173 results about "Image field" patented technology

The invention discloses a sound authenticity identification method based on multi-modal feature deep interactive fusion. According to the method, a double-flow architecture is adopted, and a pre-trained BEATs model and a CNN14 network are respectively utilized to extract Transform sequence features and convolution time-frequency embedding features of an audio; an adaptive MobileFormer fusion device is innovatively proposed, an original MobileFormer structure used in the image field is transformed into a bidirectional cross-modal interaction module suitable for one-dimensional time sequence audio features, dynamic complementary modeling of local details and global semantic features is achieved through a cross attention mechanism, and dynamic nonlinearity is introduced to activate and enhance the expression ability; and the fused enhanced features are input into a hierarchical graph attention network ASSIST, and high-order semantic modeling and authenticity classification are completed by combining spectrogram and time sequence double-flow reasoning. Experimental results show that the performance of the method on an ASVspoof2021LA data set is superior to that of an existing baseline model. The method can effectively detect AI generation voice, replay attack and other forged voice, and is suitable for a voice authentication system.

The invention discloses a multi-feature fusion method for sustainable learning, and the method comprises the steps: determining a plurality of target training pictures in a to-be-learned target image field in a plurality of image fields, and determining a plurality of pieces of target frequency domain feature sub-data of each target training picture; establishing a cross loss function of the image processing model according to a feature fusion process of the plurality of frequency domain feature sub-data in the image processing model; and training the image processing model by taking minimization of the cross loss function as a training target so as to obtain an image processing model which learns a target image field. According to the method, through the synergistic effect of frequency domain feature extraction, double loss function construction and continuous optimization training, the dynamic adaptive capacity and recognition precision of the image processing model in the multi-modal fusion task are improved, and the stability and expansibility of the model are enhanced.

An imaging optic (10) for projection lithography serves to image an object field (5), in which a reticulum to be imaged can be arranged, onto an image field (11), in which a substrate to be exposed can be arranged. The imaging optic (10) has a plurality of mirrors (M1 to M8) for guiding imaging light (16) along an imaging beam path from the object field (5) to the image field (11). The image-side numerical aperture of the imaging optic (10) is greater than 0.75. The optical conductivity of the imaging optic (10) is greater than 45 mm. 2 The result is an imaging optic whose usability for a projection exposure system is improved.

The utility model discloses a shooting device for remote sensing imaging, and relates to the field of remote sensing imaging. The shooting device for remote sensing imaging comprises an unmanned aerial vehicle, a support unit and a shooting unit, the support unit and the shooting unit are arranged below the unmanned aerial vehicle, the support unit comprises a circular sliding rail, a sliding ring and supporting legs, the sliding ring is arranged below the circular sliding rail in a sliding mode, and the supporting legs are fixedly installed below the sliding ring; the shooting unit comprises a driving motor, a connecting frame and a shooting camera, the driving motor is fixedly installed at the bottom of the unmanned aerial vehicle, the connecting frame is connected with the output end of the driving motor and connected with the supporting legs, and the shooting camera is connected with the connecting frame. According to the shooting device for remote sensing imaging, the driving motor fixedly installed at the bottom of the unmanned aerial vehicle drives the connecting frame, the shooting camera and the supporting legs to rotate, so that only the unmanned aerial vehicle needs to hover in the air, when the shooting camera rotates by a shooting angle, the supporting legs do not shield the unmanned aerial vehicle, and the shooting stability and the imaging quality are improved.

The invention relates to a visual scale adaptive unmanned aerial vehicle detection method based on HRRP physical perception, and belongs to the technical field of mobile communication. The method comprises the following steps: constructing a cooperative monitoring architecture of an ISAC base station and a visual sensor, and establishing a space-time mapping relation between a radio frequency sensing coordinate system and a visual sensor coordinate system; performing macroscopic parameter estimation based on echo signals received by the ISAC base station, resolving spatial position coordinates of a target, generating a servo control instruction to drive a visual sensor holder to rotate, and locking the target at the center of a visual image field of view; extracting a frequency domain channel response of the echo signal, generating a time domain HRRP through IDFT, and estimating a radial physical span of a target in combination with a constant false alarm detection algorithm; constructing a self-adaptive image slice model based on physical structure constraint, and performing resampling on slices by using a scale normalization scaling factor; and inputting the normalized image block into the feature fusion detection network to complete fine detection of the unmanned aerial vehicle target.

