284results about "Image acquisition" patented technology

A method for motion synchronization-based head pose estimation, by a head mounted display (HMD) device and an HMD device for performing the same are provided. The method includes receiving, by the HMD device, motion data from a plurality of motion sensors of the HMD device, receiving, by the HMD device, a plurality of image frames from at least one simultaneous localization and mapping SLAM camera of the HMD device, estimating, by the HMD device, a plurality of motion parameters of head movements of a user from the plurality of image frames received from memory, generating, by the HMD device, a filtered subset of the motion data received from the plurality of motion sensors based on the plurality of motion parameters of the head movements, synchronizing, by the HMD device, the plurality of image frames received from the memory and filtered subset of motion data, and estimating, by the HMD device, the head pose based on the synchronized plurality of image frames and motion data.

The invention discloses a cloud-side-end collaborative meat intelligent detection system and a cloud-side-end collaborative meat intelligent detection method. The system realizes high precision, low delay and low resource consumption of meat detection through three-level cooperation of the mobile terminal, the edge device and the cloud server and a dynamic task scheduling strategy based on confidence, and is suitable for meat safety supervision in a large-scale and complex environment.

A medical visualisation system including a main component including an image sensor and a light emitter; a first auxiliary component configured to transmit image data based on the signals; a second auxiliary component configured to receive signals from the main component and to transmit image data based on the signals, the second auxiliary component including a second memory having embedded therein data; and a video processing apparatus including a high frequency wireless transceiver configured to establish an image data communication channel with the high frequency wireless transceiver of the first auxiliary component or with the high frequency wireless transceiver of the second auxiliary component and to receive the image data with the image data communication channel, wherein the first auxiliary component is configured to, based on the data, cause adjustment of one or more components of the main component or the video processing apparatus.

The invention relates to sensor system arrangements and configurations. In particular, the invention provides methods, devices, systems and computer program products for integrating, compositing and / or processing data representing a measurable state within a region-of-interest, that has been received from a plurality of sensors that respectively have different input sensitivities, spectral sensitivity ranges and / or input capture ranges.

An electronic apparatus for storing wine includes a door; memory storing instructions; a camera; and at least one processor, wherein the instructions, when executed by the at least one processor, cause the electronic apparatus to acquire a captured image via the camera based on the door being open; acquire, based on the captured image, wine storage information including a shelf location where a wine object is placed and a wine location of the wine object; acquire wine feature information corresponding to the wine object; store wine information including the wine storage information and the wine feature information in the memory; and transmit the wine information to a user terminal to cause the user terminal to display at least one of the wine storage information, the wine feature information, a storage recommendation based on the wine information, or a food pairing recommendation based on the wine information.

A method for intraoral imaging generates one or more output imaging signals from an intraoral probe and acquires multimodal image content from intraoral surface locations according to tissue response from the one or more imaging signals and associates spatial coordinates to the acquired multimodal image content. A surface contour of the patient dentition is generated by stitching the acquired multimodal image content and preserving the association of spatial coordinates with the stitched multimodal image content. Tooth outlines for one or more teeth are generated from the generated surface contour and the generated outlines arranged as a dental chart representing a spatial ordering of the one or more teeth and of supporting gum tissue adjacent to the teeth. The dental chart is populated by analyzing the acquired multimodal image content and associating the analysis to positions on the dental chart according to the preserved association of spatial coordinates and is displayed.

A stream of events from an event-based sensor is processed for trajectory determination. Each event comprises a pixel position in a pixel array of the event-based sensor, and a time stamp. A grid of cells is defined for the pixel array, with each cell comprising a plurality of pixels. In the trajectory determination, incoming events are mapped to the grid of cells during a first time period, and summary data with a representative position for the pixel positions that fall within the respective cell during a first time period is generated. An intra-cell evaluation of the summary data generated for a second time period is performed to generate a cell trajectory of representative positions within the respective cell. An inter-cell evaluation of a plurality of cell trajectories generated for a plurality of cells for the second time period is performed to generate a grid trajectory.

