Security warning method, device, computer-readable storage medium, and processor

Abstract

The present application provides a safety warning method, device, computer-readable storage medium, and processor. The method includes: determining the current driving area of ​​a target vehicle and obtaining the current driving status information of the target vehicle; obtaining relevant information about the current moving target and relevant information about the current fixed target; converting the current driving status information of the target vehicle, the current moving target, and the current fixed target into a current feature image; and determining the current collision probability of the target vehicle with the current moving target and the current fixed target, respectively, based on the current feature image. This solution achieves accurate safety warnings by converting the current driving status information of the target vehicle, the current moving target, and the current fixed target into a current feature image.

Description

Technical Field

[0001] The present application relates to the field of assisted driving, and more specifically, to a safety warning method, device, computer-readable storage medium, processor, and vehicle. Background Art

[0002] Assisted driving systems are systems installed on vehicles that assist the driver. These include lane keeping assist systems, automatic parking assist systems, brake assist systems, reverse assist systems, and driving assistance systems. These systems can alert the driver to impending dangers (such as the sudden appearance of a pedestrian on the road, posing a risk of collision), providing safety warnings. However, existing assisted driving systems have low accuracy in their safety warnings, making them prone to accidents. Summary of the Invention

[0003] The main purpose of this application is to provide a safety warning method, device, computer-readable storage medium, processor and vehicle to solve the problem of low accuracy of safety warning of assisted driving systems in the prior art.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a safety warning method is provided, including: determining a current driving area of ​​a target vehicle, and obtaining current driving status information of the target vehicle, the current driving status information at least including the current driving speed and current position information of the target vehicle; obtaining relevant information of a current moving target and relevant information of a current fixed target, the relevant information of the current moving target at least including the distance information between the current moving target and the target vehicle and the moving speed of the current moving target, the relevant information of the current fixed target at least including the distance information between the current fixed target and the target vehicle, the current moving target is a moving target within the current driving area, and the current fixed target is a fixed target within the current driving area; converting the current driving status information of the target vehicle, the relevant information of the current moving target and the relevant information of the current fixed target into a current feature image; and determining the current collision probability of the target vehicle with the current moving target and the current fixed target respectively according to the current feature image.

[0005] Optionally, before determining the current driving area of ​​the target vehicle, the method further includes: obtaining historical driving status information of the target vehicle, the historical driving status information including at least historical driving speed and historical position information of the target vehicle; obtaining relevant information of historical moving targets and relevant information of historical fixed targets within the historical driving area of ​​the target vehicle, the relevant information of the historical moving targets including at least distance information between the historical moving targets and the target vehicle and the moving speed of the historical moving targets, and the relevant information of the historical fixed targets including at least distance information between the historical fixed targets and the target vehicle; obtaining historical collision probabilities of the target vehicle and the historical moving targets and the historical fixed targets.

[0006] Optionally, based on the current feature image, the current collision probability of the target vehicle with the current moving target object and the current fixed target object is determined, including: converting the historical driving status information of the target vehicle, the relevant information of the historical moving target object and the relevant information of the historical fixed target object into a historical feature image; constructing a neural network model, wherein the neural network model is trained using multiple sets of training data, and each set of training data in the multiple sets of training data includes: historical feature images and historical collision probabilities corresponding to the historical feature images obtained within a historical time period; based on the neural network model, determining the current collision probability corresponding to the current feature image.

[0007] Optionally, after obtaining the historical collision probabilities of the target vehicle and the historical moving target object and the historical fixed target object, the method further includes: using the historical driving status information of the target vehicle, the relevant information of the historical moving target object, the relevant information of the historical fixed target object and the historical collision probability to train a random forest model; based on the random forest model, according to the current driving status information of the target vehicle, the relevant information of the current moving target object and the relevant information of the current fixed target object, determining the current collision probabilities of the target vehicle with the current moving target object and the current fixed target object respectively.

[0008] Optionally, the random forest model includes multiple decision trees, which are trained using the historical driving status information of the target vehicle, the relevant information of the historical moving target object, the relevant information of the historical fixed target object and the historical collision probability to obtain a random forest model, including: using a first information combination in the historical driving status information of the target vehicle, a first information combination in the relevant information of the historical moving target object, a first information combination in the relevant information of the historical fixed target object and the historical collision probability to train a first decision tree; using a second information combination in the historical driving status information of the target vehicle, a second information combination in the relevant information of the historical moving target object, a second information combination in the relevant information of the historical fixed target object and the historical collision probability to train a second decision tree; using a third information combination in the historical driving status information of the target vehicle, a third information combination in the relevant information of the historical moving target object, a third information combination in the relevant information of the historical fixed target object and the historical collision probability to train a third decision tree; integrating the first decision tree, the second decision tree and the third decision tree to obtain the random forest model.

