Method, device and equipment for confirming passable area and automobile

Abstract

The invention relates to a passable area confirmation method, device and equipment and an automobile. The method comprises the steps that image information in front of the automobile is acquired; obtaining an initial passable area of the vehicle according to the image information, and obtaining feature information of at least one target obstacle according to the image information; wherein the target obstacle is an obstacle invading the initial passable area; and correcting the initial passable area according to the feature information of the at least one target obstacle to obtain the passable area of the vehicle. According to the invention, the problem of inaccurate confirmation of the passable area in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to a method, a device, a equipment and a car for confirming a passable area. Background Art

[0002] With the development of vehicle technology, the emergence of drivable areas provides a basis for safe driving of vehicles and autonomous driving of vehicles.

[0003] In the prior art, the passable area of ​​a vehicle is determined directly through the attribute information of the pixels in the image.

[0004] However, the methods in the prior art may lead to the problem of inaccurate confirmation of the drivable area. Summary of the invention

[0005] One of the objects of the present invention is to provide a method for confirming a passable area to solve the problem of inaccurate confirmation of a passable area in the prior art; the second object is to provide a device for confirming a passable area; the third object is to provide an electronic device; the fourth object is to provide a computer-readable storage medium; the fifth object is to provide a computer program product; and the sixth object is to provide a vehicle.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] A method for confirming a passable area, comprising:

[0008] Acquire image information in front of the vehicle;

[0009] Acquire an initial passable area of ​​the vehicle according to the image information, and acquire characteristic information of at least one target obstacle according to the image information; wherein the target obstacle is an obstacle that invades the initial passable area;

[0010] The initial traversable area is corrected according to the characteristic information of the at least one target obstacle to obtain the traversable area of ​​the vehicle.

[0011] According to the above technical means, by acquiring image information in front of the vehicle, acquiring the initial passable area of ​​the vehicle based on the image information, acquiring characteristic information of at least one target obstacle based on the image information, and correcting the initial passable area based on the characteristic information of at least one target obstacle, the passable area of ​​the vehicle is obtained, wherein, on the basis of acquiring the initial passable area of ​​the vehicle based on the image information, the initial passable area is corrected based on the characteristic information of at least one target obstacle obtained, thereby improving the accuracy of confirmation of the passable area.

[0012] Further, according to the characteristic information of the at least one target obstacle, the initial passable area is corrected to obtain the passable area of ​​the vehicle, including: for each of the target obstacles, according to the characteristic information of the target obstacle, determining the characteristic coordinates of at least one target obstacle; wherein the characteristic coordinates of the target obstacle are the coordinates of the preset position of the target obstacle in the vehicle coordinate system; from the characteristic coordinates of the at least one target obstacle, determining one or more target characteristic coordinates, and according to the target characteristic coordinates, correcting the initial passable area to obtain the passable area of ​​the vehicle.

[0013] According to the above technical means, for each target obstacle, the characteristic coordinates of at least one target obstacle are determined according to the characteristic information of the target obstacle, one or more target characteristic coordinates are determined from the characteristic coordinates of at least one target obstacle, and the initial passable area is corrected according to the target characteristic coordinates to obtain the passable area of ​​the vehicle, wherein for different target obstacles, the corresponding characteristic coordinates are determined according to different characteristic information, thereby determining the corresponding target characteristic coordinates, which can improve the accuracy of the correction processing of the initial passable area and further improve the accuracy of the obtained passable area of ​​the vehicle.

[0014] Furthermore, the target obstacle includes a target vehicle, and the characteristic information of the target obstacle includes: vehicle center point coordinates, vehicle length, vehicle width, and vehicle yaw angle; the characteristic coordinates of the target obstacle are vehicle left front coordinates, vehicle right front coordinates, vehicle right rear coordinates, or vehicle left rear coordinates.

[0015] According to the above technical means, if the target obstacle is a target vehicle, the vehicle center point coordinates, vehicle length, vehicle width, and vehicle yaw angle can accurately characterize the characteristics of the target vehicle, and the vehicle left front coordinates, vehicle right front coordinates, vehicle right rear coordinates, and vehicle left rear coordinates are coordinates that accurately characterize the characteristics of the target vehicle, which can further improve the accuracy of correcting the initial passable area according to the characteristic coordinates of the target obstacle, while improving the accuracy of determining the passable area.

[0016] Further, determining characteristic coordinates of at least one target obstacle according to the characteristic information of the target obstacle includes: determining a calculation method of the characteristic coordinates of the target obstacle according to the vehicle center point coordinates and the vehicle yaw angle included in the characteristic information of the target obstacle; calculating the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates according to the vehicle center point coordinates, the vehicle length, the vehicle width, and the vehicle yaw angle included in the characteristic information of the target obstacle and the calculation method of the characteristic coordinates of the target obstacle.

[0017] According to the above technical means, for different target obstacles, according to the calculation method of the characteristic coordinates of different target obstacles, the accuracy of determining the characteristic coordinates of the target obstacle can be improved, and the accuracy of correcting the initial passable area according to the characteristic coordinates of the target obstacle can be further improved, while the accuracy of determining the passable area can be improved.

[0018] Furthermore, the initial traversable area includes at least one coordinate set; wherein the coordinate set corresponds to the target obstacle one-to-one; the coordinate set includes a plurality of obstacle attribute coordinates; the target obstacle indicates an obstacle type; one or more target feature coordinates are determined from the feature coordinates of the at least one target obstacle, and the initial traversable area is corrected based on the target feature coordinates to obtain the traversable area for the vehicle, including: for each of the target obstacles, one or more target feature coordinates are determined from the feature coordinates of the at least one target obstacle based on the obstacle type indicated by the target obstacle; a coordinate set corresponding to the target obstacle is selected from the at least one coordinate set included in the initial traversable area; and a plurality of obstacle attribute coordinates included in the corresponding coordinate set are corrected based on the determined target feature coordinates to obtain the traversable area for the vehicle.

[0019] According to the above technical means, in the process of determining one or more target characteristic coordinates from the characteristic coordinates of at least one target obstacle, and correcting the initial passable area according to the target characteristic coordinates, and obtaining the passable area of ​​the vehicle, different determination methods are selected for different obstacle types, and the corresponding target characteristic coordinates can be accurately determined from the characteristic coordinates of the corresponding target obstacle; further, according to the determined target characteristic coordinates, a plurality of obstacle attribute coordinates included in the corresponding coordinate set can be accurately corrected, thereby further improving the accuracy of obtaining the passable area of ​​the vehicle.

[0020] Further, the target obstacle includes a target vehicle, and the characteristic information of the target obstacle includes: vehicle center point coordinates and vehicle yaw angle; the characteristic coordinates of the target obstacle are vehicle left front coordinates, or vehicle right front coordinates, or vehicle right rear coordinates, or vehicle left rear coordinates; the target characteristic coordinates include: a first vehicle coordinate, a second vehicle coordinate, and a third vehicle coordinate; wherein the first vehicle coordinate and the second vehicle coordinate are coordinates corresponding to two end points of a first side of the target vehicle; the second vehicle coordinate and the third vehicle coordinate are coordinates corresponding to two end points of a second side of the target vehicle; wherein the first side is the side of the target vehicle facing the vehicle; the second side is the side of the target vehicle adjacent to the first side, corresponding to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle.

[0021] According to the above-mentioned technical means, if the target obstacle is a target vehicle, by determining the target feature coordinates as the first vehicle coordinates, the second vehicle coordinates, and the third vehicle coordinates, the accuracy of the correction processing of the initial passable area according to the target features can be improved, and the accuracy of the obtained vehicle passable area can be further improved.

[0022] Further, according to the obstacle type indicated by the target obstacle, one or more target feature coordinates are determined from the feature coordinates of the at least one target obstacle, including: determining the first side according to the vehicle yaw angle of the target vehicle, and determining two coordinates corresponding to the two end points of the first side from the left front coordinates of the vehicle, the right front coordinates of the vehicle, the right rear coordinates of the vehicle, and the left rear coordinates of the vehicle; determining the second side according to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle, and determining two coordinates corresponding to the two end points of the second side from the left front coordinates of the vehicle, the right front coordinates of the vehicle, the right rear coordinates of the vehicle, and the left rear coordinates of the vehicle; determining the two coordinates corresponding to the two end points of the first side that are the same as the two coordinates corresponding to the two end points of the second side as the second vehicle coordinates, determining the remaining coordinates of the two coordinates corresponding to the two end points of the first side as the first vehicle coordinates, and determining the remaining coordinates of the two coordinates corresponding to the two end points of the second side as the third vehicle coordinates.

[0023] According to the above technical means, when the vehicle center point coordinates and the vehicle yaw angle of the target vehicle are different, different target vehicle coordinates are determined respectively, which can improve the accuracy of the correction processing of multiple obstacle attribute coordinates included in the corresponding coordinate set according to the determined target feature coordinates, and further improve the accuracy of the obtained vehicle's passable area.

[0024] Further, the coordinate set corresponding to the target vehicle includes at least four vehicle obstacle attribute coordinates; according to the determined target feature coordinates, the multiple obstacle attribute coordinates included in the corresponding coordinate set are corrected to obtain the passable area of ​​the vehicle, including: according to the first vehicle coordinate, the second vehicle coordinate, and the third vehicle coordinate, the corresponding first coordinate to be adjusted, the second coordinate to be adjusted, and the third coordinate to be adjusted are determined from the at least four vehicle obstacle attribute coordinates; and the other coordinates in the at least four vehicle obstacle attribute coordinates are determined as fourth coordinates to be adjusted; wherein the number of the fourth coordinates to be adjusted is greater than or equal to one; the first coordinate to be adjusted is corrected to the first vehicle coordinate, and the second coordinate to be adjusted is corrected to the second vehicle coordinate; according to the second side, the longitudinal coordinate of the third coordinate to be adjusted is corrected; and according to the corrected second coordinate to be adjusted, the corrected third coordinate to be adjusted, and the number of the fourth coordinate to be adjusted, the fourth coordinate to be adjusted is corrected.

[0025] According to the above technical means, the first coordinate to be adjusted, the second coordinate to be adjusted, the third coordinate to be adjusted, and the fourth coordinate to be adjusted are corrected in turn according to the first vehicle coordinates, the second vehicle coordinates, and the third vehicle coordinates, which can improve the accuracy of the correction processing and further improve the accuracy of the obtained passable area.

