230 results about "Image labeling" patented technology

The invention discloses a pavement crack semantic segmentation method based on Transform and CNN architecture, and relates to the technical field of pavement crack detection, and the method comprises the steps: obtaining a pavement image, marking a crack disease image in the pavement image through an image marking tool, and constructing a data set based on the marked crack disease image; preprocessing the data set, and constructing and training a self-adaptive semantic segmentation model combining a self-attention neural network and a convolutional neural network based on the preprocessed data set; and deploying the trained adaptive semantic segmentation model to a local platform, and inputting the crack disease image into the adaptive semantic segmentation model for segmentation and marking. According to the method, a dynamic scale selector composed of a texture perceptron and a scale regulation and control unit is introduced, the size of a convolution kernel is dynamically adjusted according to the local texture complexity of an image, and fine modeling of different structure areas is achieved.

The invention discloses a traffic image labeling method and device based on a D-S evidence theory and a medium, and relates to the technical field of image labeling. According to the method, two different types of real-time models are simultaneously utilized to process the same image in parallel, and two uncertainty detection results of the same image are obtained; a KM algorithm is utilized to match targets in two uncertainty detection results, then a prior credibility score is utilized to reduce a conflict coefficient, and two different types of small model prediction results are combined through an uncertainty theory. According to the traffic image labeling method and device based on the D-S evidence theory and the medium, the strong generalization ability of the open set model is utilized to make up for the defects of a closed set model, the use of a large model to improve the hardware dependence is avoided, the precision problem of a single small model is made up under the condition that the efficiency is ensured, and the iteration duration of the model is shortened.

The invention provides a three-dimensional target marking method and device based on a point cloud data-assisted two-dimensional image, and the method comprises the steps: fusing precise three-dimensional point cloud information obtained by a laser radar and two-dimensional image data collected by a camera based on a point cloud data and image data cooperation three-dimensional marking method; and a dynamic high-precision three-dimensional target marking system is constructed. Specifically, a space-image relationship is established through three-dimensional point cloud information and a two-dimensional image plane, and three-dimensional information of a target is mapped into a two-dimensional image, so that geometric and semantic information labeling is carried out on the target in the two-dimensional image, information loss of two-dimensional visual data in dimensions such as depth, attitude and space structure is made up, and the accuracy of the three-dimensional information labeling is improved. And meanwhile, when the three-dimensional point cloud is unmeasurable, a three-dimensional target labeling mode is dynamically adjusted in combination with two-dimensional image labeling information. According to the method, through dynamic high-precision three-dimensional target labeling, the obtained image-label can be used for training and reasoning of a three-dimensional target detection network, and the method has a wide application prospect.

The invention discloses an intelligent bone marrow megakaryocyte morphology detection method which comprises the following steps: S1, data preparation: collecting and preprocessing a digital large map of a bone marrow smear, labeling megakaryocytes, and establishing a labeled sample; s2, generating and sorting a sample: extracting a small graph sample by taking megakaryocyte as a center; s3, constructing a deep learning model: constructing and training a deep convolutional neural network, and performing model optimization and performance improvement by using the generated small image sample set; s4, large image detection and reasoning: calling the trained model for reasoning by adopting a sliding window mechanism, and fusing detection results of a plurality of small windows back to an original large image through confidence weighting and a non-maximum suppression strategy; and S5, target cell segmentation: carrying out target segmentation on the detected megakaryocyte, and introducing a pyramid structure for cells with different sizes to obtain an accurate segmentation mask of each target cell. According to the method, the megakaryocyte detection and segmentation precision is improved through large image labeling, small image training and a sliding window reasoning strategy.

The invention discloses a semi-supervised medical image segmentation method based on causal uncertainty decomposition, and belongs to the field of medical image processing and artificial intelligence. According to the method, a segmentation model of teacher and student architectures is constructed, and a causal uncertainty decomposition module, a self-adaptive consistency learning module and a topology perception consistency loss module are integrated. The total uncertainty is decomposed into cognitive uncertainty and random uncertainty, so that targeted processing is realized; a dual-path weight fusion and differential modulation strategy is adopted to realize pixel-level adaptive learning; and a Betti number is introduced to calculate a topological distance, so that the integrity of an anatomical structure is kept. According to the method, under the condition that only 5%-20% of annotation data is used, the Dice coefficient on multiple medical image data sets is increased by 3.2%-4.8%, the segmentation precision and the boundary positioning accuracy are remarkably improved, the segmentation problem under the condition that medical image annotation is scarce is effectively solved, and the method has important clinical application value.

