275 results about "Distance transform" patented technology

The present invention discloses a road boundary detection method based on a three-dimensional laser radar. In the process of intelligent vehicle driving, point cloud data collected by a vehicle-mounted three-dimensional laser radar is subjected to rasterizing processing to generate a binary raster graphic. The binary raster graphic is subjected to a distance conversion operation to obtain a distance grey-scale map, a filing distance is smaller than the narrow space between obstacle points of certain thresholds, the overall contour of the obstacle points is not changed, and an obstacle area contour map is obtained. A region growing method is used, with the position of an intelligent vehicle as a start point, the region growing is carried out forward, the passable area contour map of a road is obtained, and combined with the original binary raster graphic, a road area contour map is obtained. The contours of two sides of the road area contour map are extracted, the second function fitting is carried out, and a road boundary is obtained. The method is applicable to an urban road, a rural road and other roads, the influence of obstacles on a detection effect is small, the time complexity is low, the real-time processing is achieved, day and night work is achieved, and the algorithm robustness is good.

A system for automatic counting of non-overlapping objects irrespective of shape, size, and color is provided by imaging and computer subsystems. Objects to be counted are placed on a transparent surface disposed on a diffusing surface uniformly irradiated by electromagnetic radiation sources. Low intensity object shadows and high intensity object background regions are digitally imaged. The digital image is converted by a computing unit to a binary image and subjected to the Distance Transform to determine a count of the objects. Object identification verification is provided by comparing identification information obtained from a bar code associated with a supply container of the objects and identification information obtained from a digitally imaged written request.

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 provides a TV station logo training method and an identification method. The TV station logo training method comprises the following steps of: (1) determining the external rectangle of a station logo in a training video according to a frame difference method; (2) carrying out edge detection on the external rectangle of the station logo to obtain edge points of the station logo; and (3) calculating distance transformation matrix Df of the station logo according to the edge points of the station log. According to characteristics obtained by the TV station logo training method, the position of the station logo in the video is determined only by the single-frame video information of the video to be detected not by continuous multiframe video information in the identification process; moreover, under the conditions that the shape and the size of the station logo have subtle changes, the station logo still can be successfully identified.

The invention provides a three-dimensional framework fast extraction method based on branch feathers, which comprises the following steps: firstly, automatically extracting root points and tip end points of a tree type voxel model; then, carrying out seed point distance conversion on the root points and the tip end points of the voxel model; automatically judging the branching feathers and optimizing cutting surfaces according to the growth strategy of regions from the root points or the tip end points; decomposing an object into meaningful components with reasonable delimitation between components; and finally, extracting voxel component frameworks and connecting the voxel component frameworks into a structural framework of the object. The framework fast extraction method based on branch feathers is fast and effectively, and the structural integral frameworks maintain topological structures of the original voxel model, and can not generate fracture and redundant complicated branches. The actual plant model construction is carried out on the basis of the framework, the actual scanning data can be processed, and the invention has the anti-noise capability and has high reconstruction accuracy. The test on a plurality of data sets proves that the invention is applicable to bodies with annular structures and can process surface voxel models and solid voxel models.

The present invention provides a tactile sense presentation device capable of providing, during an operation for rotating an operation object image of a three-dimensional model that is the operation object, operation feeling feedback to a user by presenting a tactile sense relative to the state in which the operation object image is being rotated. The present invention is provided with: a determination part (105) for calculating the distance over which a touch panel (101) was traced as the tracing distance; a display control part (106) for converting the tracing distance to an angle of rotation of an operation object image (3), rotating the operation object image (3), and displaying the image on a display part (103); and a vibration control part (107) for driving a vibration part (102) with a drive waveform of a predetermined amplitude and frequency when starting to rotate the operation object image (3), reducing the amplitude of the drive waveform in accordance with an increase in the tracing distance, and controlling the vibration part (102) so that the amplitude of the drive waveform becomes 0 at a predetermined time when stopping the rotation of the operation object image (3); thereby providing feedback on the reduction of a feeling of resistance at the time of the rotation operation of the operation object image (3).

