1021 results about "Imaging condition" patented technology

The invention provides a wound surface grading model construction method and a wound surface self-analysis system, and the method comprises the steps: processing an obtained wound surface image, clinical text description data and structured background information data through a specific feature extraction strategy, and obtaining an image feature vector; clinical text description data and structured background information data are subjected to cleaning, word segmentation, entity labeling and other operations, a wound semantic evolution graph is constructed, related vectors are fused to obtain text embedding, wound background context vectors are generated according to the structured background information data, dynamic weighting, splicing and fusion are performed on image and text feature vectors, and the image and the text feature vectors are subjected to image fusion. According to the method, the fusion feature vector is obtained, the corresponding grading model is constructed according to the fusion feature vector, more accurate, comprehensive and explainable grading evaluation can be performed on different types of wounds, and a self-analysis system designed for the constructed model can quickly and accurately judge the wound image condition shot by a user.

The present invention optimizes conditions of an imaging device when acquiring an image so as to improve the accuracy of image recognition. An image recognition system comprises: an image acquisition unit for acquiring an image captured by an imaging device; a recognition model generation unit having at least one environment recognition unit, recognizing at least one image by the environment recognition unit, and generating a recognition model; and a state estimation unit for estimating the state of the imaging device and the characteristic of the imaging device that corresponds to said state, on the basis of the image and the recognition model. The state estimation unit further generates an imaging correction parameter to correct the imaging condition of the imaging device, on the basis of the estimated state and characteristic and / or the recognition model.

The invention discloses a cultivated land non-agrochemical detection method combining an attention mechanism and Mama, relates to the technical field of change detection, and solves the problems that during existing cultivated land non-agrochemical detection, false change of a detection result is caused by changes of imaging conditions, accurate spatial information is lost in downsampling operation, and the detection result is not accurate. Small targets cannot be effectively positioned, detail features cannot be effectively captured, missing detection is caused, and the edge of a change area is rough. According to the method, features of different levels and different scales are reserved through feature extraction, depth semantic information and space detail information are fused, information in all directions is thoroughly scanned through selective scanning, the global dependency relationship in the remote sensing image can be effectively captured, targets of different sizes are considered, and the global dependency relationship in the remote sensing image can be effectively captured. And the problem of missing detection of small targets is greatly improved. Through a cross attention mechanism, the features of the two time points are fused, and the space-time dependency relationship of the double-time-phase image is better captured, so that the model performance is improved.

The invention relates to the technical field of crack detection, in particular to a visual detection method and system for cracks machined on the surface of an automobile mold, and the method comprises the following steps: obtaining an image sequence of the surface of the automobile mold from a camera, extracting pixel data of the image sequence, and generating an original pixel result; and carrying out gray value conversion and noise data elimination on the original pixel result to obtain a processed pixel result. According to the method, the basic information of each pixel point in the image is extracted and is converted into a form which is easier to analyze, so that the feature content is purer in a mode of eliminating noise points and refining gray features in the image. On the basis, a feature information accumulation and distribution correction means is adopted to enable edge features to be converted from a disordered state to a clear and ordered direction, the variation amplitude of parameters under various image conditions is coordinated, and feature parameters are not prone to large offset due to environmental differences.

The invention provides a mobile phone glass quality detection method and system based on image detection, and relates to the technical field of image defect detection, and the method comprises the steps: configuring an imaging condition for collecting a mobile phone glass image, and collecting an original image of mobile phone glass according to the configured imaging condition; constructing a transparency enhancement algorithm according to a transparent background existing in the collected original image, and processing the original image according to the transparency enhancement algorithm to obtain an enhanced image; a crack boundary self-enhancement step is introduced, micro cracks and fuzzy scratches existing in an enhanced image are positioned, the enhanced image is marked according to the positioning result of the micro cracks and the fuzzy scratches, and a marked image is obtained. The phenomenon of false detection or missing detection easily occurring in mobile phone glass detection under a transparent background in related technologies is solved through a transparency enhancement algorithm; and the problem that boundary fuzzy defects such as microscopic cracks and fuzzy scratches with extremely low contrast are difficult to identify is solved through the crack boundary self-enhancement step.

