51 results about "Imagery technique" patented technology

The invention discloses a lens calibration system of employing an imaging technology and a calibration method thereof. The lens calibration system comprises an image retrieving module, a processing module and a display module; the image retrieving module retrieves a target image through a lens to obtain a real-time image; the processing module analyzes the real-time image to calculate the contrast, the optical axis offset, the offset direction or the offset distance, and the display module displays the real-time image, the contrast, the optical axis offset, the offset direction or the offset distance. According to the lens calibration system of employing the imaging technology and the calibration method thereof, the real-time image can be obtained through the image retrieving module, and the calibration result can be immediately corrected and confirmed without an extra calibrating element. Therefore, the production cost can be reduced. Meanwhile, preferably, the calibration method can be carried out in an automatic mode, therefore, an overlarge error caused by manual calibration or waste of working hours and personnel cost required for reducing calibration can be avoided.

The invention provides a video creation system and belongs to the field of the image technology. The video creation system solves the problem of low creation efficiency and intuition performance of the exiting video creation scheme. The video creation system comprises a storyboard editing and displaying module, a footage acquiring module and a storing module, wherein the storyboard editing and displaying module creates a plurality of scenes in some order in a storyboard and adding descriptors to the scenes; the footage acquiring module controls a video shooting device to shoot footages corresponding to the scenes selected by a user in the current storyboard; the storing module stores scene information of the storyboard provided by the storyboard editing and displaying module and footages transmitted by the footage acquiring module and the corresponding relation between the footages and the scenes. The video creation system integrates creation and edition of the storyboard and shoot, storage and edition of the footages, and can increase efficiency of intuition performance of video creation remarkably.

A microminiaturized common image surface panorama imaging technique, wherein aspheric imaging lens and corner cube mirror constitute four identical imaging optical path rack and vertically fixed. The number of divided image surfaces by image surface coupler is same to the number of divided image surfaces by aspheric imaging lens and corner cube mirror. The three-dimensional space scene information obtained by aspheric imaging lens and corner cube mirror arrives the image surface coupler by the imaging optical path rack and the imaging surface of imaging device is divided into four same imaging areas in four quadrant using image surface coupler and the four path scene information synchronizes one path to image on the four imaging areas of image surface. Four images on the image surface respectively correspond space scene information on the four direction and are subjected to character matching and image mosaicking based on the overlap area between the two adjacent scene images, in order to obtain a intact space panoramic image. The invention has features of identical linearity, good resolution and real time performance, small aberrance, microminiaturization, particularly suitable for application with higher microminiaturization requirement.

The invention relates to the field of remote sensing images, and discloses a domain self-adaptive method and system for remote sensing image classification. The domain self-adaptive method comprises the steps of selecting an unmarked sample having the largest amount of information with respect to a current classifier from a target field through active learning, marking the selected sample and adjusting the current classifier in accordance with the marked sample and a current training sample set; and adjusting the current classifier after active learning adjustment through semi-supervised learning. The domain self-adaptive method and system of the invention are suitable for migration of priori knowledge of images in the same region or in different regions at different times, solve the domain self-adaptive problem through active learning and semi-supervised learning, and allow mutual transmission and utilization of knowledge of different images.

The invention relates to the technical field of automobile glass brand mark printing, particularly relates to a system for printing a brand mark on a piece of irregular automobile glass and further provides a method for printing the brand mark on the piece of irregular automobile glass by using the system. The system for printing the brand mark comprises a computer, a feeding region, an image collection region, a printing region and a discharging region. An imaging technology is utilized to identify the outline of the automobile glass and conduct printing location, self adaptability of the printing location is improved, printing quality and printing efficiency are finally improved, and the requirement for high yield and high quality can be met. Meanwhile, the system further has a detection function, printing and detection are integrated, system production efficiency is improved, and the actual production requirement can be met. In addition, by means of the system, the automobile glass with qualified printed brand marks or unqualified printed brand marks is stored in a separation mode, the discharging efficiency of the automobile glass is improved, and operation of following work procedures is facilitated.

