51 results about "Adaptive imaging" patented technology

The invention relates to a cable channel monitoring and risk grading method based on working condition adaptive enhancement and cross-modal unified modeling, and the method comprises the steps: obtaining video modal data and sensor modal data, and building a global unified time axis; performing enhancement processing on the video modal data through a working condition self-adaptive imaging enhancement mechanism, and performing weighted fusion to calculate an image quality score; enhancing the enhanced video modal data through an attention mechanism to obtain final video features, and constructing a graph structure according to a topological relation of sensor positions to obtain sensor features; constructing a cross-modal fusion mechanism, and performing deep semantic fusion on the final video features and the sensor features to obtain final fusion features; multi-dimensional detection results are calculated, the detection results meeting the reliability condition are screened, the detection results are converted into risk grades and disposal instructions, and cable channel monitoring and risk grading are achieved. Compared with the prior art, the method has the advantages of being suitable for complex working conditions, high in anomaly recognition accuracy, high in reliability, stable in long-term operation and the like.

The invention provides an unmanned aerial vehicle dynamic path planning method and system for a strong electromagnetic interference environment, and relates to the field of unmanned aerial vehicle navigation and interference resistance. The method mainly solves the problem of robust positioning of an optical sensing system in a strong electromagnetic environment. The core of the method lies in a spectrum anti-noise technology of a visual SLAM module, and spectrum separation of visible light and near-infrared band electromagnetic noise is realized through electromagnetic shielding packaging and an adaptive imaging algorithm of a multispectral camera. According to the method, a time-frequency double-domain filtering algorithm is adopted, the phenomena of light intensity abrupt change and frequency spectrum aliasing generated by electromagnetic pulses are eliminated in the feature extraction stage, and the electromagnetic interference mismatching rate of ORB feature points is reduced to 2% or below. The optimized feature point cloud keeps electromagnetic immune characteristics in the dynamic updating process, centimeter-level positioning precision can be achieved in the field intensity environment of 30 dBm or above, and meanwhile real-time detection of dynamic obstacles is achieved through an optical flow acceleration constraint mechanism.

The application discloses a hyperspectral imaging chip, device and system based on an adjustable reconfigurable metasurface, and the chip comprises a metasurface unit array, a metasurface reconfiguration module, a metasurface adjustment module, a CMOS image sensor and a spectrum reconstruction and identification module, the metasurface unit array comprises a plurality of metasurface units arranged on a silicon layer; the metasurface reconfiguration module is used for adjusting the number of metasurface units included in the reconfigurable metasurface unit array; the metasurface adjustment module is used for connecting the silicon layer of the metasurface unit array through wires, and is used for changing the spectral response of the metasurface unit by adjusting the voltage of the wires; the CMOS image sensor is used for detecting light signals from the reconfigurable metasurface unit array after modulation; and the spectrum reconstruction and identification module is used for performing hyperspectral reconstruction and imaging according to the light signals detected by the CMOS image sensor. The application has adjustable spectral response, ultrahigh spectral resolution, real-time dynamic monitoring capability and self-adaptive imaging capability.

The invention discloses an on-line detection method for surface defects of an EVA (Ethylene Vinyl Acetate) adhesive film based on machine vision, which belongs to the technical field of industrial automatic quality detection and comprises the following steps: acquiring multiband image data of the surface of the EVA adhesive film acquired by a preset multi-angle self-adaptive imaging system; performing background difference processing on the multiband image data to generate a difference image; performing adaptive contrast enhancement processing on the difference image to obtain an enhanced image; extracting texture feature data and morphological feature data from the enhanced image to generate a multi-feature data set; performing dynamic weighted fusion processing on the multi-feature data set to generate a defect probability graph; the defect probability graph is input into the layered detection network for processing, a defect detection result is generated, the technical scheme that multi-angle self-adaptive imaging, multi-feature dynamic fusion and the layered detection network are combined is adopted, the defect imaging quality and feature significance can be improved in a self-adaptive mode, and high-speed accurate detection and dynamic optimization of the surface defects of the EVA adhesive film are achieved.

