Apparatus for acquiring surrounding information of vehicle and control method thereof

Abstract

Provided is an apparatus for acquiring surrounding information of a vehicle and a control method thereof, the apparatus including a camera configured to acquire a complete image of at least one surrounding vehicle, and a controller configured to derive at least one of coordinates of a wheel image region and coordinates of a front and rear image region included in a complete image region, and determine distance information from the vehicle to the at least one surrounding vehicle based on a relative positional relationship between the complete image region and at least one of the wheel image region coordinates and the front and rear image region coordinates.

Description

Technical Field

[0001] This disclosure relates to a vehicle and a control method thereof for acquiring information about surrounding vehicles through image recognition. Background Technology

[0002] Autonomous driving technology is a technology that allows vehicles to operate autonomously without the need for a driver to control the brakes, steering wheel, or accelerator pedal, by understanding road conditions.

[0003] Autonomous driving technology is a core technology for realizing intelligent vehicles. It includes systems such as Highway Driving Assist (HDA, a technology that automatically maintains distance between vehicles), Rear Side Warning (BSD, a technology that detects nearby vehicles and issues an alert when reversing), Automatic Emergency Braking (AEB, a technology that activates the braking system when a vehicle in front is not detected), Lane Departure Warning System (LDWS), Lane Keeping Assist System (LKAS, a technology that compensates for leaving the lane without a turn signal), Advanced Smart Cruise Control (ASCC, a technology that maintains a distance to other vehicles at a set speed and drives at a constant speed), Traffic Jam Assist (TJA), Parking Collision Avoidance Assist (PCA), and Autonomous Parking System (Remote Intelligent Parking Assist).

[0004] However, research is actively underway on efficient and accurate computational methods for analyzing the location of surrounding vehicles by recognizing images. Summary of the Invention

[0005] This disclosure provides a vehicle and a control method thereof, which can efficiently and accurately calculate the distance and direction of the vehicle and surrounding vehicles by using the positional relationship between the complete image of the surrounding vehicles, the wheel image and the front and rear images.

[0006] According to one aspect of this disclosure, an apparatus for acquiring information about the surroundings of a vehicle includes: a camera configured to acquire a complete image of at least one surrounding vehicle; and a controller configured to derive at least one of the coordinates of a wheel image region and the coordinates of a front and rear image region included in the complete image region, and to determine distance information from the vehicle to the surrounding vehicles based on the relative positional relationship between the complete image region and at least one of the wheel image region coordinates and the front and rear image region coordinates.

[0007] The controller can be configured to group at least one of the wheel image regions and the front and rear image regions, which are included in the full image region, into images corresponding to the surrounding vehicles.

[0008] The controller can be configured to determine an error detection when the center coordinates of at least two of the wheel image regions and the front and rear image regions are included in one of the wheel image regions and the front and rear image regions.

[0009] The controller can be configured to acquire multiple wheel images and front and rear images, and determine if an image is incorrectly detected when the front and rear image regions are provided between the coordinates of the multiple wheel image regions.

[0010] The controller can be configured to acquire multiple wheel images and front and rear images, and determine whether an error is detected by comparing the coordinate information of the multiple wheel images.

[0011] The controller can be configured to determine distance information from the vehicle to surrounding vehicles based on the intersection of the extension line of the lower center point of each of the multiple wheel image regions and the vertical extension lines of the front and rear image regions adjacent to the multiple wheel image regions when multiple wheel images are detected.

[0012] The controller can be configured to: determine a first distance corresponding to the camera's height coordinates and a second distance to the wheel image region; determine the height coordinates of the wheel image region based on the ratio of the first distance and the second distance; generate a vertical extension line of the front and rear image regions based on the height coordinates of the wheel image region; and determine distance information from the vehicle to surrounding vehicles based on the intersection of the vertical extension line with the ground.

[0013] The controller can be configured to determine distance information from the vehicle to surrounding vehicles based on the intersection of the vertical extension of the front and rear image regions near the center line of the full image region with the ground when only the full image and the front and rear images are detected.

[0014] The controller can be configured to determine distance information from the vehicle to surrounding vehicles based on the intersection of the extension line of the lower center point of the multiple wheel image regions and the lower edge line of the full image region when only the full image and multiple wheel images are detected.