The invention belongs to the technical field of optical technologies and medical optical images, particularly relates to a scanning synchronous imaging and indicating device and method for venous vessels and aims to receive a scanning imaging signal by using a linear array photoelectric sensing element, simulate or digitalize a photoelectric signal and form indicating vessels by using a visible light LED array in a discrete light spot form, and image processing with a large data volume and image calibration are eliminated. The technical scheme adopted by the invention is that the scanning synchronous imaging and indicating device comprises a near-infrared LED light source for illuminating the vessels and an imaging lens, wherein a scanning galvanometer is arranged between the imaging lens and an imaging plane thereof; the linear array photoelectric sensing element capable of sensing near-infrared light is arranged on the image plane reflected by the scanning galvanometer; a near-infrared interference filter is arranged between the imaging plane where the linear array photoelectric sensing element is positioned and an optical axis of reflecting light of the scanning galvanometer; the near-infrared interference filter is parallel to a mirror surface of the scanning galvanometer during immobility; the visible light LED array is connected to a driving end of a signal processing and driving circuit; a projection lens is arranged between the visible light LED array and the near-infrared interference filter.

The invention belongs to the technical field of holographic images of intelligent glasses, and discloses an intelligent adjusting method for preventing holographic images from blocking sight of near-to-eye display equipment. The intelligent adjusting method comprises the following steps: judging three-dimensional space coordinates of a fixation points of eyeballs; judging the change condition of pupils of human eyes; judging whether a real object exists at the position of the fixation points or not through an artificial intelligence image recognition technology; based on the judgment result, judging whether the user has a watching requirement on an object behind the holographic image or not at the moment; and if the user is paying attention to the object behind the holographic virtual image, controlling the near-eye display equipment to reduce the brightness of the holographic image or turn off the near-eye display equipment by the computer control system, or moving a watching shielding program, wherein when the visual fixation points of the human eyes leave the body of the object or the fixation points returns to the holographic virtual image, the holographic virtual image state (light brightness and position) presented by the optical near-to-eye display equipment recovers to the initial state. For the intelligent adjusting method for preventing holographic images from blocking sight of near-to-eye display equipment, the problem that the light brightness of the holographic image light source interferes with real object observation of a user is solved.

The embodiment of the invention discloses a CT lumbar spine automatic locating method and device and a storage medium The method comprises the following steps of: the training step: acquiring the initial CT stereoscopic image of the spine; processing the initial CT stereoscopic image of the spine so as to obtain the locating parameters of the lumbar spine position; the prediction step: acquiring the CT stereoscopic image of the spine to be measured; performing projection processing on the CT stereoscopic image of the spine to be measured by using the digital reconstruction radiography and thegeometric relationship so as to obtain the DRR image to be measured; predicting the DRR image to be measured by using the convolutional neural network and locating parameters so as to obtain the position information of the lumbar spine in the DRR image to be measured; and mapping the position information of the lumbar spine in the DRR image to be measured to the CT stereoscopic image of the spineto be measured by using the digital reconstruction radiography technology so as to obtain the position information of the lumbar spine in the CT stereoscopic image of the spine to be measured. With application of the CT lumbar spine automatic locating method and device and storage medium, the robustness, the real-time performance and the accuracy of lumbar spine automatic locating can be enhanced.

The invention belongs to the technical field of confrontation shooting simulation and in particular relates to one set of an algorithm for judging a simulated shooting effect by a flight track kineticenergy projectile, minimum structures and functions of a device and an information platform which are matched with the algorithm, and a principle for recognizing a target and identifying diversifieddamage effects. The algorithm provided by the invention takes a digital imaging technology as the foundation, and a shooter opinion is deduced through resolving an optical imaging relation and quantifying a digital image; a position relation between a target and the projectile is judged by combining actual determination and a projectile calculation technology; and simulated shooting can be carriedout on any physical object. The algorithm provided by the invention is better that a light direction collimation technology which cannot represent a trajectory, is optimized and innovated in the aspect of damage recognition, can more vividly represent the shooting and can obtain more valuable battlefield data; and the algorithm is especially applicable to the shooting simulation of a sniper riflesystem, is also applicable to other firearms or point mass destruction weapons with a parabolic trajectory and also can be used for civilian shooting sports or entertainment.

The invention relates to the technical field of vehicle-mounted images and in particular relates to a method and a device for carrying out Internet social intercourse based on a vehicle-mounted real-time image. An out-vehicle mobile terminal obtains an image resource in real time through a cloud server; a vehicle-mounted terminal selectively obtains a real-time image resource through the cloud server or an image acquisition device and the real-time image resource is observed; when network sharing of the real-time image resource needs to be shared to realize the social intercourse, the real-time image resource is uploaded to the cloud server through the vehicle-mounted terminal or an in-vehicle mobile terminal and the image resource is shared; real-time videos are watched by a user and other users in the same network direct broadcasting room and interaction is realized. Compared a current single cell phone camera, a plurality of internally-arranged and externally-arranged cameras in a vehicle provide more abundant multi-path image resources and wide ranges of the videos; people can collect sceneries along the way by utilizing the resources and share current real-time road conditions to communicate with people around or people which are interested in the sceneries and the road conditions.

