130 results about "Depth imaging" patented technology

The invention discloses an underwater single photon laser radar imaging method and system based on a gated SPAD array, and belongs to the field of photoelectric detection and image processing. Through the underwater single photon TG-SPAD array range gating imaging system, real-time intensity imaging and high-precision depth imaging of an underwater scene target are realized, and the three-dimensional target reconstruction precision can reach a millimeter level. The system comprises an onshore synchronous control and image processing module and an underwater laser radar module installed in a sealed waterproof shell. The underwater laser radar module comprises a pulse blue-green laser emission module, a single photon TG-SPAD array detection imaging module, and a multipath power supply and signal transmission module. The single-photon TG-SPAD array detection module has two modes of intensity imaging and gating imaging. The pulse blue-green laser transmitting module comprises a pulse blue-green laser and a beam expander. The multi-path power supply and signal transmission module comprises a multi-path power supply, a photoelectric composite watertight cable and a bidirectional optical transceiver. The system has the advantages of simple structure, high stability, low power consumption and high integration level.

In accordance with some embodiments, various examples of systems, methods, and media for single photon depth imaging with improved efficiency using learned compressive representations are provided. For example, systems and methods herein may detect a photon arrival based on a signal from a detector at a given position and time bin. A compressed histogram comprising K stored values, representing bins of the compressed histogram based on K values in a code word calculated based on the time bin and position and K coding tensors. Such systems and methods may be utilized for, among other uses, determining depth in a scene being imaged by the detector.

The invention discloses a photoacoustic spectrum-confocal Raman spectrum multi-view-field high-dimensional imaging method and a photoacoustic spectrum-confocal Raman spectrum multi-view-field high-dimensional imaging device. Nanosecond pulse laser with adjustable wavelength is generated through a continuous spectrum nanosecond pulser and a narrow-band spectrum tuning module and cooperates with a microscopic detection module, a depth imaging module, a galvanometer system and an electric displacement table to obtain spatial three-dimensional data, a photoacoustic spectrum and a Raman spectrum under multiple view fields; shallow photoacoustic spectrum-Raman spectrum tomography and deep three-dimensional photoacoustic imaging are realized; correcting a photoacoustic spectrum quantitative error by using a spectrum decoupling algorithm, and fusing the multi-view-field data to generate multi-view-field high-dimensional photoacoustic spectrum-Raman spectrum data; high-dimensional data features are extracted based on a 3D convolution instance segmentation network, and quantitative analysis and spatial distribution visualization of blood oxygen, inflammatory factors and the like are achieved. According to the method, the limitation that substances are difficult to analyze in photoacoustic imaging is overcome, the contradiction between the imaging resolution and the penetration depth is solved, and an accurate analysis means is provided for diagnosis of diseases such as knee osteoarthritis and sepsis.

The invention discloses a floating algae flow type microimaging sheath fluid focusing micro-fluidic chip device and system, and belongs to the technical field of micro-fluidic control. According to the device, the three-channel sheath fluid flow chip design is adopted, a large-channel inlet structure is combined to avoid algae cell blockage, and a sheath flow focusing technology is utilized to compress a sample flow to the center of a channel and limit the sample flow within the field depth range of a microscope objective to obtain a clear image. The arc-shaped structure of the sample channel reduces laminar flow disturbance, and a four-side transparent observation area supports panoramic depth imaging. The system comprises a microscopic imaging module, a fluid driving module and a sheath liquid flow chip module, a flow rate ratio of sheath liquid flow to sample flow is accurately controlled through a dual-channel liquid flow driving injection pump, and stable imaging within the depth of field of an objective lens is realized by combining a manual focusing platform. Experimental verification shows that the system can effectively compress sample flow to 21m nuclear flow diameter, imaging of floating algae such as chlorella, scenedesmus quadricauda and the like is clear, and the contradiction between flux and imaging quality of a traditional micro-fluidic chip is solved.