A method for operating a projection exposure system (1) comprises the following steps: providing a projection exposure system (1) with a radiation source (1) for generating illumination radiation (3), an illumination optic (11) for transferring the illumination radiation (3) from the radiation source (2) to an object field (8) extending in a scan direction (y) and a cross-scan direction (x), wherein the illumination optic (11) has at least one faceted mirror (6, 7) with a plurality of individual mirrors, and wherein at least a subset of the individual mirrors is configured such that they only partially illuminate the object field (8) in the scan direction (y), and a projection optic (10) for imaging a reticle (12) arranged in the object field (8) of the illumination optic (11) onto a wafer (19) arranged in an image field (17) of the projection optic (10), and specifying a set of at least one element of field-dependent aberrations. (Ai(x, y);i=(1..M)), specification of a target vector (Z(x) = (Z1(x), ..., Z; M (x) T ) for the target values ​​Z i (x) of the aberrations Ai(x, y) after averaging over the scan direction (y), dividing the extent of the object field (8) in the scan direction (y) into j ≥ 2 intervals ([y0; y1], ..., [y j-1 ; y j ]) and determining scan weights (gi(x, y)) which characterize a dependence of an illuminance at a location x in the cross-scan direction in the object field () on a position in the scan direction (y) such that a deviation of a weighted aberration vector A weighted ( x ) → : = ∑ gi A l → is reduced from the target vector (Z(x)).

In a projection exposure method for exposing a substrate arranged in the region of an image plane of a projection lens with at least one image of a pattern arranged in the region of an object plane of the projection lens, using radiation from a wavelength range around a design wavelength < 260 nm, a substrate (SUB) is coated with a relatively thick radiation-sensitive photoresist layer (RS) and exposed using a projection lens (PO). This lens produces a focus at a design focus position (FOCO) at the design wavelength and, for other wavelengths outside the wavelength range, offset focus positions from an axially extended focus area (ΔFOC) around the design focus position (FOCO). The projection lens is designed as a single-waisted or double-waisted system.During an exposure time interval, different wavelengths from the wavelength range around the design wavelength are used such that the axial extent of the focus area is at least as large as the layer thickness. The projection lens is optically corrected for chromatic aberration (CHV) such that, in the region of the design wavelength, the image scale is essentially independent of the wavelength, so that a change in wavelength of 1 picometer results in a maximum variation of 2 nm between the position of an image point corresponding to an object point within an image field.

The invention discloses an image display method, a construction system and a computing control unit of a head-mounted display, which are applied to the field of images. The first to-be-displayed image is corrected through the pre-correction network model, the visual quality of the image displayed by the first display module is improved, and the defects of geometric distortion, spherical aberration, field curvature and the like of the image seen by a user are reduced, so that the visual fatigue of the user is reduced, and the immersion of VR experience is improved. Moreover, in the process that the user uses the head-mounted display, the training data is collected online in real time, and the pre-correction network model is trained based on the collected training data, so that the training process of the pre-correction network model is simplified, and the training efficiency of the pre-correction network model is improved. And the training data in various actual use scenes can be continuously adopted in an online mode, so that the types of the training data for training the pre-correction network model are enriched, and the accuracy of the pre-correction network model is ensured.

The application discloses a kind of based on multi-modal medical image's lumbar disc herniation postoperative recurrence prediction system, belong to medical image field.Use lumbar image set and each image corresponding feature true value and each patient corresponding recurrence prediction label to carry out training to based on multi-modal image's lumbar disc herniation postoperative recurrence prediction model, in training process, using random gradient descent algorithm to update model parameter, obtain the trained based on multi-modal image's lumbar disc herniation postoperative recurrence prediction model.Through the application, benefit from the rich image features provided by multi-modal image, the prediction network trained based on multi-modal data shows higher accuracy in lumbar disc herniation postoperative recurrence prediction.

