TW202241739A - Method and system for identifying a parking space - Google Patents

Method and system for identifying a parking space Download PDF

Info

Publication number
TW202241739A
TW202241739A TW110115663A TW110115663A TW202241739A TW 202241739 A TW202241739 A TW 202241739A TW 110115663 A TW110115663 A TW 110115663A TW 110115663 A TW110115663 A TW 110115663A TW 202241739 A TW202241739 A TW 202241739A
Authority
TW
Taiwan
Prior art keywords
vehicle
parking space
adjacent vehicle
identifying
parking
Prior art date
Application number
TW110115663A
Other languages
Chinese (zh)
Other versions
TWI773288B (en
Inventor
時丕澔
王詩晴
莊喬甯
錢中方
Original Assignee
歐特明電子股份有限公司
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 歐特明電子股份有限公司 filed Critical 歐特明電子股份有限公司
Priority to TW110115663A priority Critical patent/TWI773288B/en
Application granted granted Critical
Publication of TWI773288B publication Critical patent/TWI773288B/en
Publication of TW202241739A publication Critical patent/TW202241739A/en

Links

Images

Landscapes

  • Traffic Control Systems (AREA)
  • Devices For Checking Fares Or Tickets At Control Points (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a method and a system for identifying a parking space, the method includes the following steps: obtaining continuous image frames including at least one adjacent vehicle when the vehicle is moving; determining the position and orientation of the at least one adjacent vehicle from the continuous image frames obtaining continuous sensing signals when the vehicle is moving; generating a boundary of the at least one adjacent vehicle according to the continuous image frames and the continuous sensing signals; and identifying the parking space based on the boundary of the at least one adjacent vehicle and the position and orientation of the at least one adjacent vehicle.

Description

識別停車位的方法及其系統Method and system for identifying parking spaces

本發明涉及汽車自動停車技術領域，具體涉及一種識別停車位的方法及其系統。The invention relates to the technical field of automatic parking of automobiles, in particular to a method and system for identifying a parking space.

隨著自動停車的功能需求增加，特別是自動搜尋或辨識停車位功能，在傳統的停車位識別方法中，使用超聲波的停車位識別方法的問題在於，由於超聲波的距離和解析度的限制，不僅無法精確取得與停放車輛所需的停車位相鄰的對方車輛的邊緣、車輛數量，更無法判斷停車場域的屬性，如禁止停車線或是殘疾人士專用車位等。近年來隨著影像辨識停車位技術提升，一般可藉由停車場域內的車格線作為車輛自動停車的辨識依據，亦即透過影像辨識車格線或其他停車場域內的障礙物，將車駛入空閒之停車格內。但面對於不具有停車格線的停車空間，若僅憑車格線作為停車場域的判斷，會使自動停車功能失效。With the increasing functional requirements of automatic parking, especially the automatic search or identification of parking spaces, in the traditional parking space recognition method, the problem of using ultrasonic parking space recognition method is that due to the limitation of ultrasonic distance and resolution, not only It is impossible to accurately obtain the edge and number of other vehicles adjacent to the parking space required for parking the vehicle, and it is impossible to judge the attributes of the parking area, such as no parking lines or special parking spaces for disabled people. In recent years, with the improvement of image recognition parking space technology, the grid lines in the parking area can generally be used as the identification basis for automatic parking of vehicles, that is, through image recognition of the grid lines or other obstacles in the parking area, the car can be driven into a vacant parking space. However, in the face of a parking space without parking grid lines, if only the grid lines are used as the judgment of the parking area, the automatic parking function will be invalidated.

為解決上述技術問題而提供了一種識別停車位的方法及其系統。In order to solve the above technical problems, a method and system for identifying parking spaces are provided.

本發明的目的可以透過以下的技術方案來實現：一種識別停車位的方法，包括以下步驟：獲取車輛移動時包括至少一相鄰車輛的連續影像幀，獲取車輛移動時的連續感測訊號，從所述連續影像幀中辨識所述至少一相鄰車輛的位姿，根據所述連續影像幀及所述連續感測訊號以產生所述至少一相鄰車輛的邊界，根據所述至少一相鄰車輛的邊界及所述至少一相鄰車輛的位姿識別停車位。The purpose of the present invention can be achieved through the following technical solutions: a method for identifying a parking space, comprising the following steps: acquiring continuous image frames including at least one adjacent vehicle when the vehicle is moving, acquiring continuous sensing signals when the vehicle is moving, and obtaining Identifying the pose of the at least one adjacent vehicle in the continuous image frame, generating the boundary of the at least one adjacent vehicle according to the continuous image frame and the continuous sensing signal, and generating the boundary of the at least one adjacent vehicle according to the at least one adjacent vehicle The boundary of the vehicle and the pose of the at least one adjacent vehicle identify the parking space.

根據本發明構想，所述至少一相鄰車輛的位姿還包括車輪位姿。According to the concept of the present invention, the pose of the at least one adjacent vehicle further includes a wheel pose.

