CN113469159B

CN113469159B - Obstacle information generation method and device, electronic equipment and computer readable medium

Info

Publication number: CN113469159B
Application number: CN202111035899.7A
Authority: CN
Inventors: 杨航; 付垚
Original assignee: HoloMatic Technology Beijing Co Ltd
Current assignee: Heduo Technology Guangzhou Co ltd
Priority date: 2021-09-06
Filing date: 2021-09-06
Publication date: 2021-12-07
Anticipated expiration: 2041-09-06
Also published as: CN113469159A

Abstract

The embodiment of the disclosure discloses an obstacle information generation method, an obstacle information generation device, electronic equipment and a computer readable medium. One embodiment of the method comprises: generating a first set of obstacle information; generating a second set of obstacle information; determining obstacle information corresponding to obstacles in the target range as third obstacle information; determining a distance value between first sub-obstacle information corresponding to the third sub-obstacle information; determining a distance value between second sub-obstacle information corresponding to the third sub-obstacle information; respectively carrying out feature vectorization processing on each first distance value group in the obtained at least one first distance value group and each second distance value group in the obtained at least one second distance value group; and inputting the first feature vector set and the second feature vector set into a pre-trained binary model to generate an obstacle information set. This embodiment improves the safety of the autonomous vehicle in traveling.

Description

Obstacle information generation method and device, electronic equipment and computer readable medium

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to a method and a device for generating obstacle information, electronic equipment and a computer readable medium.

Background

With the development of the technology related to the automatic driving, the automatic driving vehicle gradually walks into the field of vision of people. In order to ensure the safety of the autonomous vehicle during driving, it is important to detect obstacles around the vehicle during driving. At present, when detecting an obstacle to generate obstacle information, the following methods are generally adopted: obstacle detection is performed directly by a detection device (e.g., a laser radar) mounted on the vehicle.

However, when the obstacle information generation is performed in the above manner, there are often technical problems as follows:

firstly, because the detection range of the laser radar is limited, the obstacle at a longer distance cannot be detected in advance, so that the accuracy of subsequent vehicle path planning is influenced, and the running safety of the automatic driving vehicle is further reduced.

Secondly, by acquiring the obstacle information sent by the plurality of detection devices, because the obstacle information sent by the plurality of detection devices often has the obstacle information corresponding to the same obstacle, the processing amount and the processing time of data are increased, and further, the time for planning the vehicle path is shortened, so that the safety of the automatic driving vehicle in running is low.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose an obstacle information generation method, apparatus, electronic device, and computer-readable medium to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide an obstacle information generating method, including: in response to receiving first broadcast information sent by a target road side unit, generating a first obstacle information set according to the first broadcast information, wherein an obstacle corresponding to first obstacle information in the first obstacle information set is an obstacle in a sensing range of the target road side unit, and the first obstacle information in the first obstacle information set comprises: a first sub-obstacle information group; in response to receiving second broadcast information sent by a target vehicle, generating a second obstacle information set according to the second broadcast information, wherein an obstacle corresponding to second obstacle information in the second obstacle information set is an obstacle in a sensing range of the target vehicle, and the second obstacle information in the second obstacle information set comprises: a second sub-obstacle information set; determining obstacle information corresponding to obstacles in a target range as third obstacle information to obtain a third obstacle information set, wherein the third obstacle information in the third obstacle information set comprises: a third sub-obstacle information group; for each piece of third obstacle information in the third obstacle information set, determining a distance value between each piece of third sub-obstacle information in a third sub-obstacle information group included in the third obstacle information and first sub-obstacle information corresponding to the third sub-obstacle information in a first sub-obstacle information group included in first obstacle information in the first obstacle information set, so as to generate a first distance value, and obtaining a first distance value group; for each piece of third obstacle information in the third obstacle information set, determining a distance value between each piece of third sub-obstacle information in a third sub-obstacle information group included in the third obstacle information and a piece of second sub-obstacle information corresponding to the third sub-obstacle information in a second sub-obstacle information group included in second obstacle information in the second obstacle information set, so as to generate a second distance value, and obtaining a second distance value group; respectively carrying out feature vectorization processing on each first distance value group in the obtained at least one first distance value group and each second distance value group in the obtained at least one second distance value group to generate a first feature vector and a second feature vector, and obtaining a first feature vector set and a second feature vector set; and inputting the first feature vector set and the second feature vector set into a pre-trained binary classification model to generate an obstacle information set.

In a second aspect, some embodiments of the present disclosure provide an obstacle information generating apparatus, the apparatus comprising: a first generating unit configured to generate a first set of obstacle information according to first broadcast information sent by a target road side unit in response to receiving the first broadcast information, wherein an obstacle corresponding to first obstacle information in the first set of obstacle information is an obstacle in a sensing range of the target road side unit, and the first obstacle information in the first set of obstacle information includes: a first sub-obstacle information group; a second generating unit configured to generate a second obstacle information set according to second broadcast information sent by a target vehicle in response to receiving the second broadcast information, wherein an obstacle corresponding to second obstacle information in the second obstacle information set is an obstacle in a sensing range of the target vehicle, and the second obstacle information in the second obstacle information set includes: a second sub-obstacle information set; a first determining unit, configured to determine obstacle information corresponding to an obstacle in a target range as third obstacle information, and obtain a third obstacle information set, where the third obstacle information in the third obstacle information set includes: a third sub-obstacle information group; a second determination unit configured to determine, for each third obstacle information in the third obstacle information set, a distance value between each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information and a first sub-obstacle information corresponding to the third sub-obstacle information in a first sub-obstacle information set included in first obstacle information in the first obstacle information set, to generate a first distance value, resulting in a first distance value set; a third determining unit configured to determine, for each third obstacle information in the third obstacle information set, a distance value between each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information and a second sub-obstacle information corresponding to the third sub-obstacle information in a second sub-obstacle information set included in a second obstacle information in the second obstacle information set, to generate a second distance value, resulting in a second distance value set; a feature vectorization unit configured to perform feature vectorization processing on each of the obtained at least one first distance value group and each of the obtained at least one second distance value group to generate a first feature vector and a second feature vector, resulting in a first feature vector set and a second feature vector set; an input unit configured to input the first feature vector set and the second feature vector set into a pre-trained binary model to generate an obstacle information set.

