TWI728469B - Teaching path module for mobile vehicles - Google Patents

Teaching path module for mobile vehicles Download PDF

Info

Publication number
TWI728469B
TWI728469B TW108133575A TW108133575A TWI728469B TW I728469 B TWI728469 B TW I728469B TW 108133575 A TW108133575 A TW 108133575A TW 108133575 A TW108133575 A TW 108133575A TW I728469 B TWI728469 B TW I728469B
Authority
TW
Taiwan
Prior art keywords
mobile vehicle
path
arithmetic unit
storage
receiver
Prior art date
Application number
TW108133575A
Other languages
Chinese (zh)
Other versions
TW202012884A (en
Inventor
張國文
何彥緯
Original Assignee
台灣塔奇恩科技股份有限公司
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 台灣塔奇恩科技股份有限公司 filed Critical 台灣塔奇恩科技股份有限公司
Publication of TW202012884A publication Critical patent/TW202012884A/en
Application granted granted Critical
Publication of TWI728469B publication Critical patent/TWI728469B/en

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0217Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with energy consumption, time reduction or distance reduction criteria
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • G05D1/0251Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Multimedia (AREA)
  • Electromagnetism (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Image Analysis (AREA)

Abstract

一種移動載具之教導路徑模組,所述移動載具為可移動的機器人或車體,該模組包括一視覺感測元件與一接收器、一運算器及一儲存器,該接收器接收遠端發送的指示命令,教導移動載具行走指示的路徑,該視覺感測元件作為拍攝影像,並將移動載具行走的路徑以連續拍攝影像,並且將該連續拍攝影像資料傳到該運算器,該運算器計算出路徑提供指導路徑給儲存器,該儲存器將指導路徑提供給移動的載具,藉此提供該移動載具以進行移動者。 A teaching path module for a mobile vehicle. The mobile vehicle is a movable robot or a vehicle body. The module includes a visual sensing element and a receiver, an arithmetic unit, and a storage. The receiver receives The instruction command sent by the remote end teaches the path of the mobile vehicle's walking instructions. The visual sensing element is used as a shooting image, and the path of the mobile vehicle is used to continuously shoot images, and the continuous shooting image data is transmitted to the computing unit The arithmetic unit calculates the path to provide a guidance path to the storage, and the storage provides the guidance path to the moving vehicle, thereby providing the moving vehicle for the mover.

Description

移動載具之教導路徑模組 Teaching path module for mobile vehicles

本發明作為移動載具之教導路徑模組,是指可設於移動載具上的模組,所述移動載具包括移動式機器人或是車體,該模組是作為移動載具位移到目的位置的路徑的指導模組,模組的數據計算方法是運用拍攝連續擷取之影像運算出特徵點,再由運算器以該特徵點計算出到達目的地行走路徑,藉此提供移動載具位移的方向路徑。 The present invention, as a teaching path module for a mobile vehicle, refers to a module that can be installed on a mobile vehicle. The mobile vehicle includes a mobile robot or a vehicle body. The module is used as a mobile vehicle to move to a destination. The guidance module of the location path. The data calculation method of the module is to calculate the characteristic points using the images continuously captured by shooting, and then the computing unit uses the characteristic points to calculate the walking path to the destination, thereby providing the displacement of the mobile vehicle Direction path.

現有在工廠或高爾夫球場或餐廳等,已有需要利用移動載具來替代人類載運貨品或巡邏監視等工作,目前這些區域所使用的移動載具的行走路徑模組設有感應元件,是藉由在路徑的轉向重點位置上設有多個感測器或紅外線或者是QR Code等對應元件,藉此以提供移動載具的行走路徑上由感應元件與對應元件進行信息配對以進行固定路徑的位移,然而這樣的指引路徑的對應元件必須要設在所有必要轉折位置上,因此所需的對應元件數量眾多,如該對應元件其中有一個故障,則該移動載具就無法進行移動。 At present, in factories, golf courses, restaurants, etc., it is necessary to use mobile vehicles to replace humans to carry goods or patrol and monitor tasks. At present, the walking path modules of mobile vehicles used in these areas are equipped with sensing elements. There are multiple sensors or corresponding components such as infrared or QR Code on the turning key position of the path, so as to provide the moving path of the mobile vehicle. The sensor components and the corresponding components are matched with information to carry out the displacement of the fixed path. However, such corresponding elements for guiding the path must be located at all necessary turning positions. Therefore, there are a large number of corresponding elements required. If one of the corresponding elements fails, the mobile carrier cannot be moved.

以及,當這些工作區域遇到火災時,或者是工作區環境路徑變更,則所述對應元件無法與移動載具的感應元件達成配對;以及,這些感應元件必須設置在固定位置上,若移動載具變更執行環境位置,則必須重新建置這些感應元件於相對應的位置上。 And, when these work areas encounter a fire, or the environment path of the work area changes, the corresponding elements cannot be matched with the sensing elements of the mobile vehicle; and these sensing elements must be set in a fixed position. If the location of the execution environment is changed, these sensing elements must be re-established at the corresponding locations.

亦有運用GPS進行路徑導航,但GPS的定位精度約在數公尺範圍,且如果機器人在室內移動工作,甚至穿梭於建築物內外或樓層之間,這些GPS無法精確提供移動載具移動並執行工作。 GPS is also used for route navigation, but the positioning accuracy of GPS is about a few meters, and if the robot moves indoors, or even shuttles inside and outside buildings or between floors, these GPSs cannot accurately provide mobile vehicles to move and execute. jobs.

為此,本創作為改良習知的缺點,運用攝影取得影像建立特徵點影像,以取得導航路徑,以影像特徵點計算指導路徑,不需要強大的運算與大型儲存器,可以達到運算快速的需求。 Therefore, in order to improve the conventional shortcomings, this creation uses photography to obtain images to create feature point images to obtain the navigation path, and use the image feature points to calculate the guiding path. It does not require powerful calculations and large storage, and can meet the needs of fast calculations. .

本發明運用視覺圖像的方式來建立起教導路徑的資料,所儲存資料為視覺圖像特徵點產生的固定路徑,只儲存特徵點產生的路徑資料使數據資訊量最小化為目的。 The present invention uses visual images to establish teaching path data. The stored data is a fixed path generated by the feature points of the visual image, and only the path data generated by the feature points are stored for the purpose of minimizing the amount of data information.