The invention discloses a tracking and recording method for a single moving target track by adopting a computer program, which aims to overcome the problem that the tracking and recording of a moving target track occupies large storage space. The method adopts the steps of installing a hardware system, extracting a target contour, making template matching and track recording to the target contour. Extracting a target contour is to adopt a tth frame image, a (t-1)th frame image and a (t+1)th frame image of a target video; the steps such as three-frame differencing operation, 'AND' operation, median value filtering and extracting an actual contour and so on, are made. Making template matching and track recording to the target contour adopts to find the centroid position of a target and store the centroid position; the stored information of the centroid position is made a distance transformation and is matched with Hausdorff distance; the actual shape of the target is stored; then the (t+1)th frame image is extracted, the steps such as matching and storage and so on, are made according to the flow of extracting the target contour and the method of making template matching and track recording to the target contour; the steps are circularly made.

The invention discloses a method for detecting and tracking a faint target of a high frequency ground wave radar with a non-linear dynamics characteristic of a wave echo. The method comprises the following steps: recording intermediate frequency data in an echo signal in real time; canceling impact interference and the first-order data of an echo; establishing a chaotic dynamics forecasting model of the wave echo; and executing detection and tracking of the faint target, wherein the steps of canceling are as follows: implementing distance conversion and speed conversion to the intermediate frequency data; eliminating impact interference on a speed spectral domain through a spline wavelet filter, and eliminating a strong sea clutter through a track matrix wave of a reconstructing attractor. In addition, the invention discloses an apparatus for detecting and tracking a faint target of a high frequency ground wave radar with a non-linear dynamics characteristic of a wave echo.

The invention provides a shape sensing living example segmenting method based on an object mask network. The method mainly includes shape sensing and segmenting prediction and learning living example segmenting, the process includes the steps that intensive multi-valued mapping codes are used for modeling the shape of an object, for the minimum distance from each pixel to the boundary of the object in a box, and the multi-valued map is converted into binary system masks through inverse distance conversion to segment the object. The suggestion of an initial bounding box is generated through an area network; characteristic deformation is carried out on each execution area-of-interest, and the result is transmitted to the object mask network to generate a result. The object mask is integrated into a multi-level network cascade to construct a shape sensing living example segmenting network and a multi-level shape sensing living example segmenting network, and the networks are trained in an end-to-end mode. The shape sensing living example segmenting method is meticulous in segmentation, high in precision, small in error and beneficial for completing and expanding existing image segmenting theories and methods and provides a practical tool for image analysis and understanding and other applications.

A method and system are disclosed for automatically generating embroidery designs from a scanned image. An embroidery data generating mechanism generates accurate embroidery designs. The embroidery data generating mechanism first reads an image data file, which contains bitmapping information generated from a software scanning tool, the information being related to an embroidery pattern that has been scanned. The scanned pattern is broken up into pixels, each pixel in the scanned image having a bitmap associated with the color of the pattern. Each unique color in the scanned pattern has its own unique bitmap. The embroidery generating mechanism also includes a segmentation mechanism and a chain-encoding mechanism which perform operations to enhance the quality of the bitmapped information and to separate regions of the scanned image into objects. A distance transform evaluation mechanism classifies each object as being either a thick object or a thin, predominantly regular object. Additional mechanisms further interpret the objects into entities such as regular and singular regions and compute optimum sewing paths for embroidery data generation.

The invention belongs to the technical field of ore granularity detection and analysis in mine development, and particularly relates to an ore image granularity detection algorithm based on an image processing technology. The algorithm is characterized by comprising the following steps: (1) completing acquisition of an ore image by using an industrial camera; (2) preprocessing the collected ore image, and sequentially performing image graying, median filtering denoising and binarization processing; (3) performing distance transformation and morphological reconstruction on the obtained binarized image by applying a chain code technology; (4) adopting an ore image segmentation algorithm combining Canny operator edge detection and a watershed algorithm based on region growth; and (5) analyzing and calculating the ore granularity by utilizing the obtained ore parameters and the granularity model. According to the invention, high-precision and high-accuracy granularity detection is obtainedthrough accurate ore image segmentation, the failure rate of the crusher is reduced, and the ore yield is increased.

A method and system are disclosed for automatically generating embroidery designs from a scanned image. An embroidery data generating mechanism generates accurate embroidery designs. The embroidery data generating mechanism first reads an image data file, which contains bitmapping information generated from a software scanning tool, the information being related to an embroidery pattern that has been scanned. The scanned pattern is broken up into pixels, each pixel in the scanned image having a bitmap associated with the color of the pattern. Each unique color in the scanned pattern has its own unique bitmap. The embroidery generating mechanism also includes a segmentation mechanism and a chain-encoding mechanism which perform operations to enhance the quality of the bitmapped information and to separate regions of the scanned image into objects. A distance transform evaluation mechanism classifies each object as being either a thick object or a thin, predominantly regular object. Additional mechanisms further interpret the objects into entities such as regular and singular regions and compute optimum sewing paths for embroidery data generation.