This invention discloses an all-weather reconnaissance and alarm device, comprising a laser illumination component, an ICCD / ICMOS gating component, and an integrated processor. The laser illumination component uses high peak power pulsed laser light for illumination assistance, enhancing target brightness. The ICCD / ICMOS gating component is used to achieve high-gain photoelectric conversion of weak optical signals. Specifically, the ICCD / ICMOS gating component eliminates or reduces the influence of sunlight through "ultrafast adaptive imaging + light decay," enabling the component to operate in the linear region with the optimal signal-to-noise ratio for the target. Simultaneously, the ICCD / ICMOS gating component integrates a high-speed CCD / CMOS image sensor. Without changing the delay time, a higher image intensifier repetition frequency results in a smaller increase in delay time. Through ultra-high-speed image acquisition, it fully utilizes the energy of each laser pulse, enabling imaging of targets at different distances and high-speed moving targets. The integrated processing component focuses on controlling the ultrafast adaptive adjustment duration, the interval between auxiliary illumination and gating opening, and high-precision gain control.

The invention provides a multi-drug fluorescence spectrum adaptive imaging analysis method and device. Comprising the following steps: performing incident wavelength search on an original fluorescence image acquired by a fluorescence camera by applying a Bayesian optimization algorithm to obtain an optimal incident wavelength; and under the optimal incident wavelength, acquiring an original fluorescence image again by the fluorescence camera, acquiring an original visible light image by the visible light camera, performing deep learning filtering noise reduction on the original visible light image and the original fluorescence image, and inputting the images into an image fusion network at the same time to obtain an image fusion fluorescence image. The fluorescent drug excitation wavelength can be automatically matched, the fluorescent brightness can be automatically adjusted, the debugging time of a machine is shortened, and the utilization rate of equipment is improved.

The invention discloses a modular splicing imaging device and an image splicing method, and belongs to the technical field of camera splicing imaging. The device comprises a single-lens imaging module and an image processing box module, and the single-lens imaging module and the image processing box module are flexibly configured, freely combined and rapidly adjusted into an adaptive imaging layout, so that splicing devices of different view fields are constructed, and different use requirements are met. The device has strong expansion capability, can realize multi-layer splicing and multi-view-field splicing, and can enlarge an imaging coverage area in a vertical direction or obtain picture information of different imaging systems in a unified coverage area through multi-layer splicing; the image information can be collected in all directions and at multiple angles through multi-view-field splicing, a panoramic picture with an ultra-large view field and high resolution is formed, the requirement for fine monitoring and observation of a wide area is met, and the application boundary of the device is greatly expanded.

The invention relates to a biological teaching eyeball adaptive imaging system based on model fusion dynamic focusing and detachable modular design, a control display method and a cloud maintenance platform. Object distance obtaining is achieved through an integrated host device integrating a sliding support, an imaging module comprising a light source water lens and a retina screen, a control module comprising a microcontroller and an ultrasonic ranging module and a driving execution module comprising a steering engine and an injector, the target angle of the steering engine is calculated according to a fusion model, the steering engine is driven through PWM signals, and the target angle of the steering engine is obtained. The water volume of the injector is adjusted to vary the curvature of the water lens for dynamic focusing. Modularized design is adopted for being connected with detachable parts of the 3D printing mortise and tenon joint structure, a cloud maintenance system comprising a model database and an interaction and display module is constructed, and the advantages of being compact, low in cost and easy to maintain are achieved. As a whole, adaptive focusing control without an angle sensor is realized, the teaching demonstration quality and the equipment maintenance efficiency are improved, and the method has important significance for teaching.

The invention relates to a task-driven adaptive imaging method for power line anomaly detection, and the method comprises the steps: constructing a power line anomaly detection model, an adaptive camera control model and an image simulation model, and carrying out the combined optimization of the dynamic imaging parameters of a camera and a downstream anomaly detection task based on the three models. A dynamic mapping relation among ambient light, the moving speed of inspection equipment, dynamic imaging parameters and detection performance is established, and conversion from general imaging to task optimal imaging is realized. And the problem of poor performance of a downstream anomaly detection model caused by a general imaging means under complex illumination and motion in the existing routing inspection technology is solved. According to the invention, the image simulation model is utilized to obtain the data set for training the model based on the data set of the existing anomaly detection task, and the data set construction process is simplified.

The invention relates to the technical field of weld visual inspection, in particular to a weld visual inspection method and system. The method comprises the following steps: acquiring navigation data; evaluating a quality score of the navigation data, and when the quality score is lower than a first preset threshold value, generating an adaptive imaging mode instruction; according to the self-adaptive imaging mode instruction, imaging parameters of the main vision industrial camera are adjusted, and the imaging parameters comprise the focal length and the aperture; collecting an expanded view field image according to the adjusted imaging parameters; the expanded view field image is processed, the actual position of the welding seam is recognized, and the center line of the welding seam is extracted; and determining a core detection area of the welding seam by taking the center line as a reference, and performing defect detection on the core detection area of the welding seam. The problems that in a specific welding process, laser scanning navigation data are inaccurate due to uneven welding slag covering the surface of a welding seam, and then the welding seam detection precision and reliability are affected are solved.