本發明移動載具之位置確認模組,採取一種指導路徑定位目的地的方式,其利於快速儲存及讀取後可以快速比對;以及,提供運算器快速地將儲存器內舊有資料進行比對,來更新儲存器,以產生最新的路徑更新。 The position confirmation module of the mobile vehicle of the present invention adopts a guide path to locate the destination, which facilitates quick storage and quick comparison after reading; and provides a calculator to quickly compare the old data in the storage Yes, to update the storage to generate the latest path update.

本發明移動載具之教導路徑模組,該移動載具設有一驅動裝置與一控制器,該教導路徑模組以電路或是以無線傳輸的方式連接組裝於移動載具的該控制器;所述教導路徑模組包括:一視覺感測元件與一接收器與一運算器及一儲存器,該接收器為接收遠端發送教導路徑的訊息,並提供給移動載具進行移動 的行走方向;以及,該視覺感測元件電路連接運算器,該運算器連結該儲存器,該儲存體係供作儲存記錄路徑資料的回存與提取;以及,該視覺感測元件包括一個攝像鏡頭;以及,該視覺感測元件作為配置於該移動載具的任意表面上;以及,該視覺感測元件藉由該攝像鏡頭將接收器接收指引移動載具行走路徑進行連續拍攝影像,並提供將得到多張影像傳輸給該運算器,該運算器將多張影像取得的特徵點計算,以取得指導路徑,並將該指導路徑儲存到儲存器,這個運算指導路徑特定流程包括以FAST、HARRIS、GFTT、SIFT等適當方法,藉由該方法取出照片中的二維特徵點,並使用如Fundamental Matrix投影幾何方法,利用二維特徵點在不同照片中的視差,計算出特徵點在三維中的位置,稱為三維特徵點和移動載具所在地的位姿,如此該移動載具的位姿與當時的二維特徵點與該二維特徵點對應的該三維特徵點,將建構起對應的關係,將該關係路徑資料一併存入儲存於儲存器中,將可供後續使用;以及,該儲存器僅記錄由影像輪廓產生的二維特徵點、三維特徵點與移動載具的進行行走的路徑關係資料,因此儲存資料空間很小,因該路徑關係資料比全息影像資料更直覺簡單,所以當重新載入時能快速的比對出移動載具目前的位置,讓移動載具能快速取得所在位置,並因此依照指導路徑定位並被教導進行下一步行走路徑以達到目的地;又,該指導路徑資料建立所需的儲存器儲存空間較少,因此在進行讀取儲存器快速,所以進行比對移動載具當下定位時能有最快的搜尋指導路徑及較準確的定位精度。The teaching path module of the mobile vehicle of the present invention is provided with a driving device and a controller, and the teaching path module is connected to the controller assembled on the mobile vehicle by means of electric circuit or wireless transmission; The teaching path module includes: a visual sensing element, a receiver, an arithmetic unit, and a memory, the receiver is for receiving the message of the teaching path sent by the remote end, and providing the traveling direction of the mobile vehicle to move; And, the visual sensing element circuit is connected to an arithmetic unit, the arithmetic unit is connected to the storage, and the storage system is used for storing and retrieving record path data; and, the visual sensing element includes a camera lens; and, the The visual sensing element is arranged on any surface of the mobile carrier; and, the visual sensing element uses the camera lens to receive and guide the receiver to guide the walking path of the mobile carrier to continuously shoot images, and provide multiple images to be obtained Transmit to the arithmetic unit, the arithmetic unit calculates the feature points obtained from multiple images to obtain the guidance path, and stores the guidance path in the memory. The specific process of this calculation guidance path includes FAST, HARRIS, GFTT, SIFT, etc. Appropriate method, by using this method to take out the two-dimensional feature points in the photo, and use the Fundamental Matrix projection geometry method to use the parallax of the two-dimensional feature points in different photos to calculate the position of the feature points in three dimensions, which is called three-dimensional The feature point and the pose where the mobile vehicle is located, so that the pose of the mobile vehicle and the current two-dimensional feature point and the three-dimensional feature point corresponding to the two-dimensional feature point will construct a corresponding relationship, and the relationship path The data is stored in the memory and will be available for subsequent use; and the memory only records the two-dimensional feature points, three-dimensional feature points generated by the image outline and the path relationship data of the moving vehicle, so it is stored The data space is small, because the path relationship data is more intuitive and simple than the holographic image data, so when reloading, the current position of the mobile vehicle can be quickly compared, so that the mobile vehicle can quickly obtain the location, and therefore follow The guiding path is positioned and taught to proceed to the next walking path to reach the destination; in addition, the storage space required for the establishment of the guiding path data is less, so the reading of the storage is fast, so the current comparison of the mobile vehicle is carried out When positioning, it can have the fastest search and guidance path and more accurate positioning accuracy.

1‧‧‧視覺感測元件 1‧‧‧Visual sensor

2‧‧‧接收器 2‧‧‧Receiver

3‧‧‧運算器 3‧‧‧Computer

4‧‧‧儲存器 4‧‧‧Storage

P1、P2‧‧‧特徵點 P1, P2‧‧‧Feature points

Pi‧‧‧三維特徵點 Pi‧‧‧Three-dimensional feature points

O1、O2‧‧‧位姿 O1, O2‧‧‧Position

第一圖 為本創作之模組運作流程。 The first picture is the operation flow of the module for this creation.

第二圖 為本創作實施利方塊圖。 The second picture is a block diagram for the creation and implementation of the game.

第三圖 為本創作特徵點對應關係圖。The third picture is the corresponding relationship diagram of the creative feature points.

