CN111553956A - Calibration method and device of shooting device, electronic equipment and storage medium - Google Patents
Calibration method and device of shooting device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111553956A CN111553956A CN202010431655.XA CN202010431655A CN111553956A CN 111553956 A CN111553956 A CN 111553956A CN 202010431655 A CN202010431655 A CN 202010431655A CN 111553956 A CN111553956 A CN 111553956A
- Authority
- CN
- China
- Prior art keywords
- shooting device
- shooting
- reference points
- image
- external parameters
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 230000000007 visual effect Effects 0.000 claims abstract description 15
- 230000003068 static effect Effects 0.000 claims abstract description 9
- 230000015654 memory Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 19
- 238000006073 displacement reaction Methods 0.000 claims description 13
- 238000005096 rolling process Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims 1
- 238000003384 imaging method Methods 0.000 description 21
- 238000010586 diagram Methods 0.000 description 9
- 239000011159 matrix material Substances 0.000 description 8
- 238000004891 communication Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001680 brushing effect Effects 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 2
- 238000000576 coating method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000003973 paint Substances 0.000 description 2
- 238000010422 painting Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
Abstract
The application discloses a calibration method and device of a shooting device, electronic equipment and a storage medium, and relates to the field of intelligent transportation. The method comprises the following steps that a reference object exists in the shooting visual field range of a shooting device, a plurality of datum points are arranged on the reference object, and the reference object is a static object in the environment where the shooting device is located, and the method comprises the following steps: acquiring an image shot by a shooting device, wherein the image comprises a plurality of reference points; acquiring world coordinates of a plurality of reference points in a high-precision map according to the position of the shooting device; and obtaining the external parameters of the shooting device according to the pixel coordinates of the plurality of reference points and the world coordinates of the plurality of reference points in the image. In the application, because the plurality of reference points arranged in the shooting view field range of the shooting device are the reference points on the static object in the environment, the world coordinates of the plurality of reference points in the high-precision map of the acquired environment of the vehicle are detected, the problem of manually acquiring the world coordinates of the reference points is avoided, and the calibration efficiency of the shooting device is improved.
Description
Technical Field
The present application relates to the field of intelligent transportation technologies, and in particular, to a method and an apparatus for calibrating a camera in an automatic driving technology, an electronic device, and a storage medium.
Background
The camera external reference calibration refers to acquiring a transformation matrix from a world coordinate system of a camera to a camera coordinate system after the camera is installed, wherein the transformation matrix is the camera external reference and is also called the camera pose. The camera external parameter is a necessary condition for connecting the position of an object in the real world with the pixel position of the object in an image, and is widely applied to the fields of positioning the position of the object in the image, such as the fields of automatic driving, security protection, traffic monitoring and control of intelligent traffic and the like.
In the prior art, the external reference calibration mode of the camera is as follows: the method comprises the steps of manually setting a calibration plate in a shooting visual field range of a camera, and manually acquiring world coordinates of a plurality of angular points in the calibration plate after the calibration plate is set. After the image of the calibration board shot by the camera is obtained, the camera external parameters are determined according to the pixel coordinates of the corner points in the image and the world coordinates of the corner points.
At present, a large number of cameras are arranged on two sides of a road, if the method is adopted, a calibration plate needs to be manually arranged in the visual field range of each camera, the world coordinates of angular points in the calibration plate are obtained, the calibration speed is low, and the calibration efficiency is low.
Disclosure of Invention
The application provides a calibration method and device of a shooting device, electronic equipment and a storage medium, and the calibration efficiency of the shooting device is improved.
The first aspect of the present application provides a calibration method for a shooting device, where a reference object exists in a shooting view field of the shooting device, the reference object is provided with a plurality of reference points, and the reference object is a stationary object in an environment where the shooting device is located, the method includes: acquiring an image shot by the shooting device, wherein the image comprises the plurality of reference points; acquiring world coordinates of the plurality of reference points in the high-precision map according to the position of the shooting device; and obtaining the external parameters of the shooting device according to the pixel coordinates of the plurality of reference points and the world coordinates of the plurality of reference points in the image.
In the embodiment, because the plurality of reference points set in the shooting view field of the shooting device are the reference points on the static object in the environment, the world coordinates of the plurality of reference points in the acquired high-precision map of the environment of the vehicle are detected, the problem of manually acquiring the world coordinates of the reference points is avoided, and the calibration efficiency of the shooting device is improved.
A second aspect of the present application provides a calibration apparatus for a photographing apparatus, including:
the first processing module is used for acquiring an image shot by a shooting device, wherein the image comprises a plurality of datum points; and the second processing module is used for acquiring the world coordinates of the plurality of reference points in a high-precision map according to the position of the shooting device and obtaining the external parameters of the shooting device according to the pixel coordinates of the plurality of reference points in the image and the world coordinates of the plurality of reference points.
The beneficial effects of the calibration device of the photographing device provided by the second aspect and each possible design can be referred to the beneficial effects brought by the first aspect, which are not described herein again.
A third aspect of the present application provides an electronic device comprising: at least one processor and memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the electronic device executes the calibration method of the photographing apparatus of the first aspect.
A fourth aspect of the present application provides a computer-readable storage medium, which stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the calibration method of the shooting device of the first aspect is implemented.
