296 results about "Image stabilization" patented technology

The invention belongs to the field of tunnel wall surface deformation monitoring, and particularly relates to a tunnel wall surface deformation monitoring method based on computer image recognition, which comprises the following steps: acquiring expandable data and accessing the expandable data to a subsystem; image stabilization operation is carried out on the edge side, and a standardized preprocessing subsystem is constructed to process data; constructing a multi-modal fusion architecture of a structural topological graph and a space-time diagram neural network; constructing a hierarchical alarm judgment mechanism of an uncertainty-driven risk score and a sectionalized adaptive threshold, and linking the BIM and work order circulation to form a closed loop; according to the invention, millimeter-level displacement resolution can be realized, false alarm and missing alarm can be obviously reduced, and long-term online traceable tunnel wall surface deformation monitoring and graded early warning closed loop can be supported.

The invention discloses an image super-resolution edge reconstruction method based on morphology and coverage rate perception. The method comprises the following steps: dividing an image into an edge region and a non-edge region based on depth and brightness information; anti-aliasing edge detail recovery is realized through coverage rate perceived depth mode classification and a table look-up filter; generating direction features by using the brightness gradient and keeping details through a table look-up filter; and combining the reconstruction results of the current frame and the historical frame to ensure the image stability in a dynamic scene. The invention also provides an image super-resolution edge reconstruction system. According to the method provided by the invention, the quality of an object edge and a newly appearing pixel region can be remarkably improved, sawtooth artifacts are effectively inhibited, and relatively high time stability is kept in a dynamic scene, so that the requirements of real-time rendering and visual enhancement application are met.

The invention provides an endoscope image stabilization control method, which comprises the following steps of: acquiring an original dithering image sequence and inertial data of an endoscope, fusing the original dithering image sequence and the inertial data, acquiring an initial mixed motion field, performing operation semantic segmentation on the original dithering image sequence, and acquiring a collaborative attention map in combination with a physical motion mechanism. Obtaining a space-time adaptive filtering kernel through the collaborative attention map, filtering the initial mixed motion field according to the space-time adaptive filtering kernel, obtaining a stable motion field, carrying out image deformation and interpolation synthesis processing on the stable motion field, and obtaining a stable image sequence; through the integrated technical scheme of operation semantic segmentation, dynamic image stabilization optimization and accurate jitter suppression, the problem of interference of endoscope jitter on the neurosurgery operation visual field is solved.

The invention belongs to the technical field of video monitoring and image recognition, and particularly relates to a video monitoring transmission delay detection method and system based on image recognition, and the method comprises the steps: extracting image stable texture features through SIFT to generate a 128-dimensional descriptor, capturing an inter-frame motion trend through a Lucas-Kanade algorithm to generate a time feature, and carrying out the detection of the transmission delay of the video monitoring through the Lucas-Kanade algorithm. Finally, dynamic weighted fusion is carried out through an attention mechanism, and a space-time joint feature vector is generated; then, a dynamic template containing spatial-temporal characteristics and a local clock is generated at a sending end, cross-end matching is carried out at a receiving end by using an FLANN algorithm, the influence of network jitter and clock skew is eliminated through a double-calibration mechanism of basic time delay calculation, clock skew calibration and jitter compensation, and finally time delay after calibration is output; based on this, the method has the advantages of avoiding the interference of network jitter on the delay detection precision and reducing the delay standard exceeding false alarm condition caused by instantaneous deviation through the design of double-calibration delay calculation and cross-end feature accurate matching.

An optical image stabilization apparatus includes a first position detector and a second position detector configured to detect a position of a movable member relative to a base member in directions of first and second detection axes that are not orthogonal, a first driving unit and a second driving unit configured to drive the movable member relative to the base member in directions of first and second drive axes. The first or second detection axis is different from the first and second drive axes. An intersection of the first and second drive axes is closer to a center of gravity of a movable unit including an element fixed to the movable member among an optical element, the movable member, and the first and second driving units, than an intersection of the first and second detection axes.

