Sony Patent | Image processing device, image processing method, and program for displaying an image in accordance with a selection from a displayed menu and based on a detection by a sensor

Patent: Image processing device, image processing method, and program for displaying an image in accordance with a selection from a displayed menu and based on a detection by a sensor

Publication Number: 10175857

Publication Date: 2019-01-08

Applicants: Sony

Abstract

There is provided an image processing device including a superimposition display position determining unit which determines a position of an object having a predetermined flat surface or curved surface out of an object imaged in an input image based on an environment map, a superimposition display image generating unit which generates a superimposition display image by setting superimposition display data at the position of the object determined by the superimposition display position determining unit, an image superimposing unit which superimposes the superimposition display image on a visual field of a user, an operating object recognizing unit which recognizes an operating object imaged in the input image, and a process executing unit which executes a process corresponding to an item selected based on a position of the operating object recognized by the operating object recognizing unit.

Background

Recently, technology referred to as augmented reality (AR) has been drawing attention whereby an image obtained by imaging a real space and modified through a specific process is presented to a user. In the AR technology, useful information on an object in a real space shown in an input image may be inserted into the image to be output as an output image, for example. That is, in the AR technology, typically, a large part of the image presented to the user shows the real space, and some part of the image may be processed in accordance with an application purpose. Such a characteristic is in contrast to virtual reality in which an entire (or a large part) of the output image is composed using computer graphics (CG). By using the AR technology, for example, advantages such as easy understanding of a situation of the real space by a user or work support based on the output image may be provided.

Further, in the AR technology, in addition to the technique involving inserting useful information on an object in a real space into an image obtained by imaging a real space, there is also a technique of presenting to a user useful information on an object in a real space in a superimposing manner on a visual field of a user who is viewing the real space. In this technique, the useful information on an object in the real space is presented to the user by being optically composited with the visual field of the user who is viewing the real space by using a half mirror and the like. Also in the case of using such AR technology, for example, advantages such as easy understanding of a situation of the real space by a user or work support may be provided.

In the AR technology, in order to present really useful information to the user, it is important that a computer accurately understands the situation of the real space. Therefore, technology aimed to understand the situation of the real space, which serves as a basis of the AR technology, has been developed. For example, Japanese Patent Application Laid-Open No. 2008-304268 discloses a method of dynamically generating an environment map representing a three-dimensional positions of objects existing in a real space by applying technology referred to as simultaneous localization and mapping (SLAM) capable of simultaneously estimating a position and posture of a camera and a position of a feature point shown in an image of the camera. Note that, a basic principle of the SLAM technology using a monocular camera is disclosed in “Real-Time Simultaneous Localization and Mapping with a Single Camera” (Andrew J. Davison, Proceedings of the 9th IEEE International Conference on Computer Vision Volume 2, 2003, pp. 1403-1410).

Summary

In the meantime, as a compact display device to be mounted on the head, a head mounted display (HMD) has been in widespread use. As a technology that uses an HMD equipped with a camera, there can be exemplified a technology for modifying an image imaged by the camera through the AR technology using an image processing device, and displaying the image modified by the HMD in order for a user to view the modified image. A function which such an HMD has may be realized by a video transmissive HMD, for example. Further, for example, there is also a technology for generating an additional information image using an image imaged by the camera as a source through the AR technology by an image processing device, and optically compositing the generated additional information image using a half mirror and the like within a visual field, in order for a user to view the image. Such functions of the HMD may be realized by an optically transmissive HMD, for example. By using those technologies, the user can easily understand a situation of the real space and a work support based on the output image may be provided. As a device for inputting operation for causing the image processing device to execute a process, there may be assumed an input device such as a keyboard or a mouse, for example.

However, while there is exemplified as an advantage in using the HMD that the trouble of inputting operation by the user can be saved, there is an issue that when the input device such as a keyboard or a mouse is used as a device for inputting operation, it causes a trouble of inputting operation to the user. Thus, the advantage of using the HMD is lessened.

In light of the foregoing, it is desirable to provide an image processing device, an image processing method, and a program which are novel and improved, and which can facilitate the input of operation by the user in the configuration in which information is displayed, by the HMD, in a superimposed manner on a visual field of the user through the AR technology.

According to an embodiment of the present invention, there is provided an image processing device which includes a feature data storage unit which stores feature data indicating a feature of appearance of an object, a superimposition display data storage unit which stores superimposition display data which is to be a source of an image that is superimposed on a visual field of a user and an item position which is a position of an item forming the superimposition display data, an environment map generating unit which generates an environment map representing a position of one or more objects existing in a real space based on an input image obtained by imaging the real space using an imaging device and the feature data stored in the feature data storage unit, a superimposition display position determining unit which determines a position of an object having a predetermined flat surface or curved surface out of an object imaged in the input image based on the environment map, a superimposition display image generating unit which generates a superimposition display image by setting the superimposition display data at the position of the object determined by the superimposition display position determining unit, an image superimposing unit which superimposes the superimposition display image on the visual field of the user, an operating object recognizing unit which recognizes an operating object imaged in the input image, and a process executing unit which executes a process corresponding to the item selected based on a position of the operating object recognized by the operating object recognizing unit.

The operating object recognizing unit may recognize a foot imaged in the input image as the operating object.

The operating object recognizing unit may perform matching between a shoe registration image which is an image of a shoe which has been registered in advance and the input image, and when the operating object recognizing unit determines that a shoe which matches with the shoes in the shoe registration image is imaged in the input image, the operating object recognizing unit may recognize the shoe as the operating object.

