TWI801818B - Scoring device for drone examination room - Google Patents
Scoring device for drone examination room Download PDFInfo
- Publication number
- TWI801818B TWI801818B TW110107951A TW110107951A TWI801818B TW I801818 B TWI801818 B TW I801818B TW 110107951 A TW110107951 A TW 110107951A TW 110107951 A TW110107951 A TW 110107951A TW I801818 B TWI801818 B TW I801818B
- Authority
- TW
- Taiwan
- Prior art keywords
- image capture
- uav
- flight
- examination room
- drone
- Prior art date
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Aiming, Guidance, Guns With A Light Source, Armor, Camouflage, And Targets (AREA)
- Burglar Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
一種無人機考場評分裝置,提供應用在一無人機考場,該無人機考場包含一無人機飛行路線。該無人機考場評分裝置包括數個影像擷取模組、一鏡頭形變模組、一資料庫模組、一處理模組以及一微型發報位置設備所構成。藉此,本發明在遵守民航法規範之範疇下運用電子攝影影像處理技術、圖像校正、拼接演算法完成客觀之評分裝置,可降低考核爭議,並提供數位監評資訊有效協助無人機考試監評人員評定受測者是否具有良好的操控能力以完成監評工作,俾以客觀的數位監評資訊建置完善考場評分裝置以降低考核爭議,並增進無人機操作證考核公信力,進而順利推展無人機產業。 A scoring device for an unmanned aerial vehicle examination room is provided for application in an unmanned aerial vehicle examination room, and the unmanned aerial vehicle examination room includes a flight route of the unmanned aerial vehicle. The unmanned aerial vehicle examination room scoring device includes several image capture modules, a lens deformation module, a database module, a processing module and a miniature sending location device. In this way, the present invention uses electronic photography image processing technology, image correction, and splicing algorithm to complete an objective scoring device under the scope of complying with the civil aviation law, which can reduce assessment disputes, and provide digital monitoring and evaluation information to effectively assist UAV examination supervision. The evaluators assess whether the subjects have good control ability to complete the monitoring and evaluation work, so as to use objective digital monitoring and evaluation information to build and improve the examination room scoring device to reduce the evaluation controversy, and enhance the credibility of the UAV operation certificate evaluation, and then smoothly promote the unmanned machine industry.
Description
本發明係有關於一種無人機考場評分裝置,尤指涉及一種數位監評的評分系統,特別係指可為無人機操作證提供更具公信力的評估結果者。 The present invention relates to a scoring device for a drone examination room, in particular to a scoring system for digital monitoring and evaluation, especially to one that can provide more credible evaluation results for drone operating certificates.
根據民用航空法(遙控無人機專章)規定,操作無人機需要取得無人機操作證並規範學科與術科考試內容,然而目前術科測驗時,係由監評人員以目視方式主觀判定應試人是否純熟操作無人機達到各項考核規範,所以存在部分爭議。 According to the Civil Aviation Law (special chapter on remote control drones), operating a drone requires obtaining a drone operating certificate and standardizing the subject and technical examination content. However, in the current technical test, the supervisors visually judge whether the candidate is proficient The operation of drones has reached various assessment standards, so there are some disputes.
鑑於無人機法規已於2020年3月底開始實施,發展一套能有效協助無人機考試監評人員評定受測者是否具有良好的操控能力,並建立出標準的考試評定標準實有必要。 In view of the fact that drone regulations have been implemented at the end of March 2020, it is necessary to develop a system that can effectively assist drone test supervisors to assess whether the testee has good control ability and establish a standard test evaluation standard.
本發明之主要目的係在於,克服習知技藝所遭遇之上述問題並提供一種客觀的數位監評資訊建置完善考場評分裝置以降低考核爭議之無人機考場評分裝置。 The main purpose of the present invention is to overcome the above-mentioned problems encountered in the conventional technology and provide an objective digital monitoring and evaluation information to build a perfect examination room scoring device to reduce examination disputes.
本發明之另一目的係在於,提供一種可增進無人機操作證考核公信力,順利推展無人機產業之無人機考場評分裝置。 Another object of the present invention is to provide a scoring device for drone examinations that can enhance the credibility of the examination of drone operating certificates and smoothly promote the drone industry.