The invention discloses a highway vehicle track monitoring method and system, and the method comprises the steps: carrying out the preprocessing of a pavement vibration signal of a certain road segment through employing Hilbert transform, and obtaining an original vehicle track image with noise, and taking the image as training data in a data set; performing enhancement processing on the original vehicle track image by using a Gaussian kernel function, and then marking a label of the enhanced vehicle track image as label data in the data set; taking vehicle track images with different characteristics of label data in a similar data set as track image conditions, and generating a synthetic noisy image with real track characteristics under the control of the track image conditions; taking the synthesized noisy image and the track image condition as training data and label data in a data set to obtain an expanded data set; and training a de-noising generative adversarial model based on the expanded data set to obtain a de-noising model for de-noising the road vibration signal of any road section to obtain vehicle trajectory information.

The invention relates to the technical field of building damage identification, and provides a damage degree identification method, system and equipment based on image data and a medium, which can realize cross-disaster double-temporal building damage degree evaluation and is used for building damage degree evaluation and building positioning through an end-to-end convolutional neural network. And experiments are carried out on an xBD data set, so that the network provided by the method provided by the invention is proved to have better performance. According to the method, dual-time-phase feature fusion is adopted to effectively fuse pre-disaster and post-disaster feature maps, and feature fusion is carried out on dual-time-phase feature maps to enhance feature representation; and meanwhile, style unification is carried out by adopting fast Fourier transform, so that the problem of different dual-time-phase data imaging styles caused by different imaging conditions is reduced.

The invention belongs to the technical field of image processing, relates to a multi-scale road crack detection method and device in extreme weather and a medium, and relates to the technical field of image processing, and the method comprises the steps: constructing an extreme weather data set; constructing a target detection network; training a target detection network by adopting the data set to obtain a target recognition model; according to the method, the lightweight backbone network CAPNet is adopted to replace a backbone network of the RT-DETR, and the feature extraction efficiency is improved; a cascade multi-branch feature fusion module is used for replacing a CCFM module in a traditional neck network, dynamic integration of multi-scale features is achieved, a multi-scale edge enhancement module is additionally arranged in a network structure, the perception ability of the model to crack edges of different scales is enhanced, the feature expression problem under the low contrast and blurred image conditions is effectively solved, and the dynamic integration of the multi-scale features is achieved. And the balance between the detection precision and the efficiency is realized.

The invention provides a calcium imaging neural signal extraction method and product based on self-supervised pre-training, and relates to the technical field of artificial intelligence. Based on a pre-training data set containing a large amount of unlabeled two-photon calcium fluorescence imaging data, a pre-training decoding network and a corresponding pre-training task are self-supervised, and a pre-trained space-time coding network is trained by taking minimization of a pre-training loss function as a target; the method comprises the following steps of: firstly, establishing an encoder and decoder network, establishing fine-tuning data with accurate space-time marked neuron calcium signal positions through simulation, simultaneously performing fine-tuning on the encoder and decoder network by taking minimization of a fine-tuning loss function as a target, and checking the algorithm extraction precision based on various actual imaging data to obtain a calcium imaging signal extraction algorithm network with strong generalization performance. Therefore, a calcium signal extraction model which can be generalized in various imaging conditions and model biological brain regions can be obtained through training without manual labeling, a high-accuracy neural signal extraction result is obtained, the application difficulty that a deep learning model lacks data generalization ability is overcome, and the accuracy of a neural signal extraction result is improved. Calcium imaging neural activity analysis based on self-supervised pre-training and wide in application is achieved.

The invention relates to a high-resolution remote sensing image change detection method and system based on decoupling representation learning, and solves the defects of false change and non-ideal detection precision caused by inconsistent imaging conditions of different time phases compared with the prior art. The method comprises the following steps: obtaining a training sample; constructing content branches; constructing style branches; training a multi-branch parallel framework; obtaining a high-resolution change result; and separating image styles and obtaining a recovery result. According to the method, a reliable high-resolution remote sensing image change detection result can be obtained under the condition of multi-temporal complex imaging condition interference.