根據本發明構想，將所述連續影像幀及所述連續的感測訊號進行融合。According to the concept of the present invention, the continuous image frames and the continuous sensing signals are fused.

根據本發明構想，還包括顯示所述至少一相鄰車輛及所述停車位。According to the concept of the present invention, it also includes displaying the at least one adjacent vehicle and the parking space.

根據本發明構想，還包括產生一停車路徑，根據所述停車路徑，控制所述車輛移動至所述停車位。According to the concept of the present invention, it also includes generating a parking path, and controlling the vehicle to move to the parking space according to the parking path.

為了達成本發明的目的，本發明提供了一種識別停車位的系統，包括：影像接收模組用來獲取車輛移動時包括至少一相鄰車輛的連續影像幀，感測模組用來獲取車輛移動時的連續感測訊號，處理單元從所述連續影像幀中辨識所述至少一相鄰車輛的位姿，並根據所述連續影像幀及所述連續感測訊號以產生所述至少一相鄰車輛的邊界，所述處理單元根據所述至少一相鄰車輛的邊界及所述至少一相鄰車輛的位姿識別停車位。In order to achieve the purpose of the present invention, the present invention provides a system for identifying parking spaces, including: an image receiving module is used to obtain continuous image frames including at least one adjacent vehicle when the vehicle is moving, and a sensing module is used to obtain vehicle movement The processing unit recognizes the pose of the at least one adjacent vehicle from the continuous image frames, and generates the at least one adjacent vehicle according to the continuous image frames and the continuous sensing signals. The boundary of the vehicle, the processing unit identifies the parking space according to the boundary of the at least one adjacent vehicle and the pose of the at least one adjacent vehicle.

根據本發明構想，所述至少一相鄰車輛的位姿還包括車輪位姿。According to the concept of the present invention, the pose of the at least one adjacent vehicle further includes a wheel pose.

根據本發明構想，所述處理單元將所述連續影像幀及所述連續的感測訊號進行融合。According to the concept of the present invention, the processing unit fuses the continuous image frames and the continuous sensing signals.

根據本發明構想，還包括顯示器用來顯示所述至少一相鄰車輛及所述停車位。According to the concept of the present invention, a display is also included for displaying the at least one adjacent vehicle and the parking space.

根據本發明構想，所述處理單元產生一停車路徑，根據所述停車路徑，控制所述車輛移動至所述停車位。According to the concept of the present invention, the processing unit generates a parking path, and controls the vehicle to move to the parking space according to the parking path.

根據本發明構想，本發明具有以下優點： 1、在識別停車位時，如果停車場域不具有可辨識的停車格線時，可透過辨識已停放之相鄰車輛的位姿，並計算障礙物空間得到鄰近於已停放之相鄰車輛周圍的可達區域來識別停車位與控制車輛正確停入的方位。 2、透過結合實際具有距離訊號的感測訊號，並匹配或融合影像訊號後，對於相鄰車輛車身邊緣的資訊能更精準。 According to the concept of the present invention, the present invention has the following advantages: 1. When identifying a parking space, if the parking area does not have an identifiable parking grid line, the position and posture of the adjacent parked vehicles can be identified, and the obstacle space can be calculated to obtain the surrounding area of the adjacent parked adjacent vehicles. The accessible area is used to identify the parking space and control the orientation of the vehicle to park correctly. 2. By combining the sensing signals that actually have distance signals and matching or fusing the image signals, the information on the edge of the adjacent vehicle body can be more accurate.

為使本發明實施方式的目的、技術方案和優點更加清楚，下面將結合本發明實施方式中的附圖，對本發明實施方式中的技術方案進行清楚、完整地描述，顯然，所描述的實施方式是本發明一部分實施方式，而不是全部的實施方式。基於本發明中的實施方式，本領域普通技術人員在沒有作出創造性勞動前提下所獲得的所有其他實施方式，都屬於本發明保護的範圍。因此，以下對在附圖中提供的本發明的實施方式的詳細描述並非旨在限制要求保護的本發明的範圍，而是僅僅表示本發明的選定實施方式。基於本發明中的實施方式，本領域普通技術人員在沒有作出創造性勞動前提下所獲得的所有其他實施方式，都屬於本發明保護的範圍。In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments It is some embodiments of the present invention, but not all of them. Based on the implementation manners in the present invention, all other implementation manners obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the implementation manners in the present invention, all other implementation manners obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

在本發明的描述中，需要理解的是，術語“上”、“下”等指示的方位或位置關係為基於附圖所示的方位或位置關係，僅是為了便於描述本發明和簡化描述，而不是指示或暗示所指的設備或元件必須具有特定的方位、以特定的方位構造和操作，因此不能理解為對本發明的限制。In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "upper", "lower", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description. It is not intended to indicate or imply that the referred device or element must have a particular orientation, be constructed in a particular orientation, and operate in a particular orientation, and thus should not be construed as limiting the invention.