An imaging EUV optic (10) has a plurality of mirrors (M1 to M6) for guiding imaging light (16) along an imaging beam path from an object field (5) to an image field (11). The imaging optics (10) have a total apodization tilt APO Z3 that is less than 10%. A beam path intersection region (K1, K2, K3) lies between a first partial beam path (M1M2, M2M3) and a second partial beam path (M3M4, M4M5) in the imaging beam path. The first partial beam path (M1M2, M2M3) lies between a mirror (M1, M2) and a mirror (M2, M3) directly following this mirror in the imaging beam path. The second partial beam path (M3M4, M4M5) lies between another mirror (M3M4) and a mirror (M4M5) directly following this further mirror in the imaging beam path. An object-image offset (d) OIS) is greater than 250 mm. This results in an imaging EUV optic whose usability for an EUV projection exposure system is improved.

An imaging optic (23) serves to image an object field arranged in an object plane, in which a lithography mask can be arranged as the object to be imaged, with imaging light via an imaging beam path into an image field arranged in an image plane, in which a substrate onto which the image is to be formed can be arranged. The imaging optic (23) has at least one correction device (32). This device has a correction element (30) arranged in the imaging beam path, the imaging effect of which varies across the image field. Furthermore, the correction device (32) has a correction element holder (33) and a correction element drive unit (34). The correction element holder (33) is driven by the correction element drive unit (34) during an imaging phase of the imaging optic (23) and can be displaced along a correction element displacement direction (35) extending transversely to the imaging beam path.The result is an imaging optic whose imaging effect is improved to achieve a predetermined imaging result.

The invention relates to a remote sensing image reverse editing method for a diffusion model, and belongs to the field of computer vision. The strong generation and editing capability of the diffusion model brings a series of potential safety hazards, and the image reverse editing technology aims at adding a layer of protective noise to an image, so that the diffusion model is difficult to output an ideal editing result. In order to solve the problems that an existing anti-editing technology is poor in effect on a remote sensing image and generally faces low efficiency and obvious protection traces, the invention provides an efficient and hidden protection scheme which comprises the following three steps: step 1, generating anti-editing disturbance based on hidden space high-frequency component suppression; step 2, noise generation network training based on single-time forward transmission; and step 3, concealment enhancement based on noise perception graph constraint. The method can effectively resist malicious image editing based on a diffusion model, is suitable for the field of remote sensing images, and gives consideration to safety, efficiency and image quality.

Method for generating an overview image using a high-aperture lens (4) with the steps: - Providing an optical detection beam path (2) with the objective (4), wherein the detection beam path (2) in a first operating state has a first numerical aperture (NA1) and a first depth of field (ST1) which lies substantially in a focal plane of the detection beam path (2), and in the first operating state an image of a detection radiation with the first depth of field (ST1) and with a lateral image field is or can be detected, wherein the detection radiation is effected by directing at least one light sheet (16) along an illumination axis (15) into a sample volume (8) to be imaged located in the sample space; - transferring the detection beam path (2) into a second operating state by increasing the first depth of field (ST1) to a second depth of field (ST2), wherein the high-aperture lens (4) remains in the detection beam path (2), - adjusting a thickness of the light sheet (16) in the direction of a detection axis (3) of the lens (4) to the second depth of field (ST2) using an adjustable illumination device, so that the thickness of the light sheet (16) corresponds at least to the second depth of field (ST2); - in the second operating state, detecting a detection radiation, wherein the detection radiation coming from a sample space is collected by means of the objective (4), guided along the detection beam path (2) and detected as an image with a lateral image field by means of at least one detector (7) sensitive to the detection radiation, wherein the lateral image fields are the same in the first and second operating states.