The application provides a calibration method and device of a shooting device, electronic equipment and a storage medium, wherein a reference object exists in a shooting visual field range of the shooting device, a plurality of datum points are arranged on the reference object, and the reference object is a static object in the environment where the shooting device is located, and the method comprises the following steps: acquiring an image shot by a shooting device, wherein the image comprises a plurality of reference points; acquiring world coordinates of a plurality of reference points in a high-precision map according to the position of the shooting device; and obtaining the external parameters of the shooting device according to the pixel coordinates of the plurality of reference points and the world coordinates of the plurality of reference points in the image. In the application, because the plurality of reference points arranged in the shooting view field range of the shooting device are the reference points on the static object in the environment, the world coordinates of the plurality of reference points in the high-precision map of the acquired environment of the vehicle are detected, the problem of manually acquiring the world coordinates of the reference points is avoided, and the calibration efficiency of the shooting device is improved. And for a large number of shooting devices arranged on the roadside, the world coordinates of the reference points in the visual field range of each shooting device can be acquired in a high-precision map, the problem of calibrating each shooting device one by one is avoided, and the calibration efficiency of the shooting devices is further improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is a diagram illustrating a calibration method of a camera according to the prior art;
fig. 2 is a schematic view of a scene to which the calibration method of the photographing device provided by the present application is applied;
fig. 3 is a schematic flowchart of an embodiment of a calibration method of a shooting device provided in the present application;
FIG. 4 is a schematic view of the present application providing datum points on the side rails of a roadway;
fig. 5 is a schematic flowchart of another embodiment of a calibration method of a camera according to the present application;
FIG. 6 is a schematic diagram of a fold-half adjustment initial external reference provided herein;
fig. 7 is a schematic flowchart of another embodiment of a calibration method of a camera according to the present application;
fig. 8 is a schematic structural diagram of a calibration apparatus of the photographing apparatus provided in the present application;
fig. 9 is a schematic structural diagram of an electronic device provided in the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In order to more clearly describe the calibration method of the photographing apparatus provided by the present application, a calibration method of a photographing apparatus in the prior art is described below with reference to fig. 1. Fig. 1 is a schematic diagram of a calibration method of a shooting device in the prior art. Fig. 1 shows cameras arranged on both sides of a road, which can monitor vehicles on the road. When calibrating the shooting device, the calibration plate needs to be manually arranged in the shooting visual field range of the shooting device, for example, the calibration plate in the figure is the calibration plate with the letter A written on the calibration plate. After the calibration board is set, the world coordinates of each corner point in the letter a on the calibration board are manually acquired, and the manner of manually acquiring the world coordinates of the corner points can be that the world coordinates of surrounding objects, such as an installation rod for installing the camera, are determined first, and then the world coordinates of the corner points in the letter a are calculated. After the image containing the calibration plate acquired by the shooting device is obtained, the external parameters of the shooting device can be acquired according to the pixel coordinates of the corner points in the letter A in the image and the manually acquired world coordinates of the corner points in the letter A, and then the calibration of the shooting device is completed.
As shown in fig. 1, in the fields of automatic driving roadside sensing, security protection, traffic monitoring and control, etc., at present, a large number of shooting devices are all installed on monitoring poles and traffic light poles, if the shooting devices are calibrated according to the above method, a calibration plate needs to be manually arranged in the shooting visual field range of each shooting device, the world coordinates of the angular points in the calibration plate are manually obtained, each shooting device is sequentially calibrated, a large amount of manpower and material resources are wasted, the calibration efficiency is low, and the precision of the method for manually obtaining the world coordinates of the angular points in the calibration plate is low, which can affect the calibration result of the final shooting device.
In order to solve the above problem, the present application provides a calibration method for a photographing device, in which a reference object is determined in advance in an environment where the photographing device is located, and the reference object is a stationary object always existing in the environment, so that an additional introduction of a calibration plate is avoided. And a plurality of datum points are arranged on the reference object, and the shooting device is calibrated according to the datum points, because the reference object is a static object which always exists in the environment, when a detection vehicle acquires a high-precision map in the environment, the world coordinates of the datum points on the reference object in the environment can be acquired, so that the problem that the world coordinates of corner points on the calibration plate need to be acquired manually is avoided, and the calibration efficiency of the shooting device is improved.
Furthermore, in a scene of calibration of a large number of shooting devices, if a large number of shooting devices are arranged on the highway, standard points can be arranged on guardrails on two sides of the highway, and a plurality of reference points exist in the shooting visual field range of each shooting device, so that the calibration of the large number of shooting devices can be performed in a short time according to the mode, and the calibration efficiency of the shooting devices can be improved.
Fig. 2 is a scene schematic diagram applicable to the calibration method of the shooting device provided by the present application. As shown in fig. 2, the applicable scenes of the calibration method of the shooting device provided by the present application include: shooting device and server. It should be understood that the cameras may be cameras disposed on both sides of the road, and the cameras are used for capturing surveillance videos of the road and may capture images of the reference points on the reference object. The server can calibrate the shooting device according to the image shot by the shooting device.
It should be understood that the subject of the calibration method of the photographing apparatus in the embodiments described below may be the photographing apparatus, or a chip, a processor of the photographing apparatus, or may also be a server, a chip in a server, a processor, and the like. In the following embodiments, a calibration device of an imaging device is described as a server.
The following describes a calibration method of a photographing device provided by the present application with reference to specific embodiments, which may be combined with each other. Fig. 3 is a flowchart illustrating an embodiment of a calibration method of a camera according to the present application. As shown in fig. 3, the calibration method of the photographing apparatus provided in this embodiment may include:
s301, an image shot by the shooting device is obtained, and the image comprises a plurality of reference points.
S302, according to the position of the shooting device, the world coordinates of a plurality of reference points are acquired in a high-precision map.
And S303, obtaining external parameters of the shooting device according to the pixel coordinates of the plurality of reference points and the world coordinates of the plurality of reference points in the image.
The present embodiment may determine a reference object in advance in an environment where the photographing device is located, and set a plurality of reference points on the reference object. The reference object is a static object always existing in the environment, and optionally, the reference object can be an object common to the environment where the shooting device is located, so that the reference point on the reference object can be set in advance at one time, and the efficiency is improved.
