154 results about "Image map" patented technology

Embodiments of the present application disclose an object grabbing method, a computer readable storage medium and an electronic device. The method comprises: obtaining an RGB image collected by an image collection device for a target container in a grabbing work area, the RGB image comprising image content related to a plurality of objects stacked in the target container; calling a feature extraction model with the RGB image as input, and determining a target object to be grabbed and extracting feature information of the target object from the RGB image by the model; if the feature information indicates that a physical label is attached to the outer packaging of the target object, and the hardness information of the outer packaging material is not greater than the hardness information of the physical label, determining a region where the physical label is located as a grabbing region; determining a target end effector capable of performing a grabbing operation on the physical label; and controlling an intelligent grabbing device to perform a grabbing operation on the grabbing region of the target object by the target end effector, thereby realizing intelligent grabbing of the target object. This helps to improve the success rate of grabbing, and the grabbing strategy is more universal and compatible.

To provide an image display system that can generate sharpened images (clear and easy-to-view images) while achieving further compactness, excellent portability, and superior mobility. [Solution] The present invention provides an image display system comprising a first image display device, an image sharpening device, a second image display device, and a storage device, wherein the first image display device displays an image captured by an imaging device, the image sharpening device performs image sharpening processing on the image captured to generate a sharpened image, the second image display device displays the sharpened image, and the first image display device, the image sharpening device, and the second image display device are stored in the storage device.

An image processing apparatus according to one embodiment of this application may include: an image acquisition unit for acquiring an image of a plurality of active materials; an image segmentation unit for segmenting a plurality of active materials included in the image of active materials to obtain a segmented image; and an image generation unit for inputting the image of active materials into an artificial intelligence model to generate at least one of the following: a binary image in which the active materials and cracks on the surface of the active materials are separated, a pore binary image representing the pore characteristics of the active materials based on the segmented image, or a combination thereof.

This invention discloses a transparent body system for large mining vehicles, comprising: an image acquisition module deployed at the front and front sides of the large mining vehicle to acquire image information of areas obscured by the vehicle body in real time, obtaining multiple images; an image processing and control module, including a panoramic view generation unit and an AR enhancement unit; the panoramic view generation unit generates a panoramic view by real-time stitching and fusion of the multiple images; the AR enhancement unit performs real-time road condition information recognition and dynamic blind spot marking based on a pre-stored high-precision map of the mining area, generates an AR enhancement layer, and overlays it onto the panoramic view; and a display module installed at a prominent position at the rear of the vehicle, facing outwards, to display the panoramic view with the AR enhancement layer overlaid in real time. This system provides other road users with a transparent view of the vehicle body, fundamentally eliminating safety risks caused by blind spots.

The application relates to the field of infrared thermal imaging technology, and particularly provides an infrared thermal imaging AI intelligent temperature measurement method.The method comprises the following steps: image input and preprocessing, receiving infrared images and sunlight images photographed by an infrared thermal imager, classifying based on pixel value differences, and preprocessing to obtain binary images; image cutting, cutting the binary images, and identifying the boundaries of numbers and symbols; characteristic value calculation and extraction, dividing regions according to the boundaries of the numbers and symbols, and performing feature extraction to construct a characteristic vector; number classification and identification, comparing the characteristic vector with a pre-trained K-nearest neighbor algorithm (KNN) model to identify the numbers and symbols; and image number output, combining the identified numbers and symbols into complete temperature values, outputting the identification result, and storing the identification result for comparison diagnosis.The method automatically and accurately identifies temperature information in the infrared images, and realizes intelligent comparison diagnosis.

The application belongs to the field of electric power system operation and inspection, and discloses an image super-resolution reconstruction method and related devices, based on an original image, a pre-trained image super-resolution reconstruction model is called to obtain a reconstructed image; the image super-resolution reconstruction model comprises an edge information pre-enhancement module, an attention module and a super-resolution reconstruction module; the edge information pre-enhancement module performs adaptive edge enhancement according to the uniformity of the original image to obtain an edge-enhanced image; the attention module comprises a serial edge attention module and a dynamic spatial attention module, which are respectively used for feature re-labeling of the edge-enhanced image in the channel dimension and the spatial dimension to obtain an edge-strengthened image and a globally optimized image; the super-resolution reconstruction module fuses the edge-enhanced image and the globally optimized image, and obtains the reconstructed image through channel dimension reorganization. The high-frequency details and edge structure of the image can be effectively restored, the clarity and fidelity of the reconstructed image are improved, and the quality of the reconstructed image is ensured.