本發明移動載具之教導路徑模組,請參閱第一圖所示,所述移動載具A包含移動式機器人或運輸機具,所述教導路徑模組B是作為組裝於移動載具A的內建電子元件內,其提供移動載具A所在位置辨識與姿態的教導功能元件,該教導路徑模組B包括一視覺感測元件1與一接收器2及一運算器3與一儲存器4,該視覺感測元件1電子線路連結該接收器2與該運算器3,該運算器3電子線路連接該儲存器4;以及,其連接方法可為直接電路連接電路板上的線路,或網路無線連結,或其它的通訊連結;所述無線連接的實施是指該運算器3可為設於模組之外,如第二圖所示,該運算器3設置於一控制主機端C,藉由無線發送或網路雲端,將運算器3的計算路徑訊息傳送到該接收器2,再由該接收器2將路徑訊息儲存到儲存器4,藉此該儲存器4提供存取路徑資訊,待移動載具欲進行移動時,再由接收器2經由儲存器4取得的以儲存預定的路徑資訊提供給移動載具,以供移動載具A依照指定路徑進行移動;以及,該視覺感測元件1包括一鏡頭,該攝影鏡頭裝設於移動載具A之任一表面位置處,作為拍攝該載具所在的環境的景物功能,該攝影鏡頭連續拍攝數張影像,並將所得影像傳到該運算器3,所述運算器3從該視覺感測元件1拍攝之二維影像中,擷取出離散的二維特徵點,並依據該連續取得影像的特徵找出同一個空間點位在不同影像上的二維座標,由於移動載具的在移動位置影像產生視差,這些二維特徵點在每一張影像上的二維座標會因此改變,並以該連續取得的二維特徵點數據利用投影的方法計算出特徵點在空間中的真實三維空間位置與移動載具本身的位姿,所述位姿是指移動載具在三維空間中朝向的方向,常用數學表達方向方式有歐拉角、三維正交矩陣、單位四元數;以及,該視覺感測元件的相機模組在工作時,會持續拍攝移動載具當下環境的影像,並將拍攝數據傳給運算器,並重覆依上述方法計算出新的二維特徵點與三維特徵點與移動載具新的位姿,並將這些數據與關係的資料儲存入所述的儲存器中更新,而不需要重新建立整個儲存器4。 For the teaching path module of the mobile vehicle of the present invention, please refer to the first figure. The mobile vehicle A includes a mobile robot or a conveying machine, and the teaching path module B is assembled in the mobile vehicle A. Built in electronic components, it provides teaching functional components for position recognition and posture of the mobile carrier A. The teaching path module B includes a visual sensor component 1 and a receiver 2 as well as an arithmetic unit 3 and a storage 4, The electronic circuit of the visual sensing element 1 connects the receiver 2 and the arithmetic unit 3, and the electronic circuit of the arithmetic unit 3 is connected to the storage 4; and the connection method can be a direct circuit connection to a circuit on a circuit board, or a network Wireless connection, or other communication connection; the implementation of the wireless connection means that the arithmetic unit 3 can be installed outside the module, as shown in the second figure, the arithmetic unit 3 is disposed on a control host terminal C, by By wireless transmission or network cloud, the calculation path information of the arithmetic unit 3 is transmitted to the receiver 2, and the receiver 2 stores the path information in the storage 4, so that the storage 4 provides access path information. When the mobile vehicle wants to move, the receiver 2 obtains the predetermined path information through the storage 4 and provides it to the mobile vehicle to store the predetermined path information, so that the mobile vehicle A can move according to the designated path; and, the visual sensing Component 1 includes a lens, the photographic lens is installed at any surface position of the mobile carrier A, as a function of shooting the environment where the vehicle is located, the photographic lens continuously shoots several images, and the resulting image is transmitted to The arithmetic unit 3, the arithmetic unit 3 extracts discrete two-dimensional feature points from the two-dimensional image taken by the visual sensor element 1, and finds out the same spatial point in different locations according to the feature of the continuously acquired image The two-dimensional coordinates on the image, due to the parallax caused by the moving image of the moving vehicle, the two-dimensional coordinates of these two-dimensional feature points on each image will be changed accordingly, and the continuously obtained two-dimensional feature point data will be used The projection method calculates the true three-dimensional space position of the feature point in space and the pose of the mobile vehicle itself. The pose refers to the direction the mobile vehicle faces in the three-dimensional space. Commonly used mathematical expressions include Euler angles. , Three-dimensional orthogonal matrix, unit quaternion; and, when the camera module of the visual sensing element is working, it will continuously shoot the image of the current environment of the mobile vehicle, and transmit the shooting data to the computing unit, and repeat the above The method calculates new two-dimensional feature points and three-dimensional feature points and the new pose of the mobile vehicle, and stores these data and relational data in the storage for updating, without the need to rebuild the entire storage 4.

該運算器3分析若在一位置附近有大量類似或重覆的特徵點時,經連結該儲存器的資料比對後,則會自動將部份相似或重疊的特徵點或位姿關係等資訊從儲存器中刪除,以降低資料佔據儲存器空間。 The calculator 3 analyzes that if there are a large number of similar or repeated feature points near a location, after linking the data of the memory, it will automatically compare the partially similar or overlapping feature points or pose relations and other information Delete from storage to reduce data occupying storage space.

該視覺感測元件能透過電路、網路、行動通訊等方式,取得影像資料傳輸給運算器。 The visual sensing element can obtain image data and transmit it to the computing unit through circuits, networks, mobile communications and other methods.

以上運算器3取得影像資訊,包括:特徵點描述、特徵點在影像中的二維座標、特徵點在空間的三維座標、移動載具曾經走過的位置與當時的姿態等,運算器3將資訊組合成路徑檔案並預存於儲存器4,在移動載具A暫停或重新啟動或失去位置時,運算器3可根據此儲存器4的內容來比對當下拍到影像中取出的二維特徵點,藉此計算出移動載具A當下所在的路徑位置,並將該路徑位置訊息傳送給移動載具A的驅動裝置以供其繼續移動工作。 The above arithmetic unit 3 obtains image information, including: the description of the feature point, the two-dimensional coordinates of the feature point in the image, the three-dimensional coordinate of the feature point in space, the position where the mobile vehicle has walked and the current posture, etc., the computing unit 3 will The information is combined into a path file and pre-stored in the memory 4. When the mobile vehicle A is suspended or restarted or loses its position, the computing unit 3 can compare the two-dimensional features extracted from the current captured image according to the contents of the memory 4 Point to calculate the current path position of the mobile carrier A, and send the path position information to the driving device of the mobile carrier A for it to continue moving.