The invention discloses an airborne camera anti-shake control method and system, and relates to the field of camera anti-shake control, and the method comprises the steps: building a hysteretic deformation tensor field, generating a visual hysteretic residual tensor through differential operation and lagging feature analysis, taking the visual hysteretic residual tensor as observation input, and carrying out the state estimation through a LuGre dynamic friction model. Calculating a micro bristle deformation state and an equivalent friction torque value of a blocking holder, performing visual compensation analysis based on the equivalent friction torque value of the blocking holder, judging whether the system is in a static friction zero-crossing critical region or not based on a micro bristle deformation estimated value, generating a reverse feed-forward compensation torque instruction according to the generalized all-source anti-interference torque, and determining whether the system is in a static friction zero-crossing critical region or not. The integral term of the controller is dynamically reset, vector synthesis is carried out on a reverse feed-forward compensation torque instruction and a basic instruction of a main image stabilization control loop, final driving voltage is generated and applied to a pan-tilt motor, and stepped picture lagging and jumping caused by instant release of energy in a long-focus view field are restrained.

The invention relates to the technical field of image stabilization, in particular to an electronic anti-shake method and system, and the method comprises the following steps: obtaining an angular velocity through a gyroscope, obtaining an angular displacement vector through integration, outputting inter-frame motion transformation parameters through time alignment, segmenting an image, calculating optical flow features, and outputting regional distortion feature distribution. The method comprises the following steps: performing spatial transformation to compare direction mark abnormity to generate a full-image compensation parameter mapping table, performing region transformation based on mapping to generate an anti-shake compensation image frame, performing prediction track Kalman filtering to determine a cutting boundary, and performing dynamic cutting to output a stable image sequence. Local distortion is accurately corrected by combining optical flow feature region calculation and abnormal direction comparison, self-adaptive compensation is achieved through nonlinear reverse mapping and linear translation grading processing, boundary control and view keeping are ensured through motion trail prediction and dynamic cutting, and vibration blurring and offset are remarkably reduced.

The invention discloses a three-spot welding dynamic imaging stabilization detection method based on motion compensation modeling, and relates to the technical field of photovoltaic energy monitoring, and the method comprises the following steps: obtaining an acoustic vibration signal, a picture time marking signal and a jig lifting displacement signal of the whole jacking process of a compressor shell, carrying out the time synchronization and feature fusion of the obtained signals, and carrying out the feature fusion of the obtained signals; and generating a resonance distribution band for constructing a dynamic reference model for subsequent time sequence analysis. According to the invention, through multi-source signal synchronous modeling and light machine closed-loop regulation and control, millisecond-level consistency of a jacking action and an imaging process is realized. Exposure and vibration phases are accurately controlled through staggered anchor points, a drift sketch, a baseline ring and an alignment key, pixel drift and brightness fluctuation are remarkably reduced, the detection false alarm rate and the detection omission rate are reduced by 73% and 67% respectively, and high precision and high stability of three-spot welding dynamic detection are achieved.

A method for improved image stabilization may include shifting image data from a memory device integrated with a display device, where the image data represents motion of the display device and corresponds with a time of capture of the image data; analyzing the image data via a processor to determine a stabilization correction to apply to the image data, analyzing including, determining the stabilization correction to correct for a displacement of at least a portion of the image data; applying the determined stabilization correction to the image data stored in the memory device to achieve stabilized image data; and outputting the stabilized image data from the display device.

To provide highly reliable lens image stabilization units and image-stabilized telescopes. [Solution] The lens vibration isolation unit comprises a position limiting cover and a lens vibration isolation structure mounted inside the position limiting cover. The position limiting cover comprises a bottom cover 20 and an end cover 10 connected to the bottom cover, and both the bottom cover and the end cover are provided with through holes corresponding to the position of the vibration isolation lens in the lens vibration isolation structure. The lens vibration isolation structure comprises a main control circuit board 45 and a movable unit 41 to which a vibration isolation lens 47 is attached. The main control circuit board is fixedly connected to the bottom cover and is provided with through holes corresponding to the vibration isolation lens. The movable unit is connected to the bottom cover via a tension spring 30 so as to separate the movable unit from the main control circuit board and so as to allow the movable unit to move relative to the main control circuit board. The vibration-isolating telescope has the advantages of high vibration isolation accuracy, compact size, and excellent cost performance, as it is equipped with a lens vibration isolation unit.

