1429 results about "Feature detection" patented technology

The invention relates to a power construction monitoring method, system and device and a medium, and the method comprises the steps: carrying out the space-time calibration and anti-interference processing through collected construction images, temperature and dust data, and carrying out the fusion to generate a multi-source fusion data set containing environment information; performing feature extraction on the multi-source fusion data set based on a neural network model, synchronously identifying an action track of a constructor and equipment operation parameters, and constructing a feature map set associated with behaviors and equipment states; performing action and equipment anomaly conjoint analysis on the feature map set, and generating a construction risk event set by analyzing human body joints and temperature feature detection; performing spatial distance calculation and time monitoring on the risk event, and quantifying the coupling risk level; and based on the dynamic risk threshold, a grading early warning instruction is triggered, and precise response of field personnel warning, equipment power failure and evacuation guidance is realized. According to the method, the technical problems of low construction risk identification precision, equipment anomaly detection lagging and risk assessment deficiency in a complex environment are solved.

The invention relates to an intelligent equipment access system and access method based on an AI large model, and relates to the field of artificial intelligence and Internet of Things. According to the technical scheme, a dynamically adaptive universal object model access framework is constructed, functional attributes, control instructions and data formats of intelligent devices of different brands and protocols are mapped into a standardized logic model, meanwhile, a multi-mode AI large model engine is combined, high-precision voice recognition, voiceprint feature detection and multi-level semantic intention analysis capabilities are integrated, and the intelligent devices of different brands and protocols can be obtained. And an intelligent interaction closed loop of end-cloud collaboration is formed. Semantic analysis adopts a mixed strategy, a natural language instruction is converted through function mapping, a local knowledge base is utilized to match user scene requirements, and external data is queried by means of cloud networking to optimize instruction logic. According to the scheme, the multi-device access and operation and maintenance cost is remarkably reduced, the semantic understanding accuracy and scene adaptability are improved, and the method is widely applied to the fields of smart home, smart medical treatment and industrial Internet of Things.

The invention provides an unmanned aerial vehicle multi-mode remote sensing image target detection method and device based on a hybrid Mamb-CNN network. The method comprises the steps of obtaining a visible light image and a thermal infrared image to be detected; inputting the visible light image and the thermal infrared image into a target detection network to obtain a remote sensing detection result; the target detection network is constructed based on a twinborn feature extraction network, the twinborn feature extraction network comprises a visible light branch network, an infrared branch network, a cross-modal fusion module, a neck layer and a detection head, the visible light branch network extracts visible light local features in a visible light image, the infrared branch network extracts infrared local features in a thermal infrared image, and the cross-modal fusion module carries out cross-modal fusion; the cross-modal fusion module fuses the visible light local features and the infrared local features to obtain multi-scale features, the neck layer is based on the multi-scale features to obtain global fusion features, and the detection head is based on the global fusion features to obtain remote sensing detection results, so that the precision and robustness of multi-modal target detection are enhanced.

Systems and methods for detecting features, outputting feature representations, determining measurements, and combinations thereof using machine-learned algorithms are provided. In some embodiments, first sample data from a first characterization modality and second sample data from a second characterization modality are provided to a machine-learned algorithm. Improved feature detection, feature representation, and measurement may be realized by using multimodal data with a machine-learned algorithm. In some embodiments, a first characterization modality is an interferometric modality and a second characterization modality is a spectroscopic modality. A first characterization modality may be optical coherence tomography and a second characterization modality may be a diffuse spectroscopy modality, such as near-infrared spectroscopy. Sample data may be intraluminal and / or vascular data useful in characterizing a vascular system of a subject, such as a human.

The invention discloses a ship target tracking method based on radar imaging in a shielding environment, belongs to the technical field of target tracking, is used for ship target tracking, and comprises the following steps: obtaining multiple frames of echo images of a time sequence, obtaining a potential target on each frame by using a ship image feature detection method, and obtaining a time accumulation space diagram; initial tracks are extracted from the time accumulation space diagram, and a tracking ID is distributed to each initial track; a frame of echo image is read, the position of a potential target is detected, and the position of the potential target is associated and matched with the tracking ID; and updating the position of a potential target which is not normally associated and matched by using a ship target tracking method combining unscented Kalman filtering and LSTM. According to the method, more potential targets are extracted, and a local matching result is optimized; more and more accurate target information is provided for the VTS system, so that the VTS system can have more prior information of early warning, and safe passage of a main channel is ensured.

