Calibration method and device for sensor installed at intersection and readable storage medium

Abstract

The embodiment of the invention provides a calibration method and device for a sensor installed at an intersection and a readable storage medium. The calibration method comprises the steps that geographic position coordinates of multiple calibration points collected by a calibration tool and corresponding collection time are obtained; for any calibration point which can be detected by the sensor, determining a sensing data coordinate corresponding to the calibration tool at the calibration point according to the acquisition time corresponding to the calibration point; for any calibration point combination corresponding to the sensor, according to the geographic position coordinate of each calibration point in the calibration point combination and the sensing data coordinate corresponding to each calibration point, determining a first conversion relationship between the sensing data coordinate corresponding to the calibration point combination and the geographic position coordinate; according to the first conversion relation corresponding to each calibration point combination, determining a second conversion relation used for converting sensing data coordinates of the sensor for positioning the object into geographic position coordinates of the object; the calibration tool comprises a positioning device used for collecting geographic position coordinates of a calibration point.

Description

Technical Field

[0001] The present invention relates to the field of traffic technology, and in particular to a calibration method, a device and a readable storage medium for a sensor installed at an intersection. Background Art

[0002] With the rapid growth of social economy and the rapid development of science and technology, the accelerated urbanization process has led to increasingly prominent traffic problems. Urban traffic is facing heavy pressure. Road congestion, vehicle jams, traffic safety, and chaotic traffic order have become serious problems that China's traffic has long faced. In order to effectively reduce the safety hazards in road traffic, it is necessary to deploy various types of monitoring sensors at the intersections of urban roads to monitor vehicles and pedestrians, so as to obtain traffic data and provide corresponding data support for traffic control and command and traffic violation investigation. However, there are different actual situations between different roads. When deploying and installing monitoring sensors, how to calibrate the data of the monitoring sensors so that the monitoring sensors can correctly collect the corresponding traffic data still has room for improvement. Summary of the invention

[0003] The embodiments of the present invention provide a method, a device and a readable storage medium for calibrating a sensor installed at an intersection, which are used to calibrate the sensor installed at the intersection.

[0004] An embodiment of the present invention provides a method for calibrating a sensor installed at an intersection, comprising:

[0005] Obtaining the geographical location coordinates of multiple calibration points collected by the calibration tool and the collection time corresponding to each of the calibration points;

[0006] For any calibration point detectable by the sensor, determining the sensor data coordinates of the calibration tool corresponding to the calibration point according to the acquisition time corresponding to the calibration point;

[0007] For any calibration point combination corresponding to the sensor, a first conversion relationship between the sensor data coordinates and the geographic location coordinates corresponding to the calibration point combination is determined according to the geographic location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point; wherein each calibration point combination includes at least two calibration points, and the calibration points included in different calibration point combinations are different or not completely the same, and any calibration point combination corresponding to the sensor includes at least one calibration point detectable by the sensor;

[0008] Determine, according to the first conversion relationship corresponding to each combination of calibration points, a second conversion relationship for converting the sensor data coordinates of the sensor positioning the object into the geographic location coordinates of the object;

[0009] Wherein, the calibration tool includes a positioning device for collecting the geographical location coordinates of the calibration point.

[0010] As an optional implementation, the sensor includes an image sensor;

[0011] The calibration tool also includes an identification device fixedly connected to the positioning device; the identification device includes an identification surface that meets the preset color condition, and the identification surface is the surface with the largest area in the identification device, and the maximum distance from the geometric center of the identification surface to the edge of the identification surface is less than or equal to a preset threshold;

[0012] The sensor data coordinates are the pixel coordinates of the calibration fixture in the target image;

[0013] The step of determining the sensor data coordinates of the calibration tool corresponding to the calibration point according to the collection time corresponding to the calibration point specifically includes:

[0014] A target image captured by a sensor at a capture time corresponding to the calibration point is acquired, the target image is recognized, and pixel coordinates of the calibration tool in the target image are determined.

[0015] Optionally, for any calibration point combination corresponding to the sensor, determining a first conversion relationship between the sensor data coordinates and the geographical location coordinates corresponding to the calibration point combination according to the geographical location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point includes:

[0016] determining a combination consisting of any two calibration points detectable by the sensor;

[0017] For any calibration point combination i, the first conversion relationship corresponding to the calibration point combination i is calculated in the following way:

[0018]

[0019] Among them, the matrix is the first conversion relationship; the geographical coordinates of the first calibration point in the calibration point combination i are (lng1, lat1), and the pixel coordinates of the first calibration point are (xt1, yt1); the geographical coordinates of the second calibration point of another calibration point in the calibration point combination i are (lng2, lat2), and the pixel coordinates of the second calibration point are (xt2, yt2);

[0020] The determining, based on the first conversion relationship corresponding to each combination of calibration points, of a second conversion relationship for converting the sensor data coordinates of the sensor for positioning the object into the geographic location coordinates of the object comprises:

[0021] The second conversion relationship is calculated as follows:

[0022]

[0023] Among them, the matrix is the second conversion relationship; n is the total number of calibration point combinations i.

[0024] As another optional implementation, the sensor includes a radar, and the sensing data coordinates are radar coordinates.