[0026] Furthermore, the target obstacles also include target pedestrians, or target cyclists, or target cones, or target water barriers.

[0027] According to the above technical means, by setting multiple types of target obstacles, the accuracy of correcting the initial traversable area according to the characteristic information of at least one target obstacle can be improved, and the accuracy of determining the traversable area of ​​the vehicle can be further improved.

[0028] Furthermore, the image information includes an image at a current moment; obtaining an initial passable area of ​​the vehicle according to the image information includes: based on a panoramic segmentation technology, performing image segmentation processing on the image at the current moment included in the image information to obtain the image at the current moment after the segmentation processing; wherein the image at the current moment after the segmentation processing includes a plurality of image pixels; the image pixels indicate pixel attributes; according to the pixel attributes indicated by the image pixels, determining a set of image pixels corresponding to the initial passable area from a plurality of image pixels included in the image at the current moment after the segmentation processing; and according to a vehicle coordinate system conversion technology, processing the set of image pixels corresponding to the initial passable area to obtain the initial passable area of ​​the vehicle.

[0029] According to the above-mentioned technical means, in the process of obtaining the initial passable area of ​​the vehicle based on image information, the attributes of objects in front of the vehicle can be accurately identified based on the panoramic segmentation technology, and the image coordinate system can be converted into the vehicle coordinate system based on the vehicle coordinate system conversion technology, which can improve the accuracy of obtaining the initial passable area of ​​the vehicle and further improve the accuracy of obtaining the vehicle's passable area based on the vehicle's initial passable area.

[0030] Further, the image information includes an image at a current moment and an image at a historical moment; acquiring feature information of at least one target obstacle according to the image information includes: acquiring a current detection frame of at least one target obstacle from the image at the current moment included in the image information; and acquiring a historical detection frame of at least one target obstacle from the image at the historical moment included in the image information; determining at least one current detection frame and at least one historical detection frame corresponding to each target obstacle from the current detection frame of the at least one target obstacle and the historical detection frame of the at least one target obstacle; and determining feature information of each target obstacle according to the at least one current detection frame and at least one historical detection frame corresponding to each target obstacle.

[0031] According to the above technical means, in the process of obtaining characteristic information of at least one target obstacle based on image information, the characteristic information of each target obstacle can be accurately determined through the current detection frame and the historical detection frame of the target obstacle, thereby further improving the accuracy of determining the passable area based on the characteristic information of the target obstacle.

[0032] Furthermore, the method also includes: presenting a passable area of ​​the vehicle so that a user can control the driving of the vehicle based on the passable area of ​​the vehicle; or, controlling the vehicle to perform automatic driving according to the passable area of ​​the vehicle.

[0033] According to the above-mentioned technical means, on the basis of determining the passable area of ​​the vehicle, presenting the passable area of ​​the vehicle can improve the accuracy of the user's control of the vehicle's driving. On the basis of determining the passable area of ​​the vehicle, controlling the vehicle to perform automatic driving according to the passable area of ​​the vehicle can improve the accuracy of automatic driving.

[0034] A device for confirming a passable area, comprising:

[0035] An acquisition module, used for acquiring image information in front of the vehicle;

[0036] A processing module, configured to obtain an initial passable area of ​​the vehicle according to the image information, and obtain characteristic information of at least one target obstacle according to the image information; wherein the target obstacle is an obstacle that invades the initial passable area;

[0037] The determination module is used to correct the initial passable area according to the characteristic information of the at least one target obstacle to obtain the passable area of ​​the vehicle.

[0038] Furthermore, the determination module includes:

[0039] A first determining unit is used to determine, for each of the target obstacles, characteristic coordinates of at least one target obstacle according to characteristic information of the target obstacle; wherein the characteristic coordinates of the target obstacle are coordinates of a preset position of the target obstacle in a vehicle coordinate system;

[0040] The second determination unit is used to determine one or more target characteristic coordinates from the characteristic coordinates of the at least one target obstacle, and perform correction processing on the initial passable area according to the target characteristic coordinates to obtain the passable area of ​​the vehicle.

[0041] Furthermore, the target obstacle includes a target vehicle, and the characteristic information of the target obstacle includes: vehicle center point coordinates, vehicle length, vehicle width, and vehicle yaw angle; the characteristic coordinates of the target obstacle are vehicle left front coordinates, vehicle right front coordinates, vehicle right rear coordinates, or vehicle left rear coordinates.

[0042] Further, the first determination unit is specifically used to determine a calculation method for the characteristic coordinates of the target obstacle according to the vehicle center point coordinates and the vehicle yaw angle included in the characteristic information of the target obstacle; and calculate the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates according to the vehicle center point coordinates, the vehicle length, the vehicle width, and the vehicle yaw angle included in the characteristic information of the target obstacle, and the calculation method for the characteristic coordinates of the target obstacle.

[0043] Furthermore, the initial traversable area includes at least one coordinate set; wherein the coordinate set corresponds to the target obstacle one-to-one; the coordinate set includes a plurality of obstacle attribute coordinates; the target obstacle indicates an obstacle type; the second determination unit is specifically used to determine, for each of the target obstacles, one or more target feature coordinates from the feature coordinates of the at least one target obstacle according to the obstacle type indicated by the target obstacle; select a coordinate set corresponding to the target obstacle from the at least one coordinate set included in the initial traversable area; and perform correction processing on the plurality of obstacle attribute coordinates included in the corresponding coordinate set according to the determined target feature coordinates to obtain the traversable area for the vehicle.

[0044] Further, the target obstacle includes a target vehicle, and the characteristic information of the target obstacle includes: vehicle center point coordinates and vehicle yaw angle; the characteristic coordinates of the target obstacle are vehicle left front coordinates, or vehicle right front coordinates, or vehicle right rear coordinates, or vehicle left rear coordinates; the target characteristic coordinates include: a first vehicle coordinate, a second vehicle coordinate, and a third vehicle coordinate; wherein the first vehicle coordinate and the second vehicle coordinate are coordinates corresponding to two end points of a first side of the target vehicle; the second vehicle coordinate and the third vehicle coordinate are coordinates corresponding to two end points of a second side of the target vehicle; wherein the first side is the side of the target vehicle facing the vehicle; the second side is the side of the target vehicle adjacent to the first side, corresponding to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle.

[0045] Further, the second determination unit is further specifically used to determine the first side according to the vehicle yaw angle of the target vehicle, and determine the two coordinates corresponding to the two endpoints of the first side from the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates; determine the second side according to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle, and determine the two coordinates corresponding to the two endpoints of the second side from the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates; determine the two coordinates corresponding to the two endpoints of the first side that are the same as the two coordinates corresponding to the two endpoints of the second side as the second vehicle coordinates, and determine the remaining coordinates of the two coordinates corresponding to the two endpoints of the first side as the first vehicle coordinates, and determine the remaining coordinates of the two coordinates corresponding to the two endpoints of the second side as the third vehicle coordinates.

[0046] Further, the coordinate set corresponding to the target vehicle includes at least four vehicle obstacle attribute coordinates; the second determination unit is further specifically used to determine the corresponding first coordinate to be adjusted, second coordinate to be adjusted, and third coordinate to be adjusted from the at least four vehicle obstacle attribute coordinates according to the first vehicle coordinate, the second vehicle coordinate, and the third vehicle coordinate; and determine the other coordinates in the at least four vehicle obstacle attribute coordinates as fourth coordinates to be adjusted; wherein the number of the fourth coordinates to be adjusted is greater than or equal to one; correct the first coordinate to be adjusted to the first vehicle coordinate, and correct the second coordinate to be adjusted to the second vehicle coordinate; according to the second side, correct the longitudinal coordinate of the third coordinate to be adjusted; and correct the fourth coordinate to be adjusted according to the corrected second coordinate to be adjusted, the corrected third coordinate to be adjusted, and the number of the fourth coordinate to be adjusted.

[0047] Furthermore, the target obstacles also include target pedestrians, or target cyclists, or target cones, or target water barriers.

[0048] Furthermore, the image information includes an image at a current moment; the processing module is specifically used to perform image segmentation processing on the image at the current moment included in the image information based on panoramic segmentation technology to obtain the image at the current moment after the segmentation processing; wherein the image at the current moment after the segmentation processing includes a plurality of image pixels; the image pixel points indicate pixel attributes; according to the pixel attributes indicated by the image pixel points, a set of image pixel points corresponding to the initial passable area is determined from the plurality of image pixel points included in the image at the current moment after the segmentation processing; according to the vehicle coordinate system conversion technology, the set of image pixel points corresponding to the initial passable area is processed to obtain the initial passable area of ​​the vehicle.

[0049] Furthermore, the image information includes an image at a current moment and images at historical moments; the processing module is further specifically used to obtain a current detection frame of at least one target obstacle from the image at the current moment included in the image information; and to obtain a historical detection frame of at least one target obstacle from the images at historical moments included in the image information; determine at least one current detection frame and at least one historical detection frame corresponding to each target obstacle from the current detection frame of the at least one target obstacle and the historical detection frame of the at least one target obstacle; and determine feature information of each target obstacle according to the at least one current detection frame and at least one historical detection frame corresponding to each target obstacle.

[0050] Furthermore, the determination module is also used to present the passable area of ​​the vehicle so that the user can control the driving of the vehicle based on the passable area of ​​the vehicle; or, control the vehicle to perform automatic driving according to the passable area of ​​the vehicle.

[0051] An electronic device comprising a memory and a processor;

[0052] The memory stores computer-executable instructions;

[0053] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0054] A computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the above first aspect and / or various possible implementations of the first aspect.

[0055] A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the computer program implements the above first aspect and / or various possible implementation modes of the first aspect.

[0056] A car comprises an electronic device for implementing the above first aspect and / or various possible implementations of the first aspect.