為達以上之目的,本發明係一種無人機考場評分裝置,提供應用 在一無人機考場,該無人機考場包含一無人機飛行路線,該無人機考場評分裝置包括:數個影像擷取模組,係分設在該無人機考場之不同位置以各自擷取一視野範圍中一無人機之影像,且各該影像擷取模組在該無人機考場對應其視野範圍設有一標定線;一鏡頭形變模組,係提供該些影像擷取模組擷取一校正板不同角度之影像,以計算各該影像擷取模組的一相機校正參數,該些相機校正參數為該些影像擷取模組的一內部參數、一鏡頭形變參數、及各影像的一外部參數;一資料庫模組,係儲存有數個提供該無人機依據不同的考試級別進行應考的飛行任務;一處理模組,連接該數個影像擷取模組、該鏡頭形變模組與該資料庫模組,該處理模組具有一座標轉換單元、一校正單元、及一運算單元,該處理模組係接收該些影像擷取模組所傳送之該些無人機影像及該鏡頭形變模組所傳送之該些相機校正參數,經由該座標轉換單元將該些無人機影像之一世界座標轉換為一相機座標後,再將該些無人機影像之相機座標轉換為一成像平面座標,該校正單元藉由該些相機校正參數所產生之一鏡頭形變模型,依據該鏡頭形變模型校正該些無人機影像之成像平面座標之位置,該運算單元依據一雙眼視覺與三角定位演算法計算出該無人機之深度資訊,運用該深度資訊標示出該無人機於該些無人機影像中之位置及距離,藉此檢測該無人機是否飛出該標定線,若飛出該標定線則發出警示通知,提供判斷該無人機是否需要重飛或判斷失格,並根據判斷結果決定是否進入下一級別的飛行任務,且在最後一項飛行任務時,透過從衛星定位發出之位置資訊進行判斷,當確定該無人機誤飛至考場後方則直接判斷該無人機失格;以及一微型發報位置設備,係裝載在考試用該無人機上,用以透過衛星定位對外發報位置資訊至該處理模組中,令該無人機的所在位置被知悉以協助該運算單元評分判斷。 In order to achieve the above purpose, the present invention is a scoring device for unmanned aerial vehicles examination room, which provides application In a UAV test room, the UAV test room includes a UAV flight path, and the UAV test room grading device includes: several image capture modules, which are set in different positions of the UAV test room to capture a field of view respectively An image of a drone in the range, and each image capture module has a calibration line corresponding to its field of view in the drone test room; a lens deformation module is provided for these image capture modules to capture a calibration plate Images from different angles to calculate a camera calibration parameter for each of the image capture modules, where the camera calibration parameters are an internal parameter of the image capture modules, a lens distortion parameter, and an external parameter of each image ; a database module, which stores several flight missions for the UAV to take the test according to different test levels; a processing module, which connects the several image capture modules, the lens deformation module and the database A module, the processing module has a coordinate conversion unit, a correction unit, and a computing unit, the processing module is to receive the UAV images transmitted by the image capture modules and the lens deformation module The transmitted camera correction parameters are converted into camera coordinates from the world coordinates of the UAV images by the coordinate conversion unit, and then the camera coordinates of the UAV images are converted into imaging plane coordinates. The correction unit A lens deformation model generated by the camera correction parameters is used to correct the positions of the imaging plane coordinates of the UAV images according to the lens deformation model, and the calculation unit calculates the UAV based on a binocular vision and triangulation algorithm. The depth information of the drone, using the depth information to mark the position and distance of the drone in the images of the drone, so as to detect whether the drone flies out of the calibration line, and if it flies out of the calibration line, a warning notice will be issued. It is provided to judge whether the UAV needs to be re-flyed or judged to be disqualified, and to decide whether to enter the next level of flight mission according to the judgment result, and in the last flight mission, it is judged by the position information sent from the satellite positioning. If the UAV flies to the back of the examination room by mistake, the UAV will be directly judged to be disqualified; and a miniature position sending device is mounted on the UAV used for the test, and is used to send position information to the processing module through satellite positioning, so that the The location of the drone is known to assist the calculation unit in scoring and judging.
於本發明上述實施例中,該運算單元係以該些影像擷取模組及該無人機之三角比例關係計算該深度資訊。 In the above embodiments of the present invention, the calculation unit calculates the depth information based on the triangular ratio relationship between the image capture modules and the drone.
於本發明上述實施例中,該校正板上係設有黑白格子交錯相間的一棋盤式圖形。 In the above-mentioned embodiment of the present invention, the correction board is provided with a checkerboard pattern of alternating black and white grids.
於本發明上述實施例中,該些影像擷取模組為廣角攝影機。 In the above embodiments of the present invention, the image capture modules are wide-angle cameras.
於本發明上述實施例中,該無人機為無人直昇機或無人多旋翼機時,該飛行任務依據考試級別為定點起降與四面懸停、8字水平圓飛行、側面懸停及前進與後退、矩形飛行、以及任務飛行。 In the above-mentioned embodiments of the present invention, when the UAV is an unmanned helicopter or an unmanned multi-rotor aircraft, the flight missions are fixed-point take-off and landing and four-sided hovering, 8-shaped horizontal circle flight, side hovering and forward and backward, according to the test level. Rectangular flight, and mission flight.
於本發明上述實施例中,該定點起降與四面懸停、該8字水平圓飛行、該側面懸停及前進與後退、及該矩形飛行其中一項飛行任務失格,則無法進入到該任務飛行。 In the above-mentioned embodiment of the present invention, if one of the flight missions of the fixed-point take-off and landing, hovering in all directions, the horizontal circle flight of figure 8, the side hovering and forward and backward flight, and the rectangular flight fails, the mission cannot be entered. flight.
於本發明上述實施例中,該任務飛行包括儀表飛行、航線飛行、及興趣點飛行。 In the above embodiments of the present invention, the mission flight includes instrument flight, route flight, and point-of-interest flight.
