JP2000137160A - Image pickup device and method therefor, and storage medium capable of being read by computer - Google Patents

Abstract

PROBLEM TO BE SOLVED: To make settable an image pickup parameter of camera by the speech input of an easy demonstrative. SOLUTION: An operator sounds easy demonstratives such as 'that', 'it' and 'this' while viewing an image in order to select a desired subject out of the images picked up by a camera part 104. A camera system controller 112 detects the demonstrative from the inputted speech, selects a distance between the detected demonstrative and the corresponding subject by using a correspondence table 113 making the demonstrative correspond to a selected candidate, decides the image pickup parameter such as a focal distance, zoom magnification and pan and tilt speed in accordance with the selected distance and controls the camera part 14 based on the parameter.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image pickup apparatus and method suitable for use in an image pickup system or the like in which optical and geometrical image pickup parameters at the time of image pickup can be freely controlled by a computer, and a computer-readable image pickup apparatus used therefor It relates to a simple storage medium.

[0002]

2. Description of the Related Art As a conventional image pickup apparatus, an input voice is recognized and converted into a voice command.
A technique has been put to practical use in which a geometric imaging parameter is freely controlled by a computer and a change in an image is detected by image processing to keep track of a specific subject as needed. Further, when operating the camera system, conventionally, the operator directly operates the camera system using a keyboard or switches.

[0003]

However, it is difficult for the operator to operate the keyboard and switches when the operator is located at a distance from the camera system or when the operator himself is the subject. . Therefore, if the operation command is transmitted to the system by voice, it is not necessary to consider the distance between the operator and the system. However, specifying various shooting parameters by voice is redundant for the operator, and it is difficult for the operator. There was a problem.

The present invention has been made in order to solve the above-mentioned problems. In response to an operator's instruction with simple voice, a desired subject can be selected accurately, and imaging parameters such as zoom, focus, and pan / tilt can be obtained. The purpose is to be able to set.

[0005]

In order to achieve the above object, in an image pickup apparatus according to the present invention, an image pickup means for picking up an image of a subject, a sound input means for inputting sound, and a predetermined signal from the input sound. Position estimating means for detecting the instruction word of the above, and estimating a relative positional relationship with the subject based on the detected instruction word; determining means for determining an imaging parameter according to the estimated relative positional relationship; Control means for controlling the imaging means according to the obtained imaging parameters.

In the imaging method according to the present invention,
A voice input procedure of inputting voice, a position estimation procedure of detecting a predetermined instruction word from the input voice, and estimating a relative positional relationship with the subject based on the detected instruction word; A determination procedure for determining an imaging parameter according to a positional relationship and a control procedure for controlling the imaging unit in accordance with the determined imaging parameter are provided.

Further, in the storage medium according to the present invention, a voice input process for inputting voice, a predetermined instruction word is detected from the input voice, and a relative positional relationship with the subject is determined based on the detected instruction word. And a control process of controlling the imaging unit in accordance with the determined imaging parameter, and a control process of determining the imaging parameter according to the estimated relative positional relationship. I remember the program.

[0008]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram illustrating an imaging device 105 according to an embodiment of the present invention. This imaging device 10
No. 5 is characterized by estimating a relative positional relationship with a subject using a simple short instruction word. The imaging device 105 includes:
Camera system 101 and camera system controller 112
Consisting of The camera system control device 112 is connected to a microphone 116 for inputting voice and a telephone 114 via a telephone network 115.

The camera system 101 includes the following units 102
~ 104. Optical parameter control unit 102: Controls optical parameters of the camera such as focus and zoom. Azimuth parameter control unit 103... Controls the azimuth parameters of the camera and controls movement such as pan and tilt. Camera section 104.........

The camera system controller 112 comprises the following units 106 to 113. Voice capturing unit 106..., Telephone network 115
Audio from an external audio input device such as a microphone or a microphone 116. Voice recognition unit 107 Voice capture unit 10
The speech waveform obtained from step 6 is converted to text. I / O unit 108 Camera system 1
01 and communicates. Descriptive word interpreter 109 ······ Speech recognition unit 107
The relative position with respect to the subject is estimated from the instruction word of the input voice command.

Control parameter generation unit 110: A parameter for controlling an actual camera is calculated from a command from the voice recognition unit 107, distance information from the descriptive word interpretation unit 109, and an evaluation value from the image evaluation unit 111. Image evaluation unit 111: An image captured by the camera unit 104 is obtained via the I / O unit 108 and evaluated. The evaluation obtained here affects the control parameters at the time of the next imaging. Descriptive Word and Selection Candidate Correspondence Table 113...