又,該視覺感測元件1與該接收器2及該運算器3與該儲存器4,可為一個以上。 In addition, there may be more than one visual sensor element 1 and the receiver 2 as well as the arithmetic unit 3 and the storage 4.

又,該儲存器4設於教導路徑模組B亦可設於網路雲端或外接於一電腦主機的記憶體;以及,該儲存器4的資料提供被移動載具A直接使用,或是傳到另一個移動載具A使用,該儲存器4可提供將檔案傳到另一儲存體備存。 In addition, the storage 4 is provided in the teaching path module B, and can also be installed in the network cloud or externally connected to the memory of a computer host; and, the data in the storage 4 can be directly used by the mobile vehicle A, or transmitted For use by another mobile vehicle A, the storage 4 can provide files to be transferred to another storage for storage.

實施本發明模組的運算器3計算方法如以下舉例所述,首先,因拍攝的相機其光學成像或多或少都會產生像差,這些相差會導致空間位置計算錯誤;甚至讓計算結果發散;因此在位置計算前運算器3要根據所搭載相機的光學特性校正影像的像差(例如:image sensor的像素尺寸、像素長寬比、光學鏡頭的paraxial焦距、垂直與水平焦距差異、畸變等),還原出特徵點在影像上的真實投影位置。 The calculation method of the arithmetic unit 3 implementing the module of the present invention is as described in the following examples. First, the optical imaging of the camera taken by the camera will more or less produce aberrations, and these differences will cause errors in the calculation of the spatial position; even the calculation results may diverge; Therefore, before calculating the position, the arithmetic unit 3 should correct the aberration of the image according to the optical characteristics of the mounted camera (for example: the pixel size of the image sensor, the pixel aspect ratio, the paraxial focal length of the optical lens, the difference between vertical and horizontal focal lengths, distortion, etc.) , To restore the true projection position of the feature point on the image.

繼續,實施計算配對方法,一開始先由使用者在近端操 作移動載具進行移動,依照所要行走的路徑,遙控移動載具行走一遍該指定路徑,在移動載具開始移動當下起,該視覺感測元件1被啟動,因此開始進行連續拍攝,並將連續拍攝的影像提供給運算器3,該運算器3中找出二維特徵點,該每兩張影像的二維特徵點找出相同的特徵點配對,運用fundamental matrix及多組特徵點匹配,通常是8組但不限,還原出機器人位姿與配對特徵點的三維位置,並利用此幾何關係將影像中所有的特徵點都計算出在空間中的位置。 Continue to implement the calculation and pairing method. At the beginning, the user operates the mobile vehicle at the proximal end to move. According to the path to be traveled, the mobile vehicle is remotely controlled to walk the designated path. When the mobile vehicle starts to move, the visual The sensing element 1 is activated, so continuous shooting starts, and the continuously shot images are provided to the arithmetic unit 3, and the arithmetic unit 3 finds two-dimensional feature points. The two-dimensional feature points of each two images are found to be the same Use the fundamental matrix and multiple sets of feature point matching, usually 8 groups but not limited, to restore the robot pose and the three-dimensional position of the paired feature points, and use this geometric relationship to calculate all the feature points in the image Out of the position in space.

又,如第二圖所示,使用者可在遠端的控制主機端C以無線發送操控訊號給該接收器2,該接收器2將操控訊息提供給移動載具A的內建的驅動元件(圖面未示),進而驅動元件驅使移動載具A依照遠端控制進行移動,藉此移動載具A行走一遍該指定路徑,在移動載具開始移動當下起,該視覺感測元件1被啟動,因此開始進行連續拍攝,並將連續拍攝得影像提供給運算器3,該運算器3則將該影像資料計算出路徑資料檔案,並將路徑資料檔案儲存到儲存器4內。 Also, as shown in the second figure, the user can wirelessly send a control signal to the receiver 2 at the remote control host terminal C, and the receiver 2 provides the control information to the built-in driving element of the mobile vehicle A (Not shown in the figure), and then the driving element drives the mobile carrier A to move according to the remote control, whereby the mobile carrier A walks the specified path once, and the visual sensor element 1 is activated when the mobile carrier starts to move. Started, so the continuous shooting starts, and the continuously shot images are provided to the calculator 3, and the calculator 3 calculates the path data file from the image data, and stores the path data file in the storage 4.

如第三圖所示,從每兩張影像I1、l2中找出的眾多特徵點配對中,當空間中一個特徵點Pi被兩張影像I1、l2看到時,此時相機中心分別在位姿O1和位姿O2,當相機在位姿O1時可以看到三維特徵點Pi的投影在特徵點p1;以及,當相機在位姿O2時三維特徵點Pi的投影在特徵點p2,第二張影像l2的相機中心投影至第一張影像l1時的投影稱為極點(epipole)e1,反之位姿O1投影到12上的極點為e2,任一配對的特徵點P1與P2都能對應該真實空間中的三維特徵點Pi,特徵點三維座標為[x,y,z]t,利用多個三維特徵點投影即可算出機器人的位姿O1與位姿O2,其關係為:O2=O1.[(R‧f)]其中,

Figure 108133575-A0305-02-0010-1
亦可簡化表示如下:[x,y,z,ψ,θ,φ] As shown in the third figure, among the many feature point pairs found in each two images I1 and 12, when a feature point Pi in space is seen by the two images I1 and 12, the camera center is in place at this time. For pose O1 and pose O2, when the camera is in pose O1, you can see that the projection of the 3D feature point Pi is on the feature point p1; and when the camera is in pose O2, the projection of the 3D feature point Pi is on the feature point p2, and the second The projection when the camera center of the image l2 is projected to the first image l1 is called the pole (epipole) e1, on the contrary, the pole of the pose O1 projected on 12 is e2, and any paired feature points P1 and P2 can correspond The three-dimensional feature point Pi in the real space, the three-dimensional coordinates of the feature point are [x,y,z]t, the pose O1 and the pose O2 of the robot can be calculated by using multiple three-dimensional feature point projections, the relationship is: O2=O1 . [(R‧f)] where,
Figure 108133575-A0305-02-0010-1
It can also be simplified as follows: [x,y,z,ψ,θ,φ]