[0025] Optionally, for any calibration point combination corresponding to the sensor, determining a first conversion relationship between the sensor data coordinates and the geographical location coordinates corresponding to the calibration point combination according to the geographical location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point includes:

[0026] Determine a plurality of calibration point combinations k, each calibration point combination comprising a first calibration point and a second calibration point; the first calibration point is the location of the radar, and the second calibration point is any calibration point detectable by the sensor;

[0027] For any calibration point combination k, perform the following steps:

[0028] Determine the radar coordinates (xl2, yl2) of the second calibration point in the calibration point combination k;

[0029] The angle θ between the line connecting the first calibration point and the second calibration point and the true north direction is calculated as follows: k :

[0030]

[0031] If θ k <0, then θ k Add to 360° to get θ k The value of

[0032] The geographical location coordinates of the first calibration point are (lng1, lat1), and the geographical location coordinates of the second calibration point are (lng2, lat2);

[0033] The angle α between the line connecting the first calibration point and the second calibration point and the normal line of the radar perpendicular to the radar antenna surface is determined by: k :

[0034]

[0035] The angle β between the normal and the true north direction is determined by the following method: k :

[0036] βk =θ k -α k

[0037] Then for the calibration point combination k, the first conversion relationship is:

[0038]

[0039] The determining, based on the first conversion relationship corresponding to each combination of calibration points, of the second conversion relationship between the sensor data coordinates of the object and the geographic location coordinates of the object comprises:

[0040] The angle β between the normal and the true north direction is determined as follows:

[0041]

[0042] Where m is the total number of calibration point combinations k;

[0043] The second conversion relationship for converting the radar coordinates (xl, yl) of the object into the geographic location coordinates (lng, lat) of the object is determined as:

[0044]

[0045] Optionally, the radar coordinates (xl2, yl2) of the second calibration point in the calibration point combination k are specifically determined by the following method:

[0046] The distance D between the first calibration point and the second calibration point is determined according to the geographical location coordinates of the first calibration point and the geographical location coordinates of the second calibration point in the following manner:

[0047]

[0048] Where R is the radius of the earth;

[0049] According to the lane where the second calibration point is located, the radar coordinate ordinate yl2 of the second calibration point is determined by using the preset correspondence between the lane and the radar coordinate ordinate of the calibration point;

[0050] According to the distance D between the first calibration point and the second calibration point and the radar coordinate ordinate yl2 of the second calibration point, the radar coordinate abscissa xl2 of the second calibration point is determined by the following method:

[0051]

[0052] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, including:

[0053] A geographic location coordinate acquisition module, used to acquire the geographic location coordinates of multiple calibration points collected by the calibration tool and the collection time corresponding to each of the calibration points;

[0054] A sensor coordinate acquisition module, used for determining the sensor data coordinates of the calibration tool corresponding to any calibration point detectable by the sensor according to the acquisition time corresponding to the calibration point;

[0055] A first calculation module is used to determine, for any calibration point combination corresponding to the sensor, a first conversion relationship between the sensor data coordinates and the geographic location coordinates corresponding to the calibration point combination according to the geographic location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point; wherein each calibration point combination includes at least two calibration points, and the calibration points included in different calibration point combinations are different or not completely the same, and any calibration point combination corresponding to the sensor includes at least one calibration point detectable by the sensor;

[0056] A second calculation module is used to determine a second conversion relationship for converting the sensor data coordinates of the sensor positioning the object into the geographic location coordinates of the object according to the first conversion relationship corresponding to each combination of calibration points;

[0057] Wherein, the calibration tool includes a positioning device for collecting the geographical location coordinates of the calibration point.

[0058] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, comprising: a processor and a memory for storing instructions executable by the processor;

[0059] The processor is configured to execute the instructions to implement the calibration method for the sensor installed at the intersection.

[0060] Based on the same inventive concept, an embodiment of the present invention further provides a readable storage medium, wherein the readable storage medium stores a computer program, and the computer program is used to implement the calibration method for the sensor installed at the intersection.

[0061] Based on the same inventive concept, an embodiment of the present invention further provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes the calibration method for the sensor installed at the intersection.

[0062] The beneficial effects of the present invention are as follows:

[0063] The embodiments of the present invention provide a calibration method, device and readable storage medium for sensors installed at intersections. The geographic location coordinates of the calibration points are collected through calibration tooling, and then a first conversion relationship between the sensor data coordinates and the geographic location coordinates is calculated based on the sensor data coordinates of the geographic location coordinates corresponding to each calibration point, and a second conversion relationship is calculated based on each first conversion relationship. The above calibration process does not rely on high-precision maps, and the second conversion relationship for converting the sensor data coordinates for locating an object by the sensor into the geographic location coordinates of the object is determined by comprehensively considering each first conversion relationship, thereby reducing the error in converting the sensor data coordinates into the geographic location coordinates. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A flow chart of a calibration method for a sensor installed at an intersection provided by an embodiment of the present invention;

[0065] Figure 3 This is one of the schematic diagrams for selecting calibration points in an embodiment of the present invention;

[0066] Figure 4 This is a second schematic diagram of selecting calibration points in an embodiment of the present invention;

[0067] Figure 2 This is one of the structural schematic diagrams of the calibration tooling in an embodiment of the present invention;

[0068] Figure 5 A flow chart of a calibration method for an image sensor installed at an intersection provided by an embodiment of the present invention;

[0069] Figure 6 A flow chart of a calibration method for a radar installed at an intersection provided by an embodiment of the present invention;

[0070] Figure 7 A partial flow chart of a calibration method for a radar installed at an intersection provided by an embodiment of the present invention;