The invention provides an orientation and imaging method and system for sound wave detection data in a tunnel hole, and the method comprises the steps: obtaining sound wave data in different directions responding to the same excitation sound wave, rotating the sound wave data until an orthogonal component disappears, and determining the direction of a reflector according to a rotation angle; carrying out weighted summation on the sound wave data acquired by the receiving array to obtain scalar output, calculating an optimal weight to receive a target signal from a reflector orientation to the greatest extent, and carrying out weighted processing according to the optimal weight to obtain a superposed signal; and solving a three-dimensional elastic wave wave equation based on the processed superposed signal to obtain a forward wave field and a reverse wave field, and performing migration imaging by using a cross-correlation imaging condition to obtain a three-dimensional migration imaging result. The method can enhance the signal-to-noise ratio of the weak reflection signal, and achieves the quick and accurate judgment of the orientation of the target body in front of the tunnel face.

The invention belongs to the field of CT image processing, and particularly relates to a CT image reconstruction method based on a three-dimensional diffusion model and a related device.The method comprises the steps that a medical CT scanner is adopted to obtain three-dimensional CT voxel data, and the three-dimensional CT voxel data is preprocessed; extracting a medical object surface point cloud from the preprocessed three-dimensional CT voxel data by adopting a voxel-level reconstruction algorithm, and generating three-dimensional sparse point cloud data; processing the three-dimensional sparse point cloud data by adopting a 3D Gaussian splashing technology, and converting the three-dimensional sparse point cloud data into three-dimensional Gaussian distribution data by using a pre-trained three-dimensional Gaussian kernel; gradually adding Gaussian noise to the three-dimensional Gaussian distribution data by adopting a three-dimensional diffusion model, and gradually removing the Gaussian noise to generate reconstructed three-dimensional Gaussian distribution data; and projecting the reconstructed three-dimensional Gaussian distribution data to a two-dimensional plane by adopting a rendering technology to generate a two-dimensional CT reconstructed image. According to the method, the advantages of the 3D Gaussian splashing technology and the three-dimensional diffusion model are combined, efficient, real-time and denoising medical image reconstruction can be achieved under the low-dose CT imaging condition, and meanwhile the problem of white floater artifacts possibly occurring in the reconstruction process is effectively solved.

The invention discloses a mold defect visual inspection method, particularly relates to the technical field of industrial machine visual inspection, and is used for solving the technical problem of image spatial variation blurring caused by mechanical vibration under a mobile shooting condition. The method comprises the following steps: acquiring a to-be-detected image on the surface of a mold, analyzing the gradient magnitude of each region, determining the fuzzy characteristics of different regions in the to-be-detected image according to the difference of the gradient magnitudes, evaluating the expected confidence of each region for executing the deblurring operation based on the fuzzy characteristics, and executing the deblurring operation on the regions to obtain a preliminary restored image; an artifact index is calculated in the uniform background area of the preliminary restored image, the distribution concentration degree of image components in each local feature area in the frequency domain is analyzed in the preliminary restored image, and the distribution concentration degree is compared with a preset defect judgment threshold value adjusted according to the artifact index; judging whether the corresponding local feature region is a defect region or not; accurate recognition of mold surface defects under complex imaging conditions is realized.

The invention provides a rapid Marchenko imaging method for undulating surface conditions, and the method comprises the following steps: S1, inputting an earthquake shot record of a fixed surface and a depth domain undulating migration surface, and correcting the earthquake shot record to the migration surface through a static correction method; s2, inputting a depth domain seismic velocity model, and constructing an initial downlink focusing function from an underground target area imaging point to an undulating surface migration surface through a ray tracing algorithm; and S3, taking the shot record on the fluctuating offset surface and the initial downlink focusing function as input, and calculating uplink and downlink Green functions from the underground imaging point to the ground through an iterative method. And S4, applying an energy normalization cross-correlation imaging condition to the reconstructed uplink and downlink Green functions to obtain a Marchenko imaging result. According to the Marchenko imaging method, the problems that conventional Marchenko imaging is low in calculation efficiency and undulating surface conditions cannot be processed are solved, and the Marchenko imaging quality under the undulating surface conditions is ensured while the calculation efficiency is improved.

