Abstract: A solution is disclosed for conveniently capturing video highlights in a sports event by tracking head rotation movement of a user and synchronizing rotations of a video capturing device (e.g., the user's mobile phone) on a rotary station with the head rotation movement of the user. The user wears a rotation tracking device, which tracks the head rotation movement of the user in connection with watching an event. The head rotation data from the user's head rotation movement is filtered to generate filtered head rotation data, which excludes noise motions in the head rotation data. Corresponding rotary control data is generated based on the filtered head rotation data. The rotary control data is used to instruct a rotary system to rotate synchronously with head rotations of the user when a video capturing device mounted on the rotary system captures videos of the sports event.

Abstract: A method and system for locating a plurality of targets are provided, wherein all targets to be located move within a spatial area. The method comprises: providing an infrared light source on each of the targets to be located; according to a preset sampling frequency, controlling the infrared light source on each of the targets to be located to be turned on and off sequentially; according to the preset sampling frequency, obtaining infrared gray scale images of the space where the targets to be located are located; and locating one target to be located in each of the obtained infrared gray scale images. By the infrared light source locating, ambient interference is highly avoided, and the accuracy of the locating is improved.

Abstract: A method for determining the risk of a person falling is provided. The method includes acquiring depth image data that comprises a plurality of frames that depict a person walking through a home, and extracting a foreground object from the depth image data. The method additionally includes generating a three-dimensional data object based on the foreground object, and identifying a walking sequence from the three-dimensional data object. The method further includes generating one or more gait parameters from the identified walking sequence, and comparing the one or more gait parameters against a standard clinical measure of the one or more gait parameters to determine a level of risk at which the person is of falling.

Abstract: A method includes receiving a first image and a second image from an X-ray imaging device and determining a template window in the first image and a plurality of search windows in the second image. The method further includes generating a template vector corresponding to the template window and a plurality of search vectors corresponding to the plurality of search windows. The method also includes calculating a plurality of similarity scores based on the template vector and the plurality of search vectors. Additionally, the method includes determining a matching window from the plurality of search windows based on the plurality of similarity scores. Finally, the method includes generating a final image using the first image and the second image based on the template window and the matching window.

Abstract: Video processing for motor task analysis is described. In various examples, a video of at least part of a person or animal carrying out a motor task, such as placing the forefinger on the nose, is input to a trained machine learning system to classify the motor task into one of a plurality of classes. In an example, motion descriptors such as optical flow are computed from pairs of frames of the video and the motion descriptors are input to the machine learning system. For example, during training the machine learning system identifies time-dependent and/or location-dependent acceleration or velocity features which discriminate between the classes of the motor task. In examples, the trained machine learning system computes, from the motion descriptors, the location dependent acceleration or velocity features which it has learned as being good discriminators. In various examples, a feature is computed using sub-volumes of the video.

Abstract: A surveillance system includes an image sensing device for capturing images of a plurality of moving objects at a plurality of different locations in a field of view of the image sensing device. The system also includes a user interactive processor for performing a human-distance calibration for a given location and position of the image sensing device. The system further includes a processor for detecting a human presence among the plurality of moving objects based on the human-distance calibration.

Abstract: An image recognition system for detecting and tracking at least an image portion associated with a predefined object from a moving picture is configured to be able to perform: an object detection processing step of detecting the object; a tracking point specification processing step of specifying a predetermined point as a tracking point; a tracking target recognition processing step of recognizing an actual tracking target based on the tracking point; a tracking processing step of tracking the tracking target; and a determination processing step of determining the type of the tracking target's behavior. The tracking point specification processing step and the determination processing step are implemented by software, while the object detection processing step, the tracking target recognition processing step, and the tracking processing step are implemented by hardware.

Abstract: A method and system for displaying of a holographic image of an object in a predefined area. A positioning unit is configured for detecting positions of at least one viewer within the predefined area, a sensor is configured for detecting the environmental conditions within the predefined area, a processor is configured for collecting data including detected positions of viewers and detected environmental condition and calculating a location for displaying holographic image based on the collected data.