In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method described in any of the implementations of the first aspect.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect.

The above embodiments of the present disclosure have the following advantages: the safety of the autonomous vehicle running is improved by the obstacle information generating method of some embodiments of the present disclosure. Specifically, the reason why the traveling safety of the autonomous vehicle is low is that: due to the fact that the detection range of the laser radar is limited, obstacles in a long distance cannot be detected in advance, and therefore accuracy of subsequent vehicle path planning is affected. Based on this, some embodiments of the present disclosure first generate a first set of obstacle information according to first broadcast information sent by a target roadside unit, where an obstacle corresponding to first obstacle information in the first set of obstacle information is an obstacle within a sensing range of the target roadside unit, and the first obstacle information in the first set of obstacle information includes: a first sub-obstacle information set. Secondly, in response to receiving second broadcast information sent by a target vehicle, generating a second obstacle information set according to the second broadcast information, wherein an obstacle corresponding to second obstacle information in the second obstacle information set is an obstacle in a sensing range of the target vehicle, and the second obstacle information in the second obstacle information set comprises: a second sub-obstacle information set. Then, determining obstacle information corresponding to an obstacle in the target range as third obstacle information to obtain a third obstacle information set, wherein the third obstacle information in the third obstacle information set includes: a third sub-obstacle information set. In some cases, when the autonomous vehicle detects an obstacle around the vehicle, the obstacle information detected by the detection device on the autonomous vehicle is not accurate enough because the sensing range of the detection device on the autonomous vehicle is limited and the detection device is easily interfered by the outside. Therefore, a plurality of different detection devices (for example, the target road-side unit and the target vehicle) are used to detect the obstacle, thereby widening the detection range. Next, for each third obstacle information in the third obstacle information set, a distance value between each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information and a first sub-obstacle information corresponding to the third sub-obstacle information in a first sub-obstacle information set included in the first obstacle information set is determined to generate a first distance value, and a first distance value set is obtained. Then, for each third obstacle information in the third obstacle information set, a distance value between each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information and a second sub-obstacle information corresponding to the third sub-obstacle information in a second sub-obstacle information set included in a second obstacle information in the second obstacle information set is determined to generate a second distance value, and a second distance value set is obtained. In practical situations, by acquiring the obstacle information sent by the plurality of detection devices, since the obstacle information sent by the plurality of detection devices often has obstacle information corresponding to the same obstacle, the processing amount and the processing time of data are increased, and further, the time for planning the vehicle path is shortened, so that the safety of the automatic driving vehicle in running is reduced. Accordingly, the present disclosure determines the first obstacle information and the third obstacle information, and the correlation between the second obstacle information and the third obstacle information by generating the first distance value group and the second distance value group, respectively. Then, respectively carrying out feature vectorization processing on each first distance value group in the obtained at least one first distance value group and each second distance value group in the obtained at least one second distance value group to generate a first feature vector and a second feature vector, so as to obtain a first feature vector set and a second feature vector set. And performing feature vectorization processing on the first distance value group and the second distance value group to generate data which can be processed by the two-classification model. And finally, inputting the first feature vector set and the second feature vector set into a pre-trained binary classification model to generate an obstacle information set. According to the pre-trained two-classification model, the feature vectors can be classified more accurately through the machine learning model. Therefore, the information of a plurality of obstacles is better determined to correspond to the same obstacle, and the accuracy of the information of the obstacles is improved. In addition, the obstacles at a longer distance are detected in advance, so that the timeliness of vehicle path planning can be improved, sufficient control time is reserved for automatic vehicle control, and the driving safety of the vehicle is ensured.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.

Fig. 1 is a schematic diagram of one application scenario of the obstacle information generation method of some embodiments of the present disclosure;

fig. 2 is a flow diagram of some embodiments of an obstacle information generation method according to the present disclosure;

FIG. 3 is a flow diagram of further embodiments of an obstacle information generating method according to the present disclosure;

fig. 4 is a schematic structural diagram of some embodiments of an obstacle information generating apparatus according to the present disclosure;

FIG. 5 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 is a schematic diagram of an application scenario of the obstacle information generation method of some embodiments of the present disclosure.

In the application scenario of fig. 1, first, in response to receiving first broadcast information 102 sent by a target roadside unit, a computing device 101 may generate a first set of obstacle information 104 according to the first broadcast information 102, where an obstacle corresponding to first obstacle information in the first set of obstacle information 104 is an obstacle within a sensing range of the target roadside unit, and the first obstacle information in the first set of obstacle information 104 includes: a first sub-obstacle information set. Secondly, in response to receiving second broadcast information 103 sent by a target vehicle, the computing device 101 may generate a second set of obstacle information 106 according to the second broadcast information 103, where an obstacle corresponding to second obstacle information in the second set of obstacle information 106 is an obstacle in a sensing range of the target vehicle, and the second obstacle information in the second set of obstacle information 106 includes: a second sub-obstacle information set. Next, the computing device 101 may determine obstacle information corresponding to an obstacle within the target range as third obstacle information, resulting in a third obstacle information set 105, where the third obstacle information in the third obstacle information set 105 includes: a third sub-obstacle information set. Then, the computing device 101 may determine, for each third obstacle information in the third obstacle information set 105, a distance value between each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information and a first sub-obstacle information corresponding to the third sub-obstacle information in a first sub-obstacle information set included in the first obstacle information set 104, to generate a first distance value, resulting in a first distance value set. Then, the computing device 101 may determine, for each of the third obstacle information in the third obstacle information set 105, a distance value between each of the third sub-obstacle information in the third sub-obstacle information set included in the third obstacle information and the second sub-obstacle information corresponding to the third sub-obstacle information in the second sub-obstacle information set included in the second obstacle information set 106, to generate a second distance value, resulting in a second distance value set. Next, the computing device 101 may perform feature vectorization processing on each of the obtained at least one first distance value group 107 and each of the obtained at least one second distance value group 108 to generate a first feature vector and a second feature vector, respectively, resulting in a first feature vector set 109 and a second feature vector set 110. Finally, the computing device 101 may input the first set of feature vectors 109 and the second set of feature vectors 110 into a pre-trained classification model 111 to generate a set of obstacle information 112.