The reference object is exemplarily a guardrail on both sides of the road or a lane line in the road. When the reference object is a guardrail on both sides of a road, painting, coating, etc. may be performed on the guardrail, with the end points of the painting or coating as reference points. Fig. 4 is a schematic view of the present application for setting a reference point on a guardrail on both sides of a road. As shown in fig. 4, a line segment of 10m length may be brushed on the guard rails on both sides of the road at intervals of 30m, both end points of the line segment being reference points, and, for example, the hatched portion in fig. 4 is a line segment formed by brushing paint. The color of the paint brushing is different from the color of the guardrail, enough discrimination is provided, and the stable Lu bang end points can be extracted from the yellow and green images most easily through experimental analysis. Similarly, the envelope may be made of a reflective material to form a reflective strip on the guard rail, as shown in fig. 4. When the reference object is a lane line in the road, the lane line is a lane line with an end point, and the end point of the lane line is a reference point.
It should be noted that when the reference point is set on the reference object, it can be ensured that at least two complete line segments (i.e. 4 end points, i.e. 4 reference points) are included in the shooting visual field range of each shooting device, and of course, there may be more reference points in the shooting visual field range of each shooting device to improve the calibration accuracy. That is, the imaging field of view of the imaging device in the present embodiment includes a plurality of reference points.
In calibrating the photographing device, an image photographed by the photographing device may be acquired, the image including a plurality of reference points. After the shooting device shoots the image, the image can be uploaded to the server.
In S302, since the reference object is a stationary object that is always present in the environment, when the probe vehicle acquires the high-precision map in the environment, the world coordinates of the plurality of reference points on the reference object in the environment are also acquired, and therefore, the world coordinates of the plurality of reference points are included in the high-precision map in the environment, and further, the manual acquisition of the world coordinates of the reference points in each imaging device can be avoided, and the accuracy is high.
Optionally, in this embodiment, after the reference points are set on the reference object, the reference points may be arranged according to a preset arrangement manner, as shown in fig. 4. Therefore, the world coordinates of one reference point can be manually measured, and the world coordinates of other reference points can be deduced according to the world coordinates of the known reference points, so that the world coordinates of the reference points can be manually acquired one by one without arranging calibration plates in the shooting range of each shooting device one by one.
In the present embodiment, in order to reduce the amount of calculation for searching for the world coordinates of the reference points in the high-precision map, the world coordinates of a plurality of reference points may be acquired in the high-precision map according to the position of the imaging device. It should be understood that the reference point within the shooting range of each shooting device can be calibrated in advance in the high-precision map, and then the world coordinates of the shooting device can be determined in the high-precision map according to the position of the shooting device so as to obtain the reference point with the calibrated world coordinates of the shooting device, and the world coordinates of the reference point is taken as the world coordinates of the reference point in the image shot by the shooting device.
In S303, in the present embodiment, after the world coordinates of the plurality of reference points in the image are acquired, the reference points in the image may be identified, and the pixel coordinates of the reference points in the image may be acquired. In the method, the reference points are identified in the image, and the identification model can be used to identify reference objects in the image, such as a guardrail and a lane line, and further take the end points of the line segment on the guardrail and the end points of the lane line as the reference points. The recognition model in this embodiment may specifically refer to an image recognition method in the prior art.
After the pixel coordinates of the reference points in the image are acquired, the external parameters of the shooting device can be obtained according to the pixel coordinates of the reference points in the image and the world coordinates of the plurality of reference points. It should be understood that the high-precision map may include an arrangement of the plurality of reference points, and when the world coordinates of the plurality of reference points are obtained in the high-precision map, the arrangement of the plurality of reference points may also be obtained. And according to the arrangement mode of the multiple reference points in the image and the arrangement mode of the multiple reference points acquired in the high-precision map, the world coordinates and the pixel coordinates of each reference point are in one-to-one correspondence, and further according to the pixel coordinates and the corresponding world coordinates of each reference point, the external parameters of the shooting device are obtained. It is understood that the external reference of the photographing device is acquired based on the pixel coordinates of the reference points and the corresponding world coordinates in a manner of calibrating the photographing device according to the pixel coordinates of the corner points in the calibration board and the corresponding world coordinates in reference to the related art.
In the calibration method for the photographing device provided in this embodiment, a reference object exists in a photographing view range of the photographing device, the reference object is provided with a plurality of reference points, and the reference object is a stationary object in an environment where the photographing device is located, and the method includes: acquiring an image shot by a shooting device, wherein the image comprises a plurality of reference points; acquiring world coordinates of a plurality of reference points in a high-precision map according to the position of the shooting device; and obtaining the external parameters of the shooting device according to the pixel coordinates of the plurality of reference points and the world coordinates of the plurality of reference points in the image. Because the predetermined reference object in the embodiment is a static object always existing in the environment, and further, an additional calibration board is avoided from being introduced, and a plurality of datum points are arranged on the reference object, and the shooting device is calibrated according to the datum points. In addition, in the scene of calibration of a large number of shooting devices, standard points can be arranged on the guardrails on two sides of the highway, and a plurality of reference points exist in the shooting visual field range of each shooting device, so that the calibration of the large number of shooting devices can be performed in a short time according to the method, and the calibration efficiency of the shooting devices is further improved.
On the basis of the above embodiments, the following describes in further detail the calibration method of the imaging apparatus provided in the present application with reference to fig. 5. Fig. 5 is a schematic flowchart of another embodiment of a calibration method of a shooting device provided in the present application. As shown in fig. 5, the calibration method of the photographing apparatus in this embodiment may include:
s501, an image shot by the shooting device is obtained, and the image comprises a plurality of reference points.
And S502, acquiring world coordinates of the shooting device in a high-precision map according to the position of the shooting device.
