Method and apparatus for acquiring the position of a stationary target - Patents.com

Abstract

To provide a method and a device for acquiring a position of a stationary target.SOLUTION: A method for acquiring a position of a stationary target may include generating a fusion track on the basis of data collected from a radar and a camera, determining whether or not the fusion track is stationary, in response to the fusion track being stationary, collecting radar points related to the fusion track, and acquiring a center point of the target on the basis of the collected radar points.SELECTED DRAWING: Figure 9

Description

[Technical field]

[0001] The present invention relates to a method and apparatus for acquiring the position of a stationary target. [Background technology]

[0002] Radar (Radio Detection And Ranging) detects the position and direction of an object and makes it possible to measure the distance and speed of the object. Radar is widely used for detecting the surrounding environment using radio waves, but in the case of vehicle radar, the number of detections is low due to its low angle recognition performance, so there may be limitations to distinguishing the type of object using radar alone.

[0003] In addition, in recent years, with the development of deep learning technology, autonomous driving technology that recognizes the surrounding environment using multiple cameras inside the vehicle and generates a driving route for the vehicle based on that recognition has rapidly emerged. However, there are still many challenges related to autonomous driving, since various situations that can occur in the road traffic environment are variable and the surrounding environment must be recognized in real time before making a decision. On the other hand, sensor fusion technology, which combines multiple sensors to grasp the surrounding environment, is also attracting a lot of attention.

[0004] The above-mentioned background art is technical information possessed by the inventor for the purpose of deriving the present invention or acquired in the process of deriving the present invention, and is not necessarily publicly known art that was disclosed to the general public prior to the filing of the present application. Summary of the Invention [Problem to be solved by the invention]

[0005] The object of the present disclosure is to provide a method and device for acquiring the position of a stationary target. The problems to be solved by the present disclosure are not limited to the problems described above, and other problems and advantages of the present disclosure that are not described will be understood from the following description and will be more clearly understood from the embodiments of the present disclosure. It will also be understood that the problems and advantages to be solved by the present disclosure can be realized by the means and combinations thereof described in the claims. [Means for solving the problem]

[0006] A first aspect of the present disclosure may provide a method for acquiring a position of a stationary target, the method including the steps of generating a fusion track based on data collected from a radar and a camera, determining whether the fusion track is stationary, collecting radar points related to the fusion track in response to the fusion track being stationary, and acquiring a center point of the target based on the collected radar points.

[0007] A second aspect of the present disclosure may provide an apparatus for acquiring a position of a stationary target, the apparatus including a memory having at least one program stored therein, and a processor operating by executing the at least one program, the processor generating a fusion track based on data collected from a radar and a camera, determining whether the fusion track is stationary, collecting radar points related to the fusion track in response to the fusion track being stationary, and acquiring a center point of a target based on the collected radar points.

[0008] A third aspect of the present disclosure may provide a method for generating a contour of a stationary target, the method including generating a fusion track based on data collected from a radar and a camera, determining whether the fusion track is stationary, collecting radar points related to the fusion track in response to the fusion track being stationary, and generating a contour of a target based on the collected radar points.

[0009] A fourth aspect of the present disclosure may provide an apparatus for generating a contour of a stationary target, comprising: a memory having at least one program stored therein; and a processor operating by executing the at least one program, wherein the processor generates a fusion track based on data collected from a radar and a camera; determines whether the fusion track is stationary; and in response to the fusion track being stationary, collects radar points related to the fusion track; and generates a contour of a target based on the collected radar points.

[0010] A fifth aspect of the present disclosure may provide a computer-readable recording medium having recorded thereon a program for causing a computer to execute the method according to the first or third aspect. Effect of the Invention

[0011] According to one embodiment of the present invention, information collected by radar and cameras can be processed to perform location tracking with a high level of accuracy, thereby replacing expensive and highly accurate equipment for recognizing surrounding vehicles.

[0012] Moreover, according to an embodiment of the present invention, highly accurate position acquisition is possible even for stationary targets, and real-time performance is guaranteed since a highly complex algorithm is not used.

[0013] Furthermore, by filtering the ambient noise using the grid map, the target's pose can be accurately estimated. [Brief description of the drawings]

[0014] [Figure 1] FIG. 2 is a diagram for explaining an autonomous driving method according to an embodiment. [Diagram 2] FIG. 2 is a diagram for explaining an autonomous driving method according to an embodiment. [Diagram 3] FIG. 2 is a diagram for explaining an autonomous driving method according to an embodiment. [Figure 4] FIG. 1 is a block diagram for generally illustrating a sensor fusion system according to an embodiment. [Diagram 5] 1 is a flow diagram illustrating a data conversion process in a fusion track generation process according to an embodiment of the present disclosure. [Figure 6] FIG. 1 is a flow diagram illustrating a process for collecting radar points for a fusion truck according to one embodiment of the present disclosure. [Figure 7A] 1A to 1C are diagrams for explaining a process of acquiring a center point of a target according to an embodiment of the present disclosure. [Figure 7B] 1A to 1C are diagrams for explaining a process of acquiring a center point of a target according to an embodiment of the present disclosure. [Figure 8A] FIG. 1 is a diagram illustrating a process for generating a contour of a stationary target according to one embodiment of the present disclosure. [Figure 8B] FIG. 1 is a diagram illustrating a process for generating a contour of a stationary target according to one embodiment of the present disclosure. [Figure 8C] FIG. 1 is a diagram illustrating a process for generating a contour of a stationary target according to one embodiment of the present disclosure. [Figure 9] FIG. 2 is a flow diagram illustrating a method for acquiring a position of a stationary target according to one embodiment. [Figure 10] FIG. 1 is a flow diagram illustrating a method for generating a contour of a stationary target according to one embodiment. [Figure 11] FIG. 1 is a block diagram illustrating an apparatus according to one embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] The advantages and features of the present invention, as well as the methods for achieving them, will become apparent from the embodiments described in detail with the accompanying drawings. However, the present invention is not limited to the embodiments presented below, and can be realized in various different forms, and should be understood to include all modifications, equivalents, and alternatives within the spirit and technical scope of the present invention. The embodiments presented below are provided to complete the disclosure of the present invention and to allow those skilled in the art to fully understand the scope of the invention. In describing the present invention, if a detailed description of related publicly known technology is deemed to obscure the gist of the present invention, the detailed description will be omitted.