The invention discloses an air-ground collaborative dam termite trace detection method and device and electronic equipment. The method comprises the steps that an unmanned aerial vehicle is used for cruising and scanning the surface of a dam to obtain image information; constructing a three-dimensional map of the dam by using the image information; extracting termite activity trace characteristics on the image information; according to the image information, a detection and recognition model is constructed, and the detection and recognition model is that an efficient detector for a small target is introduced on the basis of yov8; deploying the detection and recognition model on a ground tracked robot, and performing initial detection and recognition on the termite activity trace characteristics by the unmanned aerial vehicle by using the detection and recognition model; the termite traces recognized through initial detection are determined as suspected features, and the position points of the suspected features are determined and calibrated on a map; and the ground tracked robot plans a one-way planning route map to a position point according to the position point calibrated on the three-dimensional map, then navigates to the position point with the suspected feature, and carries out detection confirmation, so that air-ground collaborative integrated dam termite earth surface exposure feature detection is comprehensively realized.

The invention provides an online car-hailing passenger position rapid positioning method based on voice interaction and visual perspective, and relates to the technical field of intelligent traffic, and the method comprises the following steps: arranging a sensor, a camera, a metal reflective curtain and a projector on a car; voice information of a driver is collected, and an intelligent voice wake-up model is designed; constructing a scenarized speech recognition model; detecting a pedestrian target for the panoramic image by using a sound-image multi-level cross-modal detection model, and obtaining appearance and posture feature detection information of the pedestrian target; a static feature matching method and a dynamic feature recognition model are designed, and passenger feature information matching is achieved; based on a matching result, determining position information of the passenger; acquiring a passenger direction taking the vehicle as a reference origin through position estimation in the panoramic image; according to the direction estimation result, a projector in the vehicle is controlled, the passenger information is projected on a curtain in the corresponding direction in the vehicle, and meanwhile voice information is used for giving a prompt.

This disclosure provides systems, methods, and devices for vehicle driving assistance systems that support enhanced sensor fusion techniques. In a first aspect, a method of includes receiving point cloud data for two or more frames from a radar device and generating scene flow parameter data based on the point cloud data. The method also includes generating voxel position adjustment data based on the scene flow parameter data, and generating feature concatenation information associated with two or more sensors based on the voxel position adjustment data and feature information associated with the two or more sensors. The method further includes performing feature detection and tracking based on the feature concatenation information to generate tracking information for one or more objects, and outputting the tracking information. Other aspects and features are also claimed and described.

The invention discloses a product internal structure defect detection method and system based on AOI multispectral imaging, and the method comprises the steps: placing a detection device at a prediction position of a to-be-detected product, obtaining an initial multispectral image of the to-be-detected product through a multispectral imaging module, and obtaining the initial position of a corresponding movable probe; the movable probe is controlled to move along a preset path, and multispectral image data of the position where the movable probe is located are collected in real time; image preprocessing is conducted on the multispectral image, defect feature detection is conducted on the interior of the product, a product defect detection result is obtained, corresponding spatial position information is obtained, and real-time depth position information of a corresponding movable probe is obtained based on the initial position and a preset path; performing spatial matching on the spatial position information and the corresponding real-time depth position information to obtain product defect target detection information; the invention provides a product defect detection mode which is convenient for meeting the requirements of modern industrial production on efficiency and cost.