[0009] Optionally, based on the current feature image, the current collision probabilities of the target vehicle with the current moving target and the current fixed target are determined, including: determining the first distance information between the target vehicle and the current moving target at the next moment, and the second distance information between the target vehicle and the current fixed target at the next moment based on the current feature image; determining the first current collision probability of the target vehicle colliding with the current moving target at the next moment based on the first distance information; and determining the second current collision probability of the target vehicle colliding with the current fixed target at the next moment based on the second distance information.

[0010] Optionally, determining a first current collision probability of the target vehicle colliding with the current moving target object at the next moment based on the first distance information includes: when the first distance information is less than a predetermined distance, determining that the first current collision probability is greater than a preset probability; determining a second current collision probability of the target vehicle colliding with the current fixed target object at the next moment based on the second distance information includes: when the second distance information is less than a predetermined distance, determining that the second current collision probability is greater than a preset probability.

[0011] Optionally, the current driving status information of the target vehicle, the relevant information of the current moving target object and the relevant information of the current fixed target object are converted into a current feature image, including: converting the current driving status information of the target vehicle into a first current feature image, the color of the first current feature image is a first color, the first current feature image has multiple channels, each of the channels represents one type of information in the current driving status information; converting the relevant information of the current moving target object into a second current feature image, the color of the second current feature image is a second color, the second current feature image has multiple channels, each of the channels represents one type of information in the relevant information of the current moving target object; converting the relevant information of the current fixed target object into a third current feature image, the color of the third current feature image is a third color, the third current feature image has multiple channels, each of the channels represents one type of information in the relevant information of the current fixed target object.

[0012] Optionally, the current driving status information of the target vehicle, the relevant information of the current moving target object and the relevant information of the current fixed target object are converted into a current feature image, including: converting the same information parameters of the target vehicle, the current moving target object and the current fixed target object into a current feature image, the current feature image includes three channels, the first channel represents the information parameters of the target vehicle, the second channel represents the information parameters of the current moving target object, and the third channel represents the information parameters of the current fixed target object.

[0013] Optionally, the same information parameter of the target vehicle, the current moving target object and the current fixed target object is converted into a current feature image, including: converting the current position information of the target vehicle, the position information of the current moving target object and the position information of the current fixed target object into a fourth current feature image; converting the current driving speed of the target vehicle, the moving speed of the current moving target object and the speed of the current fixed target object into a fifth current feature image, and the speed of the current fixed target object is zero; converting the current driving acceleration of the target vehicle, the moving acceleration of the current moving target object and the acceleration of the current fixed target object into a sixth current feature image, and the acceleration of the current fixed target object is zero.

[0014] Optionally, the current moving target objects include at least moving vehicles and moving pedestrians, and the current fixed target objects include at least fixed road signs.

[0015] According to one aspect of the present application, a safety warning device is provided, comprising: a processing unit, configured to determine a current driving area of ​​a target vehicle and obtain current driving state information of the target vehicle, wherein the current driving state information includes at least current driving speed and current position information of the target vehicle; a first obtaining unit, configured to obtain relevant information of a current moving target and relevant information of a current fixed target, wherein the relevant information of the current moving target includes at least distance information between the current moving target and the target vehicle and a moving speed of the current moving target, and the relevant information of the current fixed target includes at least distance information between the current fixed target and the target vehicle, wherein the current moving target is a moving target within the current driving area, and the current fixed target is a fixed target within the current driving area; a conversion unit, configured to convert the current driving state information of the target vehicle, the relevant information of the current moving target, and the relevant information of the current fixed target into a current feature image; and a first determining unit, configured to determine, based on the current feature image, the current collision probabilities of the target vehicle with the current moving target and the current fixed target, respectively.

[0016] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described.

[0017] According to another aspect of the present application, a processor is provided, wherein the processor is configured to run a program, wherein the program executes any one of the methods described when the program is run.

[0018] According to another aspect of the present application, a vehicle is provided, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the described methods.

[0019] Applying the technical solution of the present application, by determining the current driving area of ​​the target vehicle and obtaining the current driving state information of the target vehicle, obtaining the relevant information of the current fixed target and the relevant information of the current fixed target, the current driving state information of the target vehicle, the relevant information of the current fixed target and the relevant information of the current fixed target are converted into a current feature image, and based on the current feature image, the current collision probability of the target vehicle with the current fixed target and the current fixed target is determined. This solution achieves a safety warning by converting the current driving state information of the target vehicle, the relevant information of the current fixed target and the relevant information of the current fixed target into a current feature image, and then using the current feature image to determine the current collision probability of the target vehicle with the current fixed target and the current fixed target. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings that constitute part of this application are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0021] Figure 1 A flow chart of a method for security warning according to an embodiment of the present application is shown;

[0022] Figure 2 A schematic diagram of a safety warning device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0023] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] It should be understood that when an element (such as a layer, film, region, or substrate) is described as being “on” another element, the element may be directly on the other element or intervening elements may be present. Furthermore, in the specification and claims, when it is described that an element is “connected to” another element, the element may be “directly connected to” the other element or “connected to” the other element through a third element.