[0071] Figure 8 Schematic diagram of the geometric relationship between the first calibration point and the second calibration point in an embodiment of the present invention;

[0072] Fig. 9 One of the structural schematic diagrams of the electronic device provided by the embodiment of the present invention;

[0073] Fig.10 The second structural diagram of the electronic device provided by the embodiment of the present invention. DETAILED DESCRIPTION

[0074] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the present invention will be further described below with reference to the accompanying drawings and examples. However, the exemplary embodiments can be implemented in various forms and should not be understood as being limited to the embodiments described herein; on the contrary, these embodiments are provided to make the present invention more comprehensive and complete, and to fully convey the concepts of the exemplary embodiments to those skilled in the art. The same figure marks in the figures represent the same or similar structures, and thus their repeated descriptions will be omitted. The words expressing position and direction described in the present invention are all explained using the accompanying drawings as examples, but changes can be made as needed, and the changes made are all included in the scope of protection of the present invention. The drawings of the present invention are only used to illustrate the relative position relationship and do not represent the true proportions.

[0075] It should be noted that specific details are described in the following description to facilitate a full understanding of the present invention. However, the present invention can be implemented in a variety of other ways different from those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below. The subsequent description of the specification is a preferred embodiment of the present application, but the description is for the purpose of illustrating the general principles of the present application and is not intended to limit the scope of the present application. The scope of protection of the present application shall be determined by the definition of the attached claims.

[0076] The following specifically describes the calibration method, device and readable storage medium for sensors installed at intersections provided by the embodiments of the present invention in conjunction with the accompanying drawings.

[0077] The embodiment of the present invention provides a calibration method for a sensor installed at an intersection, such as Figure 1 As shown, including:

[0078] S110, obtaining the geographical location coordinates of multiple calibration points collected by the calibration tool and the collection time corresponding to each of the calibration points.

[0079] Wherein, the calibration tool includes a positioning device (1) for collecting the geographical location coordinates of the calibration point. In the specific implementation process, the positioning device (1) can support satellite positioning technologies such as the Global Positioning System (GPS), Beidou, Galileo, and Global Navigation Satellite System (GLONASS), which are not limited here. Preferably, the positioning device (1) supports multiple satellite positioning technologies at the same time, so as to determine the final geographical location coordinates of the same calibration point based on multiple original geographical location coordinates determined by different satellite positioning technologies, so as to reduce the positioning error of the calibration point and improve the positioning accuracy. Furthermore, the positioning device (1) can also support differential positioning (Differential Positioning), real-time kinematic positioning (Real-Time Kinematic, RTK) and other technologies, so as to reduce the positioning error of the calibration point through these positioning technologies and improve the positioning accuracy. The calibration tool can save the geographical location coordinates and acquisition time of the calibration point obtained in the following format.

[0080] Table 1 Geographical coordinates of each calibration point and corresponding collection time data table

[0081] Calibration point number Collection time Latitude lat Longitude P_0 2022 / 6 / 9 15:50:01 36.11796452 120.39545682 P_1 2022 / 6 / 9 15:50:22 36.11786954 120.39556311 P_2 2022 / 6 / 9 15:50:48 36.11769434 120.39583210 P_3 2022 / 6 / 9 15:51:07 36.11768328 120.39554678 …… …… …… ……

[0082] Further, at least some of the calibration points are determined by:

[0083] If the number of lanes on a one-way road is not greater than 3, all lanes are determined as target lanes; if the number of lanes on a one-way road is greater than 3, one lane is selected every other lane to be determined as the target lane;

[0084] For any target lane, the midpoint of the stop line of the target lane is set as a calibration point; and for any target lane facing the direction of the sensor, at least one calibration point is set in the area between 30 meters and 50 meters from the stop line.

[0085] like Figure 3 As shown in the figure, the road is a two-way road with four lanes, that is, the number of lanes in one direction is 2, so the midpoint of the stop line of all lanes is set as a calibration point. In addition, for any target lane facing the sensor, a calibration point is set at a position 50 meters before the stop line. Figure 4As shown, the road shown has 8 lanes in both directions, that is, the number of lanes in one direction is 4. Then, one lane is selected as the target lane every other lane in the road shown, and the midpoint of the stop line of the selected target lane is set as the calibration point. In addition, for any target lane facing the direction of the sensor, a calibration point is set at a position 50 meters before the stop line.

[0086] S120. For any calibration point detectable by the sensor, determine the sensor data coordinates of the calibration tool corresponding to the calibration point according to the collection time corresponding to the calibration point.

[0087] Since the sensor may continuously collect multiple sets of sensor data during working hours, including sensor data collected from calibration points and sensor data collected from non-calibration points, the sensor data coordinates corresponding to the calibration points are screened out from the sensor data collected by the sensor according to the collection time corresponding to the calibration points.

[0088] In the specific implementation process, since sensors may be installed on roads in different directions of the intersection, for any sensor to be calibrated, the calibration point where the calibration tool collects the geographic location coordinates may not be detected by the sensor to be calibrated. Figure 3 As shown, the sensor 3 can only detect the calibration points P6-P11 and P22 in the direction it is facing. Therefore, when calibrating the sensor 3, it is only necessary to determine the geographical coordinates of the calibration points P6-P11 and P22.