[0015] The controller can be configured to determine distance information from the vehicle to surrounding vehicles based on the intersection of the extension of the center line of the wheel image region and the lower edge of the full image region when only a full image and a wheel image are detected.

[0016] The controller can be configured to determine the orientation of surrounding vehicles based on the vehicle and the detection type, which is determined based on the full image, wheel images, and front and rear images.

[0017] According to another aspect of this disclosure, a control method for acquiring information about the surroundings of a vehicle includes: acquiring a complete image of at least one surrounding vehicle; deriving at least one of the coordinates of a wheel image region and the coordinates of a front and rear image region contained in the complete image region; and determining distance information from the vehicle to the surrounding vehicles based on the relative positional relationship between the complete image region and at least one of the coordinates of the wheel image region and the coordinates of the front and rear image regions.

[0018] The method may further include grouping at least one of the wheel image regions and the front and rear image regions included in the full image region into images corresponding to the surrounding vehicles.

[0019] The method may further include: determining an error detection when the center coordinates of at least two image regions, namely the wheel image region and the front and rear image regions, are included in one of the wheel image region and the front and rear image regions.

[0020] The method may further include: acquiring multiple wheel images and front and rear images, and determining that a region of the front and rear images has been erroneously detected when the region of the front and rear images is provided between the coordinates of the multiple wheel image regions.

[0021] The method may further include: acquiring multiple wheel images and multiple front and rear images, and determining whether an error detection is made by comparing the coordinate information of the multiple wheel images.

[0022] Determining distance information from a vehicle to surrounding vehicles may include: when multiple wheel images are detected, determining the distance information from a vehicle to surrounding vehicles based on the intersection of the extension line of the lower center point of each of the multiple wheel image regions with the vertical extension lines of the front and rear image regions adjacent to the multiple wheel image regions.

[0023] Determining distance information from a vehicle to surrounding vehicles may include: determining a first distance corresponding to the camera's height coordinates and a second distance to the wheel image region; determining the height coordinates of the wheel image region based on the ratio of the first and second distances; generating vertical extension lines of the front and rear image regions based on the height coordinates of the wheel image region; and determining distance information from the vehicle to surrounding vehicles based on the intersection of the vertical extension lines with the ground.

[0024] Determining distance information from a vehicle to surrounding vehicles can include: when only the complete image and the front and rear images are detected, determining the distance information from a vehicle to surrounding vehicles based on the intersection of the vertical extension of the front and rear image regions close to the center line of the complete image region with the ground.

[0025] Determining distance information from a vehicle to surrounding vehicles can include: when only a complete image and multiple wheel images are detected, determining the distance information from a vehicle to surrounding vehicles based on the intersection of the extension line of the lower center point of the multiple wheel image regions and the lower edge line of the complete image region. Attached Figure Description

[0026] Figure 1 This is a control block diagram according to an embodiment.

[0027] Figure 2A , Figure 2B and Figure 2C This is a diagram used to explain the operation of recognizing images of surrounding vehicles according to an exemplary embodiment.

[0028] Figure 3 This is a diagram illustrating the operation of grouping images corresponding to surrounding vehicles according to an exemplary embodiment.

[0029] Figures 4 to 6 This is a diagram used to explain the operation of error detection according to an exemplary embodiment.

[0030] Figure 7 This is a diagram illustrating the operation of determining the direction of nearby vehicles based on a vehicle, according to an exemplary embodiment.

[0031] Figures 8 to 13 This is a diagram illustrating the operation of determining the distance between a vehicle and surrounding vehicles according to an exemplary embodiment.

[0032] Figure 14 This is a flowchart based on an embodiment. Detailed Implementation

[0033] Throughout the following description, the same reference numerals denote the same elements. This specification does not describe all elements of the embodiments, and there is no overlap in general content or embodiments within the scope of the exemplary embodiments to which this disclosure pertains. Terms such as “unit,” “module,” “component,” and “block” can embody either hardware or software. According to embodiments, a plurality of “units,” “modules,” “components,” and “blocks” may be implemented as a single component, or a single “unit,” “module,” “component,” and “block” may comprise multiple components.

[0034] It should be understood that when an element is referred to as "connected" to another element, it can be directly or indirectly connected to the other element, where indirect connection includes "connection via wireless communication network".