[0057] Beneficial effects of the present invention:

[0058] The present invention obtains image information in front of a vehicle, obtains an initial passable area of ​​the vehicle based on the image information, obtains characteristic information of at least one target obstacle based on the image information, and corrects the initial passable area based on the characteristic information of at least one target obstacle to obtain the passable area of ​​the vehicle. The accuracy of confirmation of the passable area can be improved by correcting the initial passable area based on the characteristic information of at least one target obstacle obtained based on the initial passable area of ​​the vehicle obtained based on the image information. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 The process of the method for confirming the passable area provided by one embodiment of the present invention Figure 1 ;

[0060] Figure 2 The process of the method for confirming the passable area provided by one embodiment of the present invention Figure 2 ;

[0061] Figure 3 An example diagram of an initial traversable area provided by an embodiment of the present invention;

[0062] Figure 4 The process of the method for confirming the passable area provided by one embodiment of the present invention Figure 3 ;

[0063] Figure 5 An example diagram of target feature coordinates provided by an embodiment of the present invention;

[0064] Figure 6 The process of the method for confirming the passable area provided by one embodiment of the present invention Figure 4 ;

[0065] Figure 7 An example diagram of an initial traversable area after a first correction process provided by an embodiment of the present invention;

[0066] Figure 8 An example diagram of a traversable area provided by an embodiment of the present invention;

[0067] Fig. 9 A schematic diagram of the structure of a device for confirming a passable area provided in one embodiment of the present invention;

[0068] Fig.10 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0069] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0070] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0071] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and corresponding operation entrances shall be provided for users to choose to authorize or refuse.

[0072] In the prior art, the passable area of ​​the vehicle is determined directly through the attribute information of the pixel points in the image. However, the method in the prior art may lead to the problem of inaccurate confirmation of the passable area.

[0073] The present invention obtains image information in front of a vehicle, obtains an initial passable area of ​​the vehicle based on the image information, obtains characteristic information of at least one target obstacle based on the image information, and corrects the initial passable area based on the characteristic information of at least one target obstacle to obtain the passable area of ​​the vehicle. The accuracy of confirmation of the passable area can be improved by correcting the initial passable area based on the characteristic information of at least one target obstacle obtained based on the initial passable area of ​​the vehicle obtained based on the image information.

[0074] The technical solution of the present invention is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0075] Figure 1 The process of the method for confirming the passable area provided by one embodiment of the present invention Figure 1 .like Figure 1 As shown, the method of the embodiment of the present invention includes:

[0076] Step S101: Acquire image information in front of the vehicle.

[0077] Specifically, image information in front of the vehicle can be obtained. The image information is information representing the image in front of the vehicle. The present invention does not limit the image information, and any information that can represent the image in front of the vehicle can be used as the image information provided by the present invention.

[0078] The present invention does not limit the process of obtaining the image information in front of the vehicle, wherein the process of obtaining the image information in front of the vehicle corresponds to the image information provided by the present invention. Optionally, if the image information provided by the present invention is an image in front of the vehicle, the image information in front of the vehicle can be obtained by an image acquisition device arranged in the vehicle.

[0079] Step S102: acquiring an initial traversable area of ​​the vehicle according to the image information, and acquiring characteristic information of at least one target obstacle according to the image information.

[0080] Specifically, according to the image information in front of the vehicle obtained in step S101, the initial passable area of ​​the vehicle can be obtained, wherein the initial passable area is the passable area in front of the vehicle preliminarily determined according to the image information. The present invention does not limit the process of obtaining the initial passable area of ​​the vehicle according to the image information. Optionally, based on the panoramic segmentation technology, the image at the current moment included in the image information can be subjected to image segmentation processing to obtain the image at the current moment after the segmentation processing; wherein the image at the current moment after the segmentation processing includes a plurality of image pixels; the image pixels indicate pixel attributes; according to the pixel attributes indicated by the image pixels, the set of image pixels corresponding to the initial passable area is determined from the plurality of image pixels included in the image at the current moment after the segmentation processing; according to the vehicle coordinate system conversion technology, the set of image pixels corresponding to the initial passable area is processed to obtain the initial passable area of ​​the vehicle.

[0081] Specifically, according to the image information in front of the vehicle obtained in step S101, feature information of at least one target obstacle can be obtained, wherein the target obstacle is an obstacle that invades the initial passable area. The present invention does not limit the target obstacle, and any obstacle that invades the initial passable area in front of the vehicle can be used as the target obstacle provided by the present invention.

[0082] The present invention does not limit the process of obtaining characteristic information of at least one target obstacle based on image information. Optionally, a current detection frame of at least one target obstacle can be obtained from an image at a current moment included in the image information; and a historical detection frame of at least one target obstacle can be obtained from images at historical moments included in the image information; at least one current detection frame and at least one historical detection frame corresponding to each target obstacle are determined from the current detection frame of at least one target obstacle and the historical detection frame of at least one target obstacle; characteristic information of each target obstacle is determined based on the at least one current detection frame and at least one historical detection frame corresponding to each target obstacle.

[0083] Step S103: Correct the initial traversable area according to the characteristic information of at least one target obstacle to obtain a traversable area for the vehicle.

[0084] Specifically, according to the characteristic information of at least one target obstacle obtained in step S102, the initial passable area obtained in step S101 can be corrected to obtain the passable area of ​​the vehicle. The present invention does not limit the process of correcting the initial passable area according to the characteristic information of at least one target obstacle to obtain the passable area of ​​the vehicle. Optionally, for each target obstacle, according to the characteristic information of the target obstacle, at least one characteristic coordinate of the target obstacle can be determined; wherein the characteristic coordinate of the target obstacle is the coordinate of the preset position of the target obstacle in the vehicle coordinate system; then one or more target characteristic coordinates are determined from the characteristic coordinates of at least one target obstacle, and according to the target characteristic coordinates, the initial passable area is corrected to obtain the passable area of ​​the vehicle.

[0085] Among them, the freespace area, that is, the drivable area in autonomous driving, refers to the spatial range in which the vehicle can safely drive on the current road or environment. Freespace detection is a key component of the autonomous driving system's understanding of driving scenarios, and plays a vital role in ensuring that autonomous driving vehicles can navigate safely in complex environments. Through freespace detection, the autonomous driving system can understand the road conditions of the vehicle's environment in real time, avoid driving into unsafe areas, and reduce the risk of accidents.

[0086] The method for confirming a passable area provided in an embodiment of the present invention obtains image information in front of a vehicle, obtains an initial passable area of ​​the vehicle based on the image information, obtains feature information of at least one target obstacle based on the image information, and corrects the initial passable area based on the feature information of at least one target obstacle to obtain the passable area of ​​the vehicle. The method improves the accuracy of confirmation of the passable area by correcting the initial passable area based on the feature information of at least one target obstacle obtained based on the initial passable area of ​​the vehicle obtained based on the image information.

[0087] In a possible embodiment, the method for confirming the passable area may also include: presenting the passable area of ​​the vehicle so that the user can control the vehicle's driving based on the passable area of ​​the vehicle; or, controlling the vehicle to perform automatic driving according to the passable area of ​​the vehicle.

[0088] The present invention does not limit the manner of presenting the passable area of ​​the vehicle, and can optionally be presented on a vehicle-mounted display device of the vehicle, or can optionally be presented on a user's mobile terminal. The user can control the vehicle's driving based on the passable area of ​​the vehicle, so that the vehicle drives within the passable area.

[0089] Among them, the present invention does not limit the process of controlling the vehicle to perform automatic driving according to the vehicle's passable area. Any process that can control the vehicle to automatically drive so that the vehicle drives within the passable area can be used as the process of controlling the vehicle to perform automatic driving according to the vehicle's passable area provided by the present invention.

[0090] Among them, presenting the vehicle's passable area on the basis of determining the vehicle's passable area can improve the accuracy of users' control of vehicle driving. On the basis of determining the vehicle's passable area, controlling the vehicle to perform automatic driving according to the vehicle's passable area can improve the accuracy of automatic driving.

[0091] Figure 2 The process of the method for confirming the passable area provided by one embodiment of the present invention Figure 2 .exist Figure 1 Based on the embodiment shown, this embodiment describes in detail the process of correcting the initial passable area according to the characteristic information of at least one target obstacle to obtain the passable area for the vehicle. Figure 2 As shown, the method of the embodiment of the present invention includes:

[0092] Step S201: for each target obstacle, determine at least one characteristic coordinate of the target obstacle according to characteristic information of the target obstacle.

[0093] Specifically, for each target obstacle, the characteristic coordinates of at least one target obstacle can be determined according to the characteristic information of the target obstacle. For the description of the target obstacle, reference can be made to the description in step S102, which will not be repeated here. The characteristic coordinates of the target obstacle are the coordinates of the preset position of the target obstacle in the vehicle coordinate system. The present invention does not limit the characteristic coordinates of the target obstacle, and the coordinates of the preset position of the target obstacle in any vehicle coordinate system can be used as the characteristic coordinates of the target obstacle provided by the present invention.

[0094] Among them, in the vehicle coordinate system, the position of the vehicle center point of the current vehicle is the position of the midpoint of the coordinate system; the direction pointed by the front of the current vehicle is the positive direction of the x-axis, and the direction pointed by the left side of the current vehicle is the positive direction of the y-axis.

[0095] The present invention does not limit the process of determining the characteristic coordinates of at least one target obstacle based on the characteristic information of the target obstacle, wherein the process of determining the characteristic coordinates of at least one target obstacle based on the characteristic information of the target obstacle corresponds to the type of the target obstacle.

[0096] Optionally, the target obstacle includes a target vehicle, and the characteristic information of the target obstacle includes: vehicle center point coordinates, vehicle length, vehicle width, and vehicle yaw angle. The characteristic coordinates of the target obstacle are the left front coordinates of the vehicle, or the right front coordinates of the vehicle, or the right rear coordinates of the vehicle, or the left rear coordinates of the vehicle. Specifically, the left front coordinates of the vehicle are the coordinates at the left front vertex of the vehicle; the right front coordinates of the vehicle are the coordinates at the right front vertex of the vehicle; the right rear coordinates of the vehicle are the coordinates at the right rear vertex of the vehicle; and the left rear coordinates of the vehicle are the coordinates at the left rear vertex of the vehicle.

[0097] Among them, if the target obstacle is a target vehicle, the vehicle center point coordinates, vehicle length, vehicle width, and vehicle yaw angle can accurately characterize the characteristics of the target vehicle, and the vehicle left front coordinates, vehicle right front coordinates, vehicle right rear coordinates, and vehicle left rear coordinates are coordinates that accurately characterize the characteristics of the target vehicle, which can further improve the accuracy of correcting the initial passable area according to the characteristic coordinates of the target obstacle, and at the same time improve the accuracy of determining the passable area.

