161 results about "Learning object" patented technology

The invention discloses a manipulator grabbing method based on deep learning target detection and image segmentation, and relates to the technical field of artificial intelligence and robotics.The manipulator grabbing method comprises the following steps that a scene image to be processed is collected, the image quality is improved through the multi-light-source fusion image enhancement technology, and recognition errors caused by uneven illumination are reduced; and inputting the enhanced image to a pre-trained deep learning model, executing a target detection task, and outputting an initial bounding box and a category label of the target object. According to the method, through multi-light-source image enhancement and high-precision image segmentation, the accuracy of target recognition and contour extraction is remarkably improved, and the capture failure rate caused by image misjudgment is reduced. And meanwhile, geometric consistency verification and a multi-factor grabbing scoring mechanism are introduced, dynamic screening and collision pre-detection are conducted on the paths, the grabbing stability and safety of the mechanical arm in the complex environment are effectively guaranteed, and the intelligence and robustness of the whole system are remarkably improved.

The invention discloses a multi-view panoramic point cloud splicing method, which comprises the steps of performing joint calibration on a binocular camera and a laser radar through a calibration algorithm, and aligning a coordinate system; a binocular camera is used for collecting a two-dimensional image and carrying out distortion correction, a depth map is generated based on parallax calculation, and three-dimensional point cloud reconstruction is carried out in combination with a triangulation principle; performing deep learning target detection on the two-dimensional image, and screening a line rod assembly area through non-maximum suppression; multi-view point cloud data are collected through a laser radar, point cloud segmentation processing is carried out, and a telegraph pole assembly point cloud subset is reserved; matching the two-dimensional pixel area of the telegraph pole assembly with a laser radar point cloud projection result, and screening point cloud data belonging to the telegraph pole assembly; and carrying out alignment and fusion on the multi-view point clouds through initial registration and fine registration by adopting an improved point cloud splicing algorithm to generate a panoramic point cloud image. According to the method, the point cloud splicing processing time is shortened, and the robustness, precision and integrity of point cloud splicing are improved.

The invention discloses a video analysis-based electric power operation personnel behavior identification and early warning system and method, which realize accurate identification and real-time early warning of electric power operation personnel behaviors by combining a video analysis technology with multi-modal data fusion, and effectively improve the safety management level of an operation site. Compared with a traditional safety supervision mode, the method employs a mode of combining deep learning target detection and time sequence behavior analysis, improves the recognition accuracy of operators and safety equipment, fuses the data of equipment worn by the operators with video data, improves the detection precision, and improves the safety supervision accuracy. And misjudgment caused by illumination change, shielding or complex environment is reduced. Besides, high-risk violation behaviors such as no safety helmet wearing, no safety belt fastening, violation climbing, high-altitude object throwing and the like are accurately recognized through the violation detection module, and different levels of alarm measures are adopted according to the severity of the violation behaviors in combination with an early warning feedback mechanism, so that the pertinence and response efficiency of early warning are improved.

The invention provides a data center inspection robot monitoring analysis method and system based on machine vision, and relates to the technical field of inspection robots, and the method comprises the steps: obtaining a video stream and environment parameter data collected by an inspection robot, and carrying out the detection and recognition of an abnormal state through a deep learning target; and constructing a multi-modal data fusion analysis model to form a knowledge graph to generate a root cause analysis result, and planning an inspection path based on priority scores. According to the invention, intelligentization and precision of data center monitoring are realized, and inspection efficiency and fault diagnosis accuracy are improved.

The invention provides a moving target intelligent detection method and system based on weak supervision dynamic optimization, and the method comprises the steps: respectively extracting video features and text features from an original video and a text, carrying out the fusion, and generating a frame-level semantic similarity score as a pseudo tag; utilizing learnable object query and fusion feature interaction to generate positive and negative proposal masks; guiding feature comparison learning of the positive proposal by using a pseudo tag, so that the positive proposal infinitely fits text features in a semantic space, and the negative proposal infinitely deviates from a related region of the text features; performing text reconstruction based on a mask condition Transform by using positive and negative proposal masks, and performing semantic consistency training on different proposals to obtain a video time domain positioning result; and dynamically optimizing a video time domain positioning result, generating a final positioning result, and completing intelligent detection of the moving target. According to the invention, by constructing a learnable negative proposal and a dynamic pseudo-label constraint mechanism, the time domain positioning precision under a weak supervision condition is significantly improved.