A method and system are disclosed for automatically generating embroidery designs from a scanned image. An embroidery data generating mechanism generates accurate embroidery designs. The embroidery data generating mechanism first reads an image data file, which contains bitmapping information generated from a software scanning tool, the information being related to an embroidery pattern that has been scanned. The scanned pattern is broken up into pixels, each pixel in the scanned image having a bitmap associated with the color of the pattern. Each unique color in the scanned pattern has its own unique bitmap. The embroidery generating mechanism also includes a segmentation mechanism and a chain-encoding mechanism which perform operations to enhance the quality of the bitmapped information and to separate regions of the scanned image into objects. A distance transform evaluation mechanism classifies each object as being either a thick object or a thin, predominantly regular object. Additional mechanisms further interpret the objects into entities such as regular and singular regions and compute optimum sewing paths for embroidery data generation.

To provide a moving object detection apparatus which accurately performs region extraction, regardless of the pose or size of a moving object. The moving object detection apparatus includes: an image receiving unit receiving the video sequence; a motion analysis unit calculating movement trajectories based on motions of the image; a segmentation unit performing segmentation so as to divide the movement trajectories into subsets, and setting a part of the movement trajectories as common points shared by the subsets; a distance calculation unit calculating a distance representing a similarity between a pair of movement trajectories, for each of the subsets; a geodesic distance calculation unit transforming the calculated distance into a geodesic distance; an approximate geodesic distance calculation unit calculating an approximate geodesic distance bridging over the subsets, by integrating geodesic distances including the common points; and a region extraction unit performing clustering on the calculated approximate geodesic distance.

The invention provides a method for extracting a region of interest of a palmprint in a non-contact manner in a complex environment, which includes the following steps: collecting a palmprint image; extracting a binary image of the palm foreground; filling the holes of the binary image and removing the small-area regions of the binary image; adjusting the palm angle in the binary image to make thetip of the middle finger on the topmost in the image; determining the search scope of maximum effective inscribed circle by detecting the fingertip position and the valley point position; carrying out range transformation on the binary image after adjustment, traversing the search scope obtained in the previous step, and limiting the proportional relationship between the center and radius of theinscribed circle and the length of the middle finger to get a maximum effective inscribed circle; and rotating the maximum effective inscribed circle to get an image of a region of interest of the palmprint. The method can be used to carry out binaryzation, contour extraction, key point location, translation, rotation correction and palmprint center region-of-interest extraction on a palmprint image collected by a high-pixel mobile phone in a complex environment.

The invention provides an automatic chaetoceros and non-chaetoceros sorting method based on microscopic images. The automatic chaetoceros and the non-chaetoceros sorting method based on the microscopic images includes the steps: (1) extracting binarization images of target cells of the algae from the microscopic images of the algae; (2) setting the binarization image height, namely the line number as three hundred pixels regularly, and zooming the rows according to the original proportion; (3) performing closing operation for the images by utilizing a round structure element with a radius of five pixel width; (4) extracting skeleton from the binarization images by utilizing a distance transforming refinement algorithm; (5) extracting node number and endpoint number: extracting node assembly and endpoint assembly of the skeleton, and then acquiring the node number and the endpoint number; (6) judging whether the skeleton is the chaetoceros or not according to the criterion whether the requirements that the node number is not less than 5 and the endpoint number is not less than 5 are met or not. The automatic chaetoceros and the non-chaetoceros sorting method based on the microscopic images is high in accuracy, clear in development, very obvious in economic benefit and social benefit, lays a base for further algae sorting recognition, improves further recognition ratio for the automatic sorting of the algae, and can provide effective instructions and assistance for various algae monitoring personnel and researchers in the front line.