And S503, taking the world coordinates of the reference points of the shooting device in the preset range of the world coordinates in the high-precision map as the world coordinates of the plurality of reference points.
And S504, acquiring the predicted pixel coordinates of each reference point in the image according to the initial external parameters of the shooting device and the world coordinates of the plurality of reference points.
And S505, obtaining the external parameter of the shooting device according to the predicted pixel coordinate of each reference point, the pixel coordinate of each reference point in the image and the initial external parameter.
The implementation in S501 in this embodiment may refer to the related description in S301 in the foregoing embodiment, and is not described herein again.
In the above S502, in order to acquire the world coordinates of the reference point in the image captured by the imaging device, the world coordinates of the imaging device in the high-precision map may be acquired according to the position of the imaging device. Optionally, the position of the shooting device in this embodiment may be a longitude and latitude coordinate, and the longitude and latitude coordinate and the world coordinate have a corresponding conversion relationship, so that the world coordinate of the shooting device in the high-precision map is obtained according to the position of the shooting device.
The preset range in S503 may be a shooting visual field range of the shooting device, and the present embodiment may use the world coordinates of the shooting device in the high-precision map as a starting point, and the world coordinates of the reference points within the preset range of the starting point may be used as the world coordinates of the plurality of reference points in the image. Since the preset range in the high-precision map is the shooting visual field range of the shooting device, the plurality of reference points acquired in the high-precision map are necessarily the reference points in the image shot by the shooting device, and the accuracy is high.
In the above embodiments, in order to obtain the pixel coordinates in the image corresponding to the world coordinates of each reference point to obtain the external parameters of the photographing device, the arrangement of the reference points needs to be preset in the high-precision map, which inevitably increases the amount of data stored in the high-precision map, and further increases the storage space of the high-precision map.
In S504 of the present embodiment, in order to avoid the above problem, the predicted pixel coordinates of each reference point in the image may be acquired according to the initial external reference of the photographing device and the world coordinates of the plurality of reference points in the present embodiment. It should be understood that the initial external reference of the photographing device is used to characterize the initial conversion relationship of the world coordinates and the pixel coordinates, and thus, the predicted pixel coordinates of each reference point in the image can be acquired according to the initial conversion relationship and the world coordinates of the plurality of reference points. It should be understood that the initial parameters may be the same or different for all cameras, and may be predefined.
In the above step S505, since the predicted pixel coordinate of each reference point in the image is estimated and may not be accurate, in this embodiment, the accuracy of the initial external parameter may be determined according to the predicted pixel coordinate of each reference point in the image and the pixel coordinate of each reference point in the image, so as to obtain the external parameter of the photographing device. It should be understood that each reference point has pixel coordinates in the image that are the actual pixel coordinates of the reference point.
It is necessary to acquire actual pixel coordinates, i.e., pixel coordinates, corresponding to the predicted pixel coordinates of each reference point in the image. In this embodiment, a plurality of reference points may be identified in the image, wherein the manner of identifying the reference points may refer to the related description in the above embodiments. Further, whether or not a reference point exists around the predicted pixel coordinate may be searched for in the image, and if a reference point exists, the pixel coordinate of the reference point closest to the predicted pixel coordinate may be set as the pixel coordinate corresponding to the predicted pixel coordinate. Because the predicted pixel coordinates and the pixel coordinates of the plurality of reference points have corresponding arrangement relations, the method has higher accuracy.
In this embodiment, after obtaining the pixel coordinate corresponding to the predicted pixel coordinate of each reference point, in order to determine the accuracy of the initial external parameter, a difference value between the predicted pixel coordinate and the pixel coordinate of each reference point may be obtained; and obtaining the external parameter of the shooting device according to the difference value and the initial external parameter. It should be understood that if the difference is larger, it indicates that the accuracy of the initial external parameters is lower, and if the difference is smaller, it indicates that the accuracy of the initial external parameters is higher.
In this embodiment, a difference threshold is preset to determine the accuracy of the initial external parameter. If the difference value of each reference point is smaller than the difference threshold value, the initial external parameter is indicated to be accurate, and the initial external parameter can be used as the external parameter of the shooting device.
If the difference value of the reference points is larger than the difference threshold value, the initial external parameter is not accurate, and the initial external parameter can be adjusted to obtain a new external parameter, so that the new external parameter is accurate. In this embodiment, the manner of determining whether the new external parameter is accurate is determined by the difference between the predicted pixel coordinate and the pixel coordinate of each reference point.
Therefore, in this embodiment, the new predicted pixel coordinates of each reference point are obtained according to the new external parameters and the world coordinates of each reference point, the new predicted pixel coordinates are used as the predicted pixel coordinates, the new external parameters are used as the initial external parameters, and the step of obtaining the external parameters of the shooting device according to the difference values and the initial external parameters is performed. That is, after obtaining a new predicted pixel coordinate for each reference point, a difference value between the new predicted pixel coordinate for each reference point and the pixel coordinate may be acquired. If the difference value of each reference point is smaller than the difference threshold value, the new external parameter is indicated to be accurate, and the new external parameter can be used as the external parameter of the shooting device. If the difference value of the reference points is larger than the difference threshold value, the new external parameter is indicated to be inaccurate, the new external parameter can be adjusted, and the new external parameter can be obtained again, so that the new external parameter is accurate. Through the continuous repeated iteration, until the difference value of the new predicted pixel coordinate and the pixel coordinate of each reference point obtained through the new external parameter is smaller than the difference threshold value, the new external parameter can be used as the external parameter of the shooting device.
In this embodiment, in order to increase the speed of obtaining the external parameter of the shooting device, a mode of adjusting the external parameter by half may be adopted. It should be understood that the initial external parameters in the present embodiment may include displacement offset and angular offset of the photographing apparatus, which are degrees of freedom of the photographing apparatus. Accordingly, the initial external parameter is adjusted, and the displacement offset and the angle offset of the shooting device can be adjusted for halving.