[0098] Optionally, if the target obstacle includes a target vehicle, the process of determining the characteristic coordinates of at least one target obstacle according to the characteristic information of the target obstacle may include: determining a calculation method for the characteristic coordinates of the target obstacle according to the vehicle center point coordinates and the vehicle yaw angle included in the characteristic information of the target obstacle. Calculate the vehicle left front coordinates, vehicle right front coordinates, vehicle right rear coordinates, and vehicle left rear coordinates according to the vehicle center point coordinates, vehicle length, vehicle width, and vehicle yaw angle included in the characteristic information of the target obstacle and the calculation method for the characteristic coordinates of the target obstacle.

[0099] Among them, in the process of determining the calculation method of the characteristic coordinates of the target obstacle according to the vehicle center point coordinates and the vehicle yaw angle included in the characteristic information of the target obstacle, if the vehicle center point coordinates indicate that the target vehicle is located in the first quadrant of the vehicle coordinates, and the absolute value of the vehicle yaw angle is less than or equal to 90°, if the vehicle center point coordinates are (x, y), the vehicle length is l, the vehicle width is w, and the vehicle yaw angle is yaw, the vehicle left front coordinates are P1 (x1, y1), the vehicle right front coordinates are P2 (x2, y2), the vehicle right rear coordinates are P3 (x3, y3), and the vehicle left rear coordinates are P4 (x4, y4), then the corresponding calculation formula is as follows:

[0100]

[0101]

[0102]

[0103]

[0104]

[0105]

[0106]

[0107]

[0108] Among them, for different target obstacles, according to the calculation method of the characteristic coordinates of different target obstacles, the accuracy of determining the characteristic coordinates of the target obstacle can be improved, and the accuracy of correcting the initial passable area according to the characteristic coordinates of the target obstacle can be further improved, while the accuracy of determining the passable area can be improved.

[0109] Step S202: determine one or more target characteristic coordinates from the characteristic coordinates of at least one target obstacle, and perform correction processing on the initial passable area according to the target characteristic coordinates to obtain the passable area for the vehicle.

[0110] Specifically, one or more target feature coordinates are determined from the feature coordinates of at least one target obstacle determined in step S201. The target feature coordinates are feature coordinates selected from the feature coordinates of the target obstacle and used to perform correction processing on the initial passable area. The present invention does not limit the number of target features determined, and the number of target features determined corresponds to the type of target obstacle. For example, if the target obstacle is a target vehicle, the number of target feature coordinates determined is three. The present invention does not limit the process of determining one or more target feature coordinates from the feature coordinates of at least one target obstacle, and the process of determining one or more target feature coordinates from the feature coordinates of at least one target obstacle corresponds to the type of target obstacle.

[0111] Specifically, after determining one or more target characteristic coordinates from the characteristic coordinates of at least one target obstacle, the initial passable area can be corrected according to the target characteristic coordinates to obtain the passable area of ​​the vehicle, wherein the present invention does not limit the process of correcting the initial passable area according to the target characteristic coordinates to obtain the passable area of ​​the vehicle, wherein the process of correcting the initial passable area according to the target characteristic coordinates to obtain the passable area of ​​the vehicle corresponds to the type of the target obstacle. For example: if the target obstacle is a target vehicle, the initial passable area can be corrected according to the three determined target characteristic coordinates to obtain the passable area of ​​the vehicle.

[0112] Optionally, the process of determining one or more target characteristic coordinates from the characteristic coordinates of at least one target obstacle, and correcting the initial traversable area according to the target characteristic coordinates to obtain the traversable area for the vehicle may include:

[0113] First, for each target obstacle, one or more target characteristic coordinates may be determined from characteristic coordinates of at least one target obstacle according to the obstacle type indicated by the target obstacle.

[0114] Specifically, the present invention does not limit the process of determining one or more target feature coordinates from the feature coordinates of at least one target obstacle according to the obstacle type indicated by the target obstacle for each target obstacle. Optionally, if the target obstacle is a target vehicle, the process of determining one or more target feature coordinates from the feature coordinates of at least one target obstacle according to the obstacle type indicated by the target obstacle may include: determining a first side according to a vehicle yaw angle of the target vehicle, and determining two endpoints of the first side from the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates. corresponding two coordinates; determine the second side according to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle, and determine the two coordinates corresponding to the two endpoints of the second side from the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates; determine the two coordinates corresponding to the two endpoints of the first side that are the same as the two coordinates corresponding to the two endpoints of the second side as the second vehicle coordinates, and determine the remaining coordinates of the two coordinates corresponding to the two endpoints of the first side as the first vehicle coordinates, and determine the remaining coordinates of the two coordinates corresponding to the two endpoints of the second side as the third vehicle coordinates.

[0115] Secondly, a coordinate set corresponding to the target obstacle may be selected from at least one coordinate set included in the initial traversable area.

[0116] The initial passable area includes at least one coordinate set. The coordinate set corresponds to the target obstacle one by one. The coordinate set includes multiple obstacle attribute coordinates. The target obstacle indicates the obstacle type.

[0117] Figure 3An example diagram of an initial traversable area provided for an embodiment of the present invention. The square area on the right side of the picture is a target obstacle, wherein the obstacle type indicated by the target obstacle is a target vehicle. The set of coordinates included in the circular area is a coordinate set corresponding to the target vehicle, wherein the coordinates included in the coordinate set are vehicle obstacle attribute coordinates. The other coordinates other than the vehicle obstacle attribute coordinates included in the circular area are background attribute coordinates. Specifically, the initial traversable area includes a plurality of background attribute coordinates and a plurality of obstacle attribute coordinates, wherein the plurality of obstacle attribute coordinates belong to a coordinate set corresponding to at least one target obstacle. The square area on the left side of the picture is an obstacle far away from the initial traversable area.

[0118] Specifically, the present invention does not limit the process of selecting a coordinate set corresponding to a target obstacle from at least one coordinate set included in the initial passable area. Optionally, the object attribute of each coordinate corresponding to the initial passable area can be determined based on the pixel attribute indicated by each image pixel point in the initial passable area; and then, based on the object attribute of each coordinate and the characteristic coordinates of the target obstacle, the coordinate set corresponding to each target obstacle in the initial passable area is determined.

[0119] Then, according to the determined target feature coordinates, a plurality of obstacle attribute coordinates included in the corresponding coordinate set may be corrected to obtain a passable area for the vehicle.

[0120] Specifically, the present invention does not limit the process of correcting the multiple obstacle attribute coordinates included in the corresponding coordinate set according to the determined target feature coordinates to obtain the passable area of ​​the vehicle. Optionally, the first coordinate to be adjusted, the second coordinate to be adjusted, and the third coordinate to be adjusted can be determined from at least four vehicle obstacle attribute coordinates according to the first vehicle coordinate, the second vehicle coordinate, and the third vehicle coordinate. And the other coordinates in the at least four vehicle obstacle attribute coordinates are determined as the fourth coordinate to be adjusted; the first coordinate to be adjusted is corrected to the first vehicle coordinate, and the second coordinate to be adjusted is corrected to the second vehicle coordinate; and the vertical coordinate of the third coordinate to be adjusted is corrected according to the second side; the fourth coordinate to be adjusted is corrected according to the number of the second coordinate to be adjusted after the correction processing, the third coordinate to be adjusted after the correction processing, and the fourth coordinate to be adjusted.

[0121] Among them, in the process of determining one or more target characteristic coordinates from the characteristic coordinates of at least one target obstacle, and correcting the initial passable area according to the target characteristic coordinates to obtain the passable area of ​​the vehicle, different determination methods are selected for different obstacle types, so that the corresponding target characteristic coordinates can be accurately determined from the characteristic coordinates of the corresponding target obstacle; further, according to the determined target characteristic coordinates, a plurality of obstacle attribute coordinates included in the corresponding coordinate set can be accurately corrected, thereby further improving the accuracy of obtaining the passable area of ​​the vehicle.

[0122] The embodiment of the present invention provides a process for correcting an initial passable area according to characteristic information of at least one target obstacle to obtain a passable area for a vehicle, by determining, for each target obstacle, characteristic coordinates of at least one target obstacle according to the characteristic information of the target obstacle, determining one or more target characteristic coordinates from the characteristic coordinates of at least one target obstacle, and correcting the initial passable area according to the target characteristic coordinates to obtain a passable area for the vehicle, wherein corresponding characteristic coordinates are determined according to different characteristic information for different target obstacles, thereby determining corresponding target characteristic coordinates, which can improve the accuracy of the correction processing of the initial passable area, and further improve the accuracy of the obtained passable area for the vehicle.

[0123] Figure 4 The process of the method for confirming the passable area provided by one embodiment of the present invention Figure 3 .exist Figure 1 or Figure 2 Based on the embodiment shown in the figure, this embodiment describes in detail the process of determining one or more target characteristic coordinates from the characteristic coordinates of at least one target obstacle according to the obstacle type indicated by the target obstacle. Figure 4 As shown, the method of the embodiment of the present invention includes:

[0124] Step S401, determine a first side according to the vehicle yaw angle of the target vehicle, and determine two coordinates corresponding to two endpoints of the first side from the vehicle left front coordinate, the vehicle right front coordinate, the vehicle right rear coordinate, and the vehicle left rear coordinate.

[0125] Specifically, according to the vehicle yaw angle of the target vehicle, the first side can be determined, and the two coordinates corresponding to the two endpoints of the first side can be determined from the vehicle left front coordinates, vehicle right front coordinates, vehicle right rear coordinates, and vehicle left rear coordinates.

[0126] Optionally, the target obstacle includes a target vehicle, wherein the description of the target vehicle can refer to the description in the above embodiment and will not be repeated here.

[0127] If the target obstacle is a target vehicle, the characteristic information of the target obstacle includes: the coordinates of the center point of the vehicle and the yaw angle of the vehicle. The characteristic coordinates of the target obstacle are the left front coordinates of the vehicle, the right front coordinates of the vehicle, the right rear coordinates of the vehicle, or the left rear coordinates of the vehicle. The target characteristic coordinates include: the first vehicle coordinates, the second vehicle coordinates, and the third vehicle coordinates.

[0128] The first vehicle coordinate and the second vehicle coordinate are the coordinates corresponding to the two endpoints of the first side of the target vehicle. The second vehicle coordinate and the third vehicle coordinate are the coordinates corresponding to the two endpoints of the second side of the target vehicle. The first side is the side of the target vehicle that the vehicle is facing. The second side is the side of the target vehicle that is adjacent to the first side and corresponds to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle.