The invention discloses an unmanned aerial vehicle aerial image target detection method based on improved YOLOv8, and relates to the technical field of target detection, and the method comprises the steps: collecting image data of unmanned aerial vehicle aerial photography, inputting the image data into a backbone network of an improved YOLOv8 model, and extracting features; transmitting the feature map to a neck network for feature processing and fusion, and carrying out target classification and bounding box prediction in a head network by using a detection head specially aiming at a small target and a multi-scale feature map; and calculating the difference between a predicted bounding box and a real bounding box by using an MPDIOU loss function, updating model parameters in a back propagation manner, and outputting a detected target category and bounding box coordinates. According to the method, a C2f module is replaced by RepNCSPELAN4, a GAM attention mechanism is introduced, a small-scale feature detection head is added, an MPDIOU loss function is adopted, feature extraction and fusion are optimized, and the detection precision and bounding box regression accuracy are improved.

The invention discloses a street tree safety risk feature detection method, system and device, and a storage medium. The method comprises the steps of obtaining image information of a lesion area of a trunk on a street tree; preprocessing the image information to obtain a training sample; based on the training sample, training an improved YOLOv8 network model to obtain a trained pest and disease identification model; wherein the improved YOLOv8 network model comprises a selective multi-scale convolution kernel attention mechanism module and an average pooling module; and detecting a trunk image to be recognized by adopting the pest and disease recognition model to obtain a detection result. A pest and disease identification model obtained by training the training sample and the improved YOLOv8 network model can be used for identifying large-batch and various types of tree trunk pest and disease images, and a high-precision identification result is quickly provided, so that the identification time is saved, the troubleshooting cost is reduced, and a more comprehensive reference basis is provided for urban greening management and decision making.

The invention relates to the technical field of display screen driving, in particular to a low-power-consumption display screen driving method and system based on the OLED technology, and the method comprises the steps: S1, carrying out the image feature detection, collecting the inter-frame brightness change rate, the sub-pixel gray level distribution and the regional temperature gradient, and generating a dynamic driving signal parameter; s2, voltage compensation adjustment: dividing a power consumption area according to a brightness change rate, calculating a brightness compensation coefficient and correcting the voltage by combining gray level distribution and a temperature gradient, and realizing sub-pixel voltage dynamic adjustment; and S3, refresh frequency control: adjusting a local refresh rate according to the compensation coefficient and the correction voltage, executing a frequency reduction strategy on a high-power-consumption area, triggering ghosting suppression on a low-power-consumption area, and applying a temperature threshold to constrain a refresh upper limit. According to the invention, energy-saving driving, ghost suppression and brightness balance of the OLED display screen are realized, and the display performance and the system intelligence are effectively improved.

The invention discloses a quality detection system and method for a glue injection laser contour, and belongs to the technical field of quality detection, and the method comprises the steps: obtaining a reflection point cloud signal of a glue injection finished product, constructing a point cloud data stream, setting an image reconstruction method, constructing a glue layer three-dimensional model, synchronously generating a pseudo-color grey-scale map, and achieving the visual representation of the surface texture of a glue layer. A three-layer feature extractor is constructed, a quality primary judgment method is set, features of different scales are fused in a cross-layer mode, the problem of missing detection of complex defects in traditional single-feature detection is solved, basic defects are automatically recognized, and a quality primary judgment result is output; and performing defect judgment on the glue-injected finished product which is unqualified in primary judgment, setting a defect fine judgment method, performing voxel-level segmentation on the three-dimensional image, calculating defect characteristics, and judging whether the defects affect the use performance of the product or not so as to generate a fine judgment result, so that accurate positioning of complex defects is realized, and the defect type identification accuracy is improved.

The invention relates to the technical field of electronic component detection, in particular to an IC (integrated circuit) carrier plate detection method based on surface state image extraction, which comprises the following steps: acquiring a gray image, analyzing structural parameters, extracting gradient features, detecting boundary disturbance, integrating the image, calculating an abnormal score, identifying a defect position area, extracting features and outputting an identification result. According to the invention, by analyzing the structure parameters of the bonding pad in the gray level image, calculating the edge line segment, the center coordinate and the spacing, and constructing the two-dimensional coordinate system, the regional positioning reference is enabled to have geometric consistency, the coordinate mapping is combined with the gradient direction change frequency and the continuous aggregation point, the boundary disturbance identification precision is improved, and the image division is executed based on the disturbance region. According to the method, non-functional region mixing is effectively avoided, a clustering and probability model is introduced after region gray level statistics, a deviation scoring mechanism is constructed, gray level feature abnormity is accurately recognized, the discrimination capability of small-amplitude and low-contrast defects is improved, and the selectivity and target focusing performance of feature detection are enhanced.