The invention discloses a satellite-borne camera real-time adaptive imaging method based on target detection, and belongs to the technical field of space-based information on-satellite processing. From the perspective of satellite detection imaging engineering, imaging parameters of corresponding detection modules are adjusted based on the change condition of the exposure information amount of a frame anchor image where an on-satellite target detection result is located according to the characteristic of large change of the radiation intensity of a detection dynamic target; wherein in consideration of the fact that the gradient value of a target edge pixel area is large and the gradient value of a pixel area in a target contour is small, in order to balance the importance of a weak gradient and a strong gradient, a logarithmic function is used for mapping the relation between the gradient amplitude and the gradient information amount, and therefore the accuracy amount of the exposure information amount of the frame anchor image is achieved; based on this, the method can adapt to the change of the radiation intensity of the target in real time, thereby not only guaranteeing the effective detection of the dark and weak target, but also avoiding the detection saturation, and achieving the imaging of complete target characteristics.

The invention discloses a fast deconvolution sound source localization method based on array sparsity and broadband comprehensive processing, which comprises the following steps of: selecting microphones to form a sparse array, and converting a regular focusing plane into an irregular plane to obtain grid coordinates; calculating a sparse array cross-spectrum matrix based on coordinates, obtaining a function beam through eigenvalue decomposition and power exponent operation, and outputting the function beam; constructing a frequency domain deconvolution model according to the convolution relationship between the frequency domain and sound source distribution and the convolution relationship between the frequency domain and a rising power point spread function, and solving a sound source intensity distribution matrix by using fast Fourier transform and iterative optimization; estimating a noise floor-to-signal-to-noise ratio matrix, traversing frequency points, taking the maximum signal-to-noise ratio, and fusing the frequency points into a broadband imaging matrix; a time smoothing factor is introduced to carry out weighted fusion on the inter-frame imaging matrix, and positioning is completed; according to the method, low-consumption, high-precision and strong-robustness sound source localization is realized through array rarefaction and fast deconvolution load reduction, precision protection by means of function beam forming and Gaussian filtering, multi-frequency point fusion adaptive imaging, inter-frame smooth flicker suppression and adaptation to complex scenes.

The invention discloses a multi-mode single-photon radar system and an environment adaptive imaging method based on the same. The multi-mode single-photon radar system comprises a laser scanning module and a photon detection module. The environment detection module and the photon detection module are electrically connected with the control module, and the control module is electrically connected with the laser scanning module, the photon detection module and the environment detection module; the image reconstruction module is electrically connected with the environment detection module and the control module; and the upper computer interaction module is electrically connected with the image reconstruction module. Therefore, the multi-mode single-photon radar system can dynamically adapt to and perform high-resolution imaging in complex environments such as haze, strong background light, rain and snow and the like, and the multi-mode single-photon radar system is modularized in structure, has good expansibility and engineering realizability and is suitable for the fields of automatic driving, complex scene perception, target surveying and mapping and the like.

This application provides an image sensor and a high dynamic range adaptive imaging method. The image sensor includes: a pixel array comprising a dual-conversion gain transistor and a row selection transistor for generating a floating diffusion node readout signal; a readout module for receiving initial sampling, converting the floating diffusion node readout signal into a color-level digital signal based on a comparison between the readout signal and an analog reference voltage signal, and reading the pixel electrical signal under the selected path during the readout phase; a pre-readout module for obtaining a gain path signal based on a comparison between the color-level digital signal and the digital reference voltage signal, thereby changing the state of the dual-conversion gain transistor to obtain the selected path; and a synthesis module for mixing the color-level digital signal, the gain path signal, and the pixel electrical signal to perform high dynamic range image acquisition. This application enables rapid pre-readout judgment before the readout phase, thereby determining the optimal signal gain mode for output and achieving dynamic range optimization.

