Abstract: A sensor system includes: a radar system configured to emit a radar beam and receive reflected radar signals from in a field of view of the radar system; a camera system including one or more cameras, at least one camera including a linear polarization filter in an optical axis of the camera, a field of view of the camera system overlapping the field of view of the radar system; and a processing system including a processor and memory, the memory storing instructions that, when executed by the processor, cause the processor to: receive radar data based on the reflected radar signals captured by the radar system; receive polarization raw frames captured by the camera system; and compute a track of a target in the field of view of the camera system and the field of view of the radar system based on the radar data and the polarization raw frames.

Abstract: A camera apparatus and an electronic device including the same are disclosed. The camera apparatus according to the present disclosure includes: a light source; a lens module configured to output light from the light source to the outside; an actuator configured to move the light source or the lens module; and an image sensor configured to convert external light into an electrical signal. Accordingly, it is possible to implement a high-quality 3D volume by dynamically moving output light.

Abstract: A positioning method includes obtaining an estimated extrinsic parameter of a camera and an intrinsic parameter of the camera, where the estimated extrinsic parameter of the camera is obtained based on world coordinates of a plurality of estimation points in a shooting region of the camera, image coordinates of the plurality of estimation points, and the intrinsic parameter of the camera; obtaining image coordinates of a target in an image shot by the camera; and obtaining world coordinates of the target based on the estimated extrinsic parameter of the camera, the intrinsic parameter of the camera, and the image coordinates of the target.

Abstract: A method for identifying adversarial attacks on an image based detection system for automated driving includes providing a reference signal and a potentially manipulated signal. The method also includes calculating a plurality of metrics which quantify differences between the signals in different ways. The method further includes creating a multi-dimensional feature space based on the calculated metrics and classifying the type of attack based on the calculated metrics. The class of the adversarial attack may then be output.

Abstract: A system includes a processor, a light source controlled by the processor and configured to emit a light, and an event based vision sensor controlled by the processor. The sensor includes a plurality of pixels. At least one of the plurality of pixels includes a photosensor configured to detect incident light and first circuitry configured to output a first signal based on an output from the photosensor. The first signal indicates a change of amount of incident light. The sensor includes a comparator configured to output a comparison result based on the first signal and at least one of a first reference voltage and a second reference voltage. The processor is configured to apply one of the first reference voltage and the second reference voltage to the comparator selectively based on an operation of the light source.

Abstract: An image sensor array includes a substrate and a plurality of pixels. Each pixel includes a single photon avalanche detector (SPAD), a quench device coupled to a respective SPAD and configured to quench an avalanche current, and time measurement circuitry configured to measure a time-of-flight of a photon. The SPAD has a trench coupled to the substrate and having a lattice mismatch with the substrate, and a substantially defect-free region coupled to the trench and configured to generate the avalanche current when the photon is detected in the defect-free region, wherein the trench and the defect-free region form an electrode. An imaging system includes an infrared laser configured to provide a pulse of light, and the image sensor array configured to receive the pulse from the infrared laser.

Abstract: [Problem] To provide a signal generation apparatus that is used in a ToF camera system especially adopting an indirect system and can suppress occurrence of erroneous distance measurement caused by distance measurement of a same target by a plurality of cameras with a simple configuration. [Solving means] There is provided a signal generation apparatus including a first pulse generator configured to generate a pulse to be supplied to a light source that irradiates light upon a distance measurement target, a second pulse generator configured to generate a pulse to be supplied to a pixel that receives the light reflected by the distance measurement target, and a signal generation section configured to generate a pseudo-random signal for inverting a phase of signals to be generated by the first pulse generator and the second pulse generator.

Abstract: One example provides a method of operating a time-of-flight camera system comprising an illumination source and an image sensor. The method comprises operating the illumination source and the image sensor to control a plurality of integration cycles and a plurality of readout cycles. In each integration cycle, the method comprises performing a plurality of pulse width modulated (PWM) illumination cycles where each PWM illumination cycle is separated from one or more adjacent PWM illumination cycles by a non-illumination cycle. For each PWM illumination cycle, the method comprises directing photocharge to in-pixel memory for each pixel that is performing image integration and for each non-illumination cycle conducting photocharge away from the in-pixel memory for each pixel that is performing image integration. The readout cycle comprises, for each pixel that performed image integration, reading a charge stored in the in-pixel memory after the integration cycle.