The embodiment of the invention relates to a multi-round medical image annotation method and device introducing a cross validation mechanism, and the method comprises the steps: transmitting a first image to a plurality of expert annotation interfaces, and merging the feedback annotation sets of all interfaces to obtain a first annotation set; setting cross validation items of every two annotation boxes in the first annotation set and constructing a corresponding cross validation matrix; on the basis of a cross validation matrix, dispute-free annotation box extraction, dispute-free annotation box aggregation and consistency score estimation are carried out; if the score is lower than a threshold value, a round of multi-person labeling is initiated again, otherwise, when the dispute labeling box set is empty, the non-dispute labeling box set serves as a final labeling result, when the dispute labeling box set is not empty, reexamination is conducted on the dispute labeling box set, and a set of the reexamination result and the non-dispute labeling box set serves as the final labeling result. According to the method, the labeling error of each image can be reduced, the overall labeling quality of all the images is improved, and the stability of the overall labeling quality is guaranteed.

The embodiment of the invention discloses an image auditing method and device based on a co-creation annotation mode, equipment and a medium. A specific embodiment of the method comprises the following steps: acquiring medical film and television data as initial data; preprocessing the initial data to obtain a task image set; distributing the task image set to at least one student terminal; in response to the detected annotation information sent by the student terminal, generating annotation feedback information according to the annotation information; sending the labeled feedback information to the student terminal; in response to the received annotation task image submitted by the student terminal, performing preliminary quality inspection on the annotation task image; sending the preliminary quality inspection result to an expert end; and in response to received auditing information corresponding to the preliminary quality inspection result sent by the expert terminal, sending the auditing information to the student terminal. According to the embodiment, a co-creation annotation mode is combined with a deep learning technology, so that efficient, accurate and high-quality image annotation auditing is realized, and the overall quality of annotation data is improved.

The invention relates to the technical field of brain tumor image segmentation, in particular to a brain tumor segmentation method and system based on anatomical perception symmetric comparison and cross-modal migration. The method comprises the following steps: carrying out data preprocessing on acquired multi-modal MRI image data; constructing a brain tumor segmentation model based on anatomical perception symmetric comparison and cross-modal migration; performing model training based on a two-stage decoupling training strategy; and performing model reasoning by using the trained model, and outputting a brain tumor segmentation result. Through a self-supervised learning framework, pre-training is carried out by using unmarked MRI data, dependence on a large-scale marked data set is greatly reduced, the problems of time consumption and high cost of medical image marking are solved, and the applicability of a model in a limited data scene is improved.

The invention discloses a semi-supervised image annotation method based on a limited label data set, and the method comprises the steps: taking a FixMatch frame as a basis, and integrating a learnable batch normalization module, a dual-scale parallel convolution module, a content and style separation dual-branch module and a dynamic residual gating module in a ResNet backbone network, the stability of feature extraction and the adaptive capacity to enhanced disturbance are improved. For a label-free sample, a multi-level pseudo-label fusion mechanism is provided, prediction distribution of weak, medium and strong enhanced views is synthesized, and high-confidence pseudo-labels are generated through confidence weighted fusion of multi-level enhanced views and comparison and screening with a category threshold. On the basis, a joint loss function composed of label supervision loss and pseudo label consistency loss is constructed, and a plurality of key control parameters in FixMatch + + are adjusted and optimized in a pre-experiment and grid search combined mode to obtain a group of optimal parameters of the model. Finally, a user inputs a label-free image into the trained FixMatch + + model, and the model can automatically generate a high-confidence pseudo label, so that the number of labeled samples in a limited labeled image set is increased, and the classification precision is improved. By implementing the method, the manual annotation cost can be reduced, and efficient and reliable support is provided for image analysis and recognition tasks.

