290 results about "Real size" patented technology

A method for generating a real-time realistic-looking image of a pair of virtual glasses positioned on a real user face image issued from a single image, a bundle of pictures, a video clip or a real-time camera streams. A face analysis element estimates the 3D rotation matrix, the 3D translation vector, morphology parameters of the user's face. A glasses positioning element associated with a try-on mode for look or real-size simulation estimates the 3D rotation matrix, the 3D translation vector, global and local deformation parameters of the virtual glasses, and arms articulation, adapted to the morphology parameters computed by the face analysis element. A realistic rendering element mixes the real user face image with the virtual glasses positioned by the glasses positioning element.

The invention provides a leather area measuring system and a method based on a digital image method, which comprises a CCD video camera connected with an image acquisition device lens, the CCD video camera is connected with an image collection card and a computer; the measurement steps comprise: first, calibrating the system to gain the system pixel equivalent Epsilon, and the practical dimension represented by unit pixel, second, obtaining the gray image of the leather to be measured, third, denoising the gray image, fourth, converting the gray image to a binary image using an iterative threshold method, and separating the object from the background area, fifth, denoising the image for a second time, sixth, processing a leather image by a vector analysis method, and obtaining the edge outline and the pixel number of the object area, and seventh, calculating the leather area to be measured. The invention has the advantages of low cost, non-contact, high measuring precision, and convenient industrial use.

A method and a system for displaying an image based on texts in the image are provided. The method of the invention for displaying the image includes: a text extracting step, extracting text regions in the image to be displayed; a text occupancy amount calculating step, calculating occupancy amount of the text in said image; a comparing step, comparing the calculated occupancy amount with a predetermined threshold; a display step, displaying the image in real size of the image if said occupancy amount exceeds said predetermined threshold. It is achieved to display the image to the user in a manner of satisfying the viewing aim of the user, and unnecessary load of the computer system is avoided.

The present invention provides a calculating method for distance between a photographed object and a real scale, which can be applied to a picture searching device. First of all, a relation-corresponded table is established, which is provided with focal step numbers and object distances (the distance between the picture searching device and the photographed object); next, the real scale can be gained by directly looking up the table after focusing. On the condition that the object distance and an image distance are known, an object height (the real scale of the photographed object) can be easily worked out by using a calculating formula ''an object distance/an object height equals to an image distance/an image height''; because the image height of the photographed object can be gained by the size of the corresponded pixel of the picture searching device and calculating.

The invention discloses an object size measurement method. A calibration object is placed near a target object, pixel sizes of the target object and the calibration object are calculated, the actual size of the target object is calculated, no measurement tool is needed, and the external size of a general object can be quickly and accurately measured. Meanwhile, the invention also discloses an image database data acquisition method based on the object size measurement method. When a database comprising a target object image sample and the size of the target object is built, automatic database construction can be realized, that is, the target object image sample and the size can be obtained at the same time at one time through photographing, corresponding database construction is realized, and compared with manual recording, the method of the invention is labor-saving and time-saving, and is less error-prone.

Provided are an information processing device and an information processing method. The information processing device includes a display unit; an object image obtaining unit configured to obtain images of objects to be displayed on the screen of the display unit; a real size obtaining unit configured to obtain information related to the real size of the objects to be displayed on the screen of the display unit; and a calculating unit configured to process the images of the objects, based on the real size of the objects obtained by the real size obtaining unit.

There is provided a panoramic imaging apparatus which serves as a radiation imaging apparatus. The panoramic imaging apparatus includes an X-ray tube radiating an X-ray as a radiation, a detector outputting digital-quantity frame data corresponding to an incident X-ray, and moving means moving the pair of X-ray tube and the detector relatively to an object. The apparatus further includes means for acquiring the frame data from the detector during movement of the X-ray tube and the detector, and means for optimally focusing a portion being imaged of the object using the acquired data and producing a three-dimensional optimally focused image in which the real size and shape of the portion being imaged are reflected.

The invention relates to a taobao virtual fitting system; a customer uses client software on a computer to visit 3D virtual clothes and decorations of various brands provided by the system on internet, thus carrying out clothes fitting; the 3D clothes provided by the system can be visited for fitting online, and are set up according to standard data of clothes images and sizes provided by a clothes provider; the customer can use a camera head to take two body photos including a front photo and a side photo, so a real person 3D model can be automatically generated by the software of the system; the system generates figure size data of the customer in a real proportion according to the height inputted by the customer, thus realizing 3D virtual clothes trying on. 3D body model virtual clothes fitting can be realized according to customer figure size data and real sizes of various clothes under various sizes, so wearing effect on the model can be presented under each clothes size, and the customer can determine a suitable size.

