Intelligent driving control method, equipment and device, storage medium and vehicle

Abstract

The invention discloses an intelligent driving control method, equipment and device, a storage medium and a vehicle. The method comprises the following steps that the current distance between a running automobile and a pedestrian is obtained; when the current distance is equal to a first preset distance, extracting a first image of a current frame and a second image of a next frame in the pedestrian road condition video stream; according to the first image and the second image, determining an intention action of the pedestrian; and according to the intention action, the running automobile is controlled to execute a preset action. According to the method, the recognition accuracy in the intelligent driving process can be improved, and the timeliness of automobile control operation is improved. The method can be widely applied to the technical field of vehicle control.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to an intelligent driving control method, equipment, device, storage medium and vehicle. Background Art

[0002] In the related art, the existing in-vehicle intelligent driving image recognition function generally recognizes the movements of pedestrians on the road by using the relative position changes of the pedestrians in the image. This recognition method requires a long video stream, which slows down the detection speed. In addition, since pedestrians on the road may move slowly and hesitate, the detection accuracy of the recognition by position change is low. In addition, the recognition method by position change cannot recognize pedestrians in advance when they are about to run quickly. Therefore, there are still technical problems that need to be solved in the related art. Summary of the invention

[0003] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0004] To this end, an object of an embodiment of the present invention is to provide an intelligent driving control method, device, apparatus, storage medium and vehicle, which can improve the recognition accuracy during the intelligent driving process and improve the timeliness of automobile operation.

[0005] In order to achieve the above-mentioned technical objectives, the technical solution adopted by the embodiments of the present invention includes: an intelligent driving control method, comprising: obtaining the current distance between a moving car and a pedestrian; when the current distance is equal to a first preset distance, extracting the first image of the current frame and the second image of the next frame in the pedestrian road condition video stream; determining the intended action of the pedestrian based on the first image and the second image; and controlling the moving car to perform a preset action based on the intended action.

[0006] In addition, the intelligent driving control method according to the above embodiment of the present invention may also have the following additional technical features:

[0007] Furthermore, in an embodiment of the present invention, determining the intended action of the pedestrian based on the first image and the second image includes: extracting a first skeleton feature map of the pedestrian in the first image and a second skeleton feature map of the pedestrian in the second image; and determining the intended action of the pedestrian based on the first skeleton feature map and the second skeleton feature map.

[0008] Furthermore, in an embodiment of the present invention, determining the intended action of the pedestrian based on the first skeleton feature map and the second skeleton feature map includes: extracting a first feature bone group in the first skeleton feature map and a second feature bone group in the second skeleton feature map; and obtaining the intended action of the pedestrian based on the first feature bone group, the second feature bone group and a recognition model.

[0009] Furthermore, in an embodiment of the present invention, the preset actions include automatic lane changing, constant speed driving, deceleration and emergency braking, the intended actions include moving forward, moving backward and staying still, and controlling the moving car to perform preset actions based on the intended actions includes: determining that the intended action is moving forward, controlling the moving car to decelerate or perform emergency braking; determining that the intended action is moving backward, controlling the moving car to move at a constant speed or perform emergency braking; determining that the intended action is staying still, controlling the moving car to perform automatic lane changing or emergency braking.

[0010] Further, in an embodiment of the present invention, determining that the intended action is to move forward and controlling the moving vehicle to perform deceleration or emergency braking includes:

[0011] When it is determined that the intended action is to move forward and the current distance is greater than a second preset distance, controlling the moving vehicle to decelerate;

[0012] When it is determined that the intended action is to move forward and when the current distance is less than or equal to the second preset distance, the moving vehicle is controlled to perform emergency braking.

[0013] Further, in an embodiment of the present invention, determining that the intended action is to remain motionless and controlling the moving vehicle to perform automatic lane change or emergency braking includes:

[0014] When determining that the intended action is to move forward and when the current distance is greater than a third preset distance, controlling the moving vehicle to perform automatic lane change;

[0015] When it is determined that the intended action is to move forward and when the current distance is less than or equal to the third preset distance, the moving vehicle is controlled to perform emergency braking.

[0016] On the other hand, an embodiment of the present invention further provides an intelligent driving control device, including:

[0017] An acquisition unit, used for acquiring a current distance between a moving car and a pedestrian;

[0018] A first processing unit, configured to extract a first image of a current frame and a second image of a next frame in a pedestrian traffic video stream when the current distance is equal to a first preset distance;

[0019] a second processing unit, configured to determine an intended action of the pedestrian based on the first image and the second image;

[0020] The third processing unit is used to control the moving car to perform a preset action according to the intended action.