The invention discloses a stereomicroscope with an all-field of view stereo viewing function and belongs to the field of a microscope. The stereomicroscope is a new-type microscope combined with an optical imaging technology, a digital image and video technology and a computer technology. The microscope is equipped with an all-field of view angle stereo viewing system. The microscope is composed of an imaging device, a data processing and storage device and a viewing device. The imaging device is composed of two sets of optical imaging systems and two sets of photosensitive elements. An included angle of 12-15 degrees is formed between the two sets of optical imaging systems. The imaging device is connected with the data processing and storage device. The data processing and storage deviceconverts two ways of signals transmitted by the photosensitive elements into digital image information through utilization of a predetermined processing program. Split screen playing is carried out on the digital image information through utilization of the viewing device. The viewing device is composed of a display screen and a viewing mirror. According to the microscope provided by the invention, stereo images can be digitalized, and a viewing result can be conveniently stored, modified, replayed and shared. An all-field of view viewing effect is constructed. Immersion and a comfort level of a user are improved. Heights and angles of eyepieces can be flexibly adjusted. Use convenience is improved.

The invention relates to a millimeter wave security check instrument debugging system and a millimeter wave security check instrument debugging method. The system and method are used for debugging the imaging resolution of a millimeter wave holographic imaging security check system. A main control device is used for generating millimeter wave detection signals and reference signals; the main control device is also used for transmitting the millimeter wave detection signals to a detected object through a millimeter wave transmitting antenna and receiving echo signals reflected from the detected object through a millimeter wave receiving antenna when the millimeter wave transmitting antenna, the millimeter wave receiving antenna and the detected object are located at different relative positions, and the then, the main control device carries out 3D imaging by using a holographic image technology according to the reference signals and the echo signals; and the main control device can finally obtain a plurality of 3D imaging results, and therefore, optimal relative positions of the millimeter wave transmitting antenna, the millimeter wave receiving antenna and the detected object can be determined. The system and method can be applied to the millimeter wave holographic imaging security check system, and therefore, the imaging resolution of the millimeter wave holographic imaging security check system can be improved.

The invention provides a z-direction fly focus scanning mode and an image reconstruction method, and relates to the technical field of medical images, the z-direction fly focus scanning mode comprises Z-direction fly focus sampling, adjustment of positions of two adjacent focuses, rotation of a frame shaft by 180 degrees in an axial scanning mode, Z-direction fly focus control, and linear change slope design. The image reconstruction method comprises the following steps: respectively rearranging data of two focuses to form two parallel beams; carrying out interpolation in the angle direction, so that the scanning data angles of the two fly focuses are the same; performing interpolation in the radial direction, so that the non-equidistant parallel beams of the two focuses are converted into equidistant parallel beams; respectively carrying out filtering operation on the two parallel beams; back projection calculation. According to the Z-direction fly focus axis scanning mode and the image reconstruction method, reconstruction can be carried out at any position in the Z direction to obtain images with completely identical layer thicknesses; meanwhile, the number of Z-direction sampling points is increased through the special axis scanning mode and the reconstruction method, and therefore Z-direction aliasing artifacts are reduced.

The invention relates to the field of medical image technology, and particularly to a breast nodules auxiliary diagnosis method based on DSSD and a system. The system comprises a breast image workstation, a breast cloud diagnosis system and a breast diagnosis mobile terminal. The breast image workstation performs breast image acquisition. The breast cloud diagnosis system comprise training set anda testing set preprocessing, marking and neural network discriminating, wherein the training set and the testing set preprocessing comprises multi-scale image de-noising and enhancing. The method comprises the steps of acquiring a breast graph by the breast image workstation, performing discriminating through mainly using a DSSD neural network, and finally transmitting a result which is obtainedthrough processing of the breast cloud diagnosis system to the breast diagnosis mobile terminal. According to the method and the system, a computer-aided diagnosis (CAD) system based on deep learningis developed for aiming at the field of the medical image (unnatural image), thereby supplying a second opinion for diagnosis to a radiology department doctor, and more effectively assisting the doctor in performing diagnosis.