其中x,y,z是三維位置座標,ψ,θ,φ則表示yaw,pitch,roll三個旋轉角度;藉以表示載具在空間中的姿態,運算順序是先轉yaw(ψ),其次是pitch(θ),最後是roll(φ) Among them, x, y, z are the three-dimensional position coordinates, ψ , θ , and φ represent the three rotation angles of yaw, pitch, and roll; in order to express the posture of the vehicle in space, the order of operations is first to yaw ( ψ ), followed by pitch( θ ), and finally roll( φ )

當連續拍攝的影像中,任二張均可透過以上方式取得一定數量的特徵點匹配,與推算出來的特徵點空間位置,以及拍攝這二張影像時模組的相對位置及位姿,這些資料可以連續地建構成一個有結構性的資料檔案,並放置入儲存器4,以檔案的型態儲存,將來能被重覆使用。 In the continuously shot images, any two images can be matched with a certain number of feature points through the above methods, and the calculated spatial position of the feature points, as well as the relative positions and poses of the modules when these two images were taken, these data A structured data file can be constructed continuously and placed in the memory 4 to be stored in the form of a file, which can be reused in the future.

通常使用方式如下:該視覺感測元件1將持續擷取景物影像傳給該運算器3,並由該運算器3解析成為一個或一個以上的二維特徵點,通常至少10個特徵點,再將二維特徵點與一個或一個以上的儲存器內的二維特徵點比較,藉此得到最接近儲存器內儲存最接近的二維特徵點,並據此得到當時載具的位置與姿態,用來初步定位目前的位姿,再將新拍攝的影像中擷取出的二維特徵點與儲存器內的二維特徵點及儲存器內的特徵點三維空間位置進行運算及分析,可以得到移動載具A所在的路徑的當下位置,為此移動載具A就能依據此資訊來繼續進行移動工作,亦可將此儲存器4內的指導路徑檔案傳送給任何一個移動載具A,讓其它的移動載具A可重覆使用此儲存器4檔案,以利於進行工作,或是將該儲存器4內的指導路徑檔案上傳,當有其它移動載具A需要相同場地工作時即可藉由遠端或近端傳送儲存器4內的指導路徑檔案到另一台移動載具A的教導路徑模組內的儲存器4,藉此提供另一台移動載具A可行走與相同的指導路徑。 The usual usage method is as follows: the visual sensor 1 transmits the continuously captured scene image to the arithmetic unit 3, and the arithmetic unit 3 resolves it into one or more two-dimensional feature points, usually at least 10 feature points, and then Compare the two-dimensional feature points with the two-dimensional feature points in one or more storages to obtain the closest two-dimensional feature points stored in the storage, and then obtain the position and attitude of the vehicle at that time. It is used to initially locate the current pose, and then calculate and analyze the two-dimensional feature points extracted from the newly captured image, the two-dimensional feature points in the storage and the three-dimensional space position of the feature points in the storage, and the movement can be obtained The current position of the path where the vehicle A is located. For this reason, the mobile vehicle A can continue to move based on this information, and the guidance path file in the storage 4 can also be sent to any mobile vehicle A to let others The mobile vehicle A can use this storage 4 file repeatedly to facilitate work, or upload the guidance path file in the storage 4, when there is another mobile vehicle A that needs to work on the same site, it can be used Remotely or near-end transfers the guidance path file in the storage 4 to the storage 4 in the teaching path module of another mobile vehicle A, thereby providing another mobile vehicle A with the same guidance path that can be walked .

本方法另一實施,為可以結合其它感測器作為輔助位姿資料獲取路徑位置資料來源,藉以整合成更可靠的位置推估,例如:當環境的影像特徵稀少時,上述方法計算出來的結果誤差較大,若能從其它感測器獲取路徑位置資料,將有助於修正影像計算位姿的誤差;其優點為: Another implementation of this method is that it can be combined with other sensors as the auxiliary pose data to obtain the path position data source, so as to integrate into a more reliable position estimation, for example: when the image features of the environment are scarce, the result calculated by the above method The error is large. If the path position data can be obtained from other sensors, it will help to correct the error of the image calculation pose; its advantages are:

1.在一個特定區域內,可以在儲存器4上建立一個指導路徑檔案,該指導路徑檔案為一個以上的檔案資料夾,或是將檔案資料夾分散建在不同的儲存器4上。 1. In a specific area, you can create a guide path file on the storage 4, the guide path file is more than one file folder, or the file folders are scattered and built on different storage 4.

2.儲存器4能被儲存成指導路徑檔案,將來能被其它移動載具A直 接使用,或是傳到另一個移動載具A使用。 2. The memory 4 can be stored as a guide path file, which can be used directly by other mobile vehicle A in the future or transferred to another mobile vehicle A for use.

3.當環境改變時,儲存器4內的指導路徑檔案能被更新。 3. When the environment changes, the guide path file in the storage 4 can be updated.

4.當移動載具A指導路徑檔案超出原本儲存器4的儲存容納範圍時,儲存器4能被擴充。 4. When the guidance path file of the mobile vehicle A exceeds the storage range of the original storage 4, the storage 4 can be expanded.

5.當有相當類似的特徵或位姿在儲存器4中時,經由分析後,運算器4會將一些特徵點資訊從儲存器4中移出。 5. When there are quite similar features or poses in the storage 4, the arithmetic unit 4 will remove some feature point information from the storage 4 after analysis.

6.運算器3會因不同時間,因光影、環境…等造成的不同特徵變化的特徵點資料進行計算,並隨時由儲存器4進行存取重新計算特徵點。 6. The arithmetic unit 3 will calculate the feature point data of different feature changes caused by different time, light and shadow, environment..., etc., and will be accessed by the memory 4 to recalculate the feature points at any time.

綜上所述,僅為本發明較佳實施例而已,並非用來限定本發明實施之範圍,即凡依本發明申請專利範圍所做之均等變化與修飾,皆為本發明專利範圍所涵蓋。 In summary, these are only preferred embodiments of the present invention and are not used to limit the scope of implementation of the present invention. That is, all equivalent changes and modifications made in accordance with the scope of the patent application of the present invention are covered by the patent scope of the present invention.