Disclosed are a method, a device, and a recording medium, according to one embodiment, the method comprising the steps of: acquiring scan data for an oral cavity; acquiring undercut data including data on undercut location and undercut depth determined on the basis of an insertion path of an insert body corresponding to the oral cavity; acquiring an oral modeling image including an undercut area divided into a plurality of areas on the basis of the scan data and the undercut data; acquiring an updated oral modeling image on the basis of the undercut depth for an area adjacent to a target area according to a user input applied to the target area including one of the plurality of areas; and displaying the updated oral modeling image.

A system may include a waterslide having a waterslide entrance and a waterslide exit. The system may include a first camera positioned at the waterslide entrance in which the first camera may capture a first video feed. The system may include a second camera positioned at the waterslide exit in which the second camera may capture a second video feed. The system may include a processing device that may: determine an incoming guest count at the waterslide entrance by detecting a ride vehicle occupancy at the waterslide entrance based on the first video feed; determine an outgoing guest count at the waterslide exit by detecting the ride vehicle occupancy at the waterslide exit based a second video feed; and match the incoming guest count and the outgoing guest count.

An imaging device includes a display control unit configured to display a first indicator indicating a recommended imaging position and a second indicator indicating a current imaging position in a superimposed manner on an imaging monitor image, and perform processing for changing display of the first indicator in accordance with image obtaining processing for obtaining image data, and an imaging control unit configured to perform the image obtaining processing in accordance with a result of a matching determination between the first indicator and the second indicator on a screen.

To allow an image of a hand to be used for biometric authentication to be stably acquired even in a non-contact state.SOLUTION: A biological information acquiring apparatus includes a first camera for capturing a first image of a hand of a user inserted into an image capturing area, a second camera for capturing a second image of the hand of the user to be used for biometric authentication, and a processor for causing the second camera to capture the second hand image upon detection of a stationary state of the hand of the user based on the hand image captured by the first camera.SELECTED DRAWING: Figure 1

The invention discloses a plant three-dimensional reconstruction and phenotype extraction platform and a plant three-dimensional reconstruction and phenotype extraction method, and relates to the field of computer vision. A data acquisition controller in the platform judges whether all target plants enter a shooting window according to the center line deviation of a shooting trolley and the distance between the target plants and a distance measurement module; if yes, a differential motor PID closed-loop control algorithm is adopted to control the shooting trolley to decelerate to a preset shooting speed, the shooting trolley is controlled to shoot the target plant at multiple visual angles at the same time, a processing module adopts a NeRF model to conduct three-dimensional reconstruction on the target plant according to the image set, and a target plant surface point cloud is obtained; processing the surface point cloud of the target plant by adopting a Pointnet + + segmentation model to obtain a point cloud subset of each leaf and a stem point cloud subset; and obtaining phenotypic parameters according to the stalk point cloud subset and the leaf point cloud subset. The method and the device have the advantages of high precision, fast processing and field operation adaptability.

The invention provides a novel graph and image processing system which comprises an image acquisition module which adopts a high-resolution image sensor, has automatic focusing and exposure adjusting functions and is used for quickly and accurately acquiring static image and dynamic video image data. According to the novel graph and image processing system provided by the invention, through a parallel computing technology and an efficient algorithm, the image processing time is greatly shortened, and an application scene with a relatively high real-time requirement is met; through application of a deep learning algorithm and multi-modal fusion processing, the accuracy of image recognition, classification and analysis is improved, and image features can be extracted and a target object can be recognized more accurately. The system integrates various image processing functions and can process multi-modal data, so that diversified requirements of different fields and different users are met; meanwhile, due to the real-time feedback and interaction functions, the user can operate and control the image processing process more visually and conveniently, and the satisfaction degree of the user is improved.

A method for constructing a table including information on a pooling type based on ranges of scale of at least one object in at least one image for constructing table is provided. The method includes steps of: generating a first pooled feature map by applying max pooling and a second pooled feature map by applying avg pooling; and acquiring a first candidate bounding box by using the first pooled feature map and acquiring a second candidate bounding box by using the second pooled feature map; and comparing a first degree of similarity between the first candidate bounding box and a GT bounding box with a second degree of similarity between the second candidate bounding box and the GT bounding box to thereby construct the table so as to include information on respective optimal pooling types by respective ranges of the scale of the object.