[0027] As introduced in the background technology, the accuracy of safety warnings of existing assisted driving systems is relatively low, and safety accidents are prone to occur. In order to solve the problem that the accuracy of safety warnings of existing assisted driving systems is relatively low and safety accidents are prone to occur, the embodiments of the present application provide a safety warning method, device, computer-readable storage medium, processor and vehicle.

[0028] According to an embodiment of the present application, a security early warning method is provided.

[0029] Figure 1 This is a flow chart of a method for security warning according to an embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0030] Step S101, determining the current driving area of ​​the target vehicle and obtaining the current driving state information of the target vehicle, the current driving state information including at least the current driving speed and current position information of the target vehicle;

[0031] Step S102: Obtaining relevant information of a current moving target and relevant information of a current fixed target, wherein the relevant information of the current moving target includes at least information about the distance between the current moving target and the target vehicle and the moving speed of the current moving target, and the relevant information of the current fixed target includes at least information about the distance between the current fixed target and the target vehicle, wherein the current moving target is a moving target within the current driving area, and the current fixed target is a fixed target within the current driving area;

[0032] Specifically, the current driving state information also includes the current driving acceleration;

[0033] Specifically, the relevant information of the current moving target object also includes the acceleration of the current moving target object;

[0034] Specifically, the relevant information of the current moving target also includes the relative position of the current moving target and the target vehicle, for example, the current moving target is on the left side of the target vehicle, the current moving target is on the right side of the target vehicle, the current moving target is in front of the target vehicle, and the current moving target is behind the target vehicle. Of course, the relevant information of the current moving target may also include other information.

[0035] Specifically, the information related to the current fixed target also includes the relative position of the current fixed target and the target vehicle, for example, the current fixed target is on the left side of the target vehicle, the current fixed target is on the right side of the target vehicle, the current fixed target is in front of the target vehicle, and the current fixed target is behind the target vehicle. Of course, the information related to the current fixed target may also include other information.

[0036] Step S103, converting the current driving state information of the target vehicle, the relevant information of the current fixed target object, and the relevant information of the current fixed target object into a current feature image;

[0037] It should be noted that the above-mentioned current feature image is not a real image obtained, but an encoded image. The current feature image is used to represent the current driving status information of the target vehicle, the relevant information of the above-mentioned current fixed target object, and the relevant information of the above-mentioned current fixed target object.

[0038] Step S104 : determining the current collision probabilities of the target vehicle and the current fixed target and the current fixed target, respectively, based on the current feature image.

[0039] In the above scheme, the current driving area of ​​the target vehicle is determined, and the current driving state information of the target vehicle is obtained, and the relevant information of the current fixed target and the relevant information of the current fixed target are obtained. The current driving state information of the target vehicle, the relevant information of the current fixed target, and the relevant information of the current fixed target are converted into a current feature image. Based on the current feature image, the current collision probability of the target vehicle with the current fixed target and the current fixed target, respectively, is determined. This scheme achieves a safety warning by converting the current driving state information of the target vehicle, the relevant information of the current fixed target, and the relevant information of the current fixed target, respectively, into a current feature image, and then using the current feature image to determine the current collision probability of the target vehicle with the current fixed target and the current fixed target, respectively.

[0040] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0041] In one embodiment of the present application, before determining the current driving area of ​​the target vehicle, the method further includes: obtaining historical driving status information of the target vehicle, the historical driving status information at least including the historical driving speed and historical position information of the target vehicle; obtaining relevant information of historical moving targets and relevant information of historical fixed targets within the historical driving area of ​​the target vehicle, the relevant information of the historical moving targets at least including the distance information between the historical moving targets and the target vehicle and the moving speed of the historical moving targets, and the relevant information of the historical fixed targets at least including the distance information between the historical fixed targets and the target vehicle; obtaining the historical collision probability of the target vehicle and the historical moving targets and the historical fixed targets.

[0042] In one embodiment of the present application, the current collision probability of the target vehicle with the current moving target and the current fixed target is determined based on the current feature image, including: converting the historical driving state information of the target vehicle, the relevant information of the historical moving target, and the relevant information of the historical fixed target into a historical feature image; constructing a neural network model, wherein the neural network model is trained using multiple sets of training data, each of the multiple sets of training data including: a historical feature image and a historical collision probability corresponding to the historical feature image acquired within a historical time period; and determining the current collision probability corresponding to the current feature image based on the neural network model. That is, the historical driving state information of the target vehicle, the relevant information of the historical fixed target, and the relevant information of the historical fixed target acquired within a historical time period are converted into a historical feature image, and then a neural network model is constructed, and then the current collision probability corresponding to the current feature image is determined based on the neural network model, thereby achieving accurate determination of the current collision probability.

