382 results about "Minimum bounding rectangle" patented technology

The invention discloses a MELF (Metal Electrode Leadless Face) component positioning and detecting method based on match template which belongs to the technical field of component positioning and detecting. Under a traditional match template algorithm, it takes great amount of computing to detect a component with a rotation angle, and the process is also very slow to perform. For these reasons, the positioning and detecting speed for the component is also rather slow. In light of these shortcomings, the invention provides a MELF (Metal Electrode Leadless Face) component positioning and detecting method. The method creates a template image with angle to obtain a distance transformation image of a narrowed image of the component and a distance transformation image of the original image of the component and to obtain a final best match template image and a best match position. Key edge points are extracted from an edge image with interference points to form a minimum external rectangle. According to the number of the non-zero pixels in the minimum external rectangle with added offset value, the method determines that the positioning of the component is correct and that the length and the width of the component are in the bearable range. After that, the positioning and detecting process is complete and positioning information of the component is then transmitted out. The method provided by the invention is capable of reducing the number of positions searched during the computing of a match template value. With the method, the computing efficiency of a match template can be increased and the accurate rate for positioning and detecting reaches 95% to 98%.

The invention discloses an image recognition method based on edge geometric features. The image recognition method based on the edge geometric features comprises the steps that filtering processing is carried out on an original image of a workpiece; binarization processing is carried out on the image after the filter processing; the image after the binarization processing is searched to obtain a contour sequence set; a qualified workpiece contour is screened out of the contour sequence set; a minimum enclosing rectangle of the workpiece contour is determined, and the central point of the workpiece contour is determined; four subsequences of the workpiece contour are intercepted in the directions of the four edges of the minimum enclosing rectangle; energy values of all the four subsequences are calculated by using edge geometric feature operators; the subsequence with the maximum energy value in the four subsequences is determined, and direction angles of the workpiece are determined. The invention further provides a corresponding image recognition system. According to the image recognition method and system based on the edge geometric features, a template database of workpieces does not need to be established, storage consumption is lowered, calculation time is reduced, the requirement for high speed real-time performance can be met, and meanwhile the image recognition method and system have high fast recognition capability.

A round Mark point positioning method based on connected region filtering relates to positioning methods. The round Mark point positioning method based on the connected region filtering mainly solves the problem that traditional round Mark point positioning methods are complex in positioning algorithm, high in computer memory requirements, low in detecting time, low in detecting accuracy and prone to being affected by external environments to lead to template matching failure, meanwhile, have high Mark process requirements and cannot meet the detecting accuracy requirements for deformed round Mark points. The method comprises firstly, calculating the ROI (region of interest) of a target Mark point; secondly, obtaining the edge of the target point; thirdly, obtaining a binary ROI image; fourthly, retaining the ROI connected region with the maximum area; fifthly, retaining the ROI background connected region with the maximum area; sixthly, designing a noise filter; seventhly, obtaining filtering Canny edge points; eighthly, obtaining the minimum enclosing rectangle; ninthly, removing Canny edge defects; lastly, obtaining the central and radial parameters of the round Mark point. The round Mark point positioning method based on the connected region filtering is applied to the field of positioning methods.

The invention provides a fully-automatic face seamless synthesis-based video synthesis method. With the fully-automatic face seamless synthesis-based video synthesis method adopted, insufficient real-time property in high-definition video processing of a face detection algorithm in the prior art can be solved. The fully-automatic face seamless synthesis-based video synthesis method of the invention comprises the following steps that: a video communication application provided by an intelligent television terminal is utilized to perform video connection; an image or video file which is locally arranged or arranged in a cloud server is adopted as a background (BG) to be synthesized; face detection is respectively performed on data foreground (FG) and background (BG) data which are acquired by a camera through using the face detection algorithm, and geometric transformation coefficients are calculated through face internal key point positioning and facial contour lines or a face minimum bonding rectangle frame; and accurate registration from the foreground (FG) to the background (BG), and face region data synthesis can be accomplished. With the fully-automatic face seamless synthesis-based video synthesis method of the invention adopted, the face image of a user can be conveniently synthesized into any existing images or videos in the process of video communication, and therefore, a sense of science and technology and interestingness can be added in the video communication, and fully-automatic seamless face synthesis of non-specific people can be realized.