[0129] Among them, if the target obstacle is a target vehicle, by determining the target feature coordinates as the first vehicle coordinates, the second vehicle coordinates, and the third vehicle coordinates, the accuracy of the correction processing of the initial passable area according to the target features can be improved, and the accuracy of the obtained vehicle passable area can be further improved.

[0130] Figure 5 An example diagram of target feature coordinates provided for an embodiment of the present invention. The square area at the origin of the coordinates is the current vehicle; the square area in the first quadrant on the left front is the target vehicle. P1 (x1, y1) is the left front coordinate of the vehicle, P2 (x2, y2) is the right front coordinate of the vehicle, P3 (x3, y3) is the right rear coordinate of the vehicle, and P4 (x4, y4) is the left rear coordinate of the vehicle. The direction pointed by the arrow on the left of the target vehicle is the direction of the yaw angle. The first vehicle coordinate, the second vehicle coordinate, the third vehicle coordinate, the first side, and the second side of the target vehicle are as follows: Figure 5 as shown in .

[0131] Specifically, the first side can be determined according to the vehicle yaw angle of the target vehicle. The present invention does not limit the process of determining the first side according to the vehicle yaw angle of the target vehicle. Optionally, if the absolute value of the yaw angle is less than or equal to 90°, that is, -90°≤yaw≤90°, the rear side of the vehicle, that is, the side formed by the right rear coordinates P3 (x3, y3) of the vehicle and the left rear coordinates P4 (x4, y4) of the vehicle is selected as the first side; otherwise, the front side of the vehicle, that is, the side formed by the left front coordinates P1 (x1, y1) of the vehicle and the right front coordinates P2 (x2, y2) of the vehicle is selected as the first side.

[0132] Specifically, after determining the first side according to the vehicle yaw angle of the target vehicle, the two coordinates corresponding to the two endpoints of the first side can be determined from the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates, as shown above.

[0133] Step S402, determine the second side according to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle, and determine the two coordinates corresponding to the two endpoints of the second side from the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates.

[0134] Specifically, after determining the first side according to the vehicle yaw angle of the target vehicle, and determining the two coordinates corresponding to the two endpoints of the first side from the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates, the second side can be determined according to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle. Among them, the present invention does not limit the process of determining the second side according to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle. Optionally, if the absolute value of the yaw angle is less than or equal to 90°, and the vehicle centerline point coordinates of the target vehicle indicate that the target vehicle is located in the first quadrant, the right side of the vehicle, that is, the side formed by the right front coordinates P2 (x2, y2) of the vehicle and the right rear coordinates P3 (x3, y3) of the vehicle is selected as the second side; if the absolute value of the yaw angle is less than or equal to 90°, and the vehicle centerline point coordinates of the target vehicle indicate that the target vehicle is located in the fourth quadrant, the left side of the vehicle, that is, the left front coordinates P1 (x1, y1) of the vehicle and the right rear coordinates P3 (x3, y3) of the vehicle are selected. The side formed by the left rear coordinates P4 (x4, y4) is the second side; if the absolute value of the yaw angle is greater than 90°, and the vehicle centerline point coordinates of the target vehicle indicate that the target vehicle is located in the first quadrant, then the left side of the vehicle, that is, the side formed by the left front coordinates P1 (x1, y1) of the vehicle and the left rear coordinates P4 (x4, y4) of the vehicle is selected as the second side; if the absolute value of the yaw angle is greater than 90°, and the vehicle centerline point coordinates of the target vehicle indicate that the target vehicle is located in the fourth quadrant, then the right side of the vehicle, that is, the side formed by the right front coordinates P2 (x2, y2) of the vehicle and the right rear coordinates P3 (x3, y3) of the vehicle is selected as the second side.

[0135] Specifically, after determining the second side based on the vehicle center point coordinates and the vehicle yaw angle of the target vehicle, the two coordinates corresponding to the two endpoints of the second side can be determined from the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates, as shown above.

[0136] Step S403, determine the two coordinates corresponding to the two endpoints of the first side that are the same as the two coordinates corresponding to the two endpoints of the second side as the second vehicle coordinates, and determine the remaining coordinates of the two coordinates corresponding to the two endpoints of the first side as the first vehicle coordinates, and determine the remaining coordinates of the two coordinates corresponding to the two endpoints of the second side as the third vehicle coordinates.

[0137] Specifically, after determining the two coordinates corresponding to the two endpoints of the first side and the two coordinates corresponding to the two endpoints of the second side, the two coordinates corresponding to the two endpoints of the first side and the same coordinates as the two coordinates corresponding to the two endpoints of the second side can be determined as the second vehicle coordinates, and the remaining coordinates of the two coordinates corresponding to the two endpoints of the first side can be determined as the first vehicle coordinates, and the remaining coordinates of the two coordinates corresponding to the two endpoints of the second side can be determined as the third vehicle coordinates.

[0138] Optionally, if the absolute value of the yaw angle is less than or equal to 90°, and the vehicle centerline point coordinates of the target vehicle indicate that the target vehicle is located in the first quadrant, the first vehicle coordinates are the vehicle left rear coordinates P4 (x4, y4), the second vehicle coordinates are the vehicle right rear coordinates P3 (x3, y3), and the third vehicle coordinates are the vehicle right front coordinates P2 (x2, y2); if the absolute value of the yaw angle is less than or equal to 90°, and the vehicle centerline point coordinates of the target vehicle indicate that the target vehicle is located in the fourth quadrant, the first vehicle coordinates are the vehicle right rear coordinates P3 (x3, y3), the second vehicle coordinates are the vehicle left rear coordinates P4 (x4, y4), and the third vehicle coordinates are the vehicle left front coordinates P1 (x1 ,y1); if the absolute value of the yaw angle is greater than 90°, and the vehicle centerline point coordinates of the target vehicle indicate that the target vehicle is located in the first quadrant, the first vehicle coordinates are the vehicle right front coordinates P2 (x2, y2), the second vehicle coordinates are the vehicle left front coordinates P1 (x1, y1), and the third vehicle coordinates are the vehicle left rear coordinates P4 (x4, y4); if the absolute value of the yaw angle is greater than 90°, and the vehicle centerline point coordinates of the target vehicle indicate that the target vehicle is located in the fourth quadrant, the first vehicle coordinates are the vehicle left front coordinates P1 (x1, y1), the second vehicle coordinates are the vehicle right front coordinates P2 (x2, y2), and the third vehicle coordinates are the vehicle right rear coordinates P3 (x3, y3).

[0139] In the process of determining one or more target characteristic coordinates from characteristic coordinates of at least one target obstacle according to the obstacle type indicated by the target obstacle provided by the embodiment of the present invention, a first side is determined according to the vehicle yaw angle of the target vehicle, and two coordinates corresponding to two end points of the first side are determined from the left front coordinates of the vehicle, the right front coordinates of the vehicle, the right rear coordinates of the vehicle, and the left rear coordinates of the vehicle; a second side is determined according to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle, and two coordinates corresponding to two end points of the second side are determined from the left front coordinates of the vehicle, the right front coordinates of the vehicle, the right rear coordinates of the vehicle, and the left rear coordinates of the vehicle; The two coordinates corresponding to the two endpoints of the side are the same as the two coordinates corresponding to the two endpoints of the second side as the second vehicle coordinates, and the remaining coordinates of the two coordinates corresponding to the two endpoints of the first side are determined as the first vehicle coordinates, and the remaining coordinates of the two coordinates corresponding to the two endpoints of the second side are determined as the third vehicle coordinates, wherein, when the vehicle center point coordinates and the vehicle yaw angle of the target vehicle are different, different target vehicle coordinates are determined respectively, which can improve the accuracy of the correction processing of multiple obstacle attribute coordinates included in the corresponding coordinate set according to the determined target feature coordinates, and further improve the accuracy of the obtained vehicle's passable area.

[0140] Figure 6 The process of the method for confirming the passable area provided by one embodiment of the present invention Figure 4 .exist Figure 1 or Figure 2 or Figure 4 Based on the embodiment shown, this embodiment describes in detail the process of correcting a plurality of obstacle attribute coordinates included in the corresponding coordinate set according to the determined target feature coordinates to obtain the passable area of ​​the vehicle. Figure 5 As shown, the method of the embodiment of the present invention includes:

[0141] Step S601: Determine the corresponding first coordinate to be adjusted, second coordinate to be adjusted, and third coordinate to be adjusted from at least four vehicle obstacle attribute coordinates according to the first vehicle coordinate, the second vehicle coordinate, and the third vehicle coordinate; and determine the other coordinates in the at least four vehicle obstacle attribute coordinates as fourth coordinates to be adjusted.

[0142] Among them, the coordinate set corresponding to the target vehicle includes at least four vehicle obstacle attribute coordinates. Among them, the description of the coordinate set and the vehicle obstacle attribute coordinates can refer to the description in the above embodiment, and will not be repeated here. Among them, the number of obstacle attribute coordinates included in the coordinate set corresponding to the target obstacle corresponds to the number of target obstacle coordinates corresponding to the target obstacle. Optionally, the number of obstacle attribute coordinates included in the coordinate set corresponding to the target obstacle is at least one more than the number of target feature coordinates corresponding to the target obstacle. For example: if the target obstacle is a target vehicle, the number of vehicle attribute coordinates included in the corresponding coordinate set is at least four, which is at least one more than the number of target feature coordinates corresponding to the target vehicle, which is three.

[0143] Specifically, the present invention does not limit the process of determining the corresponding first coordinates to be adjusted, the second coordinates to be adjusted, and the third coordinates to be adjusted from at least four vehicle obstacle attribute coordinates according to the first vehicle coordinates, the second vehicle coordinates, and the third vehicle coordinates. Optionally, the coordinates close to the first vehicle coordinates among the at least four vehicle obstacle attribute coordinates can be determined as the corresponding first coordinates to be adjusted; the coordinates close to the second vehicle coordinates among the at least four vehicle obstacle attribute coordinates can be determined as the corresponding second coordinates to be adjusted; and the coordinates close to the third vehicle coordinates among the at least four vehicle obstacle attribute coordinates can be determined as the corresponding third coordinates to be adjusted.

[0144] Specifically, after determining the corresponding first coordinate to be adjusted, second coordinate to be adjusted, and third coordinate to be adjusted from at least four vehicle obstacle attribute coordinates, other coordinates in the at least four vehicle obstacle attribute coordinates can be determined as fourth coordinates to be adjusted. Based on the above description of the vehicle obstacle attribute coordinates included in the coordinate set corresponding to the target vehicle, it can be obtained that the number of the fourth coordinates to be adjusted is greater than or equal to one.

