72 results about "Visual capture" patented technology

A system and method for remitting payment from a consumer's credit or stored value account by digital presentations of account information are described. A merchant may create one or more merchant account at a point-of-sale service site (“POS service site”) and associate one or more merchant portable computing devices (“MPCDs”) with one or more of the merchant accounts. Each MPCD may be configured to receive customer data from a customer via one of a visual capture and a wireless communication, such as a near field communication (“NFC”) or a machine-readable optical code. The customer data may be received from an NFC-capable physical token such as an EMV card, or a virtual token presented by a customer portable computing device (“CPCD”) using a NFC or a machine-readable optical code. Each MPCD may contain a point-of-sale payment application supplied by the POS service site that may capture data representative of a consumer account from the received customer data.

Systems and methods are provided for selectively restricting a mobile device. In one implementation, a visual capture can be to identify one or more indicators within the visual capture. Based on the indicators, an implementation of a restriction at the mobile device can be adjusted. In another implementation inputs can be processed to compute a determination, determination reflecting at least one of the in-vehicle role of the user as a driver and the in-vehicle role of the user as a passenger; and, an operation state of the mobile device can be modified based on such a determination. According to another implementation, one or more outputs can be projected from a mobile device, inputs can be received, and such inputs and outputs can be processed to determine a correlation between them. A restriction can then be modified based on the correlation.

The invention discloses a visual capture method and device based on a depth image and a readable storage medium. The method comprises steps that a point cloud image is acquired through a depth cameraKinect, the acquired point cloud image is segmented through an RANSAN random sampling consensus algorithm and an Euclidean clustering algorithm, and an identification-needing target object is acquiredthrough segmentation; 3D global characteristics and color characteristics of the object are respectively extracted and are fused to form a new global characteristic; off-line training of a multi-class support vector machine classifier SVM is carried out through utilizing the new global characteristic of the object, category of the target object is identified through utilizing the trained multi-class support vector machine classifier SVM according to the new global characteristic; then the category and the grasping position of the target object are determined; and lastly, according to the category of the target object and the grasping position of the target object, a manipulator and a gripper are controlled for grasping the target object to the specified position. The method is advantagedin that the target object can be accurately identified and grasped.

Selectively mobile system and method detect and locate information to determine repair or replacement needs for bridge and roadway infrastructure by detection of subsurface defects. Multiple sensors collect data to be fused include 1) Visual capture device or devices (16) aboard a mobile carrier (10) capture visual spectrum in either HD or regular video and/or as still frame camera images; 2) Infrared spectrum sensors (18) aboard the mobile carrier capture video or still frame images; 3) Global positioning sensors (GPS) (12) aboard the mobile carrier determine position; 4) Light detection and ranging system (LIDAR) aboard the mobile carrier gives precise locations. Further, 5) ground penetrating microwave radar (GPR) sensors carried by a vehicle (22) and related electronics determine depth of subsurface defects. The sensor systems supply data to a digital processor (40) having analysis and graphical information system (GIS) software (44) that fuses the data and presents it for delivery and use.

The invention relates to a visual perception device which comprises a processing unit, a camera unit, a display unit, a display screen and a storage unit, wherein the processing unit comprises an image processing module, a visual calibration module, a cursor control module and an object control module; the image processing module is used for controlling the camera unit to intake the visual images of the eyes of a user when the user stares at a target object in the display screen, processing the visual images to obtain a visual focal position, and computing visual calibration offset; the visual calibration module is used for carrying out coordinate calibration on the visual focal position according to the visual calibration offset; the cursor control module is used for selecting the peripheral area of the visual focal point as a visual cursor to judge whether the dwell time of the visual cursor is longer than a set time; and the object control module is used for controlling the visual cursor to select the target object when the dwell time is longer than the set time, and controlling the next target object to enter a visual cursor area when the dwell time is shorter than or equal the set time. The invention can reduce the unreliability of visual capture and the number of times of manual interaction, and realizes the effect of electricity saving and energy saving at the same time.

