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 event filtering device and a motion recognition device using thereof are provided. The motion recognition device includes an emitter configured to emit an infrared ray in a pattern; a detector configured to detect events in a visible ray area and an infrared ray area; a filter configured to determine whether at least one portion of the detected events is detected using the infrared ray in the pattern, and filter the detected events based on a result of the determination; and a motion recognizer configured to perform motion recognition based on a detected event accepted by the filter.

Abstract: A method of extracting a static pattern from an output of an event-based sensor. The method may include receiving an event signal from the event-based sensor in response to dynamic input, and extracting a static pattern associated with the dynamic input based on an identifier and time included in the event signal. The static pattern may be extracted from a map generated based on the identifier and time.

Abstract: A proximity sensor and a proximity sensing method using an event-based vision sensor are provided. The proximity sensor may include a point identification (ID) unit which identifies a point at which an output light output from a focused light source is reflected from an object in an image taken by the proximity sensor; and a distance determination unit which determines a distance between the object and the proximity sensor based on a position of the point.

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: A method and apparatus for processing a user input are provided. The method includes: determining a type of the user input based on a change amount of an input image; and processing the user input based on the determined type.

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: An event signal processing method and an event-based sensor performing the event signal processing method are provided. The event signal processing method includes receiving an activation signal to indicate sensing of an event from a sensor array, increasing the cumulative event number of a sensing area corresponding to the activation signal among sensing areas of the sensor array, reducing the cumulative event number of each of the sensing areas based on a parameter; and determining, as a flickering area, a sensing area among the sensing areas, of which the cumulative event number exceeds a threshold.

Abstract: A method of recognizing an object includes controlling an event-based vision sensor to perform sampling in a first mode and to output first event signals based on the sampling in the first mode, determining whether object recognition is to be performed based on the first event signals, controlling the event-based vision sensor to perform sampling in a second mode and to output second event signals based on the sampling in the second mode in response to the determining indicating that the object recognition is to be performed, and performing the object recognition based on the second event signals.

Abstract: A method and apparatus for processing a gesture input are provided. The method includes determining a type of an elliptical arc corresponding to a gesture input; determining a rotation direction corresponding to the gesture input; and processing the gesture input based on the type of the elliptical arc and the rotation direction.

Abstract: A method and apparatus for detecting a movement of an object based on an event are provided. The apparatus may detect a movement of an object, for example, based on time difference information of a pixel corresponding to an event detected using an event-based vision sensor.

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.

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: An event signal processing method and apparatus are provided. The event signal processing method includes receiving, from an event-based sensor, event signals including timestamps, generating a first timestamp map based on the timestamps, and interpolating a new timestamp into the first timestamp map based on at least two timestamps of the first timestamp map, to generate a second timestamp map.

Abstract: An image deblurring method and an image deblurring apparatus are provided. The image deblurring method includes acquiring a blurred image and a dynamic vision sensor (DVS) event set that is recorded by a DVS while the blurred image is exposed, and deblurring the blurred image, based on the DVS event set.

Abstract: A user input processing apparatus using a motion of an object to determine whether to track the motion of the object, and track the motion of the object using an input image including information associated with the motion of the object.

Abstract: An image generating method and an image generating apparatus are provided. The image generating method includes generating a first image based on first event signals that are output from an event-based vision sensor during a first time period and stored in a buffer, generating a second image based on second event signals that are output from the event-based vision sensor during a second time period and stored in the buffer, and aligning the first image and the second image to generate a third image having a quality that is higher than qualities of the first image and the second 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: 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 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.