# US 2018/0025233 A1 · Image-capturing device, recording device, and video output control device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2018/0025233 A1 - Document ID: US20180025233A1 - Status: Published application - Kind: A1 - Application number: 15/556,106 - Filed: 2016-03-03 - Published: 2018-01-25 - Earliest claimed: 2015-03-19 - Assignees: Panasonic Intellectual Property Management Co., Ltd. - Applicants: Panasonic Intellectual Property Management Co., Ltd. - Inventors: Kazuhiko IWAI - Web page: https://patentgrep.com/patent/US20180025233A1 ## CPC - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - G06V 40/161: {Detection; Localisation; Normalisation} - G06V 40/165: {using facial parts and geometric relationships} - G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16) - H04N 5/77: between a recording apparatus and a television camera - H04N 5/915: for field- or frame-skip recording or reproducing - H04N 7/18: Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast - H04N 21/431: Generation of visual interfaces {for content selection or interaction}; Content or additional data rendering - H04N 23/00: Cameras or camera modules comprising electronic image sensors; Control thereof - H04N 23/611: where the recognised objects include parts of the human body - G06V 40/178: {estimating age from face image; using age information for improving recognition} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract A positional information acquirer acquires positional information for every person from a video, an attribute information acquirer acquires attribute information for every person from the video, and an activity information acquirer restricts activity information to an attribute designated by a user based on the attribute information and the positional information, and acquires the activity information of which the attribute is restricted. An activity map generator generates an activity map of which an attribute is restricted based on the activity information, and a video output outputs a video acquired by superimposing the activity map. A controller determines appropriateness indicating whether or not the video output from the imager is appropriate, enables a function of outputting the activity map of which the attribute is restricted, and disables the function of outputting the activity map of which the attribute is restricted where the video output from the imager does not have the appropriateness. ## Claims ### Claim 1 An image-capturing device that images a monitoring area, and outputs a video of the monitoring area to a browsing device, the device comprising: an imager that images the monitoring area, and outputs the video of the monitoring area according to an imaging mode; an input setter that sets the imaging mode and an attribute of a person in response to an operation input of a user; a positional information acquirer that detects persons from the video, and acquires positional information for every person; an attribute information acquirer that detects persons from the video, determines an attribute for every person, and acquires attribute information for every person; an activity information acquirer that restricts activity information corresponding to a position within the monitoring area to the attribute set by the input setter based on the attribute information and the positional information, and acquires the activity information of which the attribute is restricted; an activity map generator that generates an activity map of which the attribute is restricted based on the activity information; a video output unit that generates a video acquired by superimposing the activity map on the video of the monitoring area, and outputs the generated video; and a controller that performs control related to an output of the activity map, wherein the controller determines appropriateness indicating whether or not the video output from the imager according to the imaging mode is appropriate in acquiring the attribute information, enables a function of outputting the activity map of which the attribute is restricted in a case where it is determined that the video output from the imager has the appropriateness, and disables the function of outputting the activity map of which the attribute is restricted in a case where it is determined that the video output from the imager does not have the appropriateness. ### Claim 2 (depends on 1) The image-capturing device of claim 1, wherein, in a case where it is determined that the video output from the imager does not have the appropriateness, the controller causes the activity information acquirer to acquire activity information of which an attribute is not restricted, causes the activity map generator to generate an activity map of which the attribute is not restricted, and causes the video output unit to output a video acquired by superimposing the activity map of which the attribute is not restricted on the video of the monitoring area. ### Claim 3 (depends on 1) The image-capturing device of claim 1, wherein the imager images the monitoring area through a fisheye lens, outputs a fisheye video, and outputs a correction video acquired by performing distortion correction on the fisheye video, and the controller determines that the video output from the imager does not have the appropriateness in a case where the video output from the imager is only the fisheye video. ### Claim 4 (depends on 1) The image-capturing device of claim 1, wherein the imager images the monitoring area through a fisheye lens, outputs a fisheye video, and outputs a correction video acquired by performing distortion correction on the fisheye video, and the controller determines that the video output from the imager has the appropriateness in a case where the video output from the imager includes the correction video. ### Claim 5 An image-capturing device that images a monitoring area, and outputs a video of the monitoring area to a browsing device, the