The invention discloses an ore scale measurement method based on deep learning and an application system. The method comprises the following steps: obtaining an ore block image; image preprocessing: processing the implemented ore block image into a marked image, and dividing the marked image subjected to processing into training sample boxes and test samples; removing the abnormal marked image data; training a preset RetinaNet target recognition network by using the processed training sample; inputting the test sample to a target identification network to obtain a target identification result,and calculating the size of the ore; the invention discloses an ore scale measurement method based on deep learning and an application system. The RetinaNet target recognition network is trained by adopting a labeled ore image sample; the trained network model is obtained to be used for classifying and positioning the ore blocks, the real sizes of the ore blocks are calculated, complex features do not need to be extracted manually, the detection efficiency is high, and the problem that efficiency is low in traditional ore scale measurement is solved.

A user uses part data forming means 101 and module data forming means 102 to input the actual dimension, physical constants and mesh dividing number for fundamental shapes which are registered in advance, thereby forming parts, and then indicates the relative position between the parts to form the entire shape of an assembly of plural parts without paying attention to coincidence or non-coincidence of nodal points. Data converting means 104 divides the shape of each part thus assembled according to the indicated mesh divisional number to generate element data and nodal point data. Further, it generates a constraint equation for connecting nodal points which are non-connected between neighboring parts, and forms an analysis model 401. A finite element method analyzer 105 uses approximate calculation means 106 to approximate a non-connected nodal point displacement from a nodal point displacement of neighboring structural elements on the basis of the constraint equation.

The invention discloses a method and a device for realizing monitored video display, so as to realize monitored video display based on positioning and tracking. The method comprises steps: a three-dimensional model of a building is acquired, and according to the actual size, the geographic coordinates and the azimuth information of the building, the three-dimensional model of the building is mapped to a three-dimensional geographic coordinate system; the positioning coordinates of a positioned object are acquired; the positioning coordinates of the positioned object are converted to three-dimensional geographic coordinates in the three-dimensional geographic coordinate system as three-dimensional geographic coordinates of the positioned object; the position coordinates of a monitoring and photographing device in the building are converted to three-dimensional geographic coordinates in the three-dimensional geographic coordinate system as the three-dimensional geographic coordinates of the monitoring and photographing device; and according to the three-dimensional geographic coordinates of the positioned object and the three-dimensional geographic coordinates of the monitoring and photographing device, a monitoring and photographing device with a distance with the positioned object in a preset range is determined as a called monitoring and photographing device, and a monitored video and/or an image of each called monitoring and photographing device are/is acquired to be displayed.

The application relates to an object size measuring method and device based on three-dimensional vision technology. The method comprises the following steps: acquiring three-dimensional point cloud data of the object; performing plane fitting on the three-dimensional point cloud data to obtain at least one point cloud plane; determining a plane intersection line at which the plurality of point cloud planes intersect; and calculating the actual size of the object according to the plane intersection line. The method can not only enhance the reliability of the size measurement result, but also improve the efficiency of measuring the size of the object, thereby realizing the rapid measurement of the shape and structure of the packaging box by the object measuring system in the logistics application scenario.

The invention provides a cargo boxing method, apparatus and system, and relates to the technical field of container loading layout optimization. The cargo boxing method comprises the following steps of collecting image information of a to-be-boxed cargo through a mobile terminal; according to an image, calculating an actual size of the cargo in the image; and according to the actual size of the cargo, generating a loading scheme meeting a cargo loading box capacity constraint condition. The actual size of the cargo in the image is calculated through the mobile terminal; and the loading schememeeting the cargo loading box capacity constraint condition is generated according to the actual size of the cargo, so that the workload of manual measurement and manual input during boxing is reducedand the cargo boxing efficiency can be further improved.

The invention provides a testing device for an automatic parking system. The testing device comprises a parking controller and a test-bench, wherein the parking controller as the main controller of the automatic parking system is placed on the test-bench; a wheel is arranged at the lower part of the test-bench; a wheel speed sensor is arranged on the wheel shaft of the wheel; an ultrasonic wave sensor is arranged on at least one side surface parallel to the test-bench in the moving direction of the test-bench; the wheel speed sensor and the ultrasonic wave sensor are electrically connected with the parking controller; a parking space recognition algorithm, a parking space compensation algorithm, a parking space actual size and various working condition patterns are built in the parking controller used for verifying the accuracy of the parking space recognition algorithm and standardizing the parking space compensation algorithm when the test-bench simulates various parking working condition patterns of automobiles. Correspondingly, the invention provides a testing method applied in the testing device. According to the invention, the testing device for the automatic parking system and the testing method applied in the testing device are low in cost and short in testing time, and can simulate various parking working condition patterns.

A customer is presented with a product ordering interface for a size dependent product such as a window covering. The customer is presented with ordering options. Once the customer has selected the desired product, the user is presented with a measurement confirmation interface. The customer is directed to enter at least one first measurement and one second measurement. The measurement(s) are entered into the customer ordering interface. From these measurements the system calculates a theoretical dimension for a product feature. The customer also measures the actual dimension of the product feature. The ordering system compares the calculated dimension to the customer measured dimension. If the calculated dimension matches the customer measured dimension, the measurement is confirmed.

