93 results about "Object Class" patented technology

In order to at least partially automatically control the braking of a vehicle (1), object data containing an object class (9) of an object (6) in an environment of the vehicle (1) is generated or received by means of a data processing system (3) of the vehicle (1). By means of the data processing system (3), environment data (10) which contains statistical traffic accident data relating to the environment and / or relating to environment conditions of the environment is generated or received. By means of the data processing system (3), control data relating to a braking intensity for a desired braking maneuver of the vehicle (1) is determined according to the object class (9) and the environment data (10), and at least one control signal for at least one brake actuator of the vehicle (1) is generated according to the control data.

In a method for training a neural network for detecting an object, geometric dimensions of a test object from an object class are captured, and during a time period, recordings of the test object are generated by a plurality of cameras. From the captured geometric dimensions and the generated recordings, occupancy maps are generated. By a radar device, a radar signal is transmitted, and a radar signal reflected by the test object is received. The transmitted radar signal and the received radar signal are mixed into a complex baseband to form a mixed signal. A complex four-dimensional mixed spectrum of the mixed signal is calculated. From the complex four-dimensional mixed spectrum, a first complex two-dimensional partial spectrum and a second complex two-dimensional partial spectrum are calculated. The occupancy maps and the partial spectra are fusioned to form training data. The training data are fed to the neural network.

A method and system is disclosed for tuning a machine learning classifier. An object class requirement may be provided and include rank thresholds. The object class requirements may also include a range goal that defines a minimum distance from the object the machine learning algorithm should not provide false positive results. A base classifier may be trained using a weighted loss function that includes one or more weight values that are computed using the one or more object class requirements. An output of the weighted loss function may be evaluated using an objective function which may be established using the one or more object class requirements. The one or more weights may also be re-tuned using the weighted loss function if the output of the weighted loss function does not converge within a predetermined loss threshold.

Included is a method for estimating distance, including: emitting, with at least one light emitter disposed on a robot, a light structure onto objects; capturing, with at least one image sensor disposed on the robot, images of the light structure emitted onto the objects; identifying, with a processor, the light structure within the images; determining, with the processor, positions of elements of the light structure within the images; determining, with the processor, a characteristic relating to the objects based on positions of elements of the light structure within the images; determining, with the processor, an object class of at least one object within the images based on a comparison between features of the object extracted from the images and an object dictionary comprising various object classes and their associated features; and instructing, with the processor, the robot to execute at least one action based on the object class identified.

A computer system and method for training a machine learning system to perform a classification task by dividing input data into one of a plurality of classes. The system is configured to receive training data for each class from which a representation of each class can be derived, wherein each class is described by a plurality of representations; process the training data to form, for at least one class, a first proxy for a relatively global portion of training data items and a plurality of proxies for different relatively local portions of training data items, each proxy corresponding to a representation of data belonging to the class. For each training data item, the system is configured to: evaluate a match between the training data item and the proxies; estimate the class of the training data item from the match rating; adjust the proxies by updating a weighting matrix to reduce the distance between the training data item and the proxies of the estimated class. Defining a plurality of proxies in this way can result in richer and more stable representations of object classes.

Methods for automated process monitoring, wherein - image data (4) depicting a scene are generated by means of a camera system (2); - by means of a computing unit (3) based on the image data (4) it is determined that objects (6a, 6b, 7a, 7b, 7c, 8, 9, 10, 11, 14) are located within a specified area (B1, B2); - by means of the computing unit (3) for each of the objects (6a, 6b, 7a, 7b, 7c, 8, 9, 10, 11, 14) based on the image data (4) one of at least two predefined object classes is determined; - using the computing unit (3) depending on the specific object classes, it is checked whether a predefined rule assigned to the area (B1, B2) is fulfilled; - by means of the computing unit (3) an output signal is generated depending on a result of the check; - using the computing unit (3) based on the image data (4) for each of the objects (6a, 6b, 7a, 7b, 7c, 8, 9, 10, 11, 14) one of at least two predefined sub-areas (B1.1, B1.1.1, B1.2, B2.1, B2.1.1, B2.2, B2.2.1) of the area (B1, B2) is determined within which the respective object (6a, 6b, 7a, 7b, 7c, 8, 9, 10, 11, 14) is located; and - the verification of whether the rule is fulfilled is carried out depending on the specific sub-areas (B1.1, B1.1.1, B1.2, B2.1, B2.1.1, B2.2, B2.2.1).