Abstract: A method and an electronic device are provided for image processing. The electronic device displays a composition selection guide having at least one composition item corresponding to at least one object in an image, on at least one display connected to the electronic device. An input is received relating to a selection of a composition item from the at least one composition item of the composition selection guide. At least one composition image corresponding to the composition item is acquired. The at least one composition image is displayed on the at least one display.

Abstract: A method capable of performing an automatic focus function upon a specific movable object in a real-time manner, the method being applicable to a photographic apparatus with the automatic focus function, includes: capturing real-time image within a field of view (FOV) of a lens; comparing images of a plurality of image areas of the real-time image with a feature image of the specific movable object to identify an image area corresponding to the feature image of the specific movable object; and, performing automatic focus on the identified image area.

Abstract: The disclosure relates to technology for providing determined future fields of view (FoVs) of a 360 degree video stream in a network having multiple video streams corresponding to multiple FoVs. FoV interest messages including requests for FoVs at time instants of the video stream are collected from viewers of the stream. A sequence of popular FoVs is created according to the messages, each representing a frequently requested FoV at a distinctive time instant. FoV transitions are created according to the FoV interest messages, each FoV transition including a current FoV a time instant and a next FoV of a next time instant, indicating a likely next FoV to be subsequent requested. Future FoVs of future time instants are determined for a user viewing the video stream with a history of requested FoVs of past time instants, based on the history of requested FoVs, the sequence and the transitions.

Abstract: An information processing apparatus includes an eyeball position estimation unit that estimates an eyeball position of a user in a pupil-corneal reflection method on the basis of a captured image including an eye of the user captured when the eye of the user looking at a display surface is irradiated with light; a discrepancy estimation unit that estimates an amount of discrepancy between an eyeball position on the display surface and a visual field center of the display surface, the eyeball position being identified on the basis of the eyeball position; and an operation instruction unit that issues an operation instruction to adjust a position of a device including the display surface on the basis of the estimated amount of discrepancy.

Abstract: The present disclosure relates to a method and device for providing object-finding information. The method is performed in an electronic device for finding an object and includes: when detecting that a preset loss event occurs, detecting device-relevant information of a surrounding device located around the electronic device; and sending the detected device-relevant information, as object-finding information, to a preset device.

Abstract: The present invention relates to a vehicle driving assistance device and a vehicle having same. The vehicle driving assistance device according to an embodiment of the present invention comprises: a stereo camera; an interface unit exchanging data with at least one device inside a vehicle; and a processor performing lane detection for a first region in front of the vehicle based on a stereo image received from the stereo camera, and deducing lanes for a second region in front of the vehicle based on map information from an interface unit. Accordingly, the lanes in front of a vehicle can be perceived based on a captured image.

Abstract: A system and method for tracking and annotating objects in a 3D model is disclosed. The method includes receiving a signal feed from a group of sensors including at least one depth sensor, determining a reference signal feed from the signal feed, determining a volumetric representation of at least one object not present in the reference signal feed, assigning a unique volumetric profile to at least one object, and/or storing the unique volumetric profile in an object database. The signal feed may include at least one 3D area of interest. Also, the unique volumetric profile may include a unique volumetric id obtained from a group of attributes. The unique volumetric profile may include at least a unique volumetric position and a unique volumetric centroid. The group of sensors may further include video cameras, thermal, and chemical sensors.

Abstract: Exemplary systems and methods allow for precise formation and subsequent characterization of electrical interconnects, for example solder joints associated with integrated circuit packages. The system may utilize a cartridge-like structure for use in aligning the metal components to be interconnected, and to facilitate subsequent testing of the interconnect.

Abstract: A mobile electronic device processes a sequence of images to identify and re-identify an object of interest in the sequence. An image sensor of the device, receives a sequence of images. The device detects an object in a first image as well as positional parameters of the device that correspond to the object in the first image. The device determines a range of positional parameters within which the object may appear in a field of view of the device. When the device detects that the object of interest exited the field of view it subsequently uses motion sensor data to determine that the object of interest has likely re-entered the field of view, it will analyze the current frame to confirm that the object of interest has re-entered the field of view.