An imaging EUV optical unit serves for imaging an object field into an image field. The imaging optical unit has a plurality of mirrors for guiding EUV imaging light at a wavelength of shorter than 30 nm along an imaging beam path. The imaging EUV optical unit has an image-side numerical aperture of at least 0.3. An overall transmission of the plurality of mirrors is greater than 10%. An overall mirror surface, which represents the sum of all used mirror surfaces of the plurality of mirrors, is less than 1.5 m2. This design can yield an imaging EUV optical unit with improved usability for an EUV projection exposure apparatus.

Collected light may be split into fields using grazing incidence mirrors to avoid illuminating gaps between the active areas for readout electronics. The grazing incidence mirrors may reduce lost field space in the integrating direction by splitting the imaging field in that direction to allow the readout electronics to be outside of the field. The fields may be split so there is space for readout circuits but no associated light on the readout circuits. The size of the illumination may then be decreased and / or the number and / or size of sensors increased to improve the photon collection efficiency. The better photon collection efficiency may reduce shot noise and / or improves tool throughput.

The application discloses a kind of low field intensity magnetic susceptibility weighted imaging optimization method and system, it is related to magnetic susceptibility weighted imaging field, comprising: obtaining the K space original data obtained by scanning target object;According to K space original data reconstruction image field data, extract the amplitude data and phase data of image field data;Phase data is preliminary unwrapping processing, and unwrapping phase data is obtained;Unwrapping phase data is separated from background field, and local phase diagram is obtained;Local phase diagram and amplitude data are operated based on complex domain phase separation high-pass filter, and high-frequency phase data is obtained;According to high-frequency phase data and amplitude data, the reconstruction of magnetic susceptibility weighted image is carried out, and the magnetic susceptibility weighted image of target object is obtained.The application can significantly reduce the phase artifact of SWI image, and improve the definition of image detail.

The application discloses a kind of identification methods for human disturbance land, it is related to remote sensing image field, the method is by in edge computing terminal to the unified geometric orthographic correction of remote sensing image sequence, radiation normalization, cloud mask processing and format conversion, construct standardization image set, effectively improve the time series comparability and spectral consistency between remote sensing image, solve multi-temporal image illumination difference, geographical deviation and cloud interference and other influencing factors, provide high-quality input data basis for subsequent disturbance feature extraction;Meanwhile, the application combines air port identification algorithm, mechanical activity path detection and construction boundary expansion identification technology, comprehensively extracts ventilation corridor area, dynamic expansion area and mechanical disturbance area, constructs sensitive disturbance sampling point space layout scheme for disturbance potential, significantly improves the perception coverage ability and detection efficiency to key area, reduces redundant computing resource consumption, improves system real-time processing capability and early identification precision.

The application discloses a kind of optical lens optical axis angle determination method, device, equipment and medium, the optical axis angle determination method first provides a test chart;Test chart is by checkerboard and a plurality of target test patterns inlaying into;Then the image information of each target test pattern is collected by optical lens, and the position of corresponding optical lens and / or image sensor is moved, so that the image field of optical lens is parallel to the imaging surface of image sensor, and the line of the optical center of optical lens and the image center of image sensor is perpendicular to the imaging surface of image sensor;Then the distortion center of optical lens is identified by the corner point position information of checkerboard;The line of the optical center of optical lens and the distortion center of optical lens is parallel to the optical axis of optical lens;Finally, according to the position of the optical center of optical lens, the position of the image center of image sensor and the position of the distortion center of optical lens, the inclination of the optical axis of optical lens relative to the image field of optical lens is determined.

The application discloses a cross-domain three-dimensional Gaussian sputtering enhanced visual positioning method and system, which comprises the following steps: generating a second image corresponding to a first image in a first image field through an image editing model to obtain an extended data set of the first image data set in the first image field; performing sputtering model fine-tuning on a three-dimensional Gaussian sputtering model suitable for the feature distribution of the second image field according to the corresponding first image and second image in the extended data set; generating a positioning image training set of an image positioning model according to the three-dimensional Gaussian sputtering model after sputtering model fine-tuning, and performing positioning model training on the image positioning model according to the positioning image training set to obtain a trained image positioning model. The application makes the visual positioning system have stronger adaptability and generalization ability, reduces the positioning precision decline phenomenon, and meets the stability and high-precision requirements of cross-domain visual positioning.