於本發明上述實施例中,該無人機為無人飛機時,該飛行任務依據考試級別為正常航線起飛、8字水平飛行、以及任務模式飛行。 In the above-mentioned embodiments of the present invention, when the UAV is an unmanned aircraft, the flight missions are based on the test levels of normal route takeoff, figure-of-eight level flight, and mission mode flight.
於本發明上述實施例中,該數個影像擷取模組之第一影像擷取模組及第二影像擷取模組分別設置在該無人機考場之對角且位在該無人機飛行路線之前後方,該數個影像擷取模組之第三影像擷取模組及第四影像擷取模組分別相鄰設置在該無人機考場之側邊且位在該無人機飛行路線之一側。 In the above-mentioned embodiment of the present invention, the first image capture module and the second image capture module of the plurality of image capture modules are respectively arranged at opposite corners of the UAV examination room and on the flight path of the UAV Front and rear, the third image capture module and the fourth image capture module of the several image capture modules are respectively adjacently arranged on the side of the drone examination room and located on one side of the drone flight path .
於本發明上述實施例中,該第一影像擷取模組及該第二影像擷取模組所擷取之視野範圍中各設有一L型標定線,該第三影像擷取模組及該第四影像擷取模組所擷取之共有視野範圍中設有二同心矩形標定線。 In the above-mentioned embodiments of the present invention, an L-shaped marking line is respectively provided in the field of view captured by the first image capture module and the second image capture module, and the third image capture module and the Two concentric rectangular marking lines are set in the shared field of view captured by the fourth image capturing module.
於本發明上述實施例中,該數個影像擷取模組之第一影像擷取模組、第二影像擷取模組及第三影像擷取模組分別設置在該無人機考場之側邊且位在該無人機飛行路線之一側。 In the above-mentioned embodiment of the present invention, the first image capture module, the second image capture module and the third image capture module of the plurality of image capture modules are respectively arranged on the side of the drone examination room And it is located on one side of the drone's flight path.
於本發明上述實施例中,該第一影像擷取模組與該第三影像擷取模組所擷取之視野範圍中各設有一垂直該無人機飛行路線之標定線,該第二影像擷取模組所擷取之視野範圍中設有一垂直該無人機飛行路線之中線標定線,並以該中線標定線為基準,該些標定線為飛行標定線。 In the above-mentioned embodiments of the present invention, the field of view captured by the first image capture module and the third image capture module are each provided with a calibration line perpendicular to the flight path of the drone, and the second image capture module In the field of view captured by the module, there is a marking line perpendicular to the midline of the flight path of the UAV, and the midline marking line is used as a reference, and these marking lines are flight calibration lines.
1:影像擷取模組 1: Image capture module
11:第一影像擷取模組 11: The first image capture module
12:第二影像擷取模組 12: The second image capture module
13:第三影像擷取模組 13: The third image capture module
14:第四影像擷取模組 14: The fourth image capture module
2:鏡頭形變模組 2: Lens deformation module
21:校正板 21: Calibration board
3:資料庫模組 3: Database module
4:處理模組 4: Processing module
41:座標轉換單元 41: Coordinate conversion unit
42:校正單元 42: Correction unit
43:運算單元 43: Operation unit
5:微型發報位置設備 5: Miniature transmitter position device
6:無人機考場 6: Drone examination room
61:無人機飛行路線 61: UAV flight route
7:無人機 7: Drone
C:L型標定線 C: L type calibration line
D:同心矩形標定線 D: Concentric rectangular calibration line
E:標定線 E: calibration line
F:中線標定線 F: midline calibration line
x c 、y c 、z c :相機座標 x c , y c , z c : camera coordinates
x w 、y w 、z w :世界座標 x w , y w , z w : world coordinates
xr、yr:平面座標 x r , y r : plane coordinates
p(xw ,yw ,zw):P點世界座標 p(x w , y w , z w ): the world coordinates of point P
p(xc ,yc ,zc):P點相機座標 p(x c , y c , z c ): camera coordinates of point P
Pr(xr ,yr):P點平面座標 P r (x r , y r ): plane coordinates of point P
f:焦距 f: focal length
[R|T]:相機外部參數 [R|T]: camera external parameters
第1圖,係本發明無人機考場評分裝置之方塊架構示意圖。 Figure 1 is a schematic diagram of the block structure of the drone examination room scoring device of the present invention.
第2圖,係本發明無人直昇機與無人多旋翼機術科測驗場地攝影機架設與視野示意圖。 Fig. 2 is a schematic diagram of the camera setup and field of view of the unmanned helicopter and the unmanned multi-rotor technique department test site of the present invention.
第3圖,係本發明無人飛機術科測驗場地攝影機架設與視野示意圖。 Fig. 3 is a schematic diagram of camera setup and field of view of the unmanned aircraft surgery test site of the present invention.
第4圖,係本發明無人直昇機與無人多旋翼機術科測驗場地攝影機擷取畫面與評分標定線示意圖。 Fig. 4 is a schematic diagram of the captured images and scoring calibration lines of the unmanned helicopter and the unmanned multi-rotor maneuvering department test field camera of the present invention.
第5圖,係本發明無人飛機術科測驗場地攝影機擷取畫面與評分標定線示意圖。 Fig. 5 is a schematic diagram of the camera capture picture and the scoring calibration line of the unmanned aircraft surgery test site of the present invention.