This application relates to a video processing method, apparatus, system, and computer-readable storage medium. The method includes: sequentially acquiring video images frame by frame using a photosensitive unit, and sequentially determining whether a target object in n consecutive video images is located within the image core region, where n is any integer greater than 1; if the target object is located within the image core region in the n consecutive video images, obtaining n initial positions of the target object relative to the center point of the photosensitive unit in the n consecutive video images; performing image stabilization processing based on the n initial positions to obtain image stabilization parameters corresponding to the Nth video image in the n consecutive video images, and sending the image stabilization parameters to a video display end for image stabilization processing based on the received image stabilization parameters corresponding to each frame of video images, where N is a positive integer less than or equal to n. This can reduce video image jitter caused by video acquisition terminal jitter and improve the viewing experience for video viewers.

This application discloses a miniature gimbal, camera module, and electronic device, including a first bracket, a second bracket, a third bracket, a platform, a first driving component, a second driving component, and a third driving component. The second bracket is located inside the first bracket and is rotatably connected to the first bracket about a first axis. The third bracket is located inside the second bracket and is rotatably connected to the second bracket about a second axis. The platform is located inside the third bracket and is rotatably connected to the third bracket about a third axis. The first driving component drives the second bracket to rotate relative to the first bracket. The second driving component drives the third bracket to rotate relative to the second bracket. The third driving component drives the platform to rotate relative to the third bracket. In this application, the miniature gimbal adopts a nested bracket design and is equipped with three independently decoupled rotating driving components, so that the miniature gimbal can achieve three-axis rotation without crosstalk, and can achieve a larger angle of rotation when performing image stabilization.

The invention provides an electronic image stabilization control method, a program product, electronic equipment and a storage medium, and the method comprises the steps: converting a current frame image based on a homography matrix corresponding to the current frame image, and obtaining a first image region; determining whether a preset cutting area in the current frame image is completely located in the first image area or not; in response to the fact that the preset cutting area is not completely located in the first image area, adjusting the homography matrix; and carrying out conversion again based on the adjusted homography matrix until the preset cutting area is completely located in the first image area, and carrying out cutting based on the preset cutting area to obtain a stable image corresponding to the current frame image.

The application discloses a two-axis two-frame roll-pitch configuration photoelectric detection equipment control system and method, and belongs to the field of photoelectric detection equipment. The system comprises a power supply, an image controller, a servo controller, an outer frame, an outer frame roll motor, a first code disc, an outer frame slip ring, an inner frame, an inner frame pitch motor, a second code disc, a first gyroscope, a second gyroscope and a camera. An angle instruction is sent from a display control console to the servo controller and the image controller. The servo controller performs angle conversion, position loop control, roll rotation direction judgment and speed loop control, and outputs a signal to drive the motor. The code disc measures real-time angle information of the motor and sends the information to the servo controller. The gyroscope measures real-time angular velocity information of the camera and sends the information to the servo controller. The image controller receives a roll angle to perform electronic image stabilization, outputs an image to the display control console, and sends an image deviation to the servo controller when tracking a target. The image motion direction is consistent with the azimuth and pitch direction in the base coordinate system, and the human-computer interaction comfort is improved.

The movement of the movable part, which is movable in a plane relative to the fixed part, is appropriately restricted. [Solution] The first image stabilization unit 20 of the imaging device 10 includes a first restricting means and a second restricting means that restrict the movement of a movable part 20b that can translate and rotate in a plane relative to a fixed part 20a, and three balls 36 sandwiched between the fixed part 20a and the movable part 20b. At least a portion of the first restricting means is positioned within a region formed by a straight line connecting the three balls 36, while the second restricting means is not positioned within that region. The first restricting means has a first hole and a second hole on one of the fixed part 20a and the movable part 20b, and a contact portion 38a that is inserted into the first hole and the second hole on the other. When viewed from a direction perpendicular to the plane in which the movable part 20b can translate, the first hole is located on a straight line parallel to the first direction in which the movable part 20b can translate, passing through at least a portion of the second hole.

