Abstract: The present invention relates to a method, system, and non-transitory computer-readable recording medium for assisting object control. According to one aspect of the invention, there is provided a method for assisting object control, comprising the steps of: determining a dominant component capable of dominantly representing a motion made by a user with reference to a trace of the motion, and dynamically establishing a motion reference spatial coordinate system with reference to the dominant component; and recognizing an intention of the motion with reference to at least one of the trace specified with respect to the motion reference spatial coordinate system and properties of the trace.

Abstract: There is provided a method of estimating a gesture of a user from a two-dimensional image. The method includes the steps of: acquiring a two-dimensional image relating to a user's body from a two-dimensional camera; specifying two-dimensional relative coordinate points corresponding first and second body parts of the user in a relative coordinate system dynamically defined in the two-dimensional image, and comparing a first positional relationship between the two-dimensional relative coordinate points of the first and second body parts at a first time point, and a second positional relationship between the two-dimensional relative coordinate points of the first and second body parts at a second time point; and estimating the gesture made by the user between the first and second time points based on the result of comparing and context information acquired from the two-dimensional image.

Abstract: A method of assisting an object control comprises determining a first coordinate with reference to, as a trigger coordinate, a coordinate at a time point when a trigger event relating to movement of a control means is generated, among motion coordinates of the control means, determining a second coordinate with reference to at least one of a distance between the trigger coordinate and the motion coordinates, a straight line section specified by the trigger coordinate and the motion coordinates, a distance between the first coordinate and the motion coordinates, and a straight line section specified by the first coordinate and the motion coordinates, and determining a motion vector determined based on the first coordinate and the second coordinate as an instruction vector for determining a control position in a control object region.

Abstract: A method for providing a voice recognition trigger and a system therefor, and a non-transitory computer-readable recording medium are provided. The method for providing the voice recognition trigger includes: calculating a distance change between a device and an object on the basis of proximity information detected by the device; and determining whether or not the voice recognition trigger of the device is provided with reference to the distance change between the device and the object.

Abstract: A method of determining a dominant eye includes acquiring indicator coordinates, left-eye coordinates, and right-eye coordinates of a user at a plurality of time points; calculating left-eye difference information about an angle, distance, or direction specified based on a straight line passing through the indicator coordinate and the left-eye coordinate at a first time point and a straight line passing through the indicator coordinate and the left-eye coordinate at a second time point, and right-eye difference information about an angle, distance, or direction specified based on a straight line passing through the indicator coordinate and the right-eye coordinate at the first time point and a straight line passing through the indicator coordinate and the right-eye coordinate at the second time point; and determining the dominant eye of the user with reference to the left-eye difference information and the right-eye difference information.

Abstract: A method includes acquiring information on an in-image coordinate point of a region of interest contained in each of a plurality of images respectively photographed by a plurality of image modules; specifying, with reference to information on a position where at least one of the plurality of image modules is installed and information on an in-image coordinate point of a target region of interest contained in an image photographed by the at least one image module, a candidate figure containing a position where the target region of interest is located in a reference space; and specifying the position where the target region of interest is located in the reference space, with reference to a positional relationship between a first candidate figure of the target region of interest corresponding to a first image module and a second candidate figure of the target region of interest corresponding to a second image module.

Abstract: According to one aspect of the invention, there is provided a method for providing a voice recognition trigger, comprising the steps of: estimating a first distance, which is a distance between a device and a user, on the basis of proximity information detected by the device, and estimating a second distance, which is a distance between the device and a location where a voice detected by the device is uttered, with reference to information on the voice detected by the device; and determining whether the voice detected by the device is an object of voice recognition, with reference to similarity between the first distance and the second distance.

Abstract: According to one aspect of the present invention, there is provided a method for assisting object control using a two-dimensional camera, comprising the steps of: acquiring a two-dimensional image of a user's body from a two-dimensional camera; and determining a control target area with reference to a candidate target area specified on the basis of two-dimensional relative coordinate points respectively corresponding to a first body part and a second body part of the user in the two-dimensional image, wherein the candidate target area and the control target area are determined on a reference surface established with respect to the two-dimensional camera.

Abstract: According to one aspect of the present disclosure, there is provided a method of assisting an object control, comprising the steps of: determining a first coordinate with reference to, as a trigger coordinate, a coordinate at a time point when a trigger event relating to movement of a control means is generated, among motion coordinates of the control means; determining a second coordinate with reference to at least one of a distance between the trigger coordinate and the motion coordinates, a straight line section specified by the trigger coordinate and the motion coordinates, a distance between the first coordinate and the motion coordinates, and a straight line section specified by the first coordinate and the motion coordinates; and determining a motion vector determined based on the first coordinate and the second coordinate as an instruction vector for determining a control position in a control object region.

Abstract: A method of assisting an object control is provided. The method includes: determining an instruction vector with reference to at least one of whether or not a trigger event relating to a movement of a control means is generated and a distance between a motion coordinate of the control means and a control object region; and determining, when a position of the control means is changed, a control position in the control object region with reference to a vector that connects a virtual reference point specified based on an extension line of the instruction vector before the position of the control means is changed and the motion coordinate of the control means after the position of the control means is changed.