第6圖,係本發明之世界座標與相機座標示意圖。 Figure 6 is a schematic diagram of the world coordinates and camera coordinates of the present invention.
第7圖,係本發明之相機座標轉換成像平面座標示意圖。 Fig. 7 is a schematic diagram of the transformation of camera coordinates into imaging plane coordinates according to the present invention.
請參閱『第1圖~第7圖』所示,係分別為本發明無人機考場評分裝置之方塊架構示意圖、本發明無人直昇機與無人多旋翼機術科測驗場地攝
影機架設與視野示意圖、本發明無人飛機術科測驗場地攝影機架設與視野示意圖、本發明無人直昇機與無人多旋翼機術科測驗場地攝影機擷取畫面與評分標定線示意圖、本發明無人飛機術科測驗場地攝影機擷取畫面與評分標定線示意圖、本發明之世界座標與相機座標示意圖、以及本發明之相機座標轉換成像平面座標示意圖。如圖所示:本發明係一種無人機考場評分裝置,提供應用在一無人機考場6,該無人機考場6包含一無人機飛行路線61。該無人機考場評分裝置包括數個影像擷取模組1、一鏡頭形變模組2、一資料庫模組3、一處理模組4以及一微型發報位置設備5所構成。
Please refer to "Figures 1 to 7", which are schematic diagrams of the block structure of the scoring device for the UAV examination room of the present invention, and photographs of the test site for the unmanned helicopter and the unmanned multi-rotor aircraft of the present invention.
Schematic diagram of camera setup and field of view, schematic diagram of camera setup and field of view for the test field of unmanned aircraft of the present invention, schematic diagram of captured images and scoring calibration lines of the camera of the test field of unmanned helicopter and unmanned multi-rotor aircraft of the present invention, and camera of the test field of unmanned aircraft of the present invention Schematic diagram of captured screen and scoring calibration line, schematic diagram of world coordinates and camera coordinates of the present invention, and schematic diagram of conversion of camera coordinates into imaging plane coordinates of the present invention. As shown in the figure: the present invention is a scoring device for an unmanned aerial vehicle examination room, which is provided and applied in an unmanned aerial
上述所提之數個影像擷取模組1係分設在該無人機考場6之不同位置以各自擷取一視野範圍中一無人機7之影像,且各該影像擷取模組1在該無人機考場6對應其視野範圍設有一標定線。
The above-mentioned several
該鏡頭形變模組2係提供該些影像擷取模組1擷取一校正板21不同角度之影像,以計算各該影像擷取模組1的一相機校正參數,該些相機校正參數為該些影像擷取模組1的一內部參數、一鏡頭形變參數、及各影像的一外部參數。
The
該資料庫模組3係儲存有數個提供該無人機7依據不同的考試級別進行應考的飛行任務。
The
該處理模組4連接該數個影像擷取模組1、該鏡頭形變模組2與該資料庫模組3。該處理模組4具有一座標轉換單元41、一校正單元42、及一運算單元43。該處理模組4係接收該些影像擷取模組1所傳送之該些無人機影像及該鏡頭形變模組2所傳送之該些相機校正參數,經由該座標轉換單元41將該些無人機影像之一世界座標轉換為一相機座標後,再將該些無人機
影像之相機座標轉換為一成像平面座標,該校正單元42藉由該些相機校正參數所產生之一鏡頭形變模型(Brown-Conrady model),依據該鏡頭形變模型校正該些無人機影像之成像平面座標之位置,該運算單元43依據一雙眼視覺與三角定位演算法計算出該無人機7之深度資訊,運用該深度資訊標示出該無人機7於該些無人機影像中之位置及距離,藉此檢測該無人機7是否飛出該標定線,若飛出該標定線則發出警示通知,提供判斷該無人機7是否需要重飛或判斷失格,並根據判斷結果決定是否進入下一級別的飛行任務,且在最後一項飛行任務時,透過從衛星定位發出之位置資訊進行判斷,當確定該無人機7誤飛至考場後方則直接判斷該無人機7失格。
The
該微型發報位置設備5係裝載在考試用該無人機上,用以透過衛星定位對外發報位置資訊至該處理模組4中,令該無人機的所在位置被知悉以協助該運算單元43評分判斷。如是,藉由上述揭露之結構構成一全新之無人機考場評分裝置。
The miniature
本發明所提無人機考場評分裝置係以評定受測者基本操作能力為主。根據無人機種類型,其無人機考場6各有對應適用的無人機術科測驗場地,因此上述該些影像擷取模組1之架設與視野示意如第2、3圖所示,而其擷取畫面與評分標定線示意如第4、5圖所示。當該無人機為無人直昇機與無人多旋翼機時,該數個影像擷取模組1之第一影像擷取模組11及第二影像擷取模組12分別設置在該無人機考場6之對角且位在該無人機飛行路線61之前後方,該數個影像擷取模組1之第三影像擷取模組13及第四影像擷取模組14分別相鄰設置在該無人機考場6之側邊且位在該無人機飛行路線61之一側,如第2圖所示。並且,該第一影像擷取模組11及該第二影像擷取模組
12所擷取之視野範圍中各設有一L型標定線C,如第4圖(a)所示;該第三影像擷取模組13及該第四影像擷取模組14所擷取之共有視野範圍中設有二同心矩形標定線D,如第4圖(b)所示。當無人機為無人飛機時,該數個影像擷取模組1之第一影像擷取模組11、第二影像擷取模組12及第三影像擷取模組13分別設置在該無人機考場6之側邊且位在該無人機飛行路線61之一側,如第3圖所示。並且,該第一影像擷取模組11與該第三影像擷取模組13所擷取之視野範圍中各設有一垂直該無人機飛行路線61之標定線E,該第二影像擷取模組12所擷取之視野範圍中設有一垂直該無人機飛行路線61之中線標定線F,並以該中線標定線F為基準,該些標定線E為飛行標定線,如第5圖所示。
