15166results about "Three-dimensional object recognition" patented technology

A method for detecting an infrared ship target based on an improved YOLOv7 is provided, including the following steps: obtaining an infrared maritime ship data set; reforming a YOLOv7 network structure based on an MobileNetv3 network and a bidirectional weighted feature pyramid network, and obtaining an infrared ship target detection model by introducing an attention mechanism and an optimized loss function; training and verifying the infrared ship target detection model based on the infrared maritime ship data set to obtain the infrared ship target detection model trained; and detecting a maritime ship based on the infrared ship target detection model trained.

A 3D target detection method based on multimodal fusion and a depth attention mechanism includes the following steps: obtaining and preprocessing original point cloud data and original image data; inputting the preprocessed point cloud data and image data into a 3D target detection network based on multimodal fusion and the depth attention mechanism, where the 3D target detection network based on multimodal fusion and the depth attention mechanism includes a generation phase for 3D bounding box proposals and a refinement phase for 3D bounding boxes, and the network outputs parameters and classification confidence of a target bounding box; training the 3D target detection network based on multimodal fusion and the depth attention mechanism; and processing the collected lidar point cloud data and image data by using the trained detection network, and outputting 3D target information, to realize 3D target detection.

Disclosed are a high-performance loosely-coupled multi-modal data fusion system for a smart driving environmental perception system and a vehicle-mounted device, comprising: a fusion detection model based on a modality-independent feature interaction strategy, which is configured for converting a LiDAR point cloud, a camera image, and a millimeter-wave radar point cloud into a unified bird's-eye view representation, and performing multi-modal fusion; and a fusion tracking model based on a motion-appearance feature cascaded coupling data association strategy, which is configured for performing subsequent trajectory tracking and matching according to multi-modal fusion feature information. A VoD data set and a K-Radar data set are selected for training, verifying, and testing the comprehensive performance of the models, and a TensorRT accelerated inference model is applied, then quantized, and deployed to a vehicle-mounted computational testing platform. The present invention is compatible with mainstream sensor deployment solutions, and achieves the efficient complementary fusion of multi-source heterogeneous sensor information, significantly improving the reliability, accuracy, and adaptability of vehicle-mounted perception systems, thereby effectively responding to extreme operating conditions such as complex traffic scenarios and inclement weather.

A data processing system comprising: inputting a tiled image of a vehicle including four different angle views of the vehicle combined into a single image to a first machine learning model (e.g. CNN), the model trained based on historical image data to predict a first likelihood of total loss vehicle; inputting a multi-fusion of images each into a second set of machine learning models; the multi-fusion of images including a set of separate and distinct images for each of the views input separately into the second set of machine learning models, and extracting features to predict a second likelihood of total loss vehicle; inputting tabular data relating to the vehicle into a third machine learning model to predict a third likelihood of total loss vehicle for the vehicle; and aggregating the first, second and third likelihood of total loss vehicle to determine the overall likelihood of total loss.

Approaches presented herein provide for the ability to process, store, index, and search geospatial information such as maps with flexible granularity. A set of observations, such as may include sensor data captured for a region of an environment, can be fed as input to a language model. The language model can generate a tokenized description of the region, as may include a text string of tokens encapsulating semantics, topology, geometry, and / or other aspects of the region. A feature vector or embeddings for the region can be generated based on the tokenized description, and a similarity search performed against a vector database, for example, to identify similar feature vectors corresponding to similar regions or domains. Labels or other information associated with these similar feature vectors can be automatically applied to the example region. Clustering of feature vectors or other embeddings can also be performed based in part on the similarity.

