# US 10,372,990 B2 · System and method for identification of personal thermal comfort > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,372,990 B2 - Document ID: US10372990B2 - Status: Granted - Kind: B2 - Application number: 15/073,813 - Filed: 2016-03-18 - Published: 2017-09-21 - Granted: 2019-08-06 - Earliest claimed: 2016-03-18 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Carlos Henrique Cardonha; Andrea Britto Mattos Lima; Stefany Mazon - Web page: https://patentgrep.com/patent/US10372990B2 ## CPC - F24F 11/30: for purposes related to the operation of the system, e.g. for safety or monitoring - F24F 11/62: characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values - G06T 7/11: Region-based segmentation - G06V 20/40: in video content (extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44) - G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition} - F24F 2110/10: Temperature - F24F 2110/20: Humidity - F24F 2120/10: Occupancy - F24F: AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING (removing dirt or fumes from areas where they are produced B08B15/00; vertical ducts for carrying away waste gases from buildings E04F17/02; tops for chimneys or ventilating shafts, terminals for flues F23L17/02) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A method for temperature control includes acquiring image data, and analyzing the image data to identify one or more individuals within the image data. A level of thermal comfort is estimated for each of the identified individuals based on the image data. The determined level of thermal comfort indicates whether each individual appears to be feeling too hot, appears to be feeling too cold or appears to be feeling satisfied with an ambient temperature. An air-conditioning unit or a heating unit is controlled based on the estimation of the level of thermal comfort for each of the identified individuals. ## Claims ### Claim 1 A method for temperature control, comprising: acquiring image data, wherein the image data is color image data; analyzing the image data to identify one or more individuals within the image data; estimating a level of thermal comfort for each of the identified individuals based on the image data, the estimated level of thermal comfort indicating whether each individual appears to be feeling too hot, appears to be feeling too cold or appears to be feeling satisfied with an ambient temperature; and controlling an air-conditioning unit or a heating unit based on the estimated level of thermal comfort for each of the identified individuals, wherein estimating the level of thermal comfort for each of the identified individuals based on the image data, comprises: segmenting an individual of the identified individuals from the image data; differentiating between clothed surfaces and skin-exposed surfaces on the individual from the image data using one or more computer vision techniques; examining the skin-exposed surfaces of the individual from the image data to identify the presence of cutis anserine or horripilation; and estimating the level of thermal comfort of the individual based on the identification of cutis anserine or horripilation. ### Claim 2 (depends on 1) The method of claim 1, wherein the image data is acquired using one or more security cameras. ### Claim 3 (depends on 1) The method of claim 1, additionally comprising acquiring humidity data, wherein the estimating the level of thermal comfort for each of the identified individuals is performed based on the acquired humidity data in addition to the acquired image data. ### Claim 4 (depends on 3) The method of claim 3, wherein the humidity data is used to determine or confirm whether the individual is perspiring based on a humidity level above a predetermined threshold. ### Claim 5 (depends on 1) The method of claim 1, wherein estimating the level of thermal comfort for each of the identified individuals based on the image data, comprises: calculating a level of skin exposure of the individual based on the differentiation between the clothed surfaces and the skin-exposed surfaces of the individual; determining whether the individual appears to be dressed for a warm or cool temperature based on the calculated level of skin exposure; and estimating the level of thermal comfort of the individual based on the determination as to whether the individual appears to be dressed for warm or cold temperature. ### Claim 6 (depends on 1) The method of claim 1, wherein estimating the level of thermal comfort for each of the identified individuals based on the image data, comprises: segmenting the individual from the image data; identifying types of clothing garments being worn by the individual from within the segmented image data of the individual; determining whether the individual appears to be dressed for a warm or cool temperature based on the identified types of clothing garments being worn by the individual; and estimating the level of thermal comfort of the individual based on the determination as to whether the individual appears to be dressed for warm or cold temperature. ### Claim 7 (depends on 1) The method of claim 1, wherein estimating the level of thermal comfort for each of the identified individuals based on the image data further comprises examining the skin-exposed surfaces of the individual to identify the presence of perspiration. ### Claim 8 (depends on 1) The method of claim 1, wherein estimating the level of thermal comfort for each of the identified individuals based on the image data, comprises: segmenting the individual from the image data; analyzing the segmentation of the individual over a plurality of image frames; characterizing one or more observed actions of the individual based on the analysis of the segmentation of the individual over the plurality of image frames; determining whether any of the one or more observed actions of the individual are indicative of the individual feeling either too hot or too cold; and estimating the level of thermal comfort of the individual based on the determination as to whether the individual appears to be feeling either too hot or too cold. ### Claim 9 (depends on 1) The method of claim 1, wherein controlling the air-conditioning unit or the heating unit based on the estimation of the level of thermal comfort for each of the identified individuals, comprises: calculating a group comfort score by averaging the level of individual thermal comfort for all of the one or more individuals identified within the image data; determining whether the group comfort score is below a predetermined low threshold indicating that the one or more individuals are, on-average, feeling too cold or whether the group comfort score is above a predetermined high threshold indicating that the one or more individuals are, on-average, feeling too hot; and controlling the air-conditioning unit or the heating unit to raise the ambient temperature when it is determined that the group comfort score is below the predetermined low threshold, or controlling the air-conditioning unit or the heating unit to lower the ambient temperature when it is determined that the group comfort score is above the predetermined high threshold. ### Claim 10 A method for temperature control within an environment, comprising: acquiring temperature data at a plurality of different points within the environment; determining a temperature distribution pattern within the environment including at least one region of relatively high temperature and at least one region of relatively low temperature; acquiring image data, wherein the image data is color image data; analyzing the image data to identify an individual within the image data; estimating a level of thermal comfort for the identified individual based on the image data, the estimated level of thermal comfort indicating whether the individual appears to be