71 results about "Contour segment" patented technology

A method for segmenting a digitized ultrasound image includes providing a digitized in-phase / quadrature ultrasound image comprising a plurality of intensities defined on an N-dimensional grid, decorrelating the ultrasound image wherein spatial correlations are substantially reduced in the intensity data, modeling the decorrelated image intensities with a statistical distribution, propagating, an active contour in the image where the contour segments the image, where the contour is propagated based on the statistical distributions of intensity data inside and outside the active contour.

The invention relates to a method for extracting a contour and a corner of a building from ground LiDAR data. At first, a hierarchical grid density method is adopted to extract the contour of the building from the ground LiDAR data; then a contour extension density method is adopted to restore the extracted contour of the building to obtain the complete contour of the building; and when a corner needs to be extracted, the complete contour of the building is projected into an XY plane with a three-dimensional coordinate system to seek a two-dimensional intersection point, and if the elevation difference of contours of intersection points of any two lines is less than 1m, two contours can be judged to be intersected in the actual three-dimensional space, the intersection point of the two contours is a ground corner, and the average of the elevations of the two contours can be used as the elevation of the ground corner. By adopting the grid density method, the method for theoretical estimation and determination of the grid density threshold and the contour density extension method, the accurate contour segment of the building and the precise ground corner can be extracted from the ground LiDAR data. Moreover, automated extraction can be realized, and the efficiency of data processing can be improved greatly.

The invention discloses a method and a device for measuring the section contour of a sealing strip of a vehicle in the technical field of automatic measurement. The device comprises an image acquiring system, an image preprocessing module, an image registering module and an error detecting module, wherein the image acquiring system is connected with the image preprocessing module for transmitting a section image of the sealing strip; the image preprocessing module is connected with the image registering module for transmitting a section contour chain code; and the image registering module is connected with the error detecting module for transmitting registered contour information. In the device and the method, a sectional slice image of an adhesive tape is acquired by adopting an industrial camera, the section contour of the sealed strip is acquired by processing the image, and the acquired contour is matched with a vehicle standard CAD image contour through data processing so that a specific error value at a specified contour segment of the sealed strip of the vehicle is accurately given; and therefore, rapid non-contact measurement for the section contour of the sealing strip of the vehicle is realized. The method has the advantages of rapidness and accuracy.

A method of determining a contour segment for an object in an image captured by a camera is disclosed. A plurality of corner points located on a part of an object in the image is determined. Pairs of corner points are selected from the determined corner points. A path for at least one of the pairs of corner points is determined, the path connecting the corner points of the at least one pair of corner points along the boundary of the object. The contour segment is determined for the object using the determined path.

A method and device for improving coding efficiency in audio coding. From the pitch values of a pitch contour of an audio signal, a plurality of simplified pitch contour segments are generated to approximate the pitch contour, based on one or more pre-selected criteria. The contour segments can be linear or non-linear with each contour segment represented by a first end point and a second end point. If the contour segments are linear, then only the information regarding the end points, instead of the pitch values, are provided to a decoder for reconstructing the audio signal. The contour segment can have a fixed maximum length or a variable length, but the deviation between a contour segment and the pitch values in that segment is limited by a maximum value.

The invention relates to a target recognition method based on the spatial relationship of contour segments, which comprises the following steps: (1) establishing a database of multi-class target images; (2) extracting the peripheral contour of the target and generating a contour point set; (3) describing the shapes of the two contours according to the contextual shape features of the contour pointset, and obtaining the rough matching results of the targets according to the similarity measurement results of the two contours; (4) constructing the spatial relationship between the images in the library and the occluded images to be recognized according to the skeleton of the whole image and the centroid of the outline of the discrete image; (5) establishing the constraint standard of the characteristic parameters of the spatial relationship, and measure the similarity according to the constraint standard; in the case of complex occlusion, more feature information is provided for recognition in the process of target recognition. When the target is occluded, the target is often divided into several parts, and the outer contour no longer has integrity. In this case, considering the spatial relationship between different contour segments, the recognition rate of occluded target is increased.

A method and device for use in conjunction with an encoder for encoding an audio signal into a plurality of parameters. Based on the behavior of the parameters, such as pitch, voicing, energy and spectral amplitude information of the audio signal, the audio signal can be segmented, so that the parameter update rate can be optimized. The parameters of the segmented audio signal are recorded in a storage medium or transmitted to a decoder so as to allow the decoder to reconstruct the audio signal based on the parameters indicative of the segment audio signals. For example, based on the pitch characteristic, the pitch contour can be approximated by a plurality of contour segments. An adaptive downsampling method is used to update the parameters based on the contour segments so as to reduce the update rate. At the decoder, the parameters are updated at the original rate.