A computing system is disclosed for classifying rendered learning-object content and generating structured metadata representing competency and depth-of-knowledge attributes. The system detects rendered instructional content within a user interface and generates a cryptographic hash of the content, which is encrypted with session metadata to form a classification request. The request is transmitted to a remote categorization engine, where the content is processed using embedding models and inference classifiers to determine one or more competency labels, knowledge depth values, and confidence scores. The classification result is encrypted and returned to the client device for interface rendering. Classification records, including feedback interactions and associated metadata, are stored for use in model retraining.

The invention provides a teaching strategy generation method and device, and relates to the technical field of computers, in particular to the technical fields of natural language processing, operational research, decision science and the like. The specific implementation scheme is as follows: acquiring behavior interaction data of a learning object in a learning collaborative activity at a current stage; based on the collaborative transformation model behavior interaction data, a current collaborative transformation model of the collaborative transformation model learning object is updated, and the collaborative transformation model is used for representing a rule that a collaborative learning state is transformed along with time when the collaborative transformation model learning object participates in learning collaborative activities; based on the cognitive load information, a multi-objective function of a collaborative transformation model is determined, and the multi-objective function of the collaborative transformation model is used for representing a corresponding relation among a teaching strategy, a collaborative learning state transformation effect and cognitive load cost; and obtaining a target teaching strategy of the next stage based on the constraint condition of the collaborative transformation model and the multi-objective function.

The invention discloses a deep learning target detection and counting optimization method in a low-light environment, which runs in a GPU (Graphics Processing Unit) and comprises the following steps of: acquiring image data of an area needing to be detected by using a monitoring camera, then preprocessing the acquired data, and dividing into a training set, a test set and a verification set; training a YOLO11 target detection model, and respectively training a model of the to-be-detected area and a detection model of the drill rod in the detection area; and deploying a reasoning low-light compensation model and a target detection model to realize a counting task. According to the invention, a deep learning small target detection algorithm adapting to different illumination conditions is realized, a more efficient and more accurate target counting task is realized in actual production, and the production efficiency and the quality control level are further improved.

A system includes a learning object storing section that stores objects to be learned, a learning result storing section that stores learning results, and a control section connected to an input section. The control section computes a principal component coefficient vector of a first feature vector of an object to be processed that is designated by the input section, computes a principal component coefficient vector of a second feature vector using a principal component basis vector stored in the learning result storing section, and computes the second feature vector of the object to be processed using the principal component coefficient vector of the second feature vector.

The invention discloses a target-driven navigation method and device based on context awareness and imitation learning, and the method comprises the steps: recognizing an object instance of interest in an image based on a target detector DETR, and constructing an object graph; based on context perception graph reasoning, in the navigation process, dynamic context information such as images, actions and memories serves as guidance, object features are projected to hyperplanes of corresponding contexts by means of a TransH method at each time step, the object relation is dynamically learned, and an intelligent agent can better understand the complex environment. Based on visual representation of Transform, visual features and graph features are fused, and spatial semantic information of the environment is better captured. Based on generative adversarial imitation learning, a new dynamic reward function is designed, and an intelligent agent is helped to avoid a deadlock state in combination with environment rewards. Based on a standard asynchronous dominant actor-commentator algorithm, an effective navigation strategy is trained by using a new reward function, and the navigation success rate and efficiency of the intelligent agent in an unfamiliar environment are improved.

A method includes a computing device of a computing infrastructure identifying a non-fungible token (NFT) associated with a set of learning objects and establishing, with a user computing device, agreed licensing terms utilizing licensee information and based on available licensing terms of a smart contract for the set of learning objects. The method further includes generating a license smart contract for the set of learning objects to include the licensee information and the agreed licensing terms and causing generation of a license block affiliated with the NFT via a blockchain of the object distributed ledger.

