CN110738183A - Obstacle detection method and device - Google Patents
Obstacle detection method and device Download PDFInfo
- Publication number
- CN110738183A CN110738183A CN201911002600.0A CN201911002600A CN110738183A CN 110738183 A CN110738183 A CN 110738183A CN 201911002600 A CN201911002600 A CN 201911002600A CN 110738183 A CN110738183 A CN 110738183A
- Authority
- CN
- China
- Prior art keywords
- reference point
- ground equation
- obstacle
- determining
- ground
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Abstract
The specific implementation scheme is that the electronic equipment returns the obstacle in the 2d image to the world coordinate system through a global offline ground equation, namely a ground equation, finds a segmented ground equation according to the position of the obstacle in the world coordinate system, namely a second ground equation, then determines a third ground equation according to the second ground equation and implementation parameters of roadside equipment, finally updates the position of the obstacle in the world coordinate system by using the third ground equation, and the updated position is the accurate position of the obstacle in the world coordinate system.
Description
Technical Field
The embodiment of the application relates to the technical field of computer vision, in particular to obstacle detection methods and devices, which can be used for automatic driving.
Background
At present, in the fields of robot navigation, automatic driving and the like, how to effectively detect obstacles on a traveling road surface is a key problem to be solved.
In a commonly used obstacle detection process, a camera is used to capture a two-dimensional (2 d) image containing an obstacle, and a real position of the obstacle in the 2d image in a three-dimensional (3 d) world is calculated, where the real position may also be referred to as a position of the obstacle in a world coordinate system. In the calculation process, a ground equation of the obstacle in a camera coordinate system is needed, and the more accurate the ground equation is, the more accurate the finally determined position of the obstacle in a world coordinate system is. The process of determining the position of the obstacle in the world coordinate system using the two-dimensional image is also referred to as a 3 d-back process. In general, when determining the position of the world coordinate system of the obstacle, a global offline ground equation is used, that is, a ground equation is determined offline in advance, and in the subsequent obstacle detection process, the ground equation is used for detecting the obstacle in real time.
However, due to the high installation position of the camera, the camera may shake in real time to change the external parameters of the camera, and the ground equation in the coordinate system of the camera may also change. Obviously, if the above global offline ground equation is used, the position of the obstacle in the world coordinate system cannot be accurately determined, that is, the obstacle cannot be accurately detected.
Disclosure of Invention
The embodiment of the application provides obstacle detection methods and devices, and the traditional ground equation using global offline is replaced by a segmented ground equation, so that the obstacle detection accuracy is improved.
, the embodiment of the application provides obstacle detection methods, which include receiving a request command, determining a position of an obstacle in a world coordinate system according to the request command and a prestored ground equation, determining a second ground equation corresponding to the position from a ground equation set corresponding to the two-dimensional image according to the position of the obstacle in the world coordinate system, wherein the ground equation set comprises at least ground equations, and updating the position of the obstacle in the world coordinate system according to the second ground equation.
, the updating the position of the obstacle in the world coordinate system according to the second ground equation includes determining a third ground equation according to the second ground equation and parameters of roadside equipment, the roadside equipment being a device for capturing the two-dimensional image, and updating the position of the obstacle in the world coordinate system according to the third ground equation.
, before determining the second ground equation corresponding to the position from the ground equation set corresponding to the two-dimensional image according to the position of the obstacle in the world coordinate system, projecting the two-dimensional image to a high-precision map to determine a plurality of reference points from the high-precision map, and determining the ground equation set according to the plurality of reference points.
, determining the set of ground equations from the plurality of reference points includes determining th and second reference points from the plurality of reference points, the abscissa of the th reference point being the largest of the plurality of reference points, the abscissa of the second reference point being the smallest of the plurality of reference points, determining the number of segments of the abscissa from the th and second reference points, determining a third and fourth reference points from the plurality of reference points, the ordinate of the third reference point being the largest of the plurality of reference points, the ordinate of the fourth reference point being the largest of the plurality of reference points, determining the number of segments of the ordinate from the third and fourth reference points, determining the total number of segments from the number of segments of the abscissa and the number of segments of the ordinate, determining the set of ground equations from the total number of segments and the plurality of reference points, determining the set of ground equations from the real-time camera coordinates and the plurality of reference points, and determining the set of ground equation for improving the detection of obstacles in the world.
possible designs include that for each reference points in the plurality of reference points, a segmented tag corresponding to the reference point is determined according to the abscissa and the ordinate of the reference point, so as to determine a segmented tag corresponding to each reference point in the plurality of reference points, and whether the number of reference points corresponding to a target segmented tag exceeds a preset threshold is determined, where the target segmented tag is a segmented tag corresponding to any reference point in the plurality of reference points, and if the number of reference points corresponding to the target segmented tag exceeds the preset threshold, a ground equation corresponding to the target segmented tag is determined, so as to obtain the ground equation set.
, before determining the third ground equation according to the second ground equation and the parameters of the roadside equipment, determining the parameters of the roadside equipment according to the jitter condition of the roadside equipment, determining the parameters of the roadside camera in real time by adopting the scheme, and determining the position of the obstacle in a world coordinate system by combining the real-time parameters of the camera and the segmented ground equation in the ground equation set, thereby realizing the improvement of the obstacle detection accuracy.
, the method further comprises controlling the vehicle to automatically drive according to the updated position after updating the position of the obstacle in the world coordinate system according to the second ground equation, so as to control the automatic drive vehicle to automatically drive according to the updated position, thereby accurately avoiding obstacles and improving safety of automatic drive,
in a second aspect, an embodiment of the present application provides kinds of obstacle detection devices, including:
the device comprises a receiving module, a judging module and a judging module, wherein the receiving module is used for receiving a request instruction which is used for requesting to detect an obstacle in a two-dimensional image;
an determining module, configured to determine, according to the request instruction and a pre-stored th ground equation, a position of the obstacle in a world coordinate system;
the second determination module is used for determining a second ground equation corresponding to the position from a ground equation set corresponding to the two-dimensional image according to the position of the obstacle in a world coordinate system, wherein the ground equation set comprises at least ground equations;
and the updating module is used for updating the position of the barrier in the world coordinate system according to the second ground equation.