The invention relates to a real-time pose tracking method based on a target three-dimensional model. According to the method, based on a three-dimensional model of a target, contour features are utilized to establish a contour component model, and a contour is divided into a plurality of local contour sections according to the local contour recognition degree; For each contour segment, two dimensional-three dimensional correspondence is established in a gradient domain based on a phase matching criterion; a wrong matching pair is established by utilizing a geometrical relationship among all parts of the rigid body target; based on the established two dimensional-three dimensional matching pair, a pose parameter is solved through an RPNP algorithm, the whole process is iterated until convergence, and target pose tracking in the sequence image is realized. The algorithm is simple and clear in step and easy to apply, and drift-free tracking in the whole process can be achieved due to introduction of the three-dimensional model of the target.

A method is provided for determining shape parameters of elongated products that are moved along the longitudinal direction thereof in rolling lines, in particular for determining the roundness of round profiles, wherein at least three shadow angles are generated and measured in a known method per se using a measurement device comprising at least two laser scanners, each of which comprises a light-sensitive sensor and a laser, said angles sitting against the elongated product to be measured and surrounding the elongated product, said shadow angles forming a polygon, wherein the corresponding tangents are calculated from said shadow angles. A contour is determined from the polygon. Contour segments are established on said contour. The desired shape parameters can be calculated from this data.

The invention discloses an angular point extraction method based on an image contour. The method comprises steps that, after image contour extraction, a k-cosine-curvature method is utilized to extract significant angular points from contour points of an image contour, and the significant angular points are points having curvatures greater than a preset curvature; a fitting algorithm is utilized to generate contour curve description data corresponding to contour points between each two significant angular points; a difference between the contour curve description data and the standard data is greater than a preset threshold, according to preset rules, weak angular points are extracted from the contour points, and the weak angular points are points having curvatures smaller than a preset curvature. The invention further discloses an angular point extraction device based on the image contour. Compared with the prior art, the angular points on the image contour can be more comprehensively and accurately extracted, the acquired contour segment is guaranteed to be more accurate, and thereby precision of detection on PCB can be improved.

A molded container and closure latch mechanism include a top portion and bottom portion which are connected by a hinge which biases the top away from the bottom unless the latch mechanism is engaged. The latch mechanism is pivotally connected to the top. It engages a molded contoured segment on the bottom to secure the container in a closed position. Anomalies on the top surface of the latch mechanism provide a convenience to the user in locating pressure points for opening and closing the container. A separator can be used internal to the container to create two separate compartments. In one adaptation the interior surface can include raised protrusions which permit contents such as a soap bar to be raised off from the surface. Other modifications too the interior can be effected to accommodate a wide variety of products. The containers can be provided in a grouping with relative dimensions suitable to store a wide variety of personal effects.

A compressor blade for an axially permeated compressor, preferably of a stationary gas turbine is provided. The camber line of the blade tip side profile of the blade of the compressor blade includes at least two inflection points for reducing radial gap losses. By means of two inflection points, there is a concavely designed suction side contour segment in a segment from 35% to 50% for the suction side contour, and a convexly implemented pressure side contour segment for the pressure side contour. It is possible by means of the geometry to generate low-loss gap vortices, in order to increase the overall efficiency of an axial compressor including the compressor blades.

The present invention relates to a contour chord angle feature based identification method for a blocked target. The method comprises: establishing a template library of local features of a plurality of target images; extracting a contour feature of a target edge; constructing a chord angle feature descriptor of each contour point; describing a blocked contour by using a self-containing attribute of the chord angle feature descriptor, to obtain a chord angle feature description matrix of contour segments; calculating distances between the chord angle feature descriptors of target image contour points and the chord angle feature descriptors of the contour points of the local feature in the template library by using an L1 measurement method, to obtain a matching cost matrix; and calculating a similarity of the matching cost matrix by using an integral graph algorithm, so as to identify a partially blocked object. According to the present invention, a contour space position feature of a target shape can be extracted, and blocked targets can be identified, and scale invariance, rotational invariance and translation invariance are achieved, thereby increasing the accuracy and robustness of target identification and shape search.

A method for segmenting a digitized ultrasound image includes providing a digitized in-phase / quadrature ultrasound image comprising a plurality of intensities defined on an N-dimensional grid, decorrelating the ultrasound image wherein spatial correlations are substantially reduced in the intensity data, modeling the decorrelated image intensities with a statistical distribution, propagating, an active contour in the image where the contour segments the image, where the contour is propagated based on the statistical distributions of intensity data inside and outside the active contour.

