Driving interaction intention fragment extraction and processing method and device and storage medium

Abstract

The invention relates to the technical field of electric digital processing, in particular to a driving interaction intention fragment extraction and processing method and device and a storage medium. The driving interaction intention fragment extraction and processing method comprises the steps that in the driving process of a vehicle, driving behavior data of the vehicle and interaction behavior data of the vehicle and surrounding vehicles are collected; the surrounding vehicle is any vehicle around the own vehicle; dividing the driving behavior data to obtain a plurality of self-vehicle behavior segments; dividing the interaction behavior data according to the division time point of the self-vehicle behavior fragment to obtain a plurality of interaction intention fragments; each interaction intention fragment comprises driving behavior data of the own vehicle and interaction behavior data of the own vehicle and surrounding vehicles; and clustering the plurality of interaction intention fragments, and performing intention recognition on each type of interaction intention fragment set. According to the invention, the accuracy of division and recognition of the interactive intention fragments can be improved.

Description

Technical Field

[0001] This application relates to the field of digital signal processing technology. Specifically, it relates to a method, device, and storage medium for extracting and processing driving interaction intention picture segments. Background Art

[0002] Driving in a complex traffic environment is a game process. The host vehicle and surrounding vehicles achieve a dynamic balance of the system through interactive games and achieve their respective driving goals. By splitting the time-series data of vehicle-to-vehicle interaction into multiple minimum interaction behaviors or interaction intention picture segments with actual physical meanings, the basic types of vehicle-to-vehicle interaction, such as lane-changing games, intersection conflicts, and following regulation, can be clarified through the analysis and definition of interaction segment patterns.

[0003] In the prior art, interaction segments are generally divided based on simple acceleration and deceleration changes and the change range of vehicle heading angles. This division method has low accuracy. For example, when a vehicle is driving straight normally, there may be a small deviation from the lane. If the segment is divided using the change in heading angle, it will be classified as a turn or a lane change.

[0004] In view of this, this application is proposed. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, and storage medium for extracting and processing driving interaction intention picture segments to improve the accuracy of segment division and recognition of interaction intention picture segments.

[0006] To achieve the above purpose, this application adopts the following technical solutions: In a first aspect, this application provides a method for extracting and processing driving interaction intention picture segments, including: During the driving process of the host vehicle, collect the driving behavior data of the host vehicle and the interaction behavior data between the host vehicle and surrounding vehicles; the surrounding vehicle is any vehicle around the host vehicle; Divide the driving behavior data to obtain multiple host vehicle behavior segments; According to the division time points of the host vehicle behavior segments, divide the interaction behavior data to obtain multiple interaction intention picture segments; each interaction intention picture segment includes the driving behavior data of the host vehicle and the interaction behavior data between the host vehicle and surrounding vehicles; Cluster the multiple interaction intention picture segments and perform intention recognition on each set of interaction intention picture segments.

[0007] Dividing the driving behavior data to obtain multiple host vehicle behavior segments includes: Perform a first-level division on the driving behavior data according to the lateral behavior characterization variables of the host vehicle to obtain multiple preliminary host vehicle behavior segments; Perform a secondary division on each preliminary self-vehicle behavior segment according to the longitudinal behavior characterization variables of the self-vehicle to obtain multiple self-vehicle behavior segments.

[0008] Optionally, use the Bayesian agglomerative data segmentation algorithm for the first-level division and the second-level division.

[0009] Optionally, before performing the first-level division on the driving behavior data according to the lateral behavior characterization variables of the self-vehicle, it further includes: Perform a correlation analysis on the lateral behavior characterization variables of the self-vehicle, and retain the lateral behavior characterization variables with a correlation lower than the set threshold; Perform a correlation analysis on the longitudinal behavior characterization variables of the self-vehicle, and retain the longitudinal behavior characterization variables with a correlation lower than the set threshold.

