass, and the error is smaller than or equal to 0.5 mm

The invention discloses a target ground object AI identification method based on a multi-source aerial photo, and relates to the technical field of aerial photo processing, and the method comprises the following steps: S1, collecting a panoramic aerial photo of a to-be-identified region; s2, extracting a first data set by using the gray-level co-occurrence matrix of the panoramic aerial photo; s3, extracting a second data set according to response values of all angular points in the panoramic aerial photo; s4, inputting the first data set and the second data set into a preliminary screening condition model, and taking pixel points meeting the preliminary screening condition model as suspected target ground objects of the to-be-identified region; and S5, processing the suspected target ground feature of the to-be-identified area to obtain an accurate target ground feature. In order to overcome the limitation of a single feature, multiple information sources, such as texture features extracted by a gray-level co-occurrence matrix and structural features extracted by corner detection, are fused, the features of image control points in aerial photography can be described more comprehensively, and the accuracy and robustness of recognition are improved.

The invention relates to the technical field of image processing, in particular to an online calibration method and system for hydrological flow data, and solves the technical problem of low flow calculation precision caused by rough window segmentation and illumination interference in the prior art. The method comprises the following steps: collecting a water surface video in a river water flow process, and setting a velocity measurement line area in the water surface video along a water flow direction; according to the gray level distribution of the velocity measurement line area, carrying out illumination state judgment, and according to a judgment result, carrying out image restoration on an illumination abnormal area in the water surface video to obtain a restored water surface video; constructing a space-time image for the repaired water surface video, performing corner detection, clustering corners to divide a plurality of windows, and constructing a window weight for each window; and weighting the texture angle of each window according to the window weight of each window to obtain a weighted texture angle, and calculating hydrological flow data according to the weighted texture angle.

The invention discloses an acupoint recognition and positioning method and system, a moxibustion robot and a storage medium. The method comprises the steps of obtaining multi-modal data of a human body to be subjected to physiotherapy; carrying out preprocessing on the multi-modal data; constructing a multi-modal feature fusion model, and generating an enhanced acupoint feature map; constructing a human body meridian-acupoint incidence relation matrix on the basis of the enhanced acupoint feature map in combination with a preset human body meridian-acupoint incidence relation matrix; dynamically compensating the candidate area, calculating the real-time offset of the acupuncture point based on the body surface micro-motion data, and correcting the depth coordinate of the acupuncture point in combination with the body surface elastic modulus data to obtain the accurate three-dimensional coordinate of the acupuncture point to be positioned; on the basis of the precise three-dimensional coordinates, blood vessels and nerve dense areas around the acupuncture points are recognized through an improved Harris corner detection algorithm, and a safe moxibustion applying path is generated; meanwhile, the confidence value of the precise three-dimensional coordinate is calculated. According to the method, high-precision, self-adaptive, all-position compatible, safe and controllable acupuncture point recognition positioning is realized.

The invention discloses a camera calibration method and device, equipment and a storage medium. The method comprises the following steps: acquiring a first image acquired by shooting a calibration plate by a camera; wherein the calibration plate comprises a plurality of angular points; performing inverse perspective transformation on the first image based on the internal reference and the initial external reference of the camera to obtain a second image; detecting angular points in the second image to obtain a first angular point detection result; based on the first corner detection result, the first image and the internal reference, solving to obtain a target external reference of the camera; and calculating an error parameter based on the target external parameter, the internal parameter and the first image, and when the error parameter satisfies a preset condition, determining that camera calibration is completed. According to the technical scheme of the invention, the inverse perspective transformation is carried out on the first image shot and collected by the calibration plate, so that the influence of partial camera distortion can be eliminated, the accuracy of angular point detection is improved, and the success rate and accuracy of camera calibration can be improved.

The invention discloses visual detection equipment for surface defects of a silicon wafer, and relates to the technical field of semiconductor detection, and the technical key points are that the visual detection equipment comprises a base and a bracket fixedly mounted on the back surface of the base, a detector positioned right above the base is fixedly mounted on the bracket, and a position adjusting mechanism is arranged at the top of the base; a quantum dot fluorescence mechanism is arranged on the front face of the base, the position adjusting mechanism comprises a three-dimensional position adjusting assembly and a containing table, and the three-dimensional position adjusting assembly comprises an X rod fixedly installed on the top of the base. Free movement, accurate positioning and quantum dot fluorescence enhancement-based defect detection of the silicon wafer in a three-dimensional space are realized, the limitation of traditional equipment is broken through, wafers with different sizes and shapes are flexibly coped, comprehensive coverage and dead-corner-free detection are ensured, meanwhile, the accuracy and sensitivity of detection are remarkably improved, and the detection efficiency is improved. The detection error and the omission ratio are reduced, and reliable quality guarantee is provided for the semiconductor manufacturing industry.