When a user wears the imaging device on his/her head, the operating object recognizing unit may determine whether or not a foot imaged in the input image is coming in from a side which is the nearest from the user among respective sides that form the input image, and when the operating object recognizing unit determines that the foot is coming in from the side which is the nearest from the user, the operating object recognizing unit may recognize the foot as the operating object.

The operating object recognizing unit may determine whether or not a shoe with a mark, which has been subjected to predetermined marking in advance, is imaged in the input image, and when the operating object recognizing unit determines that the shoe with a mark is imaged in the input image, the operating object recognizing unit may recognize the shoe as the operating object.

The process executing unit may determine whether or not a contact is detected by a contact sensor attached to the foot, and when the contact is detected by the contact sensor, the process executing unit may execute a process corresponding to the item selected based on a position of the foot.

The process executing unit may determine whether or not the operating object recognized by the operating object recognizing unit has stopped at substantially the same position for a predetermined time period, and when the process executing unit determines that the operating object has stopped at substantially the same position for the predetermined time period, the process executing unit may execute a process corresponding to the item selected based on a position of the operating object.

The superimposition display data storage unit may store other superimposition display data which is displayed subsequently to the superimposition display data. When the item is selected by the process executing unit, the superimposition display image generating unit may generate a new superimposition display image by further setting the other superimposition display data. When the item is selected by the process executing unit, the image superimposing unit may further superimpose the other superimposition display data on the new superimposition display image.

The operating object recognizing unit may recognize a hand imaged in the input image as the operating object.

The image superimposing unit may superimpose the superimposition display image on the visual field of the user and may cause a display unit to display the superimposition display image.

When the image superimposing unit detects, by using a sensor which detects the gradient of the imaging device, that a user wearing the imaging device on his/her head tilts the head in a downward direction at a gradient exceeding a predetermined value, the image superimposing unit may cause the display unit to display the superimposition display image, and when the image superimposing unit does not detect that a user wearing the imaging device on his/her head tilts the head in a downward direction at a gradient exceeding the predetermined value by using the sensor which detects the gradient of the imaging device, the image superimposing unit may restrict displaying the superimposition display image, the display being performed by the display unit.

The superimposition display position determining unit may determine, as the position of the object having the predetermined flat surface or curved surface, a position of an object having a flat surface that extends in a substantially horizontal direction.

The image processing device may further include a position estimating unit which estimates a position of a floor surface or a wall surface in the real space based on a position of a point on a surface of the object represented by the environment map. The superimposition display position determining unit may determine the position of the floor surface as the position of the object further based on the position of the floor surface or the wall surface estimated by the position estimating unit.

The feature data may include data indicating, for one or more points on the surface of each object, whether each point is likely to come in contact with the floor surface or the wall surface in the real space. The position estimating unit may estimate the position of the floor surface or the wall surface in the real space further based on the feature data.

Further, according to another embodiment of the present invention, there is provided an image processing method performed by an image processing device which includes a feature data storage unit which stores feature data indicating a feature of appearance of an object, a superimposition display data storage unit which stores superimposition display data which is to be a source of an image that is superimposed on a visual field of a user and an item position which is a position of an item forming the superimposition display data, an environment map generating unit, a superimposition display position determining unit, an image superimposing unit, an operating object recognizing unit, and a process executing unit, the image processing method including the steps of generating, by the environment map generating unit, an environment map representing a position of one or more objects existing in a real space based on an input image obtained by imaging the real space using an imaging device and the feature data stored in the feature data storage unit, determining, by the superimposition display position determining unit, a position of an object having a predetermined flat surface or curved surface out of an object imaged in the input image based on the environment map, generating, by the superimposition display image generating unit, a superimposition display image by setting the superimposition display data at the position of the object determined by the superimposition display position determining unit, superimposing, by the image superimposing unit, the superimposition display image on the visual field of the user, recognizing, by the operating object recognizing unit, an operating object imaged in the input image, and executing, by the process executing unit, a process corresponding to the item selected based on a position of the operating object recognized by the operating object recognizing unit.

Further, according to another embodiment of the present invention, there is provided a program for causing a computer to function as an image processing device which includes a feature data storage unit which stores feature data indicating a feature of appearance of an object, a superimposition display data storage unit which stores superimposition display data which is to be a source of an image that is superimposed on a visual field of a user and an item position which is a position of an item forming the superimposition display data, an environment map generating unit which generates an environment map representing a position of one or more objects existing in a real space based on an input image obtained by imaging the real space using an imaging device and the feature data stored in the feature data storage unit, a superimposition display position determining unit which determines a position of an object having a predetermined flat surface or curved surface out of an object imaged in the input image based on the environment map, a superimposition display image generating unit which generates a superimposition display image by setting the superimposition display data at the position of the object determined by the superimposition display position determining unit, an image superimposing unit which superimposes the superimposition display image on the visual field of the user, an operating object recognizing unit which recognizes an operating object imaged in the input image, and a process executing unit which executes a process corresponding to the item selected based on a position of the operating object recognized by the operating object recognizing unit.

According to the image processing device, the image processing method, and the program of the present embodiments described above, it is possible to facilitate the input of operation by the user in the configuration in which information is displayed, by the HMD, in a superimposed manner on a visual field of the user through the AR technology.

发表评论

电子邮件地址不会被公开。 必填项已用*标注