380 results about "Visual Objects" patented technology

A composite pose-estimation algorithm includes a video-object segmentation sub-algorithm (311) configured to determine a mask of a visual object in an image, and an object-pose tracking sub-algorithm (312) configured to track a pose of a visual object over multiple depth-video frames, wherein the pose-estimation algorithm is configured to input a depth video, from which frames are extracted and fed to the video-object segmentation sub-algorithm, which determines respective object masks to be used by the object-pose tracking sub-algorithm alongside the depth video. A method of tracking a pose of a physical object comprises: obtaining a depth video depicting a physical object in a plurality of poses from an input interface (330); forming a storable data item representing the physical object by applying the pose-estimation algorithm to the depth video; and tracking the physical object or a copy thereof using an instance of the pose-estimation algorithm which has been initialized by means of the storable data item.

A system and method for generating contextually relevant reply suggestions for media posts is disclosed. The system analyzes media content to identify visual objects, scenes, text, and metadata attributes using computer vision techniques. Identified objects and attributes are incorporated into structured prompt templates to construct detailed natural language descriptions of the media context. The prompts are provided to a text generation artificial intelligence (AI) that outputs a plurality of contextual reply suggestions based on the media analysis. Suggestions are displayed as selectable options adjacent to the media post. Users can cycle through suggestions and select a reply to send. Selections are logged to improve the AI model. Feedback on suggestion quality can also be collected. By integrating computer vision and AI generation driven by engineered prompts, the system produces highly relevant, personalized responses tailored to media content. The techniques enhance user engagement with media posts through intelligent AI reply suggestions.

The invention provides a science and technology information deep analysis method and system based on cross-modal semantic enhancement, and relates to the technical field of science and technology information analys.The method comprises the steps that firstly, a cross-modal semantic anchor point set is constructed, and the cross-modal semantic anchor point set comprises text theme anchor points extracted from science and technology information texts, visual object anchor points extracted from images and the association mapping relation of the text theme anchor points and the visual object anchor points; constructing a semantic conduction path between anchor points based on the cross-modal semantic anchor point set, realizing bidirectional information transmission, generating a cross-modal semantic enhanced representation, performing hierarchical semantic analysis on the enhanced representation to obtain a topic association rule, a technical element dependency relationship and a concept evolution sequence, and integrating the topic association rule, the technical element dependency relationship and the concept evolution sequence into an analysis conclusion; the analysis conclusion is reversely mapped to adjust the association mapping relation strength, an updated set is obtained, finally, a structured science and technology information analysis report is generated based on the updated set, logic connection of all modules is achieved, and comprehensive and accurate science and technology information analysis is provided for users.

The invention relates to the technical field of text verification, in particular to an intelligent text verification method based on a hybrid model knowledge graph, which comprises the following steps of: analyzing a document, separating a text from a visual object, and generating semantics and visual vectors by using a bidirectional encoder and a hybrid visual model; performing form normalization verification by constructing a self-adaptive template matrix; judging the semantic homology of the image-text content by using a cross-modal gating arbiter; the text is converted into a semantic fact triple mapped to a unified space-time coordinate system, and logic irregularity is detected in a domain knowledge graph based on ontology constraint; and finally, summarizing all results to generate a structured verification report. According to the method, cross-modal semantic understanding and knowledge graph reasoning are effectively fused, full-dimension intelligent verification of content forms, image-text semantics and deep space-time causal logic is achieved, and the depth and accuracy of large-scale digital content verification are remarkably improved.

The invention provides a passable area reasoning method and system based on a visual language model, and the method comprises the steps: obtaining the multi-modal data of a vehicle and the current position information of the vehicle; analyzing the multi-modal data, and determining visual features and traffic symbol features; performing spatial position coding on the visual object and the traffic symbol elements, and determining aerial view angle coordinate information; performing semantic alignment on the visual features and the traffic symbol features, and determining a shared embedding representation; constructing a traffic semantic map by fusing, sharing and embedding representation based on a graph neural network and bird's-eye view coordinate information of a visual object and a traffic symbol element; and according to the current position information of the vehicle, the traffic semantic map and a preset traffic rule, generating a bird's-eye view semantic map including a passable area, a no-pass area and a semantic association relationship. According to the method and the device, semantic alignment and consistency expression of visual perception and traffic symbol recognition are realized, and further feasible region reasoning of a complex traffic scene is realized.

