Abstract: Techniques and systems are provided for generating media content. For example, a server computer can detect a trigger from a device located at a site. The trigger is associated with an event at the site. The server computer can obtain media segments of media captured by a plurality of media capture devices located at the site. At least one of the media segments corresponds to the detected trigger. The server computer can determine one or more quality metrics of a media segment based on a first motion of an object captured in the media segment and/or a second motion of a media capture device used to capture the media segment. A subset of media segments can be selected from the obtained media segments based on quality metrics determined for the obtained media segments. A collection of media segments including the subset of media segments can then be generated.

Abstract: Provided is a projector configured to modulate light from a light source unit and project image light, the projector including: a current measurement unit that measures a current supplied from a power supply, the current including at least a current supplied to the light source unit of the projector; and a controller that compares a measured current value measured by the current measurement unit with limit value information determined by user input or based on data stored in advance, and controls power output to the light source unit in accordance with a comparison result.

Abstract: The image display apparatus of the present disclosure comprises: a display; an audio output device; and a signal processing device, in a simultaneous sound output mode, configured to output a first audio signal based on a first additional delay time to the audio output device and to output a second audio signal based on a second additional delay time, which is lower in level than the first additional delay time, to the sound output device, and in a single sound output mode of the audio output device, configured to output a third audio signal to the audio output device, wherein the first additional delay time is greater than or equal to an additional delay time of a third sound. Accordingly, sound synchronization may be performed in case in which the sound output device and the image display apparatus simultaneously output sound.

Abstract: The disclosure relates to a camera module for a vehicle comprising: a housing having a first end and a second end opposite to the first end; at least one camera disposed proximate to or on the first end of the housing; at least one cover glass disposed proximate to or on the second end of the housing facing the at least one camera; at least one actuator, preferably being a piezo actuator, disposed between the housing and the at least one cover glass; and at least one sealing element disposed between the at least one cover glass and the housing, wherein the at least one cover glass is configured to compressibly touch the at least one sealing element, and wherein the at least one sealing element is injection molded onto the housing by a 2K injection molding process.

Abstract: Eyewear having an image signal processor (ISP) dynamically operable in a camera pipeline for augmented reality (AR) and computer vision (CV) systems. Multi-purpose cameras are used for simultaneous image capture and CV on wearable AR devices. The cameras are coupled to a frame and configured to generate images, wherein the cameras and the ISP operate in a first AR mode and capture images having a first resolution suitable for use in AR, and are configured to operate in a second CV mode to provide the images having a second resolution suitable for use in CV. The first resolution in the AR mode is higher than the second resolution in the CV mode, and the cameras and the ISP consume less power in the second CV mode than the first AR mode. The cameras and the ISP save significant system power by operating in the low power mode CV mode.

Abstract: Technologies for source degradation and auto-tuning of cameras are disclosed. In one embodiment, a system includes a compute node connected to one or more cameras. The cameras can monitor an environment, such as a manufacturing process in a factory. The compute node may use image processing, such as a machine-learning-based algorithm, to monitor processes. A system integrator may adjust parameters of the camera and/or the algorithm, such as focus, gain, contrast, white balance, etc. The compute node can monitor the system integrator and learn how to adjust parameters in order to improve key performance indicators (KPIs) of the monitored process. In a production environment, the compute node may then automatically adjust parameters of the camera and/or analysis algorithm based on the actions of the system integrator in order to improve performance of the analysis algorithm.

Abstract: Systems and techniques are provided for simulating LiDAR sensors. An example method includes generating, within a simulation environment, a first Light Detection and Ranging (LiDAR) measurement that corresponds to a first virtual beam transmission from a first channel of a first LiDAR sensor; generating, within the simulation environment, a second LiDAR measurement that corresponds to a second virtual beam transmission from a second channel of the first LiDAR sensor, wherein the first virtual beam transmission and the second virtual beam transmission are directed to a virtual object in the simulation environment; determining a channel measurement variance between the first channel and the second channel; and adjusting at least one of the first LiDAR measurement and the second LiDAR measurement based on the channel measurement variance.

Abstract: Rotational, reciprocal scanning is used in a scanning LiDAR system. A laser is mounted to a platform. A first bar and a second bar couple the platform with a pivot mount. The pivot mount is coupled with a base. The platform is arranged to rotate about the pivot mount in an arc while the laser transmits light pulses into an environment.

Abstract: A semiconductor production apparatus system includes a substrate-holding hand; an image capturer for capturing an image of at least a component of a semiconductor production apparatus; and a controller for detecting an anomaly of the component of the semiconductor production apparatus based on the captured image captured by the image capturer.

Abstract: The present disclosure relates to a surveillance camera applicable to being used in a vehicle and easily taken and placed, including a camera assembly; the camera assembly includes a bottom shell, a control board arranged in the bottom shell, and a battery electrically connected to the control board; the control board is provided with a camera for monitoring; the camera assembly includes an outer shell; the outer shell and the bottom shell fix the battery and the control board inside the bottom shell. By use of a universal ball for connection, it is convenient to adjust a monitoring angle of the surveillance camera and to remove the surveillance camera. The camera assembly is provided with an infrared lamp and a photosensor, to facilitate monitoring in a dark environment.