[0010] Optionally, before clustering the multiple interactive intention picture segments to obtain the categories of interactive intentions, it further includes: Select target segments with a duration less than the set threshold from the multiple interactive intention picture segments; Use the maximum a posteriori estimation to solve the regression model coefficients of each variable in the target segment and its adjacent segments before and after; Merge the target segment with the adjacent interactive intention picture segments according to the similarity degree of the regression model coefficients of the target segment and its adjacent segments before and after.

[0011] Optionally, the intention recognition of each set of interactive intention picture segments includes: Perform numerical statistics on the variables in each set of interactive intention picture segments; Perform intention recognition according to the numerical statistical results.

[0012] Optionally, the lateral behavior characterization variables include lateral acceleration and body heading angle, and the longitudinal behavior characterization variables include longitudinal speed and longitudinal acceleration.

[0013] In a second aspect, the present application provides an electronic device, including: At least one processor, and a memory communicatively connected to at least one of the processors; Wherein, the memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the above-mentioned driving interactive intention picture segment extraction and processing method.

[0014] In a third aspect, the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the above-mentioned driving interactive intention picture segment extraction and processing method.

[0015] Compared with the prior art, the beneficial effects of the present application are: Based on the characteristic that the behavior decision-making of the host vehicle is the corresponding result of the driving interaction process, the interaction behavior data is divided according to the time points of the host vehicle driving behavior data, effectively improving the division accuracy. Further, multiple interaction intention picture segments are clustered, and intention recognition is performed on each set of interaction intention picture segments. By the clustering method, the interaction intention picture segments with the same intention but non-adjacent in time are further summarized, realizing the extraction and recognition of the interaction intention between vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 is a flowchart of a method for extracting and processing driving interaction intention picture segments provided by an embodiment of the present application; Figure 2 is a schematic diagram of the division result of the driving behavior data of the host vehicle provided by an embodiment of the present application; Figure 3 is a schematic diagram of the structure of an electronic device provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The following describes exemplary embodiments of the present application in conjunction with the drawings. Various details of the embodiments of the present application are included to assist understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description below omits the description of well-known functions and structures.

[0019] Figure 1 is a flowchart of a method for extracting and processing driving interaction intention picture segments provided by an embodiment of the present application. This method can be executed by an electronic device. The method provided in this embodiment is applicable to the situation of extracting interaction intention picture segments and intention recognition for the driving data generated during vehicle driving and the interaction behavior data with surrounding vehicles. Refer to Figure 1 As shown in, the method provided in this embodiment includes the following operations: S110. During the driving process of the host vehicle, collect the driving behavior data of the host vehicle and the interaction behavior data between the host vehicle and surrounding vehicles.

[0020] The host vehicle is the object for analyzing interaction intentions, and the type of the host vehicle is not limited in this embodiment. The surrounding vehicles are any vehicles around the host vehicle, such as the adjacent vehicle in front or behind in the same lane, or the laterally adjacent vehicle in a different lane. The driving strategy of the host vehicle will be affected by the surrounding vehicles. For example, if the adjacent vehicle in front decelerates, the host vehicle will also decelerate to avoid rear-ending.

[0021] Positioning devices, inertial measurement units, gyroscopes and other sensors are installed on both the host vehicle and the surrounding vehicles to collect the driving behavior data of the host vehicle and the interaction behavior data between the host vehicle and the surrounding vehicles. Among them, the driving behavior data of the host vehicle includes, but is not limited to, lateral behavior characterization variables and longitudinal behavior characterization variables. The lateral behavior characterization variables include lateral acceleration and vehicle body yaw angle, and the longitudinal behavior characterization variables include longitudinal speed and longitudinal acceleration. Similarly, the interaction behavior data includes, but is not limited to, the relative position between the host vehicle and the surrounding vehicles and the relative driving behavior data. The relative driving behavior data includes relative lateral behavior characterization variables and relative longitudinal behavior characterization variables of the host vehicle and the surrounding vehicles. The relative lateral behavior characterization variables include relative lateral acceleration and relative vehicle body yaw angle, and the relative longitudinal behavior characterization variables include relative longitudinal speed and relative longitudinal acceleration.