[0035] Furthermore, when a portion "contains" or "includes" an element, unless there is a specific description to the contrary, that portion may further include other elements, but does not exclude other elements.

[0036] Throughout the specification, when a component is referred to as being "on" another component, this includes not only cases where the component is in contact with the other component, but also cases where the other component exists between the two components.

[0037] The terms "first" and "second" are used to distinguish one component from other components, and the component is not limited by the terms mentioned above.

[0038] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0039] The identification code is used in each step for ease of interpretation, and the identification code does not describe the order of each step, and the execution of each step may differ from the specified order unless the specific sequence is explicitly stated in the context.

[0040] The operating principles and embodiments of this disclosure will now be described with reference to the accompanying drawings.

[0041] Figure 1 This is a control block diagram according to an embodiment.

[0042] Reference Figure 1 According to an exemplary embodiment, the vehicle 1 may include an image recognizer 200, a controller 100, and a driver 300.

[0043] Image recognition device 200 can be provided as a camera.

[0044] The camera can have multiple channels and capture images of the area around the vehicle.

[0045] According to an embodiment, the camera can be positioned around the vehicle to perform surround view monitor (SVM) operation.

[0046] The camera may include a charge-coupled device (CCD) camera 100 or a CMOS color image sensor installed in the vehicle 1. Here, both CCD and CMOS refer to sensors that convert light that has passed through the lens of the camera 100 into electrical signals and store those electrical signals.

[0047] The camera can capture a complete image of at least one surrounding vehicle positioned around the vehicle.

[0048] A complete image can refer to an image that includes all parts of the surrounding vehicle.

[0049] In addition, the vehicle can acquire front and rear images of surrounding vehicles.

[0050] The controller 100 can export at least one of the coordinates of the wheel image region and the coordinates of the front and rear image regions included in the full image region.

[0051] That is, images of the vehicle's wheels or front and rear can be included in the complete vehicle image.

[0052] A wheel image refers to the wheels of a vehicle.

[0053] Front and rear images refer to the front or rear of a vehicle, and may also refer to images excluding the sides of the vehicle.

[0054] At the same time, the controller can derive coordinate information by acquiring each image and converting each image into coordinate system information.

[0055] The controller can determine distance information from the vehicle to surrounding vehicles based on the relative positional relationship between the complete image region and at least one of the wheel image region coordinates and the front and rear image region coordinates.

[0056] The controller can group at least one of the wheel image regions and the front and rear image regions, which are included in the full image region, into images corresponding to the surrounding vehicles.

[0057] In other words, the controller can identify vehicles by matching the wheel images and front or rear images contained in the full image with surrounding vehicles.

[0058] If the center coordinates of at least two of the wheel image region and the front and rear image region are included in one of the wheel image region and the front and rear image region, the controller can determine that the image has been detected incorrectly.

[0059] Error detection is the process by which the controller determines that an image has been incorrectly identified. If it is determined that an image has been incorrectly detected, the controller can exclude that image from the operation.

[0060] The controller acquires multiple wheel images and front and rear images of surrounding vehicles, and when the front and rear image regions of surrounding vehicles are provided between the coordinates of the multiple wheel image regions of surrounding vehicles, the controller can determine that the image has been incorrectly detected.

[0061] The controller acquires multiple wheel images and front and rear images of surrounding vehicles, and compares the coordinate information of the wheel image regions of multiple surrounding vehicles to determine whether an error has been detected.

[0062] When multiple wheel images of surrounding vehicles are detected, the controller can determine the distance information from the vehicle to the surrounding vehicles based on the intersection of the extension line of the lower center point of each of the multiple wheel image regions of the surrounding vehicles and the vertical extension line of the front and rear image regions of the surrounding vehicles that are close to the wheel image regions of the multiple surrounding vehicles.

[0063] The controller can determine the intersection of the extended lines as the closest point between the vehicle and surrounding vehicles, and determine the distance between the vehicle and surrounding vehicles based on this closest point.

[0064] When the image area of ​​the wheel of one of the surrounding vehicles is detected, the controller can determine a first distance corresponding to the height coordinates of the camera and a second distance to the image area of ​​the wheel of the surrounding vehicle.

[0065] The first distance can be defined as the intersection of the ground and the extension of the line connecting the camera's height coordinates and the height coordinates of the wheel image area.

