200 results about "Contour matching" patented technology

A method and apparatus for efficiently matching a large collection of user profiles against a large volume of data in a webcasting system. The invention generally includes in one embodiment four steps to parallelize the profiles. First, an initial profile set is partitioned into several subsets also referred to as sub-partitions using various heuristic methods. Second, each sub-partition is mapped onto one or more independent processing units. Each processing unit is not required to have equal processing performance. However, for best performance results, subset data should be mapped in one embodiment where the subset with a highest cost is mapped to a fastest processor, and the next highest cost subset mapped to the next fastest processor. Where appropriate, the invention evaluates the relative subset processing speed of each processor and adjusts future subset mapping based upon these evaluations. For each information item I that needs to be matched with a profile predicate, a third and a fourth step are executed. The third step broadcasts I to all processing units, and a fourth step performs a sequential profile match on I.

A new method has been developed as an attempt to improve speed and robustness of existing ISAR classification methods. The new method produces a set of silhouettes of possible models in a 3D model database. The set of silhouettes of each model views the model from various viewing angles, as the target dimensions will vary as it is viewed from different angles. The silhouettes are stored as a training set. Classification is done by comparing the silhouette of the target with the set of silhouettes in the training set. The silhouettes are calculated prior to the silhouette matching.

A sportsball includes a ball carcass, an inflatable ball body received in a ball cavity of the ball carcass, and a stitchless seam arrangement which includes an elongated adhesive layer having a contour matching with a contour of an opening of the ball carcass, wherein after the ball body is disposed in the ball carcass, edge portions of the opening are adhered on an outer surface of the ball body via the adhesive layer, such that the opening is sealed to close the ball cavity for enclosing the ball body in the ball cavity of the ball carcass in a stitchless seam manner. Therefore, the manufacturing method of the sportsball excludes the traditional final assembling operation of hand stitching to reduce the time-consuming manufacturing procedure of the sportsball while being cost effective.

The invention relates to a building point cloud model and base map aligned method based on an outline, which belongs to the technical field of computer vision. The method comprises the steps of: performing structural analysis on the building point cloud model obtained by three-dimensional reconstruction, automatically detecting the posture of the current model, ultimately realizing normalization of coordinates of the point cloud model, and obtaining a point cloud overlooking outline drawing of a current building on the basis; performing outline analysis on a remote sensing image of an area in which a reconstructed building is positioned, and automatically detecting to obtain a base map outline; estimating structure turning points of the current building according to the outline of the reconstructed building, and then realizing space alignment of the point cloud model and a satellite base map by virtue of outline matching information, so as to obtain a mapping matrix from the point cloud model to the satellite base map and automatically realize the placement of the building point cloud model on the satellite base map. Compared with the prior art, the method has the advantages that the point cloud model and the base map can be accurately and automatically aligned, manual workload required by alignment is effectively reduced, and the alignment cost is reduced.

The invention discloses a target identification method based on contour features. The method comprises steps of establishing a feature bank of object template contours; extracting a complete contour of an object template; extracting feature points and central points from the contour; establishing a distance matrix to describe the contour by using feature points and central points; conducting calculation of the distance matrix by aiming to all pixels on the contour; conducting target identification for an image to be detected; extracting an edge of the image to be detected; extracting feature points on the edge; calculating feature description composed of feature points; matching the feature description of the image to be detected with features in the feature bank of object template contours; estimating central points of the contour of the image to be detected; and estimating the contour of the image to be detected. Compared with the prior art, the method has the advantages that the size problem in the contour matching is solved, and the size in the contour matching is not changed. The method can be applied to target identification of images effectively.

The invention discloses a safety cap wearing condition detection method based on video stream data; the method comprises the following steps: obtaining video stream data; extracting moving objects; matching body objects; locating heads; matching safety cap colors; matching safety cap contours; matching safety cap wearing features. The method can provide multi-detection means, can combine the moving object detection, body object matching, head locating, safety cap color and contour matching and safety cap wearing feature matching technologies, thus greatly improving the safety cap and safety cap correct wearing recognition rate; the method can automatically identify and detect the safety cap wearing conditions of workers in the construction field, thus preventing workers wearing no safety cap or carrying safety caps by hands from entering the construction area, assisting construction area safety monitoring units of all levels to realize construction area intelligent monitoring, and improving the construction area safety monitoring informatization level.