This invention discloses an automated anterior tooth feature parameter extraction method and evaluation system based on computer vision, comprising: acquiring and visualizing a full-mouth scan image of a patient to be processed; cropping the corresponding tooth portion image; using Gaussian blur to eliminate specular reflection; using color segmentation to set thresholds for the H, S, and V channels respectively; separating the teeth and gingiva in each tooth portion image and performing morphological processing on each; extracting the tooth and gingiva portion contours using contour extraction methods; further refining the segmentation accuracy using the Chan-Vese active contour model algorithm and the energy function within the tooth portion contour; extracting corner points using the Shi-Tomasi corner detection method and then clustering them; extracting other important evaluation feature points through curve fitting and extreme value finding methods; and finally calculating relevant objective indicators for tooth evaluation and automatically generating the corresponding tooth score, thus completing the automated anterior tooth evaluation.

The invention relates to the technical field of industrial detection, in particular to a pin defect detection method, device and equipment and a medium. According to the method, based on pin target positioning, image segmentation is carried out on a pin image, form extraction is carried out on a pin area, an actual included angle between a central axis and a reference axis is calculated, whether the actual included angle is in a preset angle range is detected, and if the actual included angle is detected not in the preset angle range, the pin area is determined. And if so, determining that the corresponding pin has a bending defect. The method comprises the following steps: acquiring a pin image from an original image based on pin target positioning, segmenting to obtain a pin area, extracting morphological characteristics of the pin area to determine a central axis, determining a reference axis according to the pin image, and calculating an actual included angle between the reference axis and the pin image; and finally, determining whether the pin has a bending defect or not by judging whether the included angle is within a preset range or not. And performing morphological analysis on the pin image to determine an included angle between the central axis and the reference axis so as to complete defect detection of the pin.

The utility model belongs to the technical field of detection rulers, and particularly discloses a pressure vessel corner angle detection ruler. Comprising a main ruler and an auxiliary ruler which are rotationally connected, indicating mechanisms and level bubbles are arranged on the main ruler and the auxiliary ruler, the indicating mechanisms are located at the free ends of the main ruler and the auxiliary ruler, and a detection mechanism is movably arranged on the front side of the main ruler. The main ruler and the auxiliary ruler are rotationally connected, so that the total length of the detection ruler is flexibly adjusted, the auxiliary ruler can rotate around the rotating shaft relative to the main ruler, integrated detection of multiple parameters such as length, straightness, curvature, height and width can be realized, and the detection efficiency is greatly improved. The problem that the existing corner angle detection technology is difficult to adapt to the actual requirements of portability, instantaneity, manual operation and direct reading of specific deviation values in the manufacturing, mounting and inspection field of the pressure vessel is solved.

The invention relates to the technical field of sorting and recognition, and particularly discloses an intelligent recognition and sorting device and method for defective cans, the device comprises a detection and recognition unit, the detection and recognition unit comprises a machine body, a carrying mechanism is arranged in the machine body, and the carrying mechanism is used for transferring cans entering the machine body from one side of the machine body to the other side of the machine body; the two ends of the carrying mechanism correspond to the conveying line and are arranged close to the conveying line, a plurality of visual detection mechanisms are further arranged on the two sides of the carrying mechanism, and the visual detection mechanisms are used for detecting and identifying whether the cans transferred by the carrying mechanism have flaws or not; the carrying mechanism comprises a transfer assembly and a plurality of placing stations, the placing stations are arranged outside the transfer assembly in an array mode and are in running fit with the transfer assembly, when the transfer assembly works, the placing stations rotate along with the transfer assembly and achieve autorotation of the cans, then 360-degree dead-corner-free detection of the cans is achieved, and therefore the recognition and sorting precision and efficiency of the defective cans are improved.

The invention belongs to the field of wheel-rail tribology, and particularly discloses a wheel-rail fatigue crack intelligent quantitative characterization method based on microscopic analysis images, which comprises the following steps: carrying out image enhancement and noise reduction preprocessing on scanning electron microscope and optical microscope images of wheel-rail rolling contact fatigue cracks; inputting the image into a YOLOv8-CSSTAM model for target detection, and outputting an image crack prediction frame and a proportional scale prediction frame; on the basis of an automatic calibration algorithm of an image scale, calculating the widest connected region of the image in the scale prediction frame, and performing OCR character recognition to obtain the image scale; performing median filtering, threshold segmentation, edge smoothing and small area filling processing on the crack image in the crack prediction frame; carrying out Harris corner detection on the processed image to obtain candidate corners; and screening the angular points to obtain crack feature angular points, and then calculating crack size features. The method can quickly and accurately obtain crack information in the wheeltrack rolling contact fatigue crack image, wherein the crack information comprises the crack depth, the crack width and the crack propagation angle.