The invention discloses an ecological intelligent capturing method and system based on sound and infrared multi-mode cooperation, and belongs to the technical field of ecological monitoring and intelligent sensing, and the method comprises the steps: collecting an original environment sound signal, carrying out the preprocessing of the original environment sound signal, carrying out the semantic recognition of the preprocessed original environment sound signal, and obtaining a semantic recognition result; semantic tags and sound source direction information are obtained; according to the sound source direction information, infrared scanning is carried out on the corresponding direction area, and infrared features of a heat source in the scanning area are extracted; performing feature matching on the infrared features and semantic tags, outputting a target type, and generating adaptive imaging parameters based on the target type; shooting is carried out according to the self-adaptive imaging parameters, event capturing is completed, and the low-power-consumption standby state is returned. According to the method, the problems of high false triggering rate, low effective data proportion, short endurance time and poor scene adaptability in the prior art are solved, the transmission efficiency, the positioning accuracy and the adaptability are improved, and the false alarm rate is reduced.

The present invention discloses an adaptive SAR imaging method and system in a complex background environment, which is used for building imaging. The method comprises: performing coarse imaging of a target building by SAR to generate an initial image of the target building, and obtaining a position vector of the target building; obtaining background environment variables of the target building; setting a spatiotemporal dynamic reflection model, and calculating the SAR signal reflection intensity according to the position vector of the target building and the background environment variables; obtaining the original noise signal intensity of the target building, and setting a background noise suppression model to suppress the original noise signal intensity and calculate the suppressed noise signal intensity; setting an adaptive target enhancement model, and performing signal enhancement on the initial image according to the signal reflection intensity and the suppressed noise signal intensity, calculating the enhanced target building signal intensity, and generating a final image of the target building according to the enhanced target building signal intensity.

This invention discloses a method and system for quality inspection of liquid coating products based on image recognition, belonging to the field of image processing technology. The method includes acquiring a geometric topological model and extracting the interface curve; dynamically configuring the light source and adjusting the shooting direction according to the material reflectivity difference to acquire composite feature images; executing parallel analysis paths for the substrate, silicone parts, and interface bonding; the interface bonding path projects the interface curve onto the image and calculates the grayscale gradient modulus to quantify the bonding degree; inputting the indicators of each path into a multivariate nonlinear comprehensive quality evaluation function, and outputting the judgment result. This invention achieves simultaneous integrated detection of the substrate, silicone parts, and bonding interface for the first time. Adaptive imaging effectively eliminates interference from reflectivity differences, and the three-path parallel architecture meets online cycle time requirements. Combined with a graded evaluation of delamination degree and an adaptive threshold update mechanism, it possesses high detection rate, strong robustness, and good industrial adaptability.

Various embodiments of the present disclosure provide an adaptive imaging process that includes receiving a measured fill level for a container based on a distance reading measurement, selecting a focus level from a plurality of calibrated focus levels based on the measured fill level, providing, to an imaging device, one or more imaging instructions to trigger a validation image at the focus level, receiving, from the imaging device, an imaging response to the one or more imaging instructions that comprises an image classification for the validation image, generating a verification event based on the image classification, and storing the verification event in association with the container.

The application provides an intelligent control method and system based on camera automatic focusing and exposure, and relates to the technical field of camera intelligent control, comprising: collecting multi-sensor data, wherein the multi-sensor data comprises temperature data, acceleration data, illumination data and humidity data; performing fusion processing on the multi-sensor data to construct a working state data set; extracting acceleration sensor data from the working state data set, identifying vibration mode and intensity through vibration spectrum analysis, and dynamically adjusting anti-shake parameters; performing real-time analysis on the collected image, extracting image quality characteristics, constructing a multi-dimensional feature vector in combination with the working state data set, and generating a focusing state score. The application can maintain image clarity and stability in a complex and changeable environment, improve the adaptability of the camera to different scenes, realize intelligent adaptive imaging control, and significantly improve image quality and system reliability.

This invention relates to a cable channel monitoring and risk classification method based on condition-adaptive enhancement and cross-modal unified modeling, comprising: acquiring video modal data and sensor modal data, and establishing a globally unified time axis; enhancing the video modal data through a condition-adaptive imaging enhancement mechanism, and calculating the image quality score through weighted fusion; enhancing the enhanced video modal data through an attention mechanism to obtain final video features, and constructing a graph structure based on the topological relationship of sensor locations to obtain sensor features; constructing a cross-modal fusion mechanism to perform deep semantic fusion of the final video features and sensor features to obtain the final fused features; calculating multi-dimensional detection results, screening detection results that meet reliability conditions, and converting the detection results into risk levels and handling instructions to achieve cable channel monitoring and risk classification. Compared with existing technologies, this invention has advantages such as adaptability to complex working conditions, high accuracy in anomaly identification, high reliability, and long-term stable operation.