The invention relates to a lung region electrical impedance tomography (EIT) image reconstruction method based on a graph structure, and establishes an EIT depth imaging model in which double branch channels of a high-frequency channel graph attention network and a low-frequency channel graph attention network are parallel, and the model is named as HLGAT. The method comprises the following steps: injecting current excitation into a finite element simulation model of a lung region to obtain boundary voltage data required by EIT image reconstruction, and performing non-uniform mesh generation on the lung region needing image reconstruction to obtain nodes required by a graph neural network and an adjacency relationship between the nodes, so as to obtain a lung region model; storing the data in a graph structure form suitable for network input; the HLGAT aggregates the low-frequency characteristic information and the high-frequency characteristic information through the two channels, node output characteristic information of the two channels is fused in a learnable mode, a new adjacency matrix is reconstructed according to the node characteristic information output by the network, then a new Laplace matrix is constructed, more accurate conductivity distribution can be obtained, and the accuracy of the conductivity distribution is improved. And the physical process of electrical impedance imaging can be described more accurately, so that the accuracy of model imaging is improved.

According to the imaging equipment based on multi-photon depth imaging provided by the invention, a miniaturized imaging probe is realized by adopting a split type structure. In the imaging process, the imaging probe can be fixedly connected with an imaging object, the multi-photon effect is excited in the imaging object through the exciting light, so that optical signals in the imaging object are collected, and the internal situation in the imaging object is detected. Particularly, in the imaging equipment provided by the invention, the input optical fiber for connecting the imaging probe and the imaging host has the target bandwidth meeting the excitation requirement of the multi-photon effect, so that the composite laser in the target bandwidth can be carried, the multi-photon effects under different wavelengths can be excited at the same time, and different internal structures can be observed. In addition, a laser coupling module is arranged outside the imaging probe by the imaging equipment, so that the composite laser is directly transmitted through the input optical fiber, and the integration level of the imaging probe is improved.

The invention discloses a multi-mode synchronous monitoring method and system based on traditional Chinese medicine pulse conditions and microcirculation, and relates to the technical field of traditional Chinese medicine intelligent diagnosis. A pulse position coordinate set is generated by combining a preset space mapping relation; a pulse pressure signal and a microcirculation blood flow image are synchronously acquired; frequency domain transformation is performed on the pulse pressure signal and a pathological risk probability L is calculated; a comprehensive node feature vector is constructed to form a graph structure; a pathology mode recognition result is output by matching a pathology sub-atlas template library, dynamic correlation analysis of traditional Chinese medicine pulse conditions and microcirculation is achieved, and the technical bottlenecks that traditional pulse diagnosis is high in subjectivity, multi-mode asynchronous and difficult in pathology quantification are broken through.

Methods and systems for providing a dataset of human in-bed poses include simultaneously gathered images of in-bed poses of humans from imaging modalities including red-green-blue (RGB) and one or more of long wavelength infrared (LWIR), depth imaging, and pressure mapping. The images are obtained under a lighting condition and a cover condition. The dataset can be used to train a model of estimating human in-bed poses and for methods of estimating human in-bed poses. Methods and systems of estimating three-dimensional human poses from two-dimensional input images are provided.

A method for spoofing detection in a biometric object can include receiving an image pair representing two different viewpoints of the biometric object, and inputting the image pair into a disparity encoder of a trained neural network configured to map the image pair to an encoded signal conveying disparity information associated with the image pair, wherein the disparity encoder was trained for disparity map estimation together with a disparity decoder, the disparity encoder and the disparity decoder forming a disparity branch of the neural network during training. The method can also include inputting the encoded signal into a classification branch of the trained neural network configured to map the encoded signal to a probability that the biometric object is genuine or spoofed, wherein the classification branch was trained for spoofing detection together with the disparity branch. Techniques of training a neural network to perform image-based biometric anti-spoofing are also disclosed.

The invention provides imaging equipment based on multi-photon depth imaging and an imaging probe thereof, and a miniaturized imaging probe is realized by adopting a split type structure. In the imaging process, the imaging probe can be fixedly connected with an imaging object, the multi-photon effect is excited in the imaging object through the exciting light, so that optical signals in the imaging object are collected, and the internal situation in the imaging object is detected. Particularly, a plurality of input optical fibers are arranged in the imaging probe, laser of multiple wavelengths is provided at the same time in the multi-photon imaging process, optical signals can comprise optical signal components responding to exciting light of different wavelengths at the same time, and different internal structures are excited and detected at the same time. Besides, in the probe, the laser of each wavelength is subjected to beam combination treatment through the coupling module to form composite laser, so that the subsequent treatment of the composite laser is similar to that of exciting light, and the internal structure of the imaging probe is further simplified.