The embodiment of the invention provides a magnetic resonance calibration scanning sequence configuration and image obtaining method and system, and relates to the medical image technology field. The method provided by the embodiment of the invention comprises: obtaining one-dimensional projections of an interested region on at least two directions according to a measurement sequence to determine the lengths of the interested region on the at least two directions; or, obtaining the images of the interested region according to the measurement sequence to determine the lengths of the interested region on the at least two directions; and determining the scanning range of a calibration scanning sequence based on the lengths. The scanning area corresponding to the interested region is subjected to system calibration to reduce the time of the system calibration and improve the efficiency of the system calibration.

The application discloses a distribution network operation monitoring method based on a holographic image technology, which includes the following steps: acquiring the equipment ledger of a medium-/low-voltage distribution network by taking 10kV feeders of the distribution network as units, and constructing a holographic medium-/low-voltage distribution network operation monitoring topology base map according to the equipment ledger and the topological relationship; acquiring the operation information of the 10kV feeders from a production management system; acquiring the geographic informationof the 10kV feeders from a distribution network GIS (Geographic Information System); acquiring the operation meteorological information of the 10kV feeders from a meteorological system; displaying all the information in the holographic medium-/low-voltage distribution network operation monitoring topology base map to obtain a holographic medium-/low-voltage distribution network operation monitoring map; and issuing an alarm for abnormal distribution network equipment according to the information displayed in the holographic medium-/low-voltage distribution network operation monitoring map. The method provided in the embodiment of the application, together with a background monitoring system, can improve the operation and maintenance level of 10kV medium-voltage lines, quickly locate equipment faults, prevent heavy load and overload of equipment and improve the power supply reliability of the system.

The invention discloses a division method of a holographic video stream and relates to the technical field of holographic images. The division method comprises the following steps: assuming that one video stream has n frames, namely F1, F2 ...Fn; carrying out image division on a certain frame Fi to obtain divided areas Si1, Si2,...Sim; given that an image division process is Seg(x), solving a similarity function to be Sim(x, y) and a similarity threshold value to be V; and converting an adjacent-frame correlation into {Tk(x)}, k=1, 2 ...27. According to the division method of the holographic video stream, disclosed by the invention, the image division is carried out on the basis of pixel colors, and traditional image division does not need to be carried out on each frame under the condition that widths of the same objects in left and right views are different; and on the basis of keeping the division accuracy of an original algorithm, an image division speed is extremely improved.

The invention discloses a short message image stepping transmission method based on Beidou one-key alarm, which relates to the technical field of Beidou satellite short messages, and comprises the following steps of: performing change detection on an image block in an SIP (Session Initiation Protocol) at a transmitting end by adopting a ratio method, and determining whether to perform data updating on an image or not; and after processing of compression, packaging and the like, sending the image blocks needing to be updated to the receiving end by the Beidou to update the image data for the receiving end. The invention discloses a Beidou satellite short message system image transmission technology based on SIP and a transmission strategy adopted by the Beidou satellite short message system image transmission technology. According to the invention, the problem of packet loss in data transmission of the Beidou satellite system is well solved, and the real-time performance of image dataupdating in a Beidou narrow bandwidth communication environment is improved to the minute level, so that the near-real-time updating of remote sensing image data with a large data volume becomes possible, the Beidou communication function is brought into greater play, and the application value is important.

The invention provides a logistics cargo information monitoring method based on a hyperspectral information imaging technology. The logistics cargo information monitoring method comprises five steps of spectral information acquisition, spectral information base establishment, information monitoring, information querying and spectral information base correction. The logistics cargo information monitoring method is simple and reasonable, is flexible and comprehensive in acquisition of monitored information data, can perform acquisition and monitoring on logistic personnel, equipment, cargos and surrounding environment information efficiently and comprehensively, is fast and efficient in information acquisition, simple in monitoring system construction and low in cost, can operate synchronously with a current logistics information monitoring system, thus significantly improves monitoring efficiency and monitoring accuracy of cargo condition change in the logistics process and transportation process, and is conductive to improving reliability and comprehensiveness of content in a logistics information database, so as to achieve the purpose of enhancing logistics system operation supervision capability.

The invention provides a z-direction high-resolution CT scanning mode and an image reconstruction method, and relates to the technical field of medical image. The z-direction high-resolution CT scanning mode comprises the steps that z-direction flying focus sampling is conducted, the positions of every two adjacent focuses are adjusted, the optimal pitch is selected, and a rack shaft is rotated by180 degrees in a spiral scanning mode; the image reconstruction method comprises the following steps of: respectively rearranging the data of the two focuses; arranging the data to form two parallelbeams, performing interpolation in an angle direction, enabling scanning data angles of two flying focuses to be the same, performing interpolation in a radial direction, enabling non-equidistant parallel beams of the two focuses to be changed into equidistant parallel beams, performing filtering operation on the two parallel beams respectively, and performing back projection calculation. The technology of switching between the two focuses in the z direction is combined with the special spiral scanning screw pitch, so that the four-time sampling rate in the z direction is achieved, aliasing artifacts are reduced, and the resolution in the z direction is improved.