Abstract: Examples relate to a method, an apparatus and a computer program for determining distance information based on Time of Flight (ToF) sensor data. The method includes obtaining the ToF sensor data, determining one or more saturated regions within the ToF sensor data, determining distance information for one or more boundary regions located adjacent to the one or more saturated regions based on the ToF sensor data, and determining distance information for at least a part of the one or more saturated regions based on the distance information of the one or more boundary regions.

Abstract: A method for compensating stray light caused by an object in a scene that is sensed by a time-of-flight camera is provided. The method includes receiving an image of the scene from the time-of-flight camera. Further, the method includes controlling the time-of-flight camera to capture a reference image of the scene using a code modulated signal for illumination such that a measurement range of the time-of-flight camera is limited to a distance range around the object. The method additionally includes modifying the image of the scene or an image derived therefrom using the reference image to obtain a compensated image of the scene. The method includes outputting the compensated image.

Abstract: In one embodiment, a computing system may transmit, using one or more light emitters, light beams of different wavelengths simultaneously into a surrounding environment. The system may determine a characteristic of the surrounding environment based on reflections of the light beams. In response to a determinization that the characteristic of the surrounding environment satisfies a criterion, the system may configure the one or more light emitters to transmit light beams of different wavelengths sequentially into the surrounding environment for measuring distances to one or more objects in the surrounding environment.

Abstract: Various methods are provided for training and subsequently utilizing a convolutional neural network (CNN) to detect small pedestrians (e.g., pedestrians located away a large distance). One example method may comprise performing a first training stage in which a first CNN is trained to detect objects of a first size, the first CNN trained using a first set of images comprised of objects of the first size, and configured to output a first set of parameters, performing a second training stage in which a second CNN is trained using a second set of images, the second set of images comprising objects of a second size, and the first CNN is initialized with the first set of parameters and is re-trained using the second set of images, and determining parameters of the first CNN by minimizing error between the first CNN and the second CNN.

Abstract: An input interface is configured to receive at least one sensor signal corresponding to information of the exterior of the vehicle sensed by at least one sensor. A processor is configured to, based on the sensor signal, generate: a first data corresponding to first information sensed in a first area; and a second data corresponding to second information sensed in a second area located outside the first area. An output interface is configured to output the first data and the second data independently from one another.

Abstract: A method for depth image acquisition, a device (10) for depth image acquisition, and an electronic device (100) are provided. The method includes the following. An image of a field is obtained to determine a region of interest (ROI) in the image of the field. A current distance to the ROI is obtained. A time-of-flight depth camera (20) is controlled to obtain a current depth image of the field in response to the current distance being greater than a first distance. Both a dual camera (30) and the time-of-flight depth camera (20) are controlled to obtain the current depth image of the field in response to the current distance being not greater than the first distance.

Abstract: Methods and systems are described which use a sensing system in cooperation with a wireless communication system. Coordinate information (which may be from the sensing system, from an electronic device, or from a network-side device) and signal-related information (which may be from the wireless system) are associated with each other. The associated information may be used for wireless communication management, such as beam management operations, among others.

Abstract: The present disclosure relates to a tracking system for tracking the position and/or orientation of an object in an environment, the tracking system including: at least one camera mounted to the object; a plurality of spaced apart targets, at least some of said targets viewable by the at least one camera; and, one or more electronic processing devices configured to: determine target position data indicative of the relative spatial position of the targets; receive image data indicative of an image from the at least one camera, said image including at least some of the targets; process the image data to: identify one or more targets in the image; determine pixel array coordinates corresponding to a position of the one or more targets in the image; and, use the processed image data to determine the position and/or orientation of the object by triangulation.

Abstract: A distance image sensor includes a light source that generates pulsed light, a light source control means for controlling the light source, a pixel circuit including a photoelectric conversion region, charge readout regions, a charge discharge region, and control electrodes, a charge transfer control means for sequentially applying a control pulse to the control electrodes, and a distance calculation means for reading voltages of the charge readout regions as detection signals and repeatedly calculating a distance on the basis of the detection signals, and the charge transfer control means sets timings of the control pulses so that delay times of the control pulses with respect to a generation timing of the pulsed light is shifted to a time differing between the four types of subframe periods in one frame period.