The invention provides a bending actuation type four-degree-of-freedom micro-motion platform with double piezoelectric actuators and an excitation method of the bending actuation type four-degree-of-freedom micro-motion platform, and belongs to the technical field of image stabilization and vibration suppression platforms. The micro-motion platform comprises a tail end platform, eight first bolts, two flexible hinges, two amplitude-change poles, four strain gauges, two piezoelectric actuators, two second bolts and a base; all the components are fixedly connected through the first bolt and the second bolt; the flexible hinge is used for transmitting linear and bending motion, and the piezoelectric actuator can achieve displacement output in a bending mode in the up-down direction and the left-right direction under the control of two paths of voltage. By coordinating the bending directions of the two piezoelectric actuators, the tail end platform can achieve translational motion along the Y axis and the Z axis and rotational motion around the Y axis and the Z axis, and therefore four-degree-of-freedom precise micro-motion adjustment is completed. The invention has the advantages of compact structure, small number of drivers, fast response and high precision, and is suitable for aerospace, navigation and other application scenes with strict requirements on optical imaging stability.

Disclosed is a camera module, which uses a new piezoelectric actuator as a driving element to meet the driving requirement of the camera module. Specifically, the camera module uses the new piezoelectric actuator as the driving element to move an optical camera lens for optical image stabilization. Moreover, the piezoelectric actuator is arranged in the camera module in a rational arrangement scheme, so as to meet both the structural design requirement and the dimensional design requirement of the camera module.

The utility model relates to mobile phone technical field discloses mobile phone camera module, including circuit board, the top middle part fixedly connected with bottom plate of circuit board, the top of circuit board is provided with protection mechanism, protection mechanism is used for protecting equipment, the bottom of protection mechanism is provided with focusing mechanism, focusing mechanism is used for focusing when photographing, protection mechanism includes hollow shell, the outer wall of hollow shell is with the inner wall screw connection of bottom plate, the inner wall fixedly connected with hollow column of hollow shell, the top of hollow column is provided with lens, the inner wall of hollow column is provided with anti -shake subassembly. In the utility model, install permanent magnet in hollow column to ensure image stability and accurate focusing, apply glue on the top of fixed plate, make it slide along the chute and be intercepted by the baffle, and the round inclined plate provides all -round protection for the lens, thereby effectively protecting the equipment and preventing the glue overflow from polluting the lens.

The present application relates to the technical field of optical image stabilization, and discloses a real-time video space-based camera image stabilization method and a storage medium. The real-time video space-based camera image stabilization method comprises: determining effective IMU data of a single image frame on the basis of a preset image collection time and a preset shutter response time; dividing pixels of the single image frame into a plurality of row pixels by row, and determining the effective IMU data corresponding to each row of pixels; and performing position correction on the corresponding row of pixels by means of the effective IMU data, so as to implement an image stabilization operation for the single image frame.

The invention discloses a polarization image stabilization evaluation method based on a photoelectric pod platform, and belongs to the technical field of photoelectric pod imaging stability evaluation. The photoelectric pod (1) is used for carrying out polarization stable imaging test and evaluation on a to-be-tested target (2) in a smoke simulation environment; the to-be-measured target (2) is used for simulating a target needing to be observed by the ground or air photoelectric pod (1); the smoke environment simulation box body (3) is used for simulating a smoke environment; the telescopic support (4) is used for simulating and adjusting the inclination angle of the photoelectric pod (1) and the to-be-measured target (2). The azimuth angle turntable (5) is used for simulating and adjusting the azimuth angle of the photoelectric pod (1); and the photoelectric pod fixing frame (6) is used for fixing the photoelectric pod (1). The method is used for solving the problem that in the prior art, the polarization imaging stability of the photoelectric pod cannot be evaluated by accurately simulating the outdoor smoke environment in the indoor environment.

An image stabilization control apparatus performs image stabilization by controlling first and second correction means, the first correction means correcting camera shake by driving a correction lens

The utility model discloses an anti-shake device for a mobile phone lens, which comprises an outer frame, a mounting frame is arranged in the outer frame, four groups of symmetrically distributed clamping blocks are arranged in the mounting frame, two groups of symmetrically distributed first adjusting rods are arranged in the mounting frame, and two groups of symmetrically distributed second adjusting rods are arranged in the mounting frame. The two sets of first adjusting rods and the two sets of second adjusting rods are vertically distributed, the four sets of clamping blocks are slidably connected with the corresponding sets of first adjusting rods and the corresponding sets of second adjusting rods correspondingly, and two sets of vertically-distributed bidirectional lead screws are arranged in the mounting frame. The distance between the two first adjusting rods and the two second adjusting rods is adjusted through rotation of the two-way lead screw in the mounting frame, then the distance between the four clamping blocks is adjusted, the anti-shake device can be used for fixing mobile phones of different models, and then anti-shake protection on different mobile phone lenses is achieved.

