Apparatus and method for controlling electronic device

Patent metadata

Field	Value
Publication number	US-2021182545-A1
Application number	US-202016811723-A
Country	US
Kind code	A1
Filing date	Mar 6, 2020
Priority date	Dec 11, 2019
Publication date	Jun 17, 2021
Grant date	—

Abstract

A method for controlling, by a controller, an electronic device is provided. The method may include: sensing, by a sensor, a first radiation signal incident on the sensor; generating, by the sensor, a first output signal based on the first radiation signal; recognizing a human body based on the first output signal; determining a position of the human body as being located in one of an indoor space or an outdoor space based on the first output signal; and generating a control signal for controlling the electronic device connected via a wired or wireless network based on the position of the human body. A learning model includes a deep neural network generated through machine learning and transmission of a control signal may be performed in an Internet of Things (IoT) environment using a 5G network.

First claim

What is claimed is:

1 . A method for controlling an electronic device, the method comprising:
sensing, by a sensor of a controller, a first radiation signal incident on the sensor; generating, by the sensor, a first output signal based on the first radiation signal; recognizing, by a processor of the controller, a human body based on the first output signal; determining, by the processor, a position of the human body as being located in one of an indoor space or an outdoor space based on the first output signal; and generating, by the processor, a control signal for controlling the electronic device based on the position of the human body, wherein the controller is connected to the electronic device via a wired or wireless network.

2 . The method according to claim 1 , further comprising:
determining a distance between the sensor and the human body based on the first output signal; and determining the position of the human body based on the distance between the sensor and the human body.

3 . The method according to claim 1 , wherein the determining of the position of the human body further comprises:
detecting, in the first output signal, an echo reflected by a wall; detecting, in the first output signal, an echo reflected by the human body; and determining the position of the human body based on the echo reflected by the wall and the echo reflected by the human body.

4 . The method according to claim 1 , further comprising:
recognizing, by the processor, a boundary between the indoor space and the outdoor space based on the first output signal; and determining the position of the human body based on the boundary.

5 . The method according to claim 1 , further comprising:
sensing, by the sensor, a second radiation signal incident on the sensor before sensing the first radiation signal; generating, by the sensor, a second output signal based on the second radiation signal; recognizing, by the processor, a first floor area based on the second output signal; generating, by the processor, a floor model based on the recognized first floor area; and determining the position of the human body based on the floor model and the first output signal.

6 . The method according to claim 5 , further comprising:
sensing, by the sensor, a third radiation signal incident on the sensor after sensing the first radiation signal; generating, by the sensor, a third output signal based on the third radiation signal; recognizing, by the processor, a second floor area based on the third output signal; generating, by the processor, a temporary floor model based on the recognized second floor area; and changing, by the processor, the floor model based on the temporary floor model.

7 . The method according to claim 5 , further comprising recognizing the first floor area by applying, to the second output signal, a machine-learning-based learning model trained with training data in which floor images and non-floor images are distinguished from each other and labeled.

8 . The method according to claim 7 , further comprising:
determining, by the processor, whether an area that is not recognized as the first floor area is an object positioned in the first floor area in the second output signal; and generating, by the processor, the floor model including at least a part of the object positioned in the first floor area based on a result of determining whether the area that is not recognized as the first floor area is the object positioned in the first floor area.

9 . The method according to claim 5 , wherein the first output signal is an image signal of a bird's-eye view generated in response to the first radiation signal incident on the sensor, and
wherein the sensor is an array-type vision sensor having a wide-angle lens.

10 . A controller, comprising:
a sensor configured to sense a first radiation signal incident on the sensor; a processor; and a memory electrically connected to the processor, and configured to store codes executable by the processor, wherein, the memory stored codes are configured to, when executed by the processor, cause: the sensor to generate a first output signal based on the first radiation signal sensed by the sensor, and the processor to:
recognize a human body based on the first output signal,
determine a position of the human body as being located in one of an indoor space or an outdoor space based on the first output signal, and
generate a control signal for controlling an electronic device based on the position of the human body, and
wherein the controller is connected to the electronic device via a wired or wireless network.

11 . The controller according to claim 10 , wherein the memory further stores codes configured to, when executed by the processor, cause the processor to determine the position of the human body based on a boundary between the indoor space and the outdoor space recognized based on the first output signal.

12 . The controller according to claim 10 , wherein the sensor is configured to sense a second radiation signal before the first radiation signal is sensed, and
wherein the memory further stores codes configured to, when executed by the processor, cause:
the sensor to generate a second output signal based on the second radiation signal, and
the processor to:
generate a floor model based on a first floor area recognized based on the second output signal, and
determine the position of the human body based on the floor model and the first output signal.

13 . The controller according to claim 12 , wherein senor is configured to sense a third radiation signal after the first radiation signal, and
wherein the memory further stores codes configured to, when executed by the processor, cause:
the sensor to generate a third output signal based on the third radiation signal, and
the processor to:
generate a temporary floor model based on a second floor area recognized based on the third output signal, and
change the floor model based on the temporary floor model.

14 . The controller according to claim 12 , wherein the memory further stores codes configured to, when executed by the processor, cause the processor to recognize the first floor area by applying, to the second output signal, a machine-learning-based learning model trained with training data in which floor images and non-floor images are distinguished from each other and labeled.

15 . The controller according to claim 12 , wherein the memory further stores codes configured to, when executed by the processor, cause:
the sensor to generate an image signal of a bird's-eye view as the second output signal in response to the second radiation signal incident on the sensor, wherein the sensor is an array-type sensor having a wide-angle lens, and the processor to recognize the first floor area based on the second output signal.

16 . The controller according to claim 10 , wherein the controller has an outer surface with five faces connected to one another, and
wherein longitudinal extension lines of two adjacent faces among the five faces are perpendicular to each other.

17 . The controller according to claim 16 , further comprising:
a communication line configured to transmit the control signal; and a connector formed at one end of the communication line, wherein the memory further stores a code configured to, when executed by the processor, cause the processor to transmit the control signal to an external device connected to the connector via the communication line, and wherein the longitudina

Assignees

• Lg Electronics Inc

Inventors

• Chae Yeon Kyung
• Han Dongwoo
• Song Taeyup

Classifications

• G06V20/52

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title

• G06V10/82 Primary

  using neural networks · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06V40/10

  Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title