[0021] On the other hand, the present invention also provides an intelligent driving control device, comprising:

[0022] at least one processor;

[0023] at least one memory for storing at least one program;

[0024] When the at least one program is executed by the at least one processor, the at least one processor implements the intelligent driving control method as described above.

[0025] In addition, the present invention also provides a storage medium, in which processor-executable instructions are stored. When the processor-executable instructions are executed by the processor, they are used to execute the intelligent driving control method as described above.

[0026] In addition, the present invention also provides a vehicle, comprising the intelligent driving control device as described above or the intelligent driving control apparatus as described above.

[0027] The advantages and beneficial effects of the present invention will be partly given in the following description, partly become apparent from the following description, or be understood through the practice of the present invention:

[0028] The present invention can extract the first image of the current frame and the second image of the next frame in the pedestrian traffic video stream when the current distance between the moving car and the pedestrian is equal to the first preset distance; determine the intended action of the pedestrian through the first image and the second image; and control the moving car to perform the preset action according to the intended action. The present invention can identify the intended action of the pedestrian through the frame image, and then control the moving car to perform different preset actions according to the intended action. Since continuous frame image data can be obtained in a very short time, the present application can improve the detection speed data, and the short-term continuous image data can enable the smart car to predict the pedestrian's action, improving the recognition accuracy and recognition speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic diagram of the steps of an intelligent driving control method in a specific embodiment of the present invention;

[0030] Figure 2 A schematic diagram of the steps of determining the intended action of a pedestrian according to a first image and a second image in a specific embodiment of the present invention;

[0031] Figure 3 A schematic diagram of the steps of determining the intended action of a pedestrian according to the first skeleton feature map and the second skeleton feature map in a specific embodiment of the present invention;

[0032] Figure 4 A schematic diagram of the steps of determining that the intended action is to move forward and controlling a moving vehicle to perform deceleration or emergency braking in a specific embodiment of the present invention;

[0033] Figure 5 A schematic diagram of the steps of determining that the intended action is to remain stationary and controlling a moving vehicle to perform automatic lane change or emergency braking in a specific embodiment of the present invention;

[0034] Figure 6 A schematic diagram of the steps of determining that the intended action is to move backward and controlling a moving vehicle to perform constant speed driving or emergency braking in a specific embodiment of the present invention;

[0035] Figure 7 A schematic diagram of the steps of correcting the residual charge amount to obtain the corrected residual charge amount in a specific embodiment of the present invention;

[0036] Figure 8 A schematic diagram of a flow chart of an intelligent driving control method in another specific embodiment of the present invention;

[0037] Fig. 9 A schematic diagram of the structure of an intelligent driving control device in a specific embodiment of the present invention;

[0038] Fig.10 It is a structural schematic diagram of an intelligent driving control device in a specific embodiment of the present invention. DETAILED DESCRIPTION

[0039] The embodiments of the present invention are described in detail below with reference to the accompanying drawings to illustrate the principles and processes of the intelligent driving control method, device, apparatus, storage medium and vehicle in the embodiments of the present invention.

[0040] In the related art, the existing in-vehicle intelligent driving image recognition function generally recognizes the movements of pedestrians on the road by using the relative position changes of the pedestrians in the image. This recognition method requires a long video stream, which slows down the detection speed. In addition, since pedestrians on the road may move slowly and hesitate, the detection accuracy of the recognition by position change is low. In addition, the recognition method by position change cannot recognize pedestrians in advance when they are about to run quickly. Therefore, there are still technical problems that need to be solved in the related art.

[0041] In view of the above technical problems, the present invention can provide an intelligent driving control method. Figure 1 , Figure 1 Schematic diagram of the steps of the intelligent driving control method of the present invention. Figure 1 In the embodiment, the intelligent driving control method may include but is not limited to steps S101 to S104.

[0042] S101. Obtain the current distance between a moving vehicle and a pedestrian.

[0043] It is understandable that the current distance may be the distance between a moving car and a pedestrian, and the pedestrian may be a pedestrian that can be captured by a vehicle-mounted camera. The car may be a car traveling at a certain speed. Since the car is traveling, it is understandable that the current distance between the moving car and the pedestrian may be continuously reduced. That is to say, at each acquisition moment, the current distance between the moving car and the pedestrian is changing.