The present invention discloses a pipeline defect detection, positioning and ranging system based on binocular stereo vision, including a binocular camera image capture module for capturing and collecting image data of the left and right cameras; a camera calibration module for establishing a camera imaging geometric model and correcting lens distortion, and outputting internal and external camera parameters and distortion coefficients; a stereo rectification module for achieving coplanar row alignment of the left and right images, making the left and right image planes parallel to the baseline, and corresponding points in the left and right images on the same horizontal epipolar line; a deep learning object detection module for training a deep learning network based on an object detection algorithm to achieve detection and recognition of pipeline defects; and a stereo matching and depth calculation module for achieving positioning and ranging of pipeline defects. It can achieve non-contact measurement of pipeline defects, and has the advantages of a wide monitoring range, good real-time performance, high accuracy, and accurate positioning.

The invention discloses a learning path optimization method and system based on machine learning, and the method comprises the steps: collecting the learning data of a learner, and enabling the learning data to comprise a learning object and the information of the learner; establishing a double-layer knowledge graph according to the knowledge type of the learning object; collecting behavior information data of the learner, evaluating a learning style of the learner user according to the behavior information data of the learner, and analyzing and dynamically calculating a learning ability value of the learner and a difficulty value of learning resources in real time according to the learning behavior information data; according to the ability value of the learner, the difficulty value of the learning resource and the information of the learner, generating an optimal learning path by utilizing a double-layer knowledge graph, monitoring the current learning duration, score and participation degree change of the learner in real time, and circularly feeding back and updating the learning path, so that the learning efficiency is improved. And higher-quality and more personalized learning path recommendation is provided for learners.

Disclosed is a system to generate an adversarial pattern. The system receives an input specifying data describing a target object, an objective indicating whether to reduce detectability of the target object or to induce a false detection of a target type, and context parameters. The system generates candidate adversarial patterns for the target object using an AI-based generative algorithm. Each candidate adversarial pattern represents a potential solution for achieving the objective under context parameters. The system simulates a representation of the target object with candidate adversarial pattern in a virtual environment that models a plurality of sensor modalities. The simulation may use machine learning object detection models. The system analyzes the target object and generates, for each target object, a performance metric for ranking the candidate adversarial pattern based on an effectiveness of the simulated representation. The candidate adversarial pattern with highest rank is generated as an optimized adversarial pattern.

The invention relates to a monocular 3D target detection method and system based on comparative learning. The method comprises the following steps: S1, performing feature extraction on a monocular image by using a backbone network to obtain a multi-scale feature map; the weight of the backbone network is obtained through a self-supervised training stage; s2, performing visual encoding by using a visual encoder to obtain an encoded visual feature; a depth predictor and a depth encoder are used in sequence to carry out depth coding on the sum to obtain coding depth features; s3, inputting the learnable object query, the coding visual features and the coding depth features into a visual-depth decoder to obtain a final query after learning; s4, mapping the final query into 3D information by adopting a detection head; and obtaining a 3D bounding box of the corresponding target. According to the method, the precision and robustness of 3D target detection are improved.

The present invention relates to an image inspection device and a setting method for an image inspection device. In order to enable easy additional learning of non-defective product images or defective product images in both the setting mode and the operation mode. A designation related to whether to additionally learn the inspection object image displayed on the operation mode screen as a non-defective product image or a defective product image is received. The discriminator generation unit additionally learns the inspection object image designated as the additional learning object as a non-defective product image or a defective product image, and updates the discriminator.

The present disclosure provides a training method for a blind image super - resolution model, a blind image super - resolution method, an electronic device, a storage medium, and a program product. The blind image super - resolution model includes a degradation feature estimator for determining the degradation features of a blind image, an image feature correction module for correcting the image features of the blind image according to the degradation features, and an image reconstruction module for reconstructing a high - definition image based on the corrected image features. The training method includes: performing a first - stage training on the degradation feature estimator to be trained by using a contrastive learning method based on degradation prior constraints to obtain a first degradation feature estimator; performing a second - stage training on the blind image super - resolution model including the first degradation feature estimator to obtain a teacher model; using the teacher model as the learning object and performing a third - stage training by using a distillation learning method to obtain the final blind image super - resolution model. This method can obtain a low - complexity model, which is suitable for low - computing - power devices.

