Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for tracking objects. Actions include determining a respective field of view for a plurality of cameras within a monitored property, receiving one or more indications related to a detection of a target object by the plurality of cameras, and obtaining the respective field of views of each of the plurality of cameras. Additional actions include determining that a location of the target object is visible within the respective field of view of a first camera from among the plurality of cameras, and the location of the target object is not visible within the respective field of view of a second camera from among the plurality of cameras, obtaining a current field of view of the first camera, and providing the current field of view of the first camera for output.

Abstract: In this vehicular monitoring device, an imaging unit 2 captures an image of the driver of a vehicle. A driving state measurement unit 70 analyzes the image captured by the imaging unit 2 and measures a plurality of driving states including the eye opening degree of the driver. A travel state determination unit 71 determines the travel state of the vehicle. An alarm determination unit 72 uses the driving states and the travel state as a basis to determine whether to activate an alarm device 5. When the driving state measurement unit 70 fails to measure the eye opening degree but it is determined that the travel state and the driving states other than the eye opening degree are normal, the alarm determination unit 72 causes the driving state measurement unit 70 to perform measurement of the eye opening degree again.

Abstract: The present disclosure relates to motion vector refinement. As a first step, an initial motion vector and a template for the block are obtained. Then, the refinement of the initial motion vector is determined by template matching with said template in a search space. The search space is located on a position given by the initial motion vector and includes one or more fractional sample positions, wherein each of the fractional sample positions belonging to the search space is obtained by interpolation filtering with a filter of a predefined tap-size assessing integer samples only within a window, said window being formed by integer samples accessible for the template matching in said search space.

Abstract: The present disclosure relates to methods and apparatus for image processing. For example, disclosed techniques facilitate a sparse infrared pixel design for image sensors. Aspects of this disclosure include an image sensor including a pattern of pixels, the pattern of pixels including a set of visible light pixels and a set of infrared light pixels. The image sensor may be configured to generate visible light data and infrared light data based on received light. Aspects of the present disclosure also include a processor coupled to the image sensor. The processor may be configured to generate a configurable mask based on the pattern of pixels of the image sensor, and where values of the configurable mask correspond to pixel locations of the image sensor.

Abstract: A stand for a surgical microscope includes a digiscope and an imaging unit which are interconnected and mounted on an arm of the stand at a joint rotatably about an axis of rotation. The digiscope and the imaging unit are arranged on a bridge such that a fixed spatial relationship, in particular a distance larger than zero between the digiscope and the imaging unit during a relative movement between the digiscope and the patient is maintained. A method for configuring a stand with a bridge includes determining distances between eyes of a surgeon and the imaging unit, between the surgeon and an operating field, between the receptacle of the digiscope and the operating field, and between the imaging unit and the receptacle of the digiscope, and determining a length of the bridge to optimally set a distance from the surgeon to the patient and the imaging unit for the surgeon.

Abstract: A vehicular vision system includes a camera at a side of a vehicle and having a field of view exterior of the vehicle. With the vehicle parked, the system processes via an image processor image data captured by the camera to detect an object present in a detection zone at least partially along the side of the vehicle. With the vehicle parked, the system tracks the detected object to determine movement of the object relative to the parked vehicle. Responsive to tracking the detected object, the system is operable to determine that the object is in a danger zone at a side door of the parked vehicle that includes a sweep area that the side door swings through when opening. With the side door closed, and at least in part responsive to determination that the object is in the danger zone, the system limits opening of the side door.

Abstract: The present disclosure relates to methods and devices for motion estimation which may include a GPU. In one aspect, the GPU may generate at least one first motion vector in a first subset of a frame, the first motion vector providing a first motion estimation for image data in the first subset of the frame. The GPU may also perturb the image data. Also, the GPU may generate at least one second motion vector based on the perturbed image data, the second motion vector providing a second motion estimation for the image data. Moreover, the GPU may compare the first motion vector and the second motion vector. Further, the GPU may determine at least one third motion vector for the motion estimation of the image data based on the comparison between the first motion vector and the second motion vector.

Abstract: A camera apparatus, e.g., a stereoscopic camera apparatus, includes a dual element mounting plate, a pair of individual lens mounts, and a pair of sensor holders, each sensor holder holding an image sensor. The lens mounts and sensor holders are secured to the dual element mounting plate. Multiple dual element mounting plates corresponding to camera pairs may be secured to a base plate. Various features facilitate achieving and maintaining alignment between a lens and a corresponding image sensor, as well as between camera pairs and between sets of camera pairs.

Abstract: A medical safety-system for dynamic 3D healthcare environments, a medical examination system with motorized equipment, an image acquisition arrangement, and a method for providing safe movements in dynamic 3D healthcare environments. The medical safety-system for dynamic 3D healthcare environments includes a detection system, a processing unit, and an interface unit. The detection system includes at least one sensor arrangement to provide depth information of at least a part of an observed scene. The processing unit includes a correlation unit to assign the depth information and a generation unit to generate a 3D free space model to provide the 3D free space model.

Abstract: A virtual image processing method, an image processing system, and a storage medium used for realizing virtualization of a captured picture, the method includes the following steps: acquiring a reference position and a real-time position of a camera device; calculating a movement parameter of the real-time position relative to the reference position; virtualizing, according to the movement parameter, the position and the posture of the virtual camera device, and calculating a perspective parameter of a scene to be replaced with respect to the virtualized virtual camera device; encoding a virtual scene according to the perspective parameter; and using the encoded virtual scene to replace the scene to be replaced.