Fig. 6 is a schematic diagram of the initial external reference of the halving adjustment provided by the present application. Illustratively, if the initial external parameter is (a, B), then the new external parameter may be (a/2, B/2), and the further retrieved new external parameter may be (a/4, B/4) or (3A/2, 3B/2).
Optionally, in this embodiment, the computational complexity may be reduced by using a KDTree method, and the speed of obtaining the external parameters of the photographing apparatus is further increased by using large matrix multiplication instead of multi-layer circulation. It should be understood that in this embodiment, the search speed may be further increased by decomposing the 6-layer loop into a large matrix and adopting a space-to-time method, and the search may be completed by a GPU parallel matrix operation at one time. Specifically, the outer parameter obtained by each 6-layer cycle is changed into a 4 × 4 matrix, the number of times of all 6-layer cycles is changed into the number of channels, namely, an N6 × 4 matrix is obtained, the product of the large matrix and 3d points (namely, world coordinates of each reference point) is directly calculated, namely, all 3d points are projected back to 2d (namely, preset pixel coordinates of each reference point), all reprojection errors can be obtained at one time, further, the optimal outer parameter with the minimum error is obtained, and the optimal outer parameter is used as the outer parameter of the shooting device.
In the embodiment, because the preset range in the high-precision map is the shooting visual field range of the shooting device, the plurality of reference points acquired in the high-precision map are necessarily the reference points in the image shot by the shooting device, and therefore the accuracy of the world coordinates of the reference points acquired in the embodiment is high; in addition, in this embodiment, the initial external parameter may be adopted, the predicted pixel coordinate of each reference point is estimated, and then the accuracy of the initial external parameter is determined according to the predicted pixel coordinate and the pixel coordinate of each reference point, so that the initial external parameter is continuously adjusted in an iterative manner when the initial external parameter is inaccurate until the initial external parameter is accurate. In addition, in the embodiment, a half-fold adjustment mode may be adopted in the initial parameter adjustment mode, so as to improve the speed of obtaining the external parameter of the shooting device.
On the basis of the above-described embodiment, if the initial external parameter of the camera is set without any reference or according to external parameters of other calibrated cameras, it may take a long time in the subsequent adjustment process. Accordingly, in the embodiment, the initial external parameters of the shooting device can be acquired accurately before the shooting device is calibrated. Fig. 7 is a flowchart illustrating another embodiment of a calibration method of a camera according to the present application. As shown in fig. 7, before S501 or before S504, a step of acquiring an initial external reference of the camera may be further included, where in fig. 7, the step of acquiring the initial external reference of the camera is described as before S501, and the step of acquiring the initial external reference of the camera may include:
s506, initial external parameters of the shooting device are determined according to the position and the direction of the shooting device.
It should be understood that the initial external parameters include the displacement offset and the angular offset of the camera, which is essentially 6 degrees of freedom of the camera. In the present embodiment, the world coordinates in which the position of the imaging device corresponds to the high-precision map may be used as the displacement offset, and for example, the world coordinates (X, Y, Z) in which the position of the imaging device corresponds to the high-precision map may be used as the displacement offset.
In this embodiment, the angle offset may be obtained according to the orientation of the photographing device. Wherein the angular offset comprises: pitch angle (roll angle), yaw angle (yaw angle), roll angle (pitch angle). In this embodiment, a corresponding relationship between the orientation of the shooting device and the angle offset may be preset, and the initial external parameters of the shooting device may be determined according to the actual orientation of the shooting device and the corresponding relationship. Specifically, the correspondence between the orientation of the imaging device and the angular offset amount may be as follows:
if the shooting device faces west, taking a yaw angle, a pitch angle after rotating 90 degrees and a rolling angle after rotating-90 degrees in the shooting angle of the shooting device as angle offset; if the shooting device faces south, taking a pitch angle in shooting angles of the shooting device, a yaw angle after rotating by 180 degrees and a roll angle after rotating by 90 degrees as an angle offset; if the shooting device faces east, taking a pitch angle after rotating 90 degrees, a yaw angle after rotating-180 degrees and a roll angle after rotating 90 degrees in the shooting angles of the shooting device as angle offset; if the imaging device faces north, the pitch angle, yaw angle, and roll angle after-90 degrees rotation among the imaging angles of the imaging device are used as the angular offset.
In the embodiment, the initial external parameter of the shooting device can be determined according to the position and the orientation of the shooting device, so that the time for subsequently adjusting the initial external parameter can be shortened, and the calibration speed of the shooting device is further improved.
Fig. 8 is a schematic structural diagram of a calibration apparatus of a shooting apparatus provided in the present application. As shown in fig. 8, the calibration apparatus 800 of the photographing apparatus includes: a first processing module 801 and a second processing module 802.
In this embodiment, a reference object is present in the imaging view range of the imaging device, the reference object is provided with a plurality of reference points, and the reference object is a stationary object in the environment where the imaging device is located.
The first processing module 801 is used for acquiring an image shot by a shooting device, wherein the image comprises a plurality of reference points.
And a second processing module 802, configured to obtain world coordinates of the multiple reference points in the high-precision map according to the position of the shooting device, and obtain external parameters of the shooting device according to pixel coordinates of the multiple reference points in the image and the world coordinates of the multiple reference points.
In a possible implementation manner, the second processing module 802 is specifically configured to obtain predicted pixel coordinates of each reference point in the image according to an initial external parameter of the shooting device and world coordinates of a plurality of reference points; and obtaining the external parameters of the shooting device according to the predicted pixel coordinates of each reference point, the pixel coordinates of each reference point in the image and the initial external parameters.