[0066] The controller can determine the height coordinates of the wheel image area of ​​surrounding vehicles based on the ratio of the first distance to the second distance.

[0067] The controller generates vertical extension lines of the front and rear image regions of the surrounding vehicles based on the height coordinates of the wheel image regions of the surrounding vehicles, and determines the distance information from the vehicle to the surrounding vehicles based on the intersection of the vertical extension lines with the ground.

[0068] When only full images of surrounding vehicles and front and rear images of surrounding vehicles are detected, the controller can determine the distance information from the vehicle to the surrounding vehicles based on the intersection of the ground with the vertical extension line of the front and rear image area of ​​the surrounding vehicles, which is close to the center line of the full image area of ​​the surrounding vehicles.

[0069] When only the complete image of the surrounding vehicles and multiple wheel images of the surrounding vehicles are detected, the controller can determine the distance information from the vehicle to the surrounding vehicles based on the intersection of the extension line of the lower center point of the multiple wheel image area of ​​the surrounding vehicles and the lower edge line of the complete image area of ​​the surrounding vehicles.

[0070] When only a complete image of the surrounding vehicles and an image of one wheel of the surrounding vehicles are detected, the controller can determine the distance information from the vehicle to the surrounding vehicles based on the intersection of the extension of the center line of the center line of the image area of ​​one wheel of the surrounding vehicles and the lower edge of the image area of ​​the complete image area of ​​the surrounding vehicles.

[0071] Based on complete images of surrounding vehicles, wheel images of surrounding vehicles, and front and rear images of surrounding vehicles, the controller can determine the direction of surrounding vehicles based on the vehicle itself by using the determined detection type.

[0072] Specifically, the controller can categorize surrounding vehicles into multiple types. Furthermore, directions corresponding to these types can be pre-stored, and if it is determined that a surrounding vehicle corresponds to a specific type, the direction corresponding to that type can be determined as the direction of the surrounding vehicle.

[0073] The controller can be implemented using a memory (not shown) and a processor (not shown). The memory stores data about algorithms for controlling the operation of components in the vehicle, or programs for reproducing those algorithms, while the processor uses the data stored in the memory to perform those operations. In this case, the memory and processor can be implemented as separate chips. Alternatively, the memory and processor can be implemented as a single chip.

[0074] In addition, the vehicle may include a drive unit 300.

[0075] The drive can be configured as a device capable of driving a vehicle.

[0076] According to an embodiment, the driver may include an engine and may include various components for driving the engine.

[0077] Specifically, the drive unit may include brakes and steering mechanisms, and there are no restrictions on the configuration of the devices, as long as they are configurations that enable the vehicle to drive.

[0078] The controller can drive the vehicle by controlling the driver based on the derived distance information between the vehicle and surrounding vehicles.

[0079] It can correspond to Figure 1 The performance of the vehicle components shown can be improved by adding or removing at least one component. Furthermore, those skilled in the art will readily understand that the relative positions of these components can be altered to correspond to the performance or structure of the system.

[0080] Figure 1 Each component shown refers to a software and / or hardware component, such as a field-programmable gate array (FPGA) and an application-specific integrated circuit (ASIC).

[0081] Figure 2A , Figure 2B and Figure 2C This is a diagram used to explain the operation of identifying images of nearby vehicles according to an exemplary embodiment.

[0082] The controller can detect vehicles in images using a camera.

[0083] The controller can perform image processing that identifies objects on a per-frame basis from the frames received by the camera.

[0084] Figure 2A The image A2a shows that the camera has acquired a complete image of the surrounding vehicles. The complete image refers to the overall outline of the surrounding vehicles, and the complete image area of ​​the surrounding vehicles can be derived by forming bounding boxes on the complete image of the surrounding vehicles.

[0085] Figure 2BThe operation of acquiring a wheel image of a vehicle and forming a bounding box on the wheel image W2b of the vehicle to export the wheel image region is shown.

[0086] Figure 2C The image shows front and rear views of nearby vehicles captured by a camera.

[0087] exist Figure 2C The diagram illustrates the operation of acquiring a front image (F2c) of the vehicle and forming a bounding box on the front image to derive the front and rear image regions. Such an operation can be implemented in the same way for the rear of the vehicle.