[0044] In some feasible embodiments of the present invention, the processor may first establish a wired connection with the camera device on the vehicle. Through the wired connection, the processor may obtain the current distance between the moving vehicle and the pedestrian captured by the camera device on the vehicle.

[0045] In some other feasible embodiments of the present invention, the processor may also first establish a wireless connection with a camera device disposed on the road. Through the wireless connection, the processor may obtain the current distance between the moving car and the pedestrian captured by the camera device on the road.

[0046] It should be noted that the wired connection method mentioned above may include the connection between the mobile device and the processing module, and may also include the connection between the processing module and the hardware device, and the wired connection between other devices currently known or to be developed in the future and the processing module; and the wireless connection method mentioned above may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (Ultra Wide Band) connection, and other wireless connection methods currently known or to be developed in the future. The energy management module and the battery detection module may be an integrated system, or they may be two separate systems that each implements corresponding functions.

[0047] S102: When the current distance is equal to the first preset distance, extract the first image of the current frame and the second image of the next frame in the pedestrian traffic video stream.

[0048] It is understandable that the first preset distance can be the distance at which the camera on the vehicle can clearly capture the movement of pedestrians within the field of view of the camera. It can also be the distance at which the camera on the road can clearly capture the movement of pedestrians and vehicles within the field of view of the camera. The pedestrian road condition video stream can be a video stream of road conditions for a period of time captured by the camera on the vehicle, or it can be a video stream of road conditions for a period of time captured by the camera on the road. The first image of the current frame can be a frame of image corresponding to the moment when the current distance is equal to the first preset distance, and correspondingly, the second image can be an image of the next frame corresponding to the first image.

[0049] In some feasible embodiments of the present invention, the processor continuously receives the pedestrian traffic video stream while the car is driving. When the current distance is equal to the first preset distance, the processor can extract the first image of the current frame and the second image of the next frame in the pedestrian traffic video stream.

[0050] It should be noted that, in order to collect two consecutive frames of images, when the processor of this embodiment extracts the first image of the current frame in the pedestrian traffic video stream, the car can also maintain its original state and continue to move forward. The first preset distance can be set differently according to the visibility of the environment.

[0051] S103: Determine the intended action of the pedestrian according to the first image and the second image.

[0052] It will be appreciated that the person's intended movements may include moving forward, moving backward, or remaining still.

[0053] In some feasible embodiments of the present invention, the processor may be configured with an image recognition algorithm. After the image recognition algorithm is configured, the processor may pass the obtained first image and second image through the image recognition algorithm to finally determine the intended action of the pedestrian.

[0054] It should be noted that the collected pedestrians may be one or more pedestrians. Correspondingly, the intended actions of the multiple pedestrians may be different or the same.

[0055] S104: According to the intended action, the moving vehicle is controlled to execute a preset action.

[0056] It is understandable that the preset action may be automatic lane change, constant speed driving, deceleration, and emergency braking. Automatic lane change may also be a lane change to the right lane in the forward direction or a lane change to the left lane in the forward direction.

[0057] In some feasible embodiments of the present invention, according to the intended action of the pedestrian, the processor can control the moving car to perform one of the following actions: automatic lane change, constant speed driving, deceleration, and emergency braking, or a combination of two or more actions. For example, automatic lane change, constant speed driving, or deceleration can be performed first, then automatic lane change, or first deceleration and then constant speed driving, or first deceleration to a certain speed and then constant speed driving and then automatic lane change.

[0058] In summary, the present invention can identify the intended action of pedestrians through frame images, and then control the moving car to perform different preset actions according to the intended action. Since continuous frame image data can be obtained in a very short time, the present application can improve the detection speed data, and the short-term continuous image data can enable the smart car to predict the pedestrian's action, improving the recognition accuracy and recognition speed.

[0059] Further, refer to Figure 2 , Figure 2 Schematic diagram of the steps of determining the intended action of a pedestrian according to the first image and the second image in the present invention. Figure 2 In the step, this step may include but is not limited to step S201 or step S202.

[0060] S201, extracting a first skeleton feature map of a pedestrian in a first image and a second skeleton feature map of a pedestrian in a second image.

[0061] S202: Determine the intended action of the pedestrian according to the first skeleton feature map and the second skeleton feature map.