The grading device for the UAV examination room proposed by the present invention mainly focuses on evaluating the basic operation ability of the subject. According to the types of UAVs, the
本發明之評分準則,針對無人直昇機與無人多旋翼機術科測驗,在進行基本術科測驗動作時,係先利用第三影像擷取模組13及第四影像擷取模組14所拍攝之影像來計算無人機的距離(影像深度),運用深度資訊來檢測無人機是否飛出標定線D,若飛出標定線D則判定飛行失誤。當進行後續飛行任務項目時,會切換至第一影像擷取模組11及第二影像擷取模組12,若無人機飛出第一影像擷取模組11及第二影像擷取模組12之標定線C,則判定為飛行失誤。
The scoring criterion of the present invention is aimed at the unmanned helicopter and unmanned multi-rotor aircraft skill test, when performing the basic skill test action, first use the images taken by the third
本發明之評分準則,針對無人飛機術科測驗,係依據民航局無人機術科規範原則並根據考試級別將評分裝置設定不同模式。主要是以中線標定線F為基準,其餘二條標定線為飛行標定線,若規則中不允許無人飛機越中線標定線F或是越過標定線E還未起飛,本裝置將運用所擷取影像判斷快速提出警示通知,從而協助監評人員判斷受測者是否需要重飛或是失格。 The scoring criteria of the present invention is aimed at the unmanned aerial vehicle technical test, and is based on the principles of the civil aviation bureau's unmanned aerial vehicle technical test, and the scoring device is set in different modes according to the test level. It is mainly based on the centerline calibration line F, and the other two calibration lines are flight calibration lines. If the rules do not allow unmanned aircraft to cross the centerline calibration line F or cross the calibration line E before taking off, the device will use the captured The image judgment quickly provides a warning notice, thereby assisting the supervisors and evaluators to judge whether the subject needs to re-fly or be disqualified.
然而,由於所提影像擷取模組1為廣角攝影機,因此需要進行鏡頭形變修正,模擬相機成像情形建立鏡頭形變模型。其方式如下:
However, since the proposed
[世界座標轉換至相機座標] [Convert world coordinates to camera coordinates]
物件係以世界座標表示其位置,而世界座標與相機座標可能有所不同,可以藉由世界座標轉換至相機座標,利用旋轉、平移之方式完成。如第6圖所示,先將座標對X軸、Y軸、Z軸三種方向進行旋轉以對應相機座標,在此假設其分別是旋轉角度θ、Φ、ω,再來將世界座標的原點平移至相機座標原點即可完成,假設所需位移量為(t1 ,t2 ,t3),而以變換矩陣方式表示即如方程(1),其中x c 、y c 、z c 為相機座標,x w 、y w 、z w 為世界座標;為化簡方程(1),如方程(2)可將三個旋轉動作合併為一個旋轉矩陣R,再以齊次(homogeneous)表示可得方程(3),而其中[R|T]即為相機外部參數(extrinsic parameter)。 The position of an object is represented by world coordinates, and the world coordinates and camera coordinates may be different. It can be converted from world coordinates to camera coordinates, and completed by rotation and translation. As shown in Figure 6, the coordinates are first rotated in the three directions of X-axis, Y-axis, and Z-axis to correspond to the camera coordinates. Here, it is assumed that they are the rotation angles θ, Φ, and ω respectively, and then the origin of the world coordinates It can be completed by translating to the origin of the camera coordinates. Assume that the required displacement is (t 1 , t 2 , t 3 ), and expressed in the form of a transformation matrix is as in equation (1), where x c , y c , and z c are Camera coordinates, x w , y w , z w are world coordinates; in order to simplify Equation (1), such as Equation (2), the three rotation actions can be combined into one rotation matrix R, and then expressed by homogeneous Equation (3) is obtained, where [R|T] is the extrinsic parameter of the camera.