, the updating module is configured to determine a third ground equation according to the second ground equation and parameters of a roadside device, where the roadside device is a device that captures the two-dimensional image and updates the position of the obstacle in the world coordinate system according to the third ground equation.
, the apparatus further includes a third determining module configured to project the two-dimensional image to a high-precision map to determine a plurality of reference points from the high-precision map before the second determining module determines the second ground equation corresponding to the position from the set of ground equations corresponding to the two-dimensional image according to the position of the obstacle in the world coordinate system, and determine the set of ground equations according to the plurality of reference points.
, the third determining module is configured to determine a th reference point and a second reference point from the plurality of reference points, the abscissa of the th reference point is the largest reference point of the plurality of reference points, the abscissa of the second reference point is the smallest reference point of the plurality of reference points, the number of segments of the abscissa is determined according to the th reference point and the second reference point, the third reference point and the fourth reference point are determined from the plurality of reference points, the ordinate of the third reference point is the largest reference point of the ordinate of the plurality of reference points, the ordinate of the fourth reference point is the largest reference point of the ordinate of the plurality of reference points, the number of segments of the vertical axis is determined according to the third reference point and the fourth reference point, the total number of segments is determined according to the number of segments of the horizontal axis and the number of segments of the vertical axis, and the ground equation set is determined according to the total number of segments and the plurality of reference points.
, in each of the multiple reference points, the third determining module is configured to determine, for each reference points in the multiple reference points, a segment label corresponding to the reference point according to an abscissa and an ordinate of the reference point, thereby determining a segment label corresponding to each of the multiple reference points, and determining whether the number of reference points corresponding to a target segment label exceeds a preset threshold, where the target segment label is a segment label corresponding to any reference points in the multiple reference points, and if the number of reference points corresponding to the target segment label exceeds the preset threshold, determining a ground equation corresponding to the target segment label, thereby obtaining the ground equation set.
, the apparatus further includes a fourth determining module, configured to determine the parameter of the roadside device according to the jitter condition of the roadside device before the updating module updates the position of the obstacle in the world coordinate system according to the second ground equation.
, the apparatus further includes a control module for controlling the vehicle to perform automatic driving according to the updated position after the update module updates the position of the obstacle in the world coordinate system according to the second ground equation.
In a third aspect, an embodiment of the present application provides electronic devices, including:
at least processors, and
a memory communicatively coupled to the at least processors, wherein,
the memory stores instructions executable by the at least processors to enable the at least processors to perform the method of any possible implementation of aspect or aspect .
In a fourth aspect, embodiments of the present application provide computer program products containing instructions that, when run on an electronic device, cause the electronic device computer to perform the methods in the various possible implementations of aspect or aspect .
In a fifth aspect, embodiments of the present application provide storage media having instructions stored therein, which when run on an electronic device, cause the electronic device to perform the methods in the various possible implementations as described above in aspects or .
In a sixth aspect, the obstacle detection method provided by the embodiment of the application comprises the steps of determining the position of an obstacle in a two-dimensional image in a world coordinate system according to a pre-stored ground equation, determining a second ground equation from a ground equation set according to the position, wherein the ground equation set comprises at least ground equations, determining a third ground equation according to the second ground equation and parameters of roadside equipment, wherein the roadside equipment is a device for capturing the two-dimensional image, and updating the position of the obstacle in the world coordinate system according to the third ground equation.
The embodiments in the above application have the following advantages or beneficial effects that the electronic device returns the obstacle in the 2d image to the world coordinate system through a global offline ground equation, namely the ground equation, finds a segmented ground equation, namely the second ground equation, according to the position of the obstacle in the world coordinate system, then determines the third ground equation according to the second ground equation and the implementation parameters of the roadside device, and finally updates the position of the obstacle in the world coordinate system by using the third ground equation, wherein the updated position is the accurate position of the obstacle in the world coordinate system.
Other effects of the above-described alternative will be described below with reference to specific embodiments.
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 schematic operating environment diagram of an obstacle detection method according to an embodiment of the present application;
fig. 2 is a flowchart of an obstacle detection method provided in an embodiment of the present application;
FIG. 3 is a schematic diagram of the relationship of a camera coordinate system and a pixel coordinate system;
FIG. 4 is a schematic diagram of the relationship of a camera coordinate system and a world coordinate system;
fig. 5 is a schematic 2d image in obstacle detection methods provided in the embodiments of the present application;
fig. 6 is a flowchart of another obstacle detection methods provided by embodiments of the present application;
fig. 7 is a schematic structural diagram of an obstacle detection device according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of another kinds of obstacle detection devices provided in the embodiment of the present application;
fig. 9 is a block diagram of an electronic device for implementing the obstacle detection method according to the embodiment of 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.
, the traditional road side camera can only acquire 2d images but cannot acquire depth images, because the 2d images lack depth information, when calculating the real position of the obstacle in the 2d images in the 3d world, a ground equation of the position of the obstacle is needed, the ground equation is also called as a ground normal vector, the more accurate the ground equation is, the more accurate the position of the obstacle in the 3d world is determined by the ground equation, the position of the obstacle in the 3d world is also called as the position of the obstacle in a world coordinate system, and the process of determining the position of the obstacle in the world coordinate system is called as a 3d return process.
In general, when determining the position of an obstacle in a world coordinate system, a global offline ground equation is used, that is, a ground equation is determined offline in advance, and the ground equation is used for detecting the obstacle in real time in the subsequent obstacle detection process. The method has larger error, and especially when uneven road surfaces exist in the visual field of the road side camera, the inaccurate ground equation can influence the 3d return effect.
