TWI732627B - Face tracking temperature measurement system and method - Google Patents

Face tracking temperature measurement system and method Download PDF

Info

Publication number
TWI732627B
TWI732627B TW109123929A TW109123929A TWI732627B TW I732627 B TWI732627 B TW I732627B TW 109123929 A TW109123929 A TW 109123929A TW 109123929 A TW109123929 A TW 109123929A TW I732627 B TWI732627 B TW I732627B
Authority
TW
Taiwan
Prior art keywords
face
temperature measurement
data
processing circuit
thermal imaging
Prior art date
Application number
TW109123929A
Other languages
Chinese (zh)
Other versions
TW202204860A (en
Inventor
潘校安
余正威
薛勝榮
Original Assignee
麥威科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 麥威科技股份有限公司 filed Critical 麥威科技股份有限公司
Priority to TW109123929A priority Critical patent/TWI732627B/en
Application granted granted Critical
Publication of TWI732627B publication Critical patent/TWI732627B/en
Publication of TW202204860A publication Critical patent/TW202204860A/en

Links

Images

Landscapes

  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Radiation Pyrometers (AREA)

Abstract

一種人臉追蹤測溫系統及其方法,係包含有一影像擷取鏡頭、一熱紅外線擷取鏡頭及一中央處理電路板,該中央處理電路用以能夠透過該影像擷取鏡頭及該熱紅外線擷取鏡頭分別擷取一或多個影像數據與一或多個的熱成像數據,再將影像數據與熱成像數據進行位置匹配,之後再對該影像數據進行臉部辨識以取得未移動或是移動中的臉部位置,並再依據該臉部位置於該熱成像數據上進行標記以取得臉部位置的溫度值。A face tracking temperature measurement system and method thereof include an image capturing lens, a thermal infrared capturing lens, and a central processing circuit board. The central processing circuit is used to pass the image capturing lens and the thermal infrared capturing Take the lens to capture one or more image data and one or more thermal imaging data, and then position the image data and the thermal imaging data to match, and then perform facial recognition on the image data to obtain no movement or movement And then mark the face position on the thermal imaging data according to the face position to obtain the temperature value of the face position.

Description

人臉追蹤測溫系統及其方法Face tracking temperature measurement system and method

本發明是有關一種人臉追蹤測溫系統及其方法,特別是一種能夠辨識以取得未移動或是移動中的臉部位置及其溫度值之人臉追蹤測溫系統及其方法。The present invention relates to a face tracking temperature measurement system and a method thereof, in particular to a face tracking temperature measurement system and method that can be identified to obtain the position of the unmoving or moving face and its temperature value.

由於為了能夠有效阻絕冠狀病毒疾病的影響,故現今很多國家皆提倡出入公共場所應配戴口罩,以防止爆發大規模的感染;除此之外,經過醫學證實,當病人開始有發燒現象時,其體內的病毒即開始具有傳染性,故為了有效管控人員的身體狀況,故會於進出門口處設置體溫計、 耳溫槍、額溫槍這一類的裝置進行量測體溫。In order to effectively prevent the impact of the coronavirus disease, many countries now advocate wearing masks when entering and exiting public places to prevent the outbreak of large-scale infections. In addition, it is medically proven that when a patient starts to have a fever, The virus in the body becomes contagious. Therefore, in order to effectively control the physical condition of the personnel, devices such as thermometers, ear thermometers, and forehead thermometers will be installed at the entrance and exit to measure body temperature.

然而體溫計與耳溫槍這一類的接觸式裝置,皆需要其檢測頭接觸人體方能檢測,此一檢測過程係會造成待測人員的不便,具長期且大量使用於不同人,其衛生問題亦值得憂慮。However, contact devices such as clinical thermometers and ear thermometers require the detection head to contact the human body to be able to detect. This detection process will cause inconvenience to the person to be tested. It has long-term and large-scale use by different people, and its hygiene problems are also Worry about.

而額溫槍這一類的裝置,雖然能夠非接觸式的量測體溫,但同時也容易受到環境溫度的影響,進而容易造成體溫量測的誤差,這對於有需要嚴謹管控進出的場所或是公司來講,將是一大風險。Although devices such as forehead thermometers can measure body temperature in a non-contact manner, they are also susceptible to the influence of ambient temperature, which can easily cause errors in body temperature measurement. This is for places or companies that require strict control of entry and exit. Generally speaking, it will be a big risk.

因此,針對上述問題,若是能夠搭配紅外線感測鏡頭與攝像鏡頭,一部分能夠進行拍攝與紀錄進出人員的影像之外,更能夠透過紅外線感測鏡頭來感測體溫,如此將能夠精準的掌控進出人員的體溫狀態,因此,本案應為一最佳解決方案。Therefore, in order to solve the above problems, if the infrared sensor lens and the camera lens can be used, some of them can be used to shoot and record the images of the entering and exiting personnel, and the infrared sensor lens can be used to sense the body temperature, so that the entry and exit personnel can be accurately controlled Therefore, this case should be the best solution.

