87 results about "Infrared image processing" patented technology

The invention relates to the technical field of power failure prediction, and discloses a power equipment thermal failure monitoring and early warning system fused with infrared image processing. According to the invention, the infrared image acquisition module acquires and standardizes equipment temperature field data, and the electrical parameter synchronous acquisition module acquires load current and environment temperature in real time; the hot spot dynamic analysis module identifies and tracks an overheat area based on a dynamic threshold value, extracts spatio-temporal evolution characteristics of the overheat area, and comprehensively calculates a fault hot spot intensity factor capable of representing an early fault; the electrical fault diagnosis module starts deep diagnosis when the factor is abnormal, and accurately estimates the contact resistance value of the key part through a nonlinear recursive algorithm; and the comprehensive early warning module performs fusion evaluation on the multi-source information, and generates multi-level early warning information based on a layering strategy. According to the method, post-event alarm is converted into beforehand intervention, the sudden failure risk of the equipment is remarkably reduced, and accurate and reliable decision support is provided for predictive maintenance.

The present application relates to the field of infrared image processing, and discloses an infrared small target detection method and device based on image information entropy and multi-scale local contrast measure, comprising: (1) constructing a local weighted information entropy operator to obtain a local weighted information entropy image of an original infrared image; (2) using the weighted information entropy image and the structure tensor theory to construct a background prior and a target prior to obtain a local saliency prior; (3) using the original thermal infrared image to design a local contrast coefficient to obtain a multi-scale local contrast image; (4) using the multi-scale local contrast image and the corresponding structure tensor to design an information filter; and (5) fusing the local saliency prior and the information filter to realize the detection of the infrared small target. The present application comprehensively utilizes the weighted image entropy operator, the multi-scale local contrast measure and the structure tensor theory, and can effectively suppress the background, enhance the target and improve the detection performance of the infrared small target.

The invention provides an unmanned aerial vehicle image ship detection method and system based on FAST features and an HSO algorithm, and relates to the technical field of infrared image processing. The problems that a traditional method cannot efficiently position the ROI and is poor in threshold segmentation effect are solved. According to the technical key points, the method comprises the following steps: carrying out FAST feature detection on a target unmanned aerial vehicle image, and determining an interest region image according to a feature detection result; determining a candidate detection threshold value set for the interest area image by adopting an HSO algorithm, performing iterative optimization processing on the candidate detection threshold value set until a termination condition is met, and outputting a detection threshold value when the termination condition is met; and carrying out image segmentation on the region of interest image by adopting the detection threshold, and carrying out ship detection on the segmented image to obtain a ship detection result in the target unmanned aerial vehicle image. According to the method, the processing range can be greatly reduced, the target detection segmentation threshold search efficiency is improved, the noise immunity is enhanced, and an image target extraction technical system adaptive to multiple complex scenes is formed.

A system for monitoring a switchgear includes an infrared camera; a processing unit; and an output unit. The camera acquires a first infrared image. The processing unit determines a pixel in the first image with a maximum temperature and uses a second number of pixels to determine a temperature interval. The processing unit sorts the pixels in descending order of temperature to determine a threshold temperature and determines that a hot spot exists in the switchgear using the temperature interval for the first infrared image. The output unit is configured to output an indication of a fault in the switchgear when the determination has been made that a hot spot exists in the switchgear.

The invention discloses a multi-scale infrared polarization image enhancement method based on MSD-PCNN, and relates to the technical field of infrared image processing, and the method comprises the steps: firstly, carrying out the multi-scale and multi-direction decomposition of an input intensity image I and a polarization feature map DoLP based on NSST, and obtaining a low-frequency sub-band and a high-frequency sub-band; secondly, according to the obtained low-frequency sub-band, designing a low-frequency sub-band fusion rule based on distance difference perception; and finally, according to the obtained high-frequency sub-band, designing a high-frequency sub-band fusion rule based on MSD-PCNN, and fully extracting texture and edge detail features. According to the MSD-PCNN-based multi-scale infrared polarization image enhancement method provided by the invention, redundant information interference is suppressed, the hierarchical definition of an image structure is improved, and meanwhile, the visual comfort and global naturalness of a fused image are also improved.