A skin mirror image milling numerical control program fast generating method based on features includes: performing machining area division according to machine tool travel and the actual size of a skin piece, and identifying skin piece area features; determining the frame bent distribution information of each machining area and information such as feature machining sequence and cutting parameters of the current area, and building a skin middle layer process curved surface for automatic tool trajectory calculation; performing automatic numeral control programming based on the features on a machine tool spindle and top support according to tool trajectory information, adjusting frame bent positions through interference judgment, and outputting a final numerical control program for driving the machine tool to perform fast machining. The method has the advantages that by the skin mirror image milling fast numerical control programming based on the features, the tool trajectory compiling cycle is shortened, automatic numerical control programming of the machining spindle and automatic numerical control programming of the top support are achieved, programming's dependence on human experience is reduced, programming standardization is guaranteed, programming quality is increased, and programming efficiency is increased at the same time.

An object of the present invention is to provide a wider display screen to a portable information terminal including a video telephone function and to provide means for simultaneously confirming both a transmission screen and a reception screen.

A movable display part in a shape of a lid body that can be opened is provided in a back of a case of the portable information terminal and the movable display part is opened taking an axis provided on the case as a center, thereby enabling a display screen of the movable display part to be seen from the same direction as that of a fixed display part. Thus, a wider display screen than the conventional one is provided. Moreover, different information is displayed on the fixed display part and the movable display part, thus increasing an amount of information that can be recognized by an operator at a time. Particularly, in using a video telephone, a transmitted image is displayed on one of the screens and a received image is displayed on the other screen. As a result, it is made possible to make a phone call while confirming an image in an actual dimension of the transmitted image, which was difficult to perform in the conventional portable information terminal.

The invention provides a building information model generation method and system. The building information model generation method comprises the steps that through normal estimation, normal clusteringand point cloud segmentation, edge points located in an edge area of a building, corner points located in the corner point area of the building and plane points located in the plane area of the building are distinguished from the indoor three-dimensional point cloud model of the building; and through edge point analysis, corner point analysis and plane point analysis, the data of edge points located at the accurate edge of the building, corner points located at the accurate wall corners of the building and plane points located on the wall surface, the ceiling and the ground of the building inthe indoor three-dimensional cloud model are distinguished, and the building information model of the building is generated. According to the building information model generation method and system,the high-precision BIM with the real size information of the building can be generated, so that a high-precision map can be provided for indoor navigation, and accurate multi-machine scheduling of different robots is realized.

The present invention relates to a method for browsing house interactively in 3D virtual reality and system for the same. The method has steps of: (a) acquiring a 3D graph and data file of a real house structure; (b) converting the 3D graph and data file to a 3D house virtual object; and (c) browsing an inside space and space size of the 3D house virtual object in 3D virtual reality, wherein a new 3D image of the moved 3D house virtual object is displayed according to a distance or angle moving command, and a real dimension between two measured positions of the real house is provided according to a measurement command. In addition, the method of the present invention also verifies whether a size of a selected 3D household virtual object matches that of a selected position in the 3D house virtual object, where the selected 3D household virtual object is going to be placed. Accordingly, a user can quickly determine whether the real house corresponding to the 3D house virtual object is qualified.

The invention provides a robot indoor positioning method based on ceiling images. The method comprises the following steps of arranging a pattern obviously different from an image in an adjacent vision field on a ceiling; programming to make a robot traverse indoor positions, shooting pictures through a camera on the top, and splicing collected images to obtain a global image; comparing the actualindoor size with the pixel size of the global image, and obtaining coordinate conversion relationsbetween image coordinates and actual coordinates; calculating the pose of the robot in the global image through an optical flow method and image matching, and according to the coordinate conversion relations, determining the current actual pose of the robot. The robot indoor positioning method basedon the ceiling images calculates the pose of the robot in the global image through the optical flow method and image matching, and determines the current actual pose of the robot according to the coordinate conversion relations. The robot indoor positioning method based on the ceiling images is high in adoptability and good in stability.

The invention discloses a method for estimating the actual size of an object and a real object projector having a function of estimating the actual size of the object, which are used for observing images of an object to be tested. The method for estimating the actual size of the object comprises the following steps of: performing an object distance estimating procedure to obtain an object distance between a lens of the real object projector and the object to be tested; estimating size data of a photographable image area according to a viewing angle of the object distance and the lens; using the lens and an image sensor to capture the object to be tested so as to generate a digital image; counting the quantity of effective pixel points corresponding to a plurality of marking points in the digital image; and estimating data of an actual size corresponding to the plurality of the marking points according to the quantity of the effective pixel points, the quantity of the pixel points of the image sensor and the size data of the photographable image area. The method and the real object projector overcome the defects that correlative measurements and display practices in the prior art are very inconvenient and can cause errors easily for users.