[0016] The terms used in this application are merely used to describe certain embodiments and are not intended to limit the present invention. A singular expression includes a plural expression unless the context clearly indicates otherwise. In this application, the terms "include" and "have" are used to specify the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and are not to be understood as precluding the presence or additional possibility of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0017] Some embodiments of the present disclosure may be illustrated in terms of functional block configurations and various processing steps. Some or all of such functional blocks may be implemented in any number of hardware and / or software configurations for performing specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors or by circuit configurations for a given function. Also, for example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks may be implemented by algorithms executed by one or more processors. Furthermore, the present disclosure may employ conventional techniques for electronic configuration, signal processing, and / or data processing, etc. Terms such as "mechanism," "element," "means," and "configuration" may be used broadly and are not limited to mechanical and physical configurations.

[0018] It should be noted that the connecting lines or connecting members between components shown in the drawings are merely exemplary of functional and / or physical connections or circuit connections, and that in an actual device, connections between components may be represented by various alternative or additional functional connections, physical connections or circuit connections.

[0019] Hereinafter, the term "vehicle" may refer to any type of transportation means having a locomotive and used to move people or goods, such as a car, a bus, a motorcycle, a scooter, or a truck.

[0020] The present disclosure will now be described in detail with reference to the accompanying drawings.

[0021] Referring to FIG. 1, an autonomous driving device according to an embodiment of the present invention can be mounted on a vehicle to realize an autonomous driving vehicle 10. The autonomous driving device mounted on the autonomous driving vehicle 10 may include various sensors (including a camera) for collecting surrounding situation information. As an example, the autonomous driving device may detect the movement of a leading vehicle 20 traveling ahead using an image sensor and / or an event sensor mounted on the front of the autonomous driving vehicle 10. The autonomous driving device may further include sensors for detecting other vehicles 30 traveling on adjacent roads as well as in front of the autonomous driving vehicle 10, pedestrians around the autonomous driving vehicle 10, and the like.

[0022] At least one of the sensors for collecting situational information around the autonomous vehicle 10 can have a predetermined angle of view (FoV) as shown in Fig. 1. As an example, when a sensor mounted on the front of the autonomous vehicle 10 has an angle of view (FoV) as shown in Fig. 1, information detected at the center of the sensor can have a relatively high importance. This is because most of the information corresponding to the movement of the leading vehicle 20 is included in the information detected at the center of the sensor.

[0023] The autonomous driving device processes information collected by sensors of the autonomous vehicle 10 in real time to control the movement of the autonomous vehicle 10, while at least a portion of the information collected by the sensors can be stored in a memory device.

[0024] 2, the autonomous driving device 40 may include a sensor unit 41, a processor 46, a memory system 47, a vehicle control module 48, etc. The sensor unit 41 includes a plurality of sensors (including a camera) 42-45, and the plurality of sensors 42-45 may include an image sensor, an event sensor, an illuminance sensor, a GPS device, an acceleration sensor, etc.

[0025] The data collected by the sensors 42 to 45 may be transmitted to the processor 46. The processor 46 can store the data collected by the sensors 42 to 45 in the memory system 47 and control the body control module 48 to determine the movement of the vehicle based on the data collected by the sensors 42 to 45. The memory system 47 may include two or more memory devices and a system controller for controlling the memory devices. Each of the memory devices may be provided as a single semiconductor chip.

[0026] In addition to the system controller of memory system 47, each of the memory devices included in memory system 47 may include a memory controller, and the memory controller may include an artificial intelligence (AI) calculation circuit such as a neural network. The memory controller can generate calculation data by applying a predetermined weight to data received from sensors 42 to 45 or processor 46, and store the calculation data in a memory chip.

[0027] Fig. 3 is a diagram showing an example of video data acquired by a sensor (including a camera) of an autonomous vehicle equipped with an autonomous driving device. Referring to Fig. 3, video data 50 may be data acquired by a sensor attached to the front of the autonomous vehicle. Thus, video data 50 may include a front portion 51 of the autonomous vehicle, a preceding vehicle 52 on the same road as the autonomous vehicle, vehicles 53 traveling around the autonomous vehicle, and a background 54.

[0028] 3, data of the area in which the front part 51 and background 54 of the autonomous vehicle are displayed may be data that is unlikely to affect the operation of the autonomous vehicle. In other words, the front part 51 and background 54 of the autonomous vehicle may be considered to be data having a relatively low importance.

[0029] In contrast, the distance to the preceding vehicle 52, the lane-changing behavior of the moving vehicle 53, and the like can be very important factors in the safe operation of the autonomous vehicle. Therefore, in the video data 50, data of an area including the preceding vehicle 52 and the moving vehicle 53 can have a relatively high importance in the operation of the autonomous vehicle.

[0030] The memory device of the autonomous driving device can store the image data 50 received from the sensor by assigning different weights to each area. For example, a high weight can be assigned to data of an area including a leading vehicle 52 and a moving vehicle 53, and a low weight can be assigned to data of an area including a front part 51 of the autonomous driving vehicle and a background 54.