The invention discloses an information processing method and device for fish hemorrhagic disease detection, equipment and a medium, and relates to the technical field of intelligent agriculture, and the method comprises the steps: obtaining a first healthy fish image and a second healthy fish image, converting the second healthy fish image into a diseased fish image through a cyclic generative adversarial network, and obtaining a diseased fish image; constructing an initial training set by using the healthy fish image and the diseased fish image; labeling the fish individuals in the initial training set by using an image labeling model, and obtaining a target training set obtained after the expert performs health state classification on the fish individuals in the labeled training set; and training the initial image detection model based on the target training set to obtain a to-be-detected fish image, and performing hemorrhagic disease detection on fishes in the to-be-detected fish image by using the target image detection model. A healthy fish image sample is converted into a diseased fish image through the cyclic generative adversarial network, and the problem that the model cannot be trained due to insufficient abnormal samples is solved.

The invention discloses a man-machine collaborative remote sensing image intelligent labeling method and device based on a visual large model. The method comprises the steps of obtaining remote sensing image data to be labeled, and performing image enhancement processing to obtain enhanced remote sensing image data; inputting the enhanced remote sensing image data into a visual large model for mask segmentation processing, and outputting a plurality of target segmentation masks and corresponding confidence coefficients; marking layer graphs with different colors on the to-be-marked remote sensing image data to form marked remote sensing image data, and displaying the marked remote sensing image data to a user; and the user performs confirmation operation, and stores the labeled remote sensing image data as a GeoTIFF file format image with geographic reference information. In the embodiment of the invention, the image labeling precision of complex ground objects, multiple regions and the like is obviously improved.

The invention provides an image annotation method and device. The image annotation method comprises the following steps: acquiring image data including traffic control facilities; target detection is carried out on the traffic control facilities in the image data through multiple preset models, the detection result of the traffic control facilities output by each preset model is obtained, and the preset models comprise visual language models; performing target matching on the detection results output by the plurality of preset models to obtain a target matching result; determining an association rate index according to the target matching result and the detection result of each preset model, wherein the association rate index is used for evaluating the consistency of the detection results among the plurality of preset models; and under the condition of determining that the detection results output by the plurality of preset models meet a consistency condition according to the association rate index, performing tagging processing on the detection results output by the plurality of preset models according to the target matching result, and obtaining tag information of the image data.

The application provides a lung CT image processing method and system based on multi-scale space semantic fusion, which comprises the following steps: collecting multiple lung CT-DICOM images, and performing quality inspection processing and format conversion to obtain original sample images; pre-processing and lung parenchyma segmentation are performed on the original sample images to obtain standard sample images; positive and negative samples are determined according to the image labeling results, and the positive and negative samples are subjected to random interference to obtain expanded sample images; a training data set is generated based on the expanded sample images and the standard sample images; the YOLOv12 network is improved based on the MSSF module and the C3K2_MSSF module to obtain an improved YOLOv12-3D network, and the improved YOLOv12-3D network is trained by using the training data set to obtain a target detection model; and the CT image to be detected is input into the target detection model to obtain detection information. The improved YOLOv12-3D network architecture realizes deep fusion of three-dimensional space features and multi-scale space semantic features in the feature extraction stage, and significantly improves the extraction rate and efficiency of small targets.

This specification provides an image annotation model training method, image annotation method, and apparatus. The image annotation model training method includes: determining initial training data for an image annotation task, wherein the initial training data includes a training image, annotation instructions corresponding to the training image, and target region locations corresponding to the annotation instructions; identifying the initial training data to determine text data and multi-granularity location information of the text data, wherein the multi-granularity location information includes location information of at least two different text dimensions; constructing target training data based on the initial training data, the text data, and the multi-granularity location information; and training the initial image annotation model using the target training data and the target region locations to obtain a target image annotation model, wherein the target image annotation model is used to perform the image annotation task.