[0062] It can be understood that the first skeleton feature map can be a skeleton feature map of a human body extracted from the first image, the first skeleton feature map can be one or more, and the first skeleton feature map can be determined by the number of pedestrians entering the image. Correspondingly, the second skeleton feature map can be a skeleton feature map of a human body extracted from the second image, the first skeleton feature map can be one or more, and the second skeleton feature map can also be determined by the number of pedestrians entering the image.

[0063] In some feasible embodiments of the present invention, the processor may be first configured with a built-in algorithm. The processor may then execute the algorithm and extract a first skeleton feature map of the pedestrian in the first image and a second skeleton feature map of the pedestrian in the second image. After obtaining the first skeleton feature map and the second skeleton feature map, the processor may identify the intended action of the pedestrian based on the first skeleton feature map and the second skeleton feature map.

[0064] Further, refer to Figure 3 , Figure 3Schematic diagram of the steps of determining the intended action of a pedestrian according to the first skeleton feature map and the second skeleton feature map in the present invention. Figure 3 In the step, this step may include but is not limited to step S301 or step S302.

[0065] S301, extracting a first characteristic bone group in a first skeleton feature graph and a second characteristic bone group in a second skeleton feature graph.

[0066] S302: Obtain the intended action of the pedestrian based on the first feature skeleton group, the second feature skeleton group and the recognition model.

[0067] It is understandable that the first characteristic skeleton can be the skeleton of the arm part, the skeleton of the thigh part or the skeleton of the trunk part; it can also be the skeleton of the upper body, that is, the combination of the skeleton of the arm part and the skeleton of the trunk part; it can also be the skeleton of the lower body, that is, the combination of the skeleton of the arm part and the skeleton of the trunk part; it can also be the skeleton of the limbs. Correspondingly, the second characteristic skeleton can be the skeleton of the arm part, the skeleton of the thigh part or the skeleton of the trunk part; it can also be the skeleton of the upper body, that is, the combination of the skeleton of the arm part and the skeleton of the trunk part; it can also be the skeleton of the lower body, that is, the combination of the skeleton of the arm part and the skeleton of the trunk part; it can also be the skeleton of the limbs. The recognition model can be obtained by training an existing artificial intelligence model. The training process can obtain skeleton feature maps corresponding to multiple image data in the database or previously collected after algorithm processing, and the multiple skeleton feature maps are input into the artificial intelligence model for training. During training, the parameters of the model can be continuously adjusted to obtain a trained artificial intelligence model with the minimum final loss value or the maximum confidence function.

[0068] In some feasible embodiments of the present invention, the processor may be first configured with a built-in algorithm. The processor then executes the algorithm and extracts the first characteristic bone group in the first skeleton feature map and the second characteristic bone group in the second skeleton feature map. After extracting the first characteristic bone group in the first skeleton feature map and the second characteristic bone group in the second skeleton feature map, the processor may input the first characteristic bone group and the second characteristic bone group into a trained recognition model to obtain the intended action of the pedestrian.

[0069] It should be noted that the recognition model may be an existing image recognition model, and correspondingly, the training of the recognition model may be obtained by an existing method.

[0070] Furthermore, according to the intended action, the moving car is controlled to perform a preset action, including step S401 or step S402 or step S403.

[0071] S401: Determine that the intended action is to move forward, and control the moving vehicle to perform deceleration or emergency braking.

[0072] or

[0073] S402: Determine that the intended action is to move backward, and control the moving vehicle to execute constant speed driving or emergency braking.

[0074] or

[0075] S403: Determine that the intended action is to remain stationary, and control the moving vehicle to perform automatic lane change or emergency braking.

[0076] In this embodiment, the first duration determination formula can be first configured in the processor. When the processor receives an enable signal as a first preset value and receives the remaining charge, it can directly input it into the first duration determination formula to obtain the first sleep duration when the enable signal is the first preset value.

[0077] Further, refer to Figure 4 , Figure 4 This is a schematic diagram of the steps of determining that the intended action is to move forward and controlling the moving vehicle to perform deceleration or emergency braking. Figure 4 In the step, the step may include but is not limited to step S501-step S502.

[0078] S501: When it is determined that the intended action is to move forward and the current distance is greater than a second preset distance, the moving vehicle is controlled to decelerate.