在本發明的描述中，“多個”的含義是兩個或兩個以上，除非另有明確具體的限定。In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

在本發明中，除非另有明確的規定和限定，術語“安裝”、“相連”、“連接”、“固定”等術語應做廣義理解，例如，可以是固定連接，也可以是可拆卸連接，或成一體；可以是機械連接，也可以是電連接；可以是直接相連，也可以通過中間媒介間接相連，可以是兩個元件內部的連通或兩個元件的相互作用關係。對於本領域的普通技術人員而言，可以根據具體情況理解上述術語在本發明中的具體含義。In the present invention, unless otherwise clearly specified and limited, terms such as "installation", "connection", "connection" and "fixation" should be understood in a broad sense, for example, it can be a fixed connection or a detachable connection , or integrated; it can be mechanically connected or electrically connected; it can be directly connected or indirectly connected through an intermediary, and it can be the internal communication of two components or the interaction relationship between two components. Those of ordinary skill in the art can understand the specific meanings of the above terms in the present invention according to specific situations.

下面結合附圖與具體實施方式對本發明作進一步詳細描述： 請參考圖1，本發明公開了一種識別停車位的系統100包括影像訊號接收模組101、感測器訊號接收模組102、處理單元103。 Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail: Please refer to FIG. 1 , the present invention discloses a parking space recognition system 100 including an image signal receiving module 101 , a sensor signal receiving module 102 , and a processing unit 103 .

影像訊號接收模組101用來獲取連續影像幀，特別是用來獲取車輛移動時在車輛周圍的連續影像幀。影像訊號接收模組101並具有影像處理單元(ISP, Image Signal Processor)，可處理如鏡頭矯正、圖元矯正、顏色插值、Bayer 雜訊去除、 白平衡矯正、 色彩矯正、gamma 矯正、色彩空間轉換等功能。影像訊號接收模組101一般可具有LVDS(Low Voltage Differential Signaling，低電壓差分信號)或MIPI CSI傳輸介面(未標示)。而連續影像幀來自一個或多個連接於車輛上的攝影機，攝影機通常安裝在車輛的周圍拍攝行車影像，為了能獲取較好的影像品質，影像訊號可以為LVDS格式訊號。The image signal receiving module 101 is used for acquiring continuous image frames, especially for acquiring continuous image frames around the vehicle when the vehicle is moving. The image signal receiving module 101 also has an image processing unit (ISP, Image Signal Processor), capable of processing such as lens correction, pixel correction, color interpolation, Bayer noise removal, white balance correction, color correction, gamma correction, color space conversion and other functions. The video signal receiving module 101 can generally have LVDS (Low Voltage Differential Signaling, Low Voltage Differential Signaling) or MIPI CSI transmission interface (not shown). The continuous image frames come from one or more cameras connected to the vehicle. The cameras are usually installed around the vehicle to shoot driving images. In order to obtain better image quality, the image signals can be LVDS format signals.

感測器訊號接收模組102，獲取車輛移動時的連續感測訊號，感測訊號至少為超聲波訊號、光達訊號、毫米波雷達訊號(mmWave Radar)等有關距離感測的訊號。此外，感測器訊號接收模組102可透過一車輛訊號總成介面1020連接車輛CAN匯流排，接收來自車輛的行車數據訊號。車輛的行車數據訊號包括例如包括車速、引擎轉速、轉向角、加速度、檔位等。The sensor signal receiving module 102 acquires continuous sensing signals when the vehicle is moving, and the sensing signals are at least ultrasonic signals, lidar signals, millimeter wave radar signals (mmWave Radar) and other signals related to distance sensing. In addition, the sensor signal receiving module 102 can be connected to the CAN bus of the vehicle through a vehicle signal assembly interface 1020 to receive driving data signals from the vehicle. The driving data signal of the vehicle includes, for example, vehicle speed, engine speed, steering angle, acceleration, gear position and so on.

處理單元103為本發明的主要的運算單元，並具有影像的語意運算能力。通常處理單元103的處理器是DSP (digital signal processor，數位訊號處理器)。DSP 適合用來進行各種乘加運算（SOP：Sum of Products），例如：有限脈衝回應濾波運算（FIR：Finite Impulse Response）、無限脈衝回應濾波運算（IIR：Infinite Impulse Response）、離散傅立葉轉換（DFT：Discrete Fourier Transform）、離散余弦轉換（DCT：Discrete Cosine Transform）、點積運算（Dot product）、卷積運算（Convolution），以及矩陣多項式的求值運算等。處理單元103具有記憶體傳輸介面，可執行記憶體內置指令。處理單元103亦具有影像傳輸介面，與影像訊號接收模組101連接，運算自影像訊號接收模組轉換後的影像訊號。處理單元103同時與感測器訊號接收模組102連接，接收並運算感測信號如超聲波訊號、毫米波雷達訊號、光達訊號等或車輛的行車數據訊號。The processing unit 103 is the main computing unit of the present invention, and has image semantic computing capability. Usually, the processor of the processing unit 103 is a DSP (digital signal processor, digital signal processor). DSP is suitable for various multiplication and addition operations (SOP: Sum of Products), such as: Finite Impulse Response Filtering Operation (FIR: Finite Impulse Response), Infinite Impulse Response Filtering Operation (IIR: Infinite Impulse Response), Discrete Fourier Transform (DFT : Discrete Fourier Transform), discrete cosine transform (DCT: Discrete Cosine Transform), dot product (Dot product), convolution (Convolution), and matrix polynomial evaluation operations, etc. The processing unit 103 has a memory transmission interface and can execute instructions built into the memory. The processing unit 103 also has an image transmission interface connected to the image signal receiving module 101 to calculate the image signal converted from the image signal receiving module. The processing unit 103 is also connected to the sensor signal receiving module 102 to receive and calculate sensing signals such as ultrasonic signals, millimeter wave radar signals, lidar signals, etc. or vehicle driving data signals.