The invention provides a bridge structure crack position identification method based on deep learning and computer vision, and the method comprises the steps: obtaining a multi-view visible light image and a depth image, fusing the visible light image and the depth image according to registration parameters, and generating a fusion image containing the texture and depth information of a bridge; for the fused image, extracting a crack region by adopting an adaptive threshold segmentation algorithm, and dynamically adjusting the threshold to obtain a crack binary image; according to the crack binary image, calculating three-dimensional coordinates of crack pixel points through a three-dimensional reconstruction algorithm, and performing reconstruction to obtain three-dimensional point cloud data containing crack space position and form information; on the basis of the three-dimensional point cloud data, three-dimensional local feature descriptors are adopted to describe geometric attributes of the surface of the crack, crack fragment parameters are calculated, and a three-dimensional crack model is constructed; based on a deep learning model, a transfer learning strategy is adopted, a self-adaptive transferable bridge crack three-dimensional detection method is formed, and model parameters are updated so that the model parameters can adapt to the characteristics of a target bridge.

A data processing system comprising: inputting a tiled image of a vehicle including four different angle views of the vehicle combined into a single image to a first machine learning model (e.g. CNN), the model trained based on historical image data to predict a first likelihood of total loss vehicle; inputting a multi-fusion of images each into a second set of machine learning models; the multi-fusion of images including a set of separate and distinct images for each of the views input separately into the second set of machine learning models, and extracting features to predict a second likelihood of total loss vehicle; inputting tabular data relating to the vehicle into a third machine learning model to predict a third likelihood of total loss vehicle for the vehicle; and aggregating the first, second and third likelihood of total loss vehicle to determine the overall likelihood of total loss.

The invention relates to the technical field of river pollution identification, in particular to a pollutant identification and early warning method and system for a river patrol pollution source, and the method comprises the steps: constructing a three-dimensional monitoring network system, so as to build a three-dimensional data collection architecture; establishing a space-time reference unified framework to realize synchronous time service of different monitoring nodes; deploying an edge computing node, and implementing data preprocessing at an equipment end of the monitoring node; constructing a pollutant feature library which comprises spectral features, water quality parameter correlation features and visual morphological features of river pollutants, and establishing a water quality parameter correlation model of organic pollutants and inorganic pollutants, which comprises a plurality of feature dimensions; and a self-adaptive threshold early warning mechanism is established, a space-time composite early warning model is constructed, and accurate positioning and hazard degree grading early warning of pollution events are realized. According to the invention, through the hierarchical fusion model of technology fusion, the precision and speed of identifying the river pollutants are improved.

The invention discloses a point cloud data rapid processing system based on 3D vision, and relates to the technical field of point cloud data processing. The binocular acquisition module generates an anti-interference high-precision point cloud; the preprocessing module is used for reducing noise and dimensionality and retaining key geometric features; the hierarchical feature extraction module fuses curvature weight and a non-maximum suppression strategy, and improves the robustness of an ORB algorithm in rotation, scale and noise scenes; the industrial scene segmentation module accurately separates stacked objects through normal vector clustering and a dynamic region growing algorithm, and secondarily verifies boundaries in combination with a lightweight semantic model; the two-stage registration module dynamically adjusts a threshold value based on error feedback to realize pose optimization from coarse registration to fine registration; the coordinate mapping module establishes a space mapping model through multi-attitude calibration and robot multi-axis linkage trajectory optimization. The problem that in the prior art, a 3D machine vision algorithm is high in time delay is solved, the real-time performance and rapidity of 3D model recognition and feature extraction are improved, and the efficiency requirement of industrial production is met.

The invention discloses a point cloud differential defect detection system and detection method based on multi-feature fusion, which are mainly used for high-precision detection of surface defects of a side wallboard of a railway passenger car, and the method comprises the following steps: obtaining datum point cloud data through a designed standard side wallboard model of the railway passenger car, and collecting real-time point cloud data through a laser scanner; preprocessing the obtained point cloud data; calculating the difference between the real-time point cloud and the reference point cloud by adopting a difference method for fusing geometric features such as Euclidean distance, curvature and normal vector, namely calculating the Euclidean distance difference, curvature difference and normal vector difference between the reference point cloud and the real-time point cloud; and a comprehensive abnormal score is generated by further combining a dynamic weight fusion mechanism, and different region characteristics (such as a plane, a curved surface and an edge region) are adapted through dynamic threshold adjustment. According to the method, the defect region is segmented through the clustering algorithm, and the defect area and depth are quantified. The method has the advantages of high detection precision, strong adaptability and good real-time performance, and is suitable for complex surface defect detection in industrial production.