[0031] Hereinafter, operations according to various embodiments may be understood to be performed by an autonomous driving device or a processor included in the autonomous driving device.

[0032] FIG. 4 is a block diagram for illustrating a sensor fusion system according to an embodiment.

[0033] In the following, the sensor fusion system 400 may be substantially the same as the autonomous driving device of the present disclosure, may be included in the autonomous driving device, or may be a component realized as part of the functions performed by the autonomous driving device.

[0034] In one embodiment, the sensor fusion system 400 may include a radar 410, a camera 420, and a processor 430.

[0035] The radar 410 can obtain radar points by emitting radio waves to the surroundings and detecting the reflected waves reflected by objects, and can determine distance information, particularly vertical distance information, to the object based on the obtained radar points. Here, the radar 410 can determine vehicle status information using an antenna, a transmitting / receiving end, and a signal processing end. For example, the radar 410 can detect the distance, angle, and speed of each object using a transmitting antenna and multiple receiving antennas.

[0036] The radar 410 is relatively resistant to external environments and can accurately detect distances based on the round trip time of radio waves. In addition, the radar 410 can indirectly obtain speed information of surrounding vehicles by using the Doppler frequency reflected from objects.

[0037] However, in the case of the radar 410, since the angle detection performance is relatively low, all objects are recognized as a small number of points, and the accuracy of position recognition of stationary objects (vehicles) is lower than that of moving objects. Therefore, further processing may be required to recognize or distinguish surrounding objects based on the information acquired by the radar 410.

[0038] The camera 420 is mounted at least one of the front, rear, and side of the vehicle and can acquire image data and transmit it to the processor. From the acquired image data, features of an object can be extracted, a bounding box can be set for the object, and tracking information regarding the object can be acquired.

[0039] The processor 430 calibrates the radar 410 and the camera 420, generates a sensor fusion image by matching distance information from an object acquired by the radar 410 and image data acquired by the camera 420, and can determine the position of surrounding objects included in the image data by analyzing the radar points and the sensor fusion image.

[0040] Meanwhile, the sensor fusion system 400 accumulates a number of radar points and uses them as data for determining the position of an object. In general, the sensor fusion system 400 accumulates a number of radar points for a specific period of time on a time basis.

[0041] The sensor fusion system 400 can cluster the accumulated radar points to generate a radar point cloud. For example, the algorithm used for clustering can be DBSCAN (density-based clustering) or k-means algorithm. However, the clustering algorithm used to generate the radar point cloud can be computationally intensive.

[0042] Therefore, the present disclosure proposes a method and apparatus that can improve radar recognition accuracy for stationary targets and reduce the amount of computation required to determine the target's position.

[0043] An apparatus for acquiring the position of a stationary target or generating a contour of a stationary target according to various embodiments of the present disclosure may be substantially the same as sensor fusion system 400, may be included in sensor fusion system 400, or may be a component implemented as part of the functionality performed by sensor fusion system 400.

[0044] The apparatus for acquiring the position of a stationary target and the apparatus for generating the contour of the stationary target according to various embodiments of the present disclosure may be substantially the same apparatus.

[0045] The apparatus for acquiring a stationary target position of the present disclosure can generate a fusion track based on data collected from the radar and the camera. The apparatus for acquiring a stationary target position of the present disclosure can determine whether the generated fusion track is stationary. If the fusion track is stationary, the apparatus for acquiring a stationary target position can collect radar points for the fusion track. The apparatus for acquiring a stationary target position can acquire a center point of the target based on the radar points collected for the stationary fusion track.

[0046] The stationary target profile generating apparatus of the present disclosure can generate a fusion track based on data collected from the radar and the camera. The stationary target profile generating apparatus of the present disclosure can determine whether the generated fusion track is stationary. If the fusion track is stationary, the stationary target profile generating apparatus of the present disclosure can collect radar points for the fusion track. The stationary target profile generating apparatus of the present disclosure can generate a target profile based on the collected radar points.

[0047] The method by which the apparatus for acquiring the position of a stationary target acquires the position of the stationary target, and the method by which the apparatus for generating the contour of a stationary target generates the contour of the stationary target will be described in detail below.

[0048] In FIG. 5, the process in which a device for acquiring the position of a stationary target or a device for generating the contour of a stationary target generates a fusion track is illustrated.

[0049] FIG. 5 is a flow diagram that illustrates a schematic of data conversion during the fusion track generation process according to one embodiment of the present disclosure.

[0050] In the present disclosure, the device for acquiring the position of a stationary target or the device for generating the contour of a stationary target may include a radar and a camera, and may collect data from the radar and the camera. In one embodiment, the device for acquiring the position of a stationary target or the device for generating the contour of a stationary target may preprocess the data collected from the radar and the camera.

[0051] In the present disclosure, a device for acquiring the position of a stationary target or a device for generating a contour of a stationary target can generate a fusion track based on data collected from a radar and data collected from a camera.

[0052] In comparison, in detecting objects around a vehicle, data collected from a radar accurately reflects vertical position information, and data collected from a camera accurately reflects horizontal position information. The device for acquiring the position of a stationary target or generating the contour of a stationary target of the present disclosure can associate data collected from a radar and data collected from a camera to complement the characteristics of the aforementioned sensors (radar and camera) with each other.

[0053] Specifically, in one embodiment, a device for acquiring the position of a stationary target or generating a contour of a stationary target can detect radar-based objects based on data collected from a radar and can detect camera-based objects based on data collected from a camera.

[0054] Referring to FIG. 5 , a device for acquiring the position of a stationary target or generating the contour of a stationary target can detect an object based on data acquired from a radar 501 and generate a radar-based object 503, and detect an object based on data acquired from a camera 502 and generate a camera-based object 504.