The computing device 101 may be hardware or software. When the computing device is hardware, it may be implemented as a distributed cluster composed of multiple servers or terminal devices, or may be implemented as a single server or a single terminal device. When the computing device is embodied as software, it may be installed in the hardware devices enumerated above. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.

It should be understood that the number of computing devices in FIG. 1 is merely illustrative. There may be any number of computing devices, as implementation needs dictate.

With continued reference to fig. 2, a flow 200 of some embodiments of an obstacle information generation method according to the present disclosure is shown. The obstacle information generation method includes the following steps:

step 201, in response to receiving first broadcast information sent by a target road side unit, generating a first obstacle information set according to the first broadcast information.

In some embodiments, an executing subject of the obstacle information generating method (e.g., the computing device 101 shown in fig. 1) may generate a first set of obstacle information from first broadcast information transmitted by a target roadside unit in response to receiving the first broadcast information. The first obstacle information in the first obstacle information set may include: a first sub-obstacle information set. The obstacle corresponding to the first obstacle information in the first obstacle information set may be an obstacle within the sensing range of the target rsu. The target roadside unit may be a device that communicates with the vehicle. The first broadcast information may include first information in a first information list. The first information includes obstacle information corresponding to the same obstacle at different times. The first information list may be a list for storing the first information. The first information may be obstacle information corresponding to an obstacle detected by the target drive test unit. The target road side unit can acquire first information corresponding to the obstacle in the first target range through the installed radar. The first target range is a range centered on the target road-side unit and having a radius equal to a maximum perceived radius of a radar mounted on the target road-side unit. The target rsu may broadcast the first broadcast information within a second target range. The second target range is a range centered on the target rsu and having a radius equal to a maximum broadcast radius corresponding to the target rsu. The first sub-obstacle information in the first sub-obstacle information group may be obstacle information corresponding to the same obstacle detected by the target drive test unit at different times. The first sub-obstacle information group may include a target number of first sub-obstacle information. Wherein the target number may be 10. The first sub-obstacle information in the first sub-obstacle information set may include a first sub-obstacle identification and first sub-obstacle coordinates. The first sub-obstacle indicator may be an indicator corresponding to the first sub-obstacle information. The first sub-obstacle coordinates may be coordinates of an obstacle corresponding to the first sub-obstacle information. The execution main body may generate the first obstacle information set by using, as a first sub-obstacle information group, obstacle information corresponding to the same obstacle at different times in the first information included in the first broadcast information. As an example, the above-mentioned first obstacle information set may be { a first sub-obstacle information group a [ first sub-obstacle information (first sub-obstacle identification: 001, first sub-obstacle coordinate (1, 3)), first sub-obstacle information (first sub-obstacle identification: 002, first sub-obstacle coordinate (1, 2)), first sub-obstacle information (first sub-obstacle identification: 003, first sub-obstacle coordinate (2, 1)) ], a first sub-obstacle information group B [ first sub-obstacle information (first sub-obstacle identification: 001, first sub-obstacle coordinate (2, 3) ], first sub-obstacle information (first sub-obstacle identification: 002, first sub-obstacle coordinate (2, 2) ], first sub-obstacle information (first sub-obstacle identification: 003, first sub-obstacle coordinate (3, 1)) ].

Step 202, in response to receiving second broadcast information sent by the target vehicle, generating a second obstacle information set according to the second broadcast information.

In some embodiments, the execution subject may generate a second set of obstacle information according to second broadcast information sent by the target vehicle in response to receiving the second broadcast information. The second obstacle information in the second obstacle information set may include: a second sub-obstacle information set. The obstacle corresponding to the second obstacle information in the second obstacle information set may be an obstacle within the sensing range of the target vehicle. The target vehicle may be a vehicle that communicates with the vehicle in which the execution subject is located. The second broadcast information may include second information in a second information list. The second information includes obstacle information corresponding to the same obstacle at different times. The above-mentioned second information list may be a list for storing the second information. The second information may be obstacle information corresponding to an obstacle detected by the target vehicle. The target vehicle may obtain second information corresponding to an obstacle within a third target range through the installed radar. The third target range is a range centered on the target vehicle and having a radius equal to a maximum perceived radius of a radar mounted on the target vehicle. The target vehicle may broadcast the second broadcast information within a fourth target range. The fourth target range is a range centered on the target vehicle and having a radius equal to a maximum broadcast radius corresponding to the target vehicle. The second sub-obstacle information group may be obstacle information corresponding to the target vehicle detecting the same obstacle at different times. The second sub-obstacle information group may include a target number of second sub-obstacle information. Wherein the target number may be 10. The second sub-obstacle information in the second sub-obstacle information set may include a second sub-obstacle identification and second sub-obstacle coordinates. The second sub-obstacle identifier may be an identifier corresponding to the second sub-obstacle information. The second sub-obstacle coordinates are coordinates of second sub-obstacle information. The execution main body may generate the second obstacle information set by using, as a second sub-obstacle information group, obstacle information corresponding to the same obstacle at different times in second information included in the second broadcast information. As an example, the second obstacle information set may be { a second sub-obstacle information set a [ second sub-obstacle information (second sub-obstacle identification: 001, second sub-obstacle coordinate (1, 3)), second sub-obstacle information (second sub-obstacle identification: 002, second sub-obstacle coordinate (1, 2)), second sub-obstacle information (second sub-obstacle identification: 003, second sub-obstacle coordinate (2, 1)) ], a second sub-obstacle information set B [ second sub-obstacle information (second sub-obstacle identification: 001, second sub-obstacle coordinate (2, 3) ], second sub-obstacle information (second sub-obstacle identification: 002, second sub-obstacle coordinate (2, 2) ], second sub-obstacle information (second sub-obstacle identification: 003, second sub-obstacle coordinate (3, 1)) ].