Disclosed are an image labeling method and device, a storage medium and equipment, wherein the method comprises: obtaining a three-dimensional point cloud of a target scene and at least one to-be-labeled image sequence, labeling static elements in the three-dimensional point cloud of the target scene to obtain labeling information of the static elements in the three-dimensional point cloud, and then projecting the labeling information of each static element in the three-dimensional point cloud to at least one to-be-labeled image set corresponding to the target scene, thereby realizing labeling of static elements in the at least one to-be-labeled image set corresponding to the target scene. Based on the embodiments of the present disclosure, labeling of static elements in all to-be-labeled images in the at least one to-be-labeled image set corresponding to the target scene can be realized at one time, and compared with labeling of to-be-labeled images corresponding to different orientations of the target scene one by one, the image labeling efficiency can be effectively improved.

The utility model provides a keyboard circuit for remote sensing image labeling, which relates to the technical field of keyboard circuits and comprises a break point moving key, a function control key and a single chip microcomputer used for controlling terminal equipment to perform remote sensing image labeling according to input commands of the break point moving key and the function control key. One end of the break point moving key and one end of the function control key are electrically connected with the input end of the single-chip microcomputer, the other end of the break point moving key and the other end of the function control key are electrically connected with the grounding end of the single-chip microcomputer, and the output end of the single-chip microcomputer is connected with the terminal equipment. According to the utility model, the labeling operation is effectively simplified, and the label manufacturing speed and the marking accuracy of the folding point position are improved.

The invention belongs to the field of image processing and computer vision, and relates to an object-level contrast learning method for multi-modal target detection. The invention provides an object-level intra-modal and cross-modal combined contrast learning method aiming at the problems that multi-modal remote sensing image labeling cost is high, a pre-training structure and a detection task are not matched, and complementary information among modals is insufficient in utilization. The method comprises the following steps: obtaining and preprocessing paired visible light and infrared images, and generating and screening candidate boxes; performing multi-view enhancement on the two-mode image and synchronously mapping a proposal box; a double-branch pre-training network is constructed, object features are extracted in a multi-level mode in a feature pyramid, and target network parameters are updated through intra-modal and cross-modal comparison loss joint optimization and index moving average. And after pre-training is completed, migration to a detection model is carried out, multi-modal fusion detection is realized through fine adjustment of a small amount of annotation data, the detection precision and robustness can be improved, and annotation dependence is reduced.

The application discloses a coal mine transportation belt deviation detection method based on optical flow detection and end-to-end, and belongs to the technical field of safety monitoring. In view of the problems that the prior art cannot realize real-time monitoring on the running condition of the belt, the inspection efficiency is low, and there is a certain lag, a data set is made by collecting a coal mine transportation video, a carrier roller is labeled with the aid of image labeling software, and target frame position information of the carrier roller is calculated by using a carrier roller detection model, a slope of a belt transportation direction is calculated by using an optical flow detection algorithm, a straight line is determined according to the slope and the target frame position information of the carrier roller, the target frame of the carrier roller is divided into left and right regions, an edge graph obtained through edge detection and the target frame of the carrier roller with the divided position are used to generate a mask mask, an interested region is extracted, straight line information in the edge graph is processed in combination with straight line detection, position information of the belt and the carrier roller is determined, and whether the belt deviates is judged.

The invention discloses an image annotation automatic quality inspection method, and relates to the technical field of image annotation quality inspection, and the image annotation automatic quality inspection method mainly comprises the steps: processing original data to obtain training data; constructing a pseudo-twinning neural network, and training the pseudo-twinning neural network by using the training data and the loss function to obtain a quality inspection model; and predicting the image annotation data to be subjected to quality inspection by using the quality inspection model to obtain a quality inspection score, and endowing a quality inspection result to the image annotation data to be subjected to quality inspection. By implementing the image annotation automatic quality inspection method provided by the invention, the accuracy, quantification and efficiency of image annotation automatic quality inspection can be improved.

The invention provides a medical image intelligent labeling and auditing method based on deep learning, and relates to the technical field of medical image labeling, and the method comprises the steps: carrying out the preprocessing of medical image data, and obtaining the preprocessed image data; performing two-dimensional evaluation on the preprocessed image data based on image complexity and labeling task complexity to obtain a total complexity score; dividing the preprocessed image data into a simple level, a medium level and a complex level according to the total complexity score; carrying out labeling processing on the preprocessed image data by adopting a differential labeling strategy to obtain a labeling result; performing quantitative evaluation on the labeling result to obtain a quality score; extracting labeling process features, and dividing labeling results into high quality, medium quality and low quality; and determining an auditing strategy, auditing the annotation result, and outputting the annotation result which is audited to be qualified. According to the method, objective evaluation of labeling quality and reasonable configuration of auditing resources can be realized, and the consistency of auditing is guaranteed.