本發明人臉追蹤測溫系統,係包含:一殼體;一影像擷取鏡頭,係設置於該殼體上;一熱紅外線擷取鏡頭,係設置於該殼體上;一中央處理電路板,係設置於該殼體內,該中央處理電路係與該影像擷取鏡頭及該熱紅外線擷取鏡頭電性連接,其中該中央處理電路用以能夠透過該影像擷取鏡頭及該熱紅外線擷取鏡頭分別擷取一或多個影像數據與一或多個的熱成像數據,再將影像數據與熱成像數據進行位置匹配,之後再對該影像數據進行臉部辨識以取得臉部位置,並再依據該臉部位置於該熱成像數據上進行標記以取得臉部位置的溫度值。The face tracking temperature measurement system of the present invention includes: a housing; an image capturing lens arranged on the housing; a thermal infrared capturing lens arranged on the housing; and a central processing circuit board , Is disposed in the housing, the central processing circuit is electrically connected to the image capturing lens and the thermal infrared capturing lens, wherein the central processing circuit is used to be able to pass through the image capturing lens and the thermal infrared capturing The lens captures one or more image data and one or more thermal imaging data respectively, and then positions the image data and the thermal imaging data to match, and then performs face recognition on the image data to obtain the face position, and then According to the face part placed on the thermal imaging data for marking to obtain the temperature value of the face position.

更具體的說,所述中央處理電路板更包含有一圖片擷取單元,該圖片擷取單元係能夠透過該影像擷取鏡頭及該熱紅外線擷取鏡頭進行擷取一或多個影像數據與一或多個的熱成像數據。More specifically, the central processing circuit board further includes a picture capture unit capable of capturing one or more image data and one image data through the image capture lens and the thermal infrared capture lens. Or multiple thermal imaging data.

更具體的說,所述中央處理電路板更包含有一位置調整單元,該位置調整單元用以能夠將該影像數據之位置與熱成像數據之位置進行疊加匹配與調整。More specifically, the central processing circuit board further includes a position adjustment unit for superimposing, matching and adjusting the position of the image data and the position of the thermal imaging data.

更具體的說,所述中央處理電路板更包含有一臉部追蹤單元,用以能夠進行擷取多個與臉部相關的屬性,以獲取臉部位置,並於該影像數據之畫面中移動中的臉部位置做追蹤,以獲取一或多個移動參數座標。More specifically, the central processing circuit board further includes a face tracking unit for capturing multiple attributes related to the face to obtain the position of the face, and moving in the frame of the image data Track the position of the face to obtain one or more moving parameter coordinates.

更具體的說,所述中央處理電路板更包含有一與該臉部追蹤單元相連接之人臉特徵獲取單元,用以將追蹤之移動參數座標的臉部位置,依據一人臉比例數據進行判斷出該臉部位置上的人臉特徵大小及位置。More specifically, the central processing circuit board further includes a face feature acquisition unit connected to the face tracking unit for determining the position of the face of the tracked movement parameter coordinates based on a face ratio data The size and position of the facial features at the position of the face.

更具體的說,所述人臉特徵係能夠為額頭。More specifically, the facial feature system can be the forehead.

更具體的說,所述中央處理電路板更包含有一人臉位置標註單元,用以將取得之臉部位置於該熱成像數據上進行標記。More specifically, the central processing circuit board further includes a face position marking unit for placing the acquired face parts on the thermal imaging data for marking.

更具體的說,所述中央處理電路板更包含有一與該人臉位置標註單元相連接之人臉溫度獲取單元,用以依據該人臉位置標註單元所標記之位置及該熱成像數據,來取得該臉部位置所對應的溫度值。More specifically, the central processing circuit board further includes a face temperature acquiring unit connected to the face position marking unit, and is used to obtain the thermal imaging data according to the position marked by the face position marking unit Get the temperature value corresponding to the position of the face.

更具體的說,所述中央處理電路板更包含有一熱源排除單元,用以能夠將臉部位置之外的熱源或/及將過大或是過小的臉部位置進行排除。More specifically, the central processing circuit board further includes a heat source removal unit for removing heat sources other than the face position or/and the face position that is too large or too small.

更具體的說,所述熱源排除單元能夠判斷出該臉部位置大小,並依據一臉部大小數據,進行排除過大或是過小的臉部位置,用以能夠減少不必要的臉部位置溫度值偵測。More specifically, the heat source elimination unit can determine the size of the face position, and based on a face size data, eliminate the face position that is too large or too small, so as to reduce unnecessary face position temperature values. Detection.

更具體的說,所述中央處理電路板更包含有一溫度校正單元,用以能夠透過一校正數據與所偵測出之熱成像數據進行校正。More specifically, the central processing circuit board further includes a temperature correction unit for performing correction through a correction data and the detected thermal imaging data.

更具體的說,所述校正數據係能夠透過一黑體輻射偵測器或是一額溫槍進行取得。More specifically, the calibration data can be obtained through a black body radiation detector or a forehead thermometer.

更具體的說,所述中央處理電路板更包含有一記錄單元,用以能夠紀錄通過人數、超溫人臉或是全畫面內容,並能夠匯出為一資訊檔。More specifically, the central processing circuit board further includes a recording unit for recording the number of people passing by, over-temperature faces, or full-screen content, and can be exported as an information file.

一種人臉追蹤測溫方法,其步驟為: (1)     係透過一影像擷取鏡頭及熱紅外線擷取鏡頭,以分別擷取一或多個影像數據與一或多個的熱成像數據; (2)     再將影像數據與熱成像數據進行疊加匹配與調整; (3)     之後再對該影像數據進行臉部辨識以取得臉部位置,並再依據該臉部位置於該熱成像數據上進行標記以取得臉部位置的溫度值。 A face tracking temperature measurement method, the steps are: (1) It uses an image capture lens and a thermal infrared capture lens to capture one or more image data and one or more thermal imaging data respectively; (2) The image data and thermal imaging data are then superimposed, matched and adjusted; (3) Afterwards, face recognition is performed on the image data to obtain the face position, and then the face part is placed on the thermal imaging data for marking to obtain the temperature value of the face position.