Next, the operation of the image pickup apparatus 105 according to the first embodiment having the above configuration will be described with reference to the flowchart of FIG. Here, a case will be described as an example in which a plurality of cars are present in the field of view of the camera, and an image is taken by focusing on one of the cars. Importing an image (201) ... First, an image in the camera's field of view is imported. For example, assume that three cars, red, yellow, and blue, are in the camera's field of view. Creation of subject candidate (202) ... Import of the above image (2)
The image obtained in step (01) is analyzed by the image evaluation unit 111, and a pair of a candidate object name of a focus candidate and a distance to the object is created from within the image. Here, the distance to the red car = 5
0m, distance to yellow car = 20m, distance to blue car = 5
m.

Voice capture (203)... Voice voice generated by the operator is captured. It is assumed that the operator utters “this car”. Voice Recognition (204) ... Voice capture (20)
Recognize the voice waveform obtained in 3) and make it a voice command. End determination (205) ... The above speech recognition (20
If the result of 4) indicates an end command, the system ends.

[0014] Judgment by a directive (206 to 210)
-Detect a directive included in the voice command and select a subject using a correspondence table between the directive and the selection candidate as shown in FIG. In this example, the blue car closest to “this” is selected as the subject. Imaging (211) ... The selected subject is imaged with a focal length of 5 m. Also, if the operator says “the car”, a yellow car is selected,
If you say "that car", a red car will be selected.

Next, a second embodiment will be described. In the present embodiment, even when an object to be a focus candidate is not present in an image captured before imaging, it is possible to estimate a position by preparing a correspondence table as shown in FIG.

Next, an example of the operation of the camera system 101 and the operator will be described. System: The camera captures an image in the field of view of the camera, but no specific object is shown, and no focus candidate can be created. Operator: Say "around here". System: There is no “hit” candidate in the image captured before imaging. For this reason, the focal length is estimated to be 5 m from "this" from the correspondence table between the instruction word and the selection candidate in FIG.

Next, a third embodiment will be described. In the present embodiment, since the focal length can be estimated by the instruction word, it is possible to determine the initial zoom ratio and the initial pan / tilt speed using the estimated distance information.

An example of the operation will be described below. System: The camera captures an image in the field of view of the camera, but no specific object is shown, and no focus candidate can be created. Operator: Speak “over” System: Based on the correspondence table between the instruction word and each imaging parameter in FIG. 5, the imaging parameters are set as “focal length = 20 m, default pan / tilt speed = low, default zoom ratio = large” from “over”. Initialize and perform imaging.

Next, a storage medium according to the present invention will be described. The system according to the embodiment of FIG. 1 may be configured as hardware, or may be configured as a computer system including a CPU, a memory, and the like. When configured in a computer system, the memory forms a storage medium according to the present invention. The storage medium stores a program for executing the processing according to the flowchart of FIG. 2 and the processing according to each embodiment.

Further, as the storage medium, ROM, R
Semiconductor memory such as AM, optical disk, magneto-optical disk,
A magnetic storage medium or the like may be used, and these may be a CD-ROM,
The present invention may be applied to an FD, a magnetic card, a magnetic tape, a nonvolatile memory card, or the like.

Therefore, this storage medium is used in a system or apparatus other than the system according to the above embodiment,
By reading and executing the program code stored in the storage medium by the system or the computer, the same functions as those of the above embodiment can be realized, and the same effects can be obtained. Can be achieved.

An OS running on the computer
When performing part or all of the processing, or after the program code read from the storage medium is written to a memory provided in an extended function board or an extended function unit connected to the computer, Even when the CPU or the like provided in the extended function board or the extended function unit performs a part or all of the processing based on the instruction of the program code, the same functions as those of the above embodiment can be realized and the same effects can be obtained. Can be obtained, and the object of the present invention can be achieved.

[0023]

As described above, according to the present invention,
It is possible to set imaging parameters using short intuitive and simple directives such as "this, that, that", "this, that, that", "here, there, there", etc. Will be better. In addition, since it is not necessary to strictly specify each imaging parameter, even if the operator cannot directly operate the system, the imaging parameters such as the focal length of the camera, zoom magnification, pan / tilt speed, etc. can be controlled with simple voice input. To perform high-level tasks such as

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating an imaging apparatus according to an embodiment of the present invention.

FIG. 2 is a flowchart showing an operation according to the first embodiment of the present invention.