In view of the great influence of the accuracy of the ground equation on 3d, methods are available for accurately calculating the position of the obstacle in the world coordinate system, and the ground equation is replaced by an offline-constructed depth map, which is used for calculating the world coordinate of each pixels in the 2d image offline by accurately obtaining depth information.
According to the above, it can be seen that: when the road side camera shakes, the position of the obstacle in a world coordinate system cannot be determined in real time due to the fact that the depth map cannot be obtained in real time in a mode that an offline constructed depth map is used for replacing a ground equation; and a global off-line ground equation is used, so that the error is large and the 3d effect is seriously influenced.
In view of this, the embodiment of the present application provides obstacle detection methods and apparatuses, which detect an obstacle by determining a ground equation in a segmented manner, so as to improve the accuracy of obstacle detection.
Fig. 1 is a schematic operating environment diagram of an obstacle detection method according to an embodiment of the present application. Referring to fig. 1, the roadside camera 110 captures an object in a field of view to obtain a 2d image, and transmits the 2d image to the electronic device 120, the electronic device stores a high-precision map in advance, and the electronic device 120 detects an obstacle according to the high-precision map and the 2d image. Objects included in the 2d image acquired by the roadside camera 110 include a vehicle 111, a vehicle 112, trees 113, a building 114, and the like.
In fig. 1, the electronic device 120 may be any device with computing capability, such as a distributed computing device, mainframe, server, personal computer, tablet computer, in-vehicle terminal, smart phone, and the like. The electronic device 120 and the roadside camera 110 may be integrally provided or may be independently provided; alternatively, the electronic device 120 may be provided on the vehicle 111 or the vehicle 112 for self-service driving, assisted driving, or the like.
Next, the obstacle detection method according to the embodiment of the present application will be described in detail by taking an example in which the electronic device 120 is integrated with the vehicle 111 in addition to fig. 1.
Fig. 2 is a flowchart of an obstacle detection method according to an embodiment of the present application. The embodiment comprises the following steps:
201. and receiving a request instruction, wherein the request instruction is used for requesting to detect the obstacle in the two-dimensional image.
For example, the electronic device 120 is integrated with the vehicle 111, and means that the vehicle-mounted terminal of the vehicle 111 has the function of detecting the obstacle according to the embodiment of the present application. The electronic device 120 receives the 2d image acquired by the roadside camera 110 in real time. When the obstacle detection is needed, a user inputs a request instruction to the electronic equipment through a click operation mode, a touch operation mode, a voice input mode or the like, and the electronic equipment receives and identifies the request instruction.
202. And determining the position of the obstacle in a world coordinate system according to the request instruction and a prestored th ground equation.
Illustratively, the -th ground equation is, for example, a predetermined global offline ground equation, i.e., for any obstacles in the 2d image, the same ground equations are used to determine the position of each obstacle.
This step can also be understood as the process of returning the 2d obstacle to the world coordinate system by an offline ground equation.
203. And according to the position of the obstacle in a world coordinate system, determining a second ground equation corresponding to the position from a ground equation set corresponding to the two-dimensional image, wherein the ground equation set comprises at least ground equations.
For example, in the embodiment of the present application, for each 2d image, the electronic device determines a plurality of ground equations by using the high-precision map and the 2d image to obtain a ground equation set, where the ground equations in the ground equation set are also referred to as segmented ground equations. For each obstacle, after determining the position of each obstacle, the electronic device determines a second ground equation from the set of ground equations according to the position.
204. And updating the position of the obstacle in the world coordinate system according to the second ground equation.
For example, after the electronic device determines the second ground equation, the position of the obstacle in the world coordinate system is updated according to the second ground equation, so that the accurate position of the obstacle is obtained. Then, the vehicle is controlled to perform automatic driving, obstacle avoidance, and the like based on the accurate position.
According to the obstacle detection method provided by the embodiment of the application, the obstacle in the 2d image is returned to the world coordinate system through the global offline ground equation, namely the th ground equation, the segmented ground equation, namely the second ground equation, is found according to the position of the obstacle in the world coordinate system, and then the position of the obstacle in the world coordinate system is updated according to the second ground equation.
In the following, how the electronic device updates the position of the obstacle in the world coordinate system according to the second ground equation in the above embodiment is described in detail.
, when the electronic device updates the position of the obstacle in the world coordinate system according to the second ground equation, determining a third ground equation according to the second ground equation and parameters of a roadside device, which is a device for capturing the two-dimensional image, and then updating the position of the obstacle in the world coordinate system according to the third ground equation.
For example, because the installation position of the roadside camera is high, the roadside camera shakes in real time to cause the external parameters of the roadside camera to change, and the ground equation is in the camera coordinate system, in this step, the third ground equation can be accurately determined according to the real-time parameters of the roadside camera and the second ground equation. The roadside device, for example, a roadside camera or the like, is a device for capturing a two-dimensional image, and may acquire a two-dimensional color image, but the embodiment of the present application does not limit whether it may acquire a depth image. And then, the electronic equipment can determine the position of the obstacle in the 2d image in the world coordinate system according to the accurate third ground equation.
According to the obstacle detection method provided by the embodiment of the application, the obstacle in the 2d image is returned to the world coordinate system through a global offline ground equation, namely an th ground equation, a segmented ground equation, namely a second ground equation, is found according to the position of the obstacle in the world coordinate system, a third ground equation is determined according to the second ground equation and implementation parameters of roadside equipment, finally the position of the obstacle in the world coordinate system is updated through the third ground equation, and the updated position is the accurate position of the obstacle in the world coordinate system.
Next, the camera coordinate system and the world coordinate system in the above embodiment will be described in detail.