[相機座標轉換至成像平面座標] [Camera coordinates converted to imaging plane coordinates]
目標物P點由世界座標p(xw ,yw ,zw)轉換成相機座標p(xc ,yc ,zc),而依據相機的針孔成像原理,再以透射投影的方法將座標轉換至影像平面,其中為焦距f(focal length)、物體深度座標為zc,利用相似三角形的比例性質,可得方程(4)及方程 (5),而本發明可依此推算出目標物P點其成像平面座標Pr(xr ,yr),再加入比例參 數,即可表示成方程(6)之齊次方程式。 The point P of the target object is converted from the world coordinates p(x w , y w , z w ) to the camera coordinates p(x c , y c , z c ), and according to the pinhole imaging principle of the camera, the transmission projection method is used to The coordinates are converted to the image plane, where the focal length f (focal length) and the object depth coordinates are z c , using the proportional properties of similar triangles, equations (4) and equations (5) can be obtained, and the present invention can calculate the target according to this Object P point its imaging plane coordinates P r (x r , y r ), and then add the scale parameter , which can be expressed as the homogeneous equation of equation (6).
[鏡頭形變] [lens distortion]
相機的廣角鏡頭會使影像產生非線性的鏡頭形變(Lens Distortion),主要有徑向形變(radial distortion)以及切向形變(tangent distortion)兩種,徑向形變係由於透鏡中心及周圍厚薄不一的特性所產生,鏡片愈邊緣的部分光線通過時折彎愈大,愈靠近透鏡中心的光線則折彎較小,例如為了取得較大的視野範圍時,常會利用廣角或與魚眼鏡頭進行拍攝,所拍攝的照片因為徑向形變產生的桶狀變形(Barrel distortion)就非常明顯,而使用變焦鏡望遠端時則可能因為徑向形變而產生枕狀變形;而切向形變則是由於相機模組組裝的誤差所造成,例如鏡片與感應器不平行,進而使成像產生似梯形的形變。 The wide-angle lens of the camera will cause non-linear lens distortion (Lens Distortion) in the image, mainly including radial distortion and tangent distortion. Radial distortion is due to the different thickness of the lens center and surrounding Due to the characteristics of the lens, the part of the light at the edge of the lens is bent more when it passes through, and the light that is closer to the center of the lens is bent less. The barrel distortion (Barrel distortion) caused by the radial deformation in the photos taken is very obvious, and when using the telephoto end of the zoom lens, it may produce pincushion distortion due to the radial deformation; while the tangential deformation is due to the assembly of the camera module Caused by the error, for example, the lens is not parallel to the sensor, and then the imaging produces a trapezoidal deformation.
鏡頭形變模型: Lens Distortion Model:
徑向形變模型如方程(7):x=x r (1+k 1 r 2+k 2 r 4+k 3 r 6) y=y r (1+k 1 r 2+k 2 r 4+k 3 r 6) (7)
切向形變模型如方程(8):
[計算鏡頭形變模型參數] [Calculate lens deformation model parameters]
最後將桶狀變形中的方程(6),加入對感測元件像素長寬比sx、sy(pixel aspect ratio)的修正,並也在此使單位轉換為像素(pixel),而為了使影像的中心(principal point)落在光軸(principal axis)上,可能須要位移(cx ,cy)來調整影像中心,最終將方程(6)調整成如下方程(11),其中A即為相機的內部參數(intrinsic parameter)。 Finally, the equation (6) in the barrel deformation is added to the correction of the pixel aspect ratio s x and s y (pixel aspect ratio) of the sensing element, and the unit is also converted into a pixel (pixel), and in order to make The image center (principal point) falls on the optical axis (principal axis), and displacement (c x , c y ) may be required to adjust the image center. Finally, equation (6) is adjusted to the following equation (11), where A is The intrinsic parameters of the camera.
而為了取得鏡頭形變模型裡所需的各參數,可使用黑白格子交錯相間為一棋盤式圖形之校正板,以影像擷取裝置拍攝數張校正板不同角度的影像,偵測各影像格子點後,依這些格子點資訊進行運算後即可取得內部參數、鏡頭形變參數k1,k2,p1,p2,k3、各影像的外部參數等這些相機校正參數。而利用這樣的鏡頭形變模型即可對影像進行校正。 In order to obtain the parameters required in the lens deformation model, a checkerboard-like calibration plate with black and white grids alternated with each other can be used, and several images of the calibration plate at different angles can be taken by the image capture device, and after detecting the grid points of each image , camera correction parameters such as internal parameters, lens distortion parameters k 1 , k 2 , p 1 , p 2 , k 3 , and external parameters of each image can be obtained after calculations are performed based on the grid point information. The image can be corrected by using such a lens deformation model.
本發明再運用雙眼視覺與三角定位演算法計算距離深度,如下公式(13)、(14)。其中CL與CR為左右攝影機鏡頭;f為攝影機焦距;PL與PR為目標點
投影在成像平面上後之投影點。XL與XR分別為PL與PR投影點到所屬成像平面之中心點之距離;B是兩攝影機鏡頭之水平距離。依照三角形等比例之原理,可以導出下面的公式(13)、(14),找出深度:
運用深度Z標示出無人機於影像中的位置,當位置偏離標定線,即提醒監評人員判斷是否要求受測者重新飛行或判斷考試未通過。 Use the depth Z to mark the position of the drone in the image. When the position deviates from the calibration line, it will remind the supervisor to judge whether to ask the subject to re-fly or judge that the test has failed.