更具體的說,所述對該影像數據進行臉部辨識以取得臉部位置,係能夠先進行擷取多個與臉部相關的屬性,用以獲取臉部位置,之後再於該影像數據之畫面中移動中的臉部位置做追蹤,以獲取一或多個移動參數座標。More specifically, said performing face recognition on the image data to obtain the position of the face can firstly capture a plurality of attributes related to the face to obtain the position of the face, and then add the position of the face to the image data. The position of the moving face in the screen is tracked to obtain one or more moving parameter coordinates.

更具體的說,所述更能夠將追蹤之移動參數座標的臉部位置,依據一人臉比例數據進行判斷出該臉部位置上的人臉特徵大小及位置。More specifically, the face position of the tracked movement parameter coordinates can be further judged according to a face ratio data to determine the size and position of the face feature at the face position.

更具體的說,所述人臉特徵係能夠為額頭。More specifically, the facial feature system can be the forehead.

更具體的說,所述能夠將臉部位置之外的熱源或/及將過大或是過小的臉部位置進行排除。More specifically, the heat source outside the face position or/and the face position that is too large or too small can be eliminated.

更具體的說,所述更能夠透過一校正數據與所偵測出之熱成像數據進行校正。More specifically, the correction can be performed through a correction data and the detected thermal imaging data.

更具體的說,所述校正數據係能夠透過一黑體輻射偵測器或是一額溫槍進行取得。More specifically, the calibration data can be obtained through a black body radiation detector or a forehead thermometer.

更具體的說,所述更能夠紀錄通過人數、超溫人臉或是全畫面內容,用以能夠匯出為一資訊檔。More specifically, it can record the number of passing people, over-temperature faces, or full-screen content, so as to be able to export as an information file.

有關於本發明其他技術內容、特點與功效,在以下配合參考圖式之較佳實施例的詳細說明中,將可清楚的呈現。Other technical content, features and effects of the present invention will be clearly presented in the following detailed description of the preferred embodiment with reference to the drawings.

請參閱1~3圖,為本發明人臉追蹤測溫系統及其方法之實施結構示意圖、內部架構示意圖及中央處理電路板之架構示意圖,由圖中可知,該人臉追蹤測溫系統係為一裝置來實施,而該系統係具有一殼體1,該殼體1內係包含有一影像擷取鏡頭11及一熱紅外線擷取鏡頭12及一中央處理電路板13。Please refer to Figures 1 to 3, which are the implementation structure diagram, internal structure diagram and central processing circuit board diagram of the face tracking temperature measurement system and method of the present invention. It can be seen from the figure that the face tracking temperature measurement system is A device is implemented, and the system has a housing 1 which includes an image capturing lens 11 and a thermal infrared capturing lens 12 and a central processing circuit board 13 in the housing 1.

其中該中央處理電路板13係包含: (1)     一圖片擷取單元131,係能夠透過該影像擷取鏡頭11及該熱紅外線擷取鏡頭12進行擷取一或多個影像數據與一或多個的熱成像數據。 (2)     一位置調整單元132,用以能夠將該影像數據之位置與熱成像數據之位置進行疊加匹配與調整。 (3)     一臉部追蹤單元133,用以能夠進行擷取多個與臉部相關的屬性,以獲取臉部位置,並於該影像數據之畫面中移動中的臉部位置做追蹤,以獲取一或多個移動參數座標。 (4)     一人臉特徵獲取單元134,用以將追蹤之移動參數座標的臉部位置,依據一人臉比例數據進行判斷出該臉部位置上的人臉特徵大小及位置,而該人臉特徵係能夠為額頭。 (5)     一人臉位置標註單元135,用以將取得之臉部位置於該熱成像數據上進行標記。 (6)     一人臉溫度獲取單元136,用以依據該人臉位置標註單元135所標記之位置及該熱成像數據,來取得該臉部位置所對應的溫度值。 (7)     一熱源排除單元137,用以能夠將該熱成像數據之臉部位置範圍之外的熱源進行排除,而該熱源排除單元137更能夠判斷出該臉部位置之範圍大小,並依據一臉部大小數據,進行排除過大或是過小的臉部位置範圍,用以能夠減少不必要的臉部位置溫度值偵測。 (8)     一溫度校正單元138,用以能夠透過一校正數據與所偵測出之熱成像數據進行校正,而該校正數據係能夠透過一黑體輻射偵測器或是一額溫槍進行取得。 (9)     一記錄單元139,用以能夠紀錄通過人數、超溫人臉或是全畫面內容,並能夠匯出為一資訊檔。 The central processing circuit board 13 series includes: (1) An image capturing unit 131 is capable of capturing one or more image data and one or more thermal imaging data through the image capturing lens 11 and the thermal infrared capturing lens 12. (2) A position adjustment unit 132 for superimposing, matching and adjusting the position of the image data and the position of the thermal imaging data. (3) A face tracking unit 133 is used to capture multiple attributes related to the face to obtain the position of the face, and track the moving face position in the frame of the image data to obtain One or more moving parameter coordinates. (4) A face feature acquisition unit 134 is used to determine the size and position of the face feature at the face position based on the face position of the tracked movement parameter coordinates, and the face feature system Can be for the forehead. (5) A face position labeling unit 135 for placing the acquired face part on the thermal imaging data for labeling. (6) A face temperature acquisition unit 136 for acquiring the temperature value corresponding to the face position according to the position marked by the face position marking unit 135 and the thermal imaging data. (7) A heat source elimination unit 137 is used to eliminate heat sources outside the range of the face position of the thermal imaging data, and the heat source elimination unit 137 can further determine the size of the face position range based on a The face size data is used to exclude the face position range that is too large or too small, so as to reduce unnecessary face position temperature detection. (8) A temperature correction unit 138 is used to perform correction through a correction data and the detected thermal imaging data, and the correction data can be obtained through a black body radiation detector or a forehead thermometer. (9) A recording unit 139, used to record the number of people passing by, over-temperature faces, or full-screen content, and can be exported as an information file.