The invention discloses a remote sensing image anomaly detection system and method fusing multi-source noise feature anomaly in the technical field of remote sensing image detection. The method comprises the following steps: acquiring optical satellite remote sensing image data to be processed; analyzing the optical satellite remote sensing image data to obtain remote sensing image detailed information; performing exception type labeling on the detailed information of the remote sensing image, and constructing an exception feature data set; based on the abnormal feature data set, performing multi-source noise feature detection through a pre-designed abnormal detection fusion framework; and outputting an abnormal region obtained by the multi-source noise feature detection and an abnormal detection result. Through a fusion detection mode, the problems of color anomaly, cloud shadow masking, pixel information anomaly and the like of the remote sensing image are found in time, the universality of a remote sensing image anomaly image detection algorithm is improved, and the remote sensing image anomaly detection efficiency is further improved.

The invention relates to the technical field of image recognition, in particular to a harmful image detection and recognition system and method based on agent collaboration, and the system comprises a first agent module, a second agent module, a third agent module, a fourth agent module and a fifth agent module, the first agent module is used for analyzing image element semantic information, outputting structured data and constructing an image comprehensive semantic knowledge graph; and the second intelligent agent module is used for carrying out harmful feature detection and associated query on the image in combination with the structured data, and outputting a coarse-grained harmful semantic detection result and the confidence coefficient of the coarse-grained harmful semantic detection result. According to the harmful image detection and identification system based on intelligent agent cooperation, through hierarchical processing and cooperative work of the first to fifth intelligent agents, comprehensive analysis of the image is realized to obtain meta-semantic information, coarse-grained and fine-grained harmful semantic detection is performed on the meta-semantic information, and through multiple rounds of challenge and dynamic comprehensive analysis, the detection and identification efficiency of the harmful image is improved. Hidden harmful information can be accurately identified, so that the accuracy and interpretability of the harmful information are improved.

The invention discloses an automobile part quality detection method and system based on artificial intelligence visual inspection, and belongs to the field of artificial intelligence machine visual inspection, and the method comprises the steps: firstly, carrying out the registration of a collected RGB image and a depth image, and extracting a part region through a saliency detection network; two-dimensional key points are extracted based on an RGB region image and are matched with key points of a three-dimensional model, an initial three-dimensional attitude is obtained by adopting a PnP algorithm, iterative registration is performed with the three-dimensional model in combination with a point cloud generated by a depth image, and a fine three-dimensional attitude is obtained. And calculating a geometric transformation matrix from the part to a standard front view attitude according to the attitude, and performing attitude correction on the RGB and depth region image. And then matching the corrected image with a standard template image by using a feature detection and matching network so as to correct the position of the detection window. And finally, the three-dimensional size of the part is calculated in the corrected detection window in combination with the depth value, and tolerance judgment is carried out. And the precision, the robustness and the automation level of online detection of the automobile parts can be obviously improved.

An approach is provided for generating feature data. The approach, for example, involves determining a set of break points associated with at least one road feature based on mask image data. The mask image data is associated with overhead image data comprising the at least one road feature. The approach further involves generating a set of cropped feature maps based on processing of a global feature map obtained from a global feature segmentation model and the set of break points. The global feature map is associated with the overhead image data. The approach further involves generating the feature data associated with the at least one road feature based on application of a local feature detection model on the generated set of cropped feature maps and the set of break points. The approach further involves storing the generated feature data in a geographic database.