Disclosed is system and method for interactive telepresence that includes at least one data processing apparatus, at least one database, an audio/visual capture device that is configured with at least one microphone and camera. A detection module is provided to detect one of the plurality of participants who is speaking during the meeting, and a display module that is configured to display video that is generated.

Digital camera audio/visual capture includes bandpass and notch filtering for the audio input during camera lens motor operation; the filtering may be active during capture or the audio segments may be marked for later noise suppression processing.

The invention provides a measurement method for the migration rule of pre-crosslinked gel particles in a rock microscopic pore throat. The method includes: preparing a pre-crosslinked gel particle solution; building a visual measurement platform, and installing a rock microscopic pore throat model; utilizing a visual image acquisition and analysis system and a real-time pressure measurement and acquisition system respectively for real-time and visual capture and measurement of the morphologic change and pressure change of pre-crosslinked gel particles when passing the rock microscopic pore throat model; analyzing the changes to acquire microscopic seepage parameters of the pre-crosslinked gel particles when passing the rock microscopic pore throat model, and performing autoregression of amathematical model corresponding to the morphologic change and pressure change of the particles; and analyzing the migration rule of the pre-crosslinked gel particles in the rock microscopic pore throat, thus realizing integrated measurement of deformation, blockage, breakage and other morphologic change characteristics and real-time pressure change situation involved when the pre-crosslinked gelparticles pass through the rock microscopic pore throat.

This invention provides one method and system to send visual captured image in instant communication, which comprises the following steps: a, adding capture label information into the visual section to generate visual section; b, through the section label information controlling the deliver of the visual section. This invention adds section label information into the section to control the deliver through section information.

The invention discloses an immunomagnetic nano-particle with fluorescent properties and a preparation method and application thereof. The method comprises the following steps: using magnetic nano-particle Fe3O4 as a core, constructing a magnetic nano-particle with fluorescence properties by depositing a quantum dot layer on the surface of the magnetic nano-particle Fe3O4, and further introducing the anti-epithelial cell adhesion molecule antibody and the aminated polyethylene glycol molecule into the fluorescent magnetic nano-particle to obtain an immunomagnetic nano-particle. The immunomagnetic nano-particle enables rapid specific capture and release of circulating tumor cells. In addition, the quantum dot-labeled magnetic nano-particle enables visualization of capture and release processes of circulating tumor cells.

The invention discloses a game control system based on the vision and speech recognition technology. The system comprises a vision capture module, a vision recognition module, a voice acquisition module, a voice recognition module, a logical processing module and a multimedia display module. The invention further provides a game control method based on the vision and speech recognition technology. The method includes the following steps of game running, vision and speech recognition, text processing and multimedia display. According to the system and the method, the user can control a game by combining facial expression, movement and voice commands and can play a mobile game and enjoy the happiness brought by the game at any time and any place; the user can also operate or control the game through facial expression, the interestingness of the game is improved, and illiterate old people or children can enjoy the entertainment of games; the method and the system can also be applied to the fields of education, interactive entertainment and the like, damage to the eyesight is reduced, and operation is convenient.

The invention discloses an underwater UAV positioning method and an underwater UAV positioning device based on three-color laser. The underwater UAV positioning method comprises the steps that: S1, lasers of three different colors are incident into water in a coplanar, parallel and vertical manner, so as to form three laser beams underwater; S2, an underwater UAV captures positions of the laser beams and acquires an image containing the three laser beams; S3, the image is preprocessed to obtain pixel distances of the three laser beams; S4, and relative coordinates of the underwater UAV relative to the laser beams are obtained according to the pixel distances of the three laser beams and a photographic viewing angle of the image. The underwater UAV positioning method and the underwater UAVpositioning device utilize the Tyndall Effect to perform visual capture in turbid water areas through emitting three lasers of different colors underwater from above the surface of the water, and calculates the relative positions of the UAV relative to the lasers according to the photographic viewing angle and the transverse pixel length, thereby realizing precise positioning of the UAV at low cost.

