Human interface system using a plurality of sensors

• US 6,686,844 B2
• Filed: 01/08/2003
• Issued: 02/03/2004
• Est. Priority Date: 02/23/2001
• Status: Expired due to Term

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Watanabe, Kazuhiro, Watanabe, Masaki, Murase, Kentaro, Noda, Takuya
• Primary Examiner(s): Hofsass, Jeffery
• Assistant Examiner(s): TANG, SON M
• Application Number:
  US10/337,818
• Publication Number:
  US 20030097190A1
• Time in Patent Office: 391 Days
• Field of Search: 340/573.1, 340/573.7, 340/686.1, 340/5.1
• US Class Current: 340/573.1
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition

Abstract

An image sensor, a voice sensor, an auxiliary sensor part (infrared sensor, etc.), a total analyzing part, and an application communicate with each other through data/control signal communication units. Each sensor provides feedback on its signal detection results and control information used by the other sensors for determining a range of a detection target and a detection sensitivity at a time of subsequent signal acquisition, to the other sensors through the communication units. The total analyzing part investigates whether or not there is inconsistency among the results detected by the respective sensors, and provide control information to each sensor. Each sensor determines a range of a signal detection target and a detection sensitivity based on the obtained information, and acquires a signal in accordance with the determination.

Claims

1. A human interface processing method using a plurality of sensors, comprising:

at least two kinds of sensor processings, each determining a range of a detection target and a detection sensitivity and acquiring a particular detection signal from the detection target at the detection sensitivity, the respective detection signals acquired by the sensor processings being of different types;

total analyzing processing, investigating whether or not there is inconsistency among signal detection results detected by the respective sensor processings, and generating control information for the respective sensor processings;

application processing utilizing the signal detection results obtained by the respective sensor processings; and

communication processing communicating data and control information between the respective sensor processings, between the respective sensor processings and the total analyzing processing, and between the total analyzing processing and the application processing, wherein each of the sensor processings uses either of, or a combination of;

the signal detection results or control information obtained from the other sensor processings, and

the control information obtained from the total analyzing processing,

thereby determining a range of a detection target and a detection sensitivity at a time of subsequent signal acquisition;

each of the sensor processings outputs its signal detection results, and control information used by the other sensor processings to determine a range of a detection target and a detection sensitivity at a time of subsequent signal acquisition to the other sensor processings through the communication processing, and

the total analyzing processing outputs control information used by each of the sensor processings to determine a range of a detection target and a detection sensitivity at a time of subsequent signal acquisition through the communication processings.

2. A human interface processing method using a plurality of sensors according to claim 1, wherein the detection target is a human being, and the sensor processings include at least image sensor processing and voice sensor processing,

a detection signal of the image sensor processing is human recognition information,

the image sensor processing includes action recognition processing for interpreting an action of the detection target based on picture recognition results and recognizing a command inputted through a gesture,

a detection signal of the voice sensor processing is human voice recognition information, and

the voice sensor processing includes voice recognition processing for interpreting a voice of the detection target based on voice recognition results and recognizing a command inputted through a voice.

3. A human interface processing method using a plurality of sensors according to claim 1, wherein:

the detection target is a human being;

the sensor processings include at least image sensor processing and auxiliary sensor processing;

a detection signal of the image sensor processing is human picture recognition information;

the image sensor processing includes action recognition processing interpreting an action of the detection target based on picture recognition results and recognizing a command inputted through a gesture; and

a detection signal of the auxiliary sensor processing is information useful for detecting human position information.

5. A human interface processing method using a plurality of sensors according to claim 1, wherein the detection target is a human being, and:

the sensor processings include at least voice sensor processing and auxiliary sensor processing;

a detection signal of the voice sensor processing inhuman voice recognition information;

the voice sensor processing includes voice recognition processing for interpreting a voice of the detection target based on voice recognition results and recognizing a command inputted through a voice; and

a detection signal of the auxiliary sensor processing is information useful for detecting human position information.

7. A human interface processing method using a plurality of sensors according to claim 1, wherein the detection target is a human being, and:

the sensor processings include at least image sensor processing, voice sensor processing, and auxiliary sensor processing;

a detection signal of the image sensor processing is human picture recognition information;

the image sensor processing includes action recognition processing interpreting an action of the detection target based on picture recognition results and recognizing a command inputted through a gesture; and

a detection signal of the voice sensor processing is human voice recognition information;

the voice sensor processing includes voice recognition processing interpreting a voice of the detection target based on voice recognition results and recognizing a command input by a voice input; and

a detection signal of the auxiliary sensor processing is information useful for detecting human position information.

4. A human interface processing method using a plurality of sensors according 3, wherein one of, or a combination of, ultrasonic sensor processing, infrared sensor processing, and range sensor processing is used as the auxiliary sensor processing.

6. A human interface processing method using a plurality of sensors according 5, wherein either of, or a combination of, ultrasonic sensor processing, infrared sensor processing, and range sensor processing is used as the auxiliary sensor processing.

8. A human interface processing method using a plurality of sensors according 7, wherein one of, or a combination of, ultrasonic sensor processing, infrared sensor processing, and range sensor processing is used as the auxiliary sensor processing.