The invention discloses a multispectral depth camera, which comprises a combined beam splitting system, a multispectral imaging module, a depth imaging module, a precision lens and a data processing unit, the combined light splitting system comprises a dichroscope which is arranged in a light path and is used for dividing incident light into two paths, and the two paths are respectively guided to the main RGB sensor and the multispectral imaging module; the multispectral imaging module comprises a special mosaic optical filter and an image sensor; the depth imaging module comprises a main RGB sensor and an auxiliary RGB sensor; and the data processing unit is arranged behind the multispectral imaging module and the depth imaging module and is used for receiving image electric signals output by the multispectral imaging module and the depth imaging module. The method has the advantages and benefits that the multispectral information and the depth information can be accurately and quickly fused in real time, and the problems that after an independent sensor obtains the multispectral information and the depth information, image registration fusion processing is complex and low in precision are well solved.

The invention discloses an electrical source transient electromagnetic data imaging method, device and system, and a storage medium. The method comprises the following steps: S1, observing a horizontal electric field Ex and a vertical induced voltage Vz at the same measuring point; s2, respectively solving first-order derivatives of the horizontal electric field Ex and the vertical induced voltage Vz to the time t; s3, calculating the whole-period apparent resistivity according to the first-order derivative; and S4, time-depth transformation is carried out according to the whole-period apparent resistivity, and apparent resistivity depth imaging is realized. By adopting the technical scheme of the invention, the influence of the emission source is eliminated, and the imaging precision and convenience of the electrical source transient electromagnetic method can be obviously improved.

Depth imaging system implementing the method of any of the previous claims comprising: a. an imaging device (4) comprising a matrix of pixels (1) each pixel comprising a photodetector (9) capable of detecting single photons impinging thereon and optics able to make an image of the field of view on the matrix of pixel (1), said single photon detector having a binary logic status of true when a photon is detected and a logic status of false when no photon is detected in a timeframe; b. a projector (5) able to project a pattern in a time window of less than 10 sec, preferably less than 1 sec; c. a controller synchronising the projector (5) time window and the imaging device timeframe; d. a logic determining, in use, the presence, during the timeframe, of contiguous pixels (11) in the true state, and calculating the depth profile corresponding to said contiguous pixels (11).

The invention relates to the technical field of medical imaging, and discloses a peripheral lung cancer pleural invasion evaluation system based on ultrasonic targeted radiography, comprising: a double-frequency ultrasonic probe configured to independently work at different frequencies to realize depth imaging and high-resolution imaging of lung tissues and suitable for different types of lung lesions; the signal processing module can receive, analyze and process echo signals transmitted by the ultrasonic probe, generate images in real time and extract feature information; and the dynamic motion compensation module is used for automatically adjusting the emission time sequence and parameter setting of the ultrasonic signal based on the real-time breathing motion state of the patient. By adopting the design of the double-frequency ultrasonic probe and the core-shell structure, high-resolution imaging and depth detection of lung tissues are realized. By dynamically adjusting the thickness of the probe shell to be matched with the frequency, the system can adapt to complex tissue environments under different physiological conditions, and image definition and stability are ensured.

The present application relates to the technical fields of optical elements, systems, instruments and imaging, and discloses a multi-point confocal image scanning microscope and an imaging method. According to the present application, an imaging light source assembly, a light source collimation assembly, a multi-focus generation assembly, a multi-focus moving assembly, a multi-focus projection assembly, and a camera detection assembly are arranged along a light path, so as to achieve complete image recording. A unique multi-focus illumination mode provided by the present application is used in combination with an optical locked-phase detection technology, so that a defocus-induced stray signal during thick sample imaging can be effectively removed, and depth imaging is performed; the multi-focus generation assembly is switched, so that switching between a wide-field mode, a confocal mode and a super-resolution mode is easily achieved. Moreover, the present application uses a pixel redistribution algorithm to perform super-resolution reconstruction, and uses a multi-image deconvolution reconstruction algorithm and redundant information in a raw data set to perform frame reduction reconstruction, thereby increasing the imaging speed. Compared with the existing methods, the present application can increase the imaging speed, improve the imaging depth, reduce phototoxicity, and widen the diversity of imaging modes.