Abstract: The present disclosure relates to a method of laser safety verification for a depth map sensor, comprising illuminating, during a first illumination phase, using a laser illumination system, a first cluster of one or more first pixels of a pixel array of the depth map sensor, while not illuminating a second cluster, different from the first cluster, of one or more second pixels of the pixel array of the depth map sensor; and detecting, during the first illumination phase, a level of illumination of the second cluster.

Abstract: A camera module which includes an image sensor, a three-dimensional (3D) sensor, a pre-processor, and an actuator controller. The pre-processor may be suitable for receiving image information from the image sensor, generating an auto focusing control signal based on the image information, and providing an auto focusing control signal to the actuator controller. The actuator controller may be suitable for receiving the auto focusing control signal, generating an actuator driving signal based on the auto focusing control signal, and providing the actuator driving signal to the 3D sensor. The 3D sensor may be suitable for adjusting a field of view (FOV) based on the actuator driving signal.

Abstract: A photodetection apparatus according to one embodiment has a photodetection element, first reset circuitry configured to select whether to set on-resistance between a first voltage node and a terminal of the photodetection element to a first value, second reset circuitry configured to select whether to set the on-resistance to a second value smaller than the first value, and control circuitry configured to set the on-resistance to the first value by the first reset circuitry after the photodetection element detects light, and set the on-resistance to the second value by the second reset circuitry after the first reset circuitry select to set the on-resistance to the first value.

Abstract: Systems and methods presented herein include an anti-collision and motion monitoring system includes one or more light detection and ranging (LiDAR) systems configured to detect locations of one or more objects in an environment. The anti-collision and motion monitoring system also includes one or more camera systems configured to capture images of the one or more objects in the environment that are detected by the one or more LiDAR systems.

Abstract: A velocity measuring device includes an event sensor, a ranging sensor and a controller. The event sensor could detect a first image frame of an object along a plane at a first time point and detect a second image frame of the object at a second time point. The ranging sensor could detect a first depth of the object along a depth direction at the first time point, wherein the depth direction is substantially perpendicular to the plane and detect a second depth of the object along the depth direction at the second time point. The controller could obtain first-dimensional velocity and a second-dimensional velocity along the plane according to the first image frame, the second image frame, the first depth and the second depth, and obtain a third-dimensional velocity along the depth direction according to the first depth or the second depth.

Abstract: Embodiments described herein provide examples of a real-time visual object tracking system. In one aspect, an unmanned aerial vehicle (UAV) capable of performing real-time visual tracking of a moving object includes: a processor; a memory coupled to the processor; and a camera to capture a video of the moving object. This UAV additionally includes a visual tracking module to: receive a first video image and a first location of the object; receive a second video image following the first video image; place a first search window in the first video image and a second search window in the second video image centered on a second location in the second video image having the same coordinates as the first location; compute a correlation between an image patch within the first search window and an image patch within the second search window; and determine an updated location of the object in the second video image.

Abstract: A method and an arrangement for capturing a mark arrangement including an optical mark arranged on an object, the method including capturing images of the mark arrangement together with points in time, determining first evaluation information by evaluating images captured with a first capturing device and further evaluation information by evaluating images captured with a further capturing device, each of the first and further evaluation information relating to respective points in time at which the images were captured, determining a value of a movement variable describing a relative movement between the object and the capturing devices at a predetermined point in time based on the evaluation information determined at the predetermined point in time; and determining the evaluation information of the capturing devices at the predetermined point in time based on images captured at other points in time when no image was captured at the predetermined point in time.

Abstract: An apparatus includes at least one detector configured to receive return light from an object within a detector field of view the light generated by a light source. The detector includes first and second photosensitive regions configured to receive the return light from the light source. At least one non-photosensitive region is included, and the first and second photosensitive regions are separated by the at least one non-photosensitive region. The at least one non-photosensitive region is associated with one of the first or second photosensitive regions.