Step 203, determining the obstacle information corresponding to the obstacle in the target range as third obstacle information to obtain a third obstacle information set.

In some embodiments, the execution subject may determine obstacle information corresponding to an obstacle within the target range as third obstacle information, to obtain a third obstacle information set. Wherein the third obstacle information in the third obstacle information set includes: a third sub-obstacle information set. The obstacle corresponding to the third obstacle information in the third obstacle information set may be an obstacle within a vehicle sensing range in which the execution subject is located. The target range is a range centered on the vehicle in which the execution subject is located and having a radius equal to a maximum perceived radius of a radar mounted on the vehicle in which the execution subject is located. The third obstacle information may be obstacle information corresponding to an obstacle detected by a radar mounted on the vehicle in which the execution subject is located. The execution main body can acquire second obstacle information corresponding to the obstacle in the target range through the installed radar. The third sub-obstacle information may be obstacle information corresponding to the same obstacle detected by the vehicle in which the execution subject is located at different times. The third sub-obstacle information group may include a target number of third sub-obstacle information. Wherein the target number may be 10. The third sub-obstacle information in the third sub-obstacle information set may include a third sub-obstacle identification and a third sub-obstacle coordinate. The third sub-obstacle indicator may be an indicator corresponding to the third obstacle information. The third sub-obstacle coordinates are coordinates corresponding to the third obstacle information. As an example, the third obstacle information set may be { a third sub-obstacle information set a [ third sub-obstacle information (third sub-obstacle flag: 001, third sub-obstacle coordinate (1, 3)), third sub-obstacle information (third sub-obstacle flag: 002, third sub-obstacle coordinate (1, 2)), third sub-obstacle information (third sub-obstacle flag: 003, third sub-obstacle coordinate (2, 1)) ], a third sub-obstacle information set B [ third sub-obstacle information (third sub-obstacle flag: 001, third sub-obstacle coordinate (2, 3) ], third sub-obstacle information (third sub-obstacle flag: 002, third sub-obstacle coordinate (2, 2)), third sub-obstacle information (third sub-obstacle flag: 003, third sub-obstacle coordinate (3, 1)) ].

Step 204, for each third obstacle information in the third obstacle information set, determining a distance value between each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information and the first sub-obstacle information corresponding to the third sub-obstacle information in the first sub-obstacle information set included in the first obstacle information set, so as to generate a first distance value, and obtain a first distance value set.

In some embodiments, the executing main body may determine, for each third obstacle information in the third obstacle information set, each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information, and a distance value between the first sub-obstacle information corresponding to the third sub-obstacle information in a first sub-obstacle information set included in the first obstacle information set, to generate the first distance value, resulting in the first distance value set. The execution main body may determine, according to a third sub-obstacle identifier corresponding to the third sub-obstacle information, first sub-obstacle information corresponding to the third sub-obstacle information in a first sub-obstacle information group included in the first obstacle information set. The execution body may determine an euclidean distance between the third sub-obstacle information and the first sub-obstacle information corresponding to the third sub-obstacle information as a first distance value. The formula for the euclidean distance may be:

wherein,

is an abscissa in the first sub-obstacle coordinates included in the first obstacle information or the second obstacle information.

Is a vertical coordinate in the first sub-obstacle coordinates included in the first obstacle information or the second obstacle information.

Is an abscissa in the first sub-obstacle coordinates included in the third obstacle information.

Is a vertical coordinate in the first sub-obstacle coordinates included in the third obstacle information.

Is the above-mentioned euclidean distance.

As an example, the third obstacle information set may be { a third sub-obstacle information group A [ third sub-obstacle information (third sub-obstacle flag: 001, third sub-obstacle coordinate (1, 3)), third sub-obstacle information (third sub-obstacle flag: 002, third sub-obstacle coordinate (1, 2)), third sub-obstacle information (third sub-obstacle flag: 003, third sub-obstacle coordinate (2, 1))]}. The first set of obstacle information may be { a first sub-obstacle information group a [ first sub-obstacle information group(first sub-obstacle flag: 001, first sub-obstacle coordinate: (2, 2)), first sub-obstacle information (first sub-obstacle flag: 002, first sub-obstacle coordinate: (2, 2)), first sub-obstacle information (first sub-obstacle flag: 003, first sub-obstacle coordinate: (3, 1))]}. The Euclidean distance between the third sub-obstacle coordinate corresponding to the third sub-obstacle information with the third sub-obstacle identifier 001 and the first sub-obstacle coordinate corresponding to the first sub-obstacle information with the first sub-obstacle identifier 001

. The euclidean distance between the third sub-obstacle coordinates corresponding to the third sub-obstacle information having the third sub-obstacle flag 002 and the first sub-obstacle coordinates corresponding to the first sub-obstacle information having the first sub-obstacle flag 002 is 1. The euclidean distance between the third sub-obstacle coordinates corresponding to the third sub-obstacle information having the third sub-obstacle flag 003 and the first sub-obstacle coordinates corresponding to the first sub-obstacle information having the first sub-obstacle flag 003 is 1. The first distance value group is [ alpha ], [ alpha ]

,1,1]。

Step 205, for each third obstacle information in the third obstacle information set, determining a distance value between each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information and a second sub-obstacle information corresponding to the third sub-obstacle information in a second sub-obstacle information set included in the second obstacle information set, so as to generate a second distance value, and obtain a second distance value set.