The invention provides a video SAR depth imaging method and system based on interpretable sparse tensor recovery, and relates to the technical field of synthetic aperture radar imaging, and the method comprises the following steps: building a tensor signal model according to a video SAR working process and an observation model of a single-frame SAR signal; establishing a video SAR sparse reconstruction model according to the established tensor signal model in combination with the low-rank sparse characteristic of the SAR image video; carrying out iterative solution on the established video SAR sparse reconstruction model; constructing a preliminary video SAR depth imaging network by deeply expanding an iterative solution of the video SAR sparse reconstruction model, and performing SAR video image correlation learning and sparse tensor recovery on the preliminary video SAR depth imaging network; and performing network training through back propagation, and optimizing parameters of the preliminary video SAR depth imaging network to obtain a final video SAR depth imaging network. According to the method, the imaging performance under the sparse sampling condition can be effectively guaranteed, and the method has applicability to complex scenes.

Examples are disclosed that relate to motion blur corrections for time-of-flight (ToF) depth imaging. One example provides a depth camera comprising a ToF image sensor, a logic machine, and a storage machine storing instructions executable by the logic machine to receive depth image data from the ToF image sensor, the depth image data comprising phase data and active brightness (AB) data, determine a first two-dimensional (2D) AB image corresponding to a first modulation frequency, and determine a second 2D AB image corresponding to a second modulation frequency. The instructions are further executable to determine a 2D translation based upon a comparison between the first 2D AB image and the second 2D AB image, determine corrected phase data based on the 2D translation to form corrected phase data, perform phase unwrapping on the corrected phase data to obtain a three-dimensional (3D) depth image, and output the 3D depth image.

The present disclosure provides a method, an apparatus and a storage medium for constructing a scene space model, the method includes the steps of obtaining first point cloud information collected by a mobile point cloud collecting device, obtaining depth image information collected by a fixed-point depth photographing device, determining a rotation matrix of a camera coordinate system of the fixed-point depth photographing device corresponding to a global coordinate system, generating a first panoramic image according to the depth image information, mapping the first panoramic image to a three-dimensional unit sphere, rotating the three-dimensional unit sphere according to the rotation matrix to generate a second panoramic image, and generating a scene space model according to the first point cloud information and the second panoramic image.

The application discloses a wide-range noise robust depth imaging method and system based on RGB guidance. The method steps are as follows: constructing a calibrated RGB-D database; establishing a differentiable physical imaging model, and adding physical constraints of an actual scene to obtain multiple noise-free measurement values; constructing a visual TOF double-branch multi-scale fusion depth reconstruction network, taking depth feature extraction and visual feature extraction fusion as an end-to-end network for iterative optimization, and using color pseudo-edge and Fisher information loss to supervise the network reconstruction effect, and jointly training the encoding function and the depth reconstruction network; inputting test data into the trained encoding function and reconstruction network to reconstruct the depth map of the test scene; and building an RGB-guided wide-range noise robust depth imaging hardware prototype system, and using the optimized encoding function and reconstruction network to reconstruct a high-quality depth map in an actual scene.

The invention relates to the technical field of automatic boxing, in particular to a robot automatic boxing method, system and device based on multi-mode perception feedback control, and the method comprises the steps that the geometric dimension of goods to be loaded is obtained; a boxing space coordinate system fixedly associated with the container body is established above the boxing area, surface appearance data of goods placed in the container area are collected in real time, a three-dimensional height distribution diagram is constructed, and a local protruding area is identified based on the three-dimensional height distribution diagram; and on the basis of the local convex area, in combination with the geometric dimension of the to-be-filled goods, planning an optimal box falling position, and recording the optimal box falling position as a box falling area. According to the method, the packing space coordinate system fixedly associated with the box body is established, the stacking state in the box and the goods to be loaded are sensed in real time in combination with three-dimensional depth imaging, the three-dimensional height distribution diagram reflecting the actual morphology in the box is constructed, and on the basis, the physical dimension of the goods and the height distribution information in the box are fused, so that the packing space coordinate system is obtained. And planning a box falling area with the optimal stability.