[0145] Step S602: Correct the first coordinate to be adjusted to the first vehicle coordinate, and correct the second coordinate to be adjusted to the second vehicle coordinate.

[0146] Specifically, the first coordinate to be adjusted can be corrected to the first vehicle coordinate, and the second coordinate to be adjusted can be corrected to the second vehicle coordinate, wherein: Figure 7 This is an example diagram of the initial traversable area after the first correction process provided by an embodiment of the present invention. Figure 7 For Figure 3 Based on the example diagram of the initial traversable area shown, an example diagram of the initial traversable area after the first coordinates to be adjusted are corrected to the first vehicle coordinates and the second coordinates to be adjusted are corrected to the second vehicle coordinates.

[0147] Step S603, correcting the vertical coordinate of the third coordinate to be adjusted according to the second side; and correcting the fourth coordinate to be adjusted according to the corrected second coordinate to be adjusted, the corrected third coordinate to be adjusted, and the number of the fourth coordinate to be adjusted.

[0148] Specifically, the vertical coordinate of the third coordinate to be adjusted can be corrected according to the second side. The present invention does not limit the process of correcting the vertical coordinate of the third coordinate to be adjusted according to the second side. Optionally, the vertical coordinate of the third coordinate to be adjusted can be maintained, and the horizontal coordinate of the third coordinate to be adjusted can be adjusted so that the third coordinate to be adjusted is adjusted to a position that coincides with the second side.

[0149] Specifically, after the vertical coordinate of the third coordinate to be adjusted is corrected according to the second side, the fourth coordinate to be adjusted can be corrected according to the second coordinate to be adjusted after the correction processing, the third coordinate to be adjusted after the correction processing, and the number of the fourth coordinate to be adjusted. Among them, the present invention does not limit the process of correcting the fourth coordinate to be adjusted according to the second coordinate to be adjusted after the correction processing, the third coordinate to be adjusted after the correction processing, and the number of the fourth coordinate to be adjusted. Optionally, interpolation calculation can be performed according to the second coordinate to be adjusted after the correction processing, the third coordinate to be adjusted after the correction processing, and the number of the fourth coordinate to be adjusted to obtain coordinates corresponding to the number of the fourth coordinate to be adjusted, and they are respectively determined as the fourth coordinate to be adjusted after the correction processing.

[0150] in, Figure 8 This is an example diagram of a traversable area provided by an embodiment of the present invention. Figure 8 For Figure 7 On the basis of the example diagram of the initial passable area after the first correction processing shown, the vertical coordinate of the third coordinate to be adjusted is corrected according to the second side; and based on the number of the second coordinate to be adjusted after the correction processing, the third coordinate to be adjusted after the correction processing, and the fourth coordinate to be adjusted, the example diagram of the passable area is obtained after the fourth coordinate to be adjusted is corrected.

[0151] The embodiment of the present invention provides a process for correcting a plurality of obstacle attribute coordinates included in a corresponding coordinate set according to the determined target feature coordinates to obtain a passable area of ​​the vehicle, by determining the corresponding first coordinate to be adjusted, the second coordinate to be adjusted, and the third coordinate to be adjusted from at least four vehicle obstacle attribute coordinates according to the first vehicle coordinate, the second vehicle coordinate, and the third vehicle coordinate; and determining the other coordinates in the at least four vehicle obstacle attribute coordinates as the fourth coordinate to be adjusted, correcting the first coordinate to be adjusted to the first vehicle coordinate, and correcting the second coordinate to be adjusted to the second vehicle coordinate, and correcting the longitudinal coordinate of the third coordinate to be adjusted according to the second side; and correcting the fourth coordinate to be adjusted according to the second coordinate to be adjusted after the correction processing, the third coordinate to be adjusted after the correction processing, and the number of the fourth coordinate to be adjusted, wherein the first coordinate to be adjusted, the second coordinate to be adjusted, the third coordinate to be adjusted, and the fourth coordinate to be adjusted are corrected in sequence according to the first vehicle coordinate, the second vehicle coordinate, and the third vehicle coordinate, so that the accuracy of the correction processing can be improved, and the accuracy of the obtained passable area can be further improved.

[0152] In a possible embodiment, the target obstacle also includes a target pedestrian, or a target cyclist, or a target cone barrel, or a target water barrier.

[0153] Among them, by setting multiple types of target obstacles, the accuracy of correcting the initial passable area according to the characteristic information of at least one target obstacle can be improved, and the accuracy of determining the passable area of ​​the vehicle can be further improved.

[0154] In a possible embodiment, the image information includes an image at the current moment. Based on the description of the image information in step S101, the image at the current moment is an image in front of the vehicle acquired by a capture device disposed in the vehicle at the current moment. Optionally, the process of acquiring the initial passable area of ​​the vehicle according to the image information may include:

[0155] First, based on the panoramic segmentation technology, the image at the current moment included in the image information can be subjected to image segmentation processing to obtain the image at the current moment after the segmentation processing.

[0156] Among them, ‌‌ Panoptic Segmentation is a combination of semantic segmentation and instance segmentation, which aims to simultaneously segment the target at the instance level and the background content at the semantic level. Panoptic segmentation requires that each pixel in the image is assigned a semantic label and an instance ID, where the semantic label represents the category of the object, and the instance ID corresponds to a different number of objects of the same type. This segmentation method not only distinguishes the category of the object, but also distinguishes different individuals in the same category, achieving a globally unified segmented image. The goal of panoptic segmentation is similar to that of semantic segmentation and instance segmentation, but it is different. Semantic segmentation classifies each pixel in the image without distinguishing different instances; instance segmentation distinguishes different instances on the basis of semantic segmentation; and panoptic segmentation combines the characteristics of the two and performs instance and semantic level segmentation at the same time. Among them, the image at the current moment after the segmentation process includes multiple image pixels. The image pixel indicates the pixel attribute. Specifically, based on the description of the above panoptic segmentation technology, the pixel attribute indicates the semantic label, that is, the category of the object, and the instance ID, that is, the different number of the same object.

[0157] Specifically, the present invention does not limit the process of performing image segmentation processing on the image at the current moment included in the image information based on the panoramic segmentation technology to obtain the image at the current moment after the segmentation processing. Optionally, the image at the current moment can be input into a pre-built panoramic segmentation model to output the image at the current moment after the segmentation processing.

[0158] Secondly, according to the pixel attributes indicated by the image pixels, a set of image pixels corresponding to the initial passable area can be determined from a plurality of image pixels included in the image at the current moment after the segmentation process.

[0159] The set of image pixels corresponding to the initial passable area is a set of image pixels corresponding to the boundary points of the space area where safe driving is possible. The present invention does not limit the process of determining the set of image pixels corresponding to the initial passable area from multiple image pixels included in the image at the current moment after segmentation processing according to the pixel attributes indicated by the image pixels. Any process that can determine the set of image pixels corresponding to the initial passable area from multiple image pixels included in the image at the current moment after segmentation processing according to the pixel attributes indicated by the image pixels can be used as the process provided by the present invention of determining the set of image pixels corresponding to the initial passable area from multiple image pixels included in the image at the current moment after segmentation processing according to the pixel attributes indicated by the image pixels.

[0160] Then, the set of image pixel points corresponding to the initial passable area can be processed according to the vehicle coordinate system conversion technology to obtain the initial passable area of ​​the vehicle.

[0161] Specifically, the set of image pixel points corresponding to the initial passable area described above can be processed according to the vehicle coordinate system conversion technology to obtain the initial passable area of ​​the vehicle. Among them, the set of image pixel points corresponding to the initial passable area described above is in the image coordinate system. The vehicle coordinate system conversion technology is a technology for converting an image coordinate system into a vehicle coordinate system. Among them, the present invention does not limit the vehicle coordinate system conversion technology, and any technology that can convert an image coordinate system into a vehicle coordinate system can be used as the vehicle coordinate system conversion technology provided by the present invention. Optionally, according to the parameters of the device that captures the image in front of the vehicle, such as the internal and external parameters of the camera, the coordinates of each image pixel point in the set of image pixel points corresponding to the initial passable area in the image coordinate system can be converted to obtain the set of image pixel points corresponding to the initial passable area in the vehicle coordinate system, that is, the initial passable area of ​​the vehicle.

[0162] Among them, in the process of obtaining the initial passable area of ​​the vehicle based on image information, the attributes of objects in front of the vehicle can be accurately identified based on the panoramic segmentation technology, and the image coordinate system can be converted into the vehicle coordinate system based on the vehicle coordinate system conversion technology, which can improve the accuracy of obtaining the initial passable area of ​​the vehicle and further improve the accuracy of obtaining the vehicle's passable area based on the vehicle's initial passable area.

[0163] In a possible embodiment, the image information includes an image at the current moment and an image at a historical moment. Based on the description of the image information in step S101, the image at the historical moment is an image in front of the vehicle acquired by a collection device disposed in the vehicle at the historical moment. Optionally, the process of acquiring feature information of at least one target obstacle according to the image information may include:

[0164] First, a current detection frame of at least one target obstacle can be obtained from an image at a current moment included in the image information; and a historical detection frame of at least one target obstacle can be obtained from an image at a historical moment included in the image information.

[0165] Among them, the detection frame refers to a rectangular frame used to identify and locate the position and outline of an object in an autonomous driving or intelligent transportation system. This detection frame is usually implemented through image processing and machine learning algorithms, and can accurately mark the specific position of the object in the image. Among them, the number of detection frames corresponding to each object in the image is different, and the number of detection frames corresponding to each object corresponds to the type of object. For example, if the object is a vehicle, the number of corresponding detection frames can be at least four. If the object is a pedestrian, a cone, a cyclist, or a water barrier, the number of corresponding detection frames can be one.

[0166] Among them, the present invention does not limit the process of obtaining the current detection frame of at least one target obstacle from the image at the current moment included in the image information, or the process of obtaining the historical detection frame of at least one target obstacle from the image at the historical moment included in the image information. Optionally, it can be achieved through the image processing and machine learning algorithms described above.

[0167] Secondly, at least one current detection frame and at least one historical detection frame corresponding to each target obstacle may be determined from at least one current detection frame of the target obstacle and at least one historical detection frame of the target obstacle.