1‧‧‧視覺感測元件 1‧‧‧Visual sensor

2‧‧‧接收器 2‧‧‧Receiver

3‧‧‧運算器 3‧‧‧Computer

4‧‧‧儲存器 4‧‧‧Storage

Claims (11)

一種移動載具之教導路徑模組,該移動載具包含移動式機器人或運輸機具,該教導路徑模組是作為組裝於移動載具的內建電子元件內,該教導路徑模組包括一視覺感測元件與一接收器及一運算器與一儲存器,該視覺感測元件電子線路連結該接收器與該運算器,該運算器電子線路連接該儲存器;以及,該視覺感測元件包括一攝影鏡頭,該攝影鏡頭裝設於移動載具之任一表面位置處,作為拍攝該移動載具所在的環境的景物功能,並將所得影像傳到該運算器,所述運算器從該視覺感測元件拍攝之二維影像中,擷取出離散的二維特徵點,並依據該連續取得該影像的特徵找出同一個空間點位在不同影像上的二維座標,由於移動載具的在移動位置影像產生視差,移動載具的在移動位置影像的二維特徵點在每一張影像上的二維座標會因此改變,並以該連續取得該二維特徵點數據利用投影的方法計算出特徵點在空間中的真實三維空間位置與移動載具本身的位姿,所述位姿是指移動載具在三維空間中朝向的方向,常用數學表達方向方式有歐拉角、三維正交矩陣、單位四元數;以及,該視覺感測元件的相機模組會持續拍攝移動載具當下環境的影像,並將拍攝數據傳給運算器,並重覆依上述方法計算出新的二維特徵點與三維特徵點與移動載具新的位姿,並將這些數據與關係的資料儲存入所述的儲存器中更新,而不需要重新建立整個儲存器;以及,該接收器為接收遠端的一控制主機端以無線發送操控訊號給該接收器,該接收器將操控訊息提供給移動載具的內建的驅動元件,進而驅動元件驅使移動載具依照遠端控制進行移動,藉此移動載具行走指定路徑,在移動載具開始啟動當下起,該視覺感測元件被啟動,因此開始進行連續拍攝,並將連續拍攝得影像提供給運算器,該運算器則將該指定路徑拍攝的影像資料計算出路徑資料檔案,並將路徑資料檔案儲存到儲存器內。 A teaching path module of a mobile vehicle, the mobile vehicle including a mobile robot or a transportation machine, the teaching path module is assembled in a built-in electronic component of the mobile vehicle, and the teaching path module includes a visual sense A sensing element and a receiver and an arithmetic unit and a storage, the visual sensing element electronic circuit connects the receiver and the arithmetic unit, the arithmetic circuit is connected to the storage; and the visual sensing element includes a A photographic lens, which is installed at any surface position of the mobile vehicle as a function of photographing the scenery of the environment where the mobile vehicle is located, and transmits the resulting image to the arithmetic unit. The arithmetic unit obtains the visual perception from the In the two-dimensional image taken by the measuring element, the discrete two-dimensional feature points are extracted, and the two-dimensional coordinates of the same spatial point on different images are found according to the characteristics of the continuously acquired image. Because the moving vehicle is moving The position image produces parallax, and the two-dimensional coordinates of the two-dimensional feature points of the moving vehicle in the moving position image on each image will be changed accordingly, and the two-dimensional feature point data is obtained continuously and the feature is calculated by the method of projection. The real three-dimensional position of the point in space and the pose of the mobile vehicle itself. The pose refers to the direction the mobile vehicle faces in the three-dimensional space. Commonly used mathematical expressions include Euler angles, three-dimensional orthogonal matrix, Unit quaternion; and, the camera module of the visual sensor element will continue to capture images of the current environment of the moving vehicle, and transmit the captured data to the arithmetic unit, and repeatedly calculate the new two-dimensional feature points and The three-dimensional feature points and the new pose of the mobile vehicle are stored, and the data and relational data are stored in the storage for updating, without the need to re-create the entire storage; and, the receiver is a remote one for receiving The control host side wirelessly sends a control signal to the receiver, and the receiver provides the control information to the built-in driving element of the mobile vehicle, and then the driving element drives the mobile vehicle to move according to the remote control, thereby moving the vehicle Walk the designated path, the visual sensing element is activated from the moment the mobile vehicle starts to start, so continuous shooting starts, and the continuously shot images are provided to the arithmetic unit, and the arithmetic unit then takes the image data of the designated path Calculate the path data file, and save the path data file in the memory. 如申請專利範圍第1項所述之移動載具之教導路徑模組,該接收器與運算器連接方法可為直接電路連接電路板上的線路,或網路無線連結,或其它的通訊連結;所述無線連接的實施是指該運算器可為設於模組之外的一控制主機端,藉由無線發送或網路雲端,將運算器的計算路徑訊息傳送到該接收器,再由該接收器將路徑訊息儲存到儲存器,藉此該儲存器提供存取路徑資訊,待移動載具欲進行移動時,再由接收器經由儲存器取得的以儲存預定的路徑資訊提供給移動載具,以供移動載具依照指定路徑進行移動。 For the teaching path module of the mobile vehicle described in the first item of the patent application, the connection method between the receiver and the arithmetic unit can be a direct circuit connection with a circuit on a circuit board, a wireless connection with a network, or other communication connections; The implementation of the wireless connection means that the arithmetic unit can be a control host terminal located outside the module, and the calculation path information of the arithmetic unit is transmitted to the receiver through wireless transmission or network cloud, and then the The receiver stores the path information in the memory, and the memory provides access path information. When the mobile vehicle wants to move, the receiver obtains the stored path information through the memory and provides it to the mobile vehicle. , For the mobile vehicle to move according to the specified path. 如申請專利範圍第1項所述之移動載具之教導路徑模組,該儲存器一個特定區域內,可以在儲存器上建立一個以上的指導路徑檔案,或是將檔案資料夾分散建在不同的儲存器上。 For example, the teaching path module of the mobile vehicle described in item 1 of the scope of patent application, in a specific area of the storage, more than one guidance path file can be created on the storage, or the file folders can be scattered and built in different On the storage. 如申請專利範圍第1項所述之移動載具之教導路徑模組,該儲存器能儲存多個指導路徑檔案,將來能被其它移動載具直接使用,或是傳到另一個移動載具使用。 For example, the teaching path module of the mobile vehicle described in the first item of the scope of patent application, the memory can store multiple guidance path files, which can be directly used by other mobile vehicles in the future or transferred to another mobile vehicle for use . 如申請專利範圍第1項所述之移動載具之教導路徑模組,該儲存器在環境改變時,儲存器內的指導路徑檔案能被更新。 