# US 2014/0153777 A1 · Living body recognizing device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2014/0153777 A1 - Document ID: US20140153777A1 - Status: Published application - Kind: A1 - Application number: 14/131,969 - Filed: 2012-08-31 - Published: 2014-06-05 - Earliest claimed: 2011-09-28 - Assignees: Honda Motor Co., Ltd. - Inventors: Nobuharu Nagaoka; Makoto Aimura; Kodai Matsuda - Web page: https://patentgrep.com/patent/US20140153777A1 ## CPC - G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition} - G08G 1/166: {for active traffic, e.g. moving vehicles, pedestrians, bikes} - H04N 7/18: Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast - H04N 23/23: from thermal infrared radiation - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93}) - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract A living body recognizing device is equipped with a captured image acquiring unit which acquires captured images from infrared cameras having a characteristics that a luminance of an image portion of a target object becomes higher as a temperature of the target object becomes higher than a background, and vice versa, according to a temperature difference between the background and the target object, a living body image extracting unit which executes a first living body image extracting processing of extracting the image portion of the target object assumed as a living body, from a region in the captured image where the luminance is equal to or lower than a first threshold value, and a living body recognizing unit which recognizes an existence of the living body, based on the image portion of the target object extracted by the living body image extracting unit. ## Claims ### Claim 1 A living body recognizing device, comprising: a captured image acquiring unit which acquires a captured image having a characteristics that a luminance of an image portion of a target object becomes higher as a temperature of the target object becomes higher than a background, and the luminance of the image portion of the target object becomes lower as the temperature of the target object becomes lower than the background, according to a temperature difference between the background and the target object, using an infrared camera; a living body image extracting unit which executes a first living body image extracting processing of extracting the image portion of the target object assumed to be a living body, from a region in the captured image in which the luminance is equal to or lower than a predetermined first threshold value, regardless of whether or not an area of the region in which the luminance is equal to lower than the predetermined first threshold value is larger than an area of a region in which the luminance is higher than the first threshold value; and a living body recognizing unit which recognizes an existence of the living body, based on the image portion of the target object extracted by the living body image extracting unit. ### Claim 2 (depends on 1) The living body recognizing device according to claim 1, wherein the living body image extracting unit generates an inverted captured image in which the luminance of each pixel of the captured image is inverted, and executes the first living body image extracting processing by extracting the image portion of the target object assumed to be the living body, from a region in the inverted captured image in which the luminance is equal to or higher than an inverted threshold value corresponding to the first threshold value. ### Claim 3 (depends on 1) The living body recognizing device according to claim 1, wherein the living body image extracting unit executes the first living body image extracting processing, and a second living body image extracting processing which extracts the image portion of the target object assumed to be the living body, from a region in the captured image in which the luminance is equal to or higher than a predetermined second threshold value. ### Claim 4 (depends on 3) The living body recognizing device according to claim 3, wherein the first threshold value and the second threshold value are set to different values. ### Claim 5 (depends on 4) The living body recognizing device according to claim 4, wherein the living body image extracting unit sets the first threshold value and the second threshold value, according to a luminance distribution of the captured image. ### Claim 6 (depends on 1) The living body recognizing device according to claim 1, wherein the living body recognizing device further comprises an outside air temperature sensor which detects an outside air temperature, and the living body image extracting unit executes the first living body image extracting processing, when a detected temperature of the outside air temperature sensor is equal to or higher than a predetermined temperature. ### Claim 7 (depends on 1) The living body recognizing device according to claim 1, wherein the living body recognizing device further comprises a rainfall detecting unit which detects a rainfall, and the living body image extracting unit executes the first living body image extracting processing, when the rainfall is detected by the rainfall detecting unit. ### Claim 8 (depends on 1) The living body recognizing device according to claim 1, wherein the living body image extracting unit executes the first living body image extracting processing, when a contrast of the captured image is equal to or less than a predetermined width. ### Claim 9 (depends on 3) The living body recognizing device according to claim 3, wherein the living body image extracting unit executes the second living body image extracting processing, with respect to an identical range as a range of the captured image in which the first living body image extracting processing is executed.