The invention discloses a method and a system for quickly inputting voting information. The method comprises the following steps: shooting a paper voting table containing a two-dimensional code to obtain an original image; performing document four-corner detection on the original image, and performing perspective transformation processing to obtain a coarse correction image; analyzing the two-dimensional code and pulling the corresponding electronic template; key points are extracted from the rough correction image and the template image for matching, and an initial key point pair set is obtained; when the quality is insufficient, the key point pairs are supplemented through OCR character graph matching; establishing an adaptive FFD control grid, and carrying out nonlinear deformation on the rough correction image until the rough correction image is aligned with a template pixel level to obtain a fine correction image; and clipping the ROI region according to the template definition file, executing check box classification identification to obtain structured voting data, and packaging the structured voting data into a preset format and outputting the structured voting data. According to the method, the heterogeneous second-level, high-robustness and traceable automatic information input aiming at the paper voting table form is realized.

The invention discloses a measuring instrument inclination angle monitoring method and device fused with vision assistance, belongs to the technical field of precise instrument measurement, and aims to solve the problem of poor reliability of inclination angle detection of a measuring instrument in the prior art. According to the technical key points, the method comprises the following steps: respectively acquiring an image containing a level gauge and an inclination angle measurement value by using an image sensor module and an inclination angle sensor in an inclination angle detection device fixed on a measuring instrument; a multi-core processor in the dip angle detection device is used for processing images containing the level gauge, bubble position information of the level gauge is extracted, and a dip angle value of the level gauge is obtained according to the bubble position information; and carrying out fusion processing on the dip angle value of the level gauge and the dip angle measurement value to obtain a fused dip angle value, and taking the fused dip angle value as a final dip angle monitoring result of the measuring instrument. The method is suitable for a high-precision measuring instrument with extremely high requirements on the real-time performance and the accuracy of horizontal inclination angle monitoring.

The invention relates to the technical field of control systems, in particular to a tool reference intelligent control system and method based on vision measurement. The control system comprises a high-definition camera, a standard ball and a controller, the standard balls are respectively mounted at a preset position easy to photograph and measure in a machine tool and on a cutter bar; the high-definition camera is in signal connection with the controller; the high-definition camera comprises a structured light camera, a visual camera and a light time-of-flight camera; wherein the structured light camera obtains position information of an object by emitting invisible infrared laser with a specific wavelength and calculating distortion of a returned coding pattern through a Harris corner detection algorithm, and is used for determining key feature points in an image; and the visual camera is used for simulating human eyes to obtain 3D data through two common cameras with a certain distance. According to the invention, unstable factors caused by manual participation in the machining process are removed, so that the production changing time is shortened, the product quality is stabilized, manual operation errors are avoided, and the working efficiency is improved.

The invention discloses an observation and judgment device for an automatic hot upsetting test system, and the device comprises a rotation detection mechanism which is used for bearing and driving a sample to rotate so as to achieve 360-degree detection; the shooting and marking mechanism is used for marking the sample and shooting and recording the surface state of the sample; the scrap scraping and recycling mechanism is used for cleaning sweeps generated in the test process and recycling the sample and the sweeps; the rotary detection mechanism, the shooting and marking mechanism and the scrap scraping and recycling mechanism work cooperatively to complete the processes of automatic detection, marking, waste scrap cleaning and recycling of the sample. According to the observation and judgment device of the automatic hot upsetting test system, the rotating turntable is combined with a photoelectric positioning technology, the turntable is driven by the servo motor to rotate, the number of turns is accurately controlled in combination with the photoelectric sensor, 360-degree dead-corner-free detection of a sample is achieved, and the upsetting detection efficiency is improved by 80% compared with that of traditional manual operation. The invention further provides an observation and judgment method of the automatic hot upsetting test system. According to the method, automatic rotating detection, marking and waste chip cleaning of the sample are achieved based on the device.