[0055] In one embodiment, the device for acquiring the position of a stationary target or the device for generating the contour of a stationary target can determine related objects from among the radar-based objects and the camera-based objects, and generate fusion tracks for the related objects. A person skilled in the art can easily understand that the radar-based objects can include one or more objects, the camera-based objects can include one or more objects, and the related objects can also include one or more objects.

[0056] Referring to FIG. 5 , a device for acquiring the position of a stationary target or generating the contour of a stationary target can determine an associated object 505 from among a radar-based object 503 and a camera-based object 504.

[0057] In one embodiment, the stationary target location acquisition device or stationary target profile generation device may associate data on a distance basis, for example, the stationary target location acquisition device or stationary target profile generation device may determine whether a radar-based object and a camera-based object are associated with each other based on distance information from data collected from a radar and distance information from data collected from a camera.

[0058] Referring to FIG. 5, a device for acquiring the position of a stationary target or generating the contour of a stationary target can generate a fusion track 506 for an associated object 505 .

[0059] In the present disclosure, a device for acquiring the position of a stationary target or a device for generating a contour of a stationary target can collect radar points for the generated fusion track and can generate a point cloud based on the collected radar points.

[0060] In FIG. 6, the process by which a device for acquiring the position of a stationary target or generating the contour of a stationary target collects radar points is illustrated.

[0061] FIG. 6 is a flow diagram illustrating a process for collecting radar points for a fusion truck according to one embodiment of the present disclosure.

[0062] In one embodiment, a device for acquiring the position of a stationary target or a device for generating a contour of a stationary target may determine (601) whether the generated fusion track is stationary.

[0063] Generally, estimation of location information based on data collected from radar is characterized by low accuracy for stationary objects, so the device for acquiring the location of a stationary target or the device for generating the contour of a stationary target of the present disclosure can determine whether the fusion track is stationary or not, and if the fusion track is stationary, estimate the exact location of the target or the contour of the target through further processing.

[0064] In the present disclosure, a device for acquiring the position of a stationary target or a device for generating a contour of a stationary target may determine whether a fusion track is stationary based on any suitable manner.

[0065] In one embodiment, a device for acquiring the position of a stationary target or a device for generating a contour of a stationary target can determine whether the fusion track is stationary based on the object's velocity according to data collected from the radar and the absolute velocity of the fusion track.

[0066] In one embodiment, a device for acquiring the position of a stationary target or a device for generating a contour of a stationary target may determine (602) radar points assigned to the fusion track determined to be stationary (hereinafter referred to as the “first track”) in response to the fusion track being stationary.

[0067] A radar point is obtained when radio waves emitted from a radar are reflected by an object and then re-enter the radar for detection, and may include distance information between the vehicle and the object.

[0068] In the present disclosure, the data collected from the radar includes radar points, and the radar points may relate to data related to all objects around the host vehicle. In one embodiment, the device for obtaining the position of the stationary target or the device for generating the contour of the stationary target may determine the radar points assigned to the first track from the data collected from the radar.

[0069] On the other hand, a device for acquiring the position of a stationary target or a device for generating the contour of a stationary target can collect radar points for a fusion track by updating the accumulated points on a time basis. However, when collecting radar points on a time basis, if both the vehicle and the target (fusion track) are stationary, the collected radar points may be sparse.

[0070] In the present disclosure, a device for acquiring the position of a stationary target or generating a contour of a stationary target can collect radar points for a fusion track on a number of accumulated points basis. Collecting radar points on a number basis, rather than on a time basis, can be advantageous for collecting data on stationary objects.

[0071] In one embodiment, the maximum number of accumulated points for one fusion track, i.e. the number of radar points that the accumulated points for one fusion track can include, may be pre-determined, for example, a device for acquiring the position of a stationary target or generating the contour of a stationary target may collect up to 300, 500 or 700 radar points for one fusion track.

[0072] In one embodiment, a device for acquiring the position of a stationary target or a device for generating a contour of a stationary target may determine (603) whether the number of accumulated points has reached a maximum number of accumulated points.

[0073] In one embodiment, if the number of accumulated points has not reached the maximum number of accumulated points, the device for acquiring the stationary target position or the device for generating the stationary target contour may update the accumulated points for the fusion track based on the radar points assigned to the fusion track (604). Specifically, the device for acquiring the stationary target position or the device for generating the stationary target contour may determine the radar points assigned to the first track from the data collected from the radar, add the determined radar points to the accumulated points for the first track, and update the accumulated points for the first track.

[0074] In one embodiment, when the number of accumulated points reaches the maximum number of accumulated points, the device for acquiring the stationary target position or the device for generating the stationary target contour may delete the first accumulated point from the accumulated points (605). As an example, when the number of radar points assigned to the fusion track is N, the first N accumulated points from the accumulated points may be deleted. Then, the device for acquiring the stationary target position or the device for generating the stationary target contour may update the accumulated points based on the radar points assigned to the newly determined fusion track (604).

[0075] In one embodiment, a device for acquiring the position of a stationary target or generating the contour of a stationary target may continue to repeat the process of collecting points.

[0076] In one embodiment, the device for acquiring the position of a stationary target or the device for generating the contour of a stationary target may compensate for a distance traveled by the host vehicle in the process of accumulating radar points related to the fusion track. Specifically, updating the accumulated points related to the first track by the device for acquiring the position of a stationary target or the device for generating the contour of a stationary target may include compensating the previous accumulated points for a distance traveled by the host vehicle from a previous update point.

[0077] For example, a device for acquiring the position of a stationary target or a device for generating the contour of a stationary target can determine the coordinates of a new radar point relative to the fusion track by adding a compensation value based on the speed of the vehicle, time, and the degree of rotation of the vehicle to the coordinates of the previous radar point relative to the fusion track.

