JP2019168740A5

JP2019168740A5 -

Info

Publication number: JP2019168740A5
Application number: JP2018053773A
Authority: JP
Filing date: 2018-03-22
Publication date: 2020-11-12
Anticipated expiration: 2038-03-22

Description

上記問題を解決するために、本発明のある観点によれば、利用者が操作する運用時の環境にある端末の一部または全部を写した映像を取得する映像取得部と、前記映像における対象領域を設定する領域設定部と、前記対象領域から特徴量を抽出する画像処理部と、前記特徴量を用いて追加学習を行う学習部と、前記追加学習の進捗度合いを取得する学習状況判断部と、前記進捗度合いを通知する通知部と、を備える、画像処理装置が提供される。
In order to solve the above problem, according to a certain viewpoint of the present invention, an image acquisition unit that acquires an image of a part or all of a terminal in an operating environment operated by a user, and an object in the image. An area setting unit that sets an area, an image processing unit that extracts a feature amount from the target area, a learning unit that performs additional learning using the feature amount, and a learning status determination unit that acquires the progress of the additional learning. An image processing apparatus is provided that includes a notification unit that notifies the degree of progress.

また、本発明の別の観点によれば、利用者が操作する運用時の環境にある端末の一部または全部を写した映像を取得することと、前記映像における対象領域を設定することと、前記対象領域から特徴量を抽出することと、前記特徴量を用いて追加学習を行うことと、前記追加学習の進捗度合いを取得することと、前記進捗度合いを通知することと、を含む、画像処理方法が提供される。
Further, according to another aspect of the present invention, it is possible to acquire an image of a part or all of a terminal in an operating environment operated by a user, set a target area in the image, and so on. An image including extracting a feature amount from the target area, performing additional learning using the feature amount, acquiring the progress degree of the additional learning, and notifying the progress degree. A processing method is provided.

また、本発明の別の観点によれば、コンピュータを、利用者が操作する運用時の環境にある端末の一部または全部を写した映像を取得する映像取得部と、前記映像における対象領域を設定する領域設定部と、前記対象領域から特徴量を抽出する画像処理部と、前記特徴量を用いて追加学習を行う学習部と、前記追加学習の進捗度合いを取得する学習状況判断部と、前記進捗度合いを通知する通知部と、を備える画像処理装置として機能させるためのプログラムが提供される。
Further, according to another viewpoint of the present invention, a video acquisition unit that acquires a video of a part or all of a terminal in an operating environment operated by a user and a target area in the video are defined. An area setting unit to be set , an image processing unit that extracts a feature amount from the target area, a learning unit that performs additional learning using the feature amount, and a learning status determination unit that acquires the progress of the additional learning. A program for functioning as an image processing device including a notification unit for notifying the degree of progress is provided.

また、本発明の別の観点によれば、利用者が操作する端末と、運用時の環境にある前記端末の一部または全部を写した映像を撮像するカメラと、画像処理装置と、を有する、画像処理システムであって、前記画像処理装置は、前記映像を取得する映像取得部と、前記映像における対象領域を設定する領域設定部と、前記対象領域から特徴量を抽出する画像処理部と、前記特徴量を用いて追加学習を行う学習部と、前記追加学習の進捗度合いを取得する学習状況判断部と、前記進捗度合いを通知する通知部と、を備える、画像処理システムが提供される。 Further, according to another aspect of the present invention, the present invention includes a terminal operated by the user, a camera that captures an image of a part or all of the terminal in the operating environment, and an image processing device. In the image processing system, the image processing device includes a video acquisition unit that acquires the video, an area setting unit that sets a target area in the video, and an image processing unit that extracts a feature amount from the target area. Provided is an image processing system including a learning unit that performs additional learning using the feature amount, a learning status determination unit that acquires the progress degree of the additional learning, and a notification unit that notifies the progress degree. ..

Claims

A video acquisition unit that acquires video that captures part or all of the terminals in the operating environment operated by the user,
An area setting unit that sets the target area in the video,
An image processing unit that extracts features from the target area,
A learning unit that performs additional learning using the features, and
The learning status judgment unit that acquires the progress of the additional learning,
A notification unit that notifies the degree of progress,
An image processing device.

The learning unit uses deep learning as the additional learning.
The image processing apparatus according to claim 1.

The image acquisition unit acquires the image by capturing the image captured and stored in advance or the image captured by the camera.
The image processing apparatus according to claim 1.

The image processing device includes a recognition processing unit that performs recognition processing using the classifier obtained by the additional learning.
The image processing apparatus according to claim 1.

The recognition processing unit changes the recognition result by the recognition process or the notification destination of the recognition result according to the progress of the additional learning.
The image processing apparatus according to claim 4.

The area setting unit sets a plurality of target areas and sets a plurality of target areas.
The image processing unit extracts the feature amount for each target area, and then extracts the feature amount.
The learning unit performs the additional learning for each target area using the feature amount, and then performs the additional learning.
The learning situation determination unit acquires the progress of the additional learning for each target area.
The image processing apparatus according to claim 1.

The learning unit performs pre-learning based on the teacher data and the learning data before the additional learning, and performs the additional learning using the learning result obtained by the pre-learning and the feature amount.
The image processing apparatus according to claim 1.

The area setting unit sets the target area based on the area information of another terminal having the same or similar structure as the terminal.
The image processing apparatus according to claim 1.

The area setting unit sets the target area based on the movement of the moving image at a predetermined timing.
The image processing apparatus according to claim 1.

The area setting unit specifies the predetermined timing based on the update timing of the status information of the terminal.
The image processing apparatus according to claim 9.

The area setting unit identifies a region of the moving image that has moved at the predetermined timing, and sets the target region based on the region that has moved.
The image processing apparatus according to claim 9.

The area setting unit learns a moving image at the predetermined timing, generates a learning model capable of estimating the movement of the user at the predetermined timing, and uses the detected moving image based on the learning model and the moving image. The target area is set based on the place where the person moves.
The image processing apparatus according to claim 9.

The area setting unit identifies a place where the presence or absence of the object has changed from the moving image based on the feature amount of the object inserted or ejected into the terminal, and sets the target area based on the place. To do
The image processing apparatus according to claim 1.

Acquiring a video showing a part or all of the terminals in the operating environment operated by the user,
Setting the target area in the video and
Extracting the feature amount from the target area and
Performing additional learning using the features,
Acquiring the progress of the additional learning and
Notifying the degree of progress and
Image processing methods, including.

Computer,
A video acquisition unit that acquires video that captures part or all of the terminals in the operating environment operated by the user,
An area setting unit that sets the target area in the video,
An image processing unit that extracts features from the target area,
A learning unit that performs additional learning using the features, and
The learning status judgment unit that acquires the progress of the additional learning,
A notification unit that notifies the degree of progress,
A program for functioning as an image processing device.

An image processing system including a terminal operated by a user, a camera that captures an image of a part or all of the terminal in an operating environment, and an image processing device.
The image processing device is
A video acquisition unit that acquires the video and
An area setting unit that sets the target area in the video,
An image processing unit that extracts features from the target area,
A learning unit that performs additional learning using the features, and
The learning status judgment unit that acquires the progress of the additional learning,
A notification unit that notifies the degree of progress,
An image processing system.