The application provides an array laser additive-subtractive-multiphase synergistic composite manufacturing system, which comprises a forming chamber, a forming cylinder, a powder supply cylinder, a powder laying mechanism, a cooling system and an atmosphere system, and further comprises: an array laser area printing module for performing multi-laser partition scanning sintering forming; a defect detection image field module for monitoring defects of each layer of the sintering forming, identifying defect types and defect positions; and a femtosecond laser defect removal subtractive module capable of scanning a femtosecond laser beam at the defect positions through a subtractive scanning galvanometer according to the defects, the defect types and the defect positions detected by the defect detection image field module, and removing the defects in situ according to the defect types, so as to realize integrated integration of laser additive manufacturing, defect detection and defect subtractive removal, and realize high-efficiency and high-quality component manufacturing.

An imaging optical unit comprises a plurality of mirrors for imaging an object field in an object plane into an image field in an image plane. An image-side numerical aperture is greater than 0.55. A ratio between an object / image offset and a meridional transverse direction is at least 0.5. A ratio between a working distance between the object plane and a reflection portion, closest to the object plane, of one of the mirrors and the meridional transverse dimension is at least 0.05. The working distance is at least 270 mm. This can yield an imaging optical unit, the use of which is relatively manageable in a projection exposure apparatus, such as for EUV projection lithography.

We provide an imaging EUV optical unit for imaging the object field into the image field. [Solution] The imaging EUV optical unit (10) plays the role of imaging the object field (5) into the image field (11). The imaging optical unit (10) has a plurality of mirrors (M1~M5) for guiding EUV imaging light (16) with a wavelength shorter than 30 nm along the imaging beam path. The imaging EUV optical unit (10) has an image-side numerical aperture of at least 0.3. The total transmittance of the plurality of mirrors (M1~M5) is greater than 10%. The total mirror surface, which corresponds to the sum of all used mirror surfaces of the plurality of mirrors (M1~M5), is 1.5 m 2 It is less than [a certain value]. This results in an imaging EUV optical unit with improved usability for EUV projection exposure systems.

The application provides a lighting system, which comprises a light source, a coupling unit, a light-uniformizing unit and a relay unit, the light-uniformizing unit comprises a first light-uniformizing element and a second light-uniformizing element, the second light-uniformizing element is additionally arranged on the upper and lower sides of the first light-uniformizing element, the second light-uniformizing element makes full use of the light energy which is not used in the first image field without affecting the original exposure field size and illumination and without increasing the lighting light source, and separately provides uniform illumination energy for the alignment mark located outside the exposure field, so that the effective utilization rate of light energy is improved, and the second light-uniformizing element can be freely selected, so that the freedom of the illumination field selection is improved.

The present application belongs to the field of optical scattering imaging technology, and realizes the imaging through scattering medium based on optical memory effect.When the imaging target exceeds the memory effect range, the imaging failure is usually caused, thereby limiting the imaging field of view.The present application proposes a method and device for realizing non-invasive large field of view imaging through scattering medium based on PSF estimation and correlation operation.When the target is too large to exceed the memory effect range, the phase recovery algorithm is used to reconstruct the image of the sub-target O i of the target O hidden in the scattering medium, the positions of all sub-targets are obtained based on the point spread function estimation and autocorrelation and cross-correlation operation, the image of the sub-targets is spliced according to the positions, and the non-invasive large field of view imaging is realized.The present application can also realize non-invasive large field of view super-resolution imaging beyond the memory effect range, and can simultaneously consider the imaging field of view and imaging resolution.The present application has wide application in the fields of biomedical imaging and optical microscopic imaging.