A spine image generating system based on an ultrasonic rubbing technology comprises a collecting unit and a processing unit. Ultrasonic rubbings are generated by the system based on ultrasonic imageswith two-dimensional spine surface structure characteristic outlines, and matched with a digital medical image outline, and thus a personalized spine surface topographic map which is consistent with an intraoperative position of a patient and updated in real time is obtained. A spine surgical navigation positioning system based on the spine image generating system comprises a navigation module andthe spine image generating system based on the ultrasonic rubbing technology. The spine surgical navigation positioning system can obtain the spine surface topographic map which is consistent with the intraoperative position of the patient and updated in real time, and can conduct real-time intraoperative navigation based on the spine surface topographic map. The spine image generating system based on the ultrasonic rubbing technology and the spine surgical navigation positioning system can greatly reduce the difficulty of a spinal operation, can achieve the operation auxiliary purposes of precise and nonradiative guided puncture, real-time navigation and being simple, convenient and reliable, and are particularly beneficial for application and popularization of a spinal minimally invasive surgery technology which is represented by a spine endoscopy to primary health care institutions.

The invention discloses a target recognition method based on an image contour characteristic. The method comprises the steps of preprocessing a template image and a to-be-identified object image for generating a binary image; establishing a characteristic database of an object template contour; extracting a whole contour of an object template binary image, equidistantly acquiring a certain number of characteristic points on the contour, and describing the object contour by means of a context characteristic of the characteristic points; performing target recognition on the to-be-identified object image; extracting the contour edge of the to-be-identified binary image; selecting a certain number of characteristic points; converting the shape direction of the to-be-identified object to the direction of the template; describing the contour of the to-be-identified image after direction changing by means of the context characteristic of the selected points; and determining similarity between the to-be-identified object and the template object through matching cost. Compared with prior art, the target recognition method has advantages of settling a problem of rotational invariance in a contour matching process, realizing invariable rotation in the contour matching process, and realizing effective application in target recognition in the image.

Contour-matching, aspheric lenticules are disclosed for implantation in a subject's cornea to correcting refractive errors. The lenticules include a photoablatable anterior surface and a posterior surface having an aspheric profile that can substantially match the asphericity exhibited by the corneal stromal surface, on which the lenticule is placed. The posterior surface can have a generally concave shape while the anterior surface can have a generally convex shape, though other shapes can also be utilized in some embodiments. In some embodiments, the asphericity of the lenticule's posterior surface can differ from an asphericity exhibited by the corneal stromal surface by less than about 50%, or preferably by less than about 20%.

The invention discloses a geomagnetism-aided navigation method based on match degree, relating to a geomagnetic matching algorithm. The method of the invention calculates the match degree according to a gray correlation coefficient and the weight of a geomagnetic element and measures the similarity degree between the geomagnetic element value corresponding to a position point in a matching region and the geomagnetic element value actually measured by a magnetic sensor, thereby judging a matching point in the matching region and finally carrying out the matching positioning. Compared with the traditional contour matching algorithm, the method of the invention fully utilizes the information of a geomagnetic field vector for carrying out the vector positioning, eliminates the error-matching phenomenon which possibly occurs in the traditional matching algorithm, realizes precise positioning and has good real-time performance.

The invention discloses a digital human serial section image segmentation method based on geometric active contour target tracking, comprising the following steps: 1) inputting a first layer digital human serial section image which includes a target to be segmented; 2) initializing the target contour by intelligent scissors; 3) generating a target contour matching score image; 4) smoothening the target contour matching score image generated in step 3); 5) using a self-adopting geometric active contour model tracking to obtain the target contour of current layer; and 6) storing the target contour segmentation result of current layer, simultaneously taking the result as an initial target contour of next layer and returning to step 3) to continue the target tracking to obtain subsequent target contour. The digital human serial section image segmentation method can accurately and robustly segment the target contour of the digital human serial section image and simultaneously has the advantages of high automation level and processing of topology change of the target contour.