For example, in the teaching path module of the mobile vehicle described in the first item of the scope of patent application, the guidance path file in the storage can be updated when the environment of the storage is changed. 如申請專利範圍第1項所述之移動載具之教導路徑模組,該儲存器在當移動載具指導路徑檔案超出原本儲存器的儲存容納範圍時,儲存器能被擴充。 For example, the teaching path module of the mobile vehicle described in item 1 of the scope of patent application, the memory can be expanded when the guidance path file of the mobile vehicle exceeds the storage range of the original memory. 如申請專利範圍第1項所述之移動載具之教導路徑模組,該儲存器在有相當類似的特徵或位姿在儲存器中時,經由分析後,運算器會將一些特徵點資訊從儲存器中移出。 For example, the teaching path module of the mobile vehicle described in the first item of the scope of patent application, when the memory has quite similar features or poses in the memory, after analysis, the arithmetic unit will convert some feature point information from Remove from storage. 如申請專利範圍第1項所述之移動載具之教導路徑模組,該運算器會因不同時間,因光影、環境等造成的不同特徵變化的特徵點資料進行計算,並隨時由儲存器進行存取重新計算特徵點。 For example, the teaching path module of the mobile vehicle described in item 1 of the scope of patent application, the arithmetic unit will calculate the feature point data of different feature changes caused by light and shadow, environment, etc. at different times, and it will be carried out by the memory at any time Access to recalculate feature points. 如申請專利範圍第1項所述之移動載具之教導路徑模組,該視覺感測元件與該接收器及該運算器與該儲存器,可為一個以上。 For the teaching path module of the mobile vehicle described in item 1 of the scope of the patent application, there can be more than one visual sensing element and the receiver, and the arithmetic unit and the storage. 一種移動載具之教導路徑模組,該移動載具包含移動式機器人或運輸機具,該教導路徑模組是作為組裝於移動載具的內建電子元件內,該教導路徑模組包括一視覺感測元件與一運算器與一儲存器,該視覺感測元件電子線路連結該接收器與該運算器,該運算器電子線路連接該儲存器;以及,該視覺感測元件包括一攝影鏡頭,該攝影鏡頭裝設於移動載具之任一表面位置處,作為拍攝該移動載具所在的環境的景物功能,並將所得影像傳到該運算器,所述運算器從該視覺感測元件拍攝之二維影像中,擷取出離散的二維特徵點,並依據該連續取得該影像的特徵找出同一個空間點位在不同影像上的二維座標,由於移動載具的在移動位置影像產 生視差,這些二維特徵點在每一張影像上的二維座標會因此改變,並以該連續取得該二維特徵點數據利用投影的方法計算出特徵點在空間中的真實三維空間位置與移動載具本身的位姿,所述位姿是指移動載具在三維空間中朝向的方向,常用數學表達方向方式有歐拉角、三維正交矩陣、單位四元數;以及,該視覺感測元件的相機模組會持續拍攝移動載具當下環境的影像,並將拍攝數據傳給運算器,並重覆依上述方法計算出新的二維特徵點與三維特徵點與移動載具新的位姿,並將這些數據與關係的資料儲存入所述的儲存器中更新,而不需要重新建立整個儲存器;在移動載具開始啟動當下起,該視覺感測元件被啟動,因此開始進行連續拍攝,並將連續拍攝得影像提供給運算器,該運算器則將該指定路徑拍攝的影像資料計算出路徑資料檔案,並將路徑資料檔案儲存到儲存器內。 A teaching path module of a mobile vehicle, the mobile vehicle including a mobile robot or a transportation machine, the teaching path module is assembled in a built-in electronic component of the mobile vehicle, and the teaching path module includes a visual sense The sensing element and an arithmetic unit and a memory, the visual sensing element electronic circuit connects the receiver and the arithmetic unit, the arithmetic circuit is connected to the memory; and the visual sensing element includes a photographing lens, the The photographic lens is installed at any surface position of the mobile vehicle as a function of photographing the environment in which the mobile vehicle is located, and the resulting image is transmitted to the arithmetic unit, which captures the image from the visual sensor element In the two-dimensional image, the discrete two-dimensional feature points are extracted, and the two-dimensional coordinates of the same spatial point on different images are found according to the characteristics of the continuously acquired image. Parallax occurs, the two-dimensional coordinates of these two-dimensional feature points on each image will be changed accordingly, and the two-dimensional feature point data is continuously obtained using the projection method to calculate the true three-dimensional space position of the feature points in the space and The pose of the mobile vehicle itself. The pose refers to the direction the mobile vehicle faces in three-dimensional space. Commonly used mathematical expressions include Euler angles, three-dimensional orthogonal matrices, and unit quaternions; and, the visual sense The camera module of the test component will continue to capture images of the current environment of the mobile vehicle, and transmit the captured data to the arithmetic unit, and repeatedly calculate the new two-dimensional feature points and three-dimensional feature points and the new position of the mobile vehicle according to the above method. Posture, and store these data and relational data in the storage for updating, without the need to re-create the entire storage; from the moment when the mobile vehicle starts to start, the visual sensing element is activated, so it starts to continue. Shoot, and provide the continuously shot images to the calculator, and the calculator calculates the path data file from the image data shot by the specified path, and stores the path data file in the memory. 如申請專利範圍第10項所述之移動載具之教導路徑模組,該教導路徑模組設有一接收器,該接收器連結該視覺感測元件與該運算器;以及,該接收器可以外接組裝於移動載具的驅動元件;以及,接收遠端的一控制主機端以無線發送操控訊號給該接收器,該接收器將操控訊息提供給移動載具的內建的驅動元件,進而驅動元件驅使移動載具依照遠端控制進行移動,藉此移動載具被遙控行走指定路徑,並將視覺感測元件拍攝的影像傳送給運算器。 For example, the teaching path module of the mobile vehicle described in item 10 of the scope of patent application, the teaching path module is provided with a receiver, which connects the visual sensing element and the arithmetic unit; and, the receiver can be connected externally A driving element assembled in the mobile vehicle; and a control host terminal that receives the remote sends a control signal to the receiver wirelessly, and the receiver provides the control information to the built-in driving element of the mobile vehicle, and then drives the element The mobile vehicle is driven to move according to the remote control, whereby the mobile vehicle is remotely controlled to walk a designated path, and the image captured by the visual sensor element is transmitted to the computing unit.
TW108133575A 2018-09-27 2019-09-18 Teaching path module for mobile vehicles TWI728469B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
TW107134105 2018-09-27
TW107134105 2018-09-27