The invention relates to a robust splicing method for an inner wall image of a drill hole under a multi-interference imaging condition. The method specifically comprises the following steps: S1, expanding an acquired front-view shot inner wall image of the drill hole into a narrow-band image; s2, registering the expanded narrow-band images of the front frame and the rear frame, and determining the vertical offset and the horizontal offset of the reference image and the image to be spliced by adopting a grid acceleration-based template matching method; s3, determining an overlapping region of the reference image and the to-be-spliced image according to the offset, and fusing pixels in the overlapping region to obtain a spliced result image of the inner wall image of the drill hole; and S4, repeating the steps S1 to S3, splicing frame by frame until well logging is completed, and obtaining a panorama of the borehole inner wall image. According to the method, the image splicing problem caused by poor illumination conditions, loss or inaccuracy of reading of an electronic compass and a depth counter and lens rotation disturbance in actual logging operation can be effectively solved, and a smooth borehole inner wall panorama splicing result can be stably obtained.

The invention belongs to the technical field of ocean remote sensing and deep learning, and particularly relates to an SAR image ocean internal wave automatic extraction method which comprises the following steps: step 1, collecting SAR image data of a target sea area, and preprocessing the image, including radiation correction and geometric correction; 2, marking internal wave signals in the preprocessed SAR image in a manual marking mode, generating a truth value image used for deep learning model training, matching a truth value with an original image, randomly selecting four fifths of the truth value image as a training set, and randomly selecting the rest one fifths of the truth value image as a test set; by adopting the alpha-balanced cross-entropy loss function and the online data enhancement technology, the precision and efficiency of extracting the internal wave signal from the SAR image are effectively improved, especially under the complex imaging condition, the internal wave signal can be accurately extracted, high-precision geographic positioning of the internal wave signal is achieved by combining geographic information, and the method has the advantages of being high in accuracy and high in accuracy. The method is suitable for ocean research and high-precision environment monitoring, and has a wide application prospect.

The invention discloses a road broken line automatic repair method based on unmanned aerial vehicle image segmentation and fitting reconstruction, and relates to a remote sensing image semantic processing and road connectivity recovery method. The method comprises the steps of firstly extracting a road category region in an image; skeletonizing the extracted road area to form a road trunk structure; introducing a multi-scale density clustering algorithm to perform multi-level spatial clustering on the breakpoints, and superposing clustering results to enhance breakpoint coverage; screening out breakpoint pairs conforming to broken line characteristics; for each pair of matched breakpoints, backtracking along the road direction to obtain a certain number of skeleton points, and reconstructing a road connection path; and restoring the repaired road in combination with the width information of the original road to form a complete connected road structure. The method can effectively improve the automatic detection and continuity recovery capability of the road broken line area in the remote sensing image, and is suitable for a road structure intelligent restoration task under a low-quality image condition and a complex road network scene.

The invention discloses an X-ray thermoacoustic imaging method based on a diffusion model and sound velocity compensation, and relates to the technical field of X-ray thermoacoustic imaging and deep learning imaging reconstruction. According to the method, the influence of sound velocity non-uniformity on a thermal sound wave propagation path and time delay is fully considered, and a new method combining sound velocity compensation and diffusion model reconstruction is provided; on the premise that the hardware complexity of an imaging system is not increased, accurate correction of a wave propagation path is achieved through sound velocity modeling, and imaging artifacts and space positioning errors are effectively avoided; meanwhile, the image inversion framework based on the conditional diffusion model has excellent noise suppression and high-frequency detail recovery capabilities, and can generate a high-quality thermoacoustic image with a clear structure and remarkable contrast under the imaging conditions of low signal-to-noise ratio, low energy dose and the like.

The invention discloses a target positioning and recognition method for high-precision photogrammetry of a jacket. The target positioning and recognition method for high-precision photogrammetry of the jacket comprises the following steps: obtaining a plurality of jacket images through photogrammetry; drawing a histogram of the image; determining imaging conditions; using a real-time target detection algorithm to coarsely detect a possible circular target area; ellipse detection under different imaging conditions; positioning a circle center; and decoding the coding mark. According to the target positioning and recognition method for high-precision photogrammetry of the jacket, high-precision measurement work of the deepwater ultra-large jacket can be effectively completed through the target positioning and recognition method, and the measurement precision of completion measurement of the deepwater ultra-large jacket is effectively improved.