[0089] S130. For any calibration point combination corresponding to the sensor, determine a first conversion relationship between the sensor data coordinates and the geographic location coordinates corresponding to the calibration point combination according to the geographic location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point. Each calibration point combination includes at least two calibration points, and the calibration points included in different calibration point combinations are different or not completely the same. Any calibration point combination corresponding to the sensor includes at least one calibration point detectable by the sensor.

[0090] S140. Determine, based on the first conversion relationship corresponding to each combination of calibration points, a second conversion relationship for converting the sensor data coordinates of the sensor locating the object into the geographic location coordinates of the object.

[0091] In this way, the geographic location coordinates of the calibration points are collected through the calibration tooling, and then the first conversion relationship between the sensor data coordinates and the geographic location coordinates is calculated according to the sensor data coordinates of the geographic location coordinates corresponding to each calibration point, and the second conversion relationship is calculated according to each first conversion relationship. The above calibration process does not rely on high-precision maps, and the second conversion relationship for converting the sensor data coordinates used to locate the object by the sensor into the geographic location coordinates of the object is determined by comprehensively considering each first conversion relationship, thereby reducing the error in converting the sensor data coordinates into the geographic location coordinates.

[0092] The following introduces the calibration methods of two different sensors respectively.

[0093] (a) The sensor includes an image sensor.

[0094] like Figure 2 As shown, the calibration tool also includes an identification device (2) fixedly connected to the positioning device (1). The identification device (2) includes an identification surface that meets a preset color condition, and the identification surface is the surface with the largest area in the identification device, and the maximum distance from the geometric center of the identification surface to the edge of the identification surface is less than or equal to a preset threshold.

[0095] Furthermore, the preset color condition is that the color of the recognition surface is a pure color, and the color saturation of the recognition surface is not less than a saturation threshold.

[0096] Preferably, the color saturation threshold is 75%, and the preset threshold is 25 cm. Figure 3 As shown, the identification device (2) is a disc-shaped structure, and the identification device (2) also serves as the base of the calibration tool. The identification device (2) is fixedly connected to the positioning device (1) through a connecting rod (3). The color of the identification device (2) is pure red, and the radius of the identification surface of the identification device (2) is 25 cm.

[0097] Correspondingly, the sensing data coordinates are the pixel coordinates of the calibration tool in the target image.

[0098] like Figure 5 As shown, the step S120, for any calibration point detectable by the sensor, determines the sensor data coordinates of the calibration tool corresponding to the calibration point according to the acquisition time corresponding to the calibration point, specifically includes:

[0099] S120A. For any calibration point detectable by the sensor, obtain a target image captured by the sensor at a capture time corresponding to the calibration point, identify the target image, and determine pixel coordinates of the calibration tool in the target image.

[0100] In the specific implementation process, since the image sensor continuously collects video information when working, the video frame at the collection time corresponding to the calibration point can be screened out from the video information through the collection time corresponding to the calibration point to determine it as the target image. In the process of identifying the target image, the image area of ​​the calibration tool can be identified from the target image by edge detection, filtering, template matching, etc., or the target image can be identified by an image recognition algorithm designed based on a machine learning model, and the image area of ​​the calibration tool can be identified from the target image. Then, the pixel coordinates corresponding to the calibration tool are determined according to the image area of ​​the calibration tool. A pixel point in the image area of ​​the calibration tool can be selected to represent the calibration tool, and the pixel coordinates of the pixel point are used as the pixel coordinates of the calibration tool. For example, the pixel coordinates of the center, vertex, etc. of the image area of ​​the calibration tool are selected as the pixel coordinates of the calibration tool. The pixel coordinates of the calibration tool in the target image can be saved in the following format.

[0101] Table 2 Pixel coordinate data table of the calibration tool in the target image

[0102] Video ID Calibration point number Pixel coordinates V001 P_3 (1079，473) V001 P_4 (1676，483) V001 P_5 (2264，463) V001 P_12 (956，879) V001 P_14 (905，853)

[0103] By using a specially designed calibration fixture for the image sensor to shoot, since the recognition surface of the recognition device of the calibration fixture uses a highly saturated color, it is beneficial to identify the target image and determine the pixel coordinates of the calibration fixture in the target image. By limiting the size of the recognition surface, it can ensure that the image area of ​​the calibration fixture in the target image is smaller, thereby ensuring position focus. When determining the pixel coordinates corresponding to the calibration fixture, it is more accurate to use the selected pixel points to represent the calibration fixture, thereby improving the calibration accuracy.

[0104] Furthermore, if Figure 5 As shown, the step S130, for any calibration point combination corresponding to the sensor, determines a first conversion relationship between the sensor data coordinates and the geographical location coordinates corresponding to the calibration point combination according to the geographical location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point, specifically including:

[0105] S131A. Determine a combination of any two calibration points detectable by the sensor.

[0106] Specifically, the calibration points include P1, P2, P3, ..., P n , then all calibration point combinations of any two calibration points can be determined by the following matrix:

[0107]

[0108] S132A. For any calibration point combination i, a first conversion relationship in matrix form is obtained by multiplying the first matrix by the second matrix, wherein the elements of the first matrix are the geographical coordinates of the two calibration points of the calibration point combination i; the second matrix is ​​the inverse matrix of the third matrix; the elements of the third matrix are the pixel coordinates of the two calibration points of the calibration point combination i, and the elements at the same position of the first matrix and the third matrix correspond to each other.