Publications (2)

Publication Number Publication Date
TW202012884A TW202012884A (en) 2020-04-01
TWI728469B true TWI728469B (en) 2021-05-21

Family

ID=69976281

Family Applications (1)

Application Number Title Priority Date Filing Date
TW108133575A TWI728469B (en) 2018-09-27 2019-09-18 Teaching path module for mobile vehicles

Country Status (2)

Country Link
CN (1) CN110955237A (en)
TW (1) TWI728469B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW200604555A (en) * 2004-07-16 2006-02-01 Univ Feng Chia Moving carrier tracking management system
CN101726296A (en) * 2009-12-22 2010-06-09 哈尔滨工业大学 Vision measurement, path planning and GNC integrated simulation system for space robot
US7996179B2 (en) * 2007-07-19 2011-08-09 Samsung Electronics Co., Ltd. Method of measuring pose of mobile robot and method and apparatus for measuring position of mobile robot using the same
WO2017163596A1 (en) * 2016-03-22 2017-09-28 Sharp Kabushiki Kaisha Autonomous navigation using visual odometry
TW201814246A (en) * 2016-09-26 2018-04-16 劉建良 Image recognition coordinate confirmation and navigation device in which an image stored in an image coordinate database and an image processed by an image processing unit are used in the image recognition unit to determine a coordinate for a CPU to plan a navigation path

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100855657B1 (en) * 2006-09-28 2008-09-08 부천산업진흥재단 System for estimating self-position of the mobile robot using monocular zoom-camara and method therefor
CN102435188B (en) * 2011-09-15 2013-10-02 南京航空航天大学 Monocular vision/inertia autonomous navigation method for indoor environment
JP5832341B2 (en) * 2012-03-09 2015-12-16 株式会社トプコン Movie processing apparatus, movie processing method, and movie processing program
CN204131634U (en) * 2014-07-15 2015-01-28 深圳奇沃智联科技有限公司 The robot surveillance of tool image identification and automatically patrol path setting
CN104408719B (en) * 2014-11-24 2017-07-28 中国航空工业集团公司洛阳电光设备研究所 A kind of conllinear three characteristic points monocular vision space-location method
CN105760894A (en) * 2016-03-16 2016-07-13 哈尔滨伟方智能科技开发有限责任公司 Robot navigation method based on machine vision and machine learning
CN107357286A (en) * 2016-05-09 2017-11-17 两只蚂蚁公司 Vision positioning guider and its method
US20180068459A1 (en) * 2016-09-08 2018-03-08 Ford Global Technologies, Llc Object Distance Estimation Using Data From A Single Camera
CN108074251A (en) * 2016-11-14 2018-05-25 广东技术师范学院 Mobile Robotics Navigation control method based on monocular vision

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW200604555A (en) * 2004-07-16 2006-02-01 Univ Feng Chia Moving carrier tracking management system
US7996179B2 (en) * 2007-07-19 2011-08-09 Samsung Electronics Co., Ltd. Method of measuring pose of mobile robot and method and apparatus for measuring position of mobile robot using the same
CN101726296A (en) * 2009-12-22 2010-06-09 哈尔滨工业大学 Vision measurement, path planning and GNC integrated simulation system for space robot
WO2017163596A1 (en) * 2016-03-22 2017-09-28 Sharp Kabushiki Kaisha Autonomous navigation using visual odometry
TW201814246A (en) * 2016-09-26 2018-04-16 劉建良 Image recognition coordinate confirmation and navigation device in which an image stored in an image coordinate database and an image processed by an image processing unit are used in the image recognition unit to determine a coordinate for a CPU to plan a navigation path

Also Published As

Publication number Publication date
CN110955237A (en) 2020-04-03
TW202012884A (en) 2020-04-01

Similar Documents

Publication Publication Date Title
JP5222971B2 (en) Walking robot apparatus and control program therefor
CN107990899B (en) Positioning method and system based on SLAM
CN112652016B (en) Point cloud prediction model generation method, pose estimation method and pose estimation device
JP5992184B2 (en) Image data processing apparatus, image data processing method, and image data processing program
JP5775632B2 (en) Aircraft flight control system
JP6943988B2 (en) Control methods, equipment and systems for movable objects
CN110827353B (en) Robot positioning method based on monocular camera assistance
JP2018146524A (en) Survey system
WO2018121794A1 (en) Control method, electronic device and storage medium
CN111784842B (en) Three-dimensional reconstruction method, device, equipment and readable storage medium
TWI728469B (en) Teaching path module for mobile vehicles
JP6725736B1 (en) Image specifying system and image specifying method
TW201635250A (en) Indoor monitoring system and method thereof
KR102516450B1 (en) Method of generating map and visual localization system using the map
JP7078231B2 (en) 3D tour comparison display system and method
JP2022011821A (en) Information processing device, information processing method and mobile robot
CN111788457A (en) Shape estimation device, shape estimation method, program, and recording medium
KR102483388B1 (en) Method for processing omnidirectional image and server performing the same
WO2023070441A1 (en) Movable platform positioning method and apparatus
JP7467206B2 (en) Video management support system and video management support method
CN113465600B (en) Navigation method and device, electronic equipment and storage medium
KR101745626B1 (en) Apparatus and method for location-information
JP4027294B2 (en) Moving object detection apparatus, moving object detection method, and moving object detection program
Iversen Stereo visual odometry for indoor positioning
Li-Chee-Ming et al. Feasibility study of using the RoboEarth cloud engine for rapid mapping and tracking with small unmanned aerial systems