The invention discloses a non-contact type color detecting method based on a digital image technology. The non-contact type color detecting method comprises the following steps: collecting image color data of a standard color card under a standard light source in a color matching observation box through a digital camera, and obtaining a conversion relation between the image color data and the standard color card by combining with an XYZ spectrum tristimulus value of the standard color card; measuring image color data of a standard sample and a batch sample under the standard light source in the color matching observation box by using the digital camera, computing XYZ spectrum tristimulus values of the standard sample and the batch sample through the conversion relation obtained by the standard color card, computing related chromatic aberration based on the XYZ spectrum tristimulus values of the standard sample and the batch sample, and judging whether the color meets the requirement or not according to the requirement on quality of a detected article. According to the non-contact type color detecting method based on the digital image technology, disclosed by the invention, the artificial influence factors of visual inspection are removed, and compared with a visual inspection mode, the accuracy of a testing result is higher and more reliable; the color of a colorful picture, a curved surface or the surface of an article which is uneven and is mixed in colors and nonuniform or irregular in coloring can be measured, and the using range is wider.

The embodiment of the invention provides an image processing method, and relates to the technical field of digital images. Firstly the first image of the first distance is acquired through a depth sensor, then the first foreground image and the first background image of the first image are acquired, then the second background image is acquired, the second background image is different from the first background image, and finally the first foreground image and the second background image are synthesized so as to form a second image. The technical problems of low degree of automation, excessively high professional and low working efficiency caused by the fact that photographing and image processing require to be performed in two separate steps in the prior art and the foreground and the background require to be synthesized frame by frame in later image processing can be solved.

The invention provides a fusion bionic robot remote care system based on holographic imaging technology, which includes a bionic robot puppet in a sitting or standing position, a holographic imaging module, a coordinate following module, a local mobile terminal, an intermediate server, and a remote mobile terminal. On light and shadow holographic basis, the system acquires and tracks the actions of a remote user. In combination with holographic light and shadow technology, the system not only enables an end-of-life patient or an elderly person to experience the stereoscopic visual experience brought by the holographic images vividly, quickly, and accurately, but also makes the person being cared better interact with relatives and family members in the holographic image by means of inductive interaction technology, brings a new spiritual enjoyment, and improves the induction interaction effect and experience.

The invention provides a modulatable CT detector data compression and acquisition mode, and relates to the technical field of medical images. The mode comprises the steps: carrying out the scanning ofa patient positioning film; performing dynamic dividing of a plurality of scanning areas according to the rotation of a rack, wherein the plurality of scanning areas comprise a first area, a second area and a third area, an area range formed by intersecting the tangent lines of the focus and the heart scanning area in a detector is the second area, an area range formed by intersecting the tangentlines of the focus and the heart scanning area in the detector and intersecting the tangent lines of the focus and the scanning view boundary in the detector is the first area and the third area, andthe sizes of the three areas are dynamically changed along with the rotation of the rack; and dynamically compressing the data of the first and third areas, wherein the compression process is completed on a data acquisition board of a rotor part of a CT machine. The data compression and acquisition mode can reduce the data bandwidth, control the data volume and reduce the requirement of the slipring data transmission bandwidth.

The invention belongs to the technical field of microscopes, and particularly relates to a full-field-of-view augmented reality (AR) multifunctional microscope. The full-field-of-view AR multifunctional microscope is a novel microscope manufactured by combining an optical imaging technology, a digital imaging technology, an AR technology and a computer technology, and the microscope has the ability of a full field of view. The full-field-of-view AR multifunctional microscope is composed of an imaging device, a data processing and storing device and an observation device, the imaging device iscomposed of an optical imaging system and a photosensitive element, the imaging device is connected with the data processing and storing device, the data processing and storing device is at least composed of an image processor, the data processing device converts information transmitted by the photosensitive element into digital image information through a predetermined processing procedure, the digital image information is played by the observation device, and the observation device is composed of a display screen and an eyepiece. The microscope adopts the digital imaging technology and an optical amplification technology to create an effect of the full field of view, and meanwhile, additional information outside the field of view is further obtained by applying the AR technology.