The invention relates to a method for operating a projection exposure system (1) for microlithography. In the method according to the invention, during a first exposure phase, illumination radiation (16) is generated by means of an illumination optic (4) according to a first illumination setting, and the illumination radiation (16) is directed to an image field (11) of the projection optic (10) by means of a projection optic (10). During a second exposure phase, illumination radiation (16) is generated by means of the illumination optic (4) according to a second illumination setting, which differs from the first illumination setting, and the illumination radiation (16) is directed to the image field (11) of the projection optic (10) by means of the projection optic (10).During an exposure interval between the first and second exposure phases, illumination radiation (16) is generated according to the second illumination setting using the illumination optics (4). This illumination radiation (16) strikes an optical element (M2) of the projection optics (10), but is not directed to the image field (11) of the projection optics (10).

An optical detection device (14), in particular an optical detection device (14) for a vehicle, in particular a front camera for a vehicle, for monitoring at least one monitoring area (18) using optical waves (38), a driver assistance system, a vehicle, and a method for operating an optical detection device (14) are described. The optical detection device (14) comprises at least one optical system (20) for imaging at least one part of the at least one monitoring area (18) into at least one image field (42), at least one image receiver (24) arranged in the at least one image field (42), and at least one part of at least one secondary optical receiving device (48).The at least one part of the at least one secondary receiving device (48) comprises at least one optical waveguide input (26) which, viewed from the at least one optical system (20), is arranged next to the at least one image receiver (24).

The application discloses an event camera depth estimation method based on unsupervised domain adaptation, and is suitable for the technical field of event camera depth estimation in the computer vision field. The method comprehensively analyzes the differences between the image domain and the event domain, and strengthens the connection between the two modes by changing the image style. This method can make the features in the implicit space more easily aligned, and reduce the gap in the explicit space. Training in the labeled image field, then transferring the knowledge to the unlabeled event data; using cross-domain feature alignment and depth alignment to transfer knowledge from images to events, using appearance for style transfer, and using edge invariant consistency to minimize the gap between different fields. Through unsupervised domain adaptation, event monocular depth estimation is carried out only by using the depth label of the image.

The present disclosure relates to a positioning method, device, computer readable medium and electronic device. The method comprises: in response to receiving a user positioning request, determining at least one candidate point of interest corresponding to the user positioning request, wherein the user positioning request comprises first WiFi fingerprint information; for each candidate point of interest, extracting a similarity feature of the first WiFi fingerprint information and second WiFi fingerprint information of the candidate point of interest by an image feature extraction model; and determining a target point of interest where the user is located from the at least one candidate point of interest according to each similarity feature. By using the image feature extraction model in the image field to depict the fingerprint similarity, the complex work of manually designing features can be avoided, and the fingerprint similarity measurement has good generalization ability.

This invention discloses a lightweight automatic instrument identification system, comprising: a data acquisition unit including an instrument image field acquisition device for real-time acquisition of instrument images; a processing unit including a front-end module, an instrument preprocessing module, an instrument alignment processing module, and an instrument identification module for processing the instrument images to identify instrument data within them; a transmission unit including a transmission module and an instrument data module for remotely transmitting the identified instrument data from the instrument images to a database in the management department; and an operation and maintenance unit for providing remote operation and maintenance services to the data acquisition unit, processing unit, and transmission unit. This lightweight automatic instrument identification system can acquire and automatically identify data displayed on the instrument panel in real time, enabling real-time acquisition, identification, transmission, and remote operation and maintenance of data displayed on the instrument panel, providing data support and information services for modern enterprise management.

The application discloses a kind of liquid crystal polarization grating cascade light beam scanning device's calibration system and method, the calibration method includes the calibration of liquid crystal single-chip device, the derivation based on the prediction of theory, and light beam deflection angle, the optimal efficiency corresponding to the deflection angle, the voltage value corresponding to optimal efficiency.The calibration system provides a complete calibration scheme for large-scale scalable liquid crystal cascade device, which is beneficial to the further application of liquid crystal cascade system in two-dimensional light beam scanning and large field imaging field.The application can realize the fast, automatic and high-precision joint calibration of two-dimensional angle and overall diffraction efficiency of output light beam under the whole working voltage combination of multi-layer liquid crystal polarization grating.