[0078] In one embodiment, the device for acquiring the stationary target position or the device for generating the stationary target contour may initialize the accumulated points in response to the fusion track determined to be stationary not being stationary (606). In other words, the device for acquiring the stationary target position or the device for generating the stationary target contour may continue to verify whether the first track remains stationary while collecting radar points for the first track, and may initialize the accumulated points for the first track when the first track moves away from the stationary state.

[0079] In the present disclosure, the device for acquiring the position of the stationary target can generate a point cloud based on the accumulated points. In one embodiment, the device for acquiring the position of the stationary target can acquire a center point of the target based on the point cloud.

[0080] In the present disclosure, a stationary target contour generating device can generate target contours based on accumulated points.

[0081] 7A and 7B, a process in which a device for acquiring the position of a stationary target acquires the center point of the target is described.

[0082] 7A and 7B are diagrams for explaining a process of acquiring the center point of a target according to an embodiment of the present disclosure.

[0083] In the present disclosure, a device for acquiring the position of a stationary target can generate a grid map based on data collected from a radar and data collected from a camera.

[0084] 7A, the grid map 700 includes a grid forming rectangular tiles, and a device for acquiring the position of a stationary target can use the grid of the grid map 700 as coordinates. The interval of the grid represented in the grid map 700, the scale of the distance to the actual object, and the like can be arbitrarily determined according to the specifications of the sensor mounted on the vehicle or the device for acquiring the position of the stationary target, or as necessary.

[0085] 7A, grid map 700 may include an indication of the host vehicle and one or more radar points. A device for acquiring the position of a stationary target may display the detected radar points using the grids included in grid map 700 as coordinates with respect to the host vehicle. In other words, since the radar points indicate distance information to an object, the relative positions of the detected radar points may be expressed in grid map 700.

[0086] The radar points represented in the grid map 700 may include associated radar points and non-associated radar points. With reference to Figure 7A, one or more associated radar points and one or more non-associated radar points are shown.

[0087] 7A, the relevant radar points may be radar points that are assigned to a particular fusion track and updated to cumulative points, i.e., in this disclosure, a device that acquires the position of stationary targets may map radar points related to the fusion track as relevant radar points in the generated grid map 700.

[0088] In contrast, in FIG. 7A, one or more non-associated radar points may be radar points that are not associated with a fusion track at all, i.e., radar points that are not assigned to a fusion track.

[0089] In this disclosure, a device that acquires the position of a stationary target can acquire the target's center point based on the associated radar points mapped onto the grid map 700.

[0090] 7B, a device for acquiring the position of a stationary target may generate a target tile 710, which is the smallest rectangle that contains all of the radar points assigned to a particular fusion track, on a tile-by-tile basis. In other words, the target tile 710 may be rectangular in shape and may be made up of one or more tiles containing relevant radar points mapped onto the grid map 700.

[0091] In one embodiment, a device for capturing the position of a stationary target can determine the center point of the target based on the corner points of the target tile 710. The corner points can represent the four corners that make up the target tile 710.

[0092] Specifically, the device for acquiring the position of the stationary target can determine the center point of the target based on the coordinates of each of the corner points. Referring to Fig. 7B, the target tile 710 is composed of a first corner point, a second corner point, a third corner point and a fourth corner point, where the coordinates of the first corner point are (x1, y1), the coordinates of the second corner point are (x2, y2), the coordinates of the third corner point are (x3, y3) and the coordinates of the fourth corner point are (x4, y4).

[0093] Specifically, the device for acquiring the position of the stationary target can acquire four candidate center points from the coordinates of each of the four corner points. For example, the device for acquiring the position of the stationary target can acquire the x and y coordinates of the candidate center points based on the x and y coordinates of the corner points, the length of the fusion track, the width of the fusion track, and the rotation angle of the fusion track.

[0094] In one embodiment, the device for acquiring the position of the stationary target can acquire the center point of the target from four candidate center points. In one embodiment, the device for acquiring the position of the stationary target can determine the candidate center point that has the least change among the four candidate center points based on data related to previous frames as the center point of the target.

[0095] In one embodiment, a device for acquiring the position of a stationary target can estimate the pose of the target based on four candidate center points.

[0096] In the present disclosure, a device for acquiring the position of a stationary target can determine the center point of the determined target as the position of the stationary target.

[0097] In one embodiment, the size or volume occupied by the target may be determined based on the type of target (e.g., vehicle type) identified from the image data and the determined center point of the target.

[0098] In the present disclosure, a device that acquires the position of a stationary target can control the traveling of a vehicle based on the acquired position of the stationary target.

[0099] In one embodiment, a device that obtains the positions of stationary targets can determine a travel path based on the positions of the stationary targets to avoid one or more stationary targets.

[0100] In one embodiment, a device for acquiring the position of a stationary target can determine, based on the position of the stationary target, to change the driving path of the vehicle if the target is present on the existing driving path of the vehicle.

[0101] In one embodiment, the device for acquiring the position of the stationary target can determine which lane the target is stopped in based on the position of the stationary target, and can determine the driving method of the host vehicle. For example, when the target is stopped in a lane adjacent to a sidewalk, the device for acquiring the position of the stationary target can determine to perform overtaking.

[0102] 8A to 8C, a process in which a target contour is generated based on accumulated points is described.

[0103] 8A to 8C are diagrams for explaining a process of generating a contour of a stationary target according to one embodiment of the present disclosure.

[0104] In the present disclosure, a device for generating contours of stationary targets can generate a grid map based on data collected from a radar and data collected from a camera.

[0105] 8A, the grid map 800 includes a grid that forms rectangular tiles, and a device that generates the contour of a stationary target can use the grid of the grid map 800 as coordinates. The interval of the grid represented in the grid map 800, the scale of the distance to the actual object, and the like can be arbitrarily determined according to the specifications of the sensor mounted on the vehicle or the device that generates the contour of the stationary target, or as needed.