而該人臉追蹤測溫方法,如第4圖所示,其步驟為: (1)     係透過影像擷取鏡頭及熱紅外線擷取鏡頭,以分別擷取一或多個影像數據與一或多個的熱成像數據401; (2)     再將影像數據與熱成像數據進行疊加匹配與調整402; (3)     之後再對該影像數據進行臉部辨識以取得臉部位置403,並再依據該臉部位置於該熱成像數據上進行標記以取得臉部位置的溫度值404。 The face tracking temperature measurement method, as shown in Figure 4, has the following steps: (1) It uses an image capture lens and a thermal infrared capture lens to capture one or more image data and one or more thermal imaging data 401 respectively; (2) The image data and thermal imaging data are then superimposed, matched and adjusted 402; (3) Afterwards, face recognition is performed on the image data to obtain the face position 403, and then the face part is placed on the thermal imaging data for marking to obtain the temperature value 404 of the face position.

而當實際運作時,該人臉追蹤測溫系統必須先啟動,並再透過影像擷取鏡頭11及熱紅外線擷取鏡頭12,以分別擷取一或多個影像數據(RGB 影像)與一或多個的熱成像數據(IR Thermal 影像);In actual operation, the face tracking temperature measurement system must be activated first, and then through the image capture lens 11 and thermal infrared capture lens 12 to capture one or more image data (RGB images) and one or Multiple thermal imaging data (IR Thermal image);

之後,則依據以下幾個程序來進行人臉溫度值判斷,而程序說明如下: (1)     如第5圖所示,能夠透過一電子設備2(電子設備2係為桌上型電腦、筆記型電腦、平板電腦或是智慧型手持裝置)與該人臉追蹤測溫系統進行連線,並透過該電子設備2之螢幕21顯示該電子設備2內部安裝的軟體上的運用工程界面22,調整RGB鏡頭與熱紅外線鏡頭(Thermal IR)的位置(左右位置、大小位置),以將顯示的影像畫面(熱成像影像、RGB影像)疊加,以利校正; (2)     之後,再運用臉部偵測演算法(臉部辨識可偵測影像中的人臉,並傳回其位置的矩形座標),而於臉部偵測之前,能夠先取得一連串與臉部相關的屬性(例如,姿勢、性別、年齡、頭部姿勢、臉部汗毛和眼鏡等)。獲取RGB上128個特徵值,獲取人臉或戴口罩人臉的位置,而運算進一步說明如下: (a)      獲取人臉:影像獲取後進行二值化(數值化)作業,將畫面中所有的數值,進行與已經開發好的人臉資料庫,進行128特徵點分類(如鼻子或嘴巴的參數範圍為兩類),並計算此畫面中的數值為人臉的閥值是多少,即可知道此畫面是否有人臉及位置大小。 (b)     獲取戴口罩人臉:運用上述閥值及分類後的數值,可判斷是否臉部有遮蔽物,進一步獲取戴口罩人臉的位置。 (3)     再運用比例值做一計算,運用上述的追蹤人臉上,進一步計算並獲取額頭大小及位置,其中獲取額頭為上述已知人臉大小及位置後,人臉比例通常為框架上半部比例30%~50%(因額頭高低),所以獲取人臉框架後,即可運用眉毛往上比例(10%~20%)計算額頭高低。 (4)     之後,將影像數據(RGB 影像)獲取的人臉位置,找尋熱成像數據(IR Thermal 影像)中的人臉位置並標註顯示,而上述所提及的找尋,是指出廠時會運用工程界面將RGB 影像與熱成像影像大小及疊合,後續使用時,只要系統計算出人臉大小與位置,即可自動疊合於熱成像影像中,以找到人臉上額頭的溫度。 (5)     最後,將熱紅外線鏡頭上的Row Data(位元資料)運用做計算,獲取熱紅外線鏡頭上找尋到的溫度值,其中Row Data(位元資料)為一串由該熱紅外線鏡頭給予的電位參數,而熱成像影像則是將Row Data(位元資料)進行分類及上色所顯示出的影像(如第6圖所示); 而上述針對Row Data(位元資料) 運用做計算,是要經過Row Data(位元資料)獲取電位參數後進行公式計算,主要是將四個參數RBFO,進行運用及計算,本溫度計算公式為T = B / Ln ( R / (RawVal - O) + F),其中參數B、R、RawVal、O及F,其中RBFO為Planck constant(普朗克常數),而RawVal為熱紅外線鏡頭所回傳的Row Data(位元資料)。 After that, the face temperature value is judged according to the following procedures, and the procedures are described as follows: (1) As shown in Figure 5, it can be connected to the face tracking temperature measurement system through an electronic device 2 (electronic device 2 is a desktop computer, a notebook computer, a tablet computer, or a smart handheld device). Line, and display the application engineering interface 22 on the software installed inside the electronic device 2 through the screen 21 of the electronic device 2, adjust the position (left and right position, size position) of the RGB lens and the thermal infrared lens (thermal IR) to change The displayed images (thermal imaging images, RGB images) are superimposed to facilitate correction; (2) After that, use the face detection algorithm (face recognition can detect the face in the image, and return the rectangular coordinates of its position), and before the face detection, a series of faces can be obtained. Department-related attributes (for example, posture, gender, age, head posture, facial hair, glasses, etc.). Get 128 feature values on RGB, get the position of the face or face wearing a mask, and the calculation is further explained as follows: (a) Obtaining the face: After the image is acquired, binarization (numerization) is performed, and all the values in the screen are compared with the developed face database, and 128 feature points are classified (such as the parameters of the nose or mouth) The range is two types), and calculate the value in this picture as the threshold value of the face, you can know whether this picture has a face and the size of the position. (b) Obtaining the face wearing a mask: Using the above threshold and the classified value, it can be judged whether there is a mask on the face, and the position of the face wearing the mask can be further obtained. (3) Use the ratio value to do a calculation, use the above-mentioned tracking face to further calculate and obtain the forehead size and position, where the forehead is the aforementioned known face size and position, the face ratio is usually the upper half of the frame The ratio is 30%~50% (due to the height of the forehead), so after obtaining the face frame, the ratio of eyebrows up (10%~20%) can be used to calculate the height of the forehead. (4) After that, the face position obtained by the image data (RGB image) is searched for the face position in the thermal imaging data (IR Thermal image) and displayed, and the search mentioned above means that the factory will use The engineering interface superimposes the size and size of the RGB image and the thermal imaging image. In the subsequent use, as long as the system calculates the size and position of the face, it can be automatically superimposed on the thermal imaging image to find the temperature of the forehead of the face. (5) Finally, the Row Data (bit data) on the thermal infrared lens is used for calculation to obtain the temperature value found on the thermal infrared lens, where the Row Data (bit data) is a string given by the thermal infrared lens The thermal imaging image is the image displayed by classifying and coloring Row Data (as shown in Figure 6); The above calculation for the use of Row Data (bit data) requires the calculation of the formula after obtaining the potential parameters through the Row Data (bit data). The four parameters RBFO are mainly used and calculated. The temperature calculation formula is T = B / Ln (R / (RawVal-O) + F), where the parameters B, R, RawVal, O and F, where RBFO is Planck constant, and RawVal is returned by the thermal infrared lens Row Data (bit data).