In a possible implementation manner, the second processing module 802 is specifically configured to obtain, in an image, pixel coordinates corresponding to predicted pixel coordinates of each reference point; acquiring a difference value between a predicted pixel coordinate and a pixel coordinate of each reference point; and obtaining the external parameter of the shooting device according to the difference value and the initial external parameter.
In a possible implementation manner, the second processing module 802 is specifically configured to use the initial external parameter as the external parameter of the capturing device if the difference value of each reference point is smaller than the difference threshold.
In a possible implementation manner, the second processing module 802 is specifically configured to adjust the initial external parameter to obtain a new external parameter if the difference between the reference points is greater than the difference threshold; and acquiring a new predicted pixel coordinate of each reference point according to the new external parameter and the world coordinate of each reference point, taking the new predicted pixel coordinate as a predicted pixel coordinate, taking the new external parameter as an initial external parameter, and executing the step of obtaining the external parameter of the shooting device according to the difference value and the initial external parameter.
In one possible implementation, the initial external parameters include a displacement offset and an angular offset of the camera.
The second processing module 802 is specifically configured to adjust the displacement offset and the angle offset of the shooting device by a factor of two.
In a possible implementation, the second processing module 802 is specifically configured to identify a plurality of fiducial points in the image; the pixel coordinate of the reference point closest to the predicted pixel coordinate is set as the pixel coordinate corresponding to the predicted pixel coordinate.
In a possible implementation manner, the second processing module 802 is specifically configured to obtain, according to a position of the shooting device, world coordinates of the shooting device in a high-precision map; the world coordinates of the reference points of the photographing device within a preset range of the world coordinates in the high-precision map are taken as the world coordinates of the plurality of reference points.
In a possible implementation manner, the second processing module 802 is further configured to determine an initial external parameter of the camera according to the position of the camera and the orientation of the camera.
In one possible implementation, the initial external parameters include a displacement offset and an angular offset of the camera.
The second processing module 802 is specifically configured to use a world coordinate, in which the position of the shooting device corresponds to a high-precision map, as a displacement offset; and acquiring the angle offset according to the orientation of the shooting device.
In one possible implementation, the angular offset includes: pitch angle, yaw angle, roll angle.
The second processing module 802 is specifically configured to, if the shooting device is facing west, take a yaw angle, a pitch angle after rotating by 90 degrees, and a roll angle after rotating by-90 degrees in the shooting angle of the shooting device as an angle offset; if the shooting device faces south, taking a pitch angle in shooting angles of the shooting device, a yaw angle after rotating by 180 degrees and a roll angle after rotating by 90 degrees as an angle offset; if the shooting device faces east, taking a pitch angle after rotating 90 degrees, a yaw angle after rotating-180 degrees and a roll angle after rotating 90 degrees in the shooting angles of the shooting device as angle offset; if the imaging device faces north, the pitch angle, yaw angle, and roll angle after-90 degrees rotation among the imaging angles of the imaging device are used as the angular offset.
In one possible implementation, the reference object is a guardrail on both sides of the road or a lane line in the road, the lane line having an end point, the end point being a reference point.
The calibration device of the shooting device provided in this embodiment is similar to the principle and technical effect achieved by the calibration method of the shooting device, and is not described herein again.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided. Fig. 9 is a schematic structural diagram of an electronic device provided in the present application. As shown in fig. 9, the electronic device is intended to represent various forms of digital computers, processors, chips, and the like. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 9, the electronic apparatus includes: one or more processors 901, memory 902, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including being stored in or on the memory for external input/output means. In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). Fig. 9 illustrates an example of a processor 901.
The memory 902, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the calibration method of the photographing apparatus in the embodiments of the present application. The processor 901 executes various functional applications of the server and data processing by running non-transitory software programs, instructions and modules stored in the memory 902, that is, implements the calibration method of the photographing apparatus in the above method embodiment.
The memory 902 may include a program storage area and a data storage area, and the memory 902 may include a high speed random access memory and may also include a non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 902 may optionally include memory located remotely from the processor 901, which may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the calibration method of the photographing apparatus may further include: a communication device 903. The processor 901, the memory 902 and the communication interface 903 may be connected by a bus or other means, and fig. 9 illustrates the connection by the bus as an example. The communication interface 903 is used for realizing communication with other sensors, processors, or chips integrated in the vehicle, and is used for performing the transceiving operation of the calibration device of the photographing device in the above embodiments.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present application can be achieved, and the present invention is not limited herein.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (15)
1. A calibration method of a shooting device is characterized in that a reference object exists in a shooting visual field range of the shooting device, a plurality of datum points are arranged on the reference object, and the reference object is a static object in the environment where the shooting device is located, and the method comprises the following steps:
acquiring an image shot by the shooting device, wherein the image comprises the plurality of reference points;
acquiring world coordinates of the plurality of reference points in a high-precision map according to the position of the shooting device;
and obtaining the external parameters of the shooting device according to the pixel coordinates of the plurality of reference points and the world coordinates of the plurality of reference points in the image.
2. The method of claim 1, wherein the deriving the external parameters of the camera from pixel coordinates of the plurality of reference points and world coordinates of the plurality of reference points in the image comprises:
acquiring the predicted pixel coordinates of each reference point in the image according to the initial external parameters of the shooting device and the world coordinates of the plurality of reference points;
and obtaining the external parameters of the shooting device according to the predicted pixel coordinates of each reference point, the pixel coordinates of each reference point in the image and the initial external parameters.
3. The method of claim 2, wherein the deriving the external parameters of the camera from the predicted pixel coordinates of each reference point, the pixel coordinates of each reference point in the image, and the initial external parameters comprises:
acquiring pixel coordinates corresponding to the predicted pixel coordinates of each reference point in the image;
acquiring a difference value between the predicted pixel coordinate and the pixel coordinate of each reference point;
and obtaining the external parameters of the shooting device according to the difference and the initial external parameters.