The present application relates to a kind of wind snow particle adaptive imaging measurement system and method based on double view field fusion, system includes: optical illumination unit, double view field imaging unit, field of view switching unit, data acquisition control unit, data processing unit;Optical illumination unit, for illuminating sampling space;Double view field imaging unit, for wind snow particle double view field imaging;Field of view switching unit, for controlling double view field imaging unit field of view switching and adjustment;Data acquisition control unit, for controlling optical illumination unit and double view field imaging unit, wind snow particle image data acquisition;Data processing unit, for wind snow particle image data processing and display.The present application is based on the development of large field of view and small field of view array camera, can provide important data support for atmospheric science research, snow field observation, weather modification etc..

The application provides a sea surface adaptive imaging method based on SAR subview analysis, which comprises the following steps: transforming a SAR single-view complex image to a range frequency domain; according to a window function type added in an imaging direction, performing reverse correction of the window function weighting; dividing a Doppler bandwidth in the imaging direction into two parts, i.e. a left part and a right part; performing inverse Fourier transform on echoes containing only one half of the spectrum in the imaging direction to obtain left and right subaperture images; calculating a subview cross-correlation coefficient according to the left and right subaperture images; calculating a subview coherent entropy according to the left and right subaperture images; dividing a two-dimensional feature space composed of the subview cross-correlation coefficient and the subview coherent entropy into three regions, i.e. an interference region, a target region and a sea clutter region; segmenting pixels according to the divided regions; and calculating pixel amplitudes in each region. Through reprocessing of the SAR image, the application suppresses the imaging direction ambiguity and the sea clutter in the marine background SAR image, and improves the SAR imaging quality in the marine background.

The invention provides an intelligent control method and system based on camera automatic focusing and exposure, and relates to the technical field of camera intelligent control, and the method comprises the steps: collecting multi-sensor data which comprises temperature data, acceleration data, illumination data and humidity data; carrying out fusion processing on the multi-sensor data, and constructing a working state data set; acceleration sensor data are extracted from the working state data set, the vibration mode and intensity are identified through vibration spectrum analysis, and anti-shake parameters are dynamically adjusted; and performing real-time analysis on the acquired image, extracting image quality features, constructing a multi-dimensional feature vector in combination with the working state data set, and generating a focusing state score. According to the method, the image definition and stability can be kept in a complex and changeable environment, the adaptive capacity of the camera to different scenes is improved, intelligent self-adaptive imaging control is realized, and the image quality and the system reliability are remarkably improved.

This invention discloses an intelligent fish fry sorting method based on state-space modeling and adaptive imaging closed-loop, relating to the field of aquaculture technology. At the acquisition end, an imaging closed loop of "controllable illumination—frequency domain calibration—exposure and gain self-calibration" is constructed. At the computation end, a lightweight front-end of "multi-scale template matching ROI rapid localization + small-range four-sided approximation tracking" is used. At the detection end, an end-to-end detection network is constructed, with a visual state-space module introduced in the backbone stage. In the feature fusion stage, HSFPN is used, and multi-scale feature selection and complementary fusion are completed through channel attention. At the control end, the detection results are mapped to the coordinate system of the sorting actuator, and combined with trajectory correlation, activity heatmap, abnormal fish fry identification, dead fish fry identification, and closed-loop strategy, the actuator is driven to achieve non-contact hierarchical sorting and counting. This invention, using the above method, improves the detection rate of dense small targets and robustness under complex water imaging conditions while ensuring real-time performance.

The invention relates to a rotating machine fault positioning method based on a self-adaptive frequency band and a medium, and the method comprises the steps: synchronously collecting acoustic signals under a multi-channel stable working condition through an acoustic array, and carrying out the preprocessing of the acoustic signals under the multi-channel stable working condition; performing coherence-kurtosis combined filtering on the preprocessed acoustic signal to obtain a dominant frequency point in the acoustic signal; adaptive filtering is carried out on dominant frequency points in the acoustic signals, and candidate frequency bands are generated; and performing sound field imaging on each frequency band in the candidate frequency bands, generating n sound images for each frequency band, and dynamically selecting an optimal sound image through an energy saliency scoring mechanism and a weighted scoring function to complete fault positioning of the rotating machinery. According to the invention, self-adaptive imaging frequency band selection can be completed, and the fault positioning precision and effectiveness are improved.