In some embodiments, the executing body may determine, for each third obstacle information in the third obstacle information set, a distance value between each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information and a second sub-obstacle information corresponding to the third sub-obstacle information in a second sub-obstacle information set included in the second obstacle information set, to generate a second distance value, resulting in a second distance value set.

As an example, the third obstacle information set may be { a third sub-obstacle information group A [ third sub-obstacle information (third sub-obstacle flag: 001, third sub-obstacle coordinate (1, 3)), third sub-obstacle information (third sub-obstacle flag: 002, third sub-obstacle coordinate (1, 2)), third sub-obstacle information (third sub-obstacle flag: 003, third sub-obstacle coordinate (2, 1))]}. The second obstacle information set may be { a second sub-obstacle information group a [ second sub-obstacle information (second sub-obstacle flag: 001, second sub-obstacle coordinate: (0, 3)), second sub-obstacle information (second sub-obstacle flag: 002, second sub-obstacle coordinate: (0, 2)), second sub-obstacle information (second sub-obstacle flag: 003, second sub-obstacle coordinate: (1, 2) ]')]}. The euclidean distance between the third sub-obstacle coordinates corresponding to the third sub-obstacle information whose third sub-obstacle identifier is 001 and the second sub-obstacle coordinates corresponding to the second sub-obstacle information whose second sub-obstacle identifier is 001 is 1. The euclidean distance between the third sub-obstacle coordinates corresponding to the third sub-obstacle information having the third sub-obstacle flag 002 and the second sub-obstacle coordinates corresponding to the second sub-obstacle information having the second sub-obstacle flag 002 is 1. The euclidean distance between the third sub-obstacle coordinates corresponding to the third sub-obstacle information with the third sub-obstacle flag 003 and the second sub-obstacle coordinates corresponding to the second sub-obstacle information with the second sub-obstacle flag 003 is set to be

. The corresponding second set of distance values is then set to 1,

]。

step 206, respectively performing feature vectorization processing on each first distance value group and each second distance value group in the obtained first distance value group set and the obtained second distance value group set to generate a first feature vector and a second feature vector, so as to obtain a first feature vector set and a second feature vector set.

In some embodiments, the executing entity may perform feature vectorization processing on each of the obtained at least one first distance value group and each of the obtained at least one second distance value group to generate a first feature vector and a second feature vector, so as to obtain a first feature vector set and a second feature vector set. The first feature vector is a vector formed by each first distance value in the first distance value group. The second feature vector is a vector formed by each of the second distance values in the second distance value set.

As an example, the first set of distance values a may be [1, 2, 3, 4 ]. The first distance value group a is a first distance value group generated by the first sub-obstacle information group a and the third sub-obstacle information group a corresponding to the distance between the sub-obstacle information. "1" may be a euclidean distance between the corresponding first sub-obstacle information 001 and third sub-obstacle information 001. "2" corresponds to the euclidean distance between the first sub-obstacle information 002 and the third sub-obstacle information 002. "3" corresponds to the euclidean distance between the first sub-obstacle information 003 and the third sub-obstacle information 003. "4" corresponds to the euclidean distance between the first sub-obstacle information 004 and the third sub-obstacle information 004.

The first sub-obstacle information 001 is first sub-obstacle information whose first sub-obstacle identifier is 001 in the first sub-obstacle information group a, and the third sub-obstacle information 001 is third sub-obstacle information whose first sub-obstacle identifier is 001 in the third sub-obstacle information group a. The first feature vector corresponding to the first distance value group may be (1, 2, 3, 4).

And step 207, inputting the first feature vector set and the second feature vector set into a pre-trained binary classification model to generate an obstacle information set.

In some embodiments, the executing entity may input the first feature vector set and the second feature vector set into the pre-trained binary model to generate the set of obstacle information. The pre-trained binary model may be an LR (Logistic Regression) binary model.

With further reference to fig. 3, a flow 300 of further embodiments of an obstacle information generation method is shown. The flow 300 of the obstacle information generating method includes the following steps:

step 301, in response to receiving first broadcast information sent by a target rsu, generating a first set of obstacle information according to the first broadcast information.

Step 302, in response to receiving second broadcast information sent by the target vehicle, generating a second obstacle information set according to the second broadcast information.

Step 303, determining obstacle information corresponding to the obstacle in the target range as third obstacle information to obtain a third obstacle information set.

In some embodiments, the specific implementation manner and technical effects of

steps

301 and 303 can refer to steps 201 and 203 in the embodiments corresponding to fig. 2, which are not described herein again.

Step 304, determining mahalanobis distance values between each piece of third sub-obstacle information in a third sub-obstacle information group included in the third obstacle information and the first sub-obstacle information corresponding to the third sub-obstacle information in the first sub-obstacle information group included in the first obstacle information set, so as to generate first distance values corresponding to the third sub-obstacle information.

In some embodiments, the executing main body may determine each third sub-obstacle information in a third sub-obstacle information group included in the third obstacle information, and a mahalanobis distance value between first sub-obstacle information corresponding to the third sub-obstacle information in a first sub-obstacle information group included in first obstacle information in the first obstacle information group, to generate a first distance value corresponding to the third sub-obstacle information.

Wherein, the mahalanobis distance formula may be:

wherein,

is a column vector corresponding to the first sub-obstacle coordinates included in the first sub-obstacle information.