[0109] That is, the first conversion relationship corresponding to the calibration point combination i is calculated in the following manner:

[0110]

[0111] Among them, the matrix is the first conversion relationship; the geographic location coordinates of the first calibration point in the calibration point combination i are (lng1, lat1), and the pixel coordinates of the first calibration point are (xt1, yt1); the geographic location coordinates of the second calibration point of another calibration point in the calibration point combination i are (lng2, lat2), and the pixel coordinates of the second calibration point are (xt2, yt2).

[0112] Alternatively, if Figure 5 As shown, the step S140, according to the first conversion relationship corresponding to each combination of calibration points, determines a second conversion relationship for converting the sensor data coordinates of the sensor positioning the object into the geographic location coordinates of the object, specifically including:

[0113] S141A. For any matrix element position, calculate the average value of the elements at the matrix element position in each of the first conversion relationships.

[0114] S142A. Combine the average values ​​of the positions of the matrix elements according to the corresponding positions of the matrix elements to obtain a second conversion relationship in matrix form.

[0115] That is, the second conversion relationship is calculated in the following manner:

[0116]

[0117] Among them, the matrix is the second conversion relationship; n is the total number of calibration point combinations i.

[0118] Optionally, for the step S140, for any matrix element position, the elements of the matrix element position in each of the first conversion relations may first remove the extreme values ​​and then take the average of the remaining elements, and then combine the average values ​​of each matrix element position according to the corresponding matrix element position to obtain the second conversion relation in matrix form. Removing extreme values ​​may be achieved by removing the maximum and minimum values, using a normal distribution function to remove values ​​outside the 3σ range, etc., which are not limited in detail herein.

[0119] Then, the second conversion relationship is used to calculate the geographical location coordinates (lng, lat) corresponding to any pixel point (xt, yt) in the image captured by the image sensor in the following manner:

[0120]

[0121] (ii) The sensor includes a radar.

[0122] Correspondingly, the sensor data coordinates are radar coordinates.

[0123] Furthermore, if Figure 6 As shown, the step S130, for any calibration point combination corresponding to the sensor, determines a first conversion relationship between the sensor data coordinates and the geographical location coordinates corresponding to the calibration point combination according to the geographical location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point, specifically including:

[0124] S131B, determine a plurality of calibration point combinations k. Each calibration point combination includes a first calibration point and a second calibration point. The first calibration point is the location of the radar, and the second calibration point is any calibration point detectable by the sensor. Then, the radar coordinates of the first calibration point are (0, 0).

[0125] S132B. Determine a calibration point combination k without repetition.

[0126] If there is a combination of calibration points that has not been selected, execute step S133B; if all the combinations of calibration points have been selected, execute step S140.

[0127] S133B, determining the radar coordinates (xl2, yl2) of the second calibration point in the calibration point combination k.

[0128] In the specific implementation process, Figure 7 As shown, the radar coordinates (xl2, yl2) of the second calibration point can be determined in the following way:

[0129] S133B1. Determine the distance between the first calibration point and the second calibration point according to the geographical coordinates of the first calibration point and the geographical coordinates of the second calibration point. Specifically, the distance D between the first calibration point and the second calibration point is calculated in the following manner:

[0130]

[0131] Among them, R is the radius of the earth, which is approximately 6378137 meters.

[0132] S133B2. According to the lane where the second calibration point is located, the radar coordinate ordinate y12 of the second calibration point is determined by using a preset correspondence between the lane and the radar coordinate ordinate of the calibration point.

[0133] S133B3, according to the distance between the first calibration point and the second calibration point and the radar coordinate ordinate y12 of the second calibration point, determine the radar coordinate abscissa x12 of the second calibration point. Specifically, the radar coordinate abscissa of the second calibration point is calculated in the following manner:

[0134]

[0135] The above process of determining the radar coordinates of the second calibration point can be applied to the calibration process of the radar that directly collects the horizontal coordinates of the radar coordinates of the detected object during operation, and determines the vertical coordinates of the radar coordinates of the detected object according to the lane where the detected object is located.

[0136] S134B, calculating the angle θ between the line connecting the first calibration point and the second calibration point in the calibration point combination k and the true north direction k The angle θ is calculated as follows: k :

[0137] like Figure 8 As shown, the geographic coordinates of the first calibration point are (lng1, lat1), and the geographic coordinates of the second calibration point are (lng2, lat2). The earth is approximated as a sphere, with the North Pole as N and the center of the earth as O. Then N-P1P2O forms a trihedral angle. The size of the dihedral angle N-P1P2-O is θ k , whose plane angle is The magnitude of the dihedral angle P1-ON-P2 is Its plane angle is δ.

[0138] According to the trihedral sine theorem, we can get:

[0139]

[0140] According to the trihedral cosine theorem, we can get:

[0141]

[0142] So:

[0143]

[0144]

[0145] There are also:

[0146]

[0147] but:

[0148]

[0149]

[0150] but:

[0151]

[0152] If θ k <0, then θ k Add to 360° to get θ k The value of .

[0153] S135B, determine the angle α between the line connecting the first calibration point and the second calibration point in the calibration point combination k and the normal line of the radar perpendicular to the radar antenna surface. k The angle α is calculated as follows: k :

[0154]

[0155] S136B, determine the angle β between the normal line corresponding to the calibration point combination k and the true north direction k The angle β is calculated as follows: k :

[0156] β k =θ k -α k

[0157] Then, for the calibration point combination k, the first conversion relationship is obtained as follows:

[0158]

[0159] Afterwards, return to step S132B.