The present invention relates to a computer-implemented of controlling an electronic device with a display and a user input. The method includes the steps of: displaying a first visual object within a graphical user interface; wherein the first visual object comprises a plurality of first visual elements, and wherein the first visual elements are displayed in a first visual state in a ring within the graphical user interface; detecting a first user input event at one of the first visual elements; in response to the first user input event, displaying a second visual object within the graphical user interface; wherein the second visual object comprises a plurality of second visual elements, and wherein the second visual elements are displayed in a ring surrounding the first visual object within the graphical user interface; detecting a second user input event at one of the second visual elements; and, in response to the second user input event, controlling the electronic device to access functionality associated with the second visual element. An electronic device and a computer program are also disclosed.

According to an embodiment, a wearable device may display, based on contact on a second surface identified using a touch sensor, a visual object indicating a first position of the touch input on the second surface in a screen through a display. The wearable device may identify, in response to the touch input, a second position in the screen of a gaze identified based on an image obtained through a camera exposed outside at a portion of a first surface. The wearable device may provide, in response to the second position identified within a specified distance from the first position of the visual object, feedback with respect to the touch input. The wearable device may cease to provide the feedback in response to the second position identified outside from the first position by the specified distance.

The invention relates to a visual dialogue method and device based on external knowledge enhancement and semantic consistency, and the method comprises the steps: constructing a multi-modal scene graph through extracting the incidence relation between intra-domain visual objects and the incidence relation between intra-domain text vocabularies according to an obtained image, a historical dialogue text and a current question text, constructing a common sense knowledge base by extracting common sense knowledge triples; based on the common knowledge base, expanding the multi-modal scene graph and carrying out relation reinforcement learning to obtain characteristics of associated reinforcement nodes; obtaining instance-level representation by using a pre-trained large language model, obtaining text common sense-level representation based on the characteristics of the association enhancement node, and performing characteristic fusion for the instance-level representation and the common sense-level representation to obtain global fusion characteristics; and based on the fusion feature, obtaining an answer of the visual dialogue through reasoning. According to the method, semantic association can be carefully mined, so that the accuracy, richness and comprehensiveness of multiple rounds of visual dialogues are remarkably improved.

The invention discloses a cigarette end surface defect detection method based on visual target detection, and the main design concept of the invention is that the method mainly comprises the steps: collecting original data of a cigarette end surface, carrying out the preprocessing of an original image, and segmenting the original image to obtain a cigarette end surface image; in combination with the scene characteristics of actually shooting the cigarette end face, expanding and reinforcing the cigarette end face image to obtain diversified cigarette end face visual samples; marking the cigarette end face visual sample and then training a target detection model based on deep learning; the trained target detection model is used for detecting a cigarette end face real-shot picture collected in the production process in real time, and the detected end face defects are subjected to quantitative characterization and then are subjected to score estimation. Compared with a traditional image processing method and a machine vision system, a new solution is provided for cigarette end face defect detection, and the dual requirements of a high-speed production line for detection precision and real-time performance can be met.

An indoor navigation method is provided, including: receiving an instruction for navigation, and collecting an environment image; extracting an instruction room feature and an instruction object feature carried in the instruction, and determining a visual room feature, a visual object feature, and a view angle feature based on the environment image; fusing the instruction object feature and the visual object feature with a first knowledge graph representing an indoor object association relationship to obtain an object feature, and determining a room feature based on the visual room feature and the instruction room feature; and determining a navigation decision based on the view angle feature, the room feature, and the object feature.

An interactive computer-implemented system manages a virtual deck of digital cards whose attributes, such as value, status, score, or color, refresh continuously in response to live external data. A server-side ingestion pipeline normalizes event feeds and maps them to a programmable card object model executed on one or more processors. A rendering engine delivers sub-five-second visual updates, while a synchronization layer broadcasts state changes to all connected clients to maintain uniform gameplay. A rules-based constraint engine recalculates permissible user actions as card states evolve, preventing pre-event optimization and preserving competitive fairness. The architecture is device-agnostic, supports accessibility overlays, and extends beyond fantasy sports to any domain where real-time data drives interactive visual objects.