請一併參考圖1至圖4根據本發明的一種識別停車位的系統100安裝於車輛200上運作的實施方式，並具有以下步驟:Please refer to FIG. 1 to FIG. 4. A system 100 for identifying parking spaces according to the present invention is installed on a vehicle 200 to operate, and has the following steps:

步驟S01，當車輛200啟動停車位搜索，影像訊號接收模組101用來獲取本車輛200移動時包括至少一相鄰車輛201的連續影像幀，同時，感測器訊號接收模組102用來獲取車輛200移動時的連續感測訊號。在圖3中以本車輛200右側接獲取的連續影像幀及連續感測訊號為示意，但不局限在車輛本200的右側，因此，本系統100可獲取裝載於本車輛200前方、後方及左側的連續影像幀或是連續感測訊號。Step S01, when the vehicle 200 starts to search for a parking space, the image signal receiving module 101 is used to obtain continuous image frames including at least one adjacent vehicle 201 when the vehicle 200 is moving, and at the same time, the sensor signal receiving module 102 is used to obtain The continuous sensing signal when the vehicle 200 is moving. In FIG. 3 , the continuous image frames and continuous sensing signals obtained directly from the right side of the vehicle 200 are illustrated, but not limited to the right side of the vehicle 200. Therefore, the system 100 can be installed in the front, rear and left side of the vehicle 200. Continuous image frames or continuous sensing signals.

步驟S02，處理單元103從步驟S01獲取的連續影像幀中，辨識所述至少一相鄰車輛201的位姿。亦即本車輛200在行駛中，如果能辨識出連續影像幀中具有可辨識的物件(如另一相鄰的車輛201)時，且所述可辨識的物件為靜止不動的狀態，處理單元103可產生控制訊號，控制本車輛200朝向另一相鄰且靜止的車輛201的方向前進。當本車輛200靠近另一相鄰的車輛201時，由於本發明的處理單元103具有影像的語意(semantic)分析能力，因此，可從本車輛200移動時獲取的連續影像幀中辨識行進的環境中是否具有其他可辨識的物件，如車道線、停車格線、地鎖等其他於停車場域可見的物件以及可達空間。本發明的特色主要在於當本車輛200偵測停車空間時，如果發現未能有具體的停車網格線形成的停車位時，處理單元103便可根據至少一相鄰車輛201的位姿來辨識並計算停車位。位姿訊號包括所述相鄰車輛201與本車輛200的距離(如相鄰車輛201的車頭、車輛左右側或車尾與本車輛200拍攝到相鄰車輛201的攝影機之間的距離，或是進而計算相對於本車輛200幾何中心的距離)，以及相鄰車輛201與本車輛200的相對角度(舉例如相鄰車輛201的車頭、車輛左右側或車尾的切線與本車輛200的行進角度之間的夾角等)。位姿訊號更進一步包括本車輛200行駛至靠近相鄰車輛201的所有可達空間。請參考圖4，本實施方式進一步可以由處理單元103辨識相鄰車輛201的車輪2010位姿，進而計算相鄰車輛201的位姿。具體來說，車輪的位姿具有較強的特徵性，容易從影像辨識技術中取得，而車輪與地面的接線可以輕易由攝影機的視覺座標轉換成世界座標，此外，若相鄰車輛201為數台時，辨識後的車輪數量可協助判斷該等相鄰車輛201的停放位姿。位姿的計算主要是由連續影像幀為主，由於本車輛200在辨識停車位時需移動，因此須結合來自車輛訊號總成介面1020，接收來自本車輛200的行車數據訊號，來滿足對於另一相鄰車輛201位姿的計算。In step S02 , the processing unit 103 recognizes the pose of the at least one adjacent vehicle 201 from the continuous image frames acquired in step S01 . That is, when the vehicle 200 is running, if it can identify an identifiable object (such as another adjacent vehicle 201 ) in the continuous image frame, and the identifiable object is in a stationary state, the processing unit 103 A control signal can be generated to control the host vehicle 200 to move toward another adjacent stationary vehicle 201 . When the own vehicle 200 is close to another adjacent vehicle 201, since the processing unit 103 of the present invention has the semantic analysis capability of images, it can recognize the driving environment from the continuous image frames acquired when the own vehicle 200 is moving. Whether there are other identifiable objects in the parking space, such as lane lines, parking grid lines, ground locks and other objects that are visible in the parking lot and accessible space. The feature of the present invention is that when the vehicle 200 detects the parking space, if there is no parking space formed by the specific parking grid line, the processing unit 103 can identify it according to the pose of at least one adjacent vehicle 201 And count parking spaces. The pose signal includes the distance between the adjacent vehicle 201 and the own vehicle 200 (such as the distance between the front of the adjacent vehicle 201, the left and right sides of the vehicle or the rear of the vehicle and the camera of the adjacent vehicle 201 captured by the own vehicle 200, or Then calculate the distance relative to the geometric center of the vehicle 200), and the relative angle between the adjacent vehicle 201 and the vehicle 200 (for example, the tangent line between the front of the adjacent vehicle 201, the left and right sides of the vehicle, or the tail and the travel angle of the vehicle 200 angle between, etc.). The pose signal further includes all accessible spaces where the own vehicle 200 travels close to the adjacent vehicle 201 . Please refer to FIG. 4 , in this embodiment, the processing unit 103 can further recognize the pose of the wheels 2010 of the adjacent vehicle 201 , and then calculate the pose of the adjacent vehicle 201 . Specifically, the pose of the wheel has strong characteristics, which can be easily obtained from image recognition technology, and the connection between the wheel and the ground can be easily converted from the visual coordinates of the camera to the world coordinates. In addition, if there are several adjacent vehicles 201 , the number of identified wheels can assist in judging the parking poses of the adjacent vehicles 201 . The calculation of pose is mainly based on continuous image frames. Since the vehicle 200 needs to move when identifying a parking space, it must be combined with the vehicle signal assembly interface 1020 to receive the driving data signal from the vehicle 200 to meet the requirements for other vehicles. Calculation of the pose of an adjacent vehicle 201 .