The computer-implemented method for detecting defects in a 3D printer, wherein the method comprises the steps: a) capturing a first image of a construction space of the 3D printer, wherein the construction space comprises a 3D printed part that is shown in the first image; b) generating a second image that has a higher spatial resolution than the first image out of the first image by using a spatial resolution increasing artificial neural network.

This invention provides a method and system for automatically calculating the trajectory curve of mechanical motion, which acquires images A during mechanical motion using an acquisition device at a sampling period of one second. t The method acquires images and shooting parameter information, and obtains velocity values ​​from information in two adjacent images, eliminating the need to calculate velocity by obtaining displacement. This greatly simplifies the velocity calculation. Furthermore, it calculates displacement and velocity for each sampling interval using different methods, and calculates the difference between the current and previous values, comparing them to reduce the probability of misjudgment and improve the accuracy of the curve. When ΔV is less than a first threshold and ΔS is less than a second threshold, it compares the values ​​of ΔV and ΔS. If ΔV is greater than ΔS, it indicates a large deviation between the calculated vt and vt-1. This is because the method of this invention calculates v... t and s t re Since the values ​​are the same, the value of vt is replaced with s. t re This improves the accuracy of the speed curve.

The invention relates to a method for 3D reconstruction of a scene (2). The method comprises the step of providing a first camera (3) with a known position and orientation. The method further comprises a step of determining a first set of projection lines corresponding to the pixels (11) of said first camera (3), said projection lines being defined by the location and orientation of said camera (3) and the corresponding pixels (11). The method further comprises the step of projecting a light beam (13) onto the scene (2) by means of a light source (12) so as to limit a point (1) on said scene (2). The method further comprises the step of determining pixels corresponding to the image of the point (1) on the first camera (3) so as to define a corresponding first projection line (9) from the first set of projection lines. The method further comprises a step of determining a second projection line (10) from the second set of projection lines, the second projection line (10) corresponding to the instantaneous position and orientation of the light beam (13) or to the image of the point (1) on the second camera (4). The method further comprises a step of calculating a 3D position (17) of the point (1) on the scene (2) on the basis of the first and second projection lines (9, 10), wherein the 3D position (17) is defined in an area (18) in which the first projection line (9) and the second projection line (10) are closest to each other.

A matching position output system includes: a shooting means configured to shoot an image of an object; a generating means configured to generate information identifying the object from the shot image of the object; and an output means configured to, based on the generated information identifying the object, acquire information of a matching position of the object from a recording means configured to associate and record the information identifying the object and the information of the matching position of the object, and output the information of the matching position of the object.

An imaging system (1) includes an imaging unit (2) configured to capture an eye of a target person, and a mode control unit (4) configured to select one of imaging modes including a first imaging mode that sets a capture volume for which a greatest distance from the imaging unit (2) in an optical axis direction of the imaging unit (2) is a first distance, and a second imaging mode that sets the capture volume for which the greatest distance from the imaging unit is a second distance, in which the second distance is greater than the first distance. With the imaging system (1), a balance between an image quality matching a purpose of use and a capturing time may be easily achieved.

This application provides a thumbnail display method and an electronic device. In the technical solution, a target picture may have a plurality of thumbnails with different dimensions. When displaying a thumbnail with a relatively large dimension of the target picture, the electronic device may first display a thumbnail with a relatively small dimension of the target picture, decode the thumbnail with the relatively large dimension in a background, and replace the thumbnail with the relatively small dimension with the thumbnail with the relatively large dimension after decoding is completed. According to the technical solution, a speed of displaying a thumbnail by the electronic device can be increased, and a phenomenon of displaying a blank block when a plurality of thumbnails are displayed at a time can be avoided.

Projection method and projector. Improve the detection accuracy of points included in a projected point pattern. A projector (1) projects a point pattern (210a) including a first point (231), a second point (232), a third point (233), a fourth point (234), and a black point (235) to a projection surface (7). The display modes of the first point (231), the second point (232), the third point (233), the fourth point (234), and the black point (235) are different from each other, the first point (231) is located adjacent to the second point (232) in a horizontal direction and adjacent to the third point (233) in a vertical direction, the second point (232) is located adjacent to the fourth point (234) in the vertical direction, and the third point (233) is located adjacent to the first point (231) in the horizontal direction.