For example, see fig. 3 and 4. Fig. 3 is a schematic diagram of the relationship between the camera coordinate system and the pixel coordinate system. Referring to fig. 3, a standard image coordinate system o1-xy is set, a rectangular coordinate system o-uv with pixels as units, which is established with the upper left corner of the depth image as the origin, is called a pixel coordinate system, and the abscissa u and the ordinate v of the pixel are the number of columns and the number of rows in the image array, respectively. Image coordinate system o1The origin o of xy1Defined as the intersection of the camera's optical axis and the depth image plane, with the x-axis parallel to the u-axis and the y-axis parallel to the v-axis. The camera coordinate system Oc-XcYcZc has the camera optical center Oc as the origin of coordinates, the Xc axis and the Yc axis are parallel to the x axis and the y axis of the image coordinate system, respectively, the Zc axis is the optical axis of the camera, and the image plane is perpendicular to and intersects at point o 1.
Fig. 4 is a schematic diagram of the relationship between the camera coordinate system and the world coordinate system. Referring to fig. 4, the origin Ow of the world coordinate system Ow-XwYwZw coincides with the origin Oc of the camera coordinate system, which are all camera optical centers, and the horizontal right direction is selected as the positive direction of Xw axis, the vertical downward direction is the positive direction of Yw axis, and the vertical Xw Yw plane points to the positive front direction and is the positive direction of Zw axis, so as to establish the world coordinate system.
For example, refer to fig. 5 and fig. 6, fig. 5 is a schematic view of 2d images in obstacle detection methods provided by the embodiment of the present application, and fig. 6 is a flowchart of another obstacle detection methods provided by the embodiment of the present application, where the embodiment of the present application includes:
301. and projecting the two-dimensional image to a high-precision map so as to determine a plurality of reference points from the high-precision map.
Referring to fig. 5, the content included in fig. 5 may be regarded as an image captured by the roadside camera, black dots in fig. 5 are 3D dots in the high-precision map, which are also referred to as reference points, after the roadside camera captures a 2D image, the 2D image is sent to the electronic device, and the electronic device projects the 2D image onto the high-precision map, since series of reference points are located on the high-precision map, after the 2D image is projected onto the high-precision map, the reference points on the 2D image in the field of view of the roadside camera may be obtained, for example, the 2D image is images of 1920 × 1920.
Thereafter, the electronic device determines a set of ground equations according to the plurality of reference points, and the detailed process is please refer to step 302.
302. An th reference point and a second reference point are determined from the plurality of reference points.
Wherein an abscissa of the th reference point is a reference point having a maximum abscissa among the plurality of reference points, an abscissa of the second reference point is a reference point having a minimum abscissa among the plurality of reference points, and the number of segments of the abscissa is determined according to the th reference point and the second reference point.
Illustratively, the electronic device traverses all the reference points obtained in step 301, finds the reference point with the largest abscissa (i.e., Xw) and the reference point with the smallest abscissa (i.e., Xw), and uses the reference point with the largest abscissa (i.e., Xw) as the -th reference point and the reference point with the smallest abscissa (i.e., Xw) as the second reference point.
303. Determining the number of segments of the horizontal axis based on the th reference point and the second reference point.
Illustratively, the electronic device subtracts the abscissa of the second reference point from the abscissa of the reference point to obtain a -th difference, and divides the difference by the segment interval and rounds up, which is denoted as Xw _.
304. A third reference point and a fourth reference point are determined from the plurality of reference points.
The ordinate of the third reference point is the reference point with the largest ordinate among the plurality of reference points, and the ordinate of the fourth reference point is the reference point with the largest ordinate among the plurality of reference points.
For example, the electronic device traverses all the reference points obtained in step 301, finds a reference point with the largest ordinate (i.e., Yw) and a reference point with the smallest ordinate (i.e., Yw) among the reference points, and uses the reference point with the largest ordinate (i.e., Yw) as the third reference point and the reference point with the smallest ordinate (i.e., Yw) as the fourth reference point.
305. And determining the number of the segments of the longitudinal axis according to the third reference point and the fourth reference point.
Illustratively, the electronic device subtracts the ordinate of the fourth reference point from the ordinate of the third reference point to obtain a second difference, and divides the second difference by the segmentation interval and rounds up to obtain Yw _. The segmentation interval can be preset according to requirements, and can be 10 meters and the like.
306. And determining the total number of the segments according to the number of the segments on the horizontal axis and the number of the segments on the vertical axis.
Illustratively, the electronic device performs an integration of Xw _ and Yw _ to obtain a total number of segments, which is denoted as NUM, and then NUM ═ Xw _ × Yw _. The electronic device then determines the set of ground equations based on the total number of segments and the plurality of reference points, and the detailed process may be referred to as described in step 307 below.
307. For each reference points in the plurality of reference points, determining the segment label corresponding to the reference point according to the abscissa and the ordinate of the reference point, thereby determining the segment label corresponding to each reference point in the plurality of reference points.
For example, in the step 301, the electronic device traverses all the reference points obtained in the step 301, and marks segmented labels on each reference points in the labeling process, for any reference points in the reference points, the electronic device uses the abscissa of the reference point to subtract the abscissa of the second reference point to obtain differences, divides the differences by the segmentation interval and rounds up to obtain Xw _ ', and similarly, the electronic device uses the ordinate of the reference point to subtract the ordinate of the fourth reference point to obtain differences, divides the differences by the segmentation interval and rounds up to obtain Yw _', and then determines NUM _ ', NUM _ × Yw _', which is obviously, NUM _ ≦ NUM _.
308. Determining whether the number of reference points corresponding to the target segmented tag exceeds a preset threshold, and if so, executing step 309; if the threshold is not exceeded, step 310 is performed.
Wherein the target segment label is a segment label corresponding to any reference points in the plurality of reference points.
Illustratively, parts of the reference points correspond to the same segment tags, and for any segment tags, the electronic device determines whether the number of the reference points corresponding to the segment tags exceeds a preset threshold, if so, step 309 is executed, and if not, step 310 is executed.
309. And determining a ground equation corresponding to the target segmented tag, thereby obtaining a ground equation set, and then executing step 311.
310. The global offline ground equation is used as the ground equation of the target segment label, and then step 311 is executed.
The global offline ground equation is the -th ground equation in step 202 of fig. 2.