Abstract: Methods, computer program products and systems for providing video tracking. The method includes receiving a first signal from a radio frequency identification (RFID) tag. A location of the RFID tag is determined in response to the first signal. An image that includes the location of the RFID tag is recorded. The location of the RFID tag is marked on the image, resulting in a marked image.

Abstract: An image monitoring system includes a recorder that records an image captured by a camera via a network. The system is controlled to display the present image captured by the camera or a past image recorded on the recorder. A moving object is detected from the image captured by the camera, the detector including a resolution converter for generating an image with a resolution lower than the resolution of the image captured by the camera. A moving object is detected from the image generated by the resolution converter and positional information on the detected moving object is output. The positional information of the detected moving object is merged with the image captured by the camera on the basis of the positional information.

Abstract: A positioning server is connected to a collection of access points, base stations, NFC stations, and image or video cameras and the collected data is used for positioning objects. A plurality of electronic devices are paired with an object by tracking the position of the object based on imaging and the position of electronic devices based on RF signals in vicinity of the object. Once a device is paired with an object, the propagation channel profile measured through the electronic device is used to develop and tune a database of channel profiles versus location. This database is used based on signature/profile matching and correlation for positioning devices and objects that do not have pairing or have poor image-based positioning accuracy or reliability. When a device is detected that cannot be paired with any object, or a device that is unpaired from a previously associated object, a theft or loss alert is generated.

Abstract: A method and corresponding device for identifying operational mode shapes of an object in a video stream includes extracting pixel-wise Eulerian motion signals of an object from an undercomplete representation of frames within a video stream. Pixel-wise Eulerian motion signals are downselected to produce a representative set of Eulerian motion signals of the object. Operational mode shapes of the object are identified based on the representative set. Resonant frequencies can also be identified. Embodiments enable vibrational characteristics of objects to be determined using video in near real time.

Abstract: A face detection device for detecting the face of a person in an input image includes the a face detection circuit, a signal processing circuit, and a controller. The face detection circuit includes a hardware circuit that is configured to detect a face in an input image. The signal processing circuit is configured to perform signal processing based on an input image signal in accordance with a rewritable program including a face detection program for detecting a face in an input image. The controller is configured to allow the face detection circuit and the signal processing circuit to perform face detection on an image of a frame or on respective images of adjacent frames among consecutive frames, and to control face detection by the signal processing circuit on the basis of a face detection result obtained by the face detection circuit.

Abstract: A remote follow spot system includes a remote controller that has separately movable parts that are movable in two orthogonal directions, and a display attached to one of said two separately movable parts. The display receives a video feed from a controlled light, that is controlled to move in the same directions as remote controller. The display hence shows the field of view where the light is pointing. In this way, an operator of the follow spot can control the light without physically being near the light.

Abstract: Models are generated from objects identified in video. Each model is evaluated based on knowledge of the objects determined from video analysis, and preferred models are identified based on the evaluations. In some examples, each model could be evaluated by tracking a movement of each object in the video by using each model to track the object from which it was generated, evaluating an ability of each model to identify the objects in the video that are similar to the object from which it was generated, and determining an amount of false identifications made by each model of different objects in different video that does not include the object from which it was generated.

Abstract: A method and an apparatus for detecting an abnormal situation are disclosed. The method includes recognizing whether a detection target exists in a captured image; generating, based on the captured image, a three-dimensional point cloud of the detection target in the captured image, when the detection target exists; obtaining, based on the generated three-dimensional point cloud, one or more current posture features of the detection target; and determining, based on the current posture features and one or more predetermined posture feature standards, whether the abnormal situation exists, the posture feature standards being previously determined based on one or more common features when the detection target performs a plurality of abnormal actions.

Abstract: Systems and methods track one or more points between images. A point for tracking may be selected, at least in part, on a determination of how discriminable the point is relative to other points in a region containing the point. A point of an image being tracked may be located in another image by matching a patch containing the point with another patch of the other image. A search for a matching patch may be focused in a region that is determined based at least in part on an estimate of movement of the point between images. Points may be tracked across multiple images. If an ability to track one or more points is lost, information about the points being tracked may be used to relocate the points in another image.