The invention provides a machine vision inspection system and method for vehicle components. The system includes a conveying mechanism including holding platforms for holding a vehicle to be inspectedand causing the holding platforms to move along a production line on the conveying mechanism at a constant speed, wherein each holding platform is provided with a unique identifier; image acquisitionmodules installed at inspection stations on both sides of the conveying mechanism to capture the surface appearance images of respective components of the vehicle to be inspected at multiple angles by a plurality of CCD cameras when it is sensed that the vehicle to be inspected reaches; a preprocessing module for preprocessing the images to generate images conforming to a preset specification according to different components of the vehicle; a positioning module for positioning the components of the vehicle to be inspected in the images by using contour matching or template matching to generating a component image; and a visual inspection module for comparing the component image with its preset image, calculating the similarity between the two, and detecting whether the vehicle componentshave appearance defects according to similarity. The machine vision inspection system and method for vehicle components improve inspection efficiency and inspection accuracy.

The invention discloses a matching navigation method based on local gravity field approximation. The method comprises the following steps that: at first, a flight path indicated by an inertial navigation system in a period of time is acquired as an initial flight path for matching, a gravity abnormal value corresponding to the point of the flight path indicated by the inertial navigation system is acquired, grid data of a local square region are intercepted in a gravity anomaly reference graph through the flight path indicated by the inertial navigation system and a confidence interval thereof, and a function of a gravity anomaly graph of the square region is acquired; and then terrain contour matching algorithm is used for rough matching, difference pretreatment is carried out on a gravity measuring sequence, then rough matching is carried out by using the terrain contour matching algorithm, and matching results are used as an initial flight path for matching algorithm of a related extreme value; and a matching algorithm optimization interval of the related extreme value is acquired based on the rough matching results obtained through terrain contour matching and the confidence interval, an iterative random initial value is generated by an average random number and enters into BFGS for optimization, an optimal matching flight path is calculated based on optimal solution of BFGS optimization, and the original flight path is updated. The method provided by the invention enables available matching precision to be higher through construction of a local gravity field reference graph.

The invention discloses a viewing-angle greatly-variable gait recognition method based on gait three-dimensional contour matching synthesis. The method is characterized by comprising the following steps: detecting a moving body on the basis of a double-mass-center self-adaptive matching for a color and depth image collected by a single depth camera, extracting a gait depth image with background being removed, and repairing the gait depth image on the basis of multi-curve fitting and gauss distribution information fusion; carrying out cloud extraction on gait points; fusing data of all three-dimensional gait surface models within one gait period to generate a three-dimensional fusion gait energy model; rotating two fusion gait models of two training viewing angles to the same viewing angle, completing the surface butt joint of different viewing-angle three-dimensional gait models through the three-dimensional contour matching, and extracting the multi-viewing-angle gait fuzzy contour data; completing the three-dimensional gait classification recognition with the viewing angle being greatly varied through a gait sub-image which is fused with the gait fuzzy contour and an integration classifier. By adopting the method, the problem that the difficulty of viewing-angle greatly-variable gait recognition cannot be solved by the existing gait recognition method can be solved.

The invention provides a cargo pallet detection method and system based on point cloud plane contour matching. The method includes the following steps: S1, original point cloud filtering; S2, point cloud plane segmentation; S3, generating a grid map through projection; S4, contour extraction; S5, contour matching; and S6, acquiring the relative position and posture. The system includes an original point cloud filtering module, a point cloud plane segmentation module, a module for generating a grid map through projection, a contour extraction module, a contour matching module, and a relative position and posture acquisition module. The method and the system are of low cost and high detection accuracy, and are basically not affected by illumination. There is no need for label laying or other operation, and there is no need to transform the storage environment. The method and the system are suitable for pallets of various colors and specifications, and have the advantages of high accuracy, low price, strong robustness, and the like.

The invention provides a virtual sample deep learning-based robot target identification and pose reconstruction method. The method comprises the steps of extracting a region of an operation target in a camera image by adopting a CNN region detector, and preliminarily determining relative positions of the operation target and a robot end camera; estimating an observation angle deviation of a current view angle and an accurate pose solving optimal view angle of the computer end camera by adopting a CNN pose classifier; controlling a robot motion by adopting a multi-observation view angle correction method to enable the end camera to be transferred to the accurate pose solving optimal view angle; and by adopting virtual-real matching of contour features and pose inverse solving at the optimal view angle, realizing accurate calculation of a target pose. According to the method, the problem in massive sample demands of a deep convolutional neural network is solved, and the problems of feature shielding and matching difficulty caused by an excessively large contour matching view angle deviation are solved; and the activeness of robot vision perception and the algorithm flexibility of target pose reconstruction are improved.