A method for detecting optical defects within a windshield. The method takes, as input, a digital image map of the intensity of optical power of a windshield, and provides, as output, a digital image map of optical defects. The method includes (a) an image processing of the digital image map of optical powers for detecting and delimiting regions that differs in intensity of optical power; (b) computing, for each detected regions, a representative geometric distance and a representative value of the optical power; (c) computing an image map of the detected regions for which the product between the representative geometric distance and the representative value of the optical power is equal or superior to 2.9·10−4.

The application discloses a kind of measurement method and system of tire belt steel wire angle, including characteristic mark step: in the A surface and B surface of tire section, respectively mark tread pattern design width point, and confirm corresponding endpoint by on-off detection, mark as steel wire corresponding point;Image acquisition step: respectively to the image acquisition of tire section A surface and B surface of completion mark, obtain image;Image registration step: based on tread pattern design width point, A surface image and B surface image are registered in space, coordinate extraction step: from the A surface image and B surface image after registration, based on the mark of steel wire corresponding point, extract position coordinate;Angle calculation step: according to position coordinate, the angle of this steel wire is calculated.The application extracts steel wire coordinate by collecting section image and carrying out image alignment based on tread pattern design width point to calculate angle, realizes non-contact high-precision measurement, significantly improves measurement efficiency and data traceability.

Disclosed in the present invention is a local feature matching system based on keypoint detection. The system comprises: an encoder, a deep Transformer model and a matching module. An image pair to be matched (IA, IB) is input into the encoder, and fine features (formula I), coarse features (formula II), keypoints PA and PB of the image pair (IA, IB) are extracted; the coarse features (formula II) and the image pair (IA, IB) are input into the deep Transformer model, and the deep Transformer model performs feature aggregation on an image IA and an image IB to obtain keypoint features (formula III); and the matching module converts the keypoint features (formula III) into a confidence matrix C, performs matching between the keypoint PA and the keypoint PB on the basis of the confidence matrix C, and then performs matching enhancement on the basis of the fine features (formula I), so as to complete the matching of the image pair (IA, IB). A weight (parameter) reuse technique is used to share task parameters between consecutive Transformer layers on the basis of task requirements, such that a model can maintain a feature expression capability, improving the model performance, and can also effectively reduce the model size. In addition, the use of a multi-scale keypoint detector reduces the propagation of redundant information and enhances feature specificity, thereby improving the model efficiency.

Systems and methods for determining a head pose of a user are described. Images captured by a head-mounted camera worn by the user are received, the images comprising captured markers, wherein each captured marker is one of a plurality of markers on a surface that are in the FOV of the head-mounted camera. Stored markers having a predetermined orientation and corresponding to each captured marker are identified from a database, the stored markers comprising coordinates for its corresponding surface marker. An orientation of the captured marker relative to its corresponding stored marker is calculated and the stored marker is obtained. Based on the stored marker and the orientation, an absolute pose of each marker is determined. Based on the absolute pose of each marker, the head pose of the user relative to the surface is calculated.

The invention provides an inspection system and an inspection method which are beneficial to classification and collection of electronic components with good reliability based on inspection. The inspection system includes: a transport unit that transports a plurality of electronic components (W); an imaging unit that acquires a captured image of the imaging region; an image analysis unit that analyzes the captured image; and an inspection device that inspects the electronic component classified as the inspection target, the captured image including an inspection image area, which is an image of the captured inspection area in the captured area, and a peripheral image area, which is an image of the captured peripheral area in the captured area. When it is determined that an image of a single electronic component is included in the inspection image region and an image of an electronic component is not included in the peripheral image region as an analysis result, the image analysis unit classifies the single electronic component as an inspection target.

The application discloses an interpretable tongue diagnosis auxiliary diagnosis system based on knowledge graph fusion reasoning. The system obtains tongue diagnosis image data containing at least tongue surface image and sublingual plexus image, determines a plurality of preset tongue diagnosis regions and generates regional node features; constructs an image graph and updates the image graph by a first graph neural network to obtain image node features; constructs a traditional Chinese medicine knowledge graph containing tongue image, pathological factors, viscera, syndrome nodes and their relationships and updates the knowledge graph by a second graph neural network to obtain knowledge node features, projects and maps the image node features and the tongue image node features to the same embedding space, aligns the cross-modal modes according to a contrast learning loss to obtain cross-modal correlation; constructs a fusion graph based on the image graph, the knowledge graph and the cross-modal correlation and performs graph reasoning to output syndrome results and reasoning path information. Explicit connection of image regions and traditional Chinese medicine semantics and output of traceable paths reduce experience dependence and enhance interpretation and review.