Is a column vector corresponding to the third sub-obstacle coordinates included in the third sub-obstacle information.

Is that

And

the corresponding covariance matrix.

Is obtained from a kalman filter. The kalman filter is a filter implemented by an optimized autoregressive data processing algorithm.

Is that

The inverse matrix of (c).

Is that

The transposed matrix of (2).

Is the mahalanobis distance.

As an example, the column vector corresponding to the first sub-obstacle coordinate comprised by the first sub-obstacle may be

. The column vector corresponding to the coordinates of the third sub-obstacle included in the third sub-obstacle may be

。

Can be

。

Can be

。

Step 305, determining mahalanobis distance values between each piece of third sub-obstacle information in a third sub-obstacle information group included in the third obstacle information and the second sub-obstacle information corresponding to the third sub-obstacle information in a second sub-obstacle information group included in the second obstacle information set, so as to generate second distance values corresponding to the third sub-obstacle information.

In some embodiments, the executing main body may determine a mahalanobis distance value between each of the third sub-obstacle information groups included in the third obstacle information and the second sub-obstacle information corresponding to the third sub-obstacle information in the second sub-obstacle information groups included in the second obstacle information group set, so as to generate the second distance value corresponding to the third sub-obstacle information.

Wherein,

the column vector corresponding to the second sub-obstacle coordinates included in the second sub-obstacle information.

Is that

And

the corresponding covariance matrix.

Is that

The inverse matrix of (c).

Is that

The transposed matrix of (2).

Is the mahalanobis distance.

。

Can be

。

Can be

。

Step 306, the first distance values in the first distance value sets are spliced to generate a first feature vector corresponding to the first distance value set.

In some embodiments, the executing entity may stitch each of the first distance values in the first distance value set to generate a first feature vector corresponding to the first distance value set.

As an example, the executing subject concatenates each of the first distance values in the first distance value groups to generate the first feature vector corresponding to the first distance value group, and the method may include the following steps:

firstly, feature coding is carried out on each first distance value in the first distance value groups to generate first candidate features, and a first candidate feature sequence is obtained.

For example, the first distance value group A may be [1, 2, 3, 4 ]. The executing body may binary-encode each of the first distance values in the first distance value group a. 1 is binary coded to generate 0001. And 2, binary coding is carried out to generate 0010. And 3, binary coding is carried out to generate 0011. 4 binary coding generates 0100. The first candidate sequence a may be [0001, 0010, 0011, 0100 ].

And secondly, performing feature splicing on each first candidate feature in the first candidate feature sequence to generate a first feature vector corresponding to the first distance value group.

For example, the first candidate sequence a may be [0001, 0010, 0011, 0100 ]. The executing body may perform feature concatenation on each first candidate feature in the first candidate feature sequence a to generate a first feature vector corresponding to the first distance value group. The first feature vector may be 0001001000110100.

And 307, splicing each second distance value in the second distance value groups to generate a second feature vector corresponding to the second distance value group.

In some embodiments, the executing entity may stitch the second distance values in the second distance value groups to generate the second feature vectors corresponding to the second distance value groups.

As an example, the executing subject concatenates the second distance values in the second distance value sets to generate the second feature vector corresponding to the second distance value set, and the method may include:

firstly, feature coding is carried out on each second distance value in the second distance value groups to generate second candidate features, and a second candidate feature sequence is obtained.

For example, the second distance value group B may be [4, 3, 2, 1 ]. The executing body may binary-encode each of the second distance values in the second distance value group B. 4 binary coding generates 0100. And 3, binary coding is carried out to generate 0011. And 2, binary coding is carried out to generate 0010. 1 is binary coded to generate 0001. The second candidate sequence B may be [0100, 0011, 0010, 0001 ].

And secondly, performing feature splicing on each second candidate feature in the second candidate feature sequence to generate a second feature vector corresponding to the second distance value group.

For example, the second candidate sequence B may be [0100, 0011, 0010, 0001 ]. The executing entity may perform feature concatenation on each second candidate feature in the second candidate feature sequence B to generate a second feature vector corresponding to the second distance value group. The second feature vector may be 0100001100100001.

And step 308, inputting the first feature vector set and the second feature vector set into a pre-trained binary classification model to generate an obstacle information set.

In some embodiments, the execution subject may input the first set of feature vectors and the second set of feature vectors into a pre-trained binary model to generate the set of obstacle information. Wherein, the pre-trained binary classification model may be a gradient lifting tree model.

As can be seen from fig. 3, compared with the description of some embodiments corresponding to fig. 2, in the present disclosure, first, each third sub-obstacle information in the third sub-obstacle information group included in the third obstacle information is determined, and a mahalanobis distance value between the first sub-obstacle information corresponding to the third sub-obstacle information in the first sub-obstacle information group included in the first obstacle information set is determined, so as to generate a first distance value corresponding to the third sub-obstacle information. Next, a mahalanobis distance value between each of the third sub-obstacle information groups included in the third obstacle information and the second sub-obstacle information corresponding to the third sub-obstacle information in the second sub-obstacle information group included in the second obstacle information set is determined, so as to generate a second distance value corresponding to the third sub-obstacle information. In practice, determining the distance between two points is typically determining the euclidean distance between two points. The euclidean distance emphasizes considering the physical distance between the coordinates of two point correspondences rather than the similarity between the coordinates of two point correspondences. And the mahalanobis distance emphasizes the similarity of two points, so that the technical scheme is more fit. The similarity between the coordinates corresponding to the two obstacles can be judged according to the Mahalanobis distance value, so that the similarity between the obstacles corresponding to the two points can be better determined. The first distance value in the first distance value group and the second distance value in the second distance value group are subjected to feature coding and are spliced, so that the integrity of the first feature vector and the second feature vector is better, the first feature vector and the second feature vector are better classified through a pre-trained model, and the accuracy of generating the obstacle information is improved. In addition, the classification accuracy of the gradient lifting tree model is higher than that of the logistic regression model, so that the gradient lifting tree model can be used for better determining that a plurality of pieces of obstacle information correspond to the same obstacle, and therefore the accuracy of obstacle information generation is improved.