[0088] On the other hand, the images identified in these figures are merely exemplary embodiments, and there are no limitations on the form of the identified images.

[0089] Figure 3 This is a diagram illustrating the operation of grouping images corresponding to surrounding vehicles according to an exemplary embodiment.

[0090] Grouping means grouping the complete image A3 of the surrounding vehicles, the front and rear images F3 of the vehicles, and the wheel image W3 into a single object to determine the image corresponding to the surrounding vehicles.

[0091] Specifically, the controller can determine whether the front and rear image regions F3 and the wheel image region W3 are included in the image based on the detected complete vehicle image region A3.

[0092] When an object is detected, the controller can check whether the center of the object area is included in the vehicle's full image area.

[0093] When the center of each image region is within the complete image region of the vehicle, the controller can include it as a grouping element, and when it is not included, the corresponding object can be identified as an object of another vehicle.

[0094] Figure 3 The operations described herein are merely embodiments of grouping according to this disclosure, and there are no limitations in grouping complete vehicle images, wheel images, and front and rear images.

[0095] Figures 4 to 6 This is a diagram used to explain the operation of error detection according to an exemplary embodiment.

[0096] Reference Figure 4 If the center coordinates of at least two of the wheel image regions and the front and rear image regions are included in one of the wheel image regions and the front and rear image regions, the controller determines that it has been incorrectly detected.

[0097] Figure 4Specifically, this illustrates the case where the center coordinates (FP4, WP41, WP42) of each element (F4, W41, W42) detected in the complete image (A4) are contained within each other's image regions.

[0098] However, if the center coordinate FP4 of the front and rear image regions F4 is included in the wheel image regions W41 or W42, it can be determined that the objects are overlapping and the detection is a false detection.

[0099] exist Figure 4 In the image region F4, the center coordinates WP41 of the wheel image region W41 are included. In this case, the controller can determine that the corresponding object has been incorrectly detected.

[0100] Reference Figure 5 The controller acquires multiple wheel images and front and rear images of surrounding vehicles, and determines an error detection when the front and rear image regions of surrounding vehicles are provided between the coordinates of the multiple wheel image regions of surrounding vehicles.

[0101] Figure 5 This illustrates a case where, compared to the center coordinates FP5 of the preceding and following images, one of the center coordinates WP51 and WP52 of the wheel images W51 and W52 is larger than the other.

[0102] Considering the shape of the vehicle, the front and rear images F5 of the surrounding vehicles identified by the camera cannot be between the wheel images W51 and W52 within the complete image A5.

[0103] In order for the front and rear images (FP5) of the vehicle to exist between the wheel images (W51, W52) in the image, the doors on both sides of the vehicle or between the wheels must be seen simultaneously as front and rear images, so the controller identifies them as false detections.

[0104] Reference Figure 6 The controller acquires multiple wheel images and front and rear images of surrounding vehicles, and compares the coordinate information of the multiple wheel image regions of surrounding vehicles to determine whether an error has been detected.

[0105] Figure 6 This illustrates the case where the center y-coordinate of wheel image W61 is smaller than the center y-coordinate of wheel image W62. In this case, the center x-coordinate of wheel image W61 is close to the center x-coordinate of the front and rear images F6, while the center x-coordinate of wheel image W62 is not close to the center x-coordinate of the front and rear images F6.

[0106] When considering vehicle shape, based on the x-coordinates of the front and rear images (F6) within the complete image (A6) of the vehicle, the vehicle identified in the camera image is the y-coordinate of the nearest wheel image (W61) among multiple wheel images. This y-coordinate cannot be less than the y-coordinates of the other wheel images. Therefore, in this case, the controller can determine that the vehicle image has been incorrectly detected.

[0107] exist Figures 4 to 6 The error detection operations described herein are used to explain exemplary embodiments of this disclosure, and there are no limitations on the operations by which a vehicle determines whether an image of a surrounding vehicle has been incorrectly detected.

[0108] Figure 7 This is a diagram illustrating, according to an exemplary embodiment, an operation for determining the direction of a nearby vehicle based on a vehicle as reference P71.

[0109] The controller can determine the orientation of surrounding vehicles based on the closest point between the vehicle and the surrounding vehicles, which is determined based on the operation described later.