4. The method of claim 3, wherein obtaining the external parameters of the camera according to the difference and the initial external parameters comprises:
and if the difference value of each reference point is smaller than the difference threshold value, taking the initial external parameter as the external parameter of the shooting device.
5. The method of claim 3, wherein obtaining the external parameters of the camera according to the difference and the initial external parameters comprises:
if the difference value of the reference points is larger than the difference threshold value, adjusting the initial external parameters to obtain new external parameters;
and acquiring a new predicted pixel coordinate of each reference point according to the new external parameter and the world coordinate of each reference point, taking the new predicted pixel coordinate as the predicted pixel coordinate, taking the new external parameter as the initial external parameter, and executing the step of acquiring the external parameter of the shooting device according to the difference value and the initial external parameter.
6. The method of claim 5, wherein the initial external parameters include a displacement offset and an angular offset of the camera, and wherein the adjusting the initial external parameters includes:
and adjusting the displacement offset and the angle offset of the shooting device in a halving way.
7. The method according to any one of claims 3-6, wherein said obtaining pixel coordinates in said image corresponding to predicted pixel coordinates of said each reference point comprises:
identifying the plurality of fiducial points in the image;
the pixel coordinates of the reference point closest to the predicted pixel coordinates are set as the pixel coordinates corresponding to the predicted pixel coordinates.
8. The method according to any one of claims 1-7, wherein the obtaining world coordinates of the plurality of reference points in a high-precision map according to the position of the camera comprises:
according to the position of the shooting device, acquiring world coordinates of the shooting device in the high-precision map;
and taking the world coordinates of the reference points of the shooting device within a preset range of the world coordinates in the high-precision map as the world coordinates of the plurality of reference points.
9. The method according to any one of claims 1-8, further comprising:
and determining initial external parameters of the shooting device according to the position of the shooting device and the orientation of the shooting device.
10. The method of claim 9, wherein the initial external parameters include a displacement offset and an angular offset of the camera, and wherein determining the initial external parameters of the camera based on the position of the camera and the orientation of the camera comprises:
taking the world coordinate of the position of the shooting device corresponding to a high-precision map as the displacement offset;
and acquiring the angle offset according to the orientation of the shooting device.
11. The method of claim 10, wherein the angular offset comprises: pitch angle, yaw angle, roll angle, according to shooting device's orientation obtains angle offset includes:
if the shooting device faces west, taking a yaw angle, a pitch angle after rotating 90 degrees and a rolling angle after rotating-90 degrees in shooting angles of the shooting device as the angle offset;
if the shooting device faces south, taking a pitch angle in shooting angles of the shooting device, a yaw angle after rotating by 180 degrees and a rolling angle after rotating by 90 degrees as the angle offset;
if the shooting device faces east, taking a pitch angle after rotating by 90 degrees, a yaw angle after rotating by-180 degrees and a roll angle after rotating by 90 degrees in shooting angles of the shooting device as the angle offset;
and if the shooting device faces north, taking a pitch angle, a yaw angle and a rolling angle after rotating by-90 degrees in the shooting angle of the shooting device as the angle offset.
12. The method according to any one of claims 1-11, wherein the reference object is a guardrail on both sides of a roadway or a lane line in the roadway, the lane line having end points, the end points being reference points.
13. A calibration device of a shooting device is characterized by comprising:
the first processing module is used for acquiring an image shot by a shooting device, wherein the image comprises a plurality of datum points;
and the second processing module is used for acquiring the world coordinates of the plurality of reference points in a high-precision map according to the position of the shooting device and obtaining the external parameters of the shooting device according to the pixel coordinates of the plurality of reference points in the image and the world coordinates of the plurality of reference points.
14. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-12.
15. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010431655.XA CN111553956A (en) | 2020-05-20 | 2020-05-20 | Calibration method and device of shooting device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010431655.XA CN111553956A (en) | 2020-05-20 | 2020-05-20 | Calibration method and device of shooting device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111553956A true CN111553956A (en) | 2020-08-18 |
Family
ID=72008373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010431655.XA Pending CN111553956A (en) | 2020-05-20 | 2020-05-20 | Calibration method and device of shooting device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111553956A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102417A (en) * | 2020-09-15 | 2020-12-18 | 北京百度网讯科技有限公司 | Method and device for determining world coordinates and external reference calibration method for vehicle-road cooperative roadside camera |
| CN112767498A (en) * | 2021-02-03 | 2021-05-07 | 苏州挚途科技有限公司 | Camera calibration method and device and electronic equipment |
| CN113587924A (en) * | 2021-06-16 | 2021-11-02 | 影石创新科技股份有限公司 | Shooting system calibration method and device, computer equipment and storage medium |
| CN113658268A (en) * | 2021-08-04 | 2021-11-16 | 智道网联科技(北京)有限公司 | Method and device for verifying camera calibration result, electronic equipment and storage medium |
| CN114900609A (en) * | 2022-04-29 | 2022-08-12 | 北京数字绿土科技股份有限公司 | Automatic shooting control method and system for unmanned aerial vehicle |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009110417A1 (en) * | 2008-03-03 | 2009-09-11 | ティーオーエー株式会社 | Device and method for specifying installment condition of rotatable camera and camera control system equipped with the installment condition specifying device |