[0043] In one embodiment of the present application, after obtaining the historical collision probabilities of the target vehicle and the historical moving target and the historical fixed target, the method further includes: using the historical driving state information of the target vehicle, the relevant information of the historical moving target, the relevant information of the historical fixed target, and the historical collision probabilities to train a random forest model; based on the random forest model, according to the current driving state information of the target vehicle, the relevant information of the current moving target, and the relevant information of the current fixed target, determining the current collision probabilities of the target vehicle with the current moving target and the current fixed target, respectively. The random forest model is used to accurately determine the current collision probability.

[0044] In one embodiment of the present application, the random forest model includes a plurality of decision trees, and the random forest model is trained using the historical driving state information of the target vehicle, the relevant information of the historical mobile target object, the relevant information of the historical fixed target object, and the historical collision probability, including: using a first information combination of the historical driving state information of the target vehicle, a first information combination of the relevant information of the historical mobile target object, a first information combination of the relevant information of the historical fixed target object, and the historical collision probability to train a first decision tree;

[0045] A second decision tree is trained using a second combination of the target vehicle's historical driving state information, a second combination of the historical mobile object information, a second combination of the historical fixed object information, and the historical collision probability. A third decision tree is trained using a third combination of the target vehicle's historical driving state information, a third combination of the historical mobile object information, a third combination of the historical fixed object information, and the historical collision probability. The first, second, and third decision trees are integrated to obtain the random forest model. Specifically, different decision trees are first established using different information, and then the multiple decision trees are integrated to obtain the accurate random forest model.

[0046] In one embodiment of the present application, the current collision probability of the target vehicle with the current moving target and the current fixed target is determined based on the current feature image, including: determining the first distance information between the target vehicle and the current moving target at the next moment, and the second distance information between the target vehicle and the current fixed target at the next moment based on the current feature image; determining the first current collision probability of the target vehicle colliding with the current moving target at the next moment based on the first distance information; and determining the second current collision probability of the target vehicle colliding with the current fixed target at the next moment based on the second distance information. Specifically, the next moment is 3 seconds apart from the current moment. That is, based on the information obtained at the current moment, the collision probability at the next moment is predicted. This provides a safety warning.

[0047] In one embodiment of the present application, determining a first current collision probability of the target vehicle colliding with the current fixed target at the next moment based on the first distance information includes: if the first distance information is less than a predetermined distance, determining that the first current collision probability is greater than a preset probability; and determining a second current collision probability of the target vehicle colliding with the current fixed target at the next moment based on the second distance information includes: if the second distance information is less than a predetermined distance, determining that the second current collision probability is greater than a preset probability. That is, the smaller the distance between the target vehicle and the current fixed target, the greater the preliminary determination of the probability of collision at the next moment.

[0048] In one embodiment of the present application, the current driving state information of the target vehicle, the relevant information of the current moving target object, and the relevant information of the current fixed target object are converted into a current feature image, including: converting the current driving state information of the target vehicle into a first current feature image, the color of the first current feature image is a first color, the first current feature image has multiple channels, and each of the channels represents a type of information in the current driving state information; converting the relevant information of the current moving target object into a second current feature image, the color of the second current feature image is a second color, the second current feature image has multiple channels, and each of the channels represents a type of information in the relevant information of the current moving target object; converting the relevant information of the current fixed target object into a third current feature image, the color of the third current feature image is a third color, the third current feature image has multiple channels, and each of the channels represents a type of information in the relevant information of the current fixed target object. Specifically, the first color is red, the first current feature image has six channels, the second color is green, the second current feature image has six channels, the second color is blue, and the third current feature image has six channels. Different channels represent different information.

[0049] In one embodiment of the present application, the current driving status information of the target vehicle, the relevant information of the current moving target object and the relevant information of the current fixed target object are converted into a current feature image, including: converting the same information parameters of the target vehicle, the current moving target object and the current fixed target object into a current feature image, and the current feature image includes three channels, the first channel represents the information parameters of the target vehicle, the second channel represents the information parameters of the current moving target object, and the third channel represents the information parameters of the current fixed target object.

[0050] In one embodiment of the present application, the same information parameter of the target vehicle, the current moving target and the current fixed target is converted into a current feature image, including: converting the current position information of the target vehicle, the position information of the current moving target and the position information of the current fixed target into a fourth current feature image; converting the current driving speed of the target vehicle, the moving speed of the current moving target and the speed of the current fixed target into a fifth current feature image, and the speed of the current fixed target is zero; converting the current driving acceleration of the target vehicle, the moving acceleration of the current moving target and the acceleration of the current fixed target into a sixth current feature image, and the acceleration of the current fixed target is zero.

[0051] In one embodiment of the present application, the current moving target includes at least a moving vehicle and a moving pedestrian, and the current fixed target includes at least a fixed road sign. Of course, the current moving target may also include other moving targets, and the current fixed target may also include other fixed targets.

[0052] The embodiment of the present application also provides a security warning device. It should be noted that the security warning device of the embodiment of the present application can be used to execute the security warning method provided in the embodiment of the present application. The security warning device provided in the embodiment of the present application is introduced below.