[0106] 8A, grid map 800 may include an indication of the host vehicle and one or more radar points. A device for generating contours of stationary targets may display detected radar points using the grids included in grid map 800 as coordinates with respect to the host vehicle. In other words, since the radar points indicate distance information to an object, the relative positions of the detected radar points may be expressed in grid map 800.

[0107] The radar points represented in the grid map 800 may include associated radar points and non-associated radar points. With reference to Figure 8A, one or more associated radar points and one or more non-associated radar points are shown.

[0108] 8A, the relevant radar points may be radar points that are assigned to a particular fusion track and that have been updated to cumulative points, i.e., in this disclosure, a device that generates stationary target contours may map radar points associated with a fusion track as relevant radar points in the generated grid map 800.

[0109] In contrast, in FIG. 8A, one or more non-associated radar points may be radar points that are not associated with a fusion track at all, i.e., radar points that are not assigned to a fusion track.

[0110] 8A, the multiple related radar points are shown clustered into two groups, each of which may correspond to a separate object. That is, in the illustrated example, grid map 800 includes information about two objects detected as radar points, with the group of related radar points clustered on the left corresponding to a first fusion track and the group of related radar points clustered on the right corresponding to a second fusion track.

[0111] In this disclosure, a device for generating contours of stationary targets can detect the contours based on relevant radar points mapped onto grid map 800.

[0112] Referring to FIG. 8B, a first contour 810 is shown detected based on radar points for a first fusion track among relevant radar points mapped onto the grid map 800.

[0113] 8B, the stationary target contour generating device can apply a contour detection algorithm to the accumulated and mapped associated radar points. In other words, the stationary target contour generating device can apply a contour detection algorithm to the radar points related to the first fusion track to detect a first contour 810. For example, the algorithm can be a convex hull algorithm.

[0114] Meanwhile, in one embodiment, the apparatus for generating a contour of a stationary target may remove radar points corresponding to noise from among the mapped relevant radar points. Radar points corresponding to noise are radar points corresponding to a specific fusion track, unlike non-relevant radar points, and may refer to points that are relevant radar points but do not reflect information of the actual fusion track due to measurement errors, temporary obstacles, etc. Therefore, the apparatus for generating a contour of a stationary target of the present disclosure may accurately generate a contour by removing radar points corresponding to noise.

[0115] Referring to FIG. 8C, a second contour 820 is shown detected based on radar points for a second fusion track among the relevant radar points mapped onto the grid map 800.

[0116] 8C, the apparatus for generating a contour of a stationary target may detect a second contour 820 for radar points related to the second fusion track, but may exclude radar points corresponding to noise 830. That is, in the illustrated example, the apparatus for generating a contour of a stationary target may determine that radar points corresponding to noise 830 are points that do not reflect information of the second fusion track, and may detect the second contour 820 after removing the radar points corresponding to noise 830.

[0117] In one embodiment, the apparatus for generating the contour of a stationary target can use a grid map to determine radar points that correspond to noise. For example, the apparatus for generating the contour of a stationary target can determine that a particular radar point is a radar point that corresponds to noise if there are no other radar points around the particular radar point. Whether or not there are other radar points around the particular radar point can be determined based on the grid map. For example, the criterion can be whether there are other radar points within a critical distance based on the grid map above, below, to the left, or to the right of the particular radar point. For example, the critical distance can be twice the length of one side of the grid.

[0118] In the present disclosure, a stationary target contour generating device can generate a stationary target contour based on the detected contour.

[0119] In the present disclosure, the device that generates the contour of a stationary target can control the traveling of the host vehicle or generate information for the traveling of the host vehicle based on the generated contour.

[0120] For example, the device for generating the contour of a stationary target may determine a driving path to avoid one or more stationary targets based on the contour of the stationary target. For example, the device for generating the contour of a stationary target may determine to change the driving path when a target is present on an existing driving path of the host vehicle based on the contour of the stationary target. For example, the device for generating the contour of a stationary target may determine in which lane the target is stopped based on the contour of the stationary target and determine a driving method (e.g., overtaking) of the host vehicle.

[0121] In one embodiment, the device for generating the contour of the stationary target can determine a closest point based on the generated contour. The closest point can mean a point on the generated contour that is closest to the host vehicle. The closest point can include information about a closest distance to the host vehicle on the surface of the object. In one embodiment, the device for generating the contour of the stationary target can control or generate information for the host vehicle's travel based on the closest point.

[0122] FIG. 9 is a flow diagram illustrating a method for acquiring a position of a stationary target according to one embodiment.

[0123] The operations shown in Fig. 9 can be executed by the device for acquiring the position of the stationary target described above. Specifically, the operations shown in Fig. 9 can be executed by a processor included in the device for acquiring the position of the stationary target described above.

[0124] In step 910, a device that acquires the position of a stationary target can generate a fusion track based on data collected from the radar and the camera.

[0125] In one embodiment, step 910 may include detecting one or more radar-based objects based on data collected from the radar.

[0126] In one embodiment, step 910 may include detecting one or more camera-based objects based on data collected from the camera.

[0127] In one embodiment, step 910 may include determining objects associated with each other from among one or more radar-based objects and one or more camera-based objects to generate a fusion track.

[0128] In one embodiment, determining the objects relative to each other may be based on the distance from the ego vehicle to the radar-based object and the distance from the ego vehicle to the camera-based object.

[0129] In step 920, the device that acquires the position of the stationary target may determine whether the fusion track is stationary.

[0130] In step 930, a device for acquiring a position of a stationary target may collect radar points for the fusion track in response to the fusion track being stationary.