The invention relates to a zoom binocular system image ship target identification method based on homography matrix mapping, and belongs to the technical field of marine ship target image detection and identification. According to the method provided by the invention, ship targets identified through a deep learning algorithm are in two images of a binocular camera system, and four corner points and a central point of each target serve as corresponding points and are used for constructing a calculation basis of a homography matrix. Bidirectional accurate mapping between the visible light and the infrared image is realized through the constructed homography matrix, and target recognition of deep learning is supplemented. And a homography matrix group based on focal length change is constructed by adjusting the focal length of the binocular imaging system. When missing detection target identification of supplementary deep learning is carried out, the most suitable homography matrix is selected from the matrix library to be applied according to the current imaging condition and the focal length, and detection identification of missing detection or even zero detection ships obtained by a certain modal image only by using the deep learning method is realized.

The invention provides a multi-scale cultivated land change detection system based on frequency domain conversion, and belongs to the technical field of remote sensing image processing and computer vision. Firstly, feature extraction is carried out on a dual-time-phase image to obtain a multi-scale first feature map; performing multi-kernel parallel convolution processing on the first feature map through small convolution kernels with different sizes, and then splicing and fusing the first feature map into a second feature map; performing feature enhancement on the second feature map to generate an extraction feature map; and combining and classifying two paths of extracted feature maps corresponding to the double-time-phase image to obtain a detection map of cultivated land change. Meanwhile, the double-time-phase image for training is subjected to low-frequency feature replacement in the frequency domain, visual feature differences caused by different imaging conditions are effectively eliminated, and false change false detection is reduced. According to the method, false change interference is reduced through low-frequency component replacement, meanwhile, background noise caused by a large convolution kernel and information loss caused by cavity convolution can be avoided through multi-kernel parallel convolution processing of the small convolution kernel, and meanwhile the detection capacity of scale sensitive targets is improved.

An information processing device includes at least one memory storing a program, and at least one processor that, by executing the program, causes the information processing apparatus to acquire an image group obtained by imaging a subject under a plurality of imaging conditions, to select at least one inference model from a plurality of inference models on the basis of at least one imaging condition among the plurality of imaging conditions, and to perform inferencing on images in the acquired image group by using the selected inference model.

Provided by the present disclosure is an ultrasonic phased array-based in-situ imaging method for melt flow in injection molding. The ultrasonic phased array is used for the detection of an injection molding process for the first time, and an effective dynamic monitoring imaging method for a melt front position is developed. A melt flow process in a mold cavity is dynamically monitored by collecting an FMC (Full matrix capture) dataset online. A mapping relationship between an incident angle and a target pixel point is established to rapidly determine time delay of each point in a measurement target region, and a melt bottom image is acquired using TFM (Total focusing method) imaging conditions, from which the melt front can be localized. The provided method is high in measurement accuracy, short in imaging time, and capable of effectively improving imaging efficiency of online measurement.

A mounting machine according to the present invention has a function for automatically determining the positions of measurement points for measuring the substrate height of a substrate on which a component is mounted. The mounting machine comprises an imaging device, an inspection device, and a determination device. The imaging device images, on the basis of a preset imaging condition, temporary measurement points disposed at temporary positions on the substrate. The inspection device inspects the temporary measurement points and the surrounding situation thereof by using a captured image of each of the temporary measurement points, and determines the suitability of the positions of the temporary measurement points. The determination device determines the positions as measurement points when the inspection device has determined that the positions of the temporary measurement points are suitable, and does not determine the positions as the positions of the measurement points when the inspection device has determined that the positions of the temporary measurement points are not suitable.

The invention discloses a process casting image surface defect automatic identification method based on machine vision, which comprises the following steps: acquiring an original image of a process casting, recording an imaging parameter set, and preprocessing to obtain a standardized image; performing homomorphic filtering to obtain an enhanced image and an illumination component, and inputting the enhanced image into an improved OfficientAD algorithm to generate an abnormal score map and a feature residual map; updating homomorphic filtering parameters according to the abnormal score map, the feature residual map and the illumination component, and performing homomorphic filtering for three times to obtain an enhanced image; inputting the enhanced image into an improved OfficientAD algorithm to obtain an abnormal score graph; and performing threshold segmentation and connected domain extraction on the abnormal score graph to obtain a defect candidate region, extracting texture statistics and residual statistics, and matching a defect type feature library to output an identification result. According to the method, stable and consistent automatic identification is realized under complex texture and imaging conditions, and the manual visual inspection cost is reduced.