Abstract: A network camera includes: a camera main unit including an image sensor unit and a movable portion having a motor for swiveling the image sensor unit; and a base unit, connected detachably to the camera main unit and fixed to a camera installation surface, the base unit having a nonvolatile memory for storing network operation information including network setting information unique to the network camera.

Abstract: An angular velocity of an image capture apparatus and a motion vector between images are detected. An object velocity is computed based on a comparison between a change amount of the angular velocities and a change amount of the motion vectors. Then, by changing an optical axis based on the object velocity during exposure, a panning assistance function capable of dealing with various panning operations can be provided.

Abstract: An objective of the present invention is to obtain a vehicle-mounted recognition device capable of recognizing an object to be recognized in a shorter processing time than previously possible.

Abstract: Disclosed are systems and methods for detecting moving objects. A computer-implemented method for detecting moving objects comprises obtaining a streaming video captured by a camera; extracting an input image sequence including a series of images from the streaming video; tracking point features and maintaining a set of point trajectories for at least one of the series of images; measuring a likelihood for each point trajectory to determine whether it belongs to a moving object using constraints from multi-view geometry; and determining a conditional random field (CRF) on an entire frame to obtain a moving object segmentation.

Abstract: A sensor manager provides dynamic input fusion using thermal imaging to identify and segment a region of interest. Thermal overlay is used to focus heterogeneous sensors on regions of interest according to optimal sensor ranges and to reduce ambiguity of objects of interest. In one implementation, a thermal imaging sensor locates a region of interest that includes an object of interest within predetermined wavelengths. Based on the thermal imaging sensor input, the regions each of the plurality of sensors are focused on and the parameters each sensor employs to capture data from a region of interest are dynamically adjusted. The thermal imaging sensor input may be used during data pre-processing to dynamically eliminate or reduce unnecessary data and to dynamically focus data processing on sensor input corresponding to a region of interest.

Abstract: Techniques detecting usage of copyrighted video content using object recognition are provided. In one example, a computer-implemented method comprises determining, by a system operatively coupled to a processor, digest information for a video, wherein the digest information comprises objects appearing in the video and respective times at which the objects appear in the video. The method further comprises comparing, by the system, the digest information with reference digest information for reference videos, wherein the reference digest information identifies reference objects appearing in the reference videos and respective reference times at which the reference objects appear in the reference videos. The method further comprises determining, by the system, whether the video comprises content included in one or more of the reference videos based on a degree of similarity between the digest information and reference digest information associated with one or more of the reference videos.

Abstract: A 3-dimensional displaying apparatus includes an image displaying panel having a plurality of pixels and a backlight panel spaced apart from one surface of the image displaying panel. The backlight panel includes a first line source set having a plurality of line sources arranged at regular intervals and a second line source set having line sources arranged spaced apart from the respective line sources of the first line source set by a predetermined interval. The first line source set and the second line source set are driven alternately. Thus, in a case where a horizontal location of an observer varies, the change of brightness of image information and the crosstalk between adjacent visual fields are minimized, and pseudo-stereoscopic vision is prevented. Also, the irregularity of brightness distribution in a visual field may be solved.

Abstract: An example target acquisition method includes obtaining, according to a global feature of each video frame of a plurality of video frames, a target pre-estimated position of each scale in the video frame; clustering the target pre-estimated position in each video frame to obtain a corresponding target candidate region; and determining a target actual region in the video frame according to all the target candidate regions in each video frame in combination with confidence levels of the target candidate regions and corresponding scale processing. The techniques of the present disclosure quickly and effectively acquire one or multiple targets, and, more particularly, achieve accurately distinguishing and acquiring the multiple targets.

Abstract: A distance detecting device is mounted on a user's vehicle to detect a distance between the user's vehicle and a leading vehicle moving in front of the user's vehicle. The distance detecting device communicates with a processing device, which applies race based distance rules to determine whether the user's vehicle is close to or incurring a penalty based at least on the distance between the user's vehicle and the leading vehicle. An indication can be given to the user regarding an impending penalty and/or when a penalty is incurred. Similarly, the device can be read to apply a penalty. Various modifications can be made to allow for recording, display, and transmission of racing and penalty statistics, enabling and disabling recordation of penalty occurrences, tailoring the penalty determinations to a given race, and mounting the distance detecting device to a vehicle.