This invention relates to the field of intelligent transportation technology, and in particular to a method for generating images of spilled materials on highways from an aerial perspective. The method involves the following steps: road region segmentation using a pre-trained semantic segmentation model to generate a binary mask for the road region; vehicle target elimination using a pre-trained instance segmentation model to generate a vehicle contour mask; spilled material mask generation by generating a randomly shaped polygonal mask within the effective road area; local image preprocessing to perform geometric correction and size standardization on the cropped area; conditional image generation using a diffusion model combined with spatial conditions and textual prompts to generate a spilled material image adapted to the background; and image fusion and annotation to fuse the spilled material image back into the original image and automatically generate a standard annotation file. This invention can generate visually consistent and realistic composite images of spilled materials, achieve automatic generation of annotation files, significantly reduce data preparation costs, and improve data generation efficiency and diversity.

A system for context-based graphical element replacement is provided. Various graphical elements (e.g., images, icons, or the like) are detected in a source file. For each graphical element, a visual context of the graphical element and one or more additional contexts are determined. The one or more additional contexts include a context associated with information present within a predefined range of the graphical element, a visual context of at least one other graphical element, and a context associated with the source file. A replacement graphical element is then generated for each detected graphical element based on the determined visual context and the one or more additional contexts associated with the corresponding graphical element. The graphical elements in the source file are replaced with the replacement graphical elements to generate a replacement file. The replacement file is then rendered on a user device.

A radiographic imaging apparatus of the present disclosure includes an image outputter outputting a first radiographic image included in continuous radiographic images obtained by radiographic imaging of a subject, an image brightness information extractor obtaining brightness information from the first radiographic image, a first irradiation condition calculator determining a first irradiation condition based on the brightness information, an irradiation controller controlling a radiation dose based on the first irradiation condition, a second irradiation condition calculator determining a second irradiation condition based on a second radiographic image generated based on the first irradiation condition when an imaging site of the subject is fixed, and a dose reducer reducing or maintaining the radiation dose based on the second irradiation condition.

The invention relates to a method for determining an image mask for an image by means of segmentation, in particular for a mobile device that moves or is intended to move taking the image mask into account, comprising: providing a current image (204, 207) of an image data stream (200) comprising successive images, which in particular are or have been each captured by means of a camera of the mobile device; providing a most recent direct image mask (221, 223), wherein the most recent direct image mask has been obtained by performing a segmentation (220) of an earlier image (201, 203) of the image data stream, the earlier image being obtained earlier than the current image (204, 207); providing a cumulative optical flow (254, 257) that has been determined from the earlier image (201, 203) to the current image (204, 207);Determining a current image mask (264, 267) for the current image, comprising fitting the most recent direct image mask based on the cumulative optical flow; and providing the current image mask.

The present invention provides a head-mounted display device, an image display method, and an image display program that can change the displayed image depending on the person approaching the user. [Solution] The system includes a display unit 19 that displays real-world images and PC images presented during the user's work, an image acquisition unit 11 that acquires images of the user's surroundings, a person information acquisition unit 121 that acquires person information of people included in the surrounding images, and a display control unit 18 that determines whether or not there is a relationship between the person and the PC image displayed on the display unit 19 based on the person information, and controls the image displayed on the display unit 19 according to whether or not there is a relationship.

The application discloses a train brake pad abrasion detection system and a detection method, and relates to the field of train detection. The system comprises a trackside device, a field control mechanism and a remote control center, the field control mechanism is in communication connection with the trackside device and the remote control center respectively; the trackside device comprises an incoming line sensor, an offline sensor, a wheel sensor and an image acquisition device, the wheel sensor is located on both sides of the image acquisition device; the image acquisition device is provided with a plurality of image acquisition devices, which correspondingly acquire the images of each brake pad on the train axle and the wheel; the image acquisition device comprises a plane array camera and two angle lasers, the center lines of the light sections of the two angle lasers are parallel to the optical axis of the plane array camera, and are perpendicular to the ground. The application non-contactly carries out train brake pad image acquisition, train speed measurement, axle number statistics and non-contact train brake pad abrasion detection.

This image is used on the display screen of a cleaning robot when the cleaning robot is operating normally, and it changes continuously and repeatedly from "Image Diagram" to "Image Diagram 24 showing the changed state."

This application provides a method, apparatus, device, and storage medium for controlling the display of a 3D digital human. The method, applied to a 3D display device, includes: acquiring an image sequence of a digital human; wherein the image sequence is generated based on a phoneme sequence of a response speech to a target user's dialogue; mapping each facial image in the image sequence to the screen of the 3D display device based on a multi-view rendering table corresponding to the digital human, so as to adjust the displayed digital human when the response speech is played; the multi-view rendering table corresponding to the digital human is used to describe the pixels in the facial images mapped to each point on the screen. This enables the display of a dynamic, 3D digital human during dialogue, based on a multi-view rendering table, improving the stereoscopic effect of the digital human and enhancing the user's dialogue experience.