The invention relates to a target recognition method of an unmanned aerial vehicle based on minimum circle-cover matching. The target recognition method comprises the following five steps of: step 1, carrying out edge detection and communicated domain calibration to a target area and dividing the target area into a plurality of areas to be matched; step 2, creating a target model shape characteristic information base; step 3, carrying out minimum circle-cover detection to all the targets to be detected in the target area, and simultaneously recording the diameter orientation of the minimum circle-cover; step 4, matching the diameters of a target template and an outline to be matched so that the subsequent step can be implemented within a certain orientation; and step 5, matching the target template with the outline to be matched, carrying out the matching orderly to a plurality of communicated domain targets of the target area, and finally comparing and obtaining a sum-of-squared difference (SSD) measure of a minimum pixel gray difference, wherein the outline matching corresponding to the sum-of-squared difference (SSD) measure is the required result. The target recognition method utilizes the computational geometry technology, the optimization theory, the computer vision technology and other technologies, realizes the multi-target recognition of the unmanned aerial vehicle, greatly improves the speed and accuracy for recognizing the targets and has great practical value and application prospect.

The invention relates to the field of medical technology, and particularly to a method and a device for pupil positioning. The method for pupil positioning comprises the steps of successively sliding a plurality of preset eye templates according to a preset sliding length for matching a video image of a current frame, and obtaining an area video image with highest matching degree to a preset eye template; performing binarization on an area video image according to a preset first algorithm, and obtaining a binarized area video image; extracting the contour of the binarized area video image, dividing the contour into a plurality of fragments, extracting a plurality of reference points from each fragment, performing ellipse fitting on the plurality of selected reference points according a preset second algorithm; and respectively calculating matching degrees between the plurality of ellipses and the contour according to a preset third algorithm, wherein the central coordinate of the ellipse with highest matching degree to the contour is the position coordinate of the pupil. Furthermore the method and the device have advantages of quickly and accurately finding out position of the pupil, and improving diagnosis efficiency and diagnosis precision.

The present invention provides an optical displacement meter which performs a profile search for performing positional adjustment of a profile shape. The optical displacement meter includes: an amplifier for amplifying a reception light signal from a two-dimensional light receiving device; profile computing means capable of computing a profile shape of the object to be measured on the basis of an amplification signal obtained by the amplifier in a point in the first direction by the reflection light of the light emitted from the projector; a display unit capable of displaying the profile shape of the object to be measured computed by the profile computing means; registered-profile designating means for designating a registered profile as a reference of a profile search from profile shapes displayed on the display unit; and profile matching means for performing a profile search to find a match between an input profile shape and the registered profile designated by the registered profile designating means and, on the basis of a result of the profile search, rotating or moving the input profile shape.

The invention discloses a visual inspection algorithm for an outline. The algorithm comprises the following steps that: extracting a workpiece sub pixel edge, carrying out denoising and outline supplementation, carrying out outline matching, and carrying out deviation calculation. By use of the visual inspection high-accuracy algorithm for workpiece outline defects, firstly, the workpiece outlineis extracted, then, the outline matching is carried out on the basis of shape context features, accurate matching is carried out according to an iterative closet point algorithm, and finally, a matching deviation is calculated through a neighbourhood method. According to the comparison of a great quantity of experiments, the visual inspection method for the outline can accurately detect the outline defects of any shape of the workpiece, and detection accuracy can be 0.5 pixel. When the method is applied to industrial detection, the processing and the production of precise firmware can be intelligently detected at high accuracy, and production efficiency is greatly improved.