To make it possible to highly accurately specify a contour even with simple operation and further improve accuracy of a defect inspection. A plurality of edge detection regions are set on an image for inspection. A contour segment is formed in each of the edge detection regions. Connection processing for connecting an end portion of one contour segment and an end portion of another contour segment is repeatedly executed to form a closed region. A defect inspection of an inspection target object is executed with the closed region set as an inspection target region.

The invention provides an inscription restoration method based on the contour feature description of a Chinese character image. The method is applied in the fields of computer virtual reality technology, machine vision, image processing and inscription restoration, wherein the information is limited in a homologous inscription or the calligraphy works of a single writer. During the pre-treatment process, after the inscription is divided into single Chinese characters, the component decomposition and the stroke decomposition are conducted on each extracted single Chinese character. The acquired components and the acquired strokes of Chinese characters together form a component-stroke template set. During the restoration process of damaged Chinese characters, firstly, the structural information and the contour information of the credible component / stroke part of the damaged Chinese characters are extracted. Based on the partial correspondence relationship of the structure matching and contour segments, a template that is highest in similarity is found out of the component-stroke template set to be adopted as a signal source for restoring the damaged part of the damaged Chinese characters. Compared with other image restoration methods, the structural information and the contour detail information of the damaged part of Chinese characters can be restored on the premise that the original style of the inscription is well maintained.

Embodiments of the invention disclose a contour etching method and device. In the method, a contour mask is computed according to the dimension parameters of contour segments, a contour mask algorithm and an aperture radius, wherein the contour mask has the same compensation etching amount at each contour segment, in this case, even if the etching amount obtained at a corner is identical to the etching amount obtained by other parts of the contour, so that if the corner in a to-be-etched pattern is a round fillet, the corner is still the round fillet after etching and cannot become a sharp corner. Furthermore, the method carries out pattern Boolean operation on each contour segment and the contour mask and combines the contour segments included in an overlapping region in the to-be-etched pattern subjected to etching compensation, so that the extra contour segments can be eliminated. Through the contour etching method disclosed by the embodiments of the invention, an etching result is the same as an excepted etching result, so that a problem that the etching result is different from the excepted etching result in the prior art is solved.

A hydrodynamic plain bearing having a stator and a rotor rotatable with respect to the stator, a rotor bearing surface being located opposite a counter-surface of the stator in order to generate hydrodynamic pressure. The rotor bearing surface and / or the counter-surface constitutes in a section view, in the context of a section along and through the rotation axis, a continuous bearing contour that is constituted from at least two contour segments. The contour segments are suitable for generating hydrodynamic load capacity in a radial and axial direction. The contour segments are led into one another, by at least one transition segment, in such a way that hydrodynamic load capacity is generatable via the contour segments and the transition segment. The plain bearing is embodied as a multiple-surface plain bearing having two or more lubrication wedges in the region of the contour segments and of the transition segment.

A glow plug (1) including a heater (2), a metallic shell (4) assuming the form of a tube having an axial bore, a center shaft (3) and a contact member (7). The contact member (7) is configured such that a contour (70) of a cross section (75) includes a second contour segment (71) in the form of a straight line, a first contour segment (72) in the form of a curve swelling radially, and third contour segments (73) in the form of curves connecting the second contour segment (71) and the first contour segment (72).

The invention discloses an image processing method and apparatus, terminal equipment and a storage medium. The image processing method includes the steps: comparing the original face contour of a target object with a preset model face contour to obtain at least one unmatched contour segment between the original face contour and the preset model face contour; and for each unmatched contour segment,mapping the texture, corresponding to the unmatched contour segment, on the original face contour to the model face contour to obtain a target face contour of the target object. The image processingmethod enables the unmatched face part not to appear in the image after face changing, thus providing a more real display effect for a user and improving the face changing experience of the user.

The invention relates to a hydrodynamic plain bearing having a stator and a rotor rotatable with respect to the stator, a rotor bearing surface being located opposite a counter-surface of the stator in order to generate hydrodynamic pressure. In order to achieve improved utilization properties, provision is made according to the present invention that the rotor bearing surface and / or the counter-surface constitutes in a section view, in the context of a section along and through the rotation axis, a continuous bearing contour that is constituted from at least two contour segments; that the contour segments are suitable for generating hydrodynamic load capacity in a radial and axial direction; that the contour segments are led into one another, by means of at least one transition segment, in such a way that hydrodynamic load capacity is generatable via the contour segments and the transition segment; and that the plain bearing is embodied as a multiple-surface plain bearing having two or more lubrication wedges in the region of the contour segments and of the transition segment).