由於環境中有不同的熱源,因此容易造成進行人臉溫度值誤判,故本案提出了以下的去除(排除)雜訊功能,功能敘述如下: (1)     因架設的環境有所不同,必須運用遮罩處理,將顯示在鏡頭中不必要的熱源作去除掉,這裡指的遮罩處理,是於工程界面上拉取不要紀錄的區域,會顯示於畫面中,如第7圖所示,當系統判斷到人臉後,會再進行此位置是否有重疊過遮罩位置的確認,如果有,則不紀錄。 (2)     排除非臉部的熱源。 (3)     運用[0033]的第2點提及的方式取得臉部大小之後,再進一步計算人臉的距離,這裡是因為熱紅外線鏡頭特性為接收訊號,越遠訊號會衰退,因此,畫面中的人會站至前後,而計算出人臉位置,即可補償同畫面人臉位置的溫度。 (4)     排除過大或過小的臉,排除不必要的低溫與高溫偵測。 Since there are different heat sources in the environment, it is easy to cause misjudgment of the face temperature value. Therefore, this case proposes the following noise removal (removal) function, and the function is described as follows: (1) Due to the different installation environment, masking must be used to remove unnecessary heat sources displayed in the lens. The masking process here refers to the area that is not required to be recorded on the engineering interface. Displayed on the screen, as shown in Figure 7, when the system determines the face, it will confirm whether the position has overlapped the mask position. If there is, it will not record. (2) Eliminate non-face heat sources. (3) After obtaining the size of the face using the method mentioned in point 2 of [0033], the distance of the face is further calculated. This is because the characteristic of the thermal infrared lens is to receive the signal. The farther the signal is The person of will stand back and forth and calculate the face position to compensate for the temperature of the face position in the same picture. (4) Exclude faces that are too big or too small, and eliminate unnecessary low and high temperature detection.

而為了保持人臉溫度值的精準度,故本案能夠透過一校正數據與所偵測出之熱成像數據對該系統進行校正,而該校正數據係能夠透過一黑體輻射偵測器或是一額溫槍進行取得。In order to maintain the accuracy of the human face temperature value, the system can be calibrated through a calibration data and the detected thermal imaging data, and the calibration data can be passed through a black body radiation detector or a forehead Warm gun to obtain.

本案更具有追蹤與紀錄功能,功能敘述如下: (1)     紀錄通過人數,並拍照存檔,並可匯出資訊檔。 (2)     紀錄超溫人臉,並拍照存檔,並可匯出資訊檔。 (3)     紀錄全畫面,追蹤人與人之前的關係,並可匯出資訊檔。 This case also has tracking and recording functions. The functions are described as follows: (1) Record the number of passing people, take photos and archive them, and export information files. (2) Record over-temperature faces, take photos and archive them, and export information files. (3) Record the full screen, track the relationship between people, and export information files.

本發明所提供之人臉追蹤測溫系統及其方法,與其他習用技術相互比較時,其優點如下: 1.         本發明能夠搭配紅外線感測鏡頭與攝像鏡頭,能夠進行拍攝與紀錄進出人員的影像之外,更能夠透過紅外線感測鏡頭來感測體溫,如此將能夠精準的掌控進出人員的體溫狀態。 2.         本發明能夠進行多臉追蹤並同時取得多臉的體溫狀態,因此非常適合應用於人潮繁多的環境使用,除此之外,本案更具有排除功能,用以能夠偵測出真實人臉或是去除人臉以外的熱源,以排除不必要的低溫與高溫偵測。 When compared with other conventional technologies, the face tracking temperature measurement system and method provided by the present invention have the following advantages: 1. The present invention can be equipped with an infrared sensor lens and a camera lens, which can capture and record images of entering and exiting personnel, and can also sense body temperature through an infrared sensing lens, so that the body temperature status of entering and exiting personnel can be accurately controlled. 2. The present invention can perform multi-face tracking and obtain the temperature status of multiple faces at the same time, so it is very suitable for use in a crowded environment. In addition, this case has an exclusion function to detect real human faces or It removes heat sources other than the human face to eliminate unnecessary low and high temperature detection.