With further reference to fig. 4, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an obstacle information generating apparatus, which correspond to those of the method embodiments shown in fig. 2, and which may be applied in various electronic devices in particular.

As shown in fig. 4, the obstacle information generating apparatus 400 of some embodiments includes: a first generation unit 401, a second generation unit 402, a first determination unit 403, a second determination unit 404, a third determination unit 405, a feature vectorization unit 406, and an input unit 407. The first generating unit 401 is configured to generate, in response to receiving first broadcast information sent by a target roadside unit, a first set of obstacle information according to the first broadcast information, where an obstacle corresponding to first obstacle information in the first set of obstacle information is an obstacle within a sensing range of the target roadside unit, and the first obstacle information in the first set of obstacle information includes: a first sub-obstacle information set. A second generating unit 402, configured to generate a second set of obstacle information according to second broadcast information sent by a target vehicle in response to receiving the second broadcast information, where an obstacle corresponding to second obstacle information in the second set of obstacle information is an obstacle in a sensing range of the target vehicle, and the second obstacle information in the second set of obstacle information includes: a second sub-obstacle information set. A first determining unit 403, configured to determine obstacle information corresponding to an obstacle in the target range as third obstacle information, and obtain a third obstacle information set, where the third obstacle information in the third obstacle information set includes: a third sub-obstacle information set. A second determining unit 404 configured to determine, for each third obstacle information in the third obstacle information set, a distance value between each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information and a first sub-obstacle information corresponding to the third sub-obstacle information in a first sub-obstacle information set included in the first obstacle information set, to generate a first distance value, and obtain a first distance value set. A third determining unit 405 configured to determine, for each third obstacle information in the third obstacle information set, a distance value between each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information and a second sub-obstacle information corresponding to the third sub-obstacle information in a second sub-obstacle information set included in a second obstacle information in the second obstacle information set, to generate a second distance value, and obtain a second distance value set. A feature vectorization unit 406, which performs feature vectorization on each of the obtained at least one first distance value group and each of the obtained at least one second distance value group to generate a first feature vector and a second feature vector, so as to obtain a first feature vector set and a second feature vector set. The input unit 407 inputs the first feature vector set and the second feature vector set to a pre-trained binary model to generate an obstacle information set.

It will be understood that the elements described in the apparatus 400 correspond to various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 400 and the units included therein, and will not be described herein again.

Referring now to FIG. 5, a block diagram of an electronic device (such as computing device 101 shown in FIG. 1) 500 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 5 may represent one device or may represent multiple devices as desired.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program, when executed by the processing device 501, performs the above-described functions defined in the methods of some embodiments of the present disclosure.

It should be noted that the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: in response to receiving first broadcast information sent by a target road side unit, generating a first obstacle information set according to the first broadcast information, wherein an obstacle corresponding to first obstacle information in the first obstacle information set is an obstacle in a sensing range of the target road side unit, and the first obstacle information in the first obstacle information set comprises: a first sub-obstacle information group; in response to receiving second broadcast information sent by a target vehicle, generating a second obstacle information set according to the second broadcast information, wherein an obstacle corresponding to second obstacle information in the second obstacle information set is an obstacle in a sensing range of the target vehicle, and the second obstacle information in the second obstacle information set comprises: a second sub-obstacle information set; determining obstacle information corresponding to obstacles in a target range as third obstacle information to obtain a third obstacle information set, wherein the third obstacle information in the third obstacle information set comprises: a third sub-obstacle information group; for each piece of third obstacle information in the third obstacle information set, determining a distance value between each piece of third sub-obstacle information in a third sub-obstacle information group included in the third obstacle information and first sub-obstacle information corresponding to the third sub-obstacle information in a first sub-obstacle information group included in first obstacle information in the first obstacle information set, so as to generate a first distance value, and obtaining a first distance value group; for each piece of third obstacle information in the third obstacle information set, determining a distance value between each piece of third sub-obstacle information in a third sub-obstacle information group included in the third obstacle information and a piece of second sub-obstacle information corresponding to the third sub-obstacle information in a second sub-obstacle information group included in second obstacle information in the second obstacle information set, so as to generate a second distance value, and obtaining a second distance value group; respectively carrying out feature vectorization processing on each first distance value group in the obtained at least one first distance value group and each second distance value group in the obtained at least one second distance value group to generate a first feature vector and a second feature vector, and obtaining a first feature vector set and a second feature vector set; and inputting the first feature vector set and the second feature vector set into a pre-trained binary classification model to generate an obstacle information set.

Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes a first generation unit, a second generation unit, a first determination unit, a second determination unit, a third determination unit, a feature vectorization unit, and an input unit. The name of these units does not in some cases constitute a limitation on the unit itself, and for example, the feature vectorization unit may be further described as "a unit that performs feature vectorization processing on each of the obtained at least one first distance value group and each of the obtained at least one second distance value group to generate a first feature vector and a second feature vector, resulting in a first feature vector set and a second feature vector set", respectively ".