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a text-to-image model so that the text-to-image model generates images that each depict a variable instance of an object class when the object class without the unique identifier is provided as a text input, and that generates images that each depict a same subject instance of the object class when the unique identifier is provided as the text input.

The present disclosure relates to enabling active learning for object classification by an automotive vision system configured to perform visual perception tasks, based on which a vehicle is configured to perform at least one driving automation system feature. The automotive vision system determines one or more 3D bounding boxes and a corresponding object class within three-dimensional sets of automotive sensor data, which including at least one automotive camera frame, i.e. two-dimensional data, while a secondary vision system determines one or more 2D bounding box vectors for each automotive camera frame. Based at least on the one or more 2D bounding box vectors, a frame score is calculated for each automotive camera frame. Then, one or more automotive camera frames are provided to an oracle based on the corresponding frame scores. The oracle returns annotated camera frames, which may then be used to retrain the automotive vision system.

A semantic image segmentation (SIS) system includes: a semantic segmentation module trained to segment objects belonging to predetermined classes in input images using training images; and a learning module configured to selectively update at least one parameter of each of a localizer module, an encoder module, and a decoder module of the semantic segmentation module to identify objects having a new class that is not one of the predetermined classes: based on an image level class for a learning image including an object having the new class that is not one of the predetermined classes; and without a pixel-level annotation for the learning image.

The application relates to the technical field of artificial intelligence, and provides an object recognition method, device and equipment and a storage medium. Related embodiments can be applied to cloud technology, cloud security, artificial intelligence, intelligent transportation and the like, more model training samples are mined from massive data, and the prediction accuracy of a model for a user category is improved. The method comprises the following steps: extracting candidate object features from multiple candidate object information of a candidate object; performing object category possibility degree recognition on object extraction features obtained by fusing the candidate object features, to obtain a recognition possibility degree of the candidate object belonging to a target object category; clustering the object extraction features corresponding to the candidate object, to obtain a sub-extraction feature set corresponding to each clustering category; grouping candidate objects corresponding to the object extraction features in the sub-extraction feature set into a sub-object set; and selecting a representative object from the sub-object set based on the recognition possibility degrees of the candidate objects corresponding to the sub-object set.

A few-shot, unsupervised image-to-image translation (“FUNIT”) algorithm is disclosed that accepts as input images of previously-unseen target classes. These target classes are specified at inference time by only a few images, such as a single image or a pair of images, of an object of the target type. A FUNIT network can be trained using a data set containing images of many different object classes, in order to translate images from one class to another class by leveraging few input images of the target class. By learning to extract appearance patterns from the few input images for the translation task, the network learns a generalizable appearance pattern extractor that can be applied to images of unseen classes at translation time for a few-shot image-to-image translation task.

The invention relates to a space target attitude key point data set construction method and system based on an unreal engine. The method comprises the following steps: constructing a three-dimensional model of a space target, preprocessing the three-dimensional model, and importing the preprocessed three-dimensional model into the unreal engine; creating a user-defined marking component in the unreal engine for defining key points of the space target in the preprocessed three-dimensional model, and constructing a user-defined recognition object class for managing the key points of the space target; wherein the management comprises automatic detection, classified storage and sorting of key points of space targets; creating a space scene in the unreal engine, constructing an animation sequence used for simulating the motion trail and posture change of the space target in the space scene, and obtaining a plurality of space target images based on the animation sequence; and generating structured space target attitude key point data based on the space target image, and forming a space target attitude key point data set by taking the corresponding space target image as sample data and taking the extended marking attribute of the custom marking component as a sample label.