The application relates to the technical field of image recognition, and particularly provides an unmanned aerial vehicle part automatic recognition method based on corner point detection, which comprises the following steps: constructing a neural network model comprising a channel attention mechanism, acquiring multiple unmanned aerial vehicle images, and pre-processing and unmanned aerial vehicle part labeling the unmanned aerial vehicle images; acquiring corner point information in the unmanned aerial vehicle images after the unmanned aerial vehicle parts are labeled through a corner point detection method, and generating a corner point feature map; fusing the corner point feature map and the unmanned aerial vehicle images after the unmanned aerial vehicle parts are labeled to obtain a corner point image; and training the neural network model again by using the corner point image, inputting a to-be-detected target image into the trained neural network model, and recognizing unmanned aerial vehicle parts in the to-be-detected target image. The application enhances the robustness of the neural network model to complex scenes and noise interference, and realizes accurate and efficient unmanned aerial vehicle part automatic recognition.

The invention discloses a phase consistency enhancement and adaptive geometric fitting corner detection method. The method comprises the following steps: firstly, carrying out adaptive histogram equalization CLAHE contrast enhancement on a cross target area image detected by YOLO; calculating a phase consistency response of the enhanced image to obtain a corner candidate region insensitive to brightness and contrast change; and calculating Harris corner response on the enhanced image, combining the Harris response with the phase consistency response score to construct a comprehensive response diagram, and screening out a corner candidate set from the comprehensive response diagram by adopting adaptive multiple thresholds. According to the method, through combination of YOLO target detection and CLAHE region enhancement, illumination non-uniformity interference such as overexposure and shadow can be effectively suppressed in a target region, a comprehensive response diagram is constructed by adopting phase consistency and Harris response in a combined manner, corner candidates are screened by using adaptive multiple thresholds, and the luminosity invariant feature and gradient significance of corners are considered, so that the accuracy and the robustness of the target region are improved. And the angular point extraction accuracy is improved.

The invention discloses a robot for detecting in a bridge box cavity based on a flexible cable track and an operation method, and belongs to the technical field of bridge detection equipment. Comprising a mobile platform, a walking assembly, an anti-collision safety assembly, a detection assembly, a distance control assembly and a control system, a steel cable serves as a flexible track, the walking assembly clamps the steel cable to move through a V-shaped walking wheel and a safety lock rod, double encoders are fused for positioning, and a multi-degree-of-freedom mechanical arm of the detection assembly drives a detection unit to collect data in a full-dimensional mode. And anti-collision and self-adaptive lighting functions are matched. According to the invention, no-dead-corner detection of the box cavity is realized, the flexible track is convenient and reusable in deployment, accurate in positioning, safe and efficient, manual risks are avoided, the detection efficiency and data reliability are greatly improved, and the method is suitable for detection of various bridge box cavities.

The application provides a certificate integrity detection method and device and a storage medium. The method comprises the following steps: performing edge extraction on a certificate image based on a double-flow convolutional neural network (GSCNN) model to obtain an edge image of the certificate, and / or performing edge corner classification on an edge corner image of the certificate based on an edge corner detection network model to obtain an edge corner detection result; the edge image is used to determine whether the edges of the certificate belong to a closed loop; the edge corner detection result is used to determine whether the edge corners of the certificate are complete; and in the case that the edges of the certificate belong to a closed loop and the edge corners of the certificate are complete, it is determined that the certificate is complete. The certificate integrity detection method and device and the storage medium provided by the application determine whether the certificate is complete according to two automatic detection results of edge detection and edge corner detection, improve the accuracy of certificate integrity determination, improve the certificate acquisition quality, and reduce the manpower and material costs of certificate detection.

The invention discloses microfocus X-ray visual inspection equipment for surface defects of a plate-shaped object. An objective table of the microfocus X-ray visual inspection equipment is used for horizontally bearing the detected plate-shaped object; the radiation source is a signal emitter, and the detector is a signal collector; the objective table is used for achieving translation in the Z direction and the X direction and can achieve rotation in the horizontal plane, and the radiation source and the detector which are located above the objective table and below the objective table respectively can swing along with the rectangular frame and can move on the Y-direction rod in the Y direction. Three-dimensional dead-corner-free detection is achieved through multi-axis linkage, the definition and detection precision of acquisition imaging are effectively improved, the phenomena of missing detection and false detection are prevented, and the device is particularly suitable for 2D and 3D detection of chip packaging defect micro-focus X-ray vision.

The present application relates to the technical field of data processing, in particular to a data processing method and system based on unmanned aerial vehicle video and vector data fusion. By calculating the deviation of the predicted position and the actual detection position of each reference point in the image, the reference points with large errors are screened and the camera pose parameters are adjusted using the random consistency algorithm and the iterative optimization method to improve the projection accuracy and stability. Through grid division, corner detection and feature descriptor extraction, a reference point set is established, the parallax change standard deviation is introduced, and the unstable reference points with large fluctuations are removed to ensure the reliability of the pose solving process and the consistency of spatial registration. According to the registration and fusion of unmanned aerial vehicle video and vector geographic data, the problems of current vector element drift, occlusion determination difficulty and attitude error dynamic correction are solved, the spatial reality and dynamic stability of the augmented reality scene are enhanced, and the industrial needs of various application scenarios such as underground pipe network inspection are met.

The invention relates to the technical field of warehouse logistics equipment, and discloses a monocular camera-based pallet pose estimation method, a storage medium and related equipment. The method comprises the following steps: acquiring a fork entrance surface image of a pallet through a monocular camera; performing feature matching on the fork entrance surface image and a pre-stored template image to obtain a pallet area in the fork entrance surface image; the pallet area is preprocessed; detecting the edge in the pallet area through an edge detection algorithm; detecting angular points in the pallet area through angular points, and screening projection angular points corresponding to preset control angular points of the fork entrance surface of the pallet; obtaining projection coordinates of the projection angular points in a first coordinate system of the monocular camera through a sub-pixel angular point detection algorithm; and according to the 3D world coordinates and the projection coordinates of the control angular points, solving attitude parameters and position parameters of the pallet in the first coordinate system through a pose estimation algorithm. According to the method, the calculation amount of pallet pose estimation can be reduced, and the pose estimation response speed is increased.

The application discloses a kind of based on machine vision's preceding group subassembly weld joint positioning system and method, comprising the following steps: camera is hoisted above welding platform by tooling, relative position is fixed and camera center line is perpendicular to the plane of the workpiece to be measured;Camera intrinsic calibration is carried out, and hand-eye calibration between camera-welding robot or hand-eye calibration between line laser sensor-welding robot;Workpiece feeding, scene picture is shot;Based on the shooting picture, workpiece feature point set calculation is carried out using gray scale segmentation and Harris corner detection, for the scene that needs to be shot by multiple cameras, image stitching based on calibration board guide map is carried out before workpiece feature point set calculation;Seeking location feature point set and calculating weld joint end point;Weld joint tracking is carried out, and weld joint data is corrected in real time, to obtain actual weld joint data.The application can effectively improve the welding efficiency and automation degree of shipyard small group subassembly unit.

The invention provides a mineral dynamic identification and accurate sampling method and system based on deep learning, and the method comprises the steps: obtaining mineral image data and laser radar ranging data on a mine car in an underground environment, and carrying out the preprocessing of the data, and obtaining mineral feature data; designing a deep convolutional neural network architecture with multi-scale feature fusion and performing multi-stage training to determine a mineral recognition model; performing target detection by using a mineral recognition model, and realizing multi-target tracking through a Kalman filter and a Hungary algorithm; calculating mine car motion parameters by using FAST corner detection, ORB descriptors and an optical flow algorithm; predicting the future position of the target mineral by using multi-sensor fusion and an extended Kalman filter; and based on the predicted position, precise sampling operation is executed through quintic polynomial interpolation and dynamic compensation control. According to the invention, high-precision mineral identification and dynamic accurate sampling can be realized in a complex underground environment, and the representativeness and production efficiency of mineral sampling are obviously improved.

The utility model relates to the technical field of medicine automatic detection and information checking, in particular to a medicine box traceability code reading and information checking device integrating all-dimensional visual angle detection. The device comprises a conveying unit, a fixed support fixedly arranged on the conveying unit, a top detection camera, a bottom detection camera, a left detection camera, a right detection camera, a front detection camera, a rear detection camera and a central processing unit. The beneficial effects of the utility model are that according to the technical scheme, the detection cameras are arranged in the upper, lower, left, right, front and back directions of the conveying unit, so that omnibearing visual angle detection of six surfaces of the medicine box is realized, and the problem of traceability code information omission caused by fixed installation positions of the cameras in the prior art is solved.

The invention belongs to the technical field of camera equipment calibration, and provides a checkerboard corner detection method, which comprises the following steps of S1, preprocessing an original image acquired by a vehicle camera; s2, carrying out edge detection on the image preprocessed in the step S1; s3, based on the edge detection result obtained in the step S2, carrying out peak detection to obtain a local peak point; and S4, angular point calculation: based on a peak value detection result, obtaining row and column peak value point vectors, calculating all angular point coordinates, and obtaining final angular point information. Through a space and channel image fusion method, checkerboard corner detection in a vehicle sensing calibration scene is realized. Under the environmental conditions of shadow, reflection, uneven brightness and the like, the edge of the checkerboard image can be effectively extracted, and the corner detection accuracy is improved. By fusing space and channel information, the adaptive capacity of the algorithm to interference factors is remarkably improved, and the false detection rate is reduced.