[0053] Figure 2 Schematic diagram of a safety warning device according to an embodiment of the present application. Figure 2 As shown, the device includes:

[0054] The processing unit 10 is configured to determine a current driving area of ​​the target vehicle and obtain current driving state information of the target vehicle, wherein the current driving state information includes at least current driving speed and current position information of the target vehicle;

[0055] A first acquiring unit 20 is configured to acquire information related to a current fixed target and information related to the current fixed target, wherein the information related to the current fixed target includes at least information about the distance between the current fixed target and the target vehicle and a fixed speed of the current fixed target, wherein the information related to the current fixed target includes at least information about the distance between the current fixed target and the target vehicle, and the current fixed target is a fixed target within the current driving area;

[0056] A conversion unit 30 is configured to convert the current driving state information of the target vehicle, the relevant information of the current fixed target object, and the relevant information of the current fixed target object into a current feature image;

[0057] The first determining unit 40 is configured to determine, based on the current feature image, the current collision probabilities of the target vehicle and the current fixed target and the current fixed target, respectively.

[0058] In the above scheme, the processing unit determines the current driving area of ​​the target vehicle and obtains the current driving state information of the target vehicle. The first acquisition unit obtains the relevant information of the current fixed target and the relevant information of the current fixed target. The conversion unit converts the current driving state information of the target vehicle, the relevant information of the current fixed target, and the relevant information of the current fixed target into a current feature image. The first determination unit determines the current collision probability of the target vehicle with the current fixed target and the current fixed target, respectively, based on the current feature image. This scheme achieves a safety warning by converting the current driving state information of the target vehicle, the relevant information of the current fixed target, and the relevant information of the current fixed target, respectively, into a current feature image, and then using the current feature image to determine the current collision probability of the target vehicle with the current fixed target and the current fixed target, respectively.

[0059] In one embodiment of the present application, the above-mentioned device also includes a second acquisition unit, a third acquisition unit and a fourth acquisition unit. The second acquisition unit is used to obtain the historical driving status information of the above-mentioned target vehicle before determining the current driving area of ​​the target vehicle, and the above-mentioned historical driving status information at least includes the historical driving speed and historical position information of the above-mentioned target vehicle; the third acquisition unit is used to obtain the relevant information of historical moving targets and relevant information of historical fixed targets in the historical driving area of ​​the above-mentioned target vehicle before determining the current driving area of ​​the target vehicle, and the relevant information of the above-mentioned historical moving targets at least includes the distance information between the above-mentioned historical moving targets and the above-mentioned target vehicle and the moving speed of the above-mentioned historical moving targets, and the relevant information of the above-mentioned historical fixed targets at least includes the distance information between the above-mentioned historical fixed targets and the above-mentioned target vehicle; the fourth acquisition unit is used to obtain the historical collision probability of the above-mentioned target vehicle and the above-mentioned historical moving targets and the above-mentioned historical fixed targets before determining the current driving area of ​​the target vehicle.

[0060] In one embodiment of the present application, the first determination unit includes a conversion module, a construction module, and a first determination module. The conversion module is configured to convert the target vehicle's historical driving state information, the historical information related to the mobile target object, and the historical information related to the fixed target object into a historical feature image. The construction module is configured to construct a neural network model, wherein the neural network model is trained using multiple sets of training data, each of which includes: a historical feature image acquired during a historical time period; and a historical collision probability corresponding to the historical feature image. The first determination module is configured to determine the current collision probability corresponding to the current feature image based on the neural network model. Specifically, the target vehicle's historical driving state information, the historical information related to the fixed target object, and the historical information related to the fixed target object acquired during a historical time period are converted into a historical feature image, and then a neural network model is constructed. Furthermore, the current collision probability corresponding to the current feature image is determined based on the neural network model, thereby accurately determining the current collision probability.

[0061] In one embodiment of the present application, the apparatus further includes a training unit and a second determination unit. The training unit is configured to, after obtaining the target vehicle and the historical fixed target and the historical collision probabilities of the historical fixed target, use the historical driving state information of the target vehicle, the relevant information of the historical mobile target, the relevant information of the historical fixed target, and the historical collision probabilities to train a random forest model. The second determination unit is configured to determine, based on the random forest model and according to the current driving state information of the target vehicle, the relevant information of the current mobile target, and the relevant information of the current fixed target, the current collision probabilities of the target vehicle with the current mobile target and the current fixed target, respectively. The random forest model is used to accurately determine the current collision probability.

[0062] In one embodiment of the present application, the random forest model includes multiple decision trees, and the training unit includes a first training module, a second training module, a third training module and an integration module. The first training module is used to use the first information combination in the historical driving status information of the target vehicle, the first information combination in the relevant information of the historical moving target object, the first information combination in the relevant information of the historical fixed target object and the historical collision probability to train a first decision tree; the second training module is used to use the second information combination in the historical driving status information of the target vehicle, the second information combination in the relevant information of the historical moving target object, the second information combination in the relevant information of the historical fixed target object and the historical collision probability to train a second decision tree; the third training module is used to use the third information combination in the historical driving status information of the target vehicle, the third information combination in the relevant information of the historical moving target object, the third information combination in the relevant information of the historical fixed target object and the historical collision probability to train a third decision tree; the integration module is used to integrate the first decision tree, the second decision tree and the third decision tree to obtain the random forest model. That is, different information is first used to establish different decision trees, and then multiple decision trees are integrated to obtain the accurate random forest model mentioned above.