Abstract: Motion vector estimation is provided for generating and displaying images at a frame rate that is greater than a rendering frame rate. The displayed images may include late stage graphical adjustments of pre-rendered scenes that incorporate motion vector estimations. A head-mounted display (HMD) device may determine a predicted pose associated with a future position and orientation of the HMD, render a current frame based on the predicted pose, determine a set of motion vectors based on the current frame and a previous frame, generate an updated image based on the set of motion vectors and the current frame, and display the updated image on the HMD. In one embodiment, the HMD may determine an updated pose associated with the HMD subsequent to or concurrent with generating the current frame, and generate the updated image based on the updated pose and the set of motion vectors.

Abstract: The object detection device 1 detects an object being recognized (such as a pedestrian) in a frame image 42, and identifies an area 42a where a detected object which is detected in the frame image 42 is present. A frame image 43 is input after the frame image 42. The object detection device 1 detects the object being recognized in the frame image 43, and identifies an area 43a where a detected object which is detected in the frame image 43 is present. When a distance from center coordinates 42b of the area 42a to center coordinates 43b of the area 43a is smaller than a reference distance, the object detection device 1 determines that the detected object which is detected in the frame image 43 is identical to the detected object which is detected in the frame image 42.

Abstract: In accordance with one embodiment, an image processing apparatus which is accessible to at least one storage device, the apparatus includes a decision unit, a generation unit and a determination unit. The decision unit estimates a separation distance from the first camera to the display shelf. The decision unit decides a search distance, based on the separation distance. The generation unit generates a template image by converting a number of pixels of single item image acquired by photographing the product as a single piece and stored in the storage device, with a magnification corresponding to a ratio between the search distance and a known photographing distance. The determination unit determines an area, which is similar to the template image, within a shelf image stored in the storage device.

Abstract: A “Concurrent Projector-Camera” uses an image projection device in combination with one or more cameras to enable various techniques that provide visually flicker-free projection of images or video, while real-time image or video capture is occurring in that same space. The Concurrent Projector-Camera provides this projection in a manner that eliminates video feedback into the real-time image or video capture. More specifically, the Concurrent Projector-Camera dynamically synchronizes a combination of projector lighting (or light-control points) on-state temporal compression in combination with on-state temporal shifting during each image frame projection to open a “capture time slot” for image capture during which no image is being projected. This capture time slot represents a tradeoff between image capture time and decreased brightness of the projected image.

Abstract: A method for classifying at least one object of interest in a video is provided. The method includes accessing, using at least one processing device, a frame of the video, the frame including at least one object of interest to be classified, performing, using the at least one processing device, object detection on the frame to detect the object of interest, tracking, using the at least one processing device, the object of interest over a plurality of frames in the video over time using a persistent tracking capability, isolating, using the at least one processing device, a segment of the frame that includes the object of interest, classifying, using the at least one processing device, the object of interest by processing the segment using deep learning, and generating an output that indicates the classification of the object of interest.

Abstract: In accordance with example embodiments, the method and system for 360-degree video post-production generally makes use of points of view (POVs) to facilitate the 360-degree video post-production process. A POV is a rectilinear subset view of a 360-degree composition based on a particular focal length, angle of view, and orientation for each frame of the 360-degree composition. Video post-production editing can be applied to a POV by the user, using rectilinear video post-production methods or systems. The rectilinear video post-production editing done on the POV is integrated back into the 360-degree environment of the 360-degree composition. In accordance with example embodiments, the method and system for 360-degree video post-production comprises identifying a point of view in a 360-degree composition; applying video post-production editing to the point of view; and aligning a new layer containing the video post-production editing with the point of view in the 360-degree composition.