[0110] That is, in Figure 7 In this process, the vehicle's position P71 can be determined, and the directional information between the vehicle and surrounding vehicles can be derived by considering the nearest point P72 of the surrounding vehicle O and the vehicle's position.

[0111] The controller can determine the direction of surrounding vehicles, and has already determined whether an error detection has occurred for the surrounding vehicles.

[0112] According to one embodiment, the camera can be provided as a surround view monitor (SVM) camera. The controller can determine the position of the surrounding vehicle O in the image received by the camera.

[0113] For each detection type, the controller can determine the vehicle's orientation based on front and rear images and wheel images of surrounding vehicles as seen from the vehicle.

[0114] Reference Figure 7 When an image view is obtained from the camera, and when a vehicle (i.e., a surrounding vehicle O) is detected as a result of pairing, the coordinates at the lower center P72 of the surrounding vehicle image area can be derived. The controller can then determine the directional information between the vehicle and the surrounding vehicles based on the corresponding coordinates.

[0115] In addition, the controller can determine the direction of surrounding vehicles based on the detection type and the vehicle itself. The detection type is determined based on the complete image of the surrounding vehicles, the wheel images of the surrounding vehicles, and the front and rear images of the surrounding vehicles.

[0116] Once the image is acquired, the vehicle's orientation can be estimated by grouping the result elements. By combining the vehicle position angle θ and orientation estimates for each detection type, the position and orientation of another vehicle compared to that vehicle can be determined.

[0117] Figure 7 The operation of determining direction described herein is merely an embodiment of this disclosure, and there are no limitations on the operation of determining directional information about surrounding vehicles based on the vehicle.

[0118] Figures 8 to 13 This is a diagram illustrating the operation of determining the distance between a vehicle and surrounding vehicles according to an exemplary embodiment.

[0119] Reference Figure 8 When multiple wheel images W81 and W82 of surrounding vehicles are detected, the controller can determine the distance information from the vehicle to the surrounding vehicles based on the intersection point (P83) of the extension line of the lower center point (P81, P82) of each of the multiple wheel image regions W81 and W82 of the surrounding vehicles and the vertical extension line of the front and rear image regions of the surrounding vehicles that are close to the wheel image region of the surrounding vehicles.

[0120] Specifically, the controller can determine point P83 as the location of another vehicle, i.e. the nearest point, and determine the distance information between the vehicle and surrounding vehicles.

[0121] Reference Figure 9 When the wheel image area of ​​one of the surrounding vehicles is detected, the controller can determine a first distance L91 from R9 corresponding to the camera's height coordinate C9, and determine a second distance L92 from the wheel image area HW9 of the surrounding vehicles.

[0122] The controller can determine the height coordinates of the wheel image area of ​​surrounding vehicles based on the ratio of the first distance L91 and the second distance L92.

[0123] The 2D image coordinates of the top / bottom center of the detected wheel image can be converted into 3D spatial coordinates based on the ground. However, when the controller converts the 2D coordinates on the image into 3D coordinates in real-world space, the height value cannot be estimated.

[0124] The controller can create spatial coordinates based on the ground.

[0125] By ignoring the upper center coordinate height value of the wheel image area HW9, the controller can return the 3D coordinates of the point R9 where the line segment connecting the camera C9 and the wheel image area HW9 meets the ground in the image.

[0126] Since the corresponding coordinates do not consider the coordinate transformation of the height value, the upper coordinates of the wheel image HW9 below can be converted to the far point.

[0127] Subsequently, the controller can use the lower center of the wheel image HW9 and the 3D spatial coordinate length values ​​of R9, as well as the camera mounting height value (c), to estimate the height of the wheel image in a proportional manner.

[0128] Refer to together Figure 9 and Figure 10 The controller generates a vertical extension line of the front and rear image areas F10 of the surrounding vehicles based on the height coordinates of the wheel image area W10 of the surrounding vehicles, and determines the intersection point P10 of the vertical extension line with the ground as the nearest point, and determines the distance information from the vehicle to the surrounding vehicles based on this nearest point.

[0129] Reference Figure 11 The controller can detect only the complete image of the surrounding vehicles and the front and rear images of the surrounding vehicles.