A fast image region partition method receives a component labeled image and performs a two pass Zone Of Influence (ZOI) creation method to create a Zone Of Influence (ZOI) image. The two pass ZOI creation method performs a first pass scan to create a first pass intermediate distance image and a shortest distance component label image. It then performs a second pass scan using the first pass intermediate distance image and the shortest distance component label image to create a background distance transform image and a updated shortest distance component label image. An adaptive image region partition method receives a component labeled image and performs an adaptive two pass ZOI creation method to create an adaptive ZOI image. The distance lengths of the two pass adaptive ZOI creation method depend on their associated component labels. An adaptive cell segmentation method receives a nuclei mask image and a cell mask image. It performs adaptive nuclei region partition using the nuclei mask image to create adaptive nuclei mask ZOI. An adaptive cell region separation method uses the cell masks and the adaptive nuclei mask ZOI to generate adaptive cell separated regions. An adaptive dilation method receives an image and performs an adaptive background distance transform to create an adaptive background distance transform image. A threshold is applied to the adaptive background distance transform image to generate adaptive dilation image output. An adaptive erosion method receives an image and performs an adaptive foreground distance transform to create an adaptive foreground distance transform image. A threshold is applied to the adaptive foreground distance transform image to generate adaptive erosion image output.

The invention discloses a dendriform solid decomposition and graded framework extraction method, which comprises the following steps: a maximum central point diagram is constructed through integral-type boundary distance conversion and integral-type single seed point distance conversion of a solid; a dendriform clustering scheme is generated, the clustering scheme is combined with the maximum central point diagram to extract the central representative point of each clustering, and a classification framework is constructed for classification; branch points are taken as seed points for integral type distance conversion, thus constructing the section of each branch; equidistant faces of the sections are constructed through curved surface unidirectional distance conversion, thus acquiring divisional planes and completing decomposition of the solid, namely, the solid is decomposed into a plurality of blocks; finally, a three-dimensional weighted directed graph is constructed through precise Euclidean distance conversion, the cost value of a compact center is calculated, and the minimal spanning tree is extracted; the central frameworks of the blocks and a connecting framework reaching the centers of the divisional planes are acquired, thus finally getting the graded framework. The invention can measure form and structure, and represent shapes accurately according to test specifications of a plurality of data sets.

Disclosed is directed to a moving object detection apparatus and method. The apparatus comprises an image capture module, an image alignment module, a temporal differencing module, a distance transform module, and a background subtraction module. The image capture module derives a plurality of images in a time series. The image alignment module aligns the images if the image capture module is situated on a movable platform. The temporal differencing module performs temporal differencing on the captured images or the aligned images, and generates a difference image. The distance transform module transforms the difference image into a distance map. The background subtraction module applies the distance map to background subtraction technology and compares the results with the current captured image, so as to obtain the information for moving objects.

The invention discloses a method for detecting a picture contour based on the combination of a level set and a watershed, which mainly solves the problem that the prior method generates picture over-segmentation results and cannot obtain an accurate target contour. The method is achieved according to the following steps: (1) detecting the target contour of an input picture by using a level set method to obtain an initial target and a background binary segmentation result; (2) using the detected target contour as an internal control mark of the watershed; (3) performing range conversion and watershed conversion on the internal control mark in turn, and using an obtained watershed line result as an external control mark of the watershed; (4) using the internal control mark and the external control mark to correct a gradient picture of the input picture; and (5) performing the watershed conversion on the corrected gradient picture so as to detect the target contour in the picture. The method avoids the picture over-segmentation, has the advantage of positioning the boundary accurately, and can be applied to segmenting foregrounds and backgrounds and detecting target external contours.

A method for deriving character features in a character recognition system for recognising characters, such as letters and digits, and a character recognition system in which the method is applied. After deriving a character description from a recorded image pattern of a character to be recognised, a unique point Pi of said character description is appended, by means of a distance transform, to each point Ri of a subset R={Ri / i=1, - - - ,N} of preselected reference points in the plane of said image pattern. Feature values of one or more features possessed by the character description in each appended unique point are then determined. If the character description is a contour description, the unique point Pi appended to each reference point Ri is that point where the reference point Ri has the shortest distance D(Ri) to the contour of the character, and the character features selected are the shortest distance D(Ri) and the direction H(Ri) of the contour in the appended point Pi.

The invention discloses a dynamic gesture recognition system and a dynamic gesture recognition method. The dynamic gesture recognition method comprises the following steps of: detecting a motion area so as to obtain a skin color area; obtaining the position and the size of the centre of the palm in a hand-shaped area given by a skin color classifier by utilizing distance transformation; calculating the positions of the fingers and the position of a greatest defect by utilizing a convex hull and an outline of a gesture; forming a feature vector according to hand-shaped characteristics; selecting a plurality of normal human hand samples and a plurality of secondary samples to serve as training samples, learning by utilizing a support vector machine (SVM) classifier, and performing the gesture recognition on a video frame through the learned classifier; and performing hand shape tracking by utilizing an affine transformation-based image block matching method. According to the method, the aim of rapidly and dynamically recognizing the gesture with high precision can be fulfilled.