Abstract: A method includes acquiring a two-dimensional image relating to a user's body from a two-dimensional camera; calculating three-dimensional real-world coordinates corresponding to at least one body portion among a plurality of body portions of the user, which are specified from the two-dimensional image; estimating, with reference to the three-dimensional real-world coordinates corresponding to the at least one body portion, three-dimensional real-world coordinates respectively corresponding to first and second body portions used in determining the user's intention; and determining a control target area with reference to a first candidate target area specified based on the three-dimensional real-world coordinates respectively corresponding to the first and second body portions, and a second candidate target area specified based on two-dimensional relative coordinates respectively corresponding to the first and second body portions in the two-dimensional image.

Abstract: According to one aspect of the invention, there is provided a method for assisting object control, comprising the steps of: specifying, in a real-world coordinate system, a control vector corresponding to a gesture or manipulation performed by a user; determining an object indicated by the control vector as a target object to be controlled by the gesture or manipulation performed by the user; performing mapping for specifying a control coordinate point corresponding to a magnitude or direction of the control vector in a target object reference coordinate system defined on the basis of a characteristic of the target object; and determining a control command to be applied to the target object, with reference to the control coordinate point specified by the mapping.

Abstract: A method includes acquiring information on an in-image coordinate point of a region of interest contained in each of a plurality of images respectively photographed by a plurality of image modules; specifying, with reference to information on a position where at least one of the plurality of image modules is installed and information on an in-image coordinate point of a target region of interest contained in an image photographed by the at least one image module, a candidate figure containing a position where the target region of interest is located in a reference space; and specifying the position where the target region of interest is located in the reference space, with reference to a positional relationship between a first candidate figure of the target region of interest corresponding to a first image module and a second candidate figure of the target region of interest corresponding to a second image module.

Abstract: According to one aspect of the present invention, there is provided a method for assisting object control using a two-dimensional camera, comprising the steps of: acquiring a two-dimensional image of a user's body from a two-dimensional camera; and determining a control target area with reference to a candidate target area specified on the basis of two-dimensional relative coordinate points respectively corresponding to a first body part and a second body part of the user in the two-dimensional image, wherein the candidate target area and the control target area are determined on a reference surface established with respect to the two-dimensional camera.

Abstract: The present invention relates to a method, system, and non-transitory computer-readable recording medium for assisting object control. According to one aspect of the invention, there is provided a method for assisting object control, comprising the steps of: determining a dominant component capable of dominantly representing a motion made by a user with reference to a trace of the motion, and dynamically establishing a motion reference spatial coordinate system with reference to the dominant component; and recognizing an intention of the motion with reference to at least one of the trace specified with respect to the motion reference spatial coordinate system and properties of the trace.

Abstract: A virtual touch recognition apparatus and a method of correcting a recognition error of the virtual touch recognition apparatus utilize a user's eye position and an image display position or projection position of a head-up display (HUD). The virtual touch recognition apparatus includes a gesture recognizer detecting the eye position of a user, the head-up display projecting an image on the image display position in front of the user, and a controller correcting a recognition error of a virtual touch based on the eye position of the user and the image display position. The apparatus and method can minimize a virtual touch recognition error occurring depending on the user's eye position and the image display position of the HUD when gesture control technology using the virtual touch is applied to a vehicle.

Abstract: Disclosed are a method and an apparatus for accurately detecting a gesture from a user's motion using a user-based spatial coordinate system. A method for detecting a gesture in a user-based spatial coordinate system comprises the steps of: setting a user-based spatial coordinate system using a first body coordinate corresponding to a first body part of the user as a starting point; analyzing the motion vector state of a second body coordinate corresponding to a second body part of the user in the user-based spatial coordinate system over time; and detecting the user's gesture on the basis of a change in the motion vector state.

Abstract: A control method for allowing a user to specify an electronic device and switch it to a speech recognition mode is provided. With the optimum control method and the electronic device utilizing the method, a voice command may be transmitted to the electronic device more quickly and effectively regardless of the circumstances, and the electronic device may be specified through gesture recognition to enable transmission of the voice command, so that the voice command may be effectively executed without needing a user to learn or memorize a name or the like of the electronic device in advance for speech recognition. Further, it is possible to more accurately recognize a gesture that is a preliminary step for transmitting a voice command to the electronic device, thereby improving the recognition rate and preventing malfunction.

Abstract: A remote control apparatus comprises an image acquisition unit for acquiring an image of the body of a user by photographing the image, a location calculation unit for calculating coordinate data representing the locations of a first coordinate (eye) and a second coordinate (a finger or a pointer) of the body of the user by means of the image received from the image acquisition unit, and a match confirmation unit for checking whether the locations of the first and second coordinates of the body of the user match the extended connecting straight line, the coordinates having been confirmed on the basis of the camera lens-based coordinate data calculated in the location calculation unit, and if the match is confirmed, then concluding the setup intention of the user to be an affirmative.

Abstract: A display device for an autonomous vehicle includes a display unit mounted in a ceiling of the vehicle and including at least one display; and a position adjustment unit configured to move a position of at least one display of the display unit. The at least one display of the display unit is moved by the position adjustment unit between a first position in which a screen is disposed toward a ceiling or floor of the vehicle and a second position in which a screen is disposed toward each of seats facing each other. At least one display of the display unit is disposed such that the screen faces the front and the rear of the vehicle at the second position.