The invention provides a network abnormal behavior feature detection method and device, and a computer readable storage medium. The network abnormal behavior feature detection method comprises the following steps: constructing an attention-based trajectory group anomaly detection model, constructing an abnormal behavior detection model, and constructing a normal and anomaly modeling model based on unsupervised learning; inputting the network behavior data of the networking device into the trajectory group anomaly detection model to obtain group trajectory preliminary anomaly detection data; inputting the group trajectory preliminary abnormal detection data into an abnormal behavior detection model to obtain non-abnormal behavior data in a data transmission process between the networked devices; and inputting the non-abnormal behavior data into the normal and abnormal modeling models to obtain network abnormal behavior feature data. According to the invention, the accuracy of network abnormal behavior detection between networked devices can be improved.

Methods and systems for assisting a vehicle to park using mixed-domain image data. Image-domain data is generated based on raw image data received from a plurality of cameras mounted on a vehicle. The raw image data is associated with a parking zone outside the vehicle, and the image-domain data is generated by a feature-detection machine learning model. A bird's-eye-view (BEV) image is generated based on the raw image data, wherein the BEV image is a projected image of the parking zone. BEV-domain data associated with the BEV image is generated. The BEV-domain data includes data associated with parking landmarks in the parking zone. A computing system localizes the vehicle within the parking zone based on the BEV-domain data and the image-domain data to generate localization data. The computing system performs mapping of the parking zone based on the BEV-domain data, the image-domain data, and the localization data.

The invention belongs to the technical field of material production detection, and particularly discloses a contact lens production defect detection method based on artificial intelligence, which comprises the following steps: collecting environmental information in a defect detection area; judging whether the detected environment is matched or not, if yes, executing the next step, and otherwise, regulating and controlling the environment; acquiring a plurality of images at different light source angles and different light source intensities; judging whether the image preprocessing mode needs to be changed or not, if so, confirming the changed preprocessing scheme, and otherwise, preprocessing the image; building a defect detection model, and training; defect feature detection is carried out; and performing functional defect detection and analysis on the contact lenses to be detected, and outputting a production defect report. According to the method, the problem of insufficient attention in the current image processing process is effectively solved, the sufficiency, representativeness and detection efficiency of contact lens production defect detection are improved, and meanwhile, the effectiveness of a subsequent detection result is guaranteed.

The invention relates to the technical field of image processing, in particular to a remote sensing image registration method based on convolution attention, which comprises the following steps: inputting an original remote sensing image pair into a convolution layer of a modal adapter to obtain original features, and processing the original features by adopting a convolution attention method to obtain target features; inputting the target feature as a modal adaptive feature into a feature encoder to obtain a feature descriptor; inputting the feature descriptors into a feature detector, and estimating global detection feature points by using conditional probability; and performing preliminary matching on the feature descriptors and the feature points by using an FLANN algorithm, and performing outer point elimination in combination with an RANSAC algorithm to obtain a registration result. According to the method, richer feature representation can be provided for remote sensing images of sparse and repeated texture areas, and the registration effect is improved.

The invention provides an abnormal parking detection method and device in an expressway scene based on a large model, and relates to the technical field of artificial intelligence such as automatic driving, large language models and image feature detection. The method comprises the following steps: acquiring a road time sequence video shot for an expressway scene; extracting multi-scale features of each video frame forming the road time sequence video; determining image quality information and environment information of the corresponding video frame according to the multi-scale feature of each video frame; determining position information and category information of traffic elements existing in the corresponding video frames according to the image quality information, the environment information and the multi-scale features of each video frame; according to the corresponding position information, the category information and the time sequence information among the video frames, determining the motion trails of the same traffic elements of the traffic elements existing in the video frames; and determining an existing abnormal parking event according to the motion trail. By applying the method, the abnormal parking event in the expressway scene can be accurately detected.

In various examples, three-dimensional (3D) object or feature detection and localization for autonomous and semi-autonomous systems and applications is described herein. Systems and methods are disclosed that use different types of sensors, such as an image sensor and a LIDAR sensor, to determine information associated with objects, such as traffic objects (e.g., traffic signs, traffic signals, traffic markings, etc.). To determine the information for an object, image data is processed to determine a bounding shape associated with the object. The bounding shape is then used to determine a 3D shape, such as a frustum, corresponding to the object. Additionally, points data generated using the LIDAR sensor, such as an occupancy map and / or a point cloud, is processed to identify a portion of the points associated with (e.g., located within) the 3D shape. This portion of the points may then be used to determine the information associated with the object.