| DE102011100628A1 (en) * | 2011-05-05 | 2012-11-08 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Method for determining parameter of camera i.e. mobile traffic monitoring camera, involves determining camera parameter based on image coordinates of structure, absolute Cartesian coordinates of structure and programmable mapping function |
| CN107133988A (en) * | 2017-06-06 | 2017-09-05 | 科大讯飞股份有限公司 | The scaling method and calibration system of camera in vehicle-mounted panoramic viewing system |
| CN110148185A (en) * | 2019-05-22 | 2019-08-20 | 北京百度网讯科技有限公司 | Determine method, apparatus, electronic equipment and the storage medium of coordinate system conversion parameter |
| CN110517325A (en) * | 2019-08-29 | 2019-11-29 | 的卢技术有限公司 | The vehicle body surrounding objects localization method and system of a kind of coordinate transform and coordinate transform |
-
2020
- 2020-05-20 CN CN202010431655.XA patent/CN111553956A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009110417A1 (en) * | 2008-03-03 | 2009-09-11 | ティーオーエー株式会社 | Device and method for specifying installment condition of rotatable camera and camera control system equipped with the installment condition specifying device |
| DE102011100628A1 (en) * | 2011-05-05 | 2012-11-08 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Method for determining parameter of camera i.e. mobile traffic monitoring camera, involves determining camera parameter based on image coordinates of structure, absolute Cartesian coordinates of structure and programmable mapping function |
| CN107133988A (en) * | 2017-06-06 | 2017-09-05 | 科大讯飞股份有限公司 | The scaling method and calibration system of camera in vehicle-mounted panoramic viewing system |
| CN110148185A (en) * | 2019-05-22 | 2019-08-20 | 北京百度网讯科技有限公司 | Determine method, apparatus, electronic equipment and the storage medium of coordinate system conversion parameter |
| CN110517325A (en) * | 2019-08-29 | 2019-11-29 | 的卢技术有限公司 | The vehicle body surrounding objects localization method and system of a kind of coordinate transform and coordinate transform |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102417A (en) * | 2020-09-15 | 2020-12-18 | 北京百度网讯科技有限公司 | Method and device for determining world coordinates and external reference calibration method for vehicle-road cooperative roadside camera |
| CN112102417B (en) * | 2020-09-15 | 2024-04-19 | 阿波罗智联(北京)科技有限公司 | Method and device for determining world coordinates |
| CN112767498A (en) * | 2021-02-03 | 2021-05-07 | 苏州挚途科技有限公司 | Camera calibration method and device and electronic equipment |
| CN113587924A (en) * | 2021-06-16 | 2021-11-02 | 影石创新科技股份有限公司 | Shooting system calibration method and device, computer equipment and storage medium |
| CN113587924B (en) * | 2021-06-16 | 2024-03-29 | 影石创新科技股份有限公司 | Shooting system calibration method, shooting system calibration device, computer equipment and storage medium |
| CN113658268A (en) * | 2021-08-04 | 2021-11-16 | 智道网联科技(北京)有限公司 | Method and device for verifying camera calibration result, electronic equipment and storage medium |
| CN114900609A (en) * | 2022-04-29 | 2022-08-12 | 北京数字绿土科技股份有限公司 | Automatic shooting control method and system for unmanned aerial vehicle |
| CN114900609B (en) * | 2022-04-29 | 2023-03-24 | 北京数字绿土科技股份有限公司 | Automatic shooting control method and system for unmanned aerial vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111553956A (en) | Calibration method and device of shooting device, electronic equipment and storage medium | |
| JP6844043B2 (en) | Visual positioning methods, devices, electronics and systems | |
| AU2018282302B2 (en) | Integrated sensor calibration in natural scenes | |
| CN109523471B (en) | Method, system and device for converting ground coordinates and wide-angle camera picture coordinates | |
| CN105608693A (en) | Vehicle-mounted panoramic around view calibration system and method | |
| EP3771198A1 (en) | Target tracking method and device, movable platform and storage medium | |
| CN112798811B (en) | Speed measurement method, device and equipment | |
| CN110969663A (en) | Static calibration method for external parameters of camera | |
| CN111368615B (en) | Illegal building early warning method and device and electronic equipment | |
| CN115797454B (en) | Multi-camera fusion sensing method and device under bird's eye view angle | |
| CN115376109B (en) | Obstacle detection method, obstacle detection device, and storage medium | |
| US11069071B1 (en) | System and method for egomotion estimation | |
| CN109754034A (en) | A kind of terminal device localization method and device based on two dimensional code | |
| CN110969048A (en) | Target tracking method and device, electronic equipment and target tracking system | |
| JP2017181476A (en) | Vehicle location detection device, vehicle location detection method and vehicle location detection-purpose computer program | |
| CN110736472A (en) | indoor high-precision map representation method based on fusion of vehicle-mounted all-around images and millimeter wave radar | |
| CN114782548B (en) | Global image-based radar data calibration method, device, equipment and medium | |
| US20230177724A1 (en) | Vehicle to infrastructure extrinsic calibration system and method | |
| CN115962757A (en) | Unmanned aerial vehicle surveying and mapping method, system and readable storage medium | |
| CN113804100A (en) | Method, device, equipment and storage medium for determining space coordinates of target object | |
| CN114979956A (en) | Unmanned aerial vehicle aerial photography ground target positioning method and system | |
| CN113012215A (en) | Method, system and equipment for space positioning | |
| CN112001357B (en) | Target identification detection method and system | |
| CN117372516A (en) | Ultra-wide river channel surface flow velocity acquisition method, device, equipment and storage medium | |
| CN116977806A (en) | Airport target detection method and system based on millimeter wave radar, laser radar and high-definition array camera |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211028 Address after: 100176 101, floor 1, building 1, yard 7, Ruihe West 2nd Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Applicant after: Apollo Zhilian (Beijing) Technology Co.,Ltd. Address before: 2 / F, baidu building, 10 Shangdi 10th Street, Haidian District, Beijing 100085 Applicant before: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. |
|
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200818 |