[0022] Both the driving behavior data and the interaction behavior data are time series data.

[0023] S120. Divide the driving behavior data to obtain multiple host vehicle behavior segments.

[0024] During the driving interaction between the host vehicle and the surrounding vehicles, the host vehicle makes a driving behavior decision based on the interaction situation with the surrounding vehicles. Therefore, it can be considered that the driving behavior decision of the host vehicle is the corresponding result of the driving interaction process. For this reason, in this application, the segmentation situation of the driving behavior data of the host vehicle is used as the segmentation basis for the interaction behavior data between the host vehicle and the surrounding vehicles, and the segmentation of the interaction intention segments is realized through the segmentation of the driving behavior of the host vehicle.

[0025] Optionally, perform a first-level division on the driving behavior data according to the lateral behavior characterization variables of the host vehicle to obtain multiple preliminary host vehicle behavior segments; perform a second-level division on each preliminary host vehicle behavior segment according to the longitudinal behavior characterization variables of the host vehicle to obtain multiple host vehicle behavior segments.

[0026] The preliminary host vehicle behavior segments are divided according to the change characteristics of the lateral behavior characterization variables. For example, the driving behavior data with significantly different vehicle body heading angles should be divided into different preliminary host vehicle behavior segments, assumed to be m. For each preliminary host vehicle behavior segment, continue to divide according to the change characteristics of its longitudinal behavior characterization variables. For example, the driving behavior data with significantly different longitudinal accelerations should be divided into different host vehicle driving segments, and finally n host vehicle driving segments are obtained.

[0027] In a preferred embodiment, before performing the first-level classification on the driving behavior data according to the lateral behavior characterization variables of the host vehicle, it further includes: performing a correlation analysis on the lateral behavior characterization variables of the host vehicle, and retaining the lateral behavior characterization variables with a correlation lower than a set threshold; performing a correlation analysis on the longitudinal behavior characterization variables of the host vehicle, and retaining the longitudinal behavior characterization variables with a correlation lower than a set threshold.

[0028] Specifically, assuming there are multiple lateral behavior characterization variables, a correlation analysis is performed pairwise on the multiple lateral behavior characterization variables. For example, the Pearson correlation coefficient is calculated. If the correlation coefficient / correlation between two lateral behavior characterization variables is higher than the set threshold, it means that these two lateral behavior characterization variables are correlated, and only one of them is retained. If the correlation coefficient / correlation between two lateral behavior characterization variables is lower than the set threshold, both are retained, and the finally retained lateral behavior characterization variables are all those with a correlation coefficient / correlation higher than the set threshold. Similarly, the longitudinal behavior characterization variables with a correlation lower than the set threshold are retained, which will not be elaborated here.

[0029] In a preferred embodiment, the Bayesian model-based agglomerative sequence segmentation algorithm is used for the first-level and second-level divisions. The Bayesian model-based agglomerative sequence segmentation algorithm (BMASS) is an unsupervised learning method based on hierarchical clustering and Bayesian inference, which is used to divide time series data or sequence data into statistically significant continuous segments. Its core idea is to use a bottom-up (agglomerative) merging strategy and combine Bayesian criteria to evaluate the rationality of segmentation points, and finally generate an optimal data division. First, the lateral behavior characterization variables of the ego vehicle are input into BMASS. BMASS adopts a bottom-up agglomeration strategy. By calculating the marginal likelihood of all lateral behavior characterization variables, adjacent segments are gradually merged to obtain multiple segments obtained by dividing the lateral behavior characterization variables of the ego vehicle. The lateral behavior characterization variables of the ego vehicle are part of the driving behavior data and have a time correspondence with other driving behavior data (i.e., longitudinal behavior characterization variables). In the case where the lateral behavior characterization variables are divided, other driving behavior data can be correspondingly divided according to the division time points, so as to divide the complete driving behavior data of the ego vehicle and obtain multiple preliminary ego vehicle behavior segments. Then, all the longitudinal behavior characterization variables in each preliminary ego vehicle behavior segment are input into BMASS. BMASS adopts a bottom-up agglomeration strategy. By calculating the marginal likelihood of all longitudinal behavior characterization variables, adjacent segments are gradually merged to obtain multiple segments obtained by dividing the longitudinal behavior characterization variables of the ego vehicle in each preliminary ego vehicle behavior segment. According to the division time points of these multiple segments, the complete data of each preliminary ego vehicle behavior segment is divided to obtain multiple final ego vehicle behavior segments, and each of these ego vehicle behavior segments includes lateral behavior characterization variables and longitudinal behavior characterization variables.