[0130] The controller can determine the nearest point as the intersection point P112 between the ground and the vertical extension line L11 of the front and rear image areas F11 of the surrounding vehicles, which is close to the center line P112 of the complete image area of ​​the surrounding vehicles.

[0131] The controller can determine distance information from the vehicle to surrounding vehicles based on the nearest point.

[0132] Reference Figure 12 When only the complete image A12 of the surrounding vehicles and multiple wheel images W121 and W122 of the surrounding vehicles are detected, the controller determines the nearest point as the intersection (P123) of the extension line of the lower center point P121 and P122 of the wheel image area of ​​the surrounding vehicles and the lower edge line of the complete image area A12 of the surrounding vehicles. Based on this, the controller can determine the distance information from the vehicle to the surrounding vehicles.

[0133] Reference Figure 13 When only the complete image of the surrounding vehicles and only one wheel image of the surrounding vehicles are detected, the controller determines the intersection (P13) of the extension line (L13) of the center line of the wheel image area (W13) and the lower edge line (P13) of the complete image area of ​​the surrounding vehicles as the nearest point, and determines the distance information from the vehicle to the surrounding vehicles accordingly.

[0134] Figures 8 to 13 The operations described herein are merely embodiments for deriving distance information of this disclosure, and there are no limitations on the operations for deriving the nearest point of this disclosure.

[0135] Figure 14 This is a flowchart based on an embodiment.

[0136] The vehicle can obtain a complete image of the surrounding vehicles through the camera (1001).

[0137] In addition, the controller can export at least one of the wheel image region and the front and rear image regions (1002).

[0138] The controller can group the complete image, wheel image, and front and rear images (1003).

[0139] The controller can determine whether the image was detected incorrectly. If it was not detected incorrectly, distance information (1004, 1005) can be determined based on the points determined by the relative positional relationships of the images.

[0140] On the other hand, the disclosed exemplary embodiments can be implemented in the form of a recording medium containing stored instructions executable by a computer. The instructions can be stored in the form of program code, and when executed by a processor, the instructions can generate program modules to perform the operations of the disclosed exemplary embodiments. The recording medium can be implemented as a computer-readable recording medium.

[0141] Computer-readable recording media include various recording media in which instructions that can be decoded by a computer are stored. For example, read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disk, flash memory, optical data storage devices, etc., may be present.

[0142] As described above, exemplary embodiments of the disclosure have been described with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure have been shown and described, those skilled in the art will understand that changes may be made to these embodiments without departing from the principles and spirit of the present disclosure, the scope of which is defined in the claims and their equivalents.

[0143] The vehicle and control method according to the exemplary embodiments can efficiently and accurately calculate the distance and direction of the vehicle and surrounding vehicles by using the positional relationship of complete images of surrounding vehicles, wheel images and front and rear images.

Claims

1. An apparatus for acquiring surrounding information of a vehicle, comprising: a camera configured to acquire a complete image of at least one surrounding vehicle; a controller configured to: derive at least one of coordinates of a wheel image region and coordinates of a front-rear image region, the wheel image region and the front-rear image region being included in a complete image region, determine distance information from the vehicle to the at least one surrounding vehicle based on a relative positional relationship between the complete image region and the at least one of the coordinates of the wheel image region and the coordinates of the front-rear image region, wherein the controller is configured to determine that the complete image is detected in error when center coordinates of at least two of the wheel image region and the front-rear image region are included in one of the wheel image region and the front-rear image region.

2. The apparatus of claim 1, wherein, the controller is configured to group at least one of the wheel image region and the front-rear image region as an image corresponding to the at least one surrounding vehicle.

3. The apparatus of claim 1, wherein, the controller is configured to acquire a plurality of wheel images and a plurality of front-rear images, and determine that the complete image is detected in error when the front-rear image region is located between coordinates of the wheel image region.

4. The apparatus of claim 1, wherein, the controller is configured to acquire a plurality of wheel images and a plurality of front-rear images, and determine whether it is a false detection by comparing coordinate information of a plurality of the wheel images.

5. The apparatus of claim 1, wherein, when a plurality of wheel images are detected, the controller is configured to determine the distance information from the vehicle to the at least one surrounding vehicle based on an intersection between an extension line of a line connecting lower center points of each of a plurality of the wheel image regions and a vertical extension line of the front-rear image region adjacent to the plurality of the wheel image regions.