311. Obstacle detection is performed according to the 2d image, the high-precision map, and the ground equation set.
For example, for any obstacles on the 2d image, the electronic device determines the position of the obstacle in the world coordinate system through an offline ground equation, namely the ground equation, then calculates the segmentation label corresponding to the obstacle according to the position, and determines a second ground equation from the ground equation set, wherein the second ground equation is also called the segmentation ground equation in the offline world coordinate system, then the electronic device multiplies the external reference of the road side device calibrated online by the offline second ground equation to obtain a third ground equation, and finally the electronic device updates the position of the obstacle in the world coordinate system according to the third ground equation.
In the above fig. 6, the steps 301 to 310 may be regarded as offline parts, and the step 311 is an online part, since the online part in the embodiment of the present application has only steps, that is, a segmented ground equation under an offline world coordinate system is found according to a segmented tag, and the time complexity is low, the method for detecting an obstacle in the embodiment of the present application has a high speed.
In the above embodiment, the electronic device further controls the vehicle to perform automatic driving according to the updated position after updating the position of the obstacle in the world coordinate system according to the second ground equation, so , the accuracy and safety of automatic driving can be improved.
In the above description, a specific implementation of the obstacle detection method mentioned in the embodiments of the present application is described, and the following is an embodiment of the apparatus of the present application, which can be used to implement the embodiments of the method of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the embodiments of the method of the present application.
Fig. 7 is a schematic structural diagram of an obstacle detection device according to an embodiment of the present application. The device can be integrated in or realized by electronic equipment, and the electronic equipment can be terminal equipment or a server and the like. As shown in fig. 7, in the present embodiment, the obstacle detection apparatus 400 may include:
a receiving module 41, configured to receive a request instruction, where the request instruction is used to request detection of an obstacle in a two-dimensional image;
the determining module 42 is used for determining the position of the obstacle in a world coordinate system according to the request instruction and a pre-stored ground equation;
a second determining module 43, configured to determine, according to the position of the obstacle in the world coordinate system, a second ground equation corresponding to the position from a ground equation set corresponding to the two-dimensional image, where the ground equation set includes at least ground equations;
and the updating module 44 is configured to update the position of the obstacle in the world coordinate system according to the second ground equation.
, the updating module 44 is configured to determine a third ground equation according to the second ground equation and parameters of a roadside apparatus, which is a device capturing the two-dimensional image, and update the position of the obstacle in the world coordinate system according to the third ground equation.
Fig. 8 is a schematic structural diagram of another kinds of obstacle detection devices according to an embodiment of the present application, please refer to fig. 8, where the obstacle detection device 400 further includes:
a third determining module 45, configured to project the two-dimensional image to a high-precision map to determine a plurality of reference points from the high-precision map before the second determining module 43 determines the second ground equation corresponding to the position from the ground equation set corresponding to the two-dimensional image according to the position of the obstacle in the world coordinate system, and determine the ground equation set according to the plurality of reference points.
, the third determining module 45 is specifically configured to determine a reference point and a second reference point from the plurality of reference points, the abscissa of the reference point is the largest reference point, the abscissa of the second reference point is the smallest reference point, the number of segments of the abscissa is determined according to the reference point and the second reference point, the third reference point and the fourth reference point are determined from the plurality of reference points, the ordinate of the third reference point is the largest reference point, the ordinate of the fourth reference point is the largest reference point, the number of segments of the ordinate is determined according to the third reference point and the fourth reference point, the total number of segments is determined according to the number of segments of the abscissa and the number of segments of the ordinate, and the ground equation set is determined according to the total number of segments and the plurality of reference points.
, the third determining module 45 is configured to, for each reference points in the plurality of reference points, determine a segment label corresponding to the reference point according to an abscissa and an ordinate of the reference point, thereby determining the segment label corresponding to each reference point in the plurality of reference points, determine whether the number of the reference points corresponding to a target segment label exceeds a preset threshold, where the target segment label is the segment label corresponding to any reference points in the plurality of reference points, and if the number of the reference points corresponding to the target segment label exceeds the preset threshold, determine a ground equation corresponding to the target segment label, thereby obtaining the ground equation set.
, referring to fig. 8, the obstacle detecting device 400 further includes a fourth determining module 46, configured to determine the parameter of the roadside apparatus according to the jitter condition of the roadside apparatus before the updating module 44 determines the third ground equation according to the second ground equation and the parameter of the roadside apparatus.
, referring to fig. 8, the obstacle detection apparatus 400 further includes a control module 47 for controlling the vehicle to perform automatic driving according to the updated position after the update module 44 updates the position of the obstacle in the world coordinate system according to the second ground equation.
The apparatus provided in the embodiment of the present application may be used in the method executed by the electronic device in the above embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
electronic devices and readable storage media are also provided according to embodiments of the present application.
Fig. 9 is a block diagram of an electronic device for implementing the obstacle detection method according to the embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. 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 device includes or more processors 501, a memory 502, 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 otherwise as desired.
The memory 502 is a non-transitory computer readable storage medium provided herein, wherein the memory stores instructions executable by at least processors to cause the at least processors to perform the method of obstacle detection provided herein.
The memory 502 is used as non-transitory computer readable storage media for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the obstacle detection method in the embodiment of the present application (for example, the receiving module 41, the determining module 42, the second determining module 43, the updating module 44, the third determining module 45, the fourth determining module 46, and the control module 47 shown in fig. 7 and 8), the processor 501 executes various functional applications and data processing of the server by executing the non-transitory software programs, instructions, and modules stored in the memory 502, that is, implements the obstacle detection method in the above-described method embodiment.
The memory 502 may include a program storage area that may store an operating system, applications needed for at least functions, and a data storage area that may store data created from use of the electronic device, etc. additionally, the memory 502 may include high speed random access memory, and may also include non-transitory memory, such as at least disk storage devices, flash memory devices, or other non-transitory solid state storage devices in some embodiments, the memory 502 may optionally include memory located remotely from the processor 501, which may be connected to the electronic device via a network.