The invention relates to the technical field of infrared image processing, in particular to an autonomous inspection operation device and method for a control room, and solves the technical problem of low temperature detection precision in the prior art. The device comprises a data acquisition unit which is used for acquiring infrared image data of equipment in a control room; the infrared image data is used for representing an infrared time domain signal acquired based on infrared radiation reflection of the surface of the equipment in the control room; the signal processing unit is used for carrying out adaptive time-frequency transformation based on an infrared time-domain signal in the infrared image data to obtain a corresponding time-frequency matrix; the time-frequency matrix is used for representing energy distribution of infrared radiation on the surface of equipment in the control room at different times and different frequencies; and the inspection unit is used for separating the target heat radiation based on the time-frequency matrix and performing equipment temperature inspection according to the separated target heat radiation.

The present application relates to a kind of self-adapting wide gray scale range infrared image highlight target suppression method, belong to infrared image processing technical field.The present application utilizes the histogram information of original image, whether according to the decision function adaptive judgment enters highlight suppression algorithm processing flow according to statistical result, histogram of image is gathered and compressed in the flow, while using nonlinear mapping method, to achieve the purpose of effectively suppressing highlight target, so that highlight target and image background are effectively and reasonably displayed in display device.

The application discloses an ethylene cracking furnace tube infrared intelligent analysis system, which comprises, which are connected in sequence, an image acquisition module, a temperature monitoring module, a coking diagnosis module and a health management module; the image acquisition module acquires infrared images of cracking furnace tubes and burners by using an infrared thermal imaging online monitoring system, and establishes a cracking furnace tube infrared image database; the temperature monitoring module extracts and records the outer surface temperature of the ethylene cracking furnace tube from the processed infrared images of the ethylene cracking furnace tube by using an infrared image processing and recognition method; the coking diagnosis module combines the technologies of artificial intelligence and data mining, establishes a coking degree diagnosis and prediction model of the ethylene cracking furnace tube, and realizes early warning and targeted tracking of the coking abnormal conditions; the health management module carries out health evaluation of the cracking furnace tube according to the results obtained by the coking degree diagnosis and prediction model of the ethylene cracking furnace tube, and provides maintenance decision support. The application can realize integrated management of cracking furnace tube detection, diagnosis and maintenance.

The application discloses a non-uniformity correction method and system based on space domain and frequency domain features, relates to the technical field of infrared image processing, and corrects steps as follows: inputting a to-be-corrected image into a trained infrared image non-uniformity correction model to output a corrected image; model training steps are as follows: constructing a training data set based on a visible light data set; constructing an initial infrared image non-uniformity correction model, which adopts a U-Net structure to construct a non-uniformity correction backbone module, and the non-uniformity correction backbone module is provided with a space domain feature extraction module and a frequency domain feature extraction module; iteratively training the initial infrared image non-uniformity correction model by using the training data set to obtain the infrared image non-uniformity correction model. The application captures local pixel-level information through the space domain feature extraction module, combines global frequency spectrum features extracted by the frequency domain feature extraction module, realizes the synergistic effect of local noise suppression and global structure optimization, and improves the precision and robustness of non-uniformity correction.

The invention discloses a new energy automobile operation safety detection system and detection method, belongs to the field of new energy automobile detection, and aims to solve the problem of incomplete new energy automobile operation safety detection items in the prior art. The new energy automobile operation safety detection system comprises an OBD reading module, an electrical detection module, a direct current charging module, a charging detection module, a battery pack sealing detection module, an industrial personal computer, a host and a cloud server. According to the new energy vehicle operation safety detection system and detection method, the battery pack sealing detection module is arranged, the thermal imager and the convolutional neural network are utilized to perform sealing detection on the battery pack on the vehicle, the leakage type can be identified, and the detection accuracy is improved by utilizing an infrared image processing technology. The influence of a complex structure and a complex detection working condition is reduced, the recognition accuracy of the convolutional neural network model is improved, and then the battery pack sealing detection precision is improved.