本發明之評分流程,針對無人直昇機與無人多旋翼機術科測驗,當無人直昇機與無人多旋翼機起飛後,依據考試級別不同,分別進行如下步驟: The scoring process of the present invention is aimed at the test of unmanned helicopter and unmanned multi-rotor aircraft. After the unmanned helicopter and unmanned multi-rotor aircraft take off, the following steps are performed according to the different test levels:
步驟一:進行定點起降與四面停懸。 Step 1: Carry out fixed-point take-off and landing and four-sided hovering.
步驟二:進行8字水平圓飛行(切換至第一、二影像擷取模組判讀,超過範圍來不及修正回來,必須要重新飛行或失格)。 Step 2: Fly in a figure-of-eight horizontal circle (switch to the first and second image capture modules for interpretation, if the range is exceeded and it is too late to correct it, you must fly again or be disqualified).
步驟三:進行側面懸停及前進與後退(以第三、四影像擷取模組開始判讀,無人機飛行距離不足或是超出範圍,造成來不及修正回來,必須要重新飛行或失格)。 Step 3: Carry out lateral hovering and forward and backward (use the third and fourth image capture modules to start the interpretation, the flight distance of the drone is insufficient or out of range, and it is too late to correct it, and it must be re-flyed or disqualified).
步驟四:進行矩形飛行(以第三、四影像擷取模組判讀,無人機飛行距離不足或是超出範圍,造成來不及修正回來,必須要重新飛行或失格)。 Step 4: Carry out rectangular flight (according to the interpretation of the third and fourth image capture modules, the flight distance of the drone is insufficient or out of range, causing it to be too late to correct and must be re-flyed or disqualified).
步驟五:進行任務飛行,包含儀表飛行、航線飛行、興趣點飛行(此時裝置轉以運用微型發報位置設備進行判斷,當認無人機誤飛至考場後方,即為失格)。 Step 5: Carry out mission flight, including instrument flight, route flight, and point-of-interest flight (at this time, the device switches to use the micro-transmission location device for judgment. If the UAV is mistakenly flown to the rear of the examination room, it will be disqualified).
當前述步驟一至步驟四其中一項飛行任務失格,則無法進入到步驟五的任務飛行。而該微型發報位置設備係在不影響無人機操控前提下,進行發報位置資訊到處理模組中協助評分。
When one of the above-mentioned
本發明之評分流程,針對無人飛機術科測驗,依據考試級別不同,分別進行如下步驟: The scoring process of the present invention is aimed at the unmanned aircraft technical test, and according to the different test levels, the following steps are carried out respectively:
步驟一:進行正常航線起飛(以第一三影像擷取模組判斷是否起飛與起飛角度不得超過規定)。 Step 1: Take off on a normal route (use the first and third image capture modules to determine whether the takeoff and the takeoff angle must not exceed the regulations).
步驟二:進行8字水平飛行。 Step 2: Carry out figure-of-eight level flight.
步驟三:進行任務模式飛行。 Step 3: Fly in mission mode.
步驟四:結束飛行任務(超過第二影像擷取模組未降落,即為失格)。 Step 4: End the flight mission (if the second image capture module has not landed, it will be disqualified).
運用微型發報位置設備在不影響無人機操控前提下,進行發報位置資訊到處理模組中協助評分。 Use the micro-transmitting location device to send location information to the processing module to assist in scoring without affecting the control of the drone.
藉此,本發明在遵守民航法規範之範疇下運用電子攝影影像處理技術、圖像校正、拼接演算法完成客觀之評分裝置,可降低考核爭議,並提供數位監評資訊輔助監評人員完成監評工作。 In this way, the present invention uses electronic photography image processing technology, image correction, and splicing algorithm to complete the objective scoring device under the scope of complying with the civil aviation law, which can reduce assessment disputes and provide digital monitoring and evaluation information to assist the monitoring and evaluating personnel to complete the monitoring. evaluation work.
因此,本裝置係一種涉及數位監評的評分系統,可為無人機操作證提供更具公信力的評估結果,包含: Therefore, this device is a scoring system involving digital monitoring and evaluation, which can provide more credible evaluation results for UAV operation certificates, including:
1.可提供客觀的數位監評資訊建置完善考場評分裝置以降低考核爭議。 1. Can provide objective digital monitoring and evaluation information, build and improve the examination room scoring device to reduce examination disputes.
2.可增進無人機操作證考核公信力,順利推展無人機產業。 2. It can enhance the credibility of the UAV operation certificate examination and smoothly promote the UAV industry.
綜上所述,本發明係一種無人機考場評分裝置,可有效改善習用之種種缺點,有效協助無人機考試監評人員評定受測者是否具有良好的操控能力,並建立出標準的考試評定標準,進而使本發明之產生能更進步、更實用、更符合使用者之所須,確已符合發明專利申請之要件,爰依法提出專利申請。 To sum up, the present invention is a scoring device for drone examinations, which can effectively improve various disadvantages commonly used, effectively assist drone test supervisors to assess whether the testee has good control ability, and establish standard test evaluation standards , so that the production of the present invention can be more advanced, more practical, and more in line with the needs of users, and it has indeed met the requirements of the invention patent application, and the patent application is filed in accordance with the law.