[0160] The step S140, determining the second conversion relationship between the sensor data coordinates of the object and the geographical location coordinates of the object according to the first conversion relationship corresponding to each combination of calibration points, specifically includes:

[0161] S141B, determining the angle β between the normal line and the true north direction. The angle β is calculated as follows:

[0162]

[0163] Where m is the total number of calibration point combinations k.

[0164] S142B, determine a second conversion relationship for converting the radar coordinates (xl, yl) of the object into the geographic location coordinates (lng, lat) of the object. The second conversion relationship is as follows:

[0165]

[0166] In the specific implementation process, if image sensors and radars are deployed at the intersection at the same time, then the positions that can be detected by the image sensors and radars and meet the calibration point setting rules described above can be set as calibration points. In this way, when calibrating the image sensor and radar, the geographic location coordinates of the calibration points that can be detected by both the image sensor and the radar only need to be collected once, thereby reducing the workload of the calibration personnel and improving the efficiency of calibration.

[0167] Through the calibration method for sensors installed at intersections provided by the embodiment of the present invention, accurate calibration of sensors such as image sensors and radars can be achieved, and a second conversion relationship for converting the sensor data coordinates of the sensor locating an object into the geographic location coordinates of the object can be obtained. Using the second conversion relationship, the sensor data coordinates collected by the sensor for locating a vehicle traveling to the intersection can be used to analyze and predict the driving state of the vehicle.

[0168] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, such as Fig. 9 As shown, including:

[0169] The geographic location coordinate acquisition module M1 is used to acquire the geographic location coordinates of multiple calibration points collected by the calibration tool and the collection time corresponding to each of the calibration points;

[0170] The sensor coordinate acquisition module M2 is used to determine the sensor data coordinates of the calibration tool corresponding to any calibration point according to the acquisition time corresponding to the calibration point;

[0171] A first calculation module M3 is used to determine, for any calibration point combination corresponding to the sensor, a first conversion relationship between the sensor data coordinates and the geographical location coordinates corresponding to the calibration point combination according to the geographical location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point; wherein each calibration point combination includes at least two calibration points, and the calibration points included in different calibration point combinations are different or not completely the same, and any calibration point combination corresponding to the sensor includes at least one calibration point detectable by the sensor;

[0172] A second calculation module M4 is used to determine a second conversion relationship for converting the sensor data coordinates of the sensor positioning the object into the geographic location coordinates of the object according to the first conversion relationship corresponding to each calibration point combination;

[0173] Wherein, the calibration tool includes a positioning device for collecting the geographical location coordinates of the calibration point.

[0174] As an optional implementation, the sensor includes an image sensor;

[0175] The calibration tool also includes an identification device fixedly connected to the positioning device; the identification device includes an identification surface that meets the preset color condition, and the identification surface is the surface with the largest area in the identification device, and the maximum distance from the geometric center of the identification surface to the edge of the identification surface is less than or equal to a preset threshold;

[0176] The sensor data coordinates are the pixel coordinates of the calibration fixture in the target image;

[0177] The step of determining the sensor data coordinates of the calibration tool corresponding to the calibration point according to the collection time corresponding to the calibration point specifically includes:

[0178] A target image captured by a sensor at a capture time corresponding to the calibration point is acquired, the target image is recognized, and pixel coordinates of the calibration tool in the target image are determined.

[0179] Optionally, for any calibration point combination corresponding to the sensor, determining a first conversion relationship between the sensor data coordinates and the geographical location coordinates corresponding to the calibration point combination according to the geographical location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point includes:

[0180] determining a combination consisting of any two calibration points detectable by the sensor;

[0181] For any calibration point combination i, the first conversion relationship corresponding to the calibration point combination i is calculated in the following way:

[0182]

[0183] Among them, the matrix is the first conversion relationship; the geographical coordinates of the first calibration point in the calibration point combination i are (lng1, lat1), and the pixel coordinates of the first calibration point are (xt1, yt1); the geographical coordinates of the second calibration point of another calibration point in the calibration point combination i are (lng2, lat2), and the pixel coordinates of the second calibration point are (xt2, yt2);

[0184] The determining, based on the first conversion relationship corresponding to each combination of calibration points, of a second conversion relationship for converting the sensor data coordinates of the sensor for positioning the object into the geographic location coordinates of the object specifically includes:

[0185] The second conversion relationship is calculated as follows:

[0186]

[0187] Among them, the matrix is the second conversion relationship; n is the total number of calibration point combinations i.

[0188] As another optional implementation, the sensor includes a radar, and the sensing data coordinates are radar coordinates.

[0189] Optionally, for any calibration point combination corresponding to the sensor, determining a first conversion relationship between the sensor data coordinates and the geographical location coordinates corresponding to the calibration point combination according to the geographical location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point, specifically includes:

[0190] Determine a plurality of calibration point combinations k, each calibration point combination comprising a first calibration point and a second calibration point; the first calibration point is the location of the radar, and the second calibration point is any calibration point detectable by the sensor;

[0191] For any calibration point combination k, perform the following steps:

[0192] Determine the radar coordinates (xl2, yl2) of the second calibration point in the calibration point combination k;

[0193] The angle θ between the line connecting the first calibration point and the second calibration point and the true north direction is calculated as follows: k :

[0194]

[0195] If θ k <0, then θ k Add to 360° to get θ kThe value of

[0196] The geographical location coordinates of the first calibration point are (lng1, lat1), and the geographical location coordinates of the second calibration point are (lng2, lat2);