Embodiments of the present application provide an object classification method and device, terminal equipment and a storage medium, and relate to the technical field of data processing, which can quickly obtain accurate object categories. The method comprises the following steps: obtaining category information set by each business system of a plurality of business systems for a target entity to which a first object belongs, and matching a function attribute of the target entity; in a plurality of preset categories set in a local business system storing the first object, at least one first target preset category corresponding to each of the plurality of category information is queried; and the first object is classified according to the number of category information corresponding to each first target preset category.

The invention relates to a dynamic vision SLAM (Simultaneous Localization and Mapping) optimization method and device. A bounding box detection result is divided into a prior dynamic object detection box and a static object detection box according to semantic information in an RGB (Red, Green and Blue) image; motion consistency analysis is carried out on the prior dynamic object detection frame through an optical flow method, a first type of the prior dynamic object detection frame is determined, and the first type comprises a real dynamic object class and a static prior dynamic object class; determining a second type of a feature point according to the depth value of the feature point in the prior dynamic object detection frame of each real dynamic object class in the depth image, wherein the second type comprises a foreground point and a background point; calculating an initial pose result; and optimizing the initial pose result to obtain a final pose result. According to the method, the distribution characteristics of reprojection errors are analyzed in real time, and robust kernel function parameters are dynamically adjusted, so that the adaptability of an algorithm to a detection failure scene is enhanced, interference of non-Gaussian noise is effectively suppressed, and the positioning precision and robustness in a dynamic environment are improved.

This disclosure relates to object class inpainting in digital images using class-specific inpainting neural networks. The disclosure relates to systems, methods, and non-transitory computer-readable media for generating inpainted digital images using class-specific cascaded modulation inpainting neural networks. For example, the disclosed system utilizes a class-specific cascaded modulation inpainting neural network including a cascaded modulation decoder layer to generate replacement pixels depicting a specific target object class. For instance, in response to a user selecting a replacement region and a target object class, the disclosed system utilizes a class-specific cascaded modulation inpainting neural network corresponding to the target object class to generate an inpainted digital image depicting instances of the target object class within the replacement region. Furthermore, in one or more embodiments, the disclosed system trains class-specific cascaded modulation inpainting neural networks corresponding to various target object classes (such as sky object classes, water object classes, ground object classes, or human object classes).

The invention relates to an image generation method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring an indication text and a reference image containing a reference object; the expected object category included in the indication text is the same as the object category of the reference object; respectively carrying out feature extraction on the indication text and the reference image to obtain text features and semantic identity features and detail identity features of the reference object; the semantic identity features are semantic features related to the object category of the reference object; the detail identity features are detail features related to the object category of the reference object; fusing the object semantic identity feature and the text feature to obtain a fused feature; and generating a prediction image containing a target object based on the fusion feature and the detail identity feature, wherein the target object belongs to the expected object category. By adopting the method, the object identity accuracy of the target object in the predicted image can be improved.

The invention relates to a method for representing an additional information in an image of an environmental region (34) of a vehicle (10), containing contents that are represented by pixels on a display of a display device (16) of the vehicle (10), wherein the additional information is represented as overlay on top of the contents. Therein, a pixelwise classification of the contents is performed, wherein each pixel of the image is assigned to an object class. Then an assigning of a pixel value to each pixel depending on the object class and a storing of the pixel values is effected. Then the pixel values of the pixels within a region of the image to be currently overlaid by the additional information are determined and an overlaying of the additional information is effected only on top of pixels with pixel values within a predetermined range.