[0079] S502: When it is determined that the intended action is to move forward and the current distance is less than or equal to a second preset distance, the moving vehicle is controlled to perform emergency braking.

[0080] In some feasible embodiments of the present invention, when the intended action is determined to be forward and the current distance is greater than the second preset distance, the processor may control the moving car to decelerate. And / or, when the intended action is determined to be forward and the current distance is less than or equal to the second preset distance, the processor may control the moving car to perform emergency braking.

[0081] Further, refer to Figure 5 , Figure 5 is a schematic diagram of the steps of determining that the intended action is to remain stationary and controlling the moving vehicle to perform automatic lane change or emergency braking in the present invention, Figure 5 This step may include step S601-step S602.

[0082] S601: When it is determined that the intended action is to move forward and when the current distance is greater than a third preset distance, control the moving vehicle to perform automatic lane change.

[0083] S602: When it is determined that the intended action is to move forward and the current distance is less than or equal to a third preset distance, the moving vehicle is controlled to perform emergency braking.

[0084] In some feasible embodiments of the present invention, after determining that the intended action is to move forward and when the current distance is greater than the third preset distance, the processor may control the moving vehicle to perform automatic lane change. And / or, after determining that the intended action is to move forward and when the current distance is less than or equal to the third preset distance, the processor may control the moving vehicle to perform emergency braking.

[0085] Further, refer to Figure 6 , Figure 6 is a schematic diagram of the steps of determining that the intended action is to move backward and controlling the moving vehicle to perform constant speed driving or emergency braking in the present invention, Figure 6 In this step, this step may include step S701-step S702.

[0086] S701: When it is determined that the intended action is to move backward and the current distance is greater than a fourth preset distance, the moving vehicle is controlled to move at a constant speed.

[0087] S702: When it is determined that the intended action is to move backward and the current distance is less than or equal to a fourth preset distance, the moving vehicle is controlled to perform emergency braking.

[0088] Further, in some feasible embodiments of the present invention, after determining that the intended action is to move backward and when the current distance is greater than the fourth preset distance, the processor may control the moving car to drive at a constant speed. And / or, after determining that the intended action is to move backward and when the current distance is less than or equal to the fourth preset distance, the processor may control the moving car to perform emergency braking.

[0089] It is understandable that the second preset distance, the third preset distance, and the fourth preset distance may be different from the first preset distance, may be equal to the first preset distance, or may be less than the first preset distance. Moreover, the second preset distance, the third preset distance, and the fourth preset distance may be the same distance. The specific values ​​of the first preset distance, the second preset distance, the third preset distance, and the fourth preset distance may be adjusted according to actual needs.

[0090] The specific implementation principle of the present invention is described below in conjunction with the accompanying drawings:

[0091] Reference Figure 7 as well as Figure 8First, this embodiment performs video image acquisition. Specifically, this embodiment first measures the current distance between the moving car and the pedestrian. When the distance between the car and the pedestrian is equal to the distance at which the on-board camera can clearly capture the external environment video information, this embodiment uses the on-board camera to collect the vehicle's external environment video information in real time and sends the external environment video information to the intelligent driving controller in real time, where the video stream will.

[0092] Secondly, this embodiment can perform pre-action recognition on pedestrians. Specifically, the intelligent driving controller receives the video stream information of the vehicle-mounted camera in real time. The intelligent driving controller decomposes the video stream information into frame-by-frame image information in real time, and recognizes the pedestrian image separately. The intelligent driving controller converts the pedestrian image into a human body contour and a main skeleton image in real time, and realizes the decryption processing of the pedestrian information. The intelligent driving controller compares the main skeleton action angles in the two adjacent frames of human body contour and main skeleton image in real time. The intelligent driving controller pre-recognizes and determines the pedestrian's forward, backward, turn, etc. actions according to the comparison results of the human skeleton action angles. Among them, the two steps of comparing the main skeleton action angles and obtaining the intelligent driving controller pre-recognizes and determines the pedestrian's forward, backward, turn, etc. actions according to the comparison results of the human skeleton action angles can be performed by the existing recognition model. The intelligent driving controller outputs control instructions such as automatic lane change, uniform speed driving, deceleration, emergency braking, etc. according to the pre-recognition judgment results of the pedestrian action.

[0093] Finally, this embodiment can control the vehicle. Specifically, the vehicle control system can automatically change lanes, drive at a constant speed, decelerate, perform emergency braking, etc. on the vehicle at different distances from pedestrians according to the vehicle control instructions of the intelligent driving controller.