本發明已透過上述之實施例揭露如上,然其並非用以限定本發明,任何熟悉此一技術領域具有通常知識者,在瞭解本發明前述的技術特徵及實施例,並在不脫離本發明之精神和範圍內,當可作些許之更動與潤飾,因此本發明之專利保護範圍須視本說明書所附之請求項所界定者為準。The present invention has been disclosed above through the above-mentioned embodiments, but it is not intended to limit the present invention. Anyone familiar with this technical field with ordinary knowledge should understand the aforementioned technical features and embodiments of the present invention without departing from the scope of the present invention. Within the spirit and scope, some changes and modifications can be made. Therefore, the patent protection scope of the present invention shall be subject to what is defined in the claims attached to this specification.

1:殼體1: shell

11:影像擷取鏡頭11: Image capture lens

12:熱紅外線擷取鏡頭12: Thermal infrared capture lens

13:中央處理電路板13: Central processing circuit board

131:圖片擷取單元131: Picture capture unit

132:位置調整單元132: Position adjustment unit

133:臉部追蹤單元133: Face tracking unit

134:人臉特徵獲取單元134: Face feature acquisition unit

135:人臉位置標註單元135: Face position labeling unit

136:人臉溫度獲取單元136: Face temperature acquisition unit

137:熱源排除單元137: Heat source removal unit

138:溫度校正單元138: Temperature correction unit

139:記錄單元139: Recording Unit

14:熱紅外線擷取鏡頭14: Thermal infrared capture lens

2:電子設備2: electronic equipment

21:螢幕21: screen

22:運用工程界面22: Use engineering interface

[第1圖] 係本發明人臉追蹤測溫系統及其方法之實施結構示意圖。 [第2圖] 係本發明人臉追蹤測溫系統及其方法之內部架構示意圖。 [第3圖] 係本發明人臉追蹤測溫系統及其方法之中央處理電路板之架構示意圖。 [第4圖] 係本發明人臉追蹤測溫系統及其方法之流程示意圖。 [第5圖] 係本發明人臉追蹤測溫系統及其方法之影像疊加校正示意圖。 [第6圖] 係本發明人臉追蹤測溫系統及其方法之熱成像影像示意圖。 [第7圖] 係本發明人臉追蹤測溫系統及其方法之遮罩處理示意圖。 [Figure 1] is a schematic diagram of the implementation structure of the face tracking temperature measurement system and method of the present invention. [Figure 2] is a schematic diagram of the internal structure of the face tracking temperature measurement system and method of the present invention. [Figure 3] It is a schematic diagram of the architecture of the central processing circuit board of the face tracking temperature measurement system and method of the present invention. [Figure 4] is a schematic flow diagram of the face tracking temperature measurement system and method of the present invention. [Figure 5] It is a schematic diagram of image overlay correction of the face tracking temperature measurement system and method of the present invention. [Figure 6] is a schematic diagram of the thermal imaging image of the face tracking temperature measurement system and method of the present invention. [Figure 7] is a schematic diagram of the mask processing of the face tracking temperature measurement system and method of the present invention.

1:殼體 1: shell

11:影像擷取鏡頭 11: Image capture lens

12:熱紅外線擷取鏡頭 12: Thermal infrared capture lens

13:中央處理電路板 13: Central processing circuit board

Claims (19)