The invention discloses a pavement disease image adaptive enhancement and restoration processing method, and belongs to the technical field of image processing, and the method comprises the steps: obtaining a pavement disease image, and carrying out the frequency domain transformation; recognizing a pavement material type based on the frequency domain features and determining a material sensing parameter set; performing multi-scale frequency domain decomposition according to the material perception parameter set, and performing adaptive enhancement on a low-frequency illumination component and a high-frequency detail component; carrying out disease feature detection and generating a disease perception weight map, and carrying out key enhancement on a disease area; according to the method, the self-adaptive enhancement model for road surface material perception is established, and targeted image enhancement processing is realized.

In various examples, training sensor data generated by one or more sensors of autonomous machines may be localized to high definition (HD) map data to augment and / or generate ground truth data—e.g., automatically, in embodiments. The ground truth data may be associated with the training sensor data for training one or more deep neural networks (DNNs) to compute outputs corresponding to autonomous machine operations—such as object or feature detection, road feature detection and classification, wait condition identification and classification, etc. As a result, the HD map data may be leveraged during training such that the DNNs—in deployment—may aid autonomous machines in navigating environments safely without relying on HD map data to do so.

The invention discloses an intelligent director system for a symphony concert scene, and the system comprises an audio and video stream receiving and decoding module which is used for decoding original audio and video data at the same time, and transmitting the decoded audio and video data to a feature detection module; the total spectrum analysis module is used for identifying and analyzing the total symphony spectrum data and sending an identification result to the switching logic module; the feature detection module is used for analyzing the decoded video and audio data, identifying various musical instruments appearing in a video frame picture, the scene type of the current picture and the quality of the picture, and providing the identified musical instruments, the scene type and the quality to the switching logic module as reference information; the switching logic module is used for judging whether the current picture can be cut out or not according to a switching judgment rule; and the director visualization module is used for playing the picture cut by the switching logic module. According to the invention, automatic broadcasting of the symphony concert performance is realized.

The invention provides a splicing method and a splicing device for a magnetic control capsule endoscope image of a digestive tract. The method comprises the following steps: screening out a candidate lesion area image sequence from an original alimentary canal image sequence collected by a magnetic control capsule endoscope; preprocessing the candidate lesion area image sequence to obtain a preprocessed candidate lesion area image sequence; performing feature extraction on the preprocessed candidate lesion area image sequence based on an OfficientLoFTR improved model, further performing feature matching on the preprocessed candidate lesion area image sequence to obtain matched feature point pairs, and performing image registration processing on each image of the preprocessed candidate lesion area image sequence according to the matched feature point pairs to obtain a pre-processed candidate lesion area image sequence; the improved model can improve the accuracy of feature detection and matching, a good foundation is laid for subsequent image registration and image fusion, image registration can be carried out by combining global homography transformation and local thin plate spline transformation, and the problem of non-rigid deformation is solved.

The invention relates to the technical field of measuring equipment, in particular to a six-degree-of-freedom parallel mechanism pose high-precision measuring system and method.The six-degree-of-freedom parallel mechanism pose high-precision measuring system comprises a laser emission reference device, an array light spot feature target assembly, a parallel mechanism movable platform and a feature detection and recognition assembly, and the laser emission reference device is arranged at the top of the parallel mechanism fixed platform; the array light spot feature target assembly is arranged above the laser emission standard device and arranged at the bottom of the parallel mechanism movable platform, and the four corners of the bottom of the parallel mechanism movable platform are fixedly connected with the top of the parallel mechanism fixed platform through the six-degree-of-freedom parallel mechanism. The feature detection and recognition assembly is arranged at the bottom of the array light spot feature target assembly and used for recognizing light spot information and target feature information on the array light spot feature target assembly, processing of redundant data is reduced, the measurement period is shortened, and it is ensured that high-precision rapid measurement is achieved.