Abstract: A semiconductor device may include an array of single-photon avalanche diode pixels. The single-photon avalanche diode (SPAD) pixels may include a SPAD coupled to a supply voltage terminal via first and second reset paths. The first reset path may be a fast reset path that provides the SPAD with a short recovery time. The second reset path may be a slower reset path that provides the SPAD with a longer recovery time, but is used to ensure the SPAD is quenched even when the quench resistance associated with the first reset path is low. Logic circuitry may selectively activate the first or the second resets to quench and reset the SPAD. A SPAD pixel may also include one or more switches that keep nodes in the SPAD pixel at a constant voltage when the SPAD pixel is inactive.

Abstract: An imaging apparatus includes a circuitry configured to perform depth analysis of a scene by time-of-flight imaging and to perform motion analysis in the scene by structured light imaging, wherein identical sensor data is used for both, the depth analysis and the motion analysis.

Abstract: Methods, systems, and techniques for classifying and/or detecting objects using visible and invisible light images. A visible light image and an invisible light image are received at a convolutional neural network (CNN). The visible light image depicts a region-of-interest imaged using visible light. The invisible light image depicts at least a portion of the region-of-interest imaged using invisible light, and at least one of the images depicts an object-of-interest within the portion of the region-of-interest shared between the images. The CNN then classifies and/or detects the object-of-interest using the images. The CNN may be trained to perform this classification and/or detection using pairs of visible and invisible light training images.

Abstract: A method for estimating the speed of movement of a first video camera when it captures a current image of a three-dimensional scene, includes storing a reference image corresponding to an image of the same scene captured by a second video camera in a different pose, the reference image including pixels. The method also includes storing the current image, the current image including pixels containing the measurement of a physical quantity measured by that pixel, that physical quantity being the same as the physical quantity measured by the pixels of the reference image. The method further includes storing for each pixel of the reference image or of the current image the measurement of a depth that separates that pixel from the point of the scene photographed by that pixel, estimating the pose of the first camera, and estimating the speed of movement of the first camera.

Abstract: An image forming apparatus includes a job executor that executes a job, an image former that performs an image forming process on a basis of the job, an acquiror that acquires image data captured, and a detector that analyzes the image data to detect an event. The detector detects the event when the job executor is in a standby state.

Abstract: A calibration method for a camera-based measuring device comprises positioning a calibration object simulating an anterior region of the eye on a holder arranged movably in a first direction relative to a camera of the measuring device within a view field of the camera. The first direction is toward and away from the camera substantially along a camera axis. A motorized drive unit, in drive connection with the holder, is firstly controlled to drive the holder, with the calibration object positioned thereon in the camera view field, relative to the camera along the first direction at least once past a position of maximum definition of an image of the calibration object taken by the camera. A ratio between an actual size and an imaging size of the calibration object is determined on the basis of a camera image of the calibration object taken at the position of maximum definition.

Abstract: In general, the subject matter described in this disclosure can be embodied in methods, systems, and program products for detecting motion in images. A computing system receives first and second images that were captured by a camera. The computing system generates, using the images, a mathematical transformation that indicates movement of the camera from the first image to the second image. The computing system generates, using the first image and the mathematical transformation, a modified version of the first image that presents the scene that was captured by the first image from a position of the camera when the second image was captured. The computing system determines a portion of the first image or second image at which a position of an object in the scene moved, by comparing the modified version of the first image to the second image.

Abstract: A system and method for determining a position of a target. The method includes determining a first direction to the target from a first observing position, estimating a first approximate position of the target based on the first direction and the first observing position, determining a second direction to the target from a second observing position, and estimating a second approximate position of the target based on the second direction and the second observing position. The method further includes determining a first approximate intersection point of (i) a first finite length line between the first observing position and the first approximate position of the target, and (ii) a second finite length line between the second observing position and the second approximate position of the target.

Abstract: Implementations are described herein are directed to reconciling disparate orientations of multiple vision sensors deployed on a mobile robot (or other mobile vehicle) by altering orientations of the vision sensors or digital images they generate. In various implementations, this reconciliation may be performed with little or no ground truth knowledge of movement of the robot. Techniques described herein also avoid the use of visual indicia of known dimensions and/or other conventional tools for determining vision sensor orientations. Instead, techniques described herein allow vision sensor orientations to be determined and/or reconciled using less resources, and are more scalable than conventional techniques.