惟以上所述者,僅為本發明之較佳實施例而已,當不能以此限定本發明實施之範圍;故,凡依本發明申請專利範圍及發明說明書內容所作之簡 單的等效變化與修飾,皆應仍屬本發明專利涵蓋之範圍內。 But what is described above is only a preferred embodiment of the present invention, and should not limit the scope of the present invention with this; Any single equivalent change and modification shall still fall within the scope covered by the patent of the present invention.
1:影像擷取模組 1: Image capture module
2:鏡頭形變模組 2: Lens deformation module
21:校正板 21: Calibration board
3:資料庫模組 3: Database module
4:處理模組 4: Processing module
41:座標轉換單元 41: Coordinate conversion unit
42:校正單元 42: Correction unit
43:運算單元 43: Operation unit
5:微型發報位置設備 5: Miniature transmitter position device
7:無人機 7: Drone
Claims (12)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110107951A TWI801818B (en) | 2021-03-05 | 2021-03-05 | Scoring device for drone examination room |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110107951A TWI801818B (en) | 2021-03-05 | 2021-03-05 | Scoring device for drone examination room |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202236213A TW202236213A (en) | 2022-09-16 |
TWI801818B true TWI801818B (en) | 2023-05-11 |
Family
ID=84957198
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW110107951A TWI801818B (en) | 2021-03-05 | 2021-03-05 | Scoring device for drone examination room |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI801818B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018077050A1 (en) * | 2016-10-27 | 2018-05-03 | 深圳市道通智能航空技术有限公司 | Target tracking method and aircraft |
CN110060187A (en) * | 2019-04-19 | 2019-07-26 | 北方天途航空技术发展(北京)有限公司 | Unmanned plane examination assessment method and system |
TWM588088U (en) * | 2019-08-12 | 2019-12-21 | 長榮大學 | License test site setup device for multirotor drone |
CN111563689A (en) * | 2020-05-15 | 2020-08-21 | 吕静 | Aircraft operation scoring method and system |
CN112184512A (en) * | 2020-10-22 | 2021-01-05 | 广东中和时代科技有限公司 | Examination system of police unmanned aerial vehicle |
-
2021
- 2021-03-05 TW TW110107951A patent/TWI801818B/en active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018077050A1 (en) * | 2016-10-27 | 2018-05-03 | 深圳市道通智能航空技术有限公司 | Target tracking method and aircraft |
CN110060187A (en) * | 2019-04-19 | 2019-07-26 | 北方天途航空技术发展(北京)有限公司 | Unmanned plane examination assessment method and system |
TWM588088U (en) * | 2019-08-12 | 2019-12-21 | 長榮大學 | License test site setup device for multirotor drone |
CN111563689A (en) * | 2020-05-15 | 2020-08-21 | 吕静 | Aircraft operation scoring method and system |
CN112184512A (en) * | 2020-10-22 | 2021-01-05 | 广东中和时代科技有限公司 | Examination system of police unmanned aerial vehicle |
Also Published As
Publication number | Publication date |
---|---|
TW202236213A (en) | 2022-09-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106767706A (en) | A kind of unmanned plane reconnoitres the Aerial Images acquisition method and system of the scene of a traffic accident | |
CN102509261A (en) | Distortion correction method for fisheye lens | |
CN103852060B (en) | A kind of based on single visual visible images distance-finding method felt | |
JP2018160228A (en) | Route generation device, route control system, and route generation method | |
CN108140066B (en) | Drawing making device and drawing making method | |
JP2004037270A (en) | Data measuring device, method and program for calibration, computer readable recording medium and image data processing device | |
CN112949478A (en) | Target detection method based on holder camera | |
WO2020218066A1 (en) | Inspection system | |
CN109191533B (en) | Tower crane high-altitude construction method based on fabricated building | |
WO2021135854A1 (en) | Method and apparatus for performing ranging measurement using unmanned aerial vehicle | |
CN112135120B (en) | Virtual image information measuring method and system based on head-up display system | |
Peng et al. | Unmanned Aerial Vehicle for infrastructure inspection with image processing for quantification of measurement and formation of facade map | |
JP2017116453A (en) | Inspection method of structure using drone | |
CN111986267B (en) | Coordinate system calibration method of multi-camera vision system | |
CN110763697A (en) | Method for detecting engineering structure surface crack by using aircraft | |
CN111244822A (en) | Fixed-wing unmanned aerial vehicle line patrol method, system and device in complex geographic environment | |
CN110044266B (en) | Photogrammetry system based on speckle projection | |
CN105784346A (en) | Aircraft holder stability testing device and method based on digital camera | |
CN110274752A (en) | The Multifunctional test card and its test method of relay lens image quality | |
TWI801818B (en) | Scoring device for drone examination room | |
JP2010217984A (en) | Image detector and image detection method | |
CN116678322A (en) | Crack width measurement method and system considering parallel laser beam inclination angle | |
US6963666B2 (en) | Matching device | |
RU2692970C2 (en) | Method of calibration of video sensors of the multispectral system of technical vision | |
CN115328181A (en) | Method for positioning key target space in unmanned aerial vehicle power transmission line inspection |