一種人臉追蹤測溫系統,係包含:一殼體;一影像擷取鏡頭,係設置於該殼體上;一熱紅外線擷取鏡頭,係設置於該殼體上;一中央處理電路板,係設置於該殼體內,該中央處理電路係與該影像擷取鏡頭及該熱紅外線擷取鏡頭電性連接,其中該中央處理電路用以能夠透過該影像擷取鏡頭及該熱紅外線擷取鏡頭分別擷取一或多個影像數據與一或多個的熱成像數據,再將影像數據與熱成像數據進行位置匹配,之後再對該影像數據進行臉部辨識以取得臉部位置,並再依據該臉部位置於該熱成像數據上進行標記以取得臉部位置的溫度值,其中該中央處理電路板更包含有一臉部追蹤單元,用以能夠進行擷取多個與臉部相關的屬性,以獲取臉部位置,並於該影像數據之畫面中移動中的臉部位置做追蹤,以獲取一或多個移動參數座標。 A face tracking temperature measurement system includes: a housing; an image capturing lens arranged on the housing; a thermal infrared capturing lens arranged on the housing; a central processing circuit board, Is arranged in the housing, the central processing circuit is electrically connected to the image capturing lens and the thermal infrared capturing lens, wherein the central processing circuit is used to pass the image capturing lens and the thermal infrared capturing lens Respectively capture one or more image data and one or more thermal imaging data, and then position the image data and the thermal imaging data to match, and then perform face recognition on the image data to obtain the face position, and then according to The face part is placed on the thermal imaging data for marking to obtain the temperature value of the face position, wherein the central processing circuit board further includes a face tracking unit for capturing a plurality of attributes related to the face, The face position is acquired, and the moving face position in the frame of the image data is tracked to acquire one or more movement parameter coordinates. 如請求項1所述之人臉追蹤測溫系統,其中該中央處理電路板更包含有一圖片擷取單元,該圖片擷取單元係能夠透過該影像擷取鏡頭及該熱紅外線擷取鏡頭進行擷取一或多個影像數據與一或多個的熱成像數據。 The face tracking temperature measurement system according to claim 1, wherein the central processing circuit board further includes a picture capturing unit, and the picture capturing unit is capable of capturing through the image capturing lens and the thermal infrared capturing lens Take one or more image data and one or more thermal imaging data. 如請求項1所述之人臉追蹤測溫系統,其中該中央處理電路板更包含有一位置調整單元,該位置調整單元用以能夠將該影像數據之位置與熱成像數據之位置進行疊加匹配與調整。 The face tracking temperature measurement system according to claim 1, wherein the central processing circuit board further includes a position adjustment unit for being able to superimpose and match the position of the image data and the position of the thermal imaging data. Adjustment. 如請求項1所述之人臉追蹤測溫系統,其中該中央處理電路板更包含有一與該臉部追蹤單元相連接之人臉特徵獲取單元,用以將追蹤之移動參數座標的臉部位置,依據一人臉比例數據進行判斷出該臉部位置上的人臉特徵 大小及位置。 The face tracking temperature measurement system according to claim 1, wherein the central processing circuit board further includes a face feature acquisition unit connected to the face tracking unit, and is used to obtain the position of the face of the moving parameter coordinate of the tracking , To determine the facial features at the position of the face based on the data of a face ratio Size and location. 如請求項4所述之人臉追蹤測溫系統,其中該人臉特徵係能夠為額頭。 The face tracking temperature measurement system according to claim 4, wherein the face feature can be the forehead. 如請求項1所述之人臉追蹤測溫系統,其中該中央處理電路板更包含有一人臉位置標註單元,用以將取得之臉部位置於該熱成像數據上進行標記。 The face tracking temperature measurement system according to claim 1, wherein the central processing circuit board further includes a face position marking unit for placing the acquired face parts on the thermal imaging data for marking. 如請求項6所述之人臉追蹤測溫系統,其中該中央處理電路板更包含有一與該人臉位置標註單元相連接之人臉溫度獲取單元,用以依據該人臉位置標註單元所標記之位置及該熱成像數據,來取得該臉部位置所對應的溫度值。 The face tracking temperature measurement system according to claim 6, wherein the central processing circuit board further includes a face temperature acquisition unit connected to the face position marking unit, and is used to obtain a face temperature according to the mark marked by the face position marking unit The position of the face and the thermal imaging data are used to obtain the temperature value corresponding to the position of the face. 如請求項1所述之人臉追蹤測溫系統,其中該中央處理電路板更包含有一熱源排除單元,用以能夠將臉部位置之外的熱源或/及將過大或是過小的臉部位置進行排除。 The face tracking temperature measurement system according to claim 1, wherein the central processing circuit board further includes a heat source elimination unit to be able to remove heat sources other than the position of the face and/or the position of the face that is too large or too small To exclude. 如請求項8所述之人臉追蹤測溫系統,其中該熱源排除單元能夠判斷出該臉部位置大小,並依據一臉部大小數據,進行排除過大或是過小的臉部位置,用以能夠減少不必要的臉部位置溫度值偵測。 The face tracking temperature measurement system according to claim 8, wherein the heat source elimination unit can determine the size of the face position, and based on a face size data, eliminate the face position that is too large or too small to be able to Reduce unnecessary face position temperature detection. 如請求項1所述之人臉追蹤測溫系統,其中該中央處理電路板更包含有一溫度校正單元,用以能夠透過一校正數據與所偵測出之熱成像數據進行校正。 The face tracking temperature measurement system according to claim 1, wherein the central processing circuit board further includes a temperature correction unit for performing correction through a correction data and the detected thermal imaging data. 如請求項11所述之人臉追蹤測溫系統,其中該校正數據係能夠透過一黑體輻射偵測器或是一額溫槍進行取得。 The face tracking temperature measurement system according to claim 11, wherein the calibration data can be obtained through a black body radiation detector or a forehead thermometer. 如請求項1所述之人臉追蹤測溫系統,其中該中央處理電路板 更包含有一記錄單元,用以能夠紀錄通過人數、超溫人臉或是全畫面內容,並能夠匯出為一資訊檔。 The face tracking temperature measurement system according to claim 1, wherein the central processing circuit board It also includes a recording unit for recording the number of people passing by, over-temperature faces or full-screen content, and can be exported as an information file. 一種人臉追蹤測溫方法,其步驟為:係透過一影像擷取鏡頭及熱紅外線擷取鏡頭,以分別擷取一或多個影像數據與一或多個的熱成像數據;再將影像數據與熱成像數據進行疊加匹配與調整;之後再對該影像數據進行臉部辨識以取得臉部位置,並再依據該臉部位置於該熱成像數據上進行標記以取得臉部位置的溫度值,其中對該影像數據進行臉部辨識以取得臉部位置,係能夠先進行擷取多個與臉部相關的屬性,用以獲取臉部位置,之後再於該影像數據之畫面中移動中的臉部位置做追蹤,以獲取一或多個移動參數座標。 A face tracking temperature measurement method, the steps of which are: capturing one or more image data and one or more thermal imaging data through an image capturing lens and a thermal infrared capturing lens; and then combining the image data Overlay matching and adjustment with the thermal imaging data; then face recognition is performed on the image data to obtain the face position, and then the face part is placed on the thermal imaging data for marking to obtain the temperature value of the face position, Face recognition is performed on the image data to obtain the position of the face. It is possible to first capture multiple attributes related to the face to obtain the position of the face, and then move the face in the frame of the image data. Track the position of the part to obtain one or more moving parameter coordinates. 如請求項13所述之人臉追蹤測溫方法,其中更能夠將追蹤之移動參數座標的臉部位置,依據一人臉比例數據進行判斷出該臉部位置上的人臉特徵大小及位置。 The face tracking temperature measurement method according to claim 13, wherein the face position of the tracked movement parameter coordinate can be further judged according to a face ratio data to determine the size and position of the face feature at the face position. 如請求項14所述之人臉追蹤測溫方法,其中該人臉特徵係能夠為額頭。 The face tracking temperature measurement method according to claim 14, wherein the face feature can be the forehead. 如請求項13所述之人臉追蹤測溫方法,其中能夠將臉部位置之外的熱源或/及將過大或是過小的臉部位置進行排除。 The face tracking temperature measurement method according to claim 13, wherein heat sources other than the position of the face or/and the position of the face that is too large or too small can be excluded. 如請求項13所述之人臉追蹤測溫方法,其中更能夠透過一校正數據與所偵測出之熱成像數據進行校正。 The face tracking temperature measurement method according to claim 13, wherein a correction data and the detected thermal imaging data can be used for correction. 如請求項17所述之人臉追蹤測溫方法,其中該校正數據係能夠透過一黑體輻射偵測器或是一額溫槍進行取得。 The face tracking temperature measurement method according to claim 17, wherein the calibration data can be obtained through a black body radiation detector or a forehead thermometer. 如請求項13所述之人臉追蹤測溫方法,其中更能夠紀錄通過人數、超溫人臉或是全畫面內容,用以能夠匯出為一資訊檔。The face tracking temperature measurement method described in claim 13, wherein the number of people passing by, over-temperature faces or full-screen content can be recorded, so as to be able to export as an information file.
TW109123929A 2020-07-15 2020-07-15 Face tracking temperature measurement system and method TWI732627B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
TW109123929A TWI732627B (en) 2020-07-15 2020-07-15 Face tracking temperature measurement system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW109123929A TWI732627B (en) 2020-07-15 2020-07-15 Face tracking temperature measurement system and method