A media curation system configured to perform operations comprising: capturing an image at a client device, wherein the image includes a depiction of an object, identifying an object category of the object based on the depiction of the object within the image, accessing media content associated with the object category within a media repository, generating a presentation of the media content, and causing the presentation of the media content within the image to be displayed at the client device.

A method for generating training data for a machine learning model. The method includes: providing LIDAR point clouds, each of which is assigned to a point in time of a plurality of successive points in time, wherein each point of each LIDAR point cloud represents a particular object class of a plurality of object classes; for each LIDAR point cloud: ascertaining a transmission grid map in spherical coordinate space, wherein each voxel of the transmission grid map indicates how many rays pass through the voxel before they are reflected at a point in the LIDAR point cloud; ascertaining a reference transmission grid map in Cartesian coordinate space assigned to a reference point in time of the plurality of points in time; for each of the plurality of object classes: for each LIDAR point cloud, ascertaining a reflection grid map associated with the object class.

The invention relates to a method for displaying additional information in an image of an area (34) of a motor vehicle (10), which contains image content represented by pixels on a display surface of a display device (16) of the motor vehicle (10), wherein the additional information is displayed as a superimposition over the image content. The image content is classified at the pixel level, with each pixel of the image being assigned to a predetermined object class. A pixel value is then assigned to each pixel depending on the object class, and the pixel values ​​are stored. This is followed by determining the pixel values ​​of the pixels within an image area to be superimposed with the additional information, and superimposing the additional information only over those pixels whose pixel values ​​lie within a predetermined pixel value range.

The application discloses a kind of zero sample indoor robot vision navigation methods (CIRN) based on class-independent network, does not use original vision information as the state of reinforcement learning, but the target detection information under current vision is as state, relative semantic similarity between object and navigation target is used to represent different objects, and the information of multiple objects is sorted in descending order according to their relative semantic similarity.Compared with the preset object class number and fixed position of class in state matrix, the method of the application can be applied to all scenes, regardless of specific class.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate and implement behavioral policy graphs for digital image editing. For instance, in some embodiments, the disclosed systems generate, for a client device, a behavioral policy graph that assigns behaviors to object classes based on object relationships. The disclosed systems receive, from the client device, a digital image portraying a plurality of objects. Further, the disclosed systems determine behaviors of the plurality of objects utilizing the behavioral policy graph by determining, for each object of the plurality of objects, a behavior based on a relationship of the object with an additional object of the plurality of objects in accordance with the behavioral policy graph. The disclosed systems modify the digital image by modifying one or more objects based on the behaviors of the plurality of objects. 20 23 27 40 73 27 N ov 2 02 3 A B S T R A C T O F T H E D I S C L O S U R E 2 0 2 3 2 7 4 0 7 3 2 7 N o v 2 0 2 3

The present application belongs to the field of artificial intelligence computer vision, and particularly relates to a scene graph generation method based on a multi-level attention mechanism. First, a pre-trained target detection network is used to obtain object information in an image, and dynamic hierarchical prior knowledge is obtained from the image information, and on this basis, a multi-level attention structure is used to encode the existing object and object pair features, and finally the object category and relationship category are classified to obtain a scene graph. The present application constructs a clearer way to express the hierarchical relationship of objects, and effectively utilizes hierarchical attention, so that the generation of the result is more dependent on the sub-regions that have greater influence on it, thereby improving the accuracy of the result.

A method and system for detecting and avoiding an obstacle of an autonomous unmanned maritime vehicle (UMV) traveling in an initial direction are described. The method and system include receiving a video image from at least one image sensor, the video image containing an object that has been identified as an obstacle, determining if the object can be associated with an object class from the plurality of predetermined object classes, accessing a mean height value for the object class if it determined that the object can be associated with an object class from the plurality of predetermined object classes, determining a distance between the UMV and the object based on a height of the object as displayed in the video image and the mean height for the object class, and automatically adjusting the navigational control of the autonomous UMV to travel in an adjusted direction.

