METHOD AND APPARATUS FOR WORK QUALITY CONTROL

• US 20160253618A1
• Filed: 12/09/2015
• Published: 09/01/2016
• Est. Priority Date: 02/26/2015
• Status: Active Grant

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: IMAZAWA, Kei, HAMAMURA, Yuichi, TANAKA, Shigenori, TADA, Kouichirou, MOMOSE, Isamu, FUKAYA, Yusaku
• Granted Patent: US 10,614,391 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/2433 Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
• CPC Class Codes: G06F 18/29 Graphical models, e.g. Bayesian networks
• CPC Class Codes: G06Q 10/063114 Status monitoring or status determination for a person or group
• CPC Class Codes: G06Q 10/06395 Quality analysis or management
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06T 7/77 using statistical methods
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/84 using probabilistic graphical models from image or video features, e.g. Markov models or Bayesian networks
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

A method for work quality control of a worker in work where repetitive operation is performed which includes: a model construction step of statistically constructing, from past path data of the worker, past intermediate quality data on a product to be subjected to the work, and past final quality data on the product to be subjected to the work, a prediction model that receives the path data and the intermediate quality data and outputs the final quality data; a worker position recognition step of recognizing a position of the worker from image data on the work captured; and an unusual worker position determining step of substituting the position of the worker recognized in the worker position recognition step into the model constructed in the model construction step, to determine whether the position of the target worker is a usual one or an unusual one.

Claims

1. A method for work quality control of a worker in work where repetitive operation is performed, the method comprising:

an image data acquisition step of acquiring image data on the work captured;

a worker position recognition step of recognizing a position of the worker from the image data;

a prediction model construction step of acquiring a prediction model that is statistically constructed from past path data on the worker, past intermediate quality data, and past final quality data; and

an unusual worker position determining step of substituting the position of the worker recognized in the worker position recognition step into the prediction model to determine whether a position of a target worker is a usual position or an unusual position.

2. The method for work quality control according to claim 1, wherein

the path data on the worker used for model construction in the model construction step contains path data on a center of gravity, a head position or a joint position of the worker, and

in the worker position recognition step, the center of gravity, the head position, or the joint position of the worker is recognized as the position of the worker.

3. The method for work quality control according to claim 1, wherein

the determination of unusualness is performed using an unusualness degree, and further comprising

a step of displaying the unusualness degree.

4. An apparatus for work quality control of a worker in work where repetitive operation is performed, the apparatus comprising:

a DB unit and an engine unit, wherein

the DB unit includes image data on the work captured, and

a prediction model that is statistically constructed from past path data on the worker, past intermediate quality data, and past final quality data, and

the engine unit performs;

an image data acquisition step of acquiring the image data on the work captured;

a worker position recognition step of recognizing a position of the worker from the image data;

a prediction model construction step of acquiring a prediction model that is statistically constructed from the past path data on the worker, the past intermediate quality data, and the past final quality data; and

an unusual worker position determining step of substituting the position of the worker recognized in the worker position recognition step into the prediction model to determine whether a position of a target worker is a usual position or an unusual position.

5. The apparatus for work quality control according to claim 4, wherein

the path data on the worker used for model construction in the model construction step contains path data on a center of gravity, a head position, or a joint position of the worker, and

in the worker position recognition step, the center of gravity, the head position, or the joint position of the worker is recognized as the position of the worker.

6. The apparatus for work quality control according to claim 4, wherein

the engine unit performs the determination of unusualness using an unusualness degree and performs a step of causing a display device to display an unusualness degree transition display screen that displays the unusualness degree.