device comprising: an imager that outputs a first unprocessed video acquired by imaging the monitoring area and a second video acquired by cutting a part of the first video and performing distortion correction on the cut part according to an imaging mode; an input setter that sets the imaging mode and an attribute of a person in response to an operation input of a user; a positional information acquirer that detects persons from the first video, and acquires positional information on the first video for every person; an attribute information acquirer that detects persons from the second video, determines an attribute for every person, and acquires attribute information for every person; an identification processor that performs a process of correlating the positional information and the attribute information with each person; an activity information acquirer that restricts activity information corresponding to a position within the monitoring area to the attribute set by the input setter based on the positional information and the attribute information correlated by the identification processor, and acquires the activity information of which the attribute is restricted; an activity map generator that generates an activity map of which the attribute is restricted based on the activity information; and a video output unit that generates a video acquired by superimposing the activity map on the first video, and outputs the generated video. ### Claim 6 (depends on 5) The image-capturing device of claim 5, wherein the positional information acquirer correlates the positional information for every person with detection time information on the first video for every person, and acquires the correlated positional information, the attribute information acquirer correlates the attribute information for every person with positional information and detection time information on the second video, and acquires the correlated attribute information, and the identification processor performs a process of correlating the positional information and the attribute information with each person based on the positional information and the detection time information respectively acquired by the positional information acquirer and the attribute information acquirer. ### Claim 7 (depends on 5) The image-capturing device of claim 5, wherein the imager outputs, as the first video, a fisheye video acquired by imaging a monitoring area through a fisheye lens, cuts videos of a plurality of target areas set in response to an operation input of a user from the first video, performs distortion correction on the plurality of videos, and outputs, as the second video, a plurality of correction videos acquired through the distortion correction. ### Claim 8 A recording device that accumulates a video output from an image-capturing device, and outputs the video to a browsing device, the device comprising: a video input unit that receives the video, which is acquired by the image-capturing device which images the monitoring area, from the image-capturing device according to an imaging mode; a video accumulator that accumulates the video received by the video input unit; an input setter that sets the imaging mode and an attribute of a person in response to an operation input of a user; a positional information acquirer that detects persons from the video accumulated in the video accumulator, and acquires positional information for every person; an attribute information acquirer that detects persons from the video accumulated in the video accumulator, determines an attribute for every person, and acquires attribute information for every person; an activity information acquirer that restricts activity information corresponding to a-position within the monitoring area to the attribute set by the input setter based on the attribute information and the positional information, and acquires the activity information of which the attribute is restricted; an activity map generator that generates an activity map of which the attribute is restricted based on the activity information; a video output unit that generates a video acquired by superimposing the activity map on the video of the monitoring area, and outputs the generated video; and a controller that performs control related to an output of the activity map, wherein the controller determines appropriateness indicating whether or not the video output from the image-capturing device according to the imaging mode is appropriate in acquiring the attribute information, enables a function of outputting the activity map of which the attribute is restricted in a case where it is determined that the video output from the image has the appropriateness, and disables the function of outputting the activity map of which the attribute is restricted in a case where it is determined that the video output from the imager does not have the appropriateness. ### Claim 9 A recording device that accumulates a video output from an image-capturing device, and outputs the video to a browsing device, the device comprising: a video input unit that receives a first unprocessed video, which is acquired by the image-capturing device which images a monitoring area, and a second video, which is acquired by the image-capturing device that cuts a part of the first video and performs distortion correction on the cut part, from the image-capturing device according to an imaging mode; a video accumulator that accumulates the first video and the second video received by the video input unit; an input setter that sets the imaging mode and an attribute of a person in response to an operation input of a user; a positional information acquirer that detects persons from the first video, and acquires positional information on the first video for every person; an attribute information acquirer that detects persons from the second video, determines an attribute for every person, and acquires attribute information for every