The invention relates to a multimodal carotid MRI registration method based on physical alignment and contour matching. The method comprises steps that 1), image space physical coordinates are calculated; 2), body pixel spacing conversion image formats are unified; 3), the alignment relationship of multi-modal image layers is determined; 4), inner wall segmentation of multi-modal 2D images of eachsequence is carried out, a sequence of MRI images is sequentially selected, segmentation start and termination layers of the sequence images are determined, the ROI where a carotid is located in thestart layer image is selected, and the segmentation method is utilized to realize continuous automatic segmentation of the entire sequence; and 5), 3D registration based on the inner wall contour is carried out, and the clear inner wall contour segmentation result is utilized to carry out three-dimensional continuous registration. The method is advantaged in that carotid multimodal sequence imagesin various types are effective, alignment registration among pixels is excellently realized, and doctors are facilitated to carry out subsequent diagnosis and treatment determination and patch composition analysis.

The time delay (and therefore the OPD) between object and reference beams in an interferometer is manipulated by changing the spectral properties of the source. The spectral distribution is tuned to produce a modulation peak at a value of OPD equal to the optical distance between the object and reference arms of a Fizeau interferometer, thereby enabling the use of its common-axis configuration to carry out white-light measurements free of coherence noise. Unwanted interferences from other reflections in the optical path are also removed by illuminating the object with appropriate spectral characteristics. OPD scanning is implemented without mechanical means by altering the source spectrum over time so as to shift the peak location by a predetermined scanning step between acquisition frames. Finally, the spectrum is controlled on a pixel-by-pixel basis to create a virtual surface that matches the profile of a particular sample surface.

The invention discloses a multiple-subarea matching method constraint by a space relation. A plurality of subareas are selected in a matching template as sub-templates, and the sub-templates are separately and simultaneously matched with to-be-matched images. Space position relations among the sub-templates are utilized to realize the accurate matching of the images. The method comprises the following steps: the plurality of subareas are selected in the matching template respectively as the sub-templates; the space relations among the sub-templates are determined; the plurality of sub-templates keep the space position relations unchanged to form combined templates; matching is carried out by utilizing the mobile searching performed by the combined templates on the to-be-matched images, and a plurality of similarity values of the combined templates are obtained; the plurality of similarity values are compared, and a position where a maximum similarity value exists is regarded as an optimum matching position to complete the matching. The method of the invention utilizes the mutual space relations among the plurality of sub-templates to reach the requirements for accuracy and precision of matching. The object identifying performance of the method is substantially improved in real-time performance compared with the conventional large-template gray scale or contour matching algorithms.

The invention discloses an online mold monitoring and protecting system and an online mold monitoring and protecting method based on contour matching. The online monitoring and protecting method comprises the following steps: a light source of near-infrared mixed visible light generates near-infrared mixed visible light on a mechanical jig; an image acquisition device acquires an image of the mechanical jig, and sends the image to an image processing device; the image processing device receives image information of the image acquisition device, and a near-infrared fusion visible light image of the mechanical jig is acquired and is matched with the contour of a standard image by adopting an image processing algorithm of contour matching; a control command is generated according to the matching result; a jig control system receives the control command of the image processing device so as to control the movement of the mechanical jig. According to the invention, the information that whether a moving mold and a fixed mold are good or not is acquired rapidly and accurately, and the defects of an existing mold online monitoring and protecting technique are remedied.

A image recognition method based on content comprises steps: take grid division to the image; take the grid nodes as initial position to make region growing and obtain skin color information around all nodes of image; use grid cell zone and the mechanism that all nodes vote each other to determine interesting points and zones of image; based on the interesting points and zones, use the movement of points to extract soma contour; finally, extract contour information and local information inside contour to form eigen vector, recognize the image and decide its nature. The invention overcomes problems of low speed, efficiency and strong dependency of device existed in sensitive image recognition techniques such as, color histogram matching, wavelet transformation contour matching, skin color texture description, and image central moment matching, solves the classification of three-points type swim-suit image, nude image and people face image, makes the sensitive image recognition technique further expanded, and exploit its bright application future.