The present application discloses a data transmission method and apparatus, a computer device (8), a medium, and a product. The method comprises: (S201) acquiring a display image layer, wherein the display image layer comprises a transparency layer and a color layer; (S202) dividing the transparency layer of the display image layer to obtain a divided transparency layer; (S203) mapping and compositing the divided transparency layer to obtain M first RGB images, wherein M is an integer greater than 1; and (S204) splicing the M first RGB images with a second RGB image constituted by the color layer to obtain a target RGB image, and transmitting the target RGB image. In the present application, during transmission of the display image layer, operations such as dividing, mapping, and compositing are performed on the transparency layer comprised in the display image layer, so as to optimize a transmission mode of transparency layer information, thereby improving the efficiency, stability, and reliability of transparency layer information transmission.

There is described an artificial intelligence, AI, model arranged to receive a set of image data associated with an encoded image, the image being encoded using a codec that provides a base image and one or more enhancement layers so as to enable the generation of a plurality of versions of the image, wherein each version of the image has a different level of quality, the set of image data comprising: a thumbnail tile that provides a version of the image with a first level of quality; and one or more image tiles that provide a version of one or more regions of the image with a second level of quality.

According to one embodiment, provided is a chip recognition system that recognizes a chip on a gaming table in an amusement place having the gaming table, the chip recognition system including: a game recording apparatus that records, as an image, a state of chips stacked on the gaming table, using a camera; an image analysis apparatus that performs an image analysis on the recorded image of the state of chips; a plurality of chip determination apparatuses including at least a first artificial intelligence apparatus that determines a number of the chips stacked, using an image analysis result obtained by the image analysis apparatus; and a second artificial intelligence apparatus that decides a correct number of the chips stacked, when the plurality of chip determination apparatuses obtain different determination results for the number of the chips stacked.

The present invention makes it possible to obtain a highly accurate PET image in PET inspection without fixing a subject and while reducing a calculation cost. This image configuration device 1 acquires measurement data measured by a PET device 2 in time series, divides the measurement data into a plurality of frame data, generates an inverse-projection image from the frame data, generates a mask image in a frame by setting RoI by using segmentation from the inverse-projection image, derives the center of mass from the mask image, derives a main component vector of an inertia matrix obtained from the center of mass, configures a homogeneous transformation matrix composed of the center of mass and a rotation matrix, calculates the amount of change between the homogeneous transformation matrix in an initial frame and the homogeneous transformation matrix in an nth frame, and corrects a rotation matrix serving as a main component vector column component in accordance with continuity of motion so that the amount of change is minimized.

Embodiments described herein provide a system and method for subject-driven image generation. In at least one embodiment, the system receives, via a data interface, an image containing a subject, a text description of the subject in the image, and text prompts related to different depictions of the subject. The system encodes the image into an image feature vector via an image encoder. The system encodes the text description in the text feature vector via a text encoder. The system generates a vector representation of the subject based on the image feature vector and the text feature vector using a multimodal encoder. The system generates an output image based on the input, which is a combination of the text prompts and the vector representation, using a neural network-based image generation model.

This invention discloses a DLP-based anti-aliasing printing method, apparatus, device, and storage medium, relating to the field of 3D printing technology. It solves the problems of jagged edges and poor surface smoothness in existing DLP 3D printing devices. The specific technical solution is as follows: First, acquire at least one original slice image of the target model; then, read the image information of the at least one original slice image and perform cross-rendering on the image information to obtain at least one rendered slice image. The image information includes at least vertex, pixel, and size information, and the at least one rendered slice image is a slice image with a different resolution; finally, perform attribute interpolation on the at least one rendered slice image to obtain at least one anti-aliased slice image, which is a slice image with the same resolution and size. This invention improves the model edge information in the target model slice image, smooths the edge contour of each layer, and achieves an anti-aliasing effect.

An image processing method and apparatus. A de-warping circuit is configured to retrieve, in an ordered sequence, a plurality of de-warping matrices for remapping pixels of a first image from a distorted image space to a corrected image space, where the first image depicts a scene in the distorted image space. The de-warping circuit reads, into a memory buffer, blocks of pixels of the first image based at least in part on the order of the de-warping matrices, and generates a plurality of image tiles based on the blocks of pixels of the first image. Each of the image tiles is interpolated from one or more of the retrieved blocks using a respective one of the de-warping matrices. The de-warping circuit writes the plurality of image tiles to an external memory to produce a second image that depicts the scene in the corrected image space.