同時間，感測器訊號接收模組102，獲取車輛200移動時的連續感測信息，在本實施例中，可以為具有距離感測的超聲波訊號。如前述，當本車輛200朝向另一相鄰且靜止的車輛201的方向前進時，除了影像可辨識行進中是否具有障礙物及可達空間外，經由獲取車輛200移動時的連續感測訊號，可確保在影像無法辨識的物體或地面高度變化較大時，防止本車輛200碰撞障礙物或造成其他損害。此外，當本車輛200靠近另一相鄰車輛201時，可補足影像訊號對於另一相鄰車輛201造成距離訊息的誤判，特別是當障礙物未與地面接觸之情形造成的距離誤判，舉例為拍攝影像訊號為另一相鄰車輛201的車頭(未與地面接觸)時，由於透過鏡頭產生的形變，會使得相鄰車輛201的車頭在以影像判讀距離時，會得到距離攝影機較遠的結果。而本發明的處理單元103可根據連續影像幀及連續感測訊號以產生所述至少一相鄰車輛201的邊界，也就是透過實際具有距離資料的感測訊號匹配影像訊號，對相鄰車輛201辨識出車身邊緣的訊號，因而產生相鄰車輛201的邊界，這樣的匹配的結果可以透過取影像訊號與感測訊號對於相鄰車輛201產生的邊緣點距離本車輛200(舉例為本車輛的攝影機位置、幾何中心或是車身邊緣)的最小值得到。另外，本發明的處理單元103可進一步將所述連續影像幀及所述連續的感測訊號進行融合，如此以得到更精准的相鄰車輛201的邊界。訊號的融合可透過多幀影像訊號進行合併和去噪的處理產生障礙物邊緣點。At the same time, the sensor signal receiving module 102 acquires continuous sensing information when the vehicle 200 is moving. In this embodiment, it may be an ultrasonic signal with distance sensing. As mentioned above, when the vehicle 200 is moving towards the direction of another adjacent and stationary vehicle 201, in addition to visually identifying whether there are obstacles and accessible spaces during the process, by acquiring continuous sensing signals when the vehicle 200 is moving, It can be ensured that the vehicle 200 is prevented from colliding with obstacles or causing other damages when there are objects that cannot be identified in the image or when the height of the ground changes greatly. In addition, when the own vehicle 200 is close to another adjacent vehicle 201, the image signal can be supplemented to cause misjudgment of the distance information of another adjacent vehicle 201, especially the distance misjudgment caused by the obstacle not in contact with the ground, for example: When the captured image signal is the front of another adjacent vehicle 201 (not in contact with the ground), due to the deformation generated through the lens, the front of the adjacent vehicle 201 will be farther away from the camera when judging the distance from the image. . The processing unit 103 of the present invention can generate the boundary of the at least one adjacent vehicle 201 based on continuous image frames and continuous sensing signals, that is, match the image signals with the sensing signals that actually have distance data, and compare the adjacent vehicles 201 The signal of the edge of the vehicle body is identified, thereby generating the boundary of the adjacent vehicle 201. Such a matching result can be obtained by taking the distance between the edge point of the adjacent vehicle 201 generated by the image signal and the sensing signal (for example, the camera of the vehicle) Position, geometric center or the minimum value of the body edge). In addition, the processing unit 103 of the present invention can further fuse the continuous image frames and the continuous sensing signals, so as to obtain a more accurate boundary of the adjacent vehicle 201 . Signal fusion can generate obstacle edge points through merging and denoising processing of multi-frame image signals.