Abstract: A method for determining alignment of cameras at a vehicle includes mounting first and second cameras at a vehicle and providing an image processor at the vehicle. While the vehicle is moving along the road, first image data captured via the first camera is processed to determine movement of a road feature and second image data captured by the second camera is processed to determine movement of the road feature when the road feature is present in the second image data. The determined movement of the road feature in first image data is compared to the determined movement of the road feature in second image data, and an offset of the second camera relative to the first camera is determined, with the offset caused by a rotational or translational change in position of the first or second camera relative to the other.

Abstract: A method may include receiving a source video frame captured using a wide angle lens, deriving a characteristic of a target video frame from the source video frame, generating a transitional video frame using the source video frame and the target video frame, and transmitting the transitional video frame to an endpoint.

Abstract: A user control apparatus has a laser emitter that emits a laser beam in a real-world environment. Further, the user control apparatus has an optical element that receives the laser beam and generates a plurality of laser beams such that a starting point and a plurality of endpoints, each corresponding to one of the plurality of laser beams, form a laser frustum. In addition, the user control apparatus has an image capture device that captures an image of a shape of the laser frustum based on a reflection of the plurality of laser beams from an object in the real-world environment so that a spatial position of the object in the real-world environment is determined for an augmented reality or virtual reality user experience.

Abstract: Disclosed herein are an ultrasound imaging apparatus and a control method thereof. The ultrasound imaging apparatus includes: a display unit configured to display an ultrasound image and an external image such that a first reference line overlaps the ultrasound image and a second reference line overlaps the external image; an ultrasound probe configured to receive a command for moving or rotating at least one image of the ultrasound image and the external image based on a predetermined reference coordinate system; and a controller configured to determine whether the ultrasound image matches with the external image according to manipulation of the ultrasound probe, and to control the display unit to synthesize the ultrasound image with the external image and to display the ultrasound image and the external image, if determining that the ultrasound image matches with the external image.

Abstract: Techniques of reducing or eliminating artifact pixels in high dynamic range (HDR) imaging are described. One embodiment includes obtaining a first image of a scene at a first time with first exposure settings and obtaining a second image of the scene at a second time with second exposure settings that differ from the first exposure settings. The obtained images may be downsampled. The images may be compared to each other to assist with determining a number of potential artifact pixels in the scene. Depending on a relationship between the number of potential artifact pixels and a threshold value, the first image or second image may be selected as a reference image for registering the images with each other. A type of registration performed between the images may depend on which of the two images is the selected reference image. The registered images may be used to generate an HDR image.

Abstract: An information processing apparatus includes an image obtaining unit configured to obtain an image obtained while imaging is performed by pointing an imaging unit towards a target surface, a distance obtaining unit configured to obtain, with regard to a plurality of areas constituting the image, information equivalent to distances from a position corresponding to a reference to surfaces to be imaged in the respective areas, and a recognition unit configured to use the information obtained by the distance obtaining unit with regard to a first area where a predetermined region of an object is imaged in one of the images obtained by the image obtaining unit and the information obtained by the distance obtaining unit with regard to a second area that is a part of the image and in contact with a surrounding of the first area to recognize an input state to the target surface by the object.

Abstract: A digital image depicting a digital representation of a scene is captured by an image sensor of a vehicle. An identification system recognizes a real-world object from the digital image as a target object based on derived image characteristics and identifies object information about the target object based on the recognition. The identification provides the object information to the vehicle data system of the vehicle so that the vehicle data system can execute a control function of the vehicle based on the received object information.

Abstract: A method of calibrating a structure is provided. The method includes securing a first end of a tether to a device at a fixed location on an external surface of the structure, attaching an unmanned aerial vehicle to the second end of the tether, moving the unmanned aerial vehicle in a trajectory around the structure while tethered to the fixed device, scanning the external surface of the structure over a course of the trajectory using the unmanned aerial vehicle to obtain a mapping of the external surface of the structure, determining a position of the unmanned aerial vehicle with respect to the fixed device; and calibrating the structure based on i) the determined position of the unmanned aerial vehicle with respect to the fixed device, and ii) the mapping of external surface of the structure.