This application discloses a method and system for inspecting the surface quality of electroplated finished products. The method includes acquiring information about the electroplated finished product to be tested, including product attribute information and actual electroplating process parameters; determining image acquisition parameters based on the product attribute information and actual electroplating process parameters through a preset parameter mapping table; acquiring an image of the electroplated finished product based on the image acquisition parameters; extracting multi-dimensional optical features from the electroplated finished product surface image; fusing the actual electroplating process parameters with the multi-dimensional optical features to generate process-aware fusion features; and obtaining the surface quality inspection result of the electroplated finished product based on the process-aware fusion features through a preset defect detection model. This application effectively improves the accuracy of electroplated surface quality inspection by using adaptive imaging and fusing electroplating process information.

The invention provides a compound eye camera based on an electrowetting liquid diaphragm and a self-adaptive imaging method. The compound eye camera comprises a plurality of sub-imaging units, a transparent substrate, an image sensor and a driving control module, the sub-imaging unit comprises a focusable lens and an electrowetting liquid diaphragm and is used for collecting sub-view field imaging light beams and regulating and controlling an imaging aperture; the transparent substrate is used for bearing the sub-imaging units; the image sensor is used for acquiring an image formed by the sub-imaging unit; the driving control module is used for providing driving signals for the focus-adjustable lens and the electrowetting liquid diaphragm in the sub-imaging unit; the driving control module sends a driving signal to each sub-imaging unit of the compound eye camera, and regulates and controls the size and the shape of an aperture diaphragm of each sub-imaging unit, so that the self-adaptive regulation and control of the imaging brightness of the compound eye camera is realized, and a scene irradiated by light with non-uniform intensity is clearly imaged. Or self-adaptive regulation and control of the imaging modulation degree are realized so as to selectively distinguish the target from the background.

The invention provides an image sensor and a high dynamic range adaptive imaging method, and the image sensor comprises a pixel array which comprises a dual conversion gain transistor and a row selection transistor which generates a floating diffusion node reading signal; the reading module is used for receiving the initial sample and converting the initial sample into a color gradation digital signal according to a comparison result of a floating diffusion node reading signal and an analog reference voltage signal; reading a pixel electric signal under the selection path in a reading stage; the pre-reading module obtains a gain path signal according to a comparison result of the color gradation digital signal and the digital reference voltage signal so as to change the state of the dual-conversion gain transistor and obtain a selection path; and the synthesis module is used for mixing according to the color gradation digital signal, the gain path signal and the pixel electric signal so as to perform high dynamic range image acquisition. According to the invention, rapid pre-reading judgment can be carried out before the reading stage, so that the optimal signal gain mode is determined for output, and dynamic range optimization is brought.

The invention provides a self-adaptive imaging system based on a CMOS detector. The self-adaptive imaging system comprises a CMOS focal plane circuit, a data processing circuit, an interface circuit and a camera integrated electron. The interface circuit receives a power supply provided by the power supply module, and provides the power supply to the CMOS focal plane circuit and the data processing circuit after filtering conversion; each control signal of the camera integrated electronics is received and sent to the data processing circuit, and telemetering information of the data processing circuit is forwarded to the camera integrated electronics; the CMOS focal plane circuit comprises a CMOS detector; the CMOS detector receives a time sequence driving signal generated by the data processing circuit and drives the CMOS detector to work normally, and the CMOS detector outputs multichannel original image data; the data processing circuit carries out image data automatic alignment on original image data output by the CMOS detector, carries out real-time monitoring in the imaging process, carries out arrangement and preprocessing on the data, carries out target detection and image interception in real time, recognizes a target area image, carries out automatic exposure adjustment on the recognized target area image, and carries out automatic exposure adjustment on the recognized target area image. And outputting the target valid data.

The invention relates to the technical field of infrared imaging, in particular to an anti-stray-light automatic imaging control method and system for infrared imaging. The method comprises the following steps: acquiring image data and stray light data corresponding to the image data; according to the equipment temperature time sequence data and the light intensity time sequence data, the stray light imaging influence degree is determined; correcting the stray light imaging influence degree according to the dust particle concentration data to obtain a strong stray light tendency coefficient; the strong stray light tendency coefficient is used for representing the comprehensive probability of strong stray light interference of the infrared image; based on the texture difference degree of the image data and the radiation stability value corresponding to the infrared image, determining the comprehensive anti-stray light stability; determining stray light inhibition urgency according to the comprehensive stray light resistance stability and the strong stray light tendency coefficient; and according to the stray light suppression urgent degree and a preset threshold value, determining a target imaging control mode, so that the infrared imager performs adaptive imaging control according to the target imaging control mode. According to the invention, the anti-stray light imaging control precision in the infrared imaging process can be improved.