The pedestrian tracking device comprises: an image receiving unit for receiving, in time series, images continuously in time by an image capturing device; a pedestrian region selecting unit for sampling candidate pedestrian regions from an image received by the image receiving unit and for selecting a certain pedestrian region; a tracking unit provided in time series with the pedestrian region selected by the pedestrian region selecting unit for predicting motion of the pedestrian region and associating it with time direction by use of a skeleton model obtained by modeling a pedestrian, a distance-transformed image obtained from the pedestrian region and a Monte Carlo filter so as to track the pedestrian region; and a pedestrian trajectory display for displaying, in time series, the pedestrian region tracked by the tracking unit.

The invention discloses an image segmentation method combined with semi-supervised learning, and the method comprises the following steps: obtaining a gradient image of a to-be-segmented image, sequentially carrying out the compression, sharpening, binarization processing and distance transformation of the to-be-segmented image, and obtaining a distance topographic map of the to-be-segmented image; extracting one point or point set with the biggest gray value in each communication region of an obtained distance transformation image, and enabling the point or point set to serve as a foreground mark; carrying out the watershed transformation of the obtained distance topographic map, and enabling an obtained watershed ridge line to serve as a background mark; shielding a local minimum value in the gradient image, marking the local minimum value of the gradient image according to the obtained foreground mark and background mark, and obtaining the corrected gradient image; and carrying out the obtaining of multi-angle data, the building of a prediction matrix, the building of a training model and the segmentation of an image through a semi-supervised learning method. The image segmentation method can improve the precision of image segmentation.

The invention relates to a concrete crack detection method based on image distance transformation. The method comprises: step one, a computer reads an original concrete crack image and carries out preprocessing on the image to obtain a smooth image; step two, a gradient value of the smooth image is calculated; step three, a pixel point of a maximum value of the smooth image is marked; step four, crack seed points in the smooth image are marked; step five, the crack seed points are connected; step six, connecting lines of some seed points are cut off; and step seven, crack parameter informationis obtained. According to the invention, the method can be applied to the field of concrete crack detection; and with the image processing technology, the number, length, and width information of thecrack is obtained from the concrete crack image continuously at a high speed. Because of the pixel gradient value symmetric analysis method, the computing load of the crack connection is reduced by using the image distance transform fully. The concrete crack detection method has characteristics of great anti-background interference capability, high detection accuracy, and high detection speed.

The invention discloses an ore particle size image segmentation method combining multi-feature and multi-level. In the segmentation method, bilateral filtering and local self-adaptive thresholding based on an integral image are first carried out for an image. Then, filtering and distance transformation are carried out for a binary image. Finally, after watershed transformation, the image and a binary image are overlaid to obtain a first layer segmentation. After the first layer segmentation, by use of a characteristic that adhesion of two ores leads to the presence of pits, a proposed circular template method is used for detecting all the initially segmented segment lines. If two sides of a segment line are provided with pits, the segment line is retained; and the incorrect segment line is removed otherwise. By use of the brightness and shape feature of the ore image for double-deck segmentation, an ideal result is obtained and therefore higher reliability is provided for subsequent particle size measurements. The ore particle size image segmentation method combining multi-feature and multi-level has the advantages of wide application range, good real-time, high precision, easy installation and low cost.

An adaptive dilation method receives an image and performs an adaptive background distance transform to create an adaptive background distance transform image. A threshold is applied to the adaptive background distance transform image to generate adaptive dilation image output. An adaptive erosion method receives an image and performs an adaptive foreground distance transform to create an adaptive foreground distance transform image. A threshold is applied to the adaptive foreground distance transform image to generate adaptive erosion image output.

The invention relates to a high-definition aerial remote sensing data automatic road extraction method; the method employs an aerial remote sensing image and DSM data of a corresponding researched area for extracting ground and overground areas, constitutes streets and extracts central lines of roads via a series of morphological conversions, including open and close operation, convex set shell, concave set shell, range conversion, watershed segmentation, and the like. The central lines and border lines of roads obtained by the disclosed method are continuous curves. Comparing to the method of the prior art, the algorithms and theories are complete, the road lines are prices, the calculations are quick, and the algorithms are good in adaptability; indicated after experiments that the disclosed method is very strong in robustness with respect to road extraction.