[0131] In one embodiment, step 930 may include determining radar points assigned to the fusion truck from among the collected data.

[0132] In one embodiment, step 930 may include updating the cumulative points for the fusion track based on the radar points assigned to the fusion track.

[0133] In one embodiment, the number of radar points that the accumulated points for a fusion track can include may be predetermined.

[0134] In one embodiment, updating the accumulated points for the fusion track may include compensating the previous accumulated points for the distance traveled by the ego vehicle since the previous update.

[0135] In step 940, the center point of the target may be obtained based on the collected radar points.

[0136] In one embodiment, step 940 may include generating a grid map based on data collected from the radar and the camera.

[0137] In one embodiment, step 940 may include mapping radar points for the fusion track onto a grid map.

[0138] In one embodiment, step 940 may include determining a target tile, which may consist of one or more tiles that contain mapped radar points.

[0139] In one embodiment, step 940 may include obtaining corner points of the target tile.

[0140] In one embodiment, step 940 may further include determining a center point of the target based on the corner points.

[0141] In one embodiment, the method for acquiring a position of a stationary target may further include initializing the accumulation points in response to the fusion track being non-stationary.

[0142] FIG. 10 is a flow diagram illustrating a method for generating a contour of a stationary target according to one embodiment.

[0143] The operations shown in Fig. 10 may be performed by the apparatus for generating a contour of a stationary target described above. Specifically, the operations shown in Fig. 10 may be performed by a processor included in the apparatus for generating a contour of a stationary target described above.

[0144] In step 1010, a stationary target contour generating device can generate a fusion track based on data collected from the radar and the camera.

[0145] In one embodiment, step 1010 may include detecting one or more radar-based objects based on data collected from the radar.

[0146] In one embodiment, step 1010 may include detecting one or more camera-based objects based on data collected from the camera.

[0147] In one embodiment, step 1010 may include determining objects associated with each other from among one or more radar-based objects and one or more camera-based objects to generate a fusion track.

[0148] In one embodiment, determining the objects relative to each other may be based on the distance from the ego vehicle to the radar-based object and the distance from the ego vehicle to the camera-based object.

[0149] In step 1020, the stationary target contour generating device may determine whether the fusion track is stationary.

[0150] In step 1030, the stationary target contour generating device may collect radar points for the fusion track in response to the fusion track being stationary.

[0151] In one embodiment, step 1030 may include determining radar points assigned to the fusion truck from among the collected data.

[0152] In one embodiment, step 1030 may include updating the cumulative points for the fusion track based on the radar points assigned to the fusion track.

[0153] In one embodiment, the number of radar points that the accumulated points for a fusion track can include may be predetermined.

[0154] In one embodiment, updating the accumulated points for the fusion track may include compensating the previous accumulated points for the distance traveled by the ego vehicle since the previous update.

[0155] In step 1040, a target contour may be generated based on the collected radar points.

[0156] In one embodiment, step 1040 may include generating a grid map based on data collected from the radar and the camera.

[0157] In one embodiment, step 1040 may include mapping radar points for the fusion track onto a grid map.

[0158] In one embodiment, step 1040 may include detecting contours based on the mapped radar points.

[0159] In one embodiment, step 1040 may further include removing radar points that correspond to noise from among the mapped radar points.

[0160] In one embodiment, detecting the contour may include applying a convex hull algorithm to the mapped radar points.

[0161] In one embodiment, the method for generating a stationary target contour may further include initializing the accumulation points in response to the fusion track being non-stationary.

[0162] In one embodiment, the method for generating a stationary target contour may further include determining a closest point based on the generated target contour.

[0163] In one embodiment, the method for generating a contour of a stationary target may further include controlling navigation of the ego-vehicle based on the closest point.

[0164] FIG. 11 is a block diagram illustrating an apparatus according to one embodiment.

[0165] The device according to one embodiment of FIG. 11 may be a device for acquiring the position of a stationary target or a device for generating the contour of a stationary target as described above.

[0166] 11, a device 1100 may include a communication unit 1110, a processor 1120, and a DB 1130. Only components related to the embodiment are shown in the device 1100 in FIG. 11. Therefore, a person having ordinary skill in the art would understand that the device 1100 may further include other general-purpose components in addition to the components shown in FIG.

[0167] The communication unit 1110 may include one or more components that enable wired / wireless communication with an external server or device. For example, the communication unit 1110 may include at least one of a short-range communication unit (not shown), a mobile communication unit (not shown), and a broadcast receiving unit (not shown).

[0168] The DB 1130 is hardware that stores various data processed in the device 1100, and may store programs for processing and controlling the processor 1120. The DB 1130 may store payment information, user information, and the like.

[0169] DB1130 may include dynamic random access memory (DRAM), random access memory (RAM) such as static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), CD-ROM, Blu-ray or other optical disk storage, hard disk drive (HDD), solid state drive (SSD), or flash memory.

[0170] The processor 1120 controls the overall operation of the device 1100. For example, the processor 1120 may generally control an input unit (not shown), a display (not shown), a communication unit 1110, a DB 1130, etc. by executing a program stored in a DB 1130. The processor 1120 may generally control the operation of the device 1100 by executing a program stored in a DB 1130.

[0171] The processor 1120 may control at least a portion of the operation of the apparatus 1100 described above in FIGS.

[0172] The processor 1120 may be implemented using at least one of ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors, and other electrical units for performing functions.

[0173] In one embodiment, the device 1100 may be a mobile electronic device. For example, the device 1100 may be a smartphone, a tablet PC, a PC, a smart TV, a PDA (personal digital assistant), a laptop, a media player, a navigation device, a camera-equipped device, and other mobile electronic devices. The device 1100 may also be a wearable device, such as a watch, glasses, a headband, or a ring, that has a communication function and a data processing function.