6. The apparatus of claim 1, wherein, the controller is configured to: determine a first distance corresponding to a height coordinate of the camera and a second distance of the wheel image region, determine a height coordinate of the wheel image region based on a ratio of the first distance and the second distance, generate a vertical extension line of the front-rear image region based on the height coordinate of the wheel image region, and determine the distance information from the vehicle to the at least one surrounding vehicle based on an intersection of the vertical extension line and a ground surface.

7. The apparatus of claim 1, wherein, the controller is configured to determine the distance information from the vehicle to the at least one surrounding vehicle based on an intersection of a vertical extension line of the front-rear image region adjacent to a center line of the complete image region and a ground surface when only the complete image region and the front-rear image region are detected.

8. The apparatus of claim 1, wherein, when only the complete image region and a plurality of wheel image regions are detected, the controller is configured to determine distance information from the vehicle to the at least one surrounding vehicle based on an intersection between an extension line of a line connecting lower center points of the plurality of the wheel image regions and a lower edge line of the complete image region.

9. The apparatus of claim 1, wherein, When only the complete image region and one wheel image region are detected, the controller is configured to determine an intersection of an extension line of a center line of the one wheel image region and a lower edge line of the complete image region as a nearest point, and determine the distance information from the vehicle to the at least one surrounding vehicle based on the nearest point.

10. The apparatus of claim 1, wherein, The controller is configured to determine a direction of the at least one surrounding vehicle based on the vehicle and the complete image region, the wheel image region, and the front-rear image region.

11. A control method for acquiring surrounding information of a vehicle, comprising: acquiring a complete image of at least one surrounding vehicle by a camera; deriving, by a controller, at least one of a coordinate of a wheel image region and a coordinate of a front-rear image region included in a complete image region; determining, by the controller, distance information from the vehicle to the at least one surrounding vehicle based on a relative positional relationship between the at least one of the coordinate of the wheel image region and the coordinate of the front-rear image region and the complete image region; wherein the method further comprises determining that the complete image is erroneously detected when center coordinates of at least two of the wheel image region and the front-rear image region are included in one of the wheel image region and the front-rear image region.

12. The method of claim 11, further comprising: grouping at least one of the wheel image region and the front-rear image region included in the complete image region as an image corresponding to the at least one surrounding vehicle.

13. The method of claim 11, further comprising: acquiring a plurality of wheel images and a plurality of front-rear images; and wherein determining that the complete image is erroneously detected when the front-rear image region is located between coordinates of a plurality of the wheel image regions.

14. The method of claim 11, further comprising: acquiring a plurality of wheel images and a plurality of front-rear images; and wherein determining whether the erroneous detection of the complete image has occurred comprises comparing coordinate information of the plurality of wheel images. Determining the distance information from the vehicle to the at least one surrounding vehicle comprises, when a plurality of wheel image regions are detected, determining the distance information from the vehicle to the at least one surrounding vehicle based on an intersection between an extension line of a line connecting lower center points of each of the plurality of wheel image regions and a vertical extension line of the front-rear image region adjacent to the plurality of wheel image regions. Determining the distance information from the vehicle to the at least one surrounding vehicle comprises:

15. The method of claim 11, wherein, determining a first distance corresponding to a height coordinate of the camera and a second distance of the wheel image region; 16. The method of claim 11, wherein, determining a height coordinate of the wheel image region based on a ratio of the first distance and the second distance; generating a vertical extension line of the front-rear image region based on the height coordinate of the wheel image region; and determining the distance information from the vehicle to the at least one surrounding vehicle based on an intersection of the vertical extension line and a ground surface. ​ ​ 17. The method of claim 11, wherein, Determining the distance information from the vehicle to the at least one surrounding vehicle includes, when only the full image and front-rear images are detected, determining the distance information from the vehicle to the at least one surrounding vehicle based on an intersection of a vertical extension line of the front-rear image region adjacent to a center line of the full image region and a ground surface.

18. The method of claim 11, wherein, Determining the distance information from the vehicle to the at least one surrounding vehicle includes, when only the full image and a plurality of wheel images are detected, determining the distance information from the vehicle to the at least one surrounding vehicle based on an intersection of an extension line of a line connecting lower center points of a plurality of the wheel image regions and a lower edge line of the full image region.

Images