The invention provides a building construction monitoring method, which comprises the steps of obtaining multi-view video image data of a construction site, and performing fusion processing on the multi-view video image data by adopting an image splicing algorithm to obtain a panoramic three-dimensional scene model of the construction site; acquiring an image frame in the panoramic three-dimensional scene model, and analyzing the image frame by adopting a pre-trained work type identification model to obtain position information of operating personnel and equipment of each work type; acquiring position information of the operating personnel of each type of work, and analyzing postures of the operating personnel by adopting a pre-trained human body posture estimation model to obtain action state information of the operating personnel; and acquiring the position information and the action state information of the operating personnel of each type of work, and judging the specific operation state of the operating personnel of each type of work in combination with a pre-established work type operation knowledge base.

The present invention is directed to systems and methods for monitoring activities in an aviation environment. The system includes at least two monitoring units, each including at least two types of sensors, wherein: the sensors are mounted at a plurality of locations in the aviation environment. The system further includes a processing system being configured to receive said information from the sensors, to process said information to monitor and make predictions, and to combine sensor information by applying data fusion. The system is further configured to compare sensor information with predetermined safety operation criteria, and to generate an alert signal. The method of the invention includes obtaining sensor information, receiving said information from the sensors at a processing system, processing said information, comparing the processed information with predetermined safety operation criteria, and generating an alert signal.

The invention discloses an intelligent supervision management and control method and system, and the method comprises the steps: generating a violation operation recognition result and an equipment abnormality early warning signal according to construction scene multi-mode data collected by an intelligent camera and real-time monitoring information of an Internet of Things sensor; generating a non-tampering block chain evidence storage data chain based on the violation operation identification result and the equipment abnormity early warning signal; according to the engineering change information in the block chain evidence storage data chain, updating a BIM collaboration platform through an incremental three-dimensional model synchronization technology, and generating a multi-party real-time interaction enhanced three-dimensional model; based on an enhanced three-dimensional model and Internet of Things environment monitoring data, a digital twin mirror image space is constructed, a construction process is simulated through a multi-source data fusion deduction engine, and a risk pre-judgment map and a resource configuration optimization strategy are generated. According to the embodiment of the invention, visual supervision, credible tracing and prospective decision making of the construction process can be realized.

The invention provides an unmanned aerial vehicle accessory intelligent identification and access method and system based on a sensor, and relates to the technical field of unmanned aerial vehicle accessory management, and the method comprises the steps: collecting the three-dimensional contour information of unmanned aerial vehicle accessories, generating standard point cloud data, carrying out the feature extraction, and carrying out the feature alignment and interaction, generating a high-dimensional fusion feature matrix of the target unmanned aerial vehicle accessories; based on the feature pyramid network, constructing multi-scale feature representation, generating hierarchical feature descriptors, performing similarity calculation, generating a similarity score matrix, performing optimal matching, establishing an adaptive verification rule base and performing accessory verification; calculating an optimal action sequence of an access path based on model information, mapping the optimal action sequence into a motion track parameter of a mechanical arm, collecting multi-point stress data, predicting the optimal clamping force, establishing an accessory service life prediction model, performing prediction in combination with historical data, and generating an accessory state evaluation report and a maintenance suggestion.

The invention discloses an indoor real scene three-dimensional reconstruction method based on improved 3D Gaussian sputtering, belongs to the technical field of three-dimensional reconstruction, and aims to complement initial point clouds in a self-adaptive manner through a designed feed-forward point cloud densification network, generate a high-density 3D Gaussian radiation field, fill scene missing details and avoid the problem of precision attenuation caused by lack of point cloud constraints. In the cost body optimization stage, a depth regularization loss module is designed by integrating global structure features, depth information is integrated into the optimization process, algorithm reasoning is accelerated, and object structure fuzziness is relieved; and finally, in combination with adaptive density control and Gaussian pruning, radiation field parameters and density distribution are finely adjusted, indoor scene reconstruction with double improvement of visual fidelity and structural integrity is realized, interactive application becomes possible, a real-time solution is provided for indoor scene reconstruction, and application of a three-dimensional reconstruction technology is widened.

Approaches presented herein provide for the generation of a tokenized description of an environment for use in making decisions with respect to the environment. In particular, a large language model (LLM) can be used to generate a tokenized text string representation of an environment using sensor information captured at a specific location, as well as information about the semantics, topology, and geometry of the environment. A similarity-based search can be performed against tokenized descriptions for various locations until a single high-quality match is identified, and the geographic position of the match can be inferred to correspond to the current position of a vehicle that captured the sensor data. The current location and tokenized description can also be provided to a language model, along with a road-level route plan, in order to generate more detailed routing information that is optimized based on the additional information available in the tokenized description for a sequence of goals corresponding to the route plan.

The invention discloses a material grabbing offset real-time compensation method and device based on multi-sensor data fusion, relates to the technical field of automatic production, and discloses a material grabbing offset real-time compensation method and device based on multi-sensor data fusion. The three-dimensional offset is generated in real time in combination with the neural network model, mechanical arm compensation is controlled, the problems that a single sensor is large in positioning error and insufficient in compensation precision are solved, the material grabbing accuracy can be improved, and then the stability of an automatic production line is enhanced.

Exemplary methods, systems, apparatus, and computer programs are disclosed for an unmanned aerial system (UAS) inspection system that includes an unmanned aerial system and analysis system for exterior building envelopes and energy performance evaluation and simulation. The UAS can autonomously and systematically collect data for a building's exterior using a payload comprising (i) nondestructive testing (NDT) sensors configured for imaging (visible, infrared, or more) the building and (ii) one or more multi-spectral sensors (LiDAR, ultrasound, radar, or more). The acquired sensor data are provided to an analysis system comprising computer vision (CV) and signal processing modules configured to analyze the acquired data to i) identify building objects (doors, windows, rooftop units, and others) ii) characterize envelope properties (components, heat resistivity, or others) and 3) identify initial thermal anomalies (thermal bridges, physical defects, or infiltration / exfiltration) in a processing pipeline.

The invention discloses a loess tunnel surrounding rock deformation monitoring method, and relates to the technical field of civil engineering and geological engineering, and the method comprises the steps: integrating a spiral winding type optical fiber sensor, a double-cavity humidity compensation vibrating wire sensor and a microseismic array, and capturing surrounding rock strain, vibration and geological activities; the vibrating wire sensor suppresses humidity interference through a silicone oil damping medium and self-adaptive excitation frequency, and the optical fiber sensor is fixed through a pre-embedded silica gel sleeve to adapt to surrounding rock deformation; edge computing nodes are deployed on the inner wall of the tunnel, an FPGA chip and a lightweight GRU model are integrated, optical fiber strain, a micro-seismic energy spectrum and laser point cloud displacement field data are fused in real time, the strain gradient is analyzed, and a crack propagation probability cloud picture is generated; redundant optical fiber link switching is combined with a six-degree-of-freedom mechanical arm to realize breakpoint self-repairing, and a self-cleaning air curtain is integrated to inhibit dust adhesion; and constructing a geological parameter library based on a BIM-GIS fusion platform, driving a finite element-discrete element coupling model to dynamically update boundary conditions, and predicting surrounding rock deformation and collapse risks.

The invention discloses an environment modeling method and system for realizing intelligent security and protection, and relates to the technical field of intelligent security and protection, and the method comprises the steps: collecting a visual image and depth data of a monitoring region, and generating a monitoring scene feature matrix; performing hierarchical feature extraction on the monitoring scene feature matrix by using a deep convolutional neural network, and constructing a scene semantic feature map; projecting the scene semantic feature map to a three-dimensional monitoring space according to the depth data, and constructing a three-dimensional scene grid model; extracting spatial topological characteristics of each grid node in the three-dimensional scene grid model, and calculating association weights among the grid nodes; and constructing a scene dynamic knowledge graph based on the spatial topological features and the associated weights, and carrying out modeling analysis on abnormal events. According to the method, through cooperative collection of the multi-view vision sensor and the depth sensor, in combination with information entropy weighted standardization and principal component analysis, accurate generation of the monitoring scene feature matrix is realized, and the problems of information redundancy and feature coupling in traditional vision data processing are effectively solved.

Approaches presented herein provide for the training of a language model to provide human-style reasoning or “train-of-thought” support for generated inferences. In at least one embodiment, a language model can be used to assist in the generation and / or annotation of content for a specific domain or type of data. This can include, for example, tasks such as performing quality checks for high definition (HD), standard definition (SD), and / or navigational maps. In the mapping context, a language model can be trained using a large set of rules relevant to the mapping domain, in order to become a domain expert. In addition to training the language model on domain-specific rules and data, the language model can be further trained based at least in part on human feedback, such as corrections made to map data by an authorized human.

The invention discloses a single tree dynamic monitoring method and system based on multi-stage point cloud and deep learning, and the method comprises the steps: collecting multi-stage multispectral images and laser point cloud data of a research region, and carrying out the preprocessing; performing registration fusion on the preprocessed multi-period multispectral image and the laser point cloud data to generate a multi-period fusion point cloud; based on the multi-period fusion point cloud, performing individual tree segmentation by using a deep learning model; and based on the individual tree segmentation result, inverting the crown breadth and the tree height of the individual tree, and analyzing growth parameters of the individual tree according to the inversion result of the crown breadth and the tree height. By fusing the multi-temporal point cloud and the multi-spectral image data and combining the deep learning model, accurate segmentation and dynamic growth monitoring of the single tree are realized, and the defects of low single tree segmentation accuracy, insufficient multi-source data fusion and incapability of capturing forest tree growth changes in the prior art are overcome. The crown breadth and tree height inversion model is adopted, the precision of growth parameter estimation is effectively improved, and a scientific basis is provided for forest resource management.

Approaches presented herein provide for the performance of quality assurance-related tasks with respect to a representation of an environment, such as a set of generated map data. In particular, a language model can be used to generate a tokenized representation of a map using information such as the semantics, topology, and / or geometry determinable from the map data. A language model-generated representation can comply with real-world rules and constructs, and can account for omissions or errors in the input data based upon known relationships and semantics for various objects in the environment. One or more language models can be used to not only identify potential issues in the map data, but also to make recommendations for modifications and / or to generate plaintext descriptions of the issues, modifications, or recommendations to assist a human reviewer in addressing the issues.

The invention discloses a monorail crane inspection robot intelligent test method based on data analysis, and relates to the technical field of intelligent detection, and the method comprises the following steps: synchronously collecting track images, point cloud and attitude data, carrying out time alignment and preprocessing, and outputting a standardized data packet; detecting an inspection target by using a YOLO detection network, and outputting a multi-scale feature vector in combination with a point cloud feature hierarchy extraction network and a time sequence convolutional network; predicting a fault development trend in combination with an improved A-star algorithm and a long short-term memory network, optimizing an inspection path through reinforcement learning, and outputting a maintenance decision scheme; the maintenance decision scheme is converted into a control instruction, the robot is driven to execute an inspection task and feed back the operation state in real time, incremental learning and point cloud reconstruction are combined, and a visual diagnosis report is output. According to the method, the dynamic threshold algorithm is adopted for self-adaptive analysis, and the key geometric indexes are calculated in combination with the cross-modal attention mechanism, so that the recognition capability of structural anomalies is improved.

Approaches presented herein provide for the identification of differences between local map data, for a region of a physical environment, and observation or perception data generated by one or more machines or other such sources. In at least one embodiment, sensors on an ego machine can capture sensor data for a region in which the ego machine is located, and a language model on the ego machine can compare this sensor data, or perception data generated using the sensor data, against the local map data. The language model can generate a tokenized description of identified differences, in a domain-specific language. The tokenized description can be transmitted to a map management service that can compare these differences against differences identified by other machines, for example, to determine whether to update and redistribute at least a portion of the map data.

The invention discloses a transmission line three-dimensional reconstruction method and system based on a monocular channel monitoring camera, and the method comprises the steps: obtaining compensation image data through adaptive illumination compensation processing, obtaining direction feature data based on frequency domain feature analysis, constructing a texture enhancement model through a graph theory, generating enhanced image data, and carrying out the reconstruction of a transmission line. Outputting feature aggregation data through time sequence feature aggregation; generating three-dimensional contour data in combination with multi-wire topology analysis and geometric constraint optimization; depth probability modeling and multi-scale consistency processing are adopted to obtain optimized depth data; and outputting system state data, three-dimensional point cloud data and deformation parameter data through physical model construction and space-time constraint fusion. According to the method, high-precision three-dimensional reconstruction of the power transmission conductor is realized, and the method has relatively high environmental adaptability and calculation efficiency.

The invention relates to a human shape posture recognition method and system based on image analysis, and the method comprises the steps: inputting the reference human shape data of a monitored object, and collecting the multi-modal data of an RGB image, an infrared image and inertial measurement data in a target scene in real time; space-time alignment processing is carried out, and corresponding features are fused; image space features are extracted, time sequence modeling is carried out on inertial data, and dynamic weighted fusion of two paths of network outputs is realized through a gating mechanism; human body basic joint points are positioned, and refined posture vectors including joint angles and limb relative positions are generated; according to attitude data and environment information collected in real time, adaptively adjusting an attitude classification threshold value and a similarity measurement standard, and predicting abnormal behaviors in a future time period; and when the abnormal behavior is predicted, triggering to execute a preset safety measure. Multi-modal data can be efficiently fused, attitude features can be accurately extracted, an identification strategy can be adaptively adjusted, and human shape attitude identification with behavior trend prediction capability can be realized.

The invention relates to the technical field of data processing, and particularly discloses a virtual maintenance data processing system for maintenance scene optimization. Comprising an optical contact probe, a scanning measurement system, an image recognition and defect analysis module, an image auxiliary measurement module, a part visual tracking module, an augmented reality assembly guide module, a data fusion and state modeling module and a man-machine interaction and task excitation module. By fusing optical contact measurement, image recognition, point cloud modeling and augmented reality guidance, intelligent and high-precision execution of defect detection, size measurement, assembly deviation correction and state modeling in the disassembly and reassembly process of the gearbox is achieved.

The invention relates to the field of image recognition, in particular to an automatic solid waste sorting method and device applying machine vision. The method comprises the following steps that monitoring images of to-be-sorted areas in multiple directions are obtained; performing spatial geometric view angle deviation correction on the monitoring images of the to-be-sorted areas in the multiple directions, performing spatial panoramic image optimization, and constructing a panoramic image of the sorting area; performing frame-by-frame solid waste visual positioning scanning on the panoramic image of the sorting area, and performing three-dimensional morphological structure analysis so as to generate a three-dimensional morphological structure representation of each solid waste; performing solid type classification decision according to the three-dimensional morphological structure representation of each solid waste, and performing bounding box coding mapping to obtain a coding mapping bounding box of each solid waste; and performing equipment action sequence simulation on the coding mapping bounding box of each solid waste, and constructing a fine tuning action sequence. Efficient solid waste recognition is achieved, and the sorting efficiency is improved.