步驟S03，處理單元103根據所述至少一相鄰車輛201的邊界及所述至少一相鄰車輛201的位姿識別停車位。在此步驟，處理單元103同時運算步驟S02得到的相鄰車輛201的位姿及邊界，並得到鄰近於相鄰車輛201最後被運算出來可停入的停車位，最後使本車輛200停入停車位時具有準確且可供參考的停車位姿。在前述步驟S02得到至少一相鄰車輛201的邊界，特別是這些邊界在運算上都是邊緣點，針對這些邊緣點的範圍必須框限出可使本車輛200停入之停車位，而這些框限的範圍的決定，在此步驟中，處理單元103可以透過執行重複反覆運算線性回歸來計算前述的邊緣點達成，最後可以得到如圖3或圖4中框選出的相鄰車輛201的邊界。另一方面，由於得到相鄰車輛201的位姿，以及位姿訊號更包括本車輛200行駛至靠近相鄰車輛201的所有可達空間，因此透過位姿訊號，處理單元103可以運算在與相鄰車輛201鄰近的周邊可停入的停車空間，以及如果要使本車輛200停放於該停車空間時，可由相鄰車輛201的位姿作為本車輛200的停車位姿，或是透過本系統100設置一顯示器(未標示)用來顯示至少一相鄰車輛201及停車位，使操作本系統100的駕駛能根據顯示的結果決定停車位，特別是在停車位具有多個選擇時。Step S03 , the processing unit 103 identifies a parking space according to the boundary of the at least one adjacent vehicle 201 and the pose of the at least one adjacent vehicle 201 . In this step, the processing unit 103 calculates the pose and boundary of the adjacent vehicle 201 obtained in step S02 at the same time, and obtains the last computed parking space adjacent to the adjacent vehicle 201, and finally parks the own vehicle 200 It has an accurate and referenceable parking pose when parking. The boundaries of at least one adjacent vehicle 201 are obtained in the aforementioned step S02, especially these boundaries are all edge points in calculation, and the range of these edge points must be framed to limit the parking space that the vehicle 200 can park in, and these frames In this step, the processing unit 103 can calculate the aforementioned edge points by performing repeated linear regression operations, and finally obtain the boundary of the adjacent vehicle 201 as shown in FIG. 3 or FIG. 4 . On the other hand, since the pose of the adjacent vehicle 201 is obtained, and the pose signal includes all accessible spaces where the own vehicle 200 travels close to the adjacent vehicle 201, through the pose signal, the processing unit 103 can calculate the corresponding The parking space adjacent to the adjacent vehicle 201 can be parked, and if the own vehicle 200 is to be parked in the parking space, the pose of the adjacent vehicle 201 can be used as the parking pose of the own vehicle 200, or through the system 100 A display (not marked) is provided to display at least one adjacent vehicle 201 and the parking space, so that the driver operating the system 100 can determine the parking space according to the displayed results, especially when there are multiple options for the parking space.

根據前述S01至S03步驟，本系統100可以進一步搭載自動停車功能，即由處理單元103產生一停車路徑，根據該停車路徑，透過車輛訊號總成介面1020傳輸控制訊號控制本車輛200，使其移動至停車位。According to the aforementioned steps S01 to S03, the system 100 can be further equipped with an automatic parking function, that is, a parking path is generated by the processing unit 103, and according to the parking path, a control signal is transmitted through the vehicle signal assembly interface 1020 to control the vehicle 200 to make it move. to the parking space.

對於使用本系統實施停車位識別的用戶來說，特別是在不具有能輕易辨識的停車線的停車場域內的停車識別，經由本發明可得到另一相鄰的車輛的位姿，而透過對於另一相鄰的車輛的車輪位姿計算，得到與其相似的停車位姿以及該停車場域的可達空間，同時，透過獲得感測訊號並結合影像訊號，可以計算另一相鄰的車輛的邊界，使停車位的辨識更顯得精確方便。For users who use this system to implement parking space recognition, especially for parking recognition in parking areas that do not have easily identifiable parking lines, the present invention can obtain the pose of another adjacent vehicle, and through the Calculate the wheel pose of another adjacent vehicle to obtain the similar parking pose and the accessible space of the parking area. At the same time, by obtaining the sensing signal and combining the image signal, the boundary of another adjacent vehicle can be calculated , making the identification of parking spaces more accurate and convenient.