The electronic device performing the obstacle detection method may further include: an input device 503 and an output device 505. The processor 501, the memory 502, the input device 503 and the output device 505 may be connected by a bus or other means, and fig. 9 illustrates the connection by a bus as an example.
The input device 503 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of the electronic device, such as input devices like touch screens, keypads, mice, trackpads, touch pads, pointing sticks, or more mouse buttons, trackballs, joysticks, etc. the output device 505 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), etc.
Various embodiments of the systems and techniques described here can be implemented in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof, and these various embodiments can include or more computer programs that are executable and/or interpretable on a programmable system including at least programmable processors, which may be special or general purpose programmable processors, that can receive data and instructions from, and transmit data and instructions to, a storage system, the at least input devices, and the at least output devices.
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.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components.
The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
The embodiment of the application also provides obstacle detection methods, which comprise the steps of determining the position of an obstacle in a two-dimensional image under a world coordinate system according to a pre-stored ground equation, determining a second ground equation from a ground equation set according to the position, wherein the ground equation set comprises at least ground equations, determining a third ground equation according to the second ground equation and parameters of roadside equipment, wherein the roadside equipment is a device for capturing the two-dimensional image, and updating the position of the obstacle under the world coordinate system according to the third ground equation.
According to the technical scheme of the embodiment of the application, the obstacle in the 2d image is returned to the world coordinate system through a global offline ground equation, namely the th ground equation, the segmented ground equation, namely the second ground equation, is found according to the position of the obstacle in the world coordinate system, then the position of the obstacle in the world coordinate system is updated according to the second ground equation, and the updated position is the accurate position of the obstacle in the world coordinate system.
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, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
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 (17)
1, A method for obstacle detection, comprising:
receiving a request instruction, wherein the request instruction is used for requesting to detect an obstacle in a two-dimensional image;
determining the position of the obstacle in a world coordinate system according to the request instruction and a prestored th ground equation;
according to the position of the obstacle in a world coordinate system, determining a second ground equation corresponding to the position from a ground equation set corresponding to the two-dimensional image, wherein the ground equation set comprises at least ground equations;
and updating the position of the obstacle in the world coordinate system according to the second ground equation.
2. The method of claim 1, wherein updating the location of the obstacle in the world coordinate system according to the second ground equation comprises:
determining a third ground equation according to the second ground equation and parameters of road side equipment, wherein the road side equipment is a device for capturing the two-dimensional image;
and updating the position of the obstacle in the world coordinate system according to the third ground equation.
3. The method according to claim 1 or 2, wherein before determining the second ground equation corresponding to the position from the set of ground equations corresponding to the two-dimensional image according to the position of the obstacle in the world coordinate system, the method further comprises:
projecting the two-dimensional image to a high-precision map to determine a plurality of reference points from the high-precision map;
determining the set of ground equations from the plurality of reference points.
4. The method of claim 3, wherein said determining the set of ground equations from the plurality of reference points comprises:
determining th reference point and a second reference point from the plurality of reference points, wherein the abscissa of the th reference point is the largest reference point and the abscissa of the second reference point is the smallest reference point, and determining the number of segments of the abscissa according to the th reference point and the second reference point;
determining a third reference point and a fourth reference point from the plurality of reference points, wherein the ordinate of the third reference point is the reference point with the largest ordinate in the plurality of reference points, the ordinate of the fourth reference point is the reference point with the largest ordinate in the plurality of reference points, and the number of segments of the longitudinal axis is determined according to the third reference point and the fourth reference point;
determining the total number of the segments according to the number of the segments of the horizontal axis and the number of the segments of the vertical axis;
and determining the ground equation set according to the total number of the segments and the reference points.
5. The method of claim 4, wherein determining the set of ground equations from the total number of segments and the plurality of reference points comprises:
for each reference points in the plurality of reference points, determining the segment label corresponding to the reference point according to the abscissa and the ordinate of the reference point, thereby determining the segment label corresponding to each reference point in the plurality of reference points;
determining whether the number of reference points corresponding to a target segmentation label exceeds a preset threshold, wherein the target segmentation label is a segmentation label corresponding to any reference points in the plurality of reference points;
and if the number of the reference points corresponding to the target segmented label exceeds a preset threshold value, determining a ground equation corresponding to the target segmented label, so as to obtain the ground equation set.
6. The method of any one of claims 1 to 5 and , wherein prior to determining a third ground equation from the second ground equation and the parameters of the roadside device, further comprising:
and determining parameters of the road side equipment according to the jitter condition of the road side equipment.
7. The method of any one of claims 1 to 5 and , wherein the updating the position of the obstacle in the world coordinate system according to the second ground equation further comprises:
and controlling the vehicle to perform automatic driving according to the updated position.
8, kinds of obstacle detection device, characterized by comprising:
the device comprises a receiving module, a judging module and a judging module, wherein the receiving module is used for receiving a request instruction which is used for requesting to detect an obstacle in a two-dimensional image;
an determining module, configured to determine, according to the request instruction and a pre-stored th ground equation, a position of the obstacle in a world coordinate system;
the second determination module is used for determining a second ground equation corresponding to the position from a ground equation set corresponding to the two-dimensional image according to the position of the obstacle in a world coordinate system, wherein the ground equation set comprises at least ground equations;
and the updating module is used for updating the position of the barrier in the world coordinate system according to the second ground equation.
9. The apparatus of claim 8,
the updating module is used for determining a third ground equation according to the second ground equation and parameters of road side equipment, and the road side equipment is a device for capturing the two-dimensional image and updates the position of the obstacle under the world coordinate system according to the third ground equation.
10. The apparatus of claim 8 or 9, further comprising:
and the third determining module is used for projecting the two-dimensional image to a high-precision map to determine a plurality of reference points from the high-precision map before the second determining module determines a second ground equation corresponding to the position from the ground equation set corresponding to the two-dimensional image according to the position of the obstacle in the world coordinate system, and determining the ground equation set according to the plurality of reference points.