The invention discloses a data labeling method and system for plant leaf and fruit disease and insect pest detection, and relates to the technical field of artificial intelligence and agricultural information.The method includes the steps that firstly, a plant image is obtained, and whether the image is clear and contains a target subject or not is judged; lesion type preliminary judgment is carried out on the images meeting the conditions, and the images are divided into healthy plants, insect bodies or worm eggs or plants with focuses; and according to factors such as the distribution form (isolation or density) of the insect bodies, the deformation degree of the lesions, the boundary definition and the like, selecting a proper labeling strategy, including labeling covering the whole leaves or fruits, single insect body or lesions or an affected area. According to the scheme, through process decision and multi-strategy matching, the standardization degree and adaptability of plant disease and insect pest image labeling are improved, the method is suitable for constructing a high-quality training data set, and the recognition precision and generalization ability of a plant disease and insect pest detection model are remarkably improved.

The invention discloses a visual identification method and system for the grinding quality of a cover plate glass edge R corner, and belongs to the technical field of machine vision and intelligent detection. Multiple groups of high-resolution images of an R corner area are collected under the irradiation of a multi-angle light source, and image edge gray scale gradient features are extracted to construct a feature set; calculating a curvature change sequence according to gray abrupt change point distribution, and identifying a curvature anomaly concentrated region as a suspicious region; extracting textural features such as sub-pixel-level crack textures, reflection highlight interference modes and gray level distribution offset in the suspicious area; inputting the curvature and the texture features into a convolutional neural network model, and outputting a polishing quality confidence score; carrying out qualification judgment according to a scoring result, and carrying out image labeling on an abnormal position to realize defect tracing and process feedback; according to the invention, high-precision and automatic polishing defect identification can be realized, and the detection efficiency and the product yield are improved.

The invention relates to an automatic image labeling method based on an unmanned aerial vehicle GPS and tower coordinates. The method comprises the steps of S1, data preprocessing; s2, data matching; s3, a double-tower competition judgment mechanism; s4, image feature auxiliary verification; and S5, self-adaptive annotation output is carried out. According to the invention, through a mode of combining spatial distance calculation and image feature recognition, efficient and accurate labeling of the power tower in the unmanned aerial vehicle inspection image is realized, and scene adaptability and labeling reliability are improved.

Embodiments of the present disclosure disclose an image labeling method and device, electronic equipment and storage medium, wherein the method comprises: labeling each infrared image through a grayscale image labeling model to obtain first pseudo labels of the infrared images; wherein the grayscale image labeling model is constructed based on grayscale images converted from each color image and label data of the color images; wherein the infrared images and the color images constitute paired images; according to the correspondence relationship between the same points of the grayscale images converted from the color images and the corresponding infrared images, the label data of the color images is migrated to the corresponding infrared images to obtain second pseudo labels of the infrared images; and according to the first pseudo labels and the second pseudo labels, the label data of the infrared images is determined. The labeling efficiency can be improved, the labeling period can be shortened, and the labeling cost can be reduced.

The invention discloses a truth value generation method and device and a vehicle, and belongs to the field of image annotation. According to the method, a third pose of a target object in a local coordinate system at a target moment is determined through a first pose of a vehicle in a global coordinate system at the target moment and a second pose of the target object in the global coordinate system at the target moment, so that a truth value of the target object is generated. The truth value of the target object comprises the third pose of the target object at the target moment, and the target moment is the exposure moment when the camera on the vehicle shoots the target image, so that the truth value of the target object is aligned with the target image shot by the camera in time; according to the invention, the deviation when the truth value of the target object is labeled on the target image is reduced, and the problem that the accuracy of labeling the truth value generated in the related technology on the image is not high is solved.