The disclosure discloses a method and a system for generating image adversarial examples based on an acoustic wave. The method includes: acquiring an image containing a target object or a target scene; generating simulated image examples for the acquired image, wherein the simulated image examples have adversarial effects on a deep learning algorithm in a target machine vision system; optimizing the generated simulated image examples to obtain an optimal adversarial example and corresponding adversarial parameters; and injecting the adversarial parameters into an inertial sensor of the target machine vision system in a manner of an acoustic wave, such that the adversarial parameters are used as sensor readings that will cause an image stabilization module in the target machine vision system to operate to generate particular blurry patterns in a generated real-world image so as to generate an image adversarial example in a physical world.

An image capture system for enhanced electronic image stabilization (EIS) includes an image capture device and an adapter lens. The image capture device includes an image sensor, a lens housing, a processor, and a lens assembly that includes a first group of optical elements disposed within the lens housing. The first group of optical elements are used project an image onto the image sensor. The processor performs EIS. The adapter lens is used to enhance EIS of the image capture device. The adapter lens has an adapter lens housing that interfaces with the lens housing. The lens housing automatically detects the adapter lens.

The present disclosure relates to a mountable camera device, comprising: an image capturing unit for capturing a sequence of images, the image capturing unit comprising at least a lens and an image sensor; a vibration sensor for measuring camera vibrations; an optical image stabilization mechanism for physically compensating for the camera vibrations by physically moving the lens and / or the image sensor; electronic image stabilization circuitry for digitally compensating for the camera vibrations by image processing; and processing circuitry configured to select between the optical image stabilization mechanism and the electronic image stabilization circuitry by comparing the camera vibrations against a predefined stabilization margin and / or based on a location of an object of interest in the sequence of images. The disclosure further relates to a method for controlling a mountable camera device having optical image stabilization capabilities and electronic image stabilization capabilities.

The invention relates to the technical field of image stability augmentation, and particularly discloses an image stability augmentation method and system based on pixel displacement compensation. The method comprises the following steps: acquiring attitude data of a virtual holder and a global motion vector of a video frame, and identifying a key attitude segment which is easy to generate a compensation boundary conflict; pixel displacement space distribution characteristics of the key attitude segment are collected, and a boundary sensitive area corresponding to characteristic attitude points is extracted; generating a non-rectangular compensation boundary form, a dynamic mask prototype and a continuous deformation rule based on the boundary sensitive area; and outputting a stability augmentation image sequence based on the dynamic mask prototype and the deformation rule. The system comprises an attitude acquisition module, a compensation analysis module, a rule determination module and a stability augmentation reinforcement module. The method is beneficial to reducing compensation boundary conflicts under a large-angle attitude, and adapts to a complex flight scene of the unmanned aerial vehicle.

This invention relates to the field of smart wearable device technology, specifically disclosing a camera adjustment method and system for smart glasses. The system includes an eye-tracking module, a head posture perception module, an environment perception module, an intent parsing module, a perspective decision module, and a camera driving module. Through multi-source information fusion, it analyzes the user's visual intent in real time, generates target perspective parameters, and drives the camera to perform optical zoom, mechanical rotation, or electronic image stabilization, achieving intelligent adaptive adjustment of the camera's perspective and improving augmented reality registration accuracy and interactive immersion.

This device provides a runout correction device that is advantageous in that it reduces the number of parts while also reducing the occurrence of guide member detachment when the product is subjected to impact. [Solution] The shake correction device comprises a movable group that holds a lens and is movable in a direction perpendicular to the optical axis, a base that movably holds the movable group, a plurality of rolling balls arranged between the movable group and the base, and a stopper structure that prevents the rolling balls from falling out. The stopper structure comprises a plurality of claw portions formed on the side of the movable group where the base is located, and a flange portion formed on the base at a position facing the claw portions when viewed along the optical axis.