Abstract: Various embodiments include a camera with image sensor shifting capabilities and a flexure arrangement. In various embodiments, the flexure arrangement may include an upper flexure and a lower flexure. The upper flexure may include a suspension wire that extends between two sheets. The lower flexure may include one or more flexure arms that connect a moveable platform to a stationary platform.

Abstract: There is provided a mobile robot that performs the obstacle avoidance and visual simultaneous localization and mapping (VSLAM) according to image frames captured by the same optical sensor. The mobile robot includes a pixel array and a processor. An upper part of the pixel array is not coated with any filter and a lower part of the pixel array is coated with an IR filter. The processor performs range estimation using pixel data corresponding to the lower part of the pixel array, and perform the VSLAM using pixel data corresponding to the upper part of the pixel array.

Abstract: The present embodiment relates to a lens driving device comprising: a housing; a bobbin disposed inside the housing; a coil disposed at the bobbin; a magnet disposed in the housing and facing the coil; an elastic member coupled to the housing and the bobbin; and a damper disposed at the elastic member, wherein the elastic member comprises an outer part coupled to the housing, an inner part coupled to the bobbin, and a connection part for connecting the outer part and the inner part; and the damper is disposed at the connection part.

Abstract: An actuator for a camera includes a guide member, a base, and a carrier stacked in a housing in an optical axis direction, a first driving unit generating driving force in a first axial direction and a second axial direction, the first driving unit including a plurality of magnets and a plurality of coils, and a second driving unit generating driving force in the optical axis direction and including a magnet and a coil. The carrier, the base, and the guide member are movable together in the first axial direction, the carrier and the base are movable together in the second axial direction, the carrier is movable relative to the base in the optical axis direction, the magnets and the coils of the first driving unit and the magnet and the coil of the second driving unit are disposed to face each other in the optical axis direction.

Abstract: An illustrative example camera device includes a substrate and a sensor supported on the substrate. The sensor is configured to gather image information. A lens is situated near the sensor and an electroactive polymer selectively causes relative movement between the sensor and the lens.

Abstract: A program may cause a computer to perform the steps of: acquiring a target posture information indicating a target posture of a movable member with m degrees of freedom components associated with a movement or rotation of the movable member; deriving a correction information indicating a corrective component for correcting an error in respective target positions of m+n positions of the movable member due to at least one of n degrees of freedom components other than m degrees of freedom, based on at least one value of m+n values corresponding to m+n positions of the movable member indicated in respective position informations; deriving respective target positions of each of m+n positions of the movable member based on m degrees of freedom components and the corrective component; and outputting respective target position informations indicating the respective target positions to each of m+n control circuits.

Abstract: An image acquisition apparatus includes a display layer including hole regions through which external light is received and pixel regions arranged between the hole regions, an image sensor disposed under the display layer and configured to generate a raw image by sensing the external light received through the hole regions, and a processor configured to perform image processing on the raw image based on blur information based on an arrangement of the hole regions.

Abstract: Various embodiments include flex circuit arrangements for a camera with sensor shift actuation. Some embodiments include a flexure-circuit hybrid structure. Some embodiments include an actuation-module flex circuit hybrid structure. In some embodiments, the hybrid structures may include different portions that share multiple layers of a plurality of stacked layers. In some embodiments, one portion of a hybrid structure may include one or more layers that are different from the layers in another portion of the hybrid structure.

Abstract: The present disclosure relates to a method and apparatus for processing image. The method includes: determining a first translation amount based on a first voice coil motor (VCM) value of a first image photographed by a wide-angle camera, the VCM value is a normalized value corresponding to a magnitude of a current acting on a coil of a VCM in response to successful focusing of the camera; determining a second translation amount based on a zoom multiple of the first image and the first translation amount; and obtaining a target image by translating the first image by the second translation amount and amplifying the first image. According to the present disclosure, smooth switching of zooming can be achieved, and obvious geometric jump of images in continuous focal lengths and between focal lengths is avoided, thereby providing a good zooming experience to the user.

Abstract: The present invention provides a technology that acquires a high resolution iris image more quickly than before. An iris capture apparatus according to one example embodiment of the present invention includes a rotatable movable mirror; a control unit that controls rotation of the movable mirror; a capture unit that captures different regions of a face of a user via the movable mirror and outputs a group of images every time the control unit rotates the movable mirror by a predetermined angle; and an iris image acquisition unit that acquires an image of an iris of the user from the group of images.