Abstract: According to various embodiments of the present invention, an electronic device can comprise: a light source configured to allow light, excluding a visible light band, to be incident on a designated pattern; a memory for storing designated pattern information; a camera configured to receive the light, which is incident from the light source and reflected by an external object; and a processor. The processor can be configured to: acquire a first image on an external object by using a camera, wherein the first image includes a pattern formed when the designated pattern is deformed by a curve of the surface of the external object; extract deformed pattern information from the first image by using the first image and the designated pattern information; and generate a second image from which the pattern deformed in the first image has been removed, by using the first image and the extracted deformed pattern information. Additional various embodiments are possible.

Abstract: Disclosed herein is an immersive video processing method. The immersive video processing method may include classifying a multiplicity of view videos into a base view and an additional view, generating a residual video for the additional view video classified as an additional view, packing a patch, which is generated based on the residual video, into an atlas video, and generating metadata for the patch.

Abstract: An imaging module of the invention includes: an imaging element; and a substrate positioned on a rear surface opposite to an imaging surface of the imaging element and provided to extend from the rear surface to a side opposite to the imaging surface. An electrode pad provided on the rear surface of the imaging element and a front end portion of an electrode pad provided on a main surface of the substrate at a position close to the imaging element are electrically connected via a conductive connecting material portion. A notch portion recessed from a distal end of the front end portion is formed at the front end portion of the electrode pad of the substrate.

Abstract: A distance measuring camera contains a first imaging system for obtaining a first image containing a first subject image, a second imaging system for obtaining a second image containing a second subject image, a size obtaining part for detecting a plurality of feature points of the first subject image in the first image and measure a distance between the feature points of the first subject image to obtain a size of the first subject image and utilizes an epipolar line to detect a plurality of feature points of the second subject image respectively corresponding to the plurality of feature points of the first subject image and measures a distance between the feature points of the second subject image to obtain a size of the second subject image and a distance calculating part for calculating a distance to the subject based an image magnification ratio between a magnification of the first subject image and a magnification of the first subject image and a magnification of the second subject image.

Abstract: A moving image coding device 10 includes: a cost determination unit 12 that determines, as a cost relating to a block to be coded, a minimum cost among appraisal costs relating to determined candidates for a motion vector; a storage unit 13 that stores, as coding information relating to the block to be coded, a candidate for the motion vector corresponding to the determined cost; and an update unit 14 that updates, to coding information relating to the block to be coded, the cost of which is smaller than the sum total of costs relating to blocks included in the block to be coded, the coding information relating to the included blocks and stored in the storage unit 13.

Abstract: This invention provides a single-camera vision system, typically for use in logistics applications, that allows for adjustment of the camera viewing angle to accommodate a wide range of object heights and associated widths moving relative to an imaged scene with constant magnification. The camera assembly employs an image sensor that is more particularly suited to such applications, with an aspect (height-to-width) ratio of approximately 1:4 to 1:8. The camera assembly includes a distance sensor to determine the distance to the top of each object. The camera assembly employs a zoom lens that can change at relatively high speed (e.g. <10 ms) to allow adjustment of the viewing angle from object to object as each one passes under the camera's field of view (FOV). Optics that allow the image to be resolved on the image sensor within the desired range of viewing angles are provided in the camera lens assembly.

Abstract: Disclosed are a display apparatus, an image providing apparatus, and methods of controlling the same, the display apparatus including: a display; and a processor configured to: decode an encoded video stream, decompress the video stream through a neural network including a plurality of channels and a plurality of layers with a parameter set based on learning, and perform image compensation determined based on learning about the decompression with respect to the video stream.

Abstract: An example method includes recording dark images on an image sensor on-board an orbital vehicle during flight, which include a first image recorded before the orbital vehicle is over a predefined location on the Earth and a second image recorded after the orbital vehicle is over the predefined location; and recording third and fourth images on the image sensor during flight based on illumination from a light source that is on-board, with the third image being recorded before the orbital vehicle is over the predefined location and the fourth image being recorded after the orbital vehicle is over the predefined location. A fifth image is recorded on the image sensor during flight while the predefined location on the Earth is visible to the image sensor. The fifth image is based on light from a ground-based calibration system. The light source is calibrated during flight based on the five images.

Abstract: A structured-light pattern for a structured-light system includes a base light pattern having a row of a plurality of sub-patterns extending in a first direction. Each sub-pattern is adjacent to at least one other sub-pattern. Each sub-pattern is different from each other sub-pattern. Each sub-pattern includes n dots in a sub-row and n dots in a sub-column in which n is an integer. Each dot is substantially a same size. Each sub-row extends in the first direction, and each sub-column extends in a second direction that is substantially orthogonal to the first direction. The dots that are aligned in a sub-column are offset in the second direction from the dots of the base light pattern that are aligned in an adjacent sub-column. In one embodiment, a size of each sub-pattern in the second direction is larger than a size of each sub-pattern in the first direction by a stretching factor.

Abstract: The present disclosure is directed to devices and methods for simultaneously sensing irradiance with multiple photo sensors having different orientations, and determining direct and scattered components of the irradiance. One such device includes an aerial vehicle and an irradiance sensing device. The irradiance sensing device includes a base structure mounted to the aerial vehicle, and the base structure including a plurality of surfaces. A plurality of photo sensors are arranged on respective surfaces of the base structure, with each photo sensor having a different orientation.