11. The apparatus of claim 10,
the third determining module is configured to determine th reference point and a second reference point from the plurality of reference points, an abscissa of the th reference point is a reference point with a largest abscissa among the plurality of reference points, an abscissa of the second reference point is a reference point with a smallest abscissa among the plurality of reference points, determine the number of segments of the abscissa according to the th reference point and the second reference point, determine a third reference point and a fourth reference point from the plurality of reference points, an ordinate of the third reference point is a reference point with a largest ordinate among the plurality of reference points, a ordinate of the fourth reference point is a reference point with a largest ordinate among the plurality of reference points, determine the number of segments of the vertical axis according to the third reference point and the fourth reference point, determine the total number of segments according to the number of segments of the horizontal axis and the number of segments of the vertical axis, and determine the ground equation set according to the total number of segments and the plurality of reference points.
12. The apparatus of claim 11,
the third determining module is configured to determine, for each reference points in the plurality of reference points, a segment tag corresponding to the reference point according to the abscissa and the ordinate of the reference point, so as to determine the segment tag corresponding to each reference point in the plurality of reference points, determine whether the number of the reference points corresponding to a target segment tag exceeds a preset threshold, where the target segment tag is a segment tag corresponding to any reference points in the plurality of reference points, and if the number of the reference points corresponding to the target segment tag exceeds the preset threshold, determine a ground equation corresponding to the target segment tag, so as to obtain the ground equation set.
13. The apparatus of any one of claims 8 to 12, , further comprising:
and the fourth determining module is used for determining the parameters of the road side equipment according to the jitter condition of the road side equipment before the updating module updates the position of the obstacle in the world coordinate system according to the second ground equation.
14. The apparatus of any one of claims 8 to 12, , further comprising:
and the control module is used for controlling the vehicle to execute automatic driving according to the updated position after the updating module updates the position of the obstacle in the world coordinate system according to the second ground equation.
15, an electronic device, comprising:
at least processors, and
a memory communicatively coupled to the at least processors, wherein,
the memory stores instructions executable by the at least processors to be executed by the at least processors to enable the at least processors to perform the method of any of claims 1-6.
A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any of claims 1-6, wherein the computer instructions are for causing the computer to perform the method of any of claims .
A method of detecting an obstacle of the kind , comprising:
determining the position of the obstacle in the two-dimensional image under a world coordinate system according to a prestored th ground equation;
determining a second ground equation from a set of ground equations according to the position, wherein the set of ground equations comprises at least ground equations;
and updating the position of the obstacle in the world coordinate system according to the second ground equation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911002600.0A CN110738183B (en) | 2019-10-21 | 2019-10-21 | Road side camera obstacle detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911002600.0A CN110738183B (en) | 2019-10-21 | 2019-10-21 | Road side camera obstacle detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110738183A true CN110738183A (en) | 2020-01-31 |
| CN110738183B CN110738183B (en) | 2022-12-06 |
Family
ID=69270718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911002600.0A Active CN110738183B (en) | 2019-10-21 | 2019-10-21 | Road side camera obstacle detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110738183B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368794A (en) * | 2020-03-19 | 2020-07-03 | 北京百度网讯科技有限公司 | Obstacle detection method, apparatus, device, and medium |
| CN111578839A (en) * | 2020-05-25 | 2020-08-25 | 北京百度网讯科技有限公司 | Obstacle coordinate processing method and device, electronic equipment and readable storage medium |
| CN111612760A (en) * | 2020-05-20 | 2020-09-01 | 北京百度网讯科技有限公司 | Method and apparatus for detecting obstacles |
| CN111612852A (en) * | 2020-05-20 | 2020-09-01 | 北京百度网讯科技有限公司 | Method and apparatus for verifying camera parameters |
| CN111666876A (en) * | 2020-06-05 | 2020-09-15 | 北京百度网讯科技有限公司 | Method and device for detecting obstacle, electronic equipment and road side equipment |
| CN111721281A (en) * | 2020-05-27 | 2020-09-29 | 北京百度网讯科技有限公司 | Position identification method and device and electronic equipment |
| CN111767843A (en) * | 2020-06-29 | 2020-10-13 | 北京百度网讯科技有限公司 | Three-dimensional position prediction method, device, equipment and storage medium |
| CN112101209A (en) * | 2020-09-15 | 2020-12-18 | 北京百度网讯科技有限公司 | Method and apparatus for determining a world coordinate point cloud for roadside computing devices |
| CN112184914A (en) * | 2020-10-27 | 2021-01-05 | 北京百度网讯科技有限公司 | Method and device for determining three-dimensional position of target object and road side equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701478A (en) * | 2016-02-24 | 2016-06-22 | 腾讯科技（深圳）有限公司 | Method and device for extraction of rod-shaped ground object |
| CN108010360A (en) * | 2017-12-27 | 2018-05-08 | 中电海康集团有限公司 | A kind of automatic Pilot context aware systems based on bus or train route collaboration |
| CN109074668A (en) * | 2018-08-02 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | Method for path navigation, relevant apparatus and computer readable storage medium |
| CN109074490A (en) * | 2018-07-06 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | Path detection method, related device and computer readable storage medium |
| CN109540144A (en) * | 2018-11-29 | 2019-03-29 | 北京久其软件股份有限公司 | A kind of indoor orientation method and device |
-
2019