[0030] Figure 2 is a schematic diagram of the division result of the driving behavior data of the ego vehicle provided by the embodiment of the present application. Figure 2 The abscissa is time, and the ordinate is the driving behavior data, including speed, longitudinal acceleration, lateral acceleration, and yaw angle. Figure 2 The vertical dotted lines in it are the division time points of the driving behavior data, and the driving behavior data between two adjacent vertical dotted lines constitutes an ego vehicle behavior segment.

[0031] S130. According to the division time points of the ego vehicle behavior segments, divide the interaction behavior data to obtain multiple interaction intention segments.

[0032] Assume that the division time points of the ego-vehicle behavior segments are t1, t2, t3, and t4. Then, for the interaction behavior data, it is also divided at t1, t2, t3, and t4. It should be noted that the interaction intention picture segments here include the driving behavior data of the ego-vehicle and the interaction behavior data between the ego-vehicle and surrounding vehicles, that is, the segments obtained by dividing the ego-vehicle behavior segments and the interaction behavior data are merged.

[0033] S140. Cluster multiple interaction intention picture segments and perform intention recognition on each set of interaction intention picture segments.

[0034] In a preferred embodiment, the duration of some interaction intention picture segments is short and not sufficient to reflect the driving intention, so they need to be merged with the previous / next interaction intention picture segments. Specifically, from multiple interaction intention picture segments, select the target segments with a duration less than the set threshold; the set threshold here can be set by oneself, for example, it is 3s. Use the maximum a posteriori estimation (MAP) to solve the regression model coefficients of each variable in the target segment and its adjacent segments before and after; according to the similarity degree of the regression model coefficients of the target segment and its adjacent segments before and after, merge the target segment with the adjacent interaction intention picture segments.

[0035] Among them, MAP is a Bayesian estimation method. This method believes that the data follows a linear regression model and regards the parameters in the model as random variables, and estimates the parameters by fusing the prior probability and the likelihood function. In this embodiment, based on MAP, calculate the Bayesian linear regression model coefficients of each behavior characterization variable with respect to time in each interaction intention picture segment (including the target segment and the adjacent segments before and after), and finally obtain the regression model coefficient matrix of each interaction intention picture segment. Perform similarity analysis on the regression model coefficient matrix of the target segment and the regression model coefficient matrices of the adjacent segments respectively. For example, calculate the Euclidean distance between the coefficients, and merge the two similar segments.

[0036] Optionally, use clustering methods such as LDA, DTW, and fuzzy k-means to cluster the obtained multiple interaction intention picture segments. Fuzzy k-means is an extension of k-means, which allows data points to belong to multiple clusters with membership degrees (between 0 and 1), and is suitable for data sets with unclear boundaries. Among them, LDA (Latent Dirichlet Allocation) is a latent Dirichlet allocation model, which is a bag-of-words model and can be used for document clustering. The interaction intention picture segments are composed of multiple multi-dimensional data points, so the interaction intention picture segments can be regarded as documents for clustering processing. DTW (Dynamic Time Warping) is a dynamic time warping model, which calculates the similarity of two or more time series by stretching and compressing the time series data. If the similarity of the time series is higher than the set threshold, they are clustered into one cluster.