[0197] The angle α between the line connecting the first calibration point and the second calibration point and the normal line of the radar perpendicular to the radar antenna surface is determined by: k :

[0198]

[0199] The angle β between the normal and the true north direction is determined by the following method: k :

[0200] β k =θ k -α k

[0201] Then for the calibration point combination k, the first conversion relationship is:

[0202]

[0203] Determining the second conversion relationship between the sensor data coordinates of the object positioned by the sensor and the geographic location coordinates of the object according to the first conversion relationship corresponding to each combination of calibration points specifically includes:

[0204] The angle β between the normal and the true north direction is determined as follows:

[0205]

[0206] Where m is the total number of calibration point combinations k;

[0207] The second conversion relationship for converting the radar coordinates (xl, yl) of the object into the geographic location coordinates (lng, lat) of the object is determined as:

[0208]

[0209] Optionally, the radar coordinates (xl2, yl2) of the second calibration point in the calibration point combination k are specifically determined by the following method:

[0210] The distance D between the first calibration point and the second calibration point is determined according to the geographical location coordinates of the first calibration point and the geographical location coordinates of the second calibration point in the following manner:

[0211]

[0212] Where R is the radius of the earth;

[0213] According to the lane where the second calibration point is located, the radar coordinate ordinate yl2 of the second calibration point is determined by using the preset correspondence between the lane and the radar coordinate ordinate of the calibration point;

[0214] According to the distance D between the first calibration point and the second calibration point and the radar coordinate ordinate yl2 of the second calibration point, the radar coordinate abscissa xl2 of the second calibration point is determined by the following method:

[0215]

[0216] In the several embodiments provided by the present invention, it should be understood that the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0217] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0218] In addition, each functional module in each embodiment of the present invention may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may be stored in a computer-readable storage medium.

[0219] Since the specific manner in which each module of the electronic device performs operations has been described in detail in the corresponding content of the calibration method for the sensor installed at the intersection, it will not be repeated here.

[0220] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, such as Fig.10 As shown, it includes: a processor 110 and a memory 120 for storing executable instructions of the processor 110;

[0221] The processor 110 is configured to execute the instructions to implement the calibration method for the sensor installed at the intersection.

[0222] In the specific implementation process, the device may have relatively large differences due to different configurations or performances, and may include one or more processors 110, memory 120, and computer-readable storage medium 130. The memory 120 and / or computer-readable storage medium 130 include one or more applications 131 or data 132. The memory 120 and / or computer-readable storage medium 130 may also include one or more operating systems 133, such as Windows, Mac OS, Linux, IOS, Android, Unix, FreeBSD, etc. Among them, the memory 120 and the computer-readable storage medium 130 may be short-term storage or persistent storage. The application 131 may include one or more modules ( Fig.10 ), each module may include a series of instruction operations. Further, the processor 110 may be configured to communicate with the computer-readable storage medium 130, and execute a series of instruction operations in the computer-readable storage medium 130 on the device. The device may also include one or more power supplies ( Fig.10 one or more network interfaces 140, wherein the network interface 140 includes a wired network interface 141 and / or a wireless network interface 142; and one or more input / output / interfaces 143.

[0223] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is used to implement the calibration method for the sensor installed at the intersection.

[0224] Based on the same inventive concept, an embodiment of the present invention further provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes the calibration method for the sensor installed at the intersection.

[0225] The embodiments of the present invention provide a calibration method, device and readable storage medium for sensors installed at intersections. The geographic location coordinates of the calibration points are collected through calibration tooling, and then a first conversion relationship between the sensor data coordinates and the geographic location coordinates is calculated based on the sensor data coordinates of the geographic location coordinates corresponding to each calibration point, and a second conversion relationship is calculated based on each first conversion relationship. The above calibration process does not rely on high-precision maps, and the second conversion relationship for converting the sensor data coordinates for locating an object by the sensor into the geographic location coordinates of the object is determined by comprehensively considering each first conversion relationship, thereby reducing the error in converting the sensor data coordinates into the geographic location coordinates.

[0226] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0227] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0228] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0229] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0230] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for calibrating a sensor installed at an intersection, characterized in that: include: Obtaining the geographical location coordinates of multiple calibration points collected by the calibration tool and the collection time corresponding to each of the calibration points; For any calibration point detectable by the sensor, determining the sensor data coordinates of the calibration tool corresponding to the calibration point according to the acquisition time corresponding to the calibration point; For any calibration point combination corresponding to the sensor, a first conversion relationship between the sensor data coordinates and the geographic location coordinates corresponding to the calibration point combination is determined according to the geographic location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point; wherein each calibration point combination includes at least two calibration points, and the calibration points included in different calibration point combinations are different or not completely the same, and any calibration point combination corresponding to the sensor includes at least one calibration point detectable by the sensor; Determine, according to the first conversion relationship corresponding to each combination of calibration points, a second conversion relationship for converting the sensor data coordinates of the sensor positioning the object into the geographic location coordinates of the object; Wherein, the calibration tool includes a positioning device for collecting the geographical location coordinates of the calibration point.