Techniques for scanning physical media on physical items and providing information about those physical items are provided. In one technique, a digital image that is generated by a mobile device and that indicates a list of ingredients in an item is identified. Text that contains the list of ingredients is identified within the digital image. It is determined whether a particular ingredient in the list of ingredients satisfies one or more criteria. In response to determining that the particular ingredient satisfies the one or more criteria, the digital image is modified by causing a portion, of the text within the digital image, that corresponds to the particular ingredient, to be highlighted while the digital image is displayed on a screen of the mobile device. In a related technique, the mobile device performs all the steps, whereas in another technique, a remote server performs one or more of the steps.

The invention discloses an image data processing method for telescope repeated positioning precision calculation, and the method comprises the steps: installing an industrial camera on a back frame of a telescope, laying a checkerboard target in a field environment, extracting the angular point coordinates of the target through an image recognition technology, and combining with a camera imaging geometric model. And the actual angle deviation when the telescope points to the same theoretical position for multiple times is inversely calculated, so that high-precision measurement of repeated positioning precision of the telescope is realized. The method solves the problems of dependence on expensive equipment, complex operation, poor environmental adaptability and the like in the prior art, has the advantages of low cost, high precision, easiness in deployment and suitability for a plateau field environment, and is particularly suitable for field precision test of a large telescope array.

An electronic device is provided. The electronic device includes memory storing instructions and including one or more storage media and at least one processor including processing circuitry, the at least one processor communicatively coupled to the memory, wherein the instructions, when individually or collectively executed by the at least one processor, cause the electronic device to activate a search function comprising a circle-to-search function, based on a configuration of the electronic device, after the search function is activated, determine an area in which an object is to be recognized, based on a user input for a display, recognize an object displayed within the determined area, display the recognized object in a first area of the display, display a search result of the recognized object in a second area of the display, and store an image of the recognized object and information on the search result of the recognized object in a predetermined space of the memory, and wherein the circle-to-search function includes a function of designating a specific area in the display, based on an input of a user, and performing a search for an image of the predetermined area.

To provide a system and method for provisioning computing resources using computer vision.SOLUTION: A method comprises: receiving an image comprising a plurality of visual elements; and recognizing the visual elements within the image as objects that represent network elements. The recognized objects have network element types such as a database, a load balancer, a sub-network, and a virtual machine instance and comprise one or more of these types of network elements. The method also comprises: recognizing an arrangement of the recognized objects that represents a network architecture; and provisioning computing resources corresponding to the objects by provisioning network elements that comprise one or more of the network element types. The provisioning generates a network architecture for the network elements based on the recognized arrangement.SELECTED DRAWING: Figure 17

This invention discloses a method for optimizing the configuration of a polarizer and analyzer, as well as a polarizer-analyzer system. The method includes the following steps: adjusting the instrument matrix W of the polarizer and the instrument matrix A of the analyzer to minimize the equal-weighted variance EWV of the instrument matrices, thereby optimizing for Gaussian noise; and ensuring that the sum of each row of the instrument matrix W and the instrument matrix A is zero, so that the estimation variance caused by Poisson noise is independent of the sample and reaches a minimum. This invention can suppress noise to the greatest extent and make the noise pattern independent of the sample; the noise distribution pattern is the same regardless of the sample being measured.

The invention discloses a hardware acceleration deployment method of an ultrasonic full-focus algorithm on an FPGA (Field Programmable Gate Array) platform, and relates to the technical field of deployment of an acoustic imaging algorithm on the FPGA platform, a master-slave structure taking the FPGA platform as a master controller is adopted, and a plurality of FPGA slaves are controlled to collect and calculate parameters in parallel through channel gating; a full-focus parameter calculation process is modularly divided, the calculation throughput rate is improved through a pipeline method, and calculation results of the multiple FPGA slaves are transmitted to the FPGA host for imaging; furthermore, a mirror image full-focus calculation method is adopted, parameter multiplexing is achieved through a recombination calculation process, and the parameter calculation time is shortened by half. The problems that an ultrasonic full-focusing imaging algorithm is complex in calculation, long in time consumption and difficult to deploy in a lower computer platform can be solved, development of a low-cost and light-weight ultrasonic phased array full-focusing online detection instrument is facilitated, and the method has important significance on maintenance and health monitoring of a pressure container.