[0063] In one embodiment of the present application, the first determination unit includes a second determination module, a third determination module and a fourth determination module. The second determination module is used to determine the first distance information between the target vehicle and the current moving target object at the next moment, and the second distance information between the target vehicle and the current fixed target object at the next moment based on the current feature image; the third determination module is used to determine the first current collision probability of the target vehicle colliding with the current moving target object at the next moment based on the first distance information; and the fourth determination module is used to determine the second current collision probability of the target vehicle colliding with the current fixed target object at the next moment based on the second distance information.

[0064] In one embodiment of the present application, the third determination module is further used to determine that the first current collision probability is greater than the preset probability when the first distance information is less than the predetermined distance; the fourth determination module is further used to determine that the second current collision probability is greater than the preset probability when the second distance information is less than the predetermined distance.

[0065] In one embodiment of the present application, the conversion unit includes a first conversion module, a second conversion module and a third conversion module. The first conversion module is used to convert the current driving status information of the above-mentioned target vehicle into a first current feature image. The color of the above-mentioned first current feature image is a first color. The above-mentioned first current feature image has multiple channels, and each of the above-mentioned channels represents a type of information in the above-mentioned current driving status information; the second conversion module is used to convert the relevant information of the above-mentioned current moving target object into a second current feature image. The color of the above-mentioned second current feature image is a second color. The above-mentioned second current feature image has multiple channels, and each of the above-mentioned channels represents a type of information in the relevant information of the above-mentioned current moving target object; the third conversion module is used to convert the relevant information of the above-mentioned current fixed target object into a third current feature image. The color of the above-mentioned third current feature image is a third color. The above-mentioned third current feature image has multiple channels, and each of the above-mentioned channels represents a type of information in the relevant information of the above-mentioned current fixed target object.

[0066] In one embodiment of the present application, the conversion unit is also used to convert the same information parameters of the above-mentioned target vehicle, the above-mentioned current moving target object and the above-mentioned current fixed target object into a current feature image, and the above-mentioned current feature image includes three channels, the first above-mentioned channel represents the information parameters of the above-mentioned target vehicle, the second above-mentioned channel represents the information parameters of the above-mentioned current moving target object, and the third above-mentioned channel represents the information parameters of the above-mentioned current fixed target object.

[0067] In one embodiment of the present application, the conversion unit includes a fourth conversion module, a fifth conversion module and a sixth conversion module. The fourth conversion module is used to convert the current position information of the target vehicle, the position information of the current fixed target object and the position information of the current fixed target object into a fourth current feature image; the fifth conversion module is used to convert the current driving speed of the target vehicle, the moving speed of the current moving target object and the speed of the current fixed target object into a fifth current feature image, and the speed of the current fixed target object is zero; the sixth conversion module is used to convert the current driving acceleration of the target vehicle, the moving acceleration of the current moving target object and the acceleration of the current fixed target object into a sixth current feature image, and the acceleration of the current fixed target object is zero.

[0068] The security warning device includes a processor and a memory. The above-mentioned processing unit, first acquisition unit, conversion unit and first determination unit are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0069] The processor contains a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and accurate security warnings can be achieved by adjusting kernel parameters.

[0070] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0071] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program. When the program is executed, the device where the computer-readable storage medium is located is controlled to execute the security warning method.

[0072] An embodiment of the present invention provides a processor, which is used to run a program, wherein the security warning method is executed when the program is running.

[0073] An embodiment of the present invention provides a vehicle, comprising one or more processors, a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the above methods.

[0074] An embodiment of the present invention provides a device, comprising a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, at least the following steps are performed:

[0075] Step S101, determining the current driving area of ​​the target vehicle and obtaining the current driving state information of the target vehicle, the current driving state information including at least the current driving speed and current position information of the target vehicle;

[0076] Step S102: Obtaining information related to a current fixed target and information related to the current fixed target, wherein the information related to the current fixed target includes at least information about the distance between the current fixed target and the target vehicle and a fixed speed of the current fixed target, and the information related to the current fixed target includes at least information about the distance between the current fixed target and the target vehicle, and the current fixed target is a fixed target within the current driving area;

[0077] Step S103, converting the current driving state information of the target vehicle, the relevant information of the current fixed target object, and the relevant information of the current fixed target object into a current feature image;

[0078] Step S104 : determining the current collision probabilities of the target vehicle and the current fixed target and the current fixed target, respectively, based on the current feature image.