A method of forming a shaped thermoplastic sheet is described. The method includes providing a mold apparatus (1) that includes, a first mold portion (11) having an interior mold surface (14) having a plurality of perforations (26) and a perimeter edge (17). The mold apparatus (11) further includes at least one tubular sheet retainer (35) having an exterior surface (38) having a plurality of perforations (41) and a longitudinal axis (44) that is oriented along at least a portion of the perimeter edge (17) of the first mold portion (11). Each tubular sheet retainer (35) is reversibly and controllably: (i) positionable along an x-, y- and / or z-axis relative to the perimeter edge (17); and (ii) rotatable around its longitudinal axis (44), toward and / or away from the perimeter edge (17). A heated thermoplastic sheet (95) is formed and contacted (while at a thermoformable temperature) with the interior surface (14) of the first mold portion (11) and the exterior surfaces (38) of the tubular sheet retainers (35). Reduced pressure is drawn through the perforations (41) of the tubular sheet retainers (35) thereby retaining a portion of the heated thermoplastic sheet (95) thereon. The tubular sheet retainers (35) are rotated and / or moved along the x-, y- and / or z-axes with the sheet retained thereon, relative to the perimeter edge (17). Reduced pressure is drawn through the perforations (26) of the interior mold surface (14), thereby drawing the heated thermoplastic sheet (95) into intimate contour matching contact there-with. The heated thermoplastic sheet (95) is allowed to cool, and a shaped thermoplastic sheet retaining the contour of interior mold surface (14) is formed. A sheet molding apparatus (1) is also described.

The present invention relates to a method of forming a molded article (e.g., 141) from first and second heated and thermoformable thermoplastic sheets (75, 78), which are each respectively formed in situ from first and second thermoplastic compositions (e.g., by means of extrusion). The heated first and second thermoformable sheets are each drawn by reduced pressure into contour matching contact with the interior mold surfaces (14, 32) of separate first and second mold portions (11, 29), so as to form separate first and second profiled thermoplastic sheets (129, 144) within the separate mold portions. The first and second mold portions (11, 29) are positioned towards each other (e.g., together) so as to bring into contact and fuse together contact portions (159, 163) of the first and second profiled thermoplastic sheets (129, 144). Fusion between the contacted contact portions (159, 163) is achieved by means of (e.g., exclusively by means of) residual heat of sheet formation residing in each of the first and second profiled thermoplastic sheets (129, 144). The present invention also relates to a mold apparatus (e.g., 1) that includes a mold assembly (3, 5) that further includes a first mold portion (11) and a second mold portion (29) that reside between and are rotatably attached to laterally spaced first and second longitudinal supports (171, 174). At least one mold portion is longitudinally repositionable, between the first and second longitudinal supports, relative to the other mold portion.

A bicycle frame having a cavity constructed to receive a sensor device. The cavity has a shape and a contour that generally matches a shape and a contour of the sensor device. Such a configuration maintains the aerodynamic contour of the frame when the sensor device is positioned in the cavity. An optional plug occupies the cavity when the sensor device is not positioned therein. Preferably, the sensor device is constructed to wirelessly communicate bicycle operation information to a receiver that is remotely located relative to the sensor device. More preferably, the cavity is formed in a fork of the bicycle and the sensor device is configured to monitor operation of a front wheel and wirelessly communicate the operation information to the remote receiver.

A method of forming a shaped thermoplastic sheet is described. The method includes providing a mold apparatus (1) that includes, a first mold portion (11) having an interior mold surface (14) having a plurality of perforations (26) and a perimeter edge (17). The mold apparatus (11) further includes at least one sheet retainer (35) having an upper surface (38) having a plurality of perforations (41) and a longitudinal axis (44) that is oriented along at least a portion of the perimeter edge (17) of the first mold portion (11). Each sheet retainer (35) is reversibly and controllably: (i) positionable along an x-, y- and / or z-axis relative to the perimeter edge (17); and (ii) rotatable around its longitudinal axis (44), toward and / or away from the perimeter edge (17). A heated thermoplastic sheet (95) is formed and contacted (while at a thermoformable temperature) with the interior surface (14) of the first mold portion (11) and the exterior surfaces (38) of the tubular sheet retainers (35). Reduced pressure is drawn through the perforations (41) of the sheet retainers (35) thereby retaining a portion of the heated thermoplastic sheet (95) thereon. The sheet retainers (35) are moved along the x-, y- and / or z-axes, and optionally rotated, with the sheet retained thereon, relative to the perimeter edge (17). Reduced pressure is drawn through the perforations (26) of the interior mold surface (14), thereby drawing the heated thermoplastic sheet (95) into intimate contour matching contact there-with. The heated thermoplastic sheet (95) is allowed to cool, and a shaped thermoplastic sheet retaining the contour of interior mold surface (14) is formed. A sheet molding apparatus (1) is also described.