The invention discloses a visual target detection method and device based on vector quantization uncertainty perception, and the method comprises the steps: collecting image data in an open scene as original data, marking the collected original data according to the category, and taking the marked original data as an initial task data set; training a target detection model on the initial task data set, wherein the target detection model comprises a target detection module, a vector quantization module and an uncertainty perception label distribution module; a new category of interest is screened from the explored unknown objects, and image data is collected and marked to serve as a new task data set; meanwhile, selecting a part of samples from the old task data set as a playback sample set; and finely adjusting the target detection model on the new task training set and the old task playback set to realize continuous expansion and evolution of visual target detection. The device comprises a processor and a memory.

An electronic device may include: a display; a camera; a speaker, a micro array comprising a plurality of microphones; and a processor. The processor may identify a position of an external object shown through the display on the basis of an image obtained by the camera. The processor may control the microphone array on the basis of the identified position and obtain an acoustic signal generated by the external object. The processor may interlock with the external within the display on the basis of the acoustic. signal and display a visual object for adjusting a volume of the acoustic signal. The processor may output an audio signal associated with the acoustic signal through the speaker in response to an input received on the basis of the visual object and ensuring adjustment of the volume. An electronic device according to an embodiment may comprise: a display; a camera; a speaker, a micro array comprising a plurality of microphones; and a processor. The processor may identify a position of an external object shown through the display on the basis of an image obtained by the camera. The processor may control the microphone array on the basis of the identified position and obtain an acoustic signal generated by the external object. The processor may interlock with the external within the display on the basis of the acoustic signal and display a visual object for adjusting a volume of the acoustic signal. The processor may output an audio signal associated with the acoustic signal through the speaker in response to an input received on the basis of the visual object and ensuring adjustment of the volume.

Exemplary embodiments of the present disclosure are directed towards a method for detecting and identifying container number in real-time. Monitoring vehicle carrying containers and triggering first camera, second camera, third camera, fourth camera, fifth camera, and laser sensors to capture container views by pre-processing module. Transmitting containers image data to computing device by the pre-processing module. Detecting container number region in container image frames by visual object detection module. Cropping container number region by visual object detection module. Applying two-dimensional Fast Fourier Transform on cropped container number region. Segmenting each character situated in container number region by segmentation and character classification module. Classifying each character situated in container number region by segmentation and character classification module. Arranging characters in order based on relative positions of characters to obtain container number information by segmentation and character classification module. Aggregating container image frames and generating container number by post-processing module.

The invention relates to a visual target tracking method and device based on efficient sequence generation and electronic equipment, and the method comprises the steps: carrying out the processing of an obtained search image, a template image and a randomly initialized tracking mark, and obtaining search visual embedding and template visual embedding; the method comprises the following steps: performing position coding after search, template visual embedding and tracking mark connection, then coding a position coding result by adopting an encoder based on a visual transformer framework, and processing a tracking mark coding feature by adopting a tracking prediction head to obtain a target tracking prediction result; if the target tracking prediction result meets a preset condition, taking the target tracking prediction result as a target tracking result; otherwise, decoding the coding structure by adopting a transformer decoder; and processing by adopting a tracking prediction head according to a decoding result to obtain a target tracking result. By adopting the method, the forward reasoning speed is increased, and the tracking speed is increased.

The invention provides a method and a system for generating a dynamic image in real time based on dialogue content, and electronic equipment. Determining interaction parameters such as an interaction theme, an emotional tendency quantized value, interaction time, an interaction position and an interaction role corresponding to the voice signal and an interaction task preset according to the interaction position, and then determining a visual element combination matched with each parameter in the interaction parameters according to the interaction parameters; and generating a moving dynamic image based on each visual object unit designed in advance according to each interaction parameter in the interaction scene in the visual element combination. Mapping the dynamic image to an LED array used for displaying, and controlling the state change of the corresponding LED light-emitting units in the LED array according to the pixel position of the dynamic image. By means of the method and device, man-machine interaction conversation around participants in the interaction process can be achieved, matched dynamic images are generated in an accompanying mode, and more immersive interaction experience is provided for the participants.