[0079] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0080] The present application also provides a computer program product, which, when executed on a data processing device, is adapted to execute a program for initializing at least the following method steps:

[0081] Step S101, determining the current driving area of ​​the target vehicle and obtaining the current driving state information of the target vehicle, the current driving state information including at least the current driving speed and current position information of the target vehicle;

[0082] Step S102: Obtaining information related to a current fixed target and information related to the current fixed target, wherein the information related to the current fixed target includes at least information about the distance between the current fixed target and the target vehicle and a fixed speed of the current fixed target, and the information related to the current fixed target includes at least information about the distance between the current fixed target and the target vehicle, and the current fixed target is a fixed target within the current driving area;

[0083] Step S103, converting the current driving state information of the target vehicle, the relevant information of the current fixed target object, and the relevant information of the current fixed target object into a current feature image;

[0084] Step S104 : determining the current collision probabilities of the target vehicle and the current fixed target and the current fixed target, respectively, based on the current feature image.

[0085] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0086] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0087] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0089] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0090] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0091] Computer-readable media includes both permanent and non-permanent, fixed and non-fixable media that can be implemented using any method or technology to store information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0092] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0093] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0094] 1) The safety warning method of the present application determines the current driving area of ​​the target vehicle, obtains the current driving status information of the target vehicle, obtains the relevant information of the current fixed target and the relevant information of the current fixed target, converts the current driving status information of the target vehicle, the relevant information of the current fixed target and the relevant information of the current fixed target into a current feature image, and determines the current collision probability of the target vehicle with the current fixed target and the current fixed target respectively based on the current feature image. This solution achieves a safety warning by converting the current driving status information of the target vehicle, the relevant information of the current fixed target and the relevant information of the current fixed target into a current feature image, and then using the current feature image to determine the current collision probability of the target vehicle with the current fixed target and the current fixed target respectively.

[0095] 2) In the safety warning device of the present application, the processing unit determines the current driving area of ​​the target vehicle and obtains the current driving status information of the target vehicle. The first obtaining unit obtains the relevant information of the current fixed target and the relevant information of the current fixed target. The conversion unit converts the current driving status information of the target vehicle, the relevant information of the current fixed target and the relevant information of the current fixed target into the current feature image. The first determining unit determines the current collision probability of the target vehicle with the current fixed target and the current fixed target respectively based on the current feature image. This solution realizes safety warning by converting the current driving status information of the target vehicle, the relevant information of the current fixed target and the relevant information of the current fixed target into the current feature image, and then using the current feature image to determine the current collision probability of the target vehicle with the current fixed target and the current fixed target respectively.

[0096] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A safety warning method, characterized in that: include: Determine the current driving area of ​​the target vehicle and obtain current driving state information of the target vehicle, wherein the current driving state information includes at least current driving speed and current position information of the target vehicle; Obtaining relevant information of a current moving target and relevant information of a current fixed target, wherein the relevant information of the current moving target includes at least distance information between the current moving target and the target vehicle and a moving speed of the current moving target, and the relevant information of the current fixed target includes at least distance information between the current fixed target and the target vehicle, the current moving target being a moving target within the current driving area, and the current fixed target being a fixed target within the current driving area; Converting the current driving state information of the target vehicle, the relevant information of the current moving target object, and the relevant information of the current fixed target object into a current feature image; determining, based on the current feature image, current collision probabilities of the target vehicle with the current moving target object and the current fixed target object respectively; Converting the current driving state information of the target vehicle, the relevant information of the current moving target object, and the relevant information of the current fixed target object into a current feature image includes: Converting the current position information of the target vehicle, the current position information of the moving target object, and the current position information of the fixed target object into a fourth current feature image; converting the current speed of the target vehicle, the current speed of the moving target object, and the current speed of the fixed target object into a fifth current feature image, where the current speed of the fixed target object is zero; The current driving acceleration of the target vehicle, the moving acceleration of the current moving target object and the acceleration of the current fixed target object are converted into a sixth current feature image, the acceleration of the current fixed target object is zero, and the current feature image includes three channels, the first channel represents the information parameters of the target vehicle, the second channel represents the information parameters of the current moving target object, and the third channel represents the information parameters of the current fixed target object.

2. The method according to claim 1, characterized in that Before determining the current driving area of ​​the target vehicle, the method further includes: Acquire historical driving state information of the target vehicle, wherein the historical driving state information includes at least historical driving speed and historical position information of the target vehicle; Obtaining relevant information about historical moving targets and historical fixed targets within a historical travel area of ​​the target vehicle, wherein the relevant information about the historical moving targets includes at least information about the distance between the historical moving targets and the target vehicle and the moving speed of the historical moving targets, and the relevant information about the historical fixed targets includes at least information about the distance between the historical fixed targets and the target vehicle; Obtain historical collision probabilities of the target vehicle, the historical moving target object, and the historical fixed target object.