The invention relates to the field of computer vision and intelligent manufacturing, in particular to a vehicle charging port image marking method and device, and the method comprises the steps: obtaining a vehicle charging port image, and carrying out the local frame selection processing; sequentially carrying out graying processing, contrast-limited adaptive histogram equalization processing and median filtering processing; carrying out edge detection by using a Canny edge detection algorithm; adopting a Hough circle detection algorithm to generate an initial position parameter of the circular hole; or, adopting a pre-trained convolutional neural network semantic segmentation algorithm to carry out pixel-level prediction, and extracting corresponding edge points as initial position parameters of the circular holes; if it is judged that the precision of the initial position parameter does not meet the preset labeling requirement, click operation is executed, and a correction point set is formed; and based on the correction point set and the edge points corresponding to the initial position parameters, fitting an ellipse to obtain a marking result of the charging port circular hole. The method can improve the labeling efficiency, guarantees the labeling precision and stability, and is adaptive to subsequent deep learning segmentation and pose estimation algorithms.

The invention provides an image annotation method based on a multi-modal large model, and belongs to the field of image annotation. The problem of low image annotation efficiency is solved; the method specifically comprises the following steps: extracting image features of image data and text features of text information; designing a double-flow encoder according to the image feature of each piece of image data; obtaining an index table of the text information, and constructing an image-text mapping network in combination with the image features; marking a target image according to image features in the image data, and generating a text description for each marked position in the target image according to the mapping network; if a certain area of the target image is labeled for multiple times, re-labeling is carried out according to the double-flow encoder of each piece of image data; according to the method, the image information and the text information corresponding to the image information are subjected to feature extraction, image feature-text feature-text description mapping is constructed, the target image is labeled as the generated text description, and the image labeling efficiency is improved.

The invention relates to an image annotation method and device, a storage medium and electronic equipment. The method comprises the following steps: inputting to-be-labeled image data into a visual encoder of a preset multi-modal model for feature vector conversion processing to obtain an image embedding vector; obtaining a text set embedding vector corresponding to the preset text label set, the text set embedding vector being obtained by performing vector conversion on the preset text label set based on a text encoder of the preset multi-modal model, and storing the text set embedding vector as a model parameter of the preset multi-modal model; determining a target prediction result based on the image embedding vector, the text set embedding vector and a preset prediction model; and performing annotation processing on the to-be-annotated image data based on the target prediction result to obtain target annotated image data. Through the preset multi-modal model for storing the text set embedding vector, the data generation efficiency and the label quality are improved, the problem of identification range limitation caused by a label library generated based on image data is solved, open label expansion is supported, and the accuracy of image labeling is improved.

The invention provides a multi-modal data labeling method, system and device for natural driving and a vehicle, and relates to the technical field of intelligent driving. According to the method, multi-modal data of a driver state, a vehicle state and a traffic environment are synchronously acquired, time sequence alignment is realized based on a GNSS timestamp, and a structured multi-modal fusion data stream is constructed; performing target detection and semantic segmentation on the image data in combination with a YOLOv8 multi-task network to generate a preliminary labeling result; further introducing an attention sensitive area and a physiological wake-up state analysis mechanism of the driver to realize dynamic adjustment of an image labeling result, and forming an intelligent labeling result with human factor perception enhancement; finally, a key multi-modal data sample is screened out according to the labeling result and is used for driving behavior modeling and intelligent driving model training, the accuracy, semantic expression ability and application scene adaptability of data labeling are effectively improved, and high-quality data support is provided for personalized learning and safety decision making of an intelligent driving system.

The application provides a kind of image classification labeling method and system based on joint loss, it is related to image classification labeling technical field, by extracting the rust distribution area of shell surface, the rust area proportion is obtained;Further, the partial discharge amount and the sealing damage grade are extracted from the leakage current signal between the shell and the internal component;Then start insulation resistance test, obtain insulation resistance value and sealing state coefficient;Further evaluate the influence amplitude of appearance aging on equipment health, determine the appearance loss proportion of equipment;Combined with insulation resistance value and partial discharge amount, the influence amplitude of insulation deterioration on equipment health is evaluated, and then the insulation loss proportion of equipment is determined;According to the insulation loss proportion and the appearance loss proportion, a joint loss function is constructed, and then the equipment health determination result is embedded in the classification label of image labeling system.The application can improve the representation accuracy of substation equipment image classification labeling on the real health status of equipment.