[0168] Among them, the detection box is used to indicate the type and confidence of the corresponding object. As described above, the type of object can be one of a vehicle, a pedestrian, a cone, a cyclist, and a water barrier. Among them, the confidence is to accurately determine the type of the object corresponding to the detection box, and the confidence is a value between 0-1.

[0169] Among them, the current detection frame is the detection frame obtained from the image at the current moment. Specifically, at least one current detection frame corresponding to each target obstacle can be determined from the current detection frame of at least one target obstacle obtained from the image at the current moment included in the image information as described above. For example, if the target obstacle is a vehicle obstacle, the corresponding current detection frames obtained can be at least three, and optionally, they can be the current detection frame of the whole vehicle, the current detection frame of the rear of the vehicle, the current detection frame of the front of the vehicle, the current detection frame of the wheel, and the like.

[0170] The historical detection frame is a detection frame obtained from an image at a historical moment. Specifically, at least one historical detection frame corresponding to each target obstacle can be determined from the historical detection frame of at least one target obstacle obtained from an image at a historical moment included in the image information as described above. For example, if the target obstacle is a vehicle obstacle, the corresponding historical detection frames obtained can be at least three, and optionally, can be historical detection frames such as a whole vehicle historical detection frame, a rear vehicle historical detection frame, a front vehicle historical detection frame, and a wheel historical detection frame.

[0171] Specifically, at least one current detection frame and at least one historical detection frame corresponding to each target obstacle can be determined based on the target matching technology (Intersection over Union, abbreviated as IOU matching) and the feature vector matching technology, that is, all current detection frames and all historical detection frames corresponding to the same target obstacle can be determined from the current detection frame of at least one target obstacle and the historical detection frame of at least one target obstacle. Among them, the target matching technology, also known as the technology for determining the overlap between the predicted frame and the real frame, is a standard for measuring the accuracy of detecting the corresponding object in a specific data set. It represents the overlap between the predicted frame and the real frame, and is usually used to evaluate the accuracy of the detection result in the target detection task. Among them, in target detection, IOU matching is mainly used to measure the overlap between the predicted frame and the real frame. The dynamic IOU matching technology dynamically predicts the IOU value during the training process and combines it with the smooth label to provide a more accurate supervision signal. This dynamic matching method can adaptively adjust the sample division criteria according to the characteristics of different targets and the needs of the training stage, thereby improving the accuracy and efficiency of detection.

[0172] Then, feature information of each target obstacle may be determined according to at least one current detection frame and at least one historical detection frame corresponding to each target obstacle.

[0173] The characteristic information of the target obstacle is information that characterizes the characteristics of the target obstacle. The present invention does not limit the characteristic information of the target obstacle. Any information that can characterize the characteristics of the target obstacle can be used as the characteristic information of the target obstacle provided by the present invention. When the types of target obstacles are different, the corresponding characteristic information of the target obstacles is also different. For example, if the target obstacle is a target vehicle, the corresponding characteristic information of the target obstacle is information such as the coordinates of the center point of the vehicle, the length of the vehicle, the width of the vehicle, and the yaw angle of the vehicle.

[0174] Specifically, the present invention does not limit the process of determining the characteristic information of each target obstacle according to at least one current detection frame and at least one historical detection frame corresponding to each target obstacle. Optionally, if the target obstacle is a target vehicle, the process of determining the characteristic information of each target obstacle according to at least one current detection frame and at least one historical detection frame corresponding to each target obstacle may include: based on the external parameter ranging technology and the pinhole imaging technology, according to the whole vehicle historical detection frame, the rear vehicle historical detection frame, and the front vehicle historical detection frame, determining the vehicle center point coordinates, vehicle length, and vehicle width in the characteristic information of the target obstacle; according to the wheel historical detection frame.

[0175] In the process of acquiring characteristic information of at least one target obstacle based on image information, the characteristic information of each target obstacle can be accurately determined through the current detection frame and the historical detection frame of the target obstacle, thereby further improving the accuracy of determining the passable area based on the characteristic information of the target obstacle.

[0176] Fig. 9 A schematic diagram of the structure of a device for confirming a passable area provided by an embodiment of the present invention is shown in FIG. Fig. 9 As shown, the apparatus 900 for confirming the passable area in the embodiment of the present invention includes:

[0177] An acquisition module 901 is used to acquire image information in front of the vehicle;

[0178] The processing module 902 is used to obtain an initial passable area of ​​the vehicle according to the image information, and obtain characteristic information of at least one target obstacle according to the image information; wherein the target obstacle is an obstacle that invades the initial passable area;

[0179] The determination module 903 is used to correct the initial passable area according to the characteristic information of at least one target obstacle to obtain the passable area for the vehicle.

[0180] In a possible embodiment, the determining module 903 includes:

[0181] A first determining unit is used to determine, for each target obstacle, characteristic coordinates of at least one target obstacle according to characteristic information of the target obstacle; wherein the characteristic coordinates of the target obstacle are coordinates of a preset position of the target obstacle in a vehicle coordinate system;

[0182] The second determination unit is used to determine one or more target characteristic coordinates from the characteristic coordinates of at least one target obstacle, and to perform correction processing on the initial passable area according to the target characteristic coordinates to obtain the passable area for the vehicle.

[0183] In a possible embodiment, the target obstacle includes a target vehicle, and the characteristic information of the target obstacle includes: vehicle center point coordinates, vehicle length, vehicle width, and vehicle yaw angle; the characteristic coordinates of the target obstacle are the vehicle left front coordinates, or the vehicle right front coordinates, or the vehicle right rear coordinates, or the vehicle left rear coordinates.

[0184] In a possible embodiment, the first determination unit is specifically used to determine a calculation method for characteristic coordinates of the target obstacle based on the vehicle center point coordinates and the vehicle yaw angle included in the characteristic information of the target obstacle; and calculate the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates based on the vehicle center point coordinates, the vehicle length, the vehicle width, and the vehicle yaw angle included in the characteristic information of the target obstacle, and the calculation method for the characteristic coordinates of the target obstacle.

[0185] In a possible embodiment, the initial passable area includes at least one coordinate set; wherein the coordinate set corresponds to the target obstacle one-to-one; the coordinate set includes multiple obstacle attribute coordinates; the target obstacle indicates the obstacle type; the second determination unit is specifically used to determine one or more target feature coordinates from the feature coordinates of at least one target obstacle for each target obstacle according to the obstacle type indicated by the target obstacle; select the coordinate set corresponding to the target obstacle from the at least one coordinate set included in the initial passable area; and perform correction processing on the multiple obstacle attribute coordinates included in the corresponding coordinate set according to the determined target feature coordinates to obtain the passable area of ​​the vehicle.

[0186] In a possible embodiment, the target obstacle includes a target vehicle, and the characteristic information of the target obstacle includes: vehicle center point coordinates, vehicle yaw angle; the characteristic coordinates of the target obstacle are vehicle left front coordinates, or vehicle right front coordinates, or vehicle right rear coordinates, or vehicle left rear coordinates; the target characteristic coordinates include: first vehicle coordinates, second vehicle coordinates, and third vehicle coordinates; wherein the first vehicle coordinates and the second vehicle coordinates are coordinates corresponding to two endpoints of a first side of the target vehicle; the second vehicle coordinates and the third vehicle coordinates are coordinates corresponding to two endpoints of a second side of the target vehicle; wherein the first side is the side of the target vehicle facing the vehicle; the second side is the side of the target vehicle adjacent to the first side, corresponding to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle.

[0187] In a possible embodiment, the second determination unit is further specifically used to determine the first side according to the vehicle yaw angle of the target vehicle, and determine the two coordinates corresponding to the two endpoints of the first side from the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates; determine the second side according to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle, and determine the two coordinates corresponding to the two endpoints of the second side from the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates; determine the two coordinates corresponding to the two endpoints of the first side that are the same as the two coordinates corresponding to the two endpoints of the second side as second vehicle coordinates, determine the remaining coordinates of the two coordinates corresponding to the two endpoints of the first side as first vehicle coordinates, and determine the remaining coordinates of the two coordinates corresponding to the two endpoints of the second side as third vehicle coordinates.

[0188] In a possible embodiment, the coordinate set corresponding to the target vehicle includes at least four vehicle obstacle attribute coordinates; the second determination unit is further specifically used to determine the corresponding first coordinate to be adjusted, second coordinate to be adjusted, and third coordinate to be adjusted from the at least four vehicle obstacle attribute coordinates according to the first vehicle coordinate, the second vehicle coordinate, and the third vehicle coordinate; and determine the other coordinates in the at least four vehicle obstacle attribute coordinates as fourth coordinates to be adjusted; wherein the number of fourth coordinates to be adjusted is greater than or equal to one; correct the first coordinate to be adjusted to the first vehicle coordinate, and correct the second coordinate to be adjusted to the second vehicle coordinate; according to the second side, correct the longitudinal coordinate of the third coordinate to be adjusted; and correct the fourth coordinate to be adjusted according to the corrected second coordinate to be adjusted, the corrected third coordinate to be adjusted, and the number of fourth coordinates to be adjusted.

[0189] In a possible embodiment, the target obstacle also includes a target pedestrian, or a target cyclist, or a target cone barrel, or a target water barrier.

[0190] In a possible embodiment, the image information includes an image at a current moment; the processing module 902 is specifically used to perform image segmentation processing on the image at the current moment included in the image information based on a panoramic segmentation technology to obtain the image at the current moment after the segmentation processing; wherein the image at the current moment after the segmentation processing includes a plurality of image pixels; the image pixels indicate pixel attributes; according to the pixel attributes indicated by the image pixels, a set of image pixels corresponding to an initial passable area is determined from a plurality of image pixels included in the image at the current moment after the segmentation processing; according to the vehicle coordinate system conversion technology, the set of image pixels corresponding to the initial passable area is processed to obtain the initial passable area of ​​the vehicle.

[0191] In a possible embodiment, the image information includes an image at a current moment and images at historical moments; the processing module 902 is further specifically used to obtain a current detection frame of at least one target obstacle from the image at the current moment included in the image information; and obtain a historical detection frame of at least one target obstacle from the images at historical moments included in the image information; determine at least one current detection frame and at least one historical detection frame corresponding to each target obstacle from the current detection frame of the at least one target obstacle and the historical detection frame of the at least one target obstacle; and determine feature information of each target obstacle according to the at least one current detection frame and at least one historical detection frame corresponding to each target obstacle.