feeling too hot, appears to be feeling too cold or appears to be feeling satisfied with an ambient temperature, wherein estimating the level of thermal comfort for each of the identified individual based on the image data, comprises: segmenting an individual of the identified individuals from the image data; differentiating between clothed surfaces and skin-exposed surfaces on the individual from the image data using one or more computer vision techniques; examining the skin-exposed surfaces of the individual from the image data to identify the presence of cutis anserine or horripilation; and estimating the level of thermal comfort of the individual based on the identification of cutis anserine or horripilation; and reassigning the individual to a space within the at least one region of relatively high temperature when the level of thermal comfort of the individual indicates that the individual appears to be feeling too cold, or reassigning the individual to a space within the at least one region of relatively low temperature when the level of thermal comfort of the individual indicates that the individual appears to be feeling too hot. ### Claim 11 (depends on 10) The method of claim 10, further comprising controlling an air-conditioning unit or a heating unit based on the estimation of the level of thermal comfort for the identified individual. ### Claim 12 (depends on 11) The method of claim 11, wherein controlling the air-conditioning unit or the heating unit based on the estimation of the level of thermal comfort for the identified individual, comprises: determining whether the level of thermal comfort is below a predetermined low threshold indicating that the individual is feeling too cold or whether the level of thermal comfort is above a predetermined high threshold indicating that the individual is feeling too hot; and controlling the air-conditioning unit or the heating unit to raise the ambient temperature when it is determined that the level of thermal comfort is below the predetermined low threshold, or controlling the air-conditioning unit or the heating unit to lower the ambient temperature when it is determined that the level of thermal comfort is above the predetermined high threshold. ### Claim 13 (depends on 10) The method of claim 10, wherein reassigning the individual includes selecting a new workspace for the individual from among a list of available workspaces. ### Claim 14 (depends on 10) The method of claim 10, wherein reassigning the individual includes selecting a new workspace for the individual and reassigning a second individual, already assigned to the new workspace, to another work space. ### Claim 15 (depends on 10) The method of claim 10, wherein the image data is acquired using one or more security cameras. ### Claim 16 (depends on 10) The method of claim 10, additionally comprising acquiring humidity data, wherein the estimating the level of thermal comfort for the identified individual is performed based on the acquired humidity data in addition to the acquired image data. ### Claim 17 (depends on 16) The method of claim 16, wherein the humidity data is used to determine or confirm whether the individual is perspiring based on a humidity level above a predetermined threshold. ### Claim 18 A method for reassigning seating for individuals and controlling ambient temperatures within an environment, comprising: receiving a seating chart for a plurality of individuals within the environment; acquiring temperature data at a plurality of different points within the environment; determining a temperature distribution pattern within the environment including at least one region of relatively high temperature and at least one region of relatively low temperature; determining how control of an air-conditioning unit or a heating unit affects the temperature distribution pattern; acquiring image data, wherein the image data is color image data; analyzing the image data to identify each of the plurality of individuals within the seating chart; estimating a level of thermal comfort for each of the identified plurality of individuals based on the image data, the estimated level of thermal comfort indicating whether each of the identified plurality of individuals appears to be feeling too hot, appears to be feeling too cold or appears to be feeling satisfied with an ambient temperature, wherein estimating the level of thermal comfort for each of the identified individuals based on the image data, comprises: segmenting an individual of the identified individuals from the image data; differentiating between clothed surfaces and skin-exposed surfaces on the individual from the image data using one or more computer vision techniques; examining the skin-exposed surfaces of the individual from the image data to identify the presence of cutis anserine or horripilation; and estimating the level of thermal comfort of the individual based on the identification of cutis anserine or horripilation; and generating an optimized heating/cooling plan including: determining how the air-conditioning unit or the heating unit is to be controlled based on the determined temperature distribution pattern and the determination as to how the control of the air-conditioning unit or the heating unit affects the temperature distribution pattern; and generating a modified seating chart by re-assigning each of the plurality of individuals to an optimal work space based on the corresponding level of estimated thermal comfort for the individual and a location of each work space with respect to the temperature distribution pattern. ### Claim 19 (depends on 18) The method of claim 18, wherein estimating the level of thermal comfort for each of the identified individuals based on the image data, comprises: calculating a level of skin exposure of the individual based on the differentiation between the clothed surfaces and the skin-exposed surfaces of the individual; determining whether the individual appears to be dressed for a warm or cool temperature based on the calculated level of skin exposure; and estimating the level of thermal comfort of the individual based on the determination as to whether the individual appears to be dressed for warm or cold temperature. ### Claim 20 (depends on 18) The method of claim 18, wherein estimating the level of thermal comfort for each of the identified individuals based on the image data, comprises: identifying types of clothing garments being worn by the individual from within the segmented image data of the individual; determining whether the individual appears to be dressed for a warm or cool temperature based on the identified types of clothing garments being worn by the individual; and estimating the level of thermal comfort of the individual based on the determination as to whether the individual appears to be dressed for warm or cold temperature. ### Claim 21 (depends on 18) The method of claim 18, wherein estimating the level of thermal comfort for each of the identified individuals based on the image data further comprises examining the skin-exposed surfaces of the individual to identify the presence of perspiration. ### Claim 22 (depends on 18) The method of claim 18, wherein estimating the level of thermal comfort for each of the identified individuals based on the image data, comprises: analyzing the segmentation of the individual over a plurality of image frames; characterizing one or more observed actions of the individual based on the analysis of the segmentation of the individual over the plurality of image frames; determining whether any of the one or more observed actions of the individual are indicative of the individual feeling either too hot or too cold; and estimating the level of thermal comfort of the individual based on the determination as to whether the individual appears to be feeling either too hot or too cold.