[0037] After the clustering algorithm, a set of multi-class interactive intention picture segments is obtained. Each set of interactive intention picture segments includes at least one interactive intention picture segment, and all belong to an interactive intention. In this embodiment, numerical statistics are performed on the variables in each set of interactive intention picture segments; intention type recognition is performed according to the numerical statistics results. Among them, the method of numerical statistics can be to calculate the mean or variance. Optionally, the method of numerical statistics includes: solving the average value, maximum value, standard deviation, entropy value, etc. of the ego vehicle driving behavior data (speed, longitudinal acceleration, lateral acceleration, etc.) and the interactive behavior data between the ego vehicle and surrounding vehicles (relative speed, relative longitudinal distance, relative lateral distance, etc.) in each set of interactive intention picture segments (i.e., each cluster obtained by clustering). The intention refers to the interactive intention between the ego vehicle and surrounding vehicles, including: the ego vehicle accelerating and cutting in during the two-vehicle competitive game, the surrounding vehicle accelerating and approaching during the two-vehicle competitive game, the ego vehicle decelerating and yielding during the two-vehicle negotiation game, the two-vehicle mixed game, etc. Through the statistical values of the ego vehicle driving behavior data and interactive behavior data, the interactive intention between the ego vehicle and surrounding vehicles can be analyzed. For example, if the average value of the longitudinal acceleration of the ego vehicle is relatively high and the relative longitudinal distance decreases, then the ego vehicle accelerates and cuts in during the two-vehicle competitive game.

[0038] Through the above steps, this embodiment divides the interactive behavior between the ego vehicle and surrounding vehicles during the driving process. Each cluster represents an independent interactive intention type, and the interactive mode between the ego vehicle and surrounding vehicles in the cluster remains constant.

[0039] In this application, taking advantage of the characteristic that the behavior decision of the ego vehicle is the corresponding result of the driving interaction process, the interactive behavior data is divided according to the division time points of the ego vehicle driving behavior data, effectively improving the division accuracy. Further, clustering is performed on multiple interactive intention picture segments, and intention recognition is performed on each set of interactive intention picture segments. By the clustering method, the interactive intention picture segments with the same intention but non-adjacent in time are further summarized to achieve the extraction and recognition of the workshop interactive intention.

[0040] As Figure 3 shown, this embodiment provides an electronic device, including: At least one processor; and A memory communicatively connected to at least one of the processors; wherein, The memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the above method. At least one processor in this electronic device can execute the above method, and thus has at least the same advantages as the above method.

[0041] Optionally, the electronic device further includes interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Each component is interconnected using different buses and can be mounted on a common motherboard or otherwise mounted as required. The processor can process instructions executed within the electronic device, including instructions for storing graphical information in the memory or on the memory for displaying a GUI (Graphical User Interface) on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors can be used in conjunction with multiple memories, and / or multiple buses can be used in conjunction with multiple memories. Similarly, multiple electronic devices can be connected (e.g., as a server array, a set of blade servers, or a multi-processor system), with each device providing part of the necessary operations. Figure 3 In the following, a processor 301 is taken as an example.

[0042] The memory 302, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the driving interaction intention picture segment extraction and processing method in the embodiments of the present application. The processor 301 executes various functional applications and data processing of the device by running the software programs, instructions, and modules stored in the memory 302, that is, implements the above-mentioned driving interaction intention picture segment extraction and processing method.

[0043] The memory 302 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the terminal, etc. In addition, the memory 302 can include high-speed random access memory and can also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some instances, the memory 302 can further include a memory remotely set relative to the processor 301, and these remote memories can be connected to the device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0044] The electronic device may further include: an input device 303 and an output device 304. The processor 301, the memory 302, the input device 303, and the output device 304 can be connected through a bus or other means. Figure 3 In the following, the connection through a bus is taken as an example.

[0045] The input device 303 can receive input digital or character information. The output device 304 may include a display device, an auxiliary lighting device (e.g., an LED), a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light-emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touch screen.

[0046] This embodiment provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the above method. The computer instructions on the computer-readable storage medium are used to cause a computer to execute the above method, and thus have at least the same advantages as the above method.