Publications (2)

Publication Number Publication Date
TWI732627B true TWI732627B (en) 2021-07-01
TW202204860A TW202204860A (en) 2022-02-01

Family

ID=77911542

Family Applications (1)

Application Number Title Priority Date Filing Date
TW109123929A TWI732627B (en) 2020-07-15 2020-07-15 Face tracking temperature measurement system and method

Country Status (1)

Country Link
TW (1) TWI732627B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWM277919U (en) * 2003-12-03 2005-10-11 Avision Inc Temperature sensor
US7457441B2 (en) * 2005-02-25 2008-11-25 Aptina Imaging Corporation System and method for detecting thermal anomalies
CN103250037A (en) * 2010-11-17 2013-08-14 株式会社伊西特姆 Device and method for measuring temperature using infrared array sensors
TWM562100U (en) * 2018-02-14 2018-06-21 Zhang Han Wei Intelligent testing equipment
TWM602631U (en) * 2020-07-15 2020-10-11 麥威科技股份有限公司 Face tracking temperature measurement system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWM277919U (en) * 2003-12-03 2005-10-11 Avision Inc Temperature sensor
US7457441B2 (en) * 2005-02-25 2008-11-25 Aptina Imaging Corporation System and method for detecting thermal anomalies
CN103250037A (en) * 2010-11-17 2013-08-14 株式会社伊西特姆 Device and method for measuring temperature using infrared array sensors
TWM562100U (en) * 2018-02-14 2018-06-21 Zhang Han Wei Intelligent testing equipment
TWM602631U (en) * 2020-07-15 2020-10-11 麥威科技股份有限公司 Face tracking temperature measurement system

Also Published As

Publication number Publication date
TW202204860A (en) 2022-02-01

Similar Documents

Publication Publication Date Title
TWM602631U (en) Face tracking temperature measurement system
KR101729327B1 (en) A monitoring system for body heat using the dual camera
KR20180123900A (en) Method and apparatus for alarming thermal heat detection results obtained by monitoring heat from human using thermal scanner
US7548776B2 (en) Method and system for performing fever triage
KR20170050936A (en) A surveillance system for body heat by the dual camera using the black body
CN112033545B (en) Human body temperature infrared measurement method and device and computer equipment
CN111488775B (en) Device and method for judging degree of visibility
Budzan et al. Face and eyes localization algorithm in thermal images for temperature measurement of the inner canthus of the eyes
CN106096608B (en) Chest temperature anomaly area's localization method and device
US20220087536A1 (en) Temperature measurement method and measurement device
CN112131976A (en) Self-adaptive portrait temperature matching and mask recognition method and device
CN117268559B (en) Multi-mode infant abnormal body temperature detection method, device, equipment and medium
Chin et al. An infrared thermography model enabling remote body temperature screening up to 10 meters
Ward et al. Flunet: An ai-enabled influenza-like warning system
CN117373110A (en) Visible light-thermal infrared imaging infant behavior recognition method, device and equipment
Ruffin et al. Non-invasive low cost fever detection systems
Lazri et al. Detecting essential landmarks directly in thermal images for remote body temperature and respiratory rate measurement with a two-phase system
TWI732627B (en) Face tracking temperature measurement system and method
Scebba et al. Multispectral camera fusion increases robustness of ROI detection for biosignal estimation with nearables in real-world scenarios
Leñero-Bardallo et al. A customizable thermographic imaging system for medical image acquisition and processing
Rao et al. F 3 s: Free flow fever screening
Hsieh Development of a Low Cost and Raspberry-based Thermal Imaging System for Monitoring Human Body Temperature
Filipowicz et al. Analysis of the influence of external conditions on temperature readings in thermograms and adaptive adjustment of the measured temperature value
US11501560B2 (en) Infrared temperature measurement fused with facial identification in an access control system
Strąkowska et al. Automatic eye corners detection and tracking algorithm in sequence of thermal medical images