[0094] In summary, the present invention has the following advantages:

[0095] 1) The present invention can identify the intended action of pedestrians through frame images, and then control the moving car to perform different preset actions according to the intended action. Since continuous frame image data can be obtained in a very short time, the present application can improve the detection speed data, and the short-term continuous image data can enable the smart car to predict the pedestrian's action, improving the recognition accuracy and recognition speed.

[0096] 2) The present invention mainly predicts pedestrian movements through the changes in the angles of the main human skeleton movements. At the same time, the present invention desensitizes pedestrian information and converts the complete image information of pedestrians into the external contour and main skeleton information of the human body required for intelligent driving, which can achieve the desensitization of pedestrian information and improve the problem of human information security protection.

[0097] In addition, refer to Fig. 9 ,and Figure 1Corresponding to the method, an intelligent driving control device is also provided in an embodiment of the present invention. The device may include: an acquisition unit 1001, a first processing unit 1002, a second processing unit 1003 and a third processing unit 1004. The acquisition unit 1001 can be used to obtain the current distance between a moving car and a pedestrian. The first processing unit 1002 can be used to extract the first image of the current frame and the second image of the next frame in the pedestrian road condition video stream when the current distance is equal to the first preset distance. The second processing unit 1003 can be used to determine the intended action of the pedestrian based on the first image and the second image; the third processing unit 1004 can be used to control the moving car to perform a preset action based on the intended action.

[0098] It should be noted that the acquisition unit can be any integrated circuit unit or microprocessor unit obtained by integrating a chip having a processing function and its peripheral circuits through existing integration technology. The first processing unit and the second processing unit can also be any integrated circuit module or microprocessor module obtained by integrating a chip having a processing function and its peripheral circuits through existing integration technology. The first processing unit and the second processing unit can also include one or more memories. One or more memories can be used to store the specific algorithm for intelligent driving control in the present invention.

[0099] In some embodiments of the present invention, the acquisition unit 1001 can be set in the same device with a processor as the first processing unit 1002. The acquisition unit 1001 can acquire the current distance between the moving car and the pedestrian through the chip inside its own sensor. The first processing unit 1002 can extract the first image of the current frame and the second image of the next frame in the pedestrian traffic video stream when the current distance is equal to the first preset distance. The second processing unit 1003 can be used to determine the intended action of the pedestrian based on the first image and the second image. The third processing unit 1004 can control the moving car to perform a preset action based on the intended action. The acquisition unit 1001 can be any unit connected to the processor inside the gateway or device. The acquisition unit 1001 can transmit the acquired data to the processor through a wired or wireless connection with the processor of the processing unit 1002. The specific device connection method and device setting between the acquisition unit 1001 and the first processing unit 1002, and the first processing unit 1002 and the second processing unit 1003 are not limited.

[0100] It should be noted that the contents of the above-mentioned intelligent driving control method embodiment are all applicable to the present intelligent driving control device embodiment. The functions specifically implemented by the present intelligent driving control device embodiment are the same as those of the above-mentioned intelligent driving control method embodiment, and the beneficial effects achieved are also the same as those achieved by the above-mentioned intelligent driving control method embodiment.

[0101] and Figure 1 Corresponding to the method, the embodiment of the present invention also provides an intelligent driving control device, the specific structure of which can be referred to Fig.10 ,include:

[0102] at least one processor 1011;

[0103] At least one memory 1012, used to store at least one program;

[0104] When at least one program is executed by at least one processor, the at least one processor implements the intelligent driving control method.

[0105] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0106] and Figure 4 Corresponding to the method, an embodiment of the present invention further provides a computer-readable storage medium, which stores instructions executable by a processor, and the processor-executable instructions are used to execute the intelligent driving control method when executed by the processor.

[0107] The contents of the above-mentioned intelligent driving control method embodiment are all applicable to the present storage medium embodiment. The functions specifically implemented by the present storage medium embodiment are the same as those of the above-mentioned intelligent driving control method embodiment, and the beneficial effects achieved are also the same as those achieved by the above-mentioned intelligent driving control method embodiment.