A method is disclosed for determining a minimum bounding polygon for use in a geo-coding system. A first polygon is received defining a geographic region. A minimal number of points is determined corresponding to the first polygon to define a second polygon at least bounding the first polygon.

The invention discloses a three-dimensional space index method aiming at massive laser radar point cloud models. Aiming at characteristics of massive data and high spatial resolution of point cloud models, the method indexes data to a single three-dimensional space point by adopting a multi-level hybrid index strategy; aiming at an integrity characteristic of point cloud models, the method continuously subdivides massive cloud points from a minimum bounding rectangle (MBB) of an overall point cloud model by adopting a cotree index, and three-dimensional points in cotree index nodes are distributed uniformly in space; and aiming at a scattered characteristic and the data post-processing requirement of large-scale point cloud models, the method indexes a single three-dimensional space point by adopting a three-dimensional K-D tree, and the quick inquiry and processing of a single point coordinate and the attribute data of the single point coordinate can be achieved. On the basis of above integrated space index construction, the method adopts a three-dimensional R tree to manage the MBBs of a plurality of point cloud models in three-dimensional scenes, and a multi-level hybrid space index mode is formed finally.

The invention provides a target person hand gesture interaction method based on a monocular video sequence. The target person hand gesture interaction method comprises the following steps: first, acquiring an image in a monocular video frame sequence, using a movement detection algorithm to extract a movement foreground mask, and using a palm classifier to detect the minimum circumscribed rectangle frame of a palm and screen the palm of a target person; extracting a color histogram model from the palm image of the target person, calculating the reverse projection drawing of the palm image of the target person, and summarizing the area model of the palm of the target person; for a tracked target region, using a color model to calculate the reverse projection drawing, and calculating the area of the current frame of a target person hand to judge the static gesture of the target person hand: a fist or the palm; using the fist gesture or the palm gesture to carry out click or move interaction control. The target person hand can be screened under complicated background, and the tracking of any hand gesture and the recognition of any preset trajectory are finished. The method can be applied on an embedded platform with low operation capability and is simple, speedy and stable.

Systems, methods, and computer products that improve the techniques used to search multidimensional databases over techniques of the past. The preferred embodiment of the present invention advantageously improves the technique of determining a grid index that is used to locate a geometric shape in a spatial database. More particularly, the preferred embodiment of the present invention improves the technique of defining the grid cell size in a grid for a given data set, thereby improving the grid indexing process that locates a particular minimum-bounding rectangle and the associated geometric shape.

The invention discloses a method and a system for positioning a target based on multi-visual information. The method comprises the following steps that: a plurality of camera nodes are allocated, wherein a projection plane coordinate system using position coordinate of each camera node as an origin is established on a to-be-positioned plane by the camera nodes; each camera node extracts a target region on an image plane, frames the region where the target is positioned with the minimum bounding rectangle and calculates coordinates of crossing points of the median vertical line of the rectangular frame and the upper edge and the lower edge in the projection plane coordinate system; the camera node transforms two coordinates obtained by calculation into the same coordinates in a world coordinate system by coordinate transform; the camera node establishes a linear equation, packs parameters, resolution and height information of the linear equation according to a predetermined protocol and transmits the packet to a cluster-head node; the cluster-head node establishes a cost function, reduces the cost function to the minimum so as to realize accurate positioning of the target and broadcasts back the target position information obtained by calculation to each camera node.

The invention provides a pedestrian detecting and tracking method based on multi-stage detection. The method comprises the following steps that 1), background frames are extracted and preprocessed; 2), foreground regions are extracted and labeled through a rectangular frame, current frames and the background image frames are used for carrying out difference, foreground information is extracted, binarization processing is carried out on the foreground information, all the communicated foreground regions are labeled through the outer contour, a minimum bounding rectangle is drawn for each contour region, size information of all the rectangles is recorded, a differential image gray value and a threshold value T are compared, parts larger than T are determined as motion object parts, or else the parts are background parts; 3), the external characteristics of pedestrians are utilized for judging target regions preliminarily; 4), statistics is made on the number of the rectangular regions Rn judged to be the similar target regions, a pedestrian detecting algorithm based on the HOG characteristics is adopted for ruling out non-target regions, and then the optical flow method is adopted for tracking the remaining target regions. According to the method, the calculation speed is high, the instantaneity is good, and the practicality is high.

The invention relates to a method for improving accuracy and stability of image mosaic, belonging to the technical field of video image processing. The method of the invention comprises the following steps: extracting and matching SIFT characteristic points of an image to be mosaicked to obtain an initial matching point pair set; eliminating error matching to obtain a uniform maximum inner point set meeting the same homography matrix; normalizing direct linear change to obtain initial estimate of the homography matrix, and carrying out LM iterative optimization on the initial estimate of the homography matrix to obtain the optimum estimate of the homography matrix; mosaicking the images; determining the public area of two images to be mosaicked and obtaining the sub-images of the two images contained in the minimum external rectangle of the public area; carrying out seamless integration; and sticking the integrated image to the public area to obtain the final result of image mosaic. The invention can carry out image mosaic under the condition that a big amount of error matching exists in the initial matching point pair, and the mosaic has high accuracy, short time consumption and good stability.

The invention provides a visual guiding-based robot workpiece grabbing method, and belongs to the field of robot visual recognition and positioning. The method comprises the following steps of (1) establishing templates of target workpieces in advance, collecting images of the target workpieces, and acquiring edge feature images of the templates and edge feature images of the target workpieces; (2) acquiring the deflection angle of each target workpiece relative to the corresponding template by utilizing the minimum enclosing rectangle of the edge feature image of the target workpiece, and establishing a compensation template set by utilizing the deflection angles and the edge feature images of the templates; (3) matching the edge feature images of the target workpieces and the compensation template set, and recognizing the target workpieces and acquiring the center coordinates of the target workpieces under a visual coordinate system; (4) converting the visual coordinate system to a robot user coordinate system; and (5) selecting a reference point, and uniquely identifying the same target workpiece by utilizing the time and the position to complete positioning grabbing. The targetworkpieces can be accurately recognized by utilizing the method.

The invention relates to a vehicle detecting and tracking method. The method is characterized by comprising the following steps of: establishing a Gaussian background model for each frame image in a video; performing differential processing on two adjacent frames with a frame subtraction method to obtain a rough motion region and a rough static region; performing background updating on the obtained static region and not updating the motion region; differentiating a current frame image and an updated background image to obtain an accurate motion region; finding an overlap region between motionregion images of two obtained adjacent frames with a pixel point matching method and comparing the overlap region with a given threshold value; if the overlap region is larger than the given threshold value, judging whether target overlap occurs; if so, calculating the length-width ratio of a first frame motion region in two adjacent frames and detecting and tracking a motion vehicle according tothe ratio; otherwise, judging that the same vehicle moves; and if the overlap region is smaller than the given threshold value, evaluating a minimum external rectangle of a plurality of target framesto correctly detect and track the vehicle.

The invention discloses a regional early warning method based on a limited location. According to the divided geographic location ranges of different danger levels, a plurality of electronic fences used to represent different danger levels are set up, and the electronic fences are polygonal; each electronic fence is established. The outermost minimum rectangle of the electronic fence; take each side of the electronic fence as a diagonal line, and establish the minimum outer rectangle for each edge, according to the smallest outer rectangle as the leaf node, the outermost smallest rectangle of the electronic fence as the root node and the preset R The tree construction rules establish an R tree; obtain the position of the target in real time, and use the ray algorithm based on the R tree index to judge whether the position of the target is located in a certain electronic fence area; according to the judgment that the target is in a certain electronic fence, In this way, the danger warning level of the target position is divided. Notifications are made through Beidou satellite signals, enabling relevant personnel to leave the dangerous area in time.

The invention relates to a workpiece burr detection method based on image processing. A LED luminescent semiconductor is used as a light source to vertically irradiate that surface of the workpiece, aCCD camera is used as an image detecting device to continuously photograph that edge of a workpiece, finally, the image captured by the camera is captured by the computer, and then the image is filtered, segmented, the edge of the image is detected, and the edge is fused and processed by the region growth method, when the gray value reaches the set standard, the image does not need to expand, indicating that the edge is formed; then the spindle is determined to remove the pseudo-glitch, and finally the edge of the glitch is extracted. The guide line is obtained from the smallest circumscribedrectangle. The length of the contour, the angle difference between the contour and the reference line, the average distance, the variance and other positional relations are compared to determine whether the edge line is burr or not. The complexity of the method is not high. The measuring speed is fast. The detection accuracy is high, the requirement for the experimental environment is not high, and the measurement system is relatively simple.

The invention relates to a workpiece positioning and identification method based on image segmentation. The method comprises three stages of pre-processing, workpiece region positioning and segmentation and characteristic extraction and identification, for pre-processing, de-noising for an image for a workpiece on a conveying belt is carried out, gray stretch image enhancement for the image after de-noising is carried out, operation like thresholding is then carried out, the purpose is to highlight a workpiece region of the image, and preparation for positioning the workpiece region is carried out; for workpiece region positioning and segmentation, on the basis of a minimum enclosing rectangle segmentation algorithm, the workpiece region is framed by a minimum enclosing rectangle, and a workpiece region image in the minimum enclosing rectangle is then acquired through cutting and is taken as a characteristic extraction image; for characteristic extraction and identification, an invariant moment of the image and geometric characteristics of the image are extracted and taken as a characteristic set for classifier training, and multiple characteristics of various workpieces are taken as a training sample set to train classifiers. The method is advantaged in that algorithm design is simple and rapid, not only can accurate positioning be guaranteed, but also real-time demands on a pipeline can be further satisfied, and thereby positioning and identification of the workpiece on the conveying belt are realized.

The invention discloses a patch element positioning identification method based on a minimum enclosing rectangle.The method is used for obtaining the center and the deviation angle of an element and comprises the following steps of 1, conducting image segmentation and provincial characteristic extraction on the patch element; 2, dividing the patch element into two categories, namely the element without pins and the element with pins; 3, according to the characteristic of the minimum enclosing rectangle, obtaining central coordinates of the rectangle; 4, according to the geometric center of a target area obtained in step 3, namely the geometric center of the element without the pins, and then according to the length of limited edges of the rectangle, screening the two symmetrical long edges of the rectangle, wherein the mean angle corresponding to the slope of the rectangle is considered as the deviation angle of the element; 5, adopting the same practice, and according to the geometric center of the target area, obtaining the geometric center corresponding to each pin of the element with the pins; 6, according to the obtained central coordinates of the pin position of the element with the pins, obtaining the actual central coordinates of the element; 7, obtaining the deviation angle of the patch element with the pins.By means of the patch element positioning identification method, the center and the deviation angle of the element can be obtained rapidly and precisely.

The invention discloses a tool wear detection method based on a minimum enclosing rectangle, relates to a tool wear detection method, and aims to solve the problems that by the existing method for realizing tool damage detection, an acquired image cannot be identified due to relatively high environmental impact, the wear amount of a tool cannot be accurately obtained, and the maximum service life of the tool cannot be evaluated. The detection method mainly comprises the following steps: 1, acquiring a tool wear image by an image acquisition system, and transmitting the image to a computer; 2, performing image preprocessing on the acquired wear image; 3, calculating the minimum enclosing rectangle of a tool wear region on the preprocessed image by using a minimum enclosing rectangle algorithm, and calculating the width of the minimum enclosing rectangle; and 4, comparing the calculated width of the minimum enclosing rectangle of the tool wear region with the width of the minimum enclosing rectangle of a blade to obtain a ratio, and judging the size of the tool wear amount according to the size of the ratio so as to judge the tool wear degree. The method is used for detecting the tool wear.

The invention provides a station caption detection method based on color and gradient histograms. The station caption detection method includes steps: building a station caption sample library, training a support vector machine (SVM) classifier by extracting histograms of oriented gradients (HOG) characteristics in the library, extracting color characteristics of a to-be-measured station caption, confirming the parameter range and area proportion of at most front three main colors, through color matching algorithm, searching a to-be-measured area in a video frame, the to-be-measured area forming the same area with to-be-measured station caption colors, and obtaining the to-be-measured area where station captions possibly appear, image correcting for the to-be-measured area based on affine transformation and a minimum enclosing rectangle, extracting HOG characteristics in the to-be-measured area, and judging whether the to-be-measured station captions exist through a trained classifier. Strict test proves that the station caption identification method can identify the station captions of a video (including a microphone, a background and the like) in an accurate and approaching real-time mode.

The invention discloses a road extracting method based on shape characteristics of roads of remote sensing images. The road extracting method comprises the following steps: firstly, segmenting partial regions of preprocessed remote sensing images by utilizing the characteristics of consistency of partial gray levels of road surfaces and the large difference of the partial gray levels between a target region and a background; then, combining segmented results with area and the shape characteristics of a Ferret Box minimum external connection rectangle so as to obtain linear and curved road sections, performing regional seed growth on confirmed roads, and connecting large parts of road sections so as to realize the extraction of road information. Compared with the prior art, the road extracting method disclosed by the invention has the effects that not only the linear and curved road sections can be obtained, but also seed points can be automatically extracted, and road nets can be automatically obtained; the extraction of roads cannot be influenced by the rotation of images, the defect that most methods only can extract linear road sections is overcome, and the road extracting method is more intelligent.

The invention relates to a Mask R-CNN-based reinforced concrete crack identification and measurement method, which comprises the following steps of obtaining a to-be-detected picture which is a picture with a concrete crack; searching and positioning a crack region on the to-be-detected picture based on Mask R-CNN, and segmenting a crack target in the to-be-detected picture; carrying out edge detection on the crack target through combination of a Sobel edge filtering operator, a Laplacian filtering operator and a gaussian smoothing filter, and generating a crack mask; and calculating the length and width of the crack and the crack according to the pole coordinates of the generated crack mask and the minimum bounding rectangle of the mask. Compared with other technologies, the method has relatively high efficiency in crack measurement, has more accurate extraction of crack pixels, and realizes crack detection and identification and calculation of crack length, width and area.

The invention discloses a TR element locating and defect detecting method based on vision and relates to a TR element vision locating and defect detecting method based on the vision. The TR element locating and defect detecting method based on the vision solves the problems that in the prior art personal errors exist, the precision is low, the real-time performance is poor, and the calculation result is sensitive to illumination. The TR element locating and defect detecting method based on the vision is achieved through the steps that an area image is binarized, an outer boundary point set is extracted, an effective boundary point set is searched, a minimum enclosing rectangle is searched, the effective boundary point set is classified, affine transformation is conducted on the binary image, the type of the TR element is checked, the effective boundary point set is classified again and numbered, a pin straight line is fitted, a pin foot straight line is fitted, TR element detailed information is determined, and the defect of the pin of the TR element is checked. The method comprises multiple technologies including grey value filtering, four-field rapid contour tracing, the dual axial rotation method searching the minimum enclosing rectangle and other innovative technologies. The TR element locating and defect detecting method based on the vision is mainly applied to element locating and detection fields in a chip mounter vision system.

The invention relates to a detection and positioning method for a PLCC component, which solves a problem that the positioning precision of a component is seriously affected by the accuracy in acquiring pin regions through carrying out rotation correction and segmentation on an image and acquiring the center of each pin region because an algorithm at present is poor in precision and robustness. The detection and positioning method comprises the steps of acquiring a component image; carrying out threshold segmentation, judging whether the number of non-zero pixel points reaches corresponding multiple of the total number of pixels or not; acquiring an adaptive binarization image; extracting all outlines; filtering interference outlines; acquiring a least square ellipse of the pin outlines; acquiring the moment of the pin outlines; dividing the pin outlines into four categories of pin outlines; corresponding the four categories of pin outlines to actual pin groups respectively; calculating an average value of center coordinates of the four pin groups; judging whether the pin outlines in the pin groups at the opposite sides are identical in number or not; acquiring a minimum enclosing rectangle of the pin outlines; and fitting a rectangle according to a mass center of each pin outline. The detection and positioning method provided by the invention is applied to the field of visual detection.

The reliable perceptual data source can be provided for environmental perception of an unmanned vehicle by three-dimensional laser radar. The invention discloses a method for calculating absolute speed of surrounding vehicles in the area of interest of the unmanned vehicle in real time based on the three-dimensional laser radar. The method comprises the steps that the massive space point cloud data of the surrounding environment of the unmanned vehicle are acquired by using the three-dimensional laser radar; a certain layer of point cloud data representing the vehicle characteristics are extracted in a way of being adaptive to the distance and projected to an xoy plane; the moving vehicles in the area of interest of the unmanned vehicle are identified by applying the cluster merging and minimum bounding rectangle method; the relative speed of the surrounding vehicles is calculated by using distance information of the first point projected to the foremost layer and the last layer of the xoy plane in relative motion between the vehicles; and the speed is synthesized with the speed of the unmanned vehicle so as to obtain the absolute speed of the surrounding vehicles. The method is simple and reliable in algorithm and high in timeliness so that the basis can be provided for route planning and tracking and lane changing and other driving strategy of the unmanned vehicle on the road.

The invention discloses a vehicle type identification and traffic flow detection method. The method comprises: S1: a video frame image is read from a traffic monitoring video, a detection area is set, and target foreground information is extracted by using an averaging method and an ostu method; S2, whether vehicle target information exists in a foreground target is determined; and if not, the S1 is carried out again and a next frame is read; S3, shadow removing is carried out on the extracted foreground by means of a color-and-texture-based shadow detection algorithm; S4, for a target block with the shadow removed, a contour is detected by using a canny edge detection method, the contour is detected, and a minimum external rectangle of the contour is extracted, and a vehicle type is determined; and S5, the vehicle is tracked by using a kalman filter, statistics of the frame number needed by passing by the detection area by the vehicle is carried out, the vehicle type is determined further, and statistics of the traffic flow of the corresponding vehicle type is carried out.

The invention discloses a method and device for evaluating a barrier detection result of a driverless vehicle. The method in one embodiment comprises steps of: acquiring an image, sensed by the driverless vehicle, of a barrier and a real image of the barrier, and solving a minimum circumscribed rectangle to obtain the sensed area and the real area of the barrier; computing the coincidence rate of the sensed area and the real area according to the area of the intersected area of the sensed area and the real area and the area of the united area of the sensed area and the real area; computing the distance between the central point of the sensed area and the central point of the real area according to the position of the central point of the sensed area and the position of the central point of the real area; computing the figure similarity of the sensed area and the real area according to the area and the length-width ratio of the sensed area and the real area; and computing the matching degree of the sensed area and the real area on the basis of the coincidence rate, the distance between the central points, and the figure similarity. The method accurately evaluates the barrier detection result.

The invention relates to a document skew detection method and a document skew detection system and belongs to the technical field of document detection. The method comprises the following steps of: firstly, binarizing a document image to obtain a binary document image; secondly, calculating a connected domain in the binary document image, external rectangles of the connected domain and coordinates of a central point of each external rectangle; thirdly, regarding the center of the minimum external rectangle of the connected domain as an input point set for Hough transformation computation, voting in a Hough transformation parameter space, and computing an accumulation matrix A (theta, rho); fourthly, detecting a maximum value point of the parameter space; fifthly, projecting an accumulatedvalue of the maximum value point on an angle value to an angle coordinate axis to form one-dimensional data; and finally, in the one-dimensional data, detecting peak pairs which are maximally accumulated at an interval of 90 DEG, and determining a skew angle corresponding to the maximum peak pair to obtain the skew angle of a document. The invention has the advantages of high adaptability, high accuracy and high speed.

The invention discloses a digital display instrument identification method suitable for a substation inspection robot. The method comprises the steps that a digital area is located; all target areas of a digital display instrument are screened; the minimum circumscribed rectangle of the target areas is extracted; rectangular areas are screened; the remaining rectangular areas are all taken out asdigital areas to be identified; and finally, character identification is carried out after preprocessing. According to the invention, an image collected by the indoor small inspection robot can be quickly processed; the indications of various digital instruments are converted into numbers, and the numbers are transmitted to a background server in real time through the network function of the inspection robot; and digital display instrumentation in a control room of a substation can be remotely monitored.

The invention relates to a method for identifying abnormal human behaviors in power production based on a block model and belongs to the technical field of power safety production control methods. The method includes motion prospect extraction based on time domain and space domain information; elimination of potential shadows; object identification based on dimension invariant features; and abnormal human behavior identification in the power production based on a block. An enclosing rectangular density J, the rectangular density for short, refers to the proportion of a human object to a minimum enclosing rectangle, when a human body stands normally, the J is larger; and when the human body performs substantial abnormal behaviors, the J is smaller. If the J declines suddenly for a period, the human body is performing abnormal behaviors. According to the method, features are extracted through specific behaviors to identify human body specific behaviors, and accordingly, abnormal behaviors are discovered, violation of regulations is restrained, accidents are prevented, and the method has positive and great significance in the power production under the control of modern computers.