There is provided mechanisms for visual object detection in a sequence of images. A method is performed by a visual object detector (200). The method comprises obtaining (S102) a sequence of images of a scene. The sequence of images at least comprises a current image of the scene and a previous image of the scene. The method comprises extracting (S104) a set of objects from the sequence of images by performing visual object detection in the sequence of images. Performing the visual object detection in at least part of the current image is conditioned on a set of conditions being fulfilled. The set of conditions at least pertains to an image-wise descriptor classification score computed for at least one of the previous image and the current image and pertaining to which type of content the scene comprises, and an image overlapping score pertaining to how much overlap in image area there is between the previous image and the current image. The method comprises constructing (S106) an image representation of the scene using the extracted set of objects.

Techniques and apparatuses enabling high accuracy video object detection using reduced system resource requirements (e.g., reduced computational load, shallower neural network designs, etc.) are described. For example, a search domain of an object detection scheme (e.g., a target object class, a target object size, a target object rotation angle, etc.) may be separated into subdomains (e.g., such as subdomains of object classes, subdomains of object sizes, subdomains object rotation angles, etc.). Specialized, subdomain-level object detection / segmentation tasks may then be separated across sequential video frames. As such, different subdomain-level processing techniques (e.g., via specialized neural networks) may be implemented across different frames of a video sequence. Moreover, redundancy information of consecutive video frames may be leveraged, such that specialized object detection tasks combined with visual object tracking across consecutive frames may enable more efficient (e.g., more accurate, less computationally intensive, etc.) full domain object detection and object segmentation schemes.

The present invention belongs to the fields of machine learning and visual object tracking, and provides a visual single-object tracking method assisted by motion information. The present invention models the camera motion and the target motion during the tracking process respectively. For the camera motion modeling method, the present invention uses a feature point matching algorithm to calculate the transformation matrix between adjacent frames, and gives the target offset caused by the camera motion. For the target motion modeling method, the present invention uses a convolutional long short-term memory network to estimate the future speed and position of the target through the target historical motion information. After introducing motion information for assisted tracking, the present invention can significantly improve the ability of the tracking algorithm to cope with challenges such as illumination changes and occlusions, enhance the robustness of the tracking algorithm, and has a low computational amount, capable of meeting the real-time tracking requirements.

The electronic device according to various embodiments include a memory configured to store instructions and at least one processor configured, when executing the instructions, to obtain a first video sequence including a visual object corresponding to a body; obtain a local posture sequence of the visual object that indicates postures of at least one visual element of the visual object in the first video sequence, the at least one visual element of the visual object corresponding to at least one joint of the body; obtain a global motion sequence of the visual object, based on a difference between the postures of the at least one visual element, the postures of the at least one visual object obtained by using the local posture sequence; and obtain a second video sequence, based on the local posture sequence and the global motion sequence.

The invention discloses a visual target tracking method based on natural language and target state information. The method comprises the following steps: (1) constructing a training sample set; (2) constructing a visual target tracking model based on a natural language and target state information; step (3), adjusting parameters of an image-text encoder and loading a pre-training weight to obtain a feature after the text and the first template are fused, a feature of the second template and a feature of the search image; (4) fusing the position information of the target in the sample set and the bounding box information of the target into the features of the second template; step (5), obtaining features after joint modeling; step (6), acquiring a token containing target position information after query; (7) obtaining a predicted target bounding box regression result; and (8) obtaining a final tracking result. According to the invention, the tracking accuracy of the visual tracker based on the natural language is effectively improved.

According to various embodiments, an electronic device include a display, an input circuit, at least one memory and at least one processor configured to obtain a first image; display, in response to cropping an area comprising a visual object corresponding to a potential vehicle appearance from the first image, fields for inputting an attribute for the area, wherein, the fields include a first field for inputting a vehicle type as the attribute and a second field for inputting a positional relationship between a subject corresponding to the potential vehicle appearance and a camera obtained the first image as the attribute; obtain information about the attribute, by receiving a user input for each of the fields including the first field and the second field through the input circuit; store a second image configured of the area in a data set for training a computer vision model for vehicle detection.

Systems and methods of detecting activity at point of sale are provided. In one exemplary embodiment, a method is performed by a POS system having first and optical scanner devices. The optical sensor device is positioned on or about the POS system with a field of view directed towards a first spatial region of the POS system and operable to capture successive images. The optical scanner device is positioned on or about the POS system with a field of view directed towards a second spatial region disposed within the first spatial region and associated with scanning visual object identifier codes disposed on objects and operable to scan those visual object identifier codes. The method includes receiving, from the optical sensor device, a set of successive images associated with the first spatial region to enable detection of activity in or about the second spatial region.