2. The method according to claim 1, characterized in that The sensor comprises an image sensor; The calibration tool also includes an identification device fixedly connected to the positioning device; the identification device includes an identification surface that meets the preset color condition, and the identification surface is the surface with the largest area in the identification device, and the maximum distance from the geometric center of the identification surface to the edge of the identification surface is less than or equal to a preset threshold; The sensor data coordinates are the pixel coordinates of the calibration fixture in the target image; The step of determining the sensor data coordinates of the calibration tool corresponding to the calibration point according to the collection time corresponding to the calibration point specifically includes: A target image captured by a sensor at a capture time corresponding to the calibration point is acquired, the target image is recognized, and pixel coordinates of the calibration tool in the target image are determined.

3. The method according to claim 2, characterized in that For any calibration point combination corresponding to the sensor, determining a first conversion relationship between the sensor data coordinates and the geographical location coordinates corresponding to the calibration point combination according to the geographical location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point, comprises: determining a combination consisting of any two calibration points detectable by the sensor; For any calibration point combination i, the first conversion relationship corresponding to the calibration point combination i is calculated in the following way: Among them, the matrix is the first conversion relationship; the geographical coordinates of the first calibration point in the calibration point combination i are (lng1, lat1), and the pixel coordinates of the first calibration point are (xt1, yt1); the geographical coordinates of the second calibration point of another calibration point in the calibration point combination i are (lng2, lat2), and the pixel coordinates of the second calibration point are (xt2, yt2); The determining, based on the first conversion relationship corresponding to each combination of calibration points, of a second conversion relationship for converting the sensor data coordinates of the sensor for positioning the object into the geographic location coordinates of the object comprises: The second conversion relationship is calculated as follows: Among them, the matrix is the second conversion relationship; n is the total number of calibration point combinations i.

4. The method according to claim 1, characterized in that The sensor includes a radar, and the sensing data coordinates are radar coordinates.

5. The method according to claim 4, characterized in that For any calibration point combination corresponding to the sensor, determining a first conversion relationship between the sensor data coordinates and the geographical location coordinates corresponding to the calibration point combination according to the geographical location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point, comprises: Determine a plurality of calibration point combinations k, each calibration point combination comprising a first calibration point and a second calibration point; the first calibration point is the location of the radar, and the second calibration point is any calibration point detectable by the sensor; For any calibration point combination k, perform the following steps: Determine the radar coordinates (xl2, yl2) of the second calibration point in the calibration point combination k; The angle θ between the line connecting the first calibration point and the second calibration point and the true north direction is calculated as follows: k : If θ k <0, then θ k Add to 360° to get θ k The value of The geographical location coordinates of the first calibration point are (lng1, lat1), and the geographical location coordinates of the second calibration point are (lng2, lat2); The angle α between the line connecting the first calibration point and the second calibration point and the normal line of the radar perpendicular to the radar antenna surface is determined by: k : The angle β between the normal and the true north direction is determined by the following method: k : b k =θ k -a k Then for the calibration point combination k, the first conversion relationship is: The determining, based on the first conversion relationship corresponding to each combination of calibration points, of the second conversion relationship between the sensor data coordinates of the object and the geographic location coordinates of the object comprises: The angle β between the normal and the true north direction is determined as follows: Where m is the total number of calibration point combinations k; The second conversion relationship for converting the radar coordinates (xl, yl) of the object into the geographic location coordinates (lng, lat) of the object is determined as:

6. The method according to claim 5, characterized in that The radar coordinates (xl2, yl2) of the second calibration point in the calibration point combination k are specifically determined by the following method: The distance D between the first calibration point and the second calibration point is determined according to the geographical location coordinates of the first calibration point and the geographical location coordinates of the second calibration point in the following manner: Where R is the radius of the earth; According to the lane where the second calibration point is located, the radar coordinate ordinate yl2 of the second calibration point is determined by using the preset correspondence between the lane and the radar coordinate ordinate of the calibration point; According to the distance D between the first calibration point and the second calibration point and the radar coordinate ordinate yl2 of the second calibration point, the radar coordinate abscissa xl2 of the second calibration point is determined by the following method:

7. An electronic device, characterized in that: include: A geographic location coordinate acquisition module, used to acquire the geographic location coordinates of multiple calibration points collected by the calibration tool and the collection time corresponding to each of the calibration points; A sensor coordinate acquisition module, used for determining the sensor data coordinates of the calibration tool corresponding to any calibration point detectable by the sensor according to the acquisition time corresponding to the calibration point; A first calculation module is used to determine, for any calibration point combination corresponding to the sensor, a first conversion relationship between the sensor data coordinates and the geographic location coordinates corresponding to the calibration point combination according to the geographic location coordinates of each calibration point in the calibration point combination and the sensor data coordinates corresponding to each calibration point; wherein each calibration point combination includes at least two calibration points, and the calibration points included in different calibration point combinations are different or not completely the same, and any calibration point combination corresponding to the sensor includes at least one calibration point detectable by the sensor; A second calculation module is used to determine a second conversion relationship for converting the sensor data coordinates of the sensor positioning the object into the geographic location coordinates of the object according to the first conversion relationship corresponding to each combination of calibration points; Wherein, the calibration tool includes a positioning device for collecting the geographical location coordinates of the calibration point.

8. An electronic device, characterized in that: include: a processor and a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the calibration method for a sensor installed at an intersection as described in any one of claims 1-6.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and the computer program is used to implement the calibration method for a sensor installed at an intersection as described in any one of claims 1-6.

10. A computer program product, characterized in that The computer program product includes: a computer program code, which, when executed on a computer, enables the computer to execute the calibration method for a sensor installed at an intersection as described in any one of claims 1 to 6.

Images