FIG. 3 is a configuration diagram illustrating an example of a correspondence table between a descriptive word and a selection candidate;

FIG. 4 is a configuration diagram illustrating an example of a correspondence table between an instruction word and an estimated position;

FIG. 5 is a configuration diagram illustrating an example of a correspondence table between an instruction word and each imaging parameter.

[Explanation of symbols]

 Reference Signs List 101 camera system 102 optical parameter control unit 103 azimuth parameter control unit 104 camera unit 105 imaging device 106 voice capture unit 107 voice recognition unit 108 I / F unit 109 descriptive word interpretation unit 110 control parameter generation unit 111 image evaluation unit 112 camera system Control device 113 Descriptive word and selection candidate correspondence table 114 Telephone 115 Telephone network 116 Microphone

 ──────────────────────────────────────────────────続 き Continued on the front page F term (reference) 2H011 AA01 AA06 CA21 DA00 2H044 DA01 DA02 DC02 DC06 DE01 2H051 DD05 EB13 EB20 EC01 FA49 GB11 GB15 2H104 AA16

Claims (15)

[Claims] An imaging unit configured to capture an image of a subject; a voice input unit configured to input a voice; a predetermined instruction word detected from the input voice; and a relative position with respect to the subject based on the detected instruction word. Position estimating means for estimating the relationship; determining means for determining an imaging parameter according to the estimated relative positional relationship; and control means for controlling the imaging means according to the determined imaging parameter. An imaging device characterized by the above-mentioned. 2. The apparatus according to claim 1, wherein said determining means determines a focal length according to said estimated relative positional relationship, and said control means controls said imaging means to said determined focal length. Item 2. The imaging device according to Item 1. 3. The method according to claim 1, wherein the determining unit determines a zoom magnification according to the estimated relative positional relationship.
2. The imaging apparatus according to claim 1, wherein the imaging unit is controlled to the determined zoom magnification. 4. The apparatus according to claim 1, wherein said determining means determines a pan / tilt speed in accordance with said estimated relative positional relationship, and said control means controls said imaging means to said determined pan / tilt speed. Item 2. The imaging device according to Item 1. 5. The imaging apparatus according to claim 1, wherein the determination unit has a table in which a plurality of imaging parameters are described in correspondence with the plurality of instruction words. 6. A voice input procedure for inputting voice, a position estimation procedure for detecting a predetermined instruction word from the input voice and estimating a relative positional relationship with a subject based on the detected instruction word; An imaging method, comprising: a determination procedure for determining an imaging parameter according to the estimated relative positional relationship; and a control procedure for controlling an imaging unit in accordance with the determined imaging parameter. 7. The method according to claim 7, wherein the determining step determines a focal length according to the estimated relative positional relationship, and the controlling step controls the imaging unit to the determined focal length. Item 7. The imaging method according to Item 6. 8. The determining step determines a zoom magnification according to the estimated relative positional relationship, and the controlling step includes:
7. The imaging method according to claim 6, wherein the imaging unit is controlled to the determined zoom magnification. 9. The method according to claim 1, wherein the determining step determines a pan-tilt speed according to the estimated relative positional relationship, and the control step controls the imaging unit to the determined pan-tilt speed. Item 7. The imaging method according to Item 6. 10. The imaging method according to claim 6, wherein the determining step uses a table in which a plurality of imaging parameters are described in correspondence with the plurality of instruction words. 11. A voice input process for inputting voice, a position estimation process for detecting a predetermined instruction word from the input voice and estimating a relative positional relationship with a subject based on the detected instruction word; Computer-readable storage storing a program for executing a determination process of determining an imaging parameter according to the estimated relative positional relationship, and a control process of controlling an imaging unit in accordance with the determined imaging parameter. Medium. 12. The determining process determines a focal length according to the estimated relative positional relationship.
12. The computer-readable storage medium according to claim 11, wherein the imaging unit is adjusted to the determined focal length. 13. The method according to claim 12, wherein the determining process determines a zoom magnification according to the estimated relative positional relationship, and the control process controls the imaging unit to the determined zoom magnification. Item 12. A computer-readable storage medium according to item 11. 14. The method according to claim 1, wherein the determining process determines a pan-tilt speed according to the estimated relative positional relationship, and the control process controls the imaging unit to the determined pan-tilt speed. Item 12. A computer-readable storage medium according to item 11. 15. The computer-readable storage medium according to claim 11, wherein the determination process uses a table in which a plurality of imaging parameters are described in correspondence with the plurality of instruction words.