The application provides an infrared image processing method based on a space-time field and related equipment, and relates to the technical field of infrared image processing. The method comprises the following steps: acquiring continuous infrared images, constructing a unified background image, identifying key points of each target moving object and mapping the key points, determining an image sequence group according to a time sequence, and obtaining a complete motion trajectory curve according to the distribution of the key points. When a split-screen target infrared image is detected, the key points of each part are extracted after splitting, the two parts of the background are matched with the unified background image to determine an initial background area, the distance between the key points and the expected position predicted based on the trajectory, adjacent frames and motion rules is calculated, the current frame and the delayed frame are determined, and finally the complete sequence is obtained by processing the delayed frame. The method in the application can accurately repair the split-screen image in a dynamic scene, and ensure the time sequence coherence and integrity of the infrared image sequence.

The application relates to the technical field of edge computing, and particularly discloses an infrared image processing method for excavator operation early warning based on edge computing, which comprises the following steps: dividing an infrared image into regions according to the temperature values of pixel points in the infrared image to obtain an active region and a background region; distributing the active region to edge nodes for preprocessing according to a network condition score F of the edge nodes; after all the active regions received by an edge node j are preprocessed, the active regions are redistributed to the edge node for preprocessing; after preprocessing of all the active regions is completed, the active regions are combined with the background regions which have not been preprocessed into a target image, and the target image is used for excavator operation early warning; and the real-time degree of the excavator operation early warning is improved.

This invention relates to the field of infrared image processing technology, and more particularly to an infrared image processing method and system based on artificial intelligence. The system includes an infrared image processing center, a scene acquisition module, an image classification module, an image enhancement module, a processing fusion module, a task selection module, and a visual output module. It classifies the original infrared image using a task recognition sub-model, accurately determining three types: conventional processing, mixed defects, and high-probability defects. Mixed defect images are enhanced using a multi-attribute weighted fusion method, while high-probability defect images undergo specific processing according to scene priority, ensuring that core defects are addressed effectively and avoiding a one-size-fits-all approach, significantly improving the targeting of image processing. Simultaneously, by dividing the target area and background area, it objectively assesses the quality from three dimensions: information retention, detail clarity, and noise variance, providing intuitive feedback on whether the processing results meet standards, facilitating timely adjustments to processing strategies by management personnel.

The invention relates to the technical field of infrared image processing, and discloses an infrared image enhancement method based on radiation priori and a generative adversarial network, which comprises the following steps of: constructing a training data set of non-paired low-quality infrared images and high-quality infrared images, constructing a bidirectional cyclic generative adversarial network, pre-establishing infrared radiation quantity databases of different materials, and constructing a training data set of the non-paired low-quality infrared images and high-quality infrared images; the method comprises the following steps: adding a material coding branch in a generative network, inputting the material coding branch in a mapping database, obtaining radiation coding characteristics, constructing a composite loss function, and carrying out feedback optimization on a discriminant network and the generative network by using a training data set through the composite loss function to obtain a trained overall enhanced network. The infrared image to be enhanced is input into the enhancement network, the enhanced infrared image is output, and the defects that an existing infrared image enhancement method depends on paired data, material radiation characteristics are ignored, enhanced image semantics are inconsistent and the like are overcome.