Abstract: A machine learning (ML) operating mode is selected for a camera. A physical orientation of a housing of a camera is determined. In response to determining the orientation, an operating mode from a set of operating modes is selected. The set of operating modes includes at least a ML inference mode and a ML training mode. Based on the selected operating mode, images obtained by an image capturing unit are processed. In the ML inference mode, a ML controller applies a ML model to the images to infer or predict characteristics of the image (e.g., detecting objects within the images). In the ML training mode, the ML controller is configured to cause a ML model to be trained using images captured by the image capturing unit, either local to the camera or on a remotely located computing device.

Abstract: A shake correction control device includes a processor that selects mechanical correction of mechanically performing shake correction of a subject image or electronic correction of electronically performing the shake correction of the subject image. The processor performs a switching control from either of the mechanical correction or the electronic correction to the other of the mechanical correction or the electronic correction, and synchronizes shake correction operations of the mechanical correction and the electronic correction during the switching control, and changes an operation ratio of the mechanical correction and the electrical correction during the switching control.

Abstract: An image reading apparatus (1) includes image sensors (20A, 20B). The image sensor (20A) includes light guides (21A, 22A) guiding light to a reading target (M), a lens body (8A) forming an image of reflected light derived from the light guided by the light guides (21A, 22A) and reflected from the reading target (M), light receiving elements (11A) converting the image of reflected light formed by the lens body (8A) into electrical signals, and a controller (14A) controlling exposure times of the light receiving elements (11A). The image sensor (20B) includes a lens body (8B) forming an image of transmitted light derived from the light guided by the light guide (22A) and transmitted through the reading target (M), light receiving elements (11B) converting the image of transmitted light formed by the lens body (8B) into electrical signals, and a controller (14B) controlling exposure times of the light receiving elements (11B).

Abstract: A method for displaying and processing an image captured by an optical system used to simulate a rear-view system of a vehicle, includes capturing the image, identifying primary edges of a first image of the plurality of images, locating a first border within the first image that extends to part of a first edge of the first image, identifying secondary edges of a second image of the plurality of images, selecting a second edge from the secondary edges closest in position and orientation to the part of the first edge of the first image, locating a second border within the second image that extends to the second edge, and adjusting the second image such that a second part of the second border of the second image aligns with the first border of the first image, wherein the optical system simultaneously simulates both a plane mirror and a spotter mirror in form of a spherical mirror in the single image to provide a plurality of optical subsystems.

Abstract: An information processing apparatus determines a direction (first direction (12)) from a sensor (10) toward a moving object (20) by detecting the moving object (20) using the sensor (10). The information processing apparatus causes a camera (30) to perform imaging while moving the optical axis direction (34) of the camera (30) along the first direction (12). As a result, a plurality of captured images (32), each of which is captured in the different direction, are generated by the camera (30). The information processing apparatus (2000) detects the moving object (20) by performing image analysis on the captured image (32).

Abstract: A camera system includes a first camera unit and a second camera unit. The first camera unit may include a first actuator. The second camera unit may include a second actuator. The first actuator may move one or more components of the first camera unit to provide autofocus and/or optical image stabilization functionality to the first camera unit. The second actuator may move one or more components of the second camera unit to provide autofocus and/or optical image stabilization functionality to the second camera unit. The first camera unit may be configured to capture a first image of a first visual field. The second camera unit may be configured to capture, simultaneously with the first camera unit capturing the first image, a second image of a second visual field.

Abstract: An imaging support device that supports imaging performed by an imaging apparatus includes an acquisition portion that acquires an in-image shift amount between a predetermined position in a captured image obtained by capturing an imaging region by an imaging element and a position of a target subject image showing a target subject, and a focal length of the imaging apparatus, a derivation portion that derives a movement amount required for moving the position of the target subject image to a specific position by a position adjustment portion which adjusts the position of the target subject image in the captured image, based on the in-image shift amount acquired by the acquisition portion, the focal length acquired by the acquisition portion, and information related to a pixel interval of pixels in the imaging element, and an output portion that outputs the movement amount derived by the derivation portion.