[0108] In addition, the present invention also provides a vehicle, which may include the front intelligent driving control device or the front intelligent driving control equipment. Specifically, the vehicle may be a private car, such as a sedan, SUV, MPV or pickup truck. The vehicle may also be an operating vehicle, such as a van, bus, small truck or large trailer. The vehicle may be a fuel vehicle or a new energy vehicle. When the vehicle is a new energy vehicle, it may be a hybrid vehicle or a pure electric vehicle.

[0109] The contents of the above-mentioned intelligent driving control device or system embodiments are all applicable to the present vehicle embodiment. The functions specifically implemented by the present vehicle embodiment are the same as those of the above-mentioned intelligent driving control device or system embodiments, and the beneficial effects achieved are also the same as those achieved by the above-mentioned intelligent driving control device or system embodiments.

[0110] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0111] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0112] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several programs to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0113] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable programs for implementing the logical functions, and may be embodied in any computer-readable medium for use by a program execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch and execute a program from a program execution system, device or apparatus), or in conjunction with such program execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by a program execution system, device or apparatus, or in conjunction with such program execution systems, devices or apparatuses.

[0114] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0115] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0116] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0117] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0118] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. An intelligent driving control method, characterized in that: The following steps are involved: Get the current distance between the moving car and the pedestrian; When the current distance is equal to the first preset distance, extracting a first image of the current frame and a second image of the next frame in the pedestrian traffic video stream; determining an intended action of the pedestrian based on the first image and the second image; According to the intended action, the moving car is controlled to perform a preset action.

2. The intelligent driving control method according to claim 1, characterized in that: The determining the intended action of the pedestrian according to the first image and the second image includes: Extracting a first skeleton feature map of the pedestrian in the first image and a second skeleton feature map of the pedestrian in the second image; An intended action of the pedestrian is determined according to the first skeleton feature map and the second skeleton feature map.

3. The intelligent driving control method according to claim 2, characterized in that: The determining the intended action of the pedestrian according to the first skeleton feature map and the second skeleton feature map includes: Extracting a first characteristic bone group from the first skeleton feature graph and a second characteristic bone group from the second skeleton feature graph; The intended action of the pedestrian is obtained according to the first feature skeleton group, the second feature skeleton group and the recognition model.

4. The intelligent driving control method according to claim 1, characterized in that: The preset actions include automatic lane change, constant speed driving, deceleration and emergency braking, the intended actions include forward, backward and staying still, and according to the intended actions, controlling the moving vehicle to perform the preset actions includes: Determining that the intended action is to move forward, and controlling the moving vehicle to perform deceleration or emergency braking; Alternatively, determining that the intended action is to move backward, controlling the moving vehicle to perform constant speed driving or emergency braking; Alternatively, the intended action is determined to be to remain motionless, and the moving vehicle is controlled to perform automatic lane change or emergency braking.

5. The intelligent driving control method according to claim 4, characterized in that: Determining that the intended action is to move forward, and controlling the moving vehicle to perform deceleration or emergency braking, includes: Determining that the intended action is to move forward and when the current distance is greater than a second preset distance, controlling the moving vehicle to decelerate; Determine that the intended action is to move forward and when the current distance is less than or equal to the second preset distance, control the moving vehicle to perform emergency braking.

6. The intelligent driving control method according to claim 4, characterized in that: Determining that the intended action is to remain stationary, and controlling the moving vehicle to perform automatic lane change or emergency braking, includes: Determining that the intended action is to move forward and when the current distance is greater than a third preset distance, controlling the moving vehicle to perform an automatic lane change; Determine that the intended action is to move forward and when the current distance is less than or equal to the third preset distance, control the moving vehicle to perform emergency braking.

7. An intelligent driving control device, characterized in that: include: An acquisition unit, used for acquiring a current distance between a moving car and a pedestrian; A first processing unit, configured to extract a first image of a current frame and a second image of a next frame in a pedestrian traffic video stream when the current distance is equal to a first preset distance; a second processing unit, configured to determine an intended action of the pedestrian based on the first image and the second image; The third processing unit is used to control the moving car to perform a preset action according to the intended action.

8. An intelligent driving control device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the intelligent driving control method as described in any one of claims 1-6.

9. A computer-readable storage medium storing instructions executable by a processor, characterized in that: The processor-executable instructions are used to execute the intelligent driving control method as described in any one of claims 1-6 when executed by the processor.

10. A vehicle, characterized in that: It includes the intelligent driving control device as claimed in claim 7 or the intelligent driving control apparatus as claimed in claim 8.

Images