The invention discloses a fuzzy boundary image automatic segmentation method based on an active contour and deep learning. The method comprises the following steps: firstly, segmenting a fuzzy boundary image by using a deep convolutional neural network model to obtain an initial segmentation result; then, using an image internal region contour segmented by the deep convolutional neural network model as an initialization contour and contour constraint of an active contour model; the active contour model driving the contour to move towards the edge of the target through the image characteristicsof the area around each contour point, and obtaining an accurate segmentation line between the target area and other background areas. According to the method, the active contour model is introducedon the basis of the deep convolutional neural network model to further refine the segmentation result of the blurred boundary image, the capability of segmenting the blurred boundary in the image is achieved, and the segmentation accuracy of the blurred boundary image is further improved.

The invention provides a vectorization method and device for a word pattern. The method comprises the steps of extracting the contour of a to-be-vectorized word pattern; determining a straight line ofthe to-be-vectorized word pattern, a smooth endpoint of a curve of the to-be-vectorized word pattern and a non-smooth endpoint of the curve of the to-be-vectorized word pattern from the outline of the to-be-vectorized word pattern; segmenting the contour of the to-be-vectorized word pattern according to the smooth endpoint of the curve and the non-smooth endpoint of the curve to obtain at least one contour segment; vectorizing a curve contour section in the at least one contour section according to a vector curve library; and determining vectorization data of the word pattern according to thevectorized curve contour section and the straight line contour section in the at least one contour section. The embarrassing situation that the image generation technology is difficult to be used forfine font library development is effectively handled, the conversion effect from an image to the vector data is greatly enhanced, and the working efficiency of font library development and manufacturing is improved.

The disclosure provides an image processing apparatus, an image processing method, and image processing equipment. The image processing apparatus comprises a first cluster unit and a second cluster unit. For each predetermined point at a contour, the first cluster unit clusters a candidate straight line that is obtained based on the contour and passes by the point into one or more clusters based on the angle of the candidate straight line and calculates an average value of the angle of the candidate straight line in each of the one or more clusters respectively so as to obtain an angle or angles of one or more selected straight lines for the point. And the second cluster unit clusters the predetermined points at the contour according to the angles of the selected straight lines of the predetermined points and the positions of the points and uses points in each obtained cluster in clusters as a contour segment extracted from the contour to obtain contour features of a to-be-processed image.

A method for vibration avoidance in automated machinery produces actuator space-time contours that meet design objectives of the machinery while suppressing energy content at frequencies in the space-time contour, by concatenating multiple space-time contour segments together in such a way as to be mostly free of energy at the frequencies of interest while meeting other specified design goals. The segments used to construct these frequency-optimized-contours are a series of concatenated polynomial segments, the independent variable t being time. These segments can define the variable to be controlled (e.g. speed or distance) versus time, or define one of the controlled variable's time-derivatives (e.g., the slope of the speed vs. time, etc.). When these frequency-optimized-contours are fed as a command to a machine controller through an actuator or actuators, the energy at the frequencies of interest is low enough to avoid deleterious vibration from occurring while still meeting the machine performance objectives.

The invention relates to a method of coding segmented pictures, or partitions, divided into homogeneous regions. Said method, called intra-mode coding process, comprises, for each successive partition, the steps of translating the picture of the labels associated to the regions into a description in terms of a contour element chain in which the elements are defined by means of their movements through successive basic cells, tracking inside each successive cell each contour from its initial contour point, previously extracted, to its end by storing chain symbols corresponding both to input, internal and output contour elements of said cell and to priorities between possible multiple outputs elements, and repeating these steps up to the end of each successive contour segment of the concerned partition. The information corresponding in each cell to the initial point of each contour segment and to the associated chain of movements between that initial point and the initial one of the following cell is finally coded.

The invention discloses a target detection method and device based on computer vision in a complex environment, and the method comprises the steps: collecting an RGB image of a foreground region, carrying out the preprocessing of the RGB image of the foreground region, and obtaining a foreground target region segmentation binary image; analyzing the foreground target area segmentation binary image, and extracting various morphological features of the target area; analyzing various morphological characteristics of the target area, and dividing the target area into a shielded isolated target area and an overlapped target area; carrying out contour segmentation on the shielded isolated target area and the overlapped target area, and extracting effective contour segments; performing circle fitting on the target shape in the effective contour fragment by adopting a circle fitting method, performing comprehensive analysis on a fitted circle, and positioning a potential target area; eliminating interference, and identifying and obtaining a specific target of the potential target area; according to the embodiment of the invention, the target instance detection accuracy of a natural complex environment can be improved.