Abstract: Images may be captured by a moving image capture device. A reference image and a background image may be selected from the images. The reference image may include depiction of an object, with the object blocking view of the background. The background image may include depiction of the background blocked by the object in the reference image. An object layer may be generated by segmenting the depiction of the object from the reference image. A background layer may be generated by combining the depiction of the background in the background image with the reference image. The background layer may be blurred and combined with the object layer to generate a panning image.

Abstract: An imaging device has a computer executing instructions that, when executed by the computer, cause the computer to: acquire a current position in an imaging direction of the imaging device; perform a process of controlling the imaging direction of the imaging device; and control, in a case where the imaging direction is controlled to a target position, a timing of starting a stop process for stopping controlling the imaging direction based on a speed at which the imaging direction is changed.

Abstract: Described examples relate to an apparatus comprising a first sensor configured to scan an area of interest during a first time period and a second sensor configured to capture a plurality of images of a field of view. The apparatus may include at least one controller configured to receive the plurality of images captured by the second sensor, compare the timestamp information associated with at least one image of the plurality of images to at least one time period of the first time period, and select a base image from the plurality of images based on the comparison.

Abstract: The present invention relates to a device for controlling a multi-axial point tilt of a camera lens and a method therefor, characterized by controlling a camera lens to move within a common stroke section among respective stroke sections in which the camera lens can move in an axis direction (z-axis) parallel to an optical axis direction at each of three or more axial points, wherein the camera lens is moved to a target position by using a compensation factor that is compensated such that a lens movement distance for each control code is the same.

Abstract: A vibration type actuator control apparatus, which uses a vibration from a vibrator to move a contact member, includes a control unit and a drive unit. The control unit includes first and second learned models, each having a neural network, and outputs control amounts for the drive unit to move the contact member. When a contact member moving target velocity is input, the first learned model outputs a first control amount as one of the control amounts. When a positional deviation is input, the second learned model outputs a second control amount as one of the control amounts. The drive unit moves the contact member using a value based on the first and second control amounts. The positional deviation is in association with a difference between a target position for moving the contact member and a detected position detected when the contact member is moved relative to the vibrator.

Abstract: A computer-implemented method executed by at least one processor for applying rolling shutter (RS)-aware spatially varying differential homography fields for simultaneous RS distortion removal and image stitching is presented. The method includes inputting two consecutive frames including RS distortions from a video stream, performing keypoint detection and matching to extract correspondences between the two consecutive frames, feeding the correspondences between the two consecutive frames into an RS-aware differential homography estimation component to filter out outlier correspondences, sending inlier correspondences to an RS-aware spatially varying differential homography field estimation component to compute an RS-aware spatially varying differential homography field, and using the RS-aware spatially varying differential homography field in an RS stitching and correction component to produce stitched images with removal of the RS distortions.

Abstract: A device for assembling at least two shots of a scene acquired by at least one sensor includes a memory and processing circuitry. The processing circuitry is configured to save, in the memory, a first data set contained in a first signal generated by each pixel of the sensor and indicative of a first shot of the scene, and a second data set contained in a second signal generated by each pixel of the sensor and indicative of a second shot of the scene. The processing circuitry is further configured to assemble the first and second shots on the basis of the content of the first and second data sets of a plurality of pixels in order to form a resulting scene.

Abstract: A lens apparatus attachable to and detachable from an image pickup apparatus includes a detector configured to detect an angular shake of the lens apparatus, an image stabilizer configured to provide an image stabilization by driving part of an imaging optical system in the lens apparatus, and a controller configured to calculate a driving amount using a rotation angle based on an output of the detector and information for converting the rotation angle into the driving amount. The controller changes the information based on the image pickup apparatus attached to the lens apparatus.

Abstract: A method for determining a safe state for a vehicle includes disposing a camera at a vehicle and disposing an electronic control unit (ECU) at the vehicle. Image data is captured via the camera and provided to the ECU. An image processor of the ECU processes captured image data. A condition is determined via processing at the image processor of the ECU captured image data. The condition comprises a shadow present in the field of view of the camera within ten frames of captured image data or a damaged condition of the imager within two minutes of operation of the camera. The condition is indicative of a condition where processing of captured image data degrades in performance. The ECU determines a safe state for the vehicle responsive to determining the condition.