Examples are disclosed that relate to motion blur corrections for time-of-flight (ToF) depth imaging. One example provides a depth camera comprising a ToF image sensor, a logic machine, and a storage machine storing instructions executable by the logic machine to receive depth image data from the ToF image sensor, the depth image data comprising phase data and active brightness (AB) data, determine a first two-dimensional (2D) AB image corresponding to a first modulation frequency, and determine a second 2D AB image corresponding to a second modulation frequency. The instructions are further executable to determine a 2D translation based upon a comparison between the first 2D AB image and the second 2D AB image, determine corrected phase data based on the 2D translation to form corrected phase data, perform phase unwrapping on the corrected phase data to obtain a three-dimensional (3D) depth image, and output the 3D depth image.

An apparatus, system, method (100) and computer program product are disclosed for assisting in positioning an object including a subject and / or an assist device on a subject support in an imaging and / or treatment session. The method comprises acquiring (101), using a camera system, image / spatial data of the object support on which the object (s) are placed, the image / spatial data comprising depth / 3D information. The method comprises obtaining (111) reference data comprising reference depth / 3D information, the reference data representing the object support on which no object (s) are placed. Determining (104) at least one geometric attribute of the (or each) object from the image and / or spatial data, where the determining (104) comprises detecting (105) the object (s) by determining (110) 3D points of which the acquired depth / 3D information differs from the reference depth / 3D information and associating these points with the object. The geometric attribute for each object is determined by directly calculating sample statistic (s) for the point (s) associated with the object.

Disclosed is a depth imaging system with a light source; a depth sensor comprising direct Time-of-Flight (dToF) pixels and indirect Time-of-Flight (iToF) pixels; and processor(s) configured to: employ the light source to emit an intensity-modulated light pulse towards objects in a real-world environment; obtain dToF data indicative of time taken by the intensity-modulated light pulse to reach the dToF pixels after being reflected by the objects; obtain iToF data indicative of phase shifts undergone by the intensity-modulated light pulse upon reaching the iToF pixels after being reflected by the objects; determine optical depths for the dToF pixels; determine optical depths for the iToF pixels; and generate a depth image from the optical depths of the dToF pixels and the optical depths of the iToF pixels.

The system comprises a light splitting module, an imaging module and an automatic focusing module, the light splitting module is used for splitting light reflected by a sample into a main light path and a light splitting path, the imaging module is used for obtaining a full depth-of-field image corresponding to the main light path, and the automatic focusing module is used for focusing the full depth-of-field image. The automatic focusing module comprises a liquid lens and an automatic focusing sensor, the liquid lens is located between the imaging module and the light splitting module and is coaxial with the imaging module and the light splitting module, and the automatic focusing sensor is used for obtaining light on a light splitting path and calculating the defocusing amount of the sample; and the control module is used for storing a calibration mapping relation between the driving parameters of the liquid lens and the defocusing amount of the automatic focusing sensor, and is also used for calling the mapping relation table to adjust the driving parameters of the liquid lens according to the defocusing amount. Dynamic electric signals can be generated according to feedback data of the automatic focusing sensor, the liquid lens is driven to achieve millisecond-level focal length switching, high-speed focusing is achieved, and a clear panoramic depth image of a sample is shot.

A method for operating a sparse depth imaging system is presented. The method comprises receiving a depth map of an environment. The depth map comprises a plurality of pixels having locations in an optical sensor coordinate system. A pattern of illuminator dots in an optical source coordinate system is received. Each illuminator dot has a fixed location in a defined plane in the optical source coordinate system. The depth map is projected into a 3D point cloud in the optical sensor coordinate system. Each point in the 3D point cloud is assigned a 2D location in the defined plane. A depth value for each illuminator dot is interpolated based on transformed depth of points in the 3D point cloud. Each illuminator dot is assigned a 3D location in the optical sensor coordinate system. A depth for each illuminator dot is output in the optical sensor coordinate system.

A depth imaging system based on modulated light field, characterized in that it comprises the following modules: a light projection module for projecting discrete light beams to a target object and switching between a modulated light field mode and a uniform light field mode; a light source control module for light emission and control of the switching of the light field mode; a TOF sensing module for receiving the measurement light beams reflected by the target object; a multipath interference elimination module for obtaining image data under the modulated light field mode and the uniform light field mode, estimating the multipath interference component therefrom, removing the measurement error caused by the multipath interference, and outputting a high-precision depth image. The present application can determine the multipath interference component by the background area data in the first image data collected when the discrete light beams are projected to the target object, process the light spot area data to remove the multipath interference component, thereby eliminating the measurement error caused by the multipath interference, and realizing the output of a high-precision depth image.

The application discloses an unsupervised array SAR imaging method with signal-to-noise ratio robustness and target generalization, which is constructed by a deep neural network architecture including two cascaded stages of denoising and reconstruction. In the first stage, the statistical characteristics of the measurement domain are used to remove noise interference, and the pure measurement signal is extracted by using the first stage network. In the second stage, the scene details are recovered by combining the physical forward model and the regularization constraint, and the second stage network is combined with the physical forward projection operator and the regularization constraint. The method overcomes the dependence of the existing deep imaging method on a large amount of high-quality labeled data set, and the defects of high computational complexity and poor noise resistance of the traditional iterative algorithm, and has the characteristics of obtaining high signal-to-noise ratio and high-resolution array SAR images under the condition of only containing noisy observation data, and significantly improving the imaging robustness and generalization ability in complex scenes.

The present disclosure provides new and innovative systems, methods, and apparatuses for detecting non-decode events in indicia scanning settings. In an example, a system comprises a depth imaging assembly, a 2D imaging assembly, and a processing device, wherein the processing device is configured to attempt to decode an indicium affixed to a first item that is passing through at least one of a field of view of the 2D imaging assembly or a field of view of the depth imaging assembly, determine a first characteristic associated with the first item based on depth data from the depth imaging array, and responsive to a failed attempt to decode the indicium, detect a second item that is passing through the field of view of the 2D imaging assembly and the field of view of the depth imaging assembly, determine a second characteristic associated with the second item based on depth data from the depth imaging assembly, determine if the first item is a same item as the second item based on comparing the first characteristic and the second characteristic, and responsive to determining that the first item and the second item are not the same item, transmit a message to an alert module that is indicative of a non-decode event.

Depth images acquired during a scan of one or more portions of a user's body may be used to determine a full-body three-dimensional (3D) representation of the user. Depth imaging data may be used to determine the full-body shape and contours of the user when rotating in front of a user device. Machine learning methods for pose detection may be used to determine the portion of the user's body being scanned, as well as the position and pose of the user's body. A point cloud alignment process that leverages knowledge of user behavior during the scan is used to determine parameters for a full-body representation of a user, which may be based on a plurality of partial scans of the user's body. A full-body representation of a user may be output and / or displayed along with accurate measurements determined for various portions of the user's body.

This invention provides a true surface seismic-geological integrated velocity modeling and pre-stack depth imaging method, belonging to the field of seismic imaging technology. The method includes: obtaining a near-surface velocity model using first-arrival tomographic inversion and fusing it with a mid-deep velocity model obtained from a large floating surface of reflected waves to form an initial depth-migrated velocity field; optimizing the velocity model using reflected wave tomographic velocity inversion to construct a true surface isotropic velocity model; extracting azimuth and dip data from an isotropic migration seismic database, and then calculating various parameters of the anisotropic model and obtaining anisotropic velocities through anisotropic model analysis; and repeatedly iterating and updating the model using network tomographic inversion to obtain a multi-information-constrained anisotropic velocity model. This invention solves the problems of slow modeling speed, poor accuracy, poor imaging quality, and low precision in existing true surface seismic-geological velocity modeling and pre-stack depth imaging methods.