This invention relates to a method and system for super-resolution reconstruction of infrared images based on a micro-scanning device, belonging to the field of infrared image processing technology. The method includes: controlling a micro-scanning device to acquire multiple frames of low-resolution infrared images with sub-pixel displacement; constructing a high-resolution grid, projecting pixel values ​​onto the high-resolution grid through sub-pixel fusion, and accumulating weights to generate a reconstructed image and a weight matrix; generating a confidence map based on the weight matrix, calculating an adaptive sharpening coefficient based on the confidence map, and injecting high-frequency details into the reconstructed image to obtain a 2x super-resolution reconstructed image. Further, a dual-cascade fusion architecture is adopted, transforming the original multi-frame images into four sets of images, each reconstructed at 2x, and then performing a secondary fusion on the resulting intermediate images to achieve 4x super-resolution reconstruction. This invention can effectively suppress artifacts in non-ideal sampling areas, overcome the magnification limitations of fixed-magnification devices, and is independent of training data, exhibiting strong generalization ability.

The application discloses a kind of pre-processing method and system for rock fissure infrared image analysis, it is related to infrared image processing technical field, the method includes: the noise level estimation is carried out to the original infrared image of rock fissure obtained, generates noise feature description information;Based on noise feature description information, the original infrared image is carried out adaptive denoising processing, generates denoising image;Based on denoising image, background separation and high-frequency component extraction are carried out, and generate high-frequency feature image;Based on high-frequency feature image, carry out detail enhancement processing, and generate detail enhancement image;Based on detail enhancement image, carry out adaptive brightness correction processing, and generate pre-processing output image.Adaptive noise suppression and edge preservation to rock fissure infrared image are realized, fissure high-frequency detail feature and trend continuity are strengthened, and the contrast of low brightness area is improved, and high-quality data basis is established for downstream detection and segmentation task.

The application relates to a kind of double-band based infrared image blind cell compensation methods, belong to double-band infrared image processing technical field.The method includes: the double-band infrared image of input X i ( i , j )、 Y i ( i , j ) respectively carry out blind cell detection;Edge extraction is carried out to the double-band infrared image, and edge image Ex i , j 、 Ey i , j ;According to the detection condition and extraction condition, the pixel condition of the double-band infrared image is classified, and the image is output after the pixel is compensated according to the classification condition.The application method can improve the accuracy of blind cell detection, improve the accuracy of blind cell compensation, and effectively improve the compensation effect of large blind cell area in the image by using the difference of double-band background radiation information.​​

The present disclosure provides an image processing device, an imaging apparatus, an image processing method, and an image processing program capable of accurately extracting an abnormal region of a subject from an image. In the image processing device according to one aspect of the present invention, a processor generates a first mask image showing a first region where an abnormality exists on a surface of a subject and a second region including a region where an abnormality exists inside the subject, based on a visible image and a first near-infrared image, acquires a second near-infrared image of the subject captured with light in a second wavelength range in a state where the subject is held in focus with the light in the second wavelength range, and extracts an abnormal region in the first region and the second region based on the first mask image and the second near-infrared image.

This invention discloses an infrared anomaly region detection and segmentation method based on a cascaded architecture, belonging to the fields of infrared image processing and computer vision technology. Addressing the problems of high false detection rate and low segmentation accuracy in existing infrared anomaly region detection methods, this method employs a three-stage cascaded detection-filtering-segmentation architecture: After preprocessing the infrared image, it is input into a target detection model to generate candidate bounding boxes; multi-bounding box fusion technology is used to calculate spatial cue confidence; a secondary confidence assessment and false positive filtering are performed based on the channel attention mechanism and inverse residual structure of a lightweight feature extraction network, generating a filtering score; high-confidence detection boxes are converted into effective spatial codes and used as spatial cue words input into the segmentation model to complete pixel-level fine segmentation. This invention improves positioning accuracy through a multi-bounding box fusion confidence mechanism, reduces the false detection rate through secondary filtering, and achieves high-precision pixel-level segmentation without manual annotation through effective spatial code conversion.