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims

1. An obstacle information generation method comprising:

in response to receiving first broadcast information sent by a target road side unit, generating a first obstacle information set according to the first broadcast information, wherein an obstacle corresponding to first obstacle information in the first obstacle information set is an obstacle in a sensing range of the target road side unit, and the first obstacle information in the first obstacle information set comprises: a first sub-obstacle information group;

in response to receiving second broadcast information sent by a target vehicle, generating a second obstacle information set according to the second broadcast information, wherein an obstacle corresponding to second obstacle information in the second obstacle information set is an obstacle in the sensing range of the target vehicle, and the second obstacle information in the second obstacle information set comprises: a second sub-obstacle information set;

determining obstacle information corresponding to obstacles in a target range as third obstacle information to obtain a third obstacle information set, wherein the third obstacle information in the third obstacle information set comprises: a third sub-obstacle information group;

for each piece of third obstacle information in the third obstacle information set, determining a distance value between each piece of third sub-obstacle information in a third sub-obstacle information group included in the third obstacle information and first sub-obstacle information corresponding to the third sub-obstacle information in a first sub-obstacle information group included in first obstacle information in the first obstacle information set, so as to generate a first distance value, and obtaining a first distance value group;

for each piece of third obstacle information in the third obstacle information set, determining a distance value between each piece of third sub-obstacle information in a third sub-obstacle information group included in the third obstacle information and second sub-obstacle information corresponding to the third sub-obstacle information in a second sub-obstacle information group included in second obstacle information in the second obstacle information set, so as to generate a second distance value, and obtaining a second distance value group;

respectively carrying out feature vectorization processing on each first distance value group in the obtained at least one first distance value group and each second distance value group in the obtained at least one second distance value group to generate a first feature vector and a second feature vector, and obtaining a first feature vector set and a second feature vector set;

inputting the first feature vector set and the second feature vector set into a pre-trained binary classification model to generate an obstacle information set.

2. The method according to claim 1, the determining a distance value between each of third sub-obstacle information in a third sub-obstacle information group comprised by the third obstacle information and a first sub-obstacle information corresponding to the third sub-obstacle information in a first sub-obstacle information group comprised by a first obstacle information in the first obstacle information set to generate a first distance value, comprising:

determining a mahalanobis distance value between each piece of third sub-obstacle information in a third sub-obstacle information group included in the third obstacle information and the first sub-obstacle information corresponding to the third sub-obstacle information in the first sub-obstacle information group included in the first obstacle information set, so as to generate a first distance value corresponding to the third sub-obstacle information.

3. The method according to claim 2, the determining a distance value between each of third sub-obstacle information in a third sub-obstacle information group comprised by the third obstacle information and second sub-obstacle information corresponding to the third sub-obstacle information in a second sub-obstacle information group comprised by second obstacle information in the second obstacle information set to generate a second distance value, comprising:

determining a mahalanobis distance value between each piece of third sub-obstacle information in a third sub-obstacle information group included in the third obstacle information and second sub-obstacle information corresponding to the third sub-obstacle information in a second sub-obstacle information group included in second obstacle information in the second obstacle information set, so as to generate a second distance value corresponding to the third sub-obstacle information.

4. The method of claim 3, wherein performing a feature vectorization process on each of the obtained at least one first distance value set and each of the obtained at least one second distance value set to generate a first feature vector and a second feature vector, respectively, comprises:

splicing each first distance value in the first distance value groups to generate a first feature vector corresponding to the first distance value groups;

and splicing each second distance value in the second distance value groups to generate a second feature vector corresponding to the second distance value group.

5. The method of claim 4, wherein said stitching each of the first set of distance values to generate the corresponding first feature vector for the first set of distance values comprises:

performing feature coding on each first distance value in the first distance value group to generate a first candidate feature, so as to obtain a first candidate feature sequence;

and performing feature splicing on each first candidate feature in the first candidate feature sequence to generate a first feature vector corresponding to the first distance value group.

6. The method of claim 5, wherein said stitching each of the second set of distance values to generate the corresponding second eigenvector for the second set of distance values comprises:

performing feature coding on each second distance value in the second distance value group to generate a second candidate feature to obtain a second candidate feature sequence;

and performing feature splicing on each second candidate feature in the second candidate feature sequence to generate a second feature vector corresponding to the second distance value group.

7. The method of claim 6, wherein the pre-trained bi-classification model is a gradient-boosted tree model.

8. An obstacle information generating apparatus comprising:

a first generating unit configured to generate a first set of obstacle information according to first broadcast information sent by a target road side unit in response to receiving the first broadcast information, wherein an obstacle corresponding to first obstacle information in the first set of obstacle information is an obstacle in a sensing range of the target road side unit, and the first obstacle information in the first set of obstacle information includes: a first sub-obstacle information group;

a second generating unit configured to generate a second obstacle information set according to second broadcast information sent by a target vehicle in response to receiving the second broadcast information, wherein an obstacle corresponding to second obstacle information in the second obstacle information set is an obstacle in a sensing range of the target vehicle, and the second obstacle information in the second obstacle information set includes: a second sub-obstacle information set;

a first determining unit, configured to determine obstacle information corresponding to an obstacle in a target range as third obstacle information, resulting in a third obstacle information set, where the third obstacle information in the third obstacle information set includes: a third sub-obstacle information group;

a second determination unit configured to determine, for each third obstacle information in the third obstacle information set, a distance value between each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information and a first sub-obstacle information corresponding to the third sub-obstacle information in a first sub-obstacle information set included in first obstacle information in the first obstacle information set, to generate a first distance value, resulting in a first distance value set;

a third determination unit configured to determine, for each third obstacle information in the third obstacle information set, a distance value between each third sub-obstacle information in a third sub-obstacle information set included in the third obstacle information and a second sub-obstacle information corresponding to the third sub-obstacle information in a second sub-obstacle information set included in a second obstacle information in the second obstacle information set to generate a second distance value, resulting in a second distance value set;

a feature vectorization unit configured to perform feature vectorization processing on each of the obtained at least one first distance value group and each of the obtained at least one second distance value group to generate a first feature vector and a second feature vector, resulting in a first feature vector set and a second feature vector set;

an input unit configured to input the first set of feature vectors and the second set of feature vectors into a pre-trained binary model to generate a set of obstacle information.

9. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.

10. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1 to 7.