以上所述，僅是本發明的較佳實施例，並非對本發明作任何形式上的限制，雖然本發明已以較佳實施例揭露如上，然而並非用以限定本發明,任何熟悉本專業的技術人員,在不脫離本發明技術方案範圍內，當可利用上述揭示的方法及技術內容作出些許的更動或修飾為等同變化的等效實施例，但凡是未脫離本發明技術方案的內容，依據本發明的技術實質對以上實施例所作的任何簡單修改、等同變化與修飾，均仍屬於本發明技術方案的範圍內。The above descriptions are only preferred embodiments of the present invention, and do not limit the present invention in any form. Although the present invention has been disclosed as above with preferred embodiments, it is not intended to limit the present invention. Anyone familiar with the technology of this field Personnel, without departing from the scope of the technical solution of the present invention, when the method and technical content disclosed above can be used to make some changes or modifications to equivalent embodiments with equivalent changes, but all the content that does not depart from the technical solution of the present invention, according to this Technical Essence of the Invention Any simple modifications, equivalent changes and modifications made to the above embodiments still fall within the scope of the technical solutions of the present invention.

100:識別停車位的系統 101:影像訊號接收模組 102:感測器訊號接收模組 1020:車輛訊號總成介面 103:處理單元 200:本車輛 201:相鄰車輛 2010:車輪 100:A system for identifying parking spaces 101: Video signal receiving module 102: Sensor signal receiving module 1020: vehicle signal assembly interface 103: Processing unit 200: This vehicle 201: Adjacent vehicles 2010: Wheels

圖1是本發明的一種識別停車位的系統的結構示意圖; 圖2是本發明的一種識別停車位的方法流程圖; 圖3是本發明在識別另一相鄰車輛的實施示意圖; 圖4是本發明在識別另一相鄰車輛的車輪位姿實施示意圖 Fig. 1 is a structural schematic diagram of a system for identifying parking spaces of the present invention; Fig. 2 is a flow chart of a method for identifying a parking space of the present invention; Fig. 3 is a schematic diagram of the present invention in identifying another adjacent vehicle; Fig. 4 is a schematic diagram of implementing the present invention in identifying the wheel pose of another adjacent vehicle

100:識別停車位的系統 100:A system for identifying parking spaces

101:影像訊號接收模組 101: Video signal receiving module

102:感測器訊號接收模組 102: Sensor signal receiving module

1020:車輛訊號總成介面 1020: vehicle signal assembly interface

103:處理單元 103: Processing unit

200:本車輛 200: This vehicle

201:相鄰車輛 201: Adjacent vehicles

2010:車輪 2010: Wheels

Claims (10)

一種識別停車位的方法，包括以下步驟： 獲取車輛移動時包括至少一相鄰車輛的連續影像幀； 獲取車輛移動時的連續感測訊號； 從所述連續影像幀中辨識所述至少一相鄰車輛的位姿； 根據所述連續影像幀及所述連續感測訊號產生所述至少一相鄰車輛的邊界；以及 根據所述至少一相鄰車輛的邊界及所述至少一相鄰車輛的位姿識別停車位。 A method for identifying a parking space, comprising the steps of: Acquiring continuous image frames including at least one adjacent vehicle when the vehicle is moving; Obtain continuous sensing signals when the vehicle is moving; identifying the pose of the at least one adjacent vehicle from the continuous image frames; generating the boundary of the at least one adjacent vehicle according to the continuous image frames and the continuous sensing signals; and A parking space is identified according to the boundary of the at least one adjacent vehicle and the pose of the at least one adjacent vehicle. 如申請專利範圍第1項所述的識別停車位的方法，其特徵在於，所述至少一相鄰車輛的位姿還包括車輪位姿。The method for identifying a parking space as described in item 1 of the scope of the patent application is characterized in that the pose of the at least one adjacent vehicle also includes the pose of a wheel. 如申請專利範圍第1項所述的識別停車位的方法，其特徵在於，將所述連續影像幀及所述連續感測訊號進行融合。The method for identifying a parking space as described in item 1 of the scope of the patent application is characterized in that the continuous image frames and the continuous sensing signals are fused. 如申請專利範圍第1項所述的識別停車位的方法，其特徵在於，還包括顯示所述至少一相鄰車輛及所述停車位。The method for identifying a parking space as described in item 1 of the scope of the patent application further includes displaying the at least one adjacent vehicle and the parking space. 如申請專利範圍第1項所述的識別停車位的方法，其特徵在於，還包括產生一停車路徑，根據所述停車路徑，控制所述車輛移動至所述停車位。The method for identifying a parking space as described in item 1 of the scope of the patent application further includes generating a parking path, and controlling the vehicle to move to the parking space according to the parking path. 一種識別停車位的系統，包括： 影像訊號接收模組，用來獲取車輛移動時包括至少一相鄰車輛的連續影像幀； 感測器訊號接收模組，用來獲取車輛移動時的連續感測訊號；以及 處理單元，從所述連續影像幀中辨識所述至少一相鄰車輛的位姿，並根據所述連續影像幀及所述連續感測訊號產生所述至少一相鄰車輛的邊界； 其中所述處理單元根據所述至少一相鄰車輛的邊界及所述至少一相鄰車輛的位姿識別停車位。 A system for identifying parking spaces, comprising: An image signal receiving module, used to acquire continuous image frames including at least one adjacent vehicle when the vehicle is moving; The sensor signal receiving module is used to obtain continuous sensing signals when the vehicle is moving; and a processing unit, identifying the pose of the at least one adjacent vehicle from the continuous image frames, and generating the boundary of the at least one adjacent vehicle according to the continuous image frames and the continuous sensing signals; Wherein the processing unit recognizes the parking space according to the boundary of the at least one adjacent vehicle and the pose of the at least one adjacent vehicle. 如申請專利範圍第6項所述的識別停車位的系統，其特徵在於，所述至少一相鄰車輛的位姿還包括車輪位姿。The system for identifying a parking space as described in item 6 of the scope of the patent application is characterized in that the pose of the at least one adjacent vehicle also includes the pose of a wheel. 如申請專利範圍第6項所述的識別停車位的系統，其特徵在於，所述處理單元將所述連續影像幀及所述連續感測訊號進行融合。The system for identifying parking spaces as described in item 6 of the scope of the patent application is characterized in that the processing unit fuses the continuous image frames and the continuous sensing signals. 如申請專利範圍第6項所述的識別停車位的系統，其特徵在於，還包括顯示器用來顯示所述至少一相鄰車輛及所述停車位。The system for identifying a parking space as described in item 6 of the scope of the patent application further includes a display for displaying the at least one adjacent vehicle and the parking space. 如申請專利範圍第6項所述的識別停車位的系統，其特徵在於，所述處理單元產生一停車路徑，根據所述停車路徑，控制所述車輛移動至所述停車位。The system for identifying a parking space as described in item 6 of the scope of the patent application is characterized in that the processing unit generates a parking path, and controls the vehicle to move to the parking space according to the parking path.
TW110115663A 2021-04-29 2021-04-29 Method and system for identifying a parking space TWI773288B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
TW110115663A TWI773288B (en) 2021-04-29 2021-04-29 Method and system for identifying a parking space