A medium voltage switchgear or controlgear monitoring system includes: an infrared camera; and a processing unit. The infrared camera is mounted within a medium voltage switchgear or controlgear. The infrared camera is configured to acquires an infrared image including image data of two or three current carrying parts of the switchgear or control gear. The two or three current carrying parts are the same current carry part of two or three equivalent systems within the switchgear or controlgear. The infrared camera provides the infrared image to the processing unit. The processing unit determines that the two or three current carrying parts are operating correctly or that one of the two or three current carrying parts has a fault. The determination includes analysis of the infrared image by an autoencoder implemented by the processing unit.

The invention discloses an end-to-end infrared super-resolution reconstruction method, and the method comprises the steps: S1, obtaining original infrared data, carrying out the processing of the original infrared data, and building a high-resolution sample set; s2, performing down-sampling processing on the original infrared data to obtain a corresponding low-resolution sample set; s3, performing data augmentation on the high-resolution sample set and the low-resolution sample set to generate a true-value high-resolution sample set and a true-value low-resolution sample set; s4, constructing an infrared super-resolution reconstruction network; s5, training the infrared super-resolution reconstruction network based on the truth value high-resolution sample set and the truth value low-resolution sample set to obtain optimal network parameters; and S6, performing end-to-end reconstruction on the infrared low-resolution data based on the optimal network parameters. According to the method, a traditional infrared image processing algorithm and a deep learning method are combined, an infrared super-resolution reconstruction algorithm is established and put forward, and the method is not affected by various dynamic range adjustment algorithms.

This invention relates to the field of infrared image processing technology and proposes a method for dynamic suppression of vertical stripes in infrared images based on statistical characteristics. The method includes: preprocessing the original grayscale image to obtain a preprocessed image; establishing temperature segmentation intervals for the preprocessed image and adaptively configuring correction parameters for the preprocessed image based on the matching results of the working environment temperature and the temperature segmentation intervals; calculating the statistical characteristic value of each column of the preprocessed image after removing outliers to calculate the global statistical mean of the preprocessed image, and calculating the column stripe deviation coefficient of the preprocessed image based on the global statistical mean and statistical characteristic values; performing temporal recursive smoothing on the column stripe deviation coefficient using the correction parameters to generate dynamic correction coefficients; and correcting the preprocessed image column by column to output the target image after vertical stripe suppression. This invention can meet the high-fidelity real-time imaging requirements in complex dynamic environments.

The application relates to the field of infrared image processing and discloses an infrared small target detection method and device based on an improved three-layer window local contrast measurement. The method comprises the following steps: (1) using a guided filter to achieve the effects of smoothing and edge preservation of an original thermal infrared image; (2) based on a local contrast measurement theory, a sliding window with a three-layer nested structure is constructed, and a local contrast measurement operator is designed; (3) performing edge filling on the thermal infrared image subjected to the guided filter, traversing the image pixel by pixel with the sliding window, calculating the local contrast measurement value of the image block covered by the current sliding window, and obtaining a local contrast measurement matrix C; and (4) regarding the local contrast measurement matrix C as a local contrast image T, taking the local contrast image T as the infrared small target detection result, and realizing infrared small target detection. The application comprehensively utilizes the guided filter and the local contrast measurement theory, improves the local contrast measurement criterion, better represents the characteristics of small targets, and improves the detection performance of thermal infrared small targets.

A system for monitoring a switchgear includes an infrared camera; a processing unit; and an output unit. The infrared camera acquires a first infrared image having a first number of pixels, and the processing unit determines a pixel in the first infrared image with a maximum temperature. The processing unit utilizes a second number less than the first number to determine a temperature interval for the first infrared image equal to a difference between the maximum temperature in the first infrared image and a threshold temperature in the first infrared image. The processing unit is configured to determine that a hot spot exists in the switchgear using the temperature interval for the first infrared image.