Embodiments of the present disclosure relate to data-driven automation provisioning for telecommunications applications. Systems and methods for constructing service templates that allow for agentless, data-driven, and stateful automation of provisioning of services to mobile network customers. Data associated with a request to create a target schema object class for a device and a protocol is received. Based on the device and protocol information, a set of data fields associated with CRUD semantics is retrieved from a database or from user-provided data. A decorated target object class is created based on the requested target schema object class. A sub-recipe is created that includes the decorated target object class and one or more other decorated target object classes. The recipe is processed for transmission to an execution engine to form a service instance that is customizable by an operator for a particular network device, such that service instance data fields that are not pre-populated are able to be customized by the operator.

Methods and systems are disclosed for generating an augmented reality (AR) video. A set of products is obtained, where each product is associated with a respective virtual model and a respective object class. An AR video segment is generated for each product in the set of products. In a real-world video segment, a real-world object belonging to a relevant object class that is relevant to the object class of the given product is detected. A render of the virtual model associated with the given product is overlaid in the real-world video segment to obtain the AR video segment. The render of the virtual model is overlaid relative to the detected real-world object belonging to the relevant object class. A continuous AR video is generated from the AR video segments and outputted to be viewable by a user device.

An intelligent camera system with integrated artificial intelligence for real-time object classification and adaptive function control, consisting of: an image sensor unit configured to capture successive image sequences of an observed environment; an optical assembly operationally coupled to the image sensor unit to project incident light onto a sensor surface; at least one processing unit that is arranged in a camera housing and electrically connected to the image sensor unit; a non-volatile memory that is operationally connected to the processing unit and configured to store executable instructions, trained object classification parameters, and control decision data; an image preprocessing unit, which is executed by the processing unit and is configured to normalize, filter, and align successive image frames in time; an artificial intelligence inference unit executed by the processing unit, configured to perform object classification in real time directly on the preprocessed image sequences using the stored trained parameters; a decision control unit executed by the processing unit, configured to generate adaptive control outputs based on classified object attributes such as object category, spatial position, motion properties, and confidence level; and A control interface unit electrically coupled to the decision control unit and configured to transmit adaptive control outputs to one or more functional components of a machine or structure, wherein all image acquisition, classification, decision making and control signal generation takes place locally within the camera housing, wherein the image sensor unit comprises a solid-state image sensor configured to operate at a variable frame rate, which is dynamically adjusted by the processing unit based on the detected scene complexity and object motion characteristics to maintain classification accuracy in real time while reducing the computational load.

This invention relates to a simulation method, apparatus, and computer device based on a general code framework. The method includes: editing an object description file; dynamically generating framework code for the general code framework based on the object description file; generating corresponding data structures in the framework code based on object class and interaction class information from the object description file; creating interface classes that inherit from simulation function classes; adding a simulation unit to a co-simulation; calling relevant interface class functions to send and receive object class data and interaction message data in the simulation progress callback; serializing and deserializing the simulation running data input and output by the co-simulation according to the data structures; and calling a stop simulation interface to terminate the simulation when the simulation stops. This method provides a modifiable and reusable code framework for the convenient integration and development of simulation units, enabling automatic invocation of simulation middleware services and reducing the difficulty and workload of integration and development.

This application provides an object category recognition method, display method, and apparatus based on a multimodal large model, relating to the field of artificial intelligence technology. The object category recognition method based on a multimodal large model includes: acquiring a first feature image and first text information of a first object; the first feature image includes an object attribute image and an environment image of the first object; analyzing the first feature image and the first text information using a pre-trained multimodal large model to obtain a first object category prediction result for the first object; identifying target elements in the first feature image to obtain a first identification result for the target elements; and determining the target object category of the first object based on the first object category prediction result and the first identification result. This application can improve the accuracy of object category recognition and provide visual evidence for the object category recognition results, thereby enhancing the credibility of the object category recognition results.