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW110115663A TWI773288B (en) 2021-04-29 2021-04-29 Method and system for identifying a parking space

Publications (2)

Publication Number Publication Date
TWI773288B TWI773288B (en) 2022-08-01
TW202241739A true TW202241739A (en) 2022-11-01

Family

ID=83806954

Family Applications (1)

Application Number Title Priority Date Filing Date
TW110115663A TWI773288B (en) 2021-04-29 2021-04-29 Method and system for identifying a parking space

Country Status (1)

Country Link
TW (1) TWI773288B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115273523A (en) * 2021-04-29 2022-11-01 欧特明电子股份有限公司 Method and system for identifying parking space

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI784172B (en) * 2019-06-06 2022-11-21 先進光電科技股份有限公司 Mobile vehicle assistance system and parking assistance method thereof
CN112389419B (en) * 2019-08-12 2022-04-08 欧特明电子股份有限公司 Method for identifying parking space and parking assistance system
CN112550278B (en) * 2020-12-03 2022-05-17 上汽大众汽车有限公司 Automatic parking method and system based on look-around camera and ultrasonic radar detection

Also Published As

Publication number Publication date
TWI773288B (en) 2022-08-01

Similar Documents

Publication Publication Date Title
CN107577988B (en) Method, device, storage medium and program product for realizing side vehicle positioning
US8041079B2 (en) Apparatus and method for detecting obstacle through stereovision
US10000210B2 (en) Lane recognition apparatus
CN108638999B (en) Anti-collision early warning system and method based on 360-degree look-around input
JP5023872B2 (en) Image display control device and image display control system
CN112349144B (en) Monocular vision-based vehicle collision early warning method and system
CN110909705B (en) Road side parking space sensing method and system based on vehicle-mounted camera
JP2013183298A (en) Rearward visibility support device for vehicle and rearward visibility support method for vehicle
WO2022062000A1 (en) Driver assistance method based on transparent a-pillar
JP2011048520A (en) Device and method for monitoring vehicle periphery
JP2015232442A (en) Image processor and vehicle front monitoring device
CN110378836B (en) Method, system and equipment for acquiring 3D information of object
JP2012176656A (en) Parking support device
US11827148B2 (en) Display control device, display control method, moving body, and storage medium
TW202241739A (en) Method and system for identifying a parking space
JP6847709B2 (en) Camera devices, detectors, detection systems and mobiles
JP6631691B2 (en) Image processing device, device control system, imaging device, image processing method, and program
JP2007087203A (en) Collision determination system, collision determination method, and computer program
JP2002104113A (en) Rear monitoring device
JP4677820B2 (en) Predicted course display device and predicted course display method
CN116946022A (en) Vehicle driving assistance system and vehicle thereof
KR101849326B1 (en) Camera system for vehicle
JP6789151B2 (en) Camera devices, detectors, detection systems and mobiles
JP2020086956A (en) Imaging abnormality diagnosis device
JP7468207B2 (en) IMAGE RECOGNITION DEVICE, IMAGE RECOGNITION METHOD, AND IMAGE RECOGNITION PROGRAM