Abstract: An apparatus and a method for processing an input are provided. The apparatus includes a shape identifier configured to identify a first shape corresponding to a user input among shapes, a pattern identifier configured to identify a first pattern corresponding to the user input among patterns, and a determiner configured to determine a first command corresponding to the first shape and the first pattern.

Abstract: A method of displaying a menu based on at least one of a depth information and a space gesture is provided. The method including determining depth information corresponding to a distance from a screen of a user terminal to a hand of a user; identifying at least one layer among a plurality of layers based on the depth information; and applying a graphic effect to the identified layer so that a menu page corresponding to the at least one identified layer is displayed on the screen of the user terminal.

Abstract: An object detection method and a neural network system for object detection are disclosed. The object detection method acquires a current frame of a sequence of frames representing an image sequence, and extracts a feature map of the current frame. The extracted feature map is pooled with information of a pooled feature map of a previous frame to thereby obtain a pooled feature map of the current frame. An object is detected from the pooled feature map of the current frame. A dynamic vision sensor (DVS) may be utilized to provide the sequence of frames. Improved object detection accuracy may be realized, particularly when object movement speed is slow.

Abstract: Disclosed is an image adjustment apparatus including a receiver which is configured to receive a first input image of an object which is time-synchronously captured and a second input image in which a motion event of the object is sensed time-asynchronously, and an adjuster which is configured to adjust the first input image and the second input image.

Abstract: Disclosed is an image adjustment apparatus including a receiver which is configured to receive a first input image of an object which is time-synchronously captured and a second input image in which a motion event of the object is sensed time-asynchronously, and an adjuster which is configured to adjust the first input image and the second input image.

Abstract: Provided is a data output device that includes an event array including a plurality of sensing elements; a first event identifier connected to a first sensing element among the plurality of sensing elements and configured to identify first element information corresponding to the first sensing element in response to the case where an event is detected by the first sensing element; a second event identifier connected to a second sensing element among the plurality of sensing elements and configured to identify second element information corresponding to the second sensing element in response to the case where the event is detected by the second sensing element; and an event output interface configured to output event information based on at least one of the first element information and the second element information.

Abstract: The disclosure provides an object detection method and apparatus based on a Dynamic Vision Sensor (DVS). The method includes the following operations of: acquiring a plurality of image frames by a DVS; and, detecting the image frames by a recurrent coherent network to acquire a candidate box for objects to be detected, wherein the recurrent coherent network comprising a frame detection network model and a candidate graph model. By using a new recurrent coherent detection network, a bounding box for an object to be detected is fast detected from the data acquired by a DVS. The detection speed is improved greatly while ensuring the detection accuracy.

Abstract: An image processing device includes a vision sensor and a processor. The vision sensor generates a plurality of events in which an intensity of light changes and generates a plurality of timestamps depending on times when the events occur. In addition, the processor may regenerate a timestamp of a pixel where an abnormal event occurs, based on temporal correlation of the events.

Abstract: An image processing device includes a vision sensor and a processor. The vision sensor generates a plurality of events in which an intensity of light changes and generates a plurality of timestamps depending on times when the events occur. In addition, the processor may regenerate a timestamp of a pixel where an abnormal event occurs, based on temporal correlation of the events.

Abstract: An image sensor includes a CIS (CMOS image sensor) pixel, a DVS (dynamic vision sensor) pixel, and an image signal processor. The CIS pixel includes a photoelectric conversion device generating charges corresponding to an incident light and a readout circuit generating an output voltage corresponding to the generated charges. The DVS pixel detects a change in an intensity of the incident light based on the generated charges to output an event signal and does not include a separate photoelectric conversion device. The image signal processor allows the photoelectric conversion device to be connected to the readout circuit or the DVS pixel.

Abstract: A method and apparatus for processing a binocular disparity image are provided. A method of determining a disparity of a binocular disparity image that includes a left eye image and a right eye image includes acquiring features of a plurality of pixels of the binocular disparity image based on an event distribution of the binocular disparity image, calculating a cost matrix of matching respective pixels between the left eye image and the right eye image based on the features, and determining a disparity of each matched pair of pixels based on the cost matrix.

Abstract: Exemplary embodiments provide an image vision processing method, device and equipment and relate to: determining parallax and depth information of event pixel points in a dual-camera frame image acquired by Dynamic Vision Sensors; determining multiple neighboring event pixel points of each non-event pixel point in the dual-camera frame image; determining, according to location information of each neighboring event pixel point of each non-event pixel point, depth information of the non-event pixel point; and performing processing according to the depth information of each pixel point in the dual-camera frame image. Since non-event pixel points are not required to participate in the matching of pixel points, even if it is difficult to distinguish between the non-event pixel points or the non-event pixel points are occluded, depth information of the non-event pixel points can be accurately determined according to the location information of neighboring event pixel points.

Abstract: An image processing device includes a vision sensor and a processor. The vision sensor generates a plurality of events in which an intensity of light changes and generates a plurality of timestamps depending on times when the events occur. In addition, the processor may regenerate a timestamp of a pixel where an abnormal event occurs, based on temporal correlation of the events.

Abstract: A pixel includes a photoelectric device, a current readout unit configured to detect an electric current flowing in the photoelectric device to generate an input voltage, an event determination unit configured to determine an event occurrence and an event type responsive to the input voltage, and configured to output an event detection signal, and an event output unit configured to store the event detection signal for an event-storage period and configured to output the stored event detection signal responsive to an expiration of the event-storage period.

Abstract: In a method of processing data for a dynamic vision sensor, changes of light are detected by the dynamic vision sensor to output a plurality of event frames. A data format conversion is performed to convert the plurality of event frames into at least one image frame. An image compression is performed to compress the at least one image frame.

Abstract: A method and device for recognizing a motion of an object, the method including receiving event signals from a vision sensor configured to sense the motion, storing, in an event map, first time information indicating a time at which intensity of light corresponding to the event signals changes; generating an image based on second time information corresponding to a predetermined time range among the first time information, and recognizing the motion of the object based on the image.

Abstract: A method and apparatus for detecting an error in gesture recognition are provided. The method includes sensing whether an effective gesture occurs in a first area for gesture recognition of a user; setting a second area and sensing an occurrence of an event due to a movement of the user, based on a result of the sensing in the first area; and detecting the error in the gesture recognition based on whether the occurrence of the event is sensed in the second area.

Abstract: A method and device for recognizing a motion of an object, the method including receiving event signals from a vision sensor configured to sense the motion, storing, in an event map, first time information indicating a time at which intensity of light corresponding to the event signals changes; generating an image based on second time information corresponding to a predetermined time range among the first time information, and recognizing the motion of the object based on the image.

Abstract: Provided is an event signal processing method and apparatus. The event signal processing method includes acquiring, from an event based sensor, coordinates of an active pixel corresponding to an event and a timestamp corresponding to the event; mapping the event to a target voxel included in a three-dimensional (3D) grid based on the coordinates of the active pixel and the timestamp; and updating a value of the target voxel based on the event.

Abstract: A method and apparatus for acquiring an image disparity are provided. The method may include acquiring, from dynamic vision sensors, a first image having a first view of an object and a second image having a second view of the object; calculating a cost within a preset disparity range of an event of first image and a corresponding event of the second image; calculating an intermediate disparity of the event of the first image and an intermediate disparity of the event of the second image based on the cost; determining whether the event of the first image is a matched event based on the intermediate disparity of the event of the first image and the intermediate disparity of the event of the second image; and predicting optimal disparities of all events of the first image based on an intermediate disparity of the matched event of the first imaged.