[0047] The medium in this application can be any combination of one or more computer-readable media. The medium can be a computer-readable signal medium or a computer-readable storage medium. The medium can be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the medium (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0048] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0049] The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to wireless, wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.

[0050] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can 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 it can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0051] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire, such as coaxial cable, optical fiber, digital subscriber line (DSL), or wirelessly, such as infrared, wireless, microwave, etc. The computer-readable storage medium can be any available medium that the computer can access, or a data storage device such as a server or data center that contains one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium, or a semiconductor medium, etc. It should be noted that the computer-readable storage medium mentioned in the embodiments of this application can be a non-volatile storage medium, in other words, a non-transitory storage medium.

[0052] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this application can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved. This is not limited herein.

[0053] The above specific embodiments do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations, sub - combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims

1. A method for extracting and processing driving interaction intention picture segments, characterized in that including: During the driving process of the host vehicle, collecting the driving behavior data of the host vehicle and the interaction behavior data between the host vehicle and surrounding vehicles; The surrounding vehicles refer to any vehicle around the host vehicle; Dividing the driving behavior data to obtain multiple host vehicle behavior segments; According to the division time points of the host vehicle behavior segments, dividing the interaction behavior data to obtain multiple interaction intention picture segments; each of the interaction intention picture segments includes the driving behavior data of the host vehicle and the interaction behavior data between the host vehicle and surrounding vehicles; Clustering the multiple interaction intention picture segments and performing intention recognition on each set of interaction intention picture segments; Dividing the driving behavior data to obtain multiple host vehicle behavior segments, including: Performing a first-level division on the driving behavior data according to the lateral behavior characterization variables of the host vehicle to obtain multiple preliminary host vehicle behavior segments; Performing a second-level division on each preliminary host vehicle behavior segment according to the longitudinal behavior characterization variables of the host vehicle to obtain multiple host vehicle behavior segments.

2. The driving interaction intention picture segment extraction and processing method according to claim 1, characterized in that Using the Bayesian agglomerative data segmentation algorithm for the first-level division and the second-level division.

3. The method for extracting and processing driving interaction intention picture segments according to claim 1, wherein Before performing the first-level division on the driving behavior data according to the lateral behavior characterization variables of the host vehicle, it further includes: Performing a correlation analysis on the lateral behavior characterization variables of the host vehicle and retaining the lateral behavior characterization variables with a correlation lower than a set threshold; Performing a correlation analysis on the longitudinal behavior characterization variables of the host vehicle and retaining the longitudinal behavior characterization variables with a correlation lower than a set threshold.

4. The method for extracting and processing driving interaction intention picture segments according to any one of claims 1-3, characterized in that, Before clustering the multiple interaction intention picture segments to obtain the categories of interaction intentions, it further includes: Selecting target segments with a duration less than a set threshold from the multiple interaction intention picture segments; Using the maximum a posteriori estimation to solve the regression model coefficients of each variable in the target segment and its adjacent segments before and after; Merging the target segment with the adjacent interaction intention picture segments according to the similarity degree of the regression model coefficients of the target segment and its adjacent segments before and after.

5. The method for extracting and processing driving interaction intention picture fragments according to any one of claims 1-3, characterized in that, Performing intention recognition on each set of interaction intention picture segments, including: Performing numerical statistics on the variables in each set of interaction intention picture segments; Performing intention recognition according to the numerical statistics results.

6. The driving interaction intention picture segment extraction and processing method according to any one of claims 1-3, characterized in that, The lateral behavior characterization variables include lateral acceleration and body heading angle, and the longitudinal behavior characterization variables include longitudinal speed and longitudinal acceleration.

7. An electronic device, characterized in that, including: At least one processor and a memory communicatively connected to at least one of the processors; Wherein, the memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the driving interaction intention picture segment extraction and processing method according to any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, Computer instructions are stored on the medium, and the computer instructions are used to cause a computer to execute the driving interaction intention picture segment extraction and processing method according to any one of claims 1-6.

Images