A computer-implemented method includes converting by a pose tokenizer, based on a learned codebook, pose parameters of a body into a sequence of discrete pose tokens; randomly masking a portion of the sequence of discrete pose tokens; predicting the randomly masked sequence of discrete pose tokens based on multi-scale features extracted from a monocular image by an image conditioned masked transformer; optimizing the sequence of discrete pose tokens by aligning a re-projected three-dimensional (3D) pose with an estimated two-dimensional (2D) pose; directly regressing, from the multi-scale features, a shape parameter of the body and a weak perspective camera parameter; and generating a 3D mesh reconstruction of the body based on the shape parameter and the weak perspective camera parameter.

The invention discloses a method and device for detecting color reducibility of a mobile phone camera and a medium, and relates to the technical field of image quality detection.The method comprises the steps that after geometric alignment is conducted on a color card image set, color block areas are divided, and a cross-light-source color block observation matrix is obtained through color block feature extraction; converting the cross-light-source color block observation matrix into a target color space coordinate, and performing illumination correction to obtain a cross-light-source color coordinate matrix; inputting the cross-light-source color coordinate matrix into a deep learning model, outputting a color block level high-dimensional color embedding matrix, and obtaining a high-dimensional color embedding vector set corresponding to the tested mobile phone camera in combination with an attention weight; calculating a color reducibility error index based on the high-dimensional color embedding vector set in combination with the standard reference library; and performing qualification judgment according to the color reducibility error index to generate a qualification detection conclusion. According to the invention, a stable and reliable technical basis is provided for camera quality detection under a multi-light-source imaging condition.

The invention discloses a compensation device and method for a digital holographic microscope, relates to the technical field of optical imaging, and can dynamically adjust optical response according to wavefront distortion data measured in real time by using a deformable lens group and a real-time wavefront sensing technology. The adaptive optical element accurately controls the light wavefront, effectively expands the imaging depth, optimizes the focus control, and enhances the resolution. In addition, according to the compensation phase algorithm, the required compensation is calculated by introducing a regularization item, so that the adaptability of the algorithm to environment change is improved, and the robustness of the algorithm in the imaging process is enhanced. Reconstruction and post-processing, such as phase recovery and image sharpening, of the digital hologram are carried out through the constructed phase recovery algorithm, a high-quality imaging result can still be generated under the condition that noise is large or imaging conditions change, and it is further guaranteed that the algorithm can maintain high performance under various imaging conditions.

The invention discloses a hyperspectral fast imaging method and system based on spectral difference depth matrix decomposition, and aims at low signal-to-noise ratio data under a limit imaging condition to realize high-quality image recovery through structural modeling of an average spectrum chart and a spectral difference chart. The method comprises the following steps: firstly, quickly collecting and splicing hyperspectral data to form a three-dimensional tensor, and constructing a forward observation model under a weak light condition; decomposing into an average spectrum chart, a spectrum difference chart and a noise item; rearranging the spectral difference graph into a two-dimensional low-rank matrix, and obtaining a space and spectral principal component matrix by adopting PCA decomposition; an unsupervised dual-path optimization network is innovatively constructed; a 2D jump network is used to optimize a spatial principal component so as to model structural information, and a 1D jump network is used to optimize a spectral principal component so as to fit detail changes; and finally, outputting an optimized spectrum difference graph by the network after joint training, and fusing the optimized spectrum difference graph with the average spectrum graph to complete reconstruction. High-fidelity image reconstruction is realized under single-frame and unsupervised conditions, and the reconstruction quality and robustness are significantly improved.

Means for rigorous quantitative assessment of sperm motility are presented, based on a number of movement and morphology parameters measured using various image processing methods. The quantitative assessment thereby achieved is objective and multidimensional, allowing for detailed and repeatable assessment of samples. Deep learning methods are also disclosed for detection and classification of sperm cells (or other types of cells or particles) using neural networks, adapted to work both in good and in poor imaging condition, such as low magnification and resolution. Specific methods for both supervised and unsupervised deep learning approaches are delineated. In a non-limiting disclosure, the methods are particularly adapted to deal with cases of azoospermia, where there is a very low number of sperm cells (most of which do not swim) and a lot of debris in the imaged field of view.