An information processing device acquires a learning image in which a subject for learning and a color chart appear. The information processing device calculates a correction coefficient for correcting a color appearing in the color chart in the learning image to a reference color as a reference. The information processing device generates learning data in which an image of a portion of the subject for learning in the learning image is associated with the correction coefficient. The information processing device generates a trained model that outputs a correction coefficient for correcting a color of an image in which a subject appears in response to an input of the image based on the learning data.

The invention relates to a self-learning method of a robot with a body based on a pseudo tag and a robot with a body system. The method comprises the steps of generating a state pseudo tag and a component pseudo tag about a to-be-learned object based on interactive multimedia data between a robot with a body and the to-be-learned object; generating a cross-view pseudo-tag about the to-be-learned object based on the state pseudo-tag, the component pseudo-tag and the interactive multimedia data; performing motion simulation on the to-be-learned object based on the interactive multimedia data to obtain simulation multimedia data of the to-be-learned object, and generating an enhanced pseudo tag about the to-be-learned object based on the simulation multimedia data; and verifying the state false label, the component false label, the cross-view false label and the enhanced false label, and training the robot with the body based on the false labels passing the verification. By adopting the method, the richness of the pseudo labels can be improved, and the success rate of interaction tasks of the robot with the body is further improved.

The invention discloses a multi-task learning target tracking method and system based on domain self-adaption, and the method comprises the steps: taking a first frame image provided by a sample video sequence as the image data of a source domain and a target domain, employing a large and small target decision mechanism, carrying out the online selection of the scale of a model, and carrying out the feature extraction of the image data through a deep network; establishing a multi-task learning objective function fusing shallow and deep features; regarding a target tracking task as a field adaptive optimization problem under a multi-task learning framework, constructing a global target function fusing cross-domain sparse reconstruction constraint, multi-task loss and field adaptive loss, and obtaining a model after adaptive target tracking demand optimization; utilizing the optimized model to construct a likelihood function to obtain the probability density of the target position; determining a final tracking result of the target according to the probability density, the historical information and the predicted position of the linear motion model; according to the method, the accuracy and robustness of target tracking are effectively improved, and the method has relatively high application value and practicability.

A mapping, which is as a subject of learning, is a learning model that uses a sound signal as an input variable and outputs a variable indicating the cause of a sound in a vehicle. A learning method includes a signal correction process that corrects a sound signal by superimposing a noise signal on the sound signal, and an update process that updates the mapping through machine learning in which the sound signal corrected in the signal correction process serves as training data and a cause of a sound paired with the sound signal serves as teaching data.

This invention proposes a 3D semantic scene completion method based on hierarchical grouping and aggregation. The model proposes a novel dual-branch structure. The explicit constraint branch starts with the overall 3D scene features, focusing on regional aspects of the scene and aggregating explicitly similar features into grouped regional features. The implicit diffusion branch starts with the visible voxel query suggestions output by the query suggestion network, focusing on the details of objects in the scene and learning the implicit fine-grained features of the objects. A hierarchical grouping module is also proposed, which divides the 3D space into multiple sub-regions and performs similarity calculation and aggregation on the voxel features within each region, thereby generating a compact regional feature representation. This grouping method can focus on the local regions of specific objects in the scene, avoiding mutual interference from features of independently distributed objects in the distance, thus extracting more detailed and accurate semantic features.

Systems and methods for object detection can include obtaining one or more images and processing the one or more images with a machine-learned object detection model to generate one or more bounding boxes and one or more object classifications. The object detection model may perform atrous convolution, feature fusion, feature map generation, and prediction based on feature extraction.

A method and system perform incremental learning object detection in images and / or videos without catastrophic forgetting of previously learned object classes. A two-stage neural network object detector is trained to locate and identify objects belonging to additional object classes by iteratively updating the two-stage neural network object detector until an overall detection accuracy criterion is met. The update is performed to balance minimizing the loss of the initial ability to locate and identify objects belonging to previously learned object classes and maximizing the ability to additionally locate and identify objects belonging to additional object classes. Evaluating whether the overall detection accuracy criterion is met compares the output of an initial version of the two-stage neural network object detector with current region proposals output by a current version of the two-stage neural network object detector to determine a region proposal distillation loss and a previously learned object recognition distillation loss.

To provide an information processing device, an information processing method, and an information processing program that make it possible to estimate a placement state of a food.SOLUTION: An information processing device includes: an acquisition unit that acquires image information generated by capturing images of containers on which multiple types of foods are placed; a determination unit that recognizes a food recorded in the image information acquired by the acquisition unit and, when estimating a placement state of the food, determines whether the food can be estimated using a first learned model in which learning target foods corresponding to the food and placement states of the learning target foods are learned, or whether the learning target foods corresponding to the food have not been used in the learning and therefore the food cannot be estimated using the first learned model; and a learning unit that, if the determination unit determines that the food cannot be estimated using the first learned model, performs learning using the foods recorded in the image information acquired by the acquisition unit to generate a second learned model.SELECTED DRAWING: Figure 1

The invention discloses a course recommendation method and device, electronic equipment and a storage medium. The method comprises the following steps: determining a recommendation score of each course; sorting the courses according to the recommendation scores of the courses; and recommending the courses according to the sorting sequence of the courses. According to the technical scheme, the recommendation score of each course is determined; according to the method, the curriculums are sorted according to the recommendation scores of the curriculums, and finally, curriculum recommendation is performed according to the sorting order of the curriculums, so that when curriculum recommendation is performed on the object, the curriculum quality of the recommended curriculums can be ensured as much as possible, and the influence of the curriculum click rate on recommendation is reduced; and finally, the course learning quality of the learning object is ensured.

An object detection model and relationship prediction model are jointly trained with parameters that may be updated through a joint backbone. The offset detection model predicts object locations based on keypoint detection, such as a heatmap local peak, enabling disambiguation of objects. The relationship prediction model may predict a relationship between detected objects and be trained with a joint loss with the object detection model. The loss may include terms for object connectedness and model confidence, enabling training to focus first on highly-connected objects and later on lower-confidence items.

Machine learning device (2) which learns a correlation between shipping control information (X1n) obtained by checking an object during its shipping and operational alarm information (X2n) issued during the operation of the object, and which includes: - a condition monitoring unit (21) that monitors the shipping control information (X1n) and the operational alarm information (X2n) as data input from an environment (1), and - a learning unit (22) which generates a learning model based on the shipping control information (X1n) and operational alarm information (X2n) monitored by the condition monitoring unit (21), wherein the object includes a motor the environment (1) comprises an engine control device (11) that controls the engine during its shipment and outputs the shipping control information (X1n), and an engine control device (12) that gives an alarm during the operation of the engine and outputs the operating alarm information (X2n), The shipping control information (X1n) includes control element results associated with a motor model and motor inspection date, an insulation resistance value, an earth resistance value, a current value and / or a switching impulse voltage for the motor, and The operating alarm information (X2n) includes an overcurrent alarm, a noise alarm and / or an overload alarm for the motor.

A visual model-based intelligent personnel restriction method for mines prone to rockbursts, belonging to the field of coal mine safety monitoring and computer vision technology, comprises the following steps: 1. Acquiring and preprocessing real-time video stream data from mine roadways; 2. Extracting personnel identity features from the preprocessed video stream data based on a deep learning object detection model; 3. Performing cross-frame association and continuous tracking of detected personnel based on a multi-target dynamic tracking algorithm; 4. Extracting the foot tracking points of the tracked personnel and determining their entry / exit directions and counting personnel based on a preset polygonal target area; 5. Integrating personnel flow statistics and implementing graded early warning for personnel restriction at the working face. This invention, through the above method, can effectively reduce the risk of rockburst disasters and ensure the safety of underground workers and mine production.

Systems and methods for generating performance metrics for autonomous vehicle systems are provided. The performance metrics include two complementary metrics that evaluate a machine-learning object prediction model relative to a number of potential trajectories of an autonomous vehicle. The performance metrics include an avoidance metric that quantifies a probability that a region occupied by a real-world or simulated object is reached by the autonomous vehicle, the region is not blocked by another object, and the region is not blocked by a prediction output by the machine-learning object prediction model. The performance metrics also include an availability metric that quantifies a probability that a simulated or real-world object is not located within a region, the region is not blocked by another simulated or real-world object, and the autonomous vehicle is unnecessarily blocked by the prediction output before the autonomous vehicle reaches the particular footprint.