Abstract: Systems and methods are described for a network video camera device. Specifically, various techniques and systems are provided for embodiments of a network video camera with a blocking mechanism for privacy and control of the blocking mechanism. Embodiments of the present invention include a network video capture device. The network video capture device comprises a lens connected to a housing; a blocking mechanism, wherein the a blocking mechanism is configured to selectively block the lens from capturing video images, and wherein the blocking mechanism includes a physical body; an indication device, wherein the indication device is configured to provide visible feedback that the lens is blocked; and a circuit board having a data processor, a wireless transceiver, and a memory configured to store a customizable setting associated with the blocking mechanism.

Abstract: A parallax calculating apparatus is provided with: a processor configured to perform, on each of a plurality of types of block shapes that are different from each other, (i) a parallax calculation process, (ii) a block group setting process, and (iii) a cost calculation process, by using a pair of images photographed by a stereo camera; and a selector configured to perform, on each of a plurality of pixels that constitute the image, a parallax selection process of setting a parallax value of a block in which a cost associated by the cost calculation process is minimum, as a parallax of a target pixel in which the parallax is to be obtained, from among a plurality of blocks, each of which includes the target pixel and which respectively correspond to the plurality of types of block shapes.

Abstract: An optical inertial measurement method for determining a 6DOF pose in respect of a moving platform, the method comprising providing, in respect of said moving platform, a camera unit (10) comprised of at least three monocular cameras (14, 16, 18) connected rigidly together and configured such that their fields of view do not overlap and cover motion of said platform in each of three principal, substantially orthogonal axes; receiving video outputs from each of said cameras; determining individual point correspondences from said video outputs, and estimating therefrom, for each camera, a transform that includes translation values representative of direction of translation in the x and y axes, rotation about the optical axis and a scale factor, each transform being expressed with respect to a local 3D coordinate system associated with a respective camera; and mapping said translation values in the x and y axes to a global 3D coordinate system, having its origin defined by a point between said cameras, and multi

Abstract: Provided is a position detection method using a first imaging unit and a second imaging unit that each capture an image of an object. The detection method may include: acquiring a first captured image with use of the first imaging unit; acquiring a second captured image with use of the second imaging unit; defining a position vector of the object based on the first captured image; calculating a first direction vector directed from the second imaging unit to the object with use of the defined position vector; calculating a second direction vector directed from the second imaging unit to the object based on the second captured image; and calculating a position of the object based on the first direction vector and the second direction vector.

Abstract: A method of calibrating a structure is provided. The method includes securing a first end of a tether to a device at a fixed location on an external surface of the structure, attaching an unmanned aerial vehicle to the second end of the tether, moving the unmanned aerial vehicle in a trajectory around the structure while tethered to the fixed device, scanning the external surface of the structure over a course of the trajectory using the unmanned aerial vehicle to obtain a mapping of the external surface of the structure, determining a position of the unmanned aerial vehicle with respect to the fixed device; and calibrating the structure based on i) the determined position of the unmanned aerial vehicle with respect to the fixed device, and ii) the mapping of external surface of the structure.

Abstract: Systems and methods are described for a network video camera device. Specifically, various techniques and systems are provided for embodiments of a network video camera with a blocking mechanism for privacy and control of the blocking mechanism. Embodiments of the present invention include a network video capture device. The network video capture device comprises a lens connected to a housing; a blocking mechanism, wherein the a blocking mechanism is configured to selectively block the lens from capturing video images, and wherein the blocking mechanism includes a physical body; an indication device, wherein the indication device is configured to provide visible feedback that the lens is blocked; and a circuit board having a data processor, a wireless transceiver, and a memory configured to store a customizable setting associated with the blocking mechanism.

Abstract: A computer-implemented method, a computer program product, and a system for adapting a model for estimating a concentration of particulate matter (PM) in the atmosphere includes obtaining image data, humidity data and actual PM concentration data. Visibility is determined from the obtained image data. An estimation model for estimating PM concentration is adapted, based on the determined visibility, the obtained humidity data, and the obtained actual PM concentration data.

Abstract: A method for generating an adapted slice image from a focal stack of refocused images using an all-in-focus image derived from the focal stack comprises: selecting a slice image in the focal stack; selecting at least one object in the all-in-focus image to be focused in the adapted slice image; and generating the adapted slice image by combining the selected at least one object in the all-in-focus image onto the selected slice image.