Abstract: An imaging apparatus is provided. The apparatus comprises a controller configured to transmit an image obtained by an image sensor to an external device via a communication circuit, and cause the external device to execute a predetermined image processing on the image. The controller obtains information indicating recommendation or non-recommendation for the execution of the predetermined image processing on the image by the external device, based on a state of at least one of an imaging optical system and the image sensor when capturing the image, and transmits an execution request for the predetermined image processing on the image to the external device via the communication circuit, if the obtained information indicates the recommendation.

Abstract: An image pickup apparatus is mountable with a lens apparatus including a first optical image stabilizing unit configured to move an optical element that is a part of the imaging optical system, in a direction intersecting an optical axis of the imaging optical system. The image pickup apparatus includes an image sensor, a second optical image stabilizing unit configured to move the image sensor in a direction intersecting the optical axis, and a control unit configured to control the second optical image stabilizing unit based on an image stabilizing reference position of the first optical image stabilizing unit which is a reference position for an image stabilization of the first optical image stabilizing unit.

Abstract: A camera may include at least one suspension assembly as part of optical image stabilization and/or autofocus systems of the camera. The suspension assembly may include an inner frame, an outer frame, and one or more flexure arms. Electrical traces may be deposited at both sides of the suspension assembly. A connection may be created, for electrical traces at the different sides of the suspension assembly, through the suspension assembly by removing (e.g., using an etching process) one or more parts in the body of the suspension assembly to create one or more cavities. A remaining part of the suspension assembly surrounded (and thus isolated) by the cavities may thus form at least a part of the connection for the electrical traces. The connection may further include one or more filled trenches connecting the electrical traces to the remaining part of the suspension assembly.

Abstract: Various embodiments include perimeter sheet spring suspension arrangements for cameras. A perimeter sheet spring suspension arrangement may be used to suspend a moveable platform of the camera from a base structure of the camera, and allow a lens group of the camera to move laterally. According to some embodiments, the perimeter sheet spring suspension arrangement may include one or more tabs that may be used as bumpers that cushion lateral movement of the moveable platform.

Abstract: The described technology is a technique related to a method for controlling a mobile device cradle and combining images. The method for controlling a mobile device cradle performed in an application of a user device linked with the mobile device cradle, comprises: pairing the mobile device cradle with the user device; starting capturing an image based on an input of a user; extracting a subject from a captured image; calculating a moving speed and a moving direction of the subject extracted; and calculating a rotation speed and a rotation direction of a motor included in the mobile device cradle based on the calculated moving speed and moving direction, and controlling the motor based on the calculated rotation speed and rotation direction.

Abstract: A lens driving device includes a fixing bracket; first and second support frames; a rotation assembly including first and second rolling balls so that the fixing bracket and the first support frame are spaced apart from each other and form a rotational connection about a first direction, and the first and second support frames are spaced apart from each other and form a rotational connection about a second direction; a driving assembly for driving the fixing bracket to rotate relative to the first and second support frames about the first direction and for driving the first support frame to rotate relative to the second support frame about the second direction; a flexible circuit board; and first and second elastic support components. The lens driving device reduces the height of the overall structure, and effectively reduces the height of the lens driving device.

Abstract: Disclosed herein are system, method, and computer program product embodiments for machine learning systems to process incoming call-center calls based on inferred sentiments. An incoming call is routed to a call agent based on an inferred topic, classified based on one or more inferred sentiments of a current caller's speech, determining, based on the call classification, that a complaint has been articulated and initiating an automated assistance by searching for one or more similar callers to the current caller. Based on finding a successful call outcome associated with one or more similar callers, the system suggests one or more phrases to the call agent for use in a dialog with the current caller to improve the one or more inferred sentiments.

Abstract: A sensor driving device is provided. A sensor driving device according to one aspect of the present invention comprises: a first substrate; a second substrate disposed on the first substrate and electrically connected to the first substrate; and an image sensor disposed on the second substrate, wherein the second substrate comprises a body and a first protrusion part protruding from one end of the body, and the first protrusion part comprises a first extension part extending in a first direction from the body, and a second extension part extending in a second direction that differs from the first direction from the first extension part.

Abstract: In a method, it is determined that a detachable lens is mounted on an image capture device in a first orientation. A first image of a controlled scene is captured with the detachable lens mounted in the first orientation. It is determined that the detachable lens is mounted on the image capture device in a second orientation that is rotated approximately 180 degrees from the first orientation. A second image of the controlled scene is captured with the detachable lens in the second orientation. A first image circle center of the first image is determined. A second image circle center of the second image is determined. An average image circle center is determined, based on the first image circle center and the second image circle center. The average image circle center is provided to an image stabilization algorithm when the detachable lens is mounted on the image capture device.

Abstract: In a camera device that includes a hand tremor correction mechanism, an anti-vibration mechanism for the camera device is provided. An optical system that is movable in an optical axis direction and includes a focus adjustment mechanism is provided in the camera device, includes an anti-vibration mechanism that performs hand tremor correction by anti-vibration of the imaging element, and includes from an object side, an imaging lens group, the anti-vibration mechanism, and an imaging element provided on the anti-vibration mechanism, and a plane perpendicular to the optical axis of the imaging lens group is used as a movement plane to allow the imaging element on the anti-vibration mechanism to move, so as to achieve hand tremor correction.

Abstract: In various examples, a set of object trajectories may be determined based at least in part on sensor data representative of a field of view of a sensor. The set of object trajectories may be applied to a long short-term memory (LSTM) network to train the LSTM network. An expected object trajectory for an object in the field of view of the sensor may be computed by the LSTM network based at least in part an observed object trajectory. By comparing the observed object trajectory to the expected object trajectory, a determination may be made that the observed object trajectory is indicative of an anomaly.

Abstract: A camera module includes a housing, a carrier, a frame, a lens holder, an autofocusing (AF) ball bearing, and an optical image stabilization (OIS) ball bearing. The carrier is coupled to the housing and configured to move in an optical axis direction. The frame is coupled to the carrier and configured to move in a first axis direction, perpendicular to the optical axis direction. The lens holder is coupled to the frame and configured to move in a second axis direction, perpendicular to the optical axis and the first axis. The AF ball bearing is disposed between the housing and the carrier. The OIS ball bearing is disposed on either one or both of the carrier and the frame, and the frame and the lens holder. Either one or both of the AF ball bearing and the OIS ball bearing have an elastic modulus of 20 GPa or less.

Abstract: An optical member driving mechanism is provided. The optical member driving mechanism includes a movable portion, a fixed portion, a driving assembly and a guiding assembly. The movable portion is connected to an optical member, and is movable relative to the fixed portion. The driving assembly drives the movable portion to move relative to the fixed portion. The guiding assembly limits the mode of movement for the movable portion relative to the fixed portion.

Abstract: An optical member driving mechanism for driving an optical member having an optical axis is provided, including a fixed portion, a movable portion, a driving assembly, and a circuit board. The fixed portion includes a case and a frame, and a gap is formed therebetween. The movable portion is movably connected to the fixed portion, and configured to hold the optical member. The driving assembly can drive the movable portion to move relative to the fixed portion. The circuit board is disposed in the gap, and has a plate portion and a protruding portion. The protruding portion is disposed between the plate portion and the fixed portion, so as to tightly dispose the circuit board in the gap.

Abstract: A method and apparatus for capturing digital video includes displaying a preview of a field of view of the imaging device in a user interface of the imaging device. A sequence of images is captured. A main subject and a background in the sequence of images is determined, wherein the main subject is different than the background. A sequence of modified images for use in a final video is obtained, wherein each modified image is obtained by combining two or more images of the sequence of images such that the main subject in the modified image is blur free and the background is blurred. The sequence of modified images is combined to obtain the final video, which is stored in a memory of the imaging device, and displayed in the user interface.

Abstract: A camera module includes a support structure having an internal space, a movable body disposed in the internal space of the support structure, and a plurality of driving wires supporting the movable body in the internal space of the support structure and configured to move the movable body relative to the support structure, each of the driving wires being made of a shape-memory alloy and having one end connected to the support structure, and another end connected to the movable body. An angle between the movable body and each of the driving wire is maintained at 15.5° or less at all positions to which the movable body is movable by the driving wires.

Abstract: Broadly speaking, the present techniques provide specific arrangements of shape memory alloy (SMA) actuator wires in SMA actuation apparatuses. In one arrangement, a single straight shape memory alloy actuator wire may be used, which may be inclined at an acute angle greater than 0 degrees with respect to a plane normal to the movement direction. In another arrangement, two straight lengths of shape memory alloy actuator wire may be used, where the SMA wires may be inclined at an acute angle greater than 0 degrees with respect to a plane normal to the movement direction.