person; an identification processor that performs a process of correlating the positional information and the attribute information with each person; an activity information acquirer that restricts activity information corresponding to a position within the monitoring area to the attribute set by the input setter based on the positional information and the attribute information correlated by the identification processor, and acquires the activity information of which the attribute is restricted; an activity map generator that generates an activity map of which the attribute is restricted based on the activity information; a video output unit that generates a video acquired by superimposing the activity map on the first video, and outputs the generated video. ### Claim 10 A video output control device that is connected to an image-capturing device, and controls an output of a video to a browsing device, the device comprising: a video input unit that receives a video, which is acquired by the image-capturing device which images a monitoring area, from the image-capturing device according to an imaging mode; an input setter that sets the imaging mode and an attribute of a person in response to an operation input of a user; a positional information acquirer that detects persons from the video received by the video input unit, and acquires positional information for every person; an attribute information acquirer that detects persons from the video received by the video input unit, determines an attribute for every person, and acquires attribute information for every person; an activity information acquirer that restricts activity information corresponding to a position within the monitoring area to the attribute set by the input setter based on the attribute information and the positional information, and acquires the activity information of which the attribute is restricted; an activity map generator that generates an activity map of which the attribute is restricted based on the activity information; a video output unit that generates a video acquired by superimposing the activity map on the video of the monitoring area, and outputs the generated video; and a controller that performs control related to an output of the activity map, wherein the controller determines appropriateness indicating whether or not the video output from the image-capturing device according to the imaging mode is appropriate in acquiring the attribute information, enables a function of outputting the activity map of which the attribute is restricted in a case where it is determined that the video output from the imager has the appropriateness, and disables the function of outputting the activity map of which the attribute is restricted in a case where it is determined that the video output from the imager does not have the appropriateness. ### Claim 11 A video output control device that is connected to an image-capturing device, and controls an output of a video to a browsing device, the device comprising: a video input unit that receives a first unprocessed video, which is acquired by the image-capturing device which images a monitoring area, and a second video, which is acquired by the image-capturing device which cuts a part of the first video and performs distortion correction on the cut part, from the image-capturing device according to an imaging mode; an input setter that sets the imaging mode and an attribute of a person in response to an operation input of a user; a positional information acquirer that detects persons from the first video received by the video input unit, and acquires positional information on the first video for every person; an attribute information acquirer that detects persons from the second video received by the video input unit, determines an attribute for every person, and acquires attribute information for every person; an identification processor that performs a process of correlating the positional information and the attribute information with each person; an activity information acquirer that restricts activity information corresponding to a position within the monitoring area to the attribute set by the input setter based on the positional information and the attribute information correlated by the identification processor, and acquires the activity information of which the attribute is restricted; an activity map generator that generates an activity map of which the attribute is restricted based on the activity information; a video output unit that generates a video acquired by superimposing the activity map on the first video, and outputs the generated video. ### Claim 12 (depends on 2) The image-capturing device of claim 2, wherein the imager images the monitoring area through a fisheye lens, outputs a fisheye video, and outputs a correction video acquired by performing distortion correction on the fisheye video, and the controller determines that the video output from the imager does not have the appropriateness in a case where the video output from the imager is only the fisheye video. ### Claim 13 (depends on 2) The image-capturing device of claim 2, wherein the imager images the monitoring area through a fisheye lens, outputs a fisheye video, and outputs a correction video acquired by performing distortion correction on the fisheye video, and the controller determines that the video output from the imager has the appropriateness in a case where the video output from the imager includes the correction video. ### Claim 14 (depends on 6) The image-capturing device of claim 6, wherein the imager outputs, as the first video, a fisheye video acquired by imaging a monitoring area through a fisheye lens, cuts videos of a plurality of target areas set in response to an operation input of a user from the first video, performs distortion correction on the plurality of videos, and outputs, as the second video, a plurality of correction videos acquired through the distortion correction.