- 2019-10-21 CN CN201911002600.0A patent/CN110738183B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701478A (en) * | 2016-02-24 | 2016-06-22 | 腾讯科技（深圳）有限公司 | Method and device for extraction of rod-shaped ground object |
| CN108010360A (en) * | 2017-12-27 | 2018-05-08 | 中电海康集团有限公司 | A kind of automatic Pilot context aware systems based on bus or train route collaboration |
| CN109074490A (en) * | 2018-07-06 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | Path detection method, related device and computer readable storage medium |
| CN109074668A (en) * | 2018-08-02 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | Method for path navigation, relevant apparatus and computer readable storage medium |
| CN109540144A (en) * | 2018-11-29 | 2019-03-29 | 北京久其软件股份有限公司 | A kind of indoor orientation method and device |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368794B (en) * | 2020-03-19 | 2023-09-19 | 北京百度网讯科技有限公司 | Obstacle detection method, device, equipment and medium |
| CN111368794A (en) * | 2020-03-19 | 2020-07-03 | 北京百度网讯科技有限公司 | Obstacle detection method, apparatus, device, and medium |
| CN111612760A (en) * | 2020-05-20 | 2020-09-01 | 北京百度网讯科技有限公司 | Method and apparatus for detecting obstacles |
| CN111612852A (en) * | 2020-05-20 | 2020-09-01 | 北京百度网讯科技有限公司 | Method and apparatus for verifying camera parameters |
| CN111612760B (en) * | 2020-05-20 | 2023-11-17 | 阿波罗智联(北京)科技有限公司 | Method and device for detecting obstacles |
| US11688099B2 (en) | 2020-05-20 | 2023-06-27 | Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd. | Method and apparatus for detecting obstacle |
| EP3846129A3 (en) * | 2020-05-20 | 2021-10-06 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for detecting obstacle |
| CN111578839B (en) * | 2020-05-25 | 2022-09-20 | 阿波罗智联(北京)科技有限公司 | Obstacle coordinate processing method and device, electronic equipment and readable storage medium |
| CN111578839A (en) * | 2020-05-25 | 2020-08-25 | 北京百度网讯科技有限公司 | Obstacle coordinate processing method and device, electronic equipment and readable storage medium |
| CN111721281A (en) * | 2020-05-27 | 2020-09-29 | 北京百度网讯科技有限公司 | Position identification method and device and electronic equipment |
| CN111721281B (en) * | 2020-05-27 | 2022-07-15 | 阿波罗智联(北京)科技有限公司 | Position identification method and device and electronic equipment |
| CN111666876B (en) * | 2020-06-05 | 2023-06-09 | 阿波罗智联(北京)科技有限公司 | Method and device for detecting obstacle, electronic equipment and road side equipment |
| CN111666876A (en) * | 2020-06-05 | 2020-09-15 | 北京百度网讯科技有限公司 | Method and device for detecting obstacle, electronic equipment and road side equipment |
| CN111767843A (en) * | 2020-06-29 | 2020-10-13 | 北京百度网讯科技有限公司 | Three-dimensional position prediction method, device, equipment and storage medium |
| CN111767843B (en) * | 2020-06-29 | 2024-01-02 | 阿波罗智联(北京)科技有限公司 | Three-dimensional position prediction method, device, equipment and storage medium |
| CN112101209A (en) * | 2020-09-15 | 2020-12-18 | 北京百度网讯科技有限公司 | Method and apparatus for determining a world coordinate point cloud for roadside computing devices |
| CN112101209B (en) * | 2020-09-15 | 2024-04-09 | 阿波罗智联(北京)科技有限公司 | Method and apparatus for determining world coordinate point cloud for roadside computing device |
| CN112184914A (en) * | 2020-10-27 | 2021-01-05 | 北京百度网讯科技有限公司 | Method and device for determining three-dimensional position of target object and road side equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110738183B (en) | 2022-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110738183B (en) | Road side camera obstacle detection method and device | |
| KR102407504B1 (en) | Method and apparatus for detecting obstacle, electronic device and storage medium | |
| CN111722245B (en) | Positioning method, positioning device and electronic equipment | |
| CN110827325B (en) | Target tracking method and device, electronic equipment and storage medium | |
| EP3968266B1 (en) | Obstacle three-dimensional position acquisition method and apparatus for roadside computing device | |
| CN111578839B (en) | Obstacle coordinate processing method and device, electronic equipment and readable storage medium | |
| CN111079079B (en) | Data correction method, device, electronic equipment and computer readable storage medium | |
| JP7110310B2 (en) | MONITORING METHOD, APPARATUS, ELECTRONIC EQUIPMENT, STORAGE MEDIUM, AND PROGRAM FOR IMAGE ACQUISITION FACILITIES | |
| CN112184914A (en) | Method and device for determining three-dimensional position of target object and road side equipment | |
| CN112668428A (en) | Vehicle lane change detection method, roadside device, cloud control platform and program product | |
| CN111652112A (en) | Lane flow direction identification method and device, electronic equipment and storage medium | |
| CN110866504B (en) | Method, device and equipment for acquiring annotation data | |
| CN111191619A (en) | Method, device and equipment for detecting virtual line segment of lane line and readable storage medium | |
| CN111353466A (en) | Lane line recognition processing method, lane line recognition processing device, and storage medium | |
| CN110717474A (en) | Target association calculation method, device, equipment and medium | |
| KR20220004604A (en) | Method for detecting obstacle, electronic device, roadside device and cloud control platform | |
| CN111949816B (en) | Positioning processing method, device, electronic equipment and storage medium | |
| CN110798681B (en) | Monitoring method and device of imaging equipment and computer equipment | |
| CN112509126A (en) | Method, device, equipment and storage medium for detecting three-dimensional object | |
| CN111783611A (en) | Unmanned vehicle positioning method and device, unmanned vehicle and storage medium | |
| CN111612851A (en) | Method, apparatus, device and storage medium for calibrating camera | |
| CN111275827A (en) | Edge-based augmented reality three-dimensional tracking registration method and device and electronic equipment | |
| CN111596086B (en) | Method and device for estimating speed of obstacle in automatic driving and electronic equipment | |
| CN110728721B (en) | Method, device and equipment for acquiring external parameters | |
| CN111336984A (en) | Obstacle ranging method, device, equipment and medium |
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 |
Effective date of registration: 20211025 Address after: 105 / F, building 1, No. 10, Shangdi 10th Street, Haidian District, Beijing 100085 Applicant after: Apollo Intelligent Technology (Beijing) 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. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |