6649 results about "Image sensor" patented technology

The invention relates to the technical field of machine vision structure health monitoring, and discloses a steel structure weld fatigue cracking real-time monitoring system based on machine vision. The system comprises a space-time registration and fusion module, a multi-scale feature analysis module, a health monitoring module, a crack deduction calculation module and a regulation and control strategy generation module. Performing space-time registration and pixel-level fusion through the visual data of the plurality of image sensors to generate a synchronous multi-source image stream; a multi-level welding seam characteristic spectrum is constructed through multi-scale characteristic analysis, and a welding seam structure knowledge base is dynamically updated; the knowledge base and the real-time characteristic spectrum are used for monitoring the welding seam health state, and abnormity is recognized; deducing a crack initiation position and an evolution path in combination with historical damage data; and real-time load information is fused to pre-estimate the remaining service life, and a structural integrity regulation and control strategy is generated online. According to the invention, high-precision fusion of the multi-source visual data and active prediction of the crack trend are realized, and the monitoring accuracy and the early warning capability are improved.

The invention relates to the technical field of goods shelf detection, in particular to a self-detection method and device for goods shelf settlement, and provides the following scheme: obtaining a top view image through an image sensor arranged right above the top of a goods shelf, dividing the image into a plurality of grid units, and positioning a rectangular geometric shape by utilizing Hough transform; and screening a plurality of to-be-detected areas in combination with the edge features. For an area to be measured, homographic registration and ortho-rectification are carried out based on a reference image, a displacement field is obtained by adopting sub-pixel-level dense registration, and a geometric parallax component field corresponding to imaging parameters is obtained through robust estimation. And under the hypothesis of small deformation, inverting the parallax into a pixel normal distance, and carrying out weighted aggregation on the local region to obtain a local distance measurement result. And by iteratively combining adjacent grids, determining a settlement area boundary, and finally outputting a settlement detection result. Millimeter-level settlement quantification can be realized under a single-frame image, hardware transformation is avoided, and the method is suitable for automatic detection and long-term monitoring of multi-specification goods shelves.

The invention provides an offshore wind turbine generator fault diagnosis method and system based on multi-source sensor data fusion. The method comprises the steps that a vibration signal from at least one component of a wind turbine generator is acquired through a vibration sensor; performing time-frequency conversion on the vibration signal by applying synchronous compression wavelet transform to obtain time-frequency representation of the vibration signal; when the reconstruction error exceeds a preset threshold value, it is judged that an abnormal event exists in the vibration signal; obtaining the position of a part corresponding to the abnormal event; starting an image sensor and an acoustic sensor according to the position of the component, and acquiring an image signal and a sound signal of the component according to the image sensor and the acoustic sensor; according to the DS evidence theory, the vibration signal, the image signal and the sound signal, obtaining the confidence of the fault type; the fault type of the component is judged according to the maximum confidence allocation principle, high-resolution time-frequency analysis can be achieved through synchronous compression wavelet transform (SST), and the fault feature identification degree is improved in combination with the self-encoding neural network and the D-S evidence theory.

The invention discloses an intelligent welding control system and method based on multiple sensors and electronic equipment, and belongs to the technical field of automatic welding, the system comprises a sensing layer, a decision-making layer and an execution layer, through cooperative work of a front laser vision sensor, a rear laser vision sensor and a molten pool image sensor, a groove three-dimensional model can be accurately established before welding, and the welding precision is improved. And dynamic information of the molten pool is continuously collected in the welding process, a dual monitoring mechanism for the geometric characteristics of the welding line and the state of the molten pool is formed, and multi-source data collection and fusion in the whole welding process are achieved. The control method comprises the steps of pre-scanning modeling, feedforward parameter planning, real-time feedback adjustment of a molten pool, data fusion optimization and the like, and high-precision self-adaptive control over welding parameters is achieved by combining deep learning and the Kalman filtering technology. According to the method, the welding adaptability, the control precision and the intelligent level can be remarkably improved, and the method is suitable for high-precision welding scenes such as pipelines, pressure containers and steel structures and has remarkable engineering application value and popularization prospects.

The invention relates to the technical field of camera control, and discloses a megapixel camera control method based on multifunctional fusion. The method comprises the following steps: acquiring original image data of an image sensor, and preprocessing to generate an initial brightness distribution diagram; and calculating a scene dynamic range to determine a target exposure parameter set containing exposure time, a gain coefficient and an aperture value, synchronously analyzing color temperature information, matching a preset white balance model to output a correction coefficient, and combining the two to generate a first control instruction to be sent to the image sensor. Receiving a touch screen focusing signal, and extracting a focus area coordinate to adjust a stroke parameter of a focusing motor; ambient light intensity is monitored in real time, and when the ambient light intensity is lower than a preset threshold, a flash lamp compensation module is activated and a compensation light quantity value is calculated. In the photographing mode, the output power of the flash lamp is adjusted according to the compensation light quantity value, the target exposure parameter set is recalibrated based on the focus area coordinates, and the camera complex scene adaptation and imaging quality are improved.

The invention discloses a multi-protocol high-speed image data receiving and aligning method and system based on an FPGA (Field Programmable Gate Array), and relates to the technical field of electronic information and image processing. Serial data streams from an image sensor are received, an FPGA serial input primitive is dynamically called to convert serial data into parallel data; a low-voltage differential signal protocol, a mobile industry processor interface protocol and a serial low-voltage signal protocol are supported; a configurable sliding window mechanism is adopted to compare synchronous codes in real time, and byte boundaries are locked; by identifying the time difference of arrival of data of each channel, multi-channel phase alignment is realized by adopting hardware-level delay compensation, and data arriving at the channel in advance is compensated by adopting a first-level register cache; and analyzing frame header and frame tail information of the image data, reconstructing an original image matrix and generating a video time sequence signal. The problems of poor compatibility and high resource consumption in multi-protocol high-speed image data receiving are solved.

The invention discloses a low-power-consumption warning ground pile awakening method and system based on human activity recognition, and belongs to the technical field of image analysis and intelligent security and protection. According to the method, in a micro-power-consumption mode, the environment is monitored through an image sensor, and when environment changes meet awakening conditions, lightweight human body detection is conducted through an edge AI chip. And if the human activity probability exceeds the confidence coefficient, starting a main camera and a high-computing-power AI chip to carry out deep behavior analysis, fusing a behavior analysis result with a geographic position and a timestamp, generating a risk decision result, and triggering a dynamic response. According to the invention, a hierarchical wake-up and multi-source fusion technology is adopted, on-demand work is realized, power consumption is greatly reduced, early warning accuracy is improved through deep behavior analysis, and the problems of high energy consumption and inaccurate early warning of traditional equipment are effectively solved.

The invention relates to the technical field of coating detection, and particularly provides an aluminum pigment thickness uniformity analysis and detection method and system.The method comprises the steps that a multispectral image and a polarization image of an aluminum pigment coating are obtained, and geometrical shape information of a base material is obtained; analyzing whether the aluminum pigment coating has a non-uniformity defect or not according to the multispectral image and the polarization image; when the non-uniformity defect exists, acquiring the defect type and the optical characteristic of the non-uniformity defect according to the multispectral image and the polarization image; acquiring a target light source parameter and an image sensor target receiving angle according to the defect type, the optical characteristic and the geometrical shape information; adjusting a light source and an image sensor of the aluminum pigment thickness uniformity analysis and detection equipment according to the target light source parameter and the target receiving angle of the image sensor; the method comprises the following steps: acquiring a coating image by using aluminum pigment thickness uniformity analysis and detection equipment, and acquiring non-uniformity defect characteristics according to the coating image; according to the method, adaptive adjustment of detection parameters can be realized.

A camera system has at least a first and a second camera each with an image sensor. Active areas of the image sensors of the first and second camera are determined and define an extended image space of a real-time panoramic video. A bounding box captures a fixed position in space or an object is set. The bounding box moves through extended image space. Image data determined only by the bounding box is harvested from camera image sensors and displayed within a window on a screen in real-time. Scan-line control of images sensors based on the bounding box is updated in real-time to form an e-gimbal. Steps of the e-gimbal are performed by a machine learning inference phase on a processor.

A control apparatus is provided for a camera system that includes an image pickup apparatus including an image sensor and a lens apparatus including an optical system that includes at least one optical member for changing at least one of a tilt effect of tilting a focal plane relative to an imaging plane of the image sensor and a shift effect of moving an imaging range. The control apparatus includes at least one memory that stores a set of instructions, and at least one processor that executes the set of instructions to acquire information on an optical state of the optical system, and correct defocus caused by movement of the at least one optical member using the information on the optical state of the optical system.

The invention relates to a naked eye 3D binocular image acquisition and real-time processing system based on hardware synchronous triggering, and belongs to the technical field of image processing and three-dimensional display. According to the system, a hardware synchronous triggering mechanism is adopted, a time sequence synchronous control unit is used for sending a synchronous pulse signal to a binocular image sensor, and strict synchronization of left and right viewpoint image acquisition is ensured. The image signal processing unit processes collected original data, the stereo parallax correction module performs epipolar correction, and the sub-pixel interleaving module generates a composite view frame according to grating parameters of the display terminal. The system realizes high-speed data transmission through a double-buffer direct memory access DMA mechanism. The problems of visual tearing and weak stereoscopic impression caused by asynchronous binocular image acquisition in the prior art are solved, nanosecond-level synchronization precision is realized, optical crosstalk is reduced, and smoothness and comfort of stereoscopic display are ensured.

The embodiment of the invention provides a camera module and electronic equipment, relates to the technical field of camera shooting, and is used for reducing the size of a camera. The circuit board of the camera module can comprise a first part and a second part. The first part is arranged on the side where the first surface of the image sensor is located and covers the non-photosensitive area. The first portion is electrically connected with the image sensor. In addition, the second part is arranged around the periphery of the first part. The vertical projection of the second part on the plane where the first surface is located is not overlapped with the image sensor. In the direction perpendicular to the first surface, the first part can be overlapped with the image sensor so as to reduce the length of the camera module. The first portion is located between the lens assembly and the image sensor such that the thickness of the first portion of the circuit board can be multiplexed with the total length of the lens.

The invention discloses a water supply and drainage pipeline anomaly detection method based on image recognition. Initial video image data are acquired through an image sensor; establishing a three-channel feature extraction network model, wherein the three-channel feature extraction network model at least comprises a visible light channel, a geometrical shape channel for extracting pipeline structure deformation features through 3D convolution and a dynamic optical flow channel for capturing liquid flow abnormal features based on an RAFT algorithm; inputting an initial video image into the three-channel feature extraction network model to perform feature extraction, establishing an analysis model based on a bidirectional LSTM neural network, inputting feature image data into the analysis model to establish time sequence association, performing abnormal evolution through a GNN graph neural network, performing abnormal type classification according to a pipeline state evaluation index, and obtaining a pipeline state evaluation result. And performing early warning based on a classification result. The detection efficiency is improved, the labor cost and the safety risk are reduced, and operation and maintenance personnel can master the state of the pipeline in time.

An image sensor includes a substrate having pixel regions, and a deep isolation pattern provided between the pixel regions within the substrate, wherein the deep isolation pattern includes a liner film covering a sidewall of a trench in the substrate, a first pattern provided on an inner sidewall of the liner film and having a height less than a height of the liner film, an isolation film on inner sidewall of the first pattern, and a second pattern covering inner sidewalls of the isolation film and an upper portion of an inner sidewall of the liner film, a void is provided in the second pattern, the second pattern is spaced apart from the first pattern by the isolation film, and a grain size of the second pattern is larger than a grain size of the first pattern.

An apparatus an method for generating three-dimensional representations of serial sections, wherein the method includes creating a plurality of slide images using a slide scanner, the slide scanner comprising an image sensor and a stage, receiving, using at least a processor, the plurality of slide images from the slide scanner, extracting, using the at least a processor, a plurality of features from the plurality of serial slide section images using a feature extraction algorithm, registering, using the at least a processor, the plurality of serial slide section images as a function of the plurality of feature, generating, using the at least a processor, a three-dimensional (3D) stack view, wherein the 3D stack view comprises the plurality of serial slide section images, and displaying the 3D stack view through a display device.

The invention discloses an ultra-wide-spectrum endoscopic imaging device capable of being used for short-wave infrared fluorescence imaging, which is used for in-vivo minimally invasive imaging and comprises an illumination module, a wide-spectrum image transmission module, an imaging module and an image processing module. The illumination module consists of a light source and a light guide optical fiber, and is used for generating illumination light from ultraviolet to short wave infrared band and transmitting the illumination light to the wide-spectrum image transmission module; the wide-spectrum image transmission module consists of a few-interface optical imaging channel and a light guide illumination channel, and is used for illuminating an imaging target, exciting target fluorescence and collecting image signals from ultraviolet to short-wave infrared bands; the imaging module is composed of an optical filter and an imaging camera, and the imaging camera can be a wide spectral response image sensor or can be formed by combining cameras working in different wavebands and is used for converting optical images in different wavebands into image data; and the image processing module is used for registering and fusing image data of different wavebands in real time and displaying the image data.

An image sensor includes a substrate the substrate including a plurality of unit pixels arranged in a direction parallel to a first direction; a first and second photodiode inside of the substrate in each of the plurality of unit pixels and separated from each other in a second direction, perpendicular to the first direction; and a device isolation film between the plurality of unit pixels. A pair of pixels side-by-side in a third direction, perpendicular to the first and second direction, among the plurality of unit pixels, share a microlens, and at least one of the plurality of unit pixels includes a light shielding film on the substrate. Accordingly, in the image sensor, while maintaining the existing photodiode forming process, the autofocusing function in a vertical direction may be supplemented, and further, performance of the image sensor may be improved.

The invention relates to a back-illuminated image sensor and a preparation method thereof, and relates to the technical field of integrated circuits, in which a plurality of photodiode structures are distributed at intervals along a first direction parallel to a back surface and penetrate through a P-type epitaxial layer along a second direction close to a substrate; the bottom photosensitive part comprises a first horizontal part extending along a first direction and a first longitudinal protruding part extending to the back surface of the substrate; the middle photosensitive part comprises a second horizontal part extending in the first direction and a second longitudinal protruding part extending to the top face of the first horizontal part. The second longitudinal protruding part is located on the side, away from the first longitudinal protruding part, of the first horizontal part in the first direction. The top photosensitive part comprises a third horizontal part extending in the first direction and a third longitudinal protruding part extending to the top face of the second horizontal part. The electron concentration of a photosensitive area can be increased at least, and the photosensitive performance and the integration density of the BSI image sensor are improved.

The invention relates to the technical field of intelligent urethral surgical instruments, and particularly discloses a urethral dilation path planning system integrating visual SLAM and force perception, which synchronously acquires image data of the internal environment of the urethra and contact force data between the instrument and tissues through an image sensor and a force sensing unit integrated at the front end of the dilation instrument; constructing a three-dimensional environment model in the urethra by utilizing a visual SLAM technology, and positioning the position of an instrument in real time; the force data and the three-dimensional model are fused to generate a dynamic force distribution diagram, and a safe expansion path is planned based on the distribution diagram and the current position of the instrument; dynamically adjusting the advancing direction and the expansion force of the instrument through a closed-loop control system to enable the instrument to move along a planned path; meanwhile, path deviation and force abnormity are detected in real time through a monitoring mechanism, and model updating and path re-planning are triggered.

Systems and techniques are provided for foveated sensing. For example, a process can include obtaining, from a first image sensor, a first image of a scene. The first image includes a full region including a fovea region and a peripheral region. The first image sensor is associated with a first spatial resolution. The process can include obtaining, from a second image sensor, a second image of the scene. The second image includes the fovea region. The second image sensor is associated with a second spatial resolution different from the first spatial resolution. The process can include generating a combined image. The combined image includes a first plurality of pixels associated with the fovea region of the scene and a second plurality of pixels associated with associated with a peripheral region of the scene. The second plurality of pixels is generated from pixel values of the first image.

An image sensor including a substrate having first and second surfaces, the second surface opposite the first surface; a first deep trench isolation layer in the substrate and defining pixel region groups, each pixel region group having a pair of pixel regions; a second deep trench isolation layer between the pair of pixel regions of each pixel region group; photoelectric conversion areas in each pixel region; and a lens array on the second surface and composed of two-dimensionally arranged microlenses. Each microlens having a shape, in plan view, with a long axis and a short axis, the short axis being substantially perpendicular to the long axis and shorter than the long axis. The microlenses covering each pixel region group, and a width of at least a first portion of the second deep trench isolation layer being smaller than a width of the first deep trench isolation layer.

A training system for an endoscopic procedure, the training system including an endoscope having an image sensor configured to generate images; an image processing device including a housing and a processing circuit in the housing, the processing circuit including a processor and memory, the memory having graphical user interface (GUI) logic and a trained single-pass neural network model, the processor being configured to process the neural network model and the GUI logic to present a GUI; and a physical model including cavities corresponding to interconnected human cavities. The GUI is configured to receive a user input corresponding to a training mode or an exam mode. In the training mode the GUI is configured to present navigation feedback, and in the exam mode the GUI is configured to not present navigation feedback.

The invention relates to a backside illuminated image sensor preparation method and a backside illuminated image sensor, and relates to the technical field of integrated circuits, and the method comprises the steps: providing a substrate which comprises a plurality of trench isolation parts distributed at intervals in a first direction; self-aligning the plurality of trench isolation parts to form a first type bottom semiconductor layer comprising a plurality of first target patterns which are distributed at intervals along the first direction, the first target patterns comprising a first type second semiconductor part, a first semiconductor part and a second semiconductor part which are sequentially distributed along the first direction; forming a second type photosensitive lamination layer on the surface, deviating from the substrate, of the bottom semiconductor layer; self-aligning the first semiconductor part, and forming a plurality of first type semiconductor columns which penetrate through the photosensitive lamination layer along a second direction and extend to the first semiconductor part; and forming a first type top semiconductor layer by adopting the same preparation process as the bottom semiconductor layer. The electron concentration of a photosensitive area can be increased at least, and the photosensitive performance of the BSI image sensor is improved.

In some embodiments, techniques are provided for autonomously backing a vehicle (such as a Class 8 truck) to a trailer. In some embodiments, environment sensors such as image sensors and range sensors mounted to the vehicle detect a trailer and determine distances between the trailer and the vehicle as well as relative angles of the trailer and the vehicle. In some embodiments, the vehicle determines a path to the trailer based on this information, and autonomously controls braking, torque, and / or steering of the vehicle to autonomously back the vehicle along the determined path.

The invention discloses a field-of-view self-stabilization and self-adjustment hyperspectral camera system and a control method, and relates to the technical field of hyperspectral imaging. The system comprises a first imaging lens group, a movable slit, a two-dimensional linear driver, a slit outer layer light shield, a collimating lens group, a light splitting element, a second imaging lens group, an area array image sensor, an attitude sensor and a control acquisition circuit. Angle disturbance is obtained in real time, two-dimensional compensation displacement of the slit is calculated to drive the slit to move reversely, field-of-view collection is kept basically constant, collection is triggered according to a set rhythm, slit position and attitude data are recorded synchronously, and the pre-calibrated slit position and mapping of original coordinates and ideal coordinates are combined, so that field-of-view collection is completed. Geometric transformation and resampling dynamic correction are carried out on view field inclination aberration and spectrum bending aberration generated along with slit position changes, the environmental adaptability and reliability are improved, a hyperspectral data cube with accurate space coordinates and a stable spectrum curve is output, and the method is suitable for unmanned aerial vehicle-mounted hyperspectral remote sensing.

The invention provides a visual bronchoscope device, and relates to the technical field of endoscope catheters. The visual bronchoscope device comprises a catheter body and a handle sleeve, an integrated imaging module is eccentrically arranged at the far end of the catheter body, the near end of the catheter body is connected with the handle sleeve, a sputum suction channel is formed in the catheter body, and a handle isolating membrane is further arranged on the imaging catheter; the integrated imaging module comprises a plurality of miniature LEDs and an ultra-miniature CMOS image sensor; the device further comprises a handle and a computer, and the computer comprises an image processing unit which is used for receiving original image data from the integrated imaging module, performing image processing on the original image data and displaying an image processing result on the display screen. The kit can be used for auxiliary diagnosis of lung diseases.

Systems and methods of the present disclosure enable fault risk detection in renal care systems and / or devices, by receiving, from an image sensor, an image of a component of the renal care system / device and using a fault risk detection machine learning model to output a detected fault risk in the component based at least in part on trained machine learning model parameters configured, through training, to classify the detected fault risk as matching to one or more known fault risks. An alert is generated to an operator or technician of the renal care system / device, including an indication of the detected fault risk.

The invention relates to the field of wafer defect detection, in particular to a rapid zooming wafer detection microscope based on MEMS and a detection method. The microscope comprises an illumination part, a sample stage, a spectroscope, a microscope objective, an MEMS micromirror array zoom module, a CMOS image sensor, a laser interference distance measuring sensor and a synchronous control and processing module based on an FPGA. The MEMS micro-mirror array zoom module composed of a plurality of micro-mirror units is introduced into a light path, the deflection state of each micro-mirror unit is adjusted, a dynamic reflecting surface with a controllable equivalent curvature is formed, focusing regulation and control of imaging light beams are achieved, electronic focusing without mechanical movement is completed, the response speed is superior to that of traditional mechanical adjustment, and the imaging quality is improved. And the method is suitable for high-speed online detection.

The invention relates to the technical field of video monitoring, and particularly discloses a video acquisition system and method based on time triggering, and the system comprises a high-precision clock source, a hardware triggering signal generation module, an image sensor, a timestamp precise acquisition module and a system main control module. The high-precision clock source provides a reference clock; the hardware trigger signal generation module generates a synchronous trigger pulse to drive the image sensor to expose; the timestamp accurate acquisition module directly captures an exposure completion signal output by the sensor and generates a corresponding high-precision original timestamp; and the system main control module fuses and packages the timestamp and the image data. The method is realized based on the system. According to the invention, the accuracy and stability of the triggering moment are ensured from the source, and the accurate correspondence between the timestamp and the physical exposure moment is realized.

The present disclosure relates to an image sensor and / or a method for manufacturing the same. The image sensor may include a substrate including a first surface, a second surface opposite the first surface, and a plurality of unit pixel regions in the substrate; a pixel defining pattern; and a micro lens. Each of the plurality of unit pixel regions may include a photoelectric conversion layer. The pixel defining pattern may extend through the substrate in a first direction so as to define each of the unit pixel regions. The micro lens may be on the second surface of the substrate and corresponding to the unit pixel regions. The pixel defining pattern may include a first conductive layer and a second conductive layer spaced apart from the first conductive layer.