Abstract: A vision device (11) for a motor vehicle adapted to capture images of the surrounding of the motor vehicle and includes alignment elements (21a-21c, 23a-23b) each adapted to cooperate with a corresponding alignment counter-element (42a-42c, 44a-44b) of a holding part (15) in order to align the vision device (11) relative to the holding part (15). Each alignment element (21a-21c, 23a-23b) has a planar surface (22, 24) adapted to abut against a planar surface (43, 45) of the corresponding alignment counter-element (42a-42c, 44a-44b).

Abstract: Endoscopic imaging systems are disclosed herein. In some embodiments, an endoscopic imaging system can include an endoscope having a distal tip with a distal face configured to face a scene, such as a portion of a body cavity of a patient. The endoscope can further include first cameras for capturing first image data of the scene, a projector for projecting a light pattern into the scene, and second cameras for capturing second image data of the scene including the light pattern. A processor can be communicatively coupled to the first and second cameras for receiving the first and second image data. The processor can process the first and second image data to generate an image of the scene at the perspective of a virtual camera, and can vary the perspective, the aperture, the focus plane, and/or another parameter of the virtual camera without requiring the endoscope to be physically moved.

Abstract: A fiber scanning projector includes a piezoelectric element and a scanning fiber passing through and mechanically coupled to the piezoelectric element. The scanning fiber emits light propagating along an optical path. The fiber scanning projector also includes a first polarization sensitive reflector disposed along and perpendicular to the optical path. The first polarization sensitive reflector includes an aperture and the scanning fiber passes through the aperture. The fiber scanning projector also includes a second polarization sensitive reflector disposed along and perpendicular to the optical path.

Abstract: A method for calibrating an endoscopic camera is described. The endoscopic camera includes an endoscope and a camera and the camera includes a camera head. The method includes receiving a lens descriptor associated with the endoscope, the lens descriptor including first calibration parameters indicating first characteristics of the endoscope independent of the endoscopic camera, with the endoscope installed in the endoscopic camera, acquiring an image frame using the endoscopic camera, detecting second characteristics of the image frame acquired using the endoscopic camera, calculating second calibration parameters using the lens descriptor and the second characteristics captured for the image frame, the second calibration parameters being different from the first calibration parameters, and at least one of storing and outputting the second calibration parameters to be used to operate the endoscopic camera.

Abstract: An extended reality (XR) projection system, a notebook computer and a projection method using the same are provided. The projection method includes the following steps. An image in front of a pair of XR glasses is captured by the pair of the XR glasses. The pair of the XR glasses searches the image in front of the pair of the XR glasses for an identification pattern on a curtain. The pair of the XR glasses transmits the identification pattern to a notebook computer. The notebook computer identifies an identification code of the curtain according to the identification pattern. The notebook computer transmits a frame corresponding to the identification code to the pair of the XR glasses. The pair of the XR glasses tracks the identification pattern to project the frame on the curtain.

Abstract: A light source of a photographing environment in which the electronic device is located is a flicker light source. The method includes: running a camera application in the electronic device; displaying a first image, where first exposure time is less than first duration, and the first image includes banding and/or a color cast image area; detecting a first operation; obtaining a second image in response to the first operation, where second exposure time is an integer multiple of the first duration; obtaining a color transformation matrix and/or a brightness parameter based on the first image and the second image; performing first image processing on the first image based on the color transformation matrix and/or the brightness parameter, to obtain a third image, where the third image is an image obtained by removing the banding and/or the color cast image area; and displaying or saving the third image.

Abstract: A method for automatically determining whether to perform denoising includes the following steps: S1: scanning a sample using a light field microscopy system to obtain a light field microscopic image containing 4-dimensional information, where the sample is a sample to be 3D reconstructed; S2: rearranging the light field microscopic image to obtain a multi-view rearranged image; S3: calculating a cleanliness score of the multi-view rearranged image; and determining whether to perform denoising process on the multi-view rearranged image, based on the cleanliness score of the multi-view rearranged image.

Abstract: A control device includes one or more processors including hardware, the one or more processors being configured to: generate a white light image based on a first image signal captured as a result of irradiating a subject with a white light; generate a narrow-band light image based on a second image signal captured as a result of irradiating the subject with a narrow-band light; control a light intensity of the white light to a first value which is determine according to brightness of the white light image and according to a first ratio; and control a light intensity of the narrow-band light to a second value which is determine according to brightness of the narrow-band light image and according to a second ratio that is different than the first ratio.

Abstract: A driving assistance apparatus has: an acquiring section that acquires an infrared image capturing an image capturing area including a driver's seat of a vehicle; a determining section that determines whether a flared highlight has occurred in the infrared image in a case where it is not possible to recognize the driver in the infrared image, on the basis of whether a pixel value of a pixel of a portion capturing an image of an area which is in the image capturing area in the infrared image and is hit by sunlight is equal to or greater than a predetermined value; and a setting section that makes waiting time longer than reference time, the waiting time being a time point at which a warning is given in a case where it is determined that the flared highlight has occurred in the infrared image.

Abstract: Methods and systems are described herein for optimizing how recorded data frames are processed and stored when a recording device (e.g., mounted upon an uncrewed vehicle) is within a non-transmit zone. A determination may be made that a non-transmit zone has been entered, and the current network conditions may be evaluated, including available bandwidth and/or latency for each radio. The data frames may be split into queues associated with the radios on board the vehicle based on the frame size and network conditions. This mechanism may ensure efficient use storage space in preparation for data transmission.