Abstract: A disappearing direction determination device and method, a video camera calibration apparatus and method, a video camera and a computer program product are provided. The device comprises: a moving target detecting unit for detecting in the video image a moving target area where a moving object locates; a feature point extracting unit for extracting at least one feature point on the moving object in the detected moving target area; a moving trajectory obtaining unit for tracking a movement of the feature point in a predetermined number of video image frames to obtain a movement trajectory of the feature point; and a disappearing direction determining unit for determining, according to the movement trajectories of one or more moving objects in the video image, a disappearing direction pointed by a major moving direction of the moving objects. Thus, a disappearing direction and video camera gesture parameters can be determined accurately.

Abstract: A method of determining eye position information includes identifying an eye area in a facial image; verifying a two-dimensional (2D) feature in the eye area; and performing a determination operation including, determining a three-dimensional (3D) target model based on the 2D feature; and determining 3D position information based on the 3D target model.

Abstract: Examples of an electronic device according to an embodiment include an electronic device in which user can see through at least a transparent part of a first display area when the electronic device is worn on a body of the user. The electronic device includes: a processor configured to transmit a first part included in a first position on an image imaged by the camera and first information regarding the first part and receive second information relating to processing result on the first part after a first term has passed since transmission of the first information; and display circuitry configured to display the second information at a third position on the first display area, the third position determined according to a second position in the first part on an image imaged by the camera after the first term has passed since transmission of the first information.

Abstract: Examples of the present disclosure relate to a method, apparatus, computer program and system for image analysis. According to certain examples, there is provided method comprising causing, at least in part, actions that result in: receiving orientation information of an image capturing device; receiving one or more features detected from an image captured by the image capturing device; and selecting a clustering model for clustering the features, wherein the clustering model is selected, at least in part, in dependence upon the orientation information.

Abstract: Embodiments are directed to an object detection system having at least one processor circuit configured to receive a series of image regions and apply to each image region in the series a detector, which is configured to determine a presence of a predetermined object in the image region. The object detection system performs a method of selecting and applying the detector from among a plurality of foreground detectors and a plurality of background detectors in a repeated pattern that includes sequentially selecting a selected one of the plurality of foreground detectors; sequentially applying the selected one of the plurality of foreground detectors to one of the series of image regions until all of the plurality of foreground detectors have been applied; selecting a selected one of the plurality of background detectors; and applying the selected one of the plurality of background detectors to one of the series of image regions.

Abstract: A system comprising a computer-readable storage medium storing at least one program and a method for identifying and monitoring vehicles in motion is presented. The method may include accessing sets of pixel coordinates defining a location of a vehicle within a first image and a second image. The method may further include translating the sets of pixel coordinates to sets of global coordinates defining a first and second geospatial location of the vehicle. The method further includes determining the vehicle is in motion based on a comparison of the first and second geospatial locations of the vehicle. The method further includes causing presentation of a user interface that includes a geospatial map with visual indicators of the first and second geospatial location of the vehicle.

Abstract: For cameras that capture several images in a burst mode, some embodiments of the invention provide a method that presents one or more of the captured images differently than the remaining captured images. The method identifies at least one captured image as dominant image and at least another captured image as a non-dominant image. The method then displays each dominant image different from each non-dominant image in a concurrent presentation of the images captured during the burst mode. The dominant images may appear larger than non-dominant images, and/or appear with a marking that indicates that the images are dominant.

Abstract: An image processing apparatus comprises: a dividing unit that divides two frame images into a plurality of divided areas; a determination unit that determines a representative point for each of the divided areas in one of the two frame images; a setting unit that, for each of the two frame images, sets image portions for detecting movement between the two frame images, based on the representative points; and a detection unit that detects movement between the two frame images based on correlation values of image signals in the set image portions, wherein for each of the divided areas, the determination unit determines a feature point of the divided area or a predetermined fixed point as the representative point of the divided area in accordance with a position of the divided area in the one frame image.

Abstract: Provided is a glass type terminal and a control method thereof. The glass type terminal includes: a frame unit configured to be wearable on a user's head; a display unit; and a control unit configured to turn on power of a camera when preset conditions are met, analyze an image captured by the camera to produce image capture guide information, and control the display unit to output the produced image capture guide information.