The invention discloses an image restoration method for an infrared simple lens imaging system with a wide signal-to-noise ratio range, and belongs to infrared image processing. The method comprises the following steps: S1, collecting a data set of infrared simple lens imaging as a training data set of a restoration model; s2, a Wavelet-ProxNet model is constructed to serve as a restoration model, and the restoration model adopts an asymmetric encoder-decoder structure and comprises an encoder and a decoder; s3, establishing a composite loss function as a constraint, and training the recovery model by using the training data set; and S4, for an image to be restored, generating a restored image by the trained restoration model. The diffraction lens infrared image reconstruction network model and the reconstruction method thereof provided by the invention have the advantages of high reconstruction quality, strong noise generalization and low calculation complexity, and promote practical and lightweight development of a diffraction lens infrared imaging technology.

The application discloses an image processing method for infrared image detail enhancement and belongs to the technical field of infrared image processing. The method solves the technical problem of urgently needing an infrared image processing method capable of strengthening small target detail feature extraction in an infrared image and optimizing deep and shallow feature fusion effect of the infrared image. In view of the problems that a small infrared target is small in size, poor in features, easy to be fused with a background, and an existing feature map construction mode is insufficient in detail extraction and insufficient in feature fusion, a brand-new image processing network is constructed, and a detail enhancement module and a self-adaptive feature recalibration module are integrated as cores. The detail enhancement module strengthens small target detail feature extraction through multi-branch differential convolution and reparameterization technology. The self-adaptive feature recalibration module is composed of a series of recalibration attention units and is used for adaptively fusing deep and shallow features to optimize feature expression.

The invention discloses a gas cloud cluster image enhancement and quantitative analysis method and system based on a thermal infrared imager and the thermal infrared imager. The method comprises the following steps: S1, preprocessing and background modeling; s2, screening candidate gas areas; s3, performing gas enhanced display; and S4, cloud cluster quantification and analysis. The image enhancement and quantitative analysis method disclosed by the invention is simple in steps, and realizes automatic, real-time, accurate and quantitative detection of invisible gas clouds through a multi-level, self-adaptive and intelligent infrared image processing and mode recognition algorithm; the problems that in the existing gas leakage detection process, the early warning capacity is weak, the false alarm rate is high, the leakage rate and concentration are difficult to quantify, and environmental interference is large are solved.

A system and method for monitoring a switchgear includes an infrared camera, a processing unit, and an output unit. The infrared camera acquires an infrared image of the switchgear, and the processing unit converts it into a binary image. Pixels in the infrared image having a temperature equal to or above a first threshold value are given the same first value. Pixels in the infrared image having a temperature below the first threshold value are given the same second value. The processing unit is configured to implement a Siamese neural network to determine if a hot spot exists in the infrared image.

Embodiments of the present application disclose an infrared image processing method, device and equipment and a storage medium. The technical scheme provided by the embodiments of the present application finds a temperature mutation point in an original image set, determines a to-be-compensated image and a thermal stable image from the original image set based on the temperature mutation point, determines reference statistical information according to temperature information of the thermal stable image, and compensates the temperature of each to-be-compensated image based on the reference statistical information and the temperature information of each to-be-compensated image, thereby improving the temperature measurement effect of the original image in the original image set, and effectively improving the image acquisition and image splicing efficiency without waiting for the thermal stable time of an infrared camera before shooting the original image.

This invention discloses a multi-branch parallel weighted and multi-scale spatially adaptive infrared image processing method and system. It reconstructs the output data of an infrared detector into a two-dimensional grayscale image matrix; obtains three branch output images through parallel processing of three-branch complementary feature extraction operators; obtains a base image through pixel-level weighted fusion using local spatial information entropy mapping; normalizes and inverts the base image to obtain an inverted image; and processes the inverted image based on a spatially adaptive exponential enhancement model using a multi-scale Gaussian ratio factor to obtain the final enhanced image. This invention not only achieves heterogeneous branch complementary fusion with adaptive parameter determination, enabling the extraction of subtle target details, and low computational complexity, but also possesses potential for dataset generation and migration to embedded real-time systems. Furthermore, it addresses the challenge of existing infrared image enhancement techniques in balancing noise suppression, target detail preservation, and real-time processing.