Abstract: A lens driving module includes a holder, a cover, a carrier, at least one first magnet, a first coil, at least two second magnets, at least one first sensor and at least one second sensor. The holder includes an opening hole. The cover is made of metal material and coupled to the holder. The carrier is movably disposed in the cover and for coupling to a lens. The first magnet is movably disposed in the cover. The first coil is wound around an outer side of the carrier. The second magnets are disposed on one end of the carrier. The first sensor is for detecting a magnetic field of the second magnets. The second sensor is for detecting a magnetic field of the first magnet.

Abstract: An image stabilization control apparatus includes an extraction unit configured to extract signals in a plurality of frequency bands from a signal output from a first shake detection sensor detecting a translation component of shake, and extract signals in the plurality of frequency bands from a signal output from a second shake detection sensor detect detecting a rotation component of shake; a first calculation unit configured to calculate a rotational radius of shake for each of the plurality of frequency bands, using the signal from the first shake detection sensor and the signal from the second shake detection sensor; and a second calculation unit configured to calculate a parallel shake amount for each of the plurality of frequency bands, using the signal output from the second shake detection sensor and the rotational radius.

Abstract: A method, computer program, and computer system is provided for coding video data. Video data including (1) a first frame comprising a first current view and a first reference view and (2) a second frame comprising a second current view and a second reference view is received. A co-located block in the first reference view is identified for a current block in the first current view. A predicted offset vector is calculated based on the motion vector between the co-located block and its reference block in the second reference view. The video data is encoded/decoded based on the predicted offset vector.

Abstract: An image shake correction device includes: a movable member; an imager that is fixed to the movable member; a support member that supports the movable member to be movable; and two movement restrictors that restrict a movement range of the movable member, each of the two movement restrictors includes a recess portion or a through-hole and an insertion member as defined herein, a shape of the recess portion or the through-hole is as defined herein, and a second diagonal line overlaps an extension line of a first diagonal line and the center of the light receiving surface overlaps a line connecting the first diagonal line and the second diagonal line as defined herein.

Abstract: An optical element driving mechanism is provided and includes a fixed assembly, a movable assembly, a driving assembly, and a position-sensing assembly. The movable assembly corresponds to an optical element, and the movable assembly is movable relative to the fixed assembly. The driving assembly is configured to drive the movable assembly to move relative to the fixed assembly. The position-sensing assembly is configured to sense the movement of the movable assembly relative to the fixed assembly, and the position-sensing assembly includes a sensed unit and a sensing element. The sensing element corresponds to the sensed unit. The sensed unit has a plurality of reference magnetic elements arranged in a first direction, the sensed unit and the sensing element are arranged in an arrangement direction, and the first direction is not parallel to the arrangement direction.

Abstract: When swinging of a camera does not follow a motion of a subject in following-photographing, the position of the subject deviates among a plurality of images, and thus there is a problem that the subject that is moving is blurred. An image processing apparatus includes: a standard region designation unit configured to designate a partial region in an image as a standard region; a standard region motion blur setting unit configured to set a motion blur in the standard region designated by the standard region designation unit as a predetermined motion blur; and a motion blur adjustment unit configured to adjust a motion blur in the standard region so that the motion blur becomes the predetermined motion blur and adjust a motion blur on a screen of a region different from the standard region in accordance with the adjusting of the motion blur in the standard region.

Abstract: The present invention provides an anti-shake method for a panoramic video, which comprises: obtaining, in real time, an output video frame, a fisheye image corresponding thereto, a pixel timestamp in the video frame, and a corresponding camera gyroscope timestamp; synchronizing the pixel timestamp in the video frame with the corresponding camera gyroscope timestamp, and calculating a rotation matrix of the camera movement in the camera gyroscope timestamp; smoothing the camera movement and establishing a coordinate system of a smooth trajectory; correcting the fisheye image distortion; and rendering the fisheye image by means of forward rendering to generate a stable video. According to the present invention, the rolling shutter distortion of a panoramic video sequence can be corrected, the image distortion caused by the rolling shutter of a CMOS can be corrected, and the rolling shutter is eliminated, thereby achieving a better anti-shake effect of a video image.