[0174] In other embodiments, the apparatus 1100 may be an electronic device that is integrated into a vehicle, for example, the apparatus 1100 may be an electronic device that is inserted into a vehicle after the manufacturing process for tuning.

[0175] In yet another embodiment, the device 1100 may be a server located outside the vehicle. The server may be realized by a computer device or multiple computer devices that communicate over a network to provide instructions, codes, files, content, services, etc. The server may receive data required to determine the vehicle's travel route from a device installed in the vehicle, and may determine the vehicle's travel route based on the received data.

[0176] In yet other embodiments, the processes executed by the apparatus 1100 may be executed at least in part by a mobile electronic device, an electronic device integrated into a vehicle, and a server located outside the vehicle.

[0177] The embodiments according to the present invention may be realized in the form of a computer program executable by various components on a computer, and such a computer program may be recorded on a computer readable medium, including magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program instructions, such as ROMs, RAMs, flash memories, and the like.

[0178] On the other hand, the computer program may be one specially designed and constructed for the present invention, or it may be one that is well known and available to those skilled in the art of computer software. Examples of computer programs include not only machine code, such as that produced by a compiler, but also high-level language code that is executed by a computer using an interpreter or the like.

[0179] According to one embodiment, the methods according to various embodiments of the present disclosure can be provided in a computer program product. The computer program product can be traded between sellers and buyers as a commodity. The computer program product can be distributed in the form of a machine-readable storage medium (e.g., a compact disc read only memory (CD-ROM)) or can be distributed in the form of an application store (e.g., the Play Store). TM) or directly between two user devices. In the case of online distribution, at least a part of the computer program product may be at least temporarily stored or temporarily generated on a machine-readable storage medium, such as a memory of a manufacturer's server, an application store's server, or an intermediary server.

[0180] Unless there is an explicit order description or a contrary description regarding the steps constituting the method according to the present invention, the steps can be performed in any suitable order. The present invention is not necessarily limited to the order of the steps described above. The use of all examples or exemplary terms (such as, for example, etc.) in the present invention is merely for the purpose of explaining the present invention in detail, and the scope of the present invention is not limited by the examples or exemplary terms unless limited by the claims. In addition, those skilled in the art will understand that various modifications, combinations and changes can be made within the scope of the claims or their equivalents according to design conditions and factors.

[0181] Therefore, the concept of the present invention should not be limited to the above-described embodiments, and all scopes equivalent to or modified equivalently to the scope of the attached claims, as well as the scope of the present invention, fall within the scope of the concept of the present invention.

Claims

1. 1. A method for acquiring a position of a stationary target, comprising: generating a fusion track based on data collected from the radar and the camera; determining whether the fusion truck is stationary; collecting radar points related to the fusion truck in response to the fusion truck being stationary; and obtaining a center point of a target based on the collected radar points; The step of acquiring a center point of the target includes: generating a grid map including a grid forming tiles based on data collected from the radar and the camera; mapping radar points for the fusion track onto the grid map; generating a target tile, which is a minimum rectangle including all radar points assigned to the fusion track, in units of the tile; obtaining a corner point of the target tile; determining a center point of the target based on the corner points; method.

2. The step of generating the fusion track comprises: detecting one or more radar-based objects based on data collected from the radar; detecting one or more camera-based objects based on data collected from the camera; and determining associated objects from among the one or more radar-based objects and the one or more camera-based objects to generate a fusion track.

3. Determining the interrelated objects includes: The method of claim 2 , based on a radar-based distance from the ego-vehicle to the object and a camera-based distance from the ego-vehicle to the object.

4. The step of collecting radar points for the fusion truck comprises: determining radar points assigned to the fusion truck from among the collected data; and updating accumulated points for the fusion track based on radar points assigned to the fusion track.

5. The method of claim 4 , wherein the number of radar points that the accumulated points for the fusion track can include is predetermined.

6. The step of updating the accumulated points for the fusion track includes:

5. The method of claim 4, including compensating the previous accumulated points for the distance traveled by the ego vehicle since the previous update.

7. The method comprises: The method of claim 4 , further comprising the step of initializing the accumulation points in response to the fusion track being non-stationary.

8. The method comprises: The method of claim 1 , further comprising the step of controlling travel of the host vehicle based on the center point of the target.

9. The method comprises: The method of claim 1 , further comprising generating a target profile based on the collected radar points.

10. The step of generating a contour of the target comprises: generating a grid map based on data collected from the radar and the camera; mapping radar points for the fusion track onto the grid map; and detecting contours based on the mapped radar points.

11. The step of generating a contour of the target comprises: The method of claim 10 , further comprising removing radar points that correspond to noise from among the mapped radar points.

12. The step of detecting the contour comprises: The method of claim 10 comprising applying a Convex Hull Algorithm to the mapped radar points.

13. The method comprises: determining a closest point based on the generated target contour; and controlling travel of the host vehicle based on the closest point.

14. 1. An apparatus for acquiring the position of a stationary target, comprising: a memory having at least one program stored therein; a processor that operates by executing the at least one program; The processor, Generates fusion tracks based on data collected from radar and cameras, determining whether the fusion track is stationary; collecting radar points related to the fusion truck in response to the fusion truck being stationary; Obtaining a center point of a target based on the collected radar points; Obtaining the center point of the target generating a grid map including a grid forming tiles based on data collected from the radar and the camera; mapping radar points for the fusion track onto the grid map; generating a target tile in units of the tile, the target tile being the smallest rectangle that includes all radar points assigned to the fusion track; Obtaining a corner point of the target tile; determining a center point of the target based on the corner points; Including, Device.

15. A computer-readable recording medium having recorded thereon a program for executing the method according to claim 1 on a computer.

Images