[0192] In a possible embodiment, the determination module 903 is also used to present the vehicle's passable area so that the user can control the vehicle's driving based on the vehicle's passable area; or, control the vehicle to perform automatic driving based on the vehicle's passable area.

[0193] The device of the embodiment of the present invention can be used to execute the technical solution of any of the above-mentioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0194] Fig.10 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Fig.10 As shown, the electronic device 100 may include: at least one processor 101 and a memory 102 .

[0195] The memory 102 is used to store programs. Specifically, the programs may include program codes, and the program codes include computer-executable instructions.

[0196] The memory 102 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0197] The processor 101 is used to execute the computer-executable instructions stored in the memory 102 to implement the method for confirming the passable area described in the above method embodiment. The processor 101 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiment of the present invention. Specifically, when implementing the method for confirming the passable area described in the above method embodiment, the electronic device may be, for example, an electronic control unit on a vehicle, a server, or other electronic device with processing functions.

[0198] Optionally, the electronic device 100 may further include a communication interface 103. In a specific implementation, if the communication interface 103, the memory 102 and the processor 101 are implemented independently, the communication interface 103, the memory 102 and the processor 101 may be interconnected through a bus and communicate with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0199] Optionally, in a specific implementation, if the communication interface 103, the memory 102 and the processor 101 are integrated on a chip, the communication interface 103, the memory 102 and the processor 101 can communicate through an internal interface.

[0200] The present invention also provides a computer-readable storage medium, in which computer program instructions are stored. When a processor executes the computer program instructions, the method for confirming a passable area as described above is implemented.

[0201] The present invention also provides a computer program product, including a computer program, which implements the above-mentioned method for confirming a passable area when executed by a processor.

[0202] The present invention also provides a car, comprising an electronic device for implementing the above method for confirming a passable area.

[0203] The computer-readable storage medium mentioned above may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium may be any available medium that can be accessed by a general or special purpose computer.

[0204] An exemplary readable storage medium is coupled to the processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in a dedicated integrated circuit. Of course, the processor and the readable storage medium can also be present as discrete components in the confirmation device of the passable area.

[0205] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0206] Finally, it should be noted that the above embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Any equivalent substitution or change made by a person skilled in the art based on the present invention is within the protection scope of the present invention.

Claims

1. A method for confirming a passable area, characterized in that: include: Acquire image information in front of the vehicle; Acquire an initial passable area of ​​the vehicle according to the image information, and acquire characteristic information of at least one target obstacle according to the image information; wherein the target obstacle is an obstacle that invades the initial passable area; The initial traversable area is corrected according to the characteristic information of the at least one target obstacle to obtain the traversable area of ​​the vehicle.

2. The method according to claim 1, characterized in that: According to the characteristic information of the at least one target obstacle, the initial passable area is corrected to obtain the passable area of ​​the vehicle, including: For each of the target obstacles, determining at least one characteristic coordinate of the target obstacle according to the characteristic information of the target obstacle; wherein the characteristic coordinate of the target obstacle is the coordinate of a preset position of the target obstacle in the vehicle coordinate system; One or more target characteristic coordinates are determined from the characteristic coordinates of the at least one target obstacle, and the initial traversable area is corrected according to the target characteristic coordinates to obtain the traversable area of ​​the vehicle.

3. The method according to claim 2, characterized in that The target obstacle includes a target vehicle, and the characteristic information of the target obstacle includes: vehicle center point coordinates, vehicle length, vehicle width, and vehicle yaw angle; the characteristic coordinates of the target obstacle are vehicle left front coordinates, vehicle right front coordinates, vehicle right rear coordinates, or vehicle left rear coordinates.

4. The method according to claim 3, characterized in that Determining characteristic coordinates of at least one target obstacle according to the characteristic information of the target obstacle includes: Determining a calculation method of characteristic coordinates of the target obstacle according to the vehicle center point coordinates and the vehicle yaw angle included in the characteristic information of the target obstacle; According to the vehicle center point coordinates, the vehicle length, the vehicle width, and the vehicle yaw angle included in the characteristic information of the target obstacle, and the calculation method of the characteristic coordinates of the target obstacle, the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates are calculated.

5. The method according to claim 2, characterized in that: The initial passable area includes at least one coordinate set; wherein the coordinate set corresponds to the target obstacle one by one; the coordinate set includes a plurality of obstacle attribute coordinates; the target obstacle indicates the obstacle type; Determining one or more target characteristic coordinates from the characteristic coordinates of the at least one target obstacle, and performing correction processing on the initial passable area according to the target characteristic coordinates to obtain the passable area of ​​the vehicle, including: For each of the target obstacles, determining one or more target characteristic coordinates from the characteristic coordinates of the at least one target obstacle according to the obstacle type indicated by the target obstacle; Selecting a coordinate set corresponding to the target obstacle from at least one coordinate set included in the initial traversable area; According to the determined target feature coordinates, a plurality of obstacle attribute coordinates included in the corresponding coordinate set are corrected to obtain a passable area for the vehicle.

6. The method according to claim 5, characterized in that The target obstacle includes a target vehicle, and the characteristic information of the target obstacle includes: vehicle center point coordinates and vehicle yaw angle; the characteristic coordinates of the target obstacle are vehicle left front coordinates, vehicle right front coordinates, vehicle right rear coordinates, or vehicle left rear coordinates; the target characteristic coordinates include: first vehicle coordinates, second vehicle coordinates, and third vehicle coordinates; Among them, the first vehicle coordinates and the second vehicle coordinates are the coordinates corresponding to the two end points of the first side of the target vehicle; the second vehicle coordinates and the third vehicle coordinates are the coordinates corresponding to the two end points of the second side of the target vehicle; wherein, the first side is the side of the target vehicle facing the vehicle; the second side is the side of the target vehicle adjacent to the first side, corresponding to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle.

7. The method according to claim 6, characterized in that Determining one or more target characteristic coordinates from the characteristic coordinates of the at least one target obstacle according to the obstacle type indicated by the target obstacle, including: Determine the first side according to the vehicle yaw angle of the target vehicle, and determine two coordinates corresponding to two endpoints of the first side from the vehicle left front coordinate, the vehicle right front coordinate, the vehicle right rear coordinate, and the vehicle left rear coordinate; Determine the second side according to the vehicle center point coordinates and the vehicle yaw angle of the target vehicle, and determine two coordinates corresponding to two endpoints of the second side from the vehicle left front coordinates, the vehicle right front coordinates, the vehicle right rear coordinates, and the vehicle left rear coordinates; The two coordinates corresponding to the two endpoints of the first side are determined as the second vehicle coordinates, and the remaining coordinates of the two coordinates corresponding to the two endpoints of the second side are determined as the first vehicle coordinates, and the remaining coordinates of the two coordinates corresponding to the two endpoints of the second side are determined as the third vehicle coordinates.

8. The method according to claim 7, characterized in that The coordinate set corresponding to the target vehicle includes at least four vehicle obstacle attribute coordinates; According to the determined target feature coordinates, a plurality of obstacle attribute coordinates included in the corresponding coordinate set are corrected to obtain a passable area for the vehicle, including: According to the first vehicle coordinate, the second vehicle coordinate, and the third vehicle coordinate, the corresponding first coordinate to be adjusted, the second coordinate to be adjusted, and the third coordinate to be adjusted are determined from the at least four vehicle obstacle attribute coordinates; and the other coordinates in the at least four vehicle obstacle attribute coordinates are determined as fourth coordinates to be adjusted; wherein the number of the fourth coordinates to be adjusted is greater than or equal to one; Correcting the first coordinates to be adjusted to the first vehicle coordinates, and correcting the second coordinates to be adjusted to the second vehicle coordinates; According to the second side, the vertical coordinate of the third coordinate to be adjusted is corrected; and according to the corrected second coordinate to be adjusted, the corrected third coordinate to be adjusted, and the number of the fourth coordinate to be adjusted, the fourth coordinate to be adjusted is corrected.

9. The method according to claim 1, characterized in that: The target obstacles also include target pedestrians, or target cyclists, or target cone barrels, or target water barriers.

10. The method according to claim 1, characterized in that The image information includes an image at the current moment; obtaining an initial passable area of ​​the vehicle according to the image information includes: Based on the panoramic segmentation technology, the image at the current moment included in the image information is subjected to image segmentation processing to obtain the image at the current moment after the segmentation processing; wherein the image at the current moment after the segmentation processing includes a plurality of image pixels; and the image pixels indicate pixel attributes; Determining, according to the pixel attributes indicated by the image pixel points, a set of image pixel points corresponding to the initial passable area from a plurality of image pixel points included in the image at the current moment after the segmentation process; According to the vehicle coordinate system conversion technology, the set of image pixel points corresponding to the initial passable area is processed to obtain the initial passable area of ​​the vehicle.

11. The method according to claim 1, characterized in that: The image information includes an image at a current moment and an image at a historical moment; acquiring feature information of at least one target obstacle according to the image information includes: Acquire a current detection frame of at least one target obstacle from an image at a current moment included in the image information; and acquire a historical detection frame of at least one target obstacle from an image at a historical moment included in the image information; Determining at least one current detection frame and at least one historical detection frame corresponding to each target obstacle from the current detection frame of the at least one target obstacle and the historical detection frame of the at least one target obstacle; Determine feature information of each target obstacle according to at least one current detection frame and at least one historical detection frame corresponding to each target obstacle.

12. The method according to any one of claims 1 to 11, characterized in that: The method further comprises: Presenting a passable area of ​​the vehicle so that a user can control the driving of the vehicle based on the passable area of ​​the vehicle; Alternatively, the vehicle is controlled to perform automatic driving according to the passable area of ​​the vehicle.

13. A device for confirming a passable area, characterized in that: include: An acquisition module, used for acquiring image information in front of the vehicle; A processing module, configured to obtain an initial passable area of ​​the vehicle according to the image information, and obtain characteristic information of at least one target obstacle according to the image information; wherein the target obstacle is an obstacle that invades the initial passable area; The determination module is used to correct the initial passable area according to the characteristic information of the at least one target obstacle to obtain the passable area of ​​the vehicle.

14. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 12 when executed by a processor.

16. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 12.

17. A car, characterized in that: The invention comprises an electronic device for executing the method for confirming a passable area as described in any one of claims 1 to 12.

Images