The invention relates to the technical field of application of unmanned aerial vehicles, in particular to a visual capture based unmanned aerial vehicle transplanting system. The visual capture basedunmanned aerial vehicle transplanting system comprises an engine body and a transplanting mechanism, the transplanting mechanism is slidably arranged at one end of the bottom of the engine body to beconnected with seedlings for transplanting, the transplanting mechanism includes a first sliding table and a transplanting assembly, and further includes a material channel and a clamping mechanism, the material channel is horizontally arranged at the other end of the base of the engine body to accommodate to-be-transplanted seedlings, the clamping mechanism is arranged above the material channeland is located at the other end of the base of the engine body to take the seedlings from the material channel, and the clamping mechanism includes a second sliding table and a clamping assembly. By the arrangement that a current mainstream manual transplanting mode is replaced with an automatic mode, the working efficiency is improved, time is saved, and the labor intensity is low; compared withan vehicle transplanter in the prior art, the unmanned aerial vehicle transplanting system has the advantages of simple structure, small size, less destructive power to farmland and lower cost at thesame time.

The invention discloses a chopstick sorting device and algorithm. The device comprises a rack. A left side baffle, a side face baffle, a bottom baffle and a right side baffle are fixedly installed atthe top of the rack. A lifting frame is fixedly installed at one side of the right side baffle. According to the chopstick sorting device, a camera is used for replacing human eyes to complete the functions of recognition, measurement, positioning and the like, manual work is replaced to remove chopsticks with stains or mildew stains and chipped edges, a visual detection system is used for effectively improving the detection speed and precision of a production assembly line, the yield and the quality are greatly improved, meanwhile, misjudgment caused by human eye fatigue is avoided, a camerais used for photographing, computer vision is adopted for catching defects of the chopsticks, an instruction is sent, a motor drives a transmission chain to lower the transmission speed, chopsticks are blown out to fall into a waste collection box by turning on an air injection pump, and therefore the chopstick sorting accuracy is greatly increased, and the chopstick sorting efficiency and qualityare accelerated.

The invention relates to a visual capture system for cable film aging test and a test method thereof. The visual capture system comprises a test box body, and a sample rack and an optical measuring device arranged in the test box body. One side of the test box body is opened. The optical measuring device comprises prisms rotationally connected with the two sides of the test box body, a laser transmitter arranged opposite to the prisms and a photoelectric conversion screen arranged on the side, opposite to the opening, of the inner wall of the test box body, and the sample frame is arranged between the prisms and the photoelectric conversion screen. According to the invention, the length of the to-be-measured film is obtained in real time through the photoelectric conversion screen, the mechanical property of the to-be-tested film is analyzed and judged according to the length change of the to-be-tested film, the measurement precision is high by adopting an optical mode, the length of the film in the test box can be observed without frequently opening a box door of the test box, the change of the temperature in the box body is avoided, and the normal proceeding of an experiment is ensured.

This invention relates to one mobile traffic accident monitor system in machine visual technique, wherein the system comprises system hardware and software parts; the hardware comprises cameral head one to four, visual integrator, digital memory, DSP and selective display and data restore device through wires and plug connection; the system software comprises visual capture, image collection, visual integration, data memory and inquire, display and restore and extraction module. This invention can process collection, process, memory, restore and extraction to realize mobile traffic accident real time monitor on visual data information.

The invention aims to provide an intelligent system for obtaining the state of the power equipment based on the computer vision, which is good in safety, high in reliability, high in adaptability, simple and convenient in digital management, convenient to use and low in production cost. The system comprises an equipment identification module, a visual capture module and a state identification module. The equipment identification module is used for marking a state indication area on the power equipment, and when the operation state of the power equipment is changed, the state indication area is changed; the visual capture module is used for capturing image information of the equipment identification module, pre-processing the image information after determining the identity and the effective area of the power equipment, and then transmitting the pre-processed image information to the state recognition module; and the state identification module is used for verifying the preprocessed image information by applying a computer vision algorithm and cooperating with an internal preset image identification model, and extracting the operation state of the power equipment. The system is applied to the technical field of power equipment state acquisition.