3. The method according to claim 2, characterized in that Determining, based on the current feature image, current collision probabilities of the target vehicle with the current moving target object and the current fixed target object, respectively, includes: Converting the historical driving state information of the target vehicle, the historical relevant information of the mobile target object, and the historical relevant information of the fixed target object into a historical feature image; Constructing a neural network model, wherein the neural network model is trained using multiple sets of training data, each set of training data including: a historical feature image and a historical collision probability corresponding to the historical feature image, acquired during a historical time period; The current collision probability corresponding to the current feature image is determined according to the neural network model.

4. The method according to claim 2, characterized in that After obtaining the historical collision probabilities of the target vehicle and the historical moving target object and the historical fixed target object, the method further includes: A random forest model is obtained by training using the historical driving state information of the target vehicle, the historical relevant information of the moving target object, the historical relevant information of the fixed target object, and the historical collision probability; Based on the random forest model, the current collision probabilities of the target vehicle with the current moving target and the current fixed target are determined according to the current driving state information of the target vehicle, the relevant information of the current moving target and the relevant information of the current fixed target.

5. The method according to claim 4, characterized in that The random forest model includes multiple decision trees, which are trained using the historical driving state information of the target vehicle, the historical relevant information of the moving target object, the historical relevant information of the fixed target object, and the historical collision probability to obtain the random forest model, including: A first decision tree is trained using a first information combination of the historical driving state information of the target vehicle, a first information combination of the historical relevant information of the moving target object, a first information combination of the historical relevant information of the fixed target object, and the historical collision probability; A second decision tree is trained using a second information combination of the historical driving state information of the target vehicle, a second information combination of the historical relevant information of the moving target object, a second information combination of the historical relevant information of the fixed target object, and the historical collision probability; A third decision tree is trained using a third information combination of the historical driving state information of the target vehicle, a third information combination of the historical relevant information of the moving target object, a third information combination of the historical relevant information of the fixed target object, and the historical collision probability; The first decision tree, the second decision tree and the third decision tree are integrated to obtain the random forest model.

6. The method according to claim 1, characterized in that Determining, based on the current feature image, current collision probabilities of the target vehicle with the current moving target object and the current fixed target object, respectively, includes: Determining, based on the current feature image, first distance information between the target vehicle and the current moving target at a next moment, and second distance information between the target vehicle and the current fixed target at the next moment; determining a first current collision probability of the target vehicle colliding with the current moving target object at the next moment according to the first distance information; A second current collision probability of the target vehicle colliding with the current fixed target object at the next moment is determined according to the second distance information.

7. The method according to claim 6, characterized in that Determining a first current collision probability of the target vehicle colliding with the current moving target object at the next moment according to the first distance information includes: When the first distance information is less than a predetermined distance, determining that the first current collision probability is greater than a preset probability; Determining a second current collision probability of the target vehicle colliding with the current fixed target object at the next moment according to the second distance information includes: When the second distance information is less than a predetermined distance, it is determined that the second current collision probability is greater than a preset probability.

8. The method according to any one of claims 1 to 7, characterized in that The current moving target objects include at least moving vehicles and moving pedestrians, and the current fixed target objects include at least fixed road signs.

9. A safety warning device, characterized in that: include: a processing unit, configured to determine a current driving area of ​​a target vehicle and obtain current driving state information of the target vehicle, wherein the current driving state information includes at least current driving speed and current position information of the target vehicle; a first acquiring unit, configured to acquire relevant information of a current moving target and relevant information of a current fixed target, wherein the relevant information of the current moving target includes at least information about the distance between the current moving target and the target vehicle and a moving speed of the current moving target, and the relevant information of the current fixed target includes at least information about the distance between the current fixed target and the target vehicle, the current moving target being a moving target within the current driving area, and the current fixed target being a fixed target within the current driving area; A conversion unit, configured to convert the current driving state information of the target vehicle, the relevant information of the current moving target object, and the relevant information of the current fixed target object into a current feature image; a first determining unit, configured to determine, based on the current feature image, current collision probabilities of the target vehicle with the current moving target object and the current fixed target object; The conversion unit includes a fourth conversion module, a fifth conversion module and a sixth conversion module, wherein the fourth conversion module is used to convert the current position information of the target vehicle, the position information of the current fixed target object and the position information of the current fixed target object into a fourth current feature image; The fifth conversion module is used to convert the current driving speed of the target vehicle, the moving speed of the current moving target object and the speed of the current fixed target object into a fifth current feature image, and the speed of the current fixed target object is zero; the sixth conversion module is used to convert the current driving acceleration of the target vehicle, the moving acceleration of the current moving target object and the acceleration of the current fixed target object into a sixth current feature image, and the acceleration of the current fixed target object is zero. The current feature image includes three channels, the first channel represents the information parameters of the target vehicle, the second channel represents the information parameters of the current moving target object, and the third channel represents the information parameters of the current fixed target object.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 8.

11. A processor, characterized in that: The processor is configured to run a program, wherein the program executes the method according to any one of claims 1 to 8 when running.

12. A vehicle, characterized in that: The method comprises one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of claims 1 to 8.

Images