A method of a wearable device, includes: in a first state for displaying a first image of a camera of the wearable device: identifying types and positions of external objects included in the first image, displaying, on a display, a second image comprising visual objects corresponding to the identified types and arranged with respect to the external objects, identifying an input for changing to a second state for providing a virtual reality, and in the second state for displaying, on the display, at least a portion of a virtual space, changed from the first state based on the input: maintaining displaying of a first visual object corresponding to a first external object from among the visual objects, based on identifying the first external object that is spaced apart below a threshold distance from the wearable device from among the external objects.

An electronic device displays, in an unfolded state of the electronic device, a screen on a flexible display, based on data detected by one or more sensors. The unfolded state is distinguished by an angle between a first side and a second side of a foldable housing in which the flexible display is disposed. A visual object is displayed for selecting at least a portion of the screen to be displayed on a cover display, in a sub-folded state of the electronic device that is switched from the unfolded state, based on the data. An input selecting at least a portion of the screen is received based on the visual object. In the sub-folded state, within the cover display, the at least a portion of the screen selected by the input is displayed, in response to an input identified based on the received input.

The invention discloses a space-time correlation visual target tracking algorithm based on multi-level feature aggregation, which comprises the following steps of: inputting a video clip consisting of a time token, a reference frame and a search frame into a feature extraction network taking ViT-Base as a basic structure to capture a long-distance global context in a video, and extracting multi-level time token and search frame features; for a multi-level time token, features of different levels are aggregated by adopting a bidirectional strategy, then a learnable time token combined with Fourier transform is introduced, and noise interference caused by multi-level aggregation is suppressed and target features are enhanced by emphatically paying attention to multi-level frequency characteristics of the time token from a shallow layer to a deep layer. Attention features of different levels and axial directions are calculated and fused by using a multi-level cross-axis attention mechanism for search frame features, so that richer target feature representation is obtained. And finally, aggregating the multi-level time tokens and the search frame features by using self-attention, and sending the aggregated features to a prediction head network to realize target tracking.

The present invention relates to a communication maintenance tool identification method based on YOLO V5, and belongs to the technical field of communication maintenance tool identification. The method of the present invention uses MOT semi-automatic annotation tool and VoTT visual object annotation tool to annotate communication line maintenance tool samples, generate a dedicated data set, and has practical value in the field of communication; the YOLO V5 model is improved by using attention mechanism, and the improved YOLO V5 model is used to perform data enhancement and model training on the communication line maintenance tool data set to improve detection efficiency and recognition accuracy; OpenVINO is used to optimize and accelerate model reasoning to improve detection speed; by deploying to a portable mobile terminal Raspberry Pi to perform real-time detection and result display of communication line maintenance tools, the current communication line maintenance tool identification problem is better solved, and the communication operation provides convenience for classification, storage and selection of communication line maintenance tool identification.

A method executed by a wearable device including a display system including a first display and a second display facing eyes of a user wearing the wearable device, and a plurality of cameras configured to obtain an image including the eyes, includes: displaying objects at different time points on a screen of the display system, based on the image, identifying gazes looking at the objects, identifying, based on the identified gazes, errors associated with the gazes, wherein the errors indicate differences between display positions of the objects and focal positions of the gazes, and wherein the focal positions have a one-to-one correspondence with the objects, displaying a visual object on a background screen on the display system to move the visual object through partial display positions of the display positions, which are selected based on the errors, and based on another gaze looking at the visual object, correcting the errors.

The invention discloses a method and a system for identifying a multi-modal named entity, and belongs to the technical field of digital data processing. In order to solve the technical problems that in the prior art, when images and text information are processed, shared information and private information are sequentially connected in series, and the shared information and the private information of visual objects in the images are directly connected in series, so that feature information confusion is caused, fine-grained alignment in visual modes is influenced, and cross-modal understanding of a GMNER system is influenced. The shared visual features and the private visual features of the image are extracted respectively, the features of the visual objects in the image and the relation features between the visual objects are distinguished, and then the images are dynamically integrated and projected to the text embedding space, so that the corresponding relation between the visual object entities and the text entities is clearer, and the text embedding efficiency is improved. And the accuracy of fine granularity alignment is improved, so that the comprehensive cross-modal understanding capability of the GMNER system is improved. The method is mainly used for multi-modal named entity recognition.