CN111942317B

CN111942317B - Driving door anti-collision method, device, system and computer readable storage medium

Info

Publication number: CN111942317B
Application number: CN202010809465.7A
Authority: CN
Inventors: 田振华
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2020-08-12
Filing date: 2020-08-12
Publication date: 2021-06-25
Anticipated expiration: 2040-08-12
Also published as: CN111942317A

Abstract

The application provides a driving door anti-collision method, a driving door anti-collision device, a driving door anti-collision system and a computer readable storage medium, wherein the method comprises the following steps: collecting picture information in the vehicle; identifying whether people in the vehicle make a preselected action or not based on the in-vehicle picture information; wherein the pre-selected action is an action for representing the intention of the person in the vehicle to drive the vehicle door; when the preselected action is identified, detecting whether an object to be avoided exists in a selected range; the selected range is a preset interval with the vehicle as the center; and if the object to be avoided exists, limiting the vehicle door to be opened. This application is through the action intention of the driving door of listening personnel in the car, and the detection of waiting to dodge the object is independently started to when detecting and waiting to dodge the object, the opening of restriction door, thereby solve the potential safety hazard that the door of opening easily causes the collision accident, improve the security that the vehicle used.

Description

Driving door anti-collision method, device, system and computer readable storage medium

Technical Field

The application relates to the technical field of vehicles, in particular to a driving door anti-collision method, device and system and a computer readable storage medium.

Background

In recent years, collision accidents caused by opening of vehicle doors are frequent, which not only bring great economic loss to vehicle owners, but also bring irreparable life cost. At present, the prevention of collision accidents caused by opening the door mainly depends on the prevention consciousness of people. However, even if the owner himself/herself is left to observe the direct door opening, the potential safety hazard of the collision accident caused by the driving of the vehicle door still exists.

Disclosure of Invention

In view of the above, an object of the present application is to provide a method, an apparatus, a system, and a computer-readable storage medium for preventing collision when a vehicle door is opened, which can start detection of an object to be avoided by detecting the intention of a vehicle door opening behavior of a vehicle occupant, and limit opening of a vehicle door when the object to be avoided is detected, so as to solve a potential safety hazard that a collision accident is easily caused when the vehicle door is opened, and improve safety of vehicle use.

In a first aspect, an embodiment of the present invention provides a method for preventing a door from being knocked down, including: collecting picture information in the vehicle; identifying whether people in the vehicle make a preselected action or not based on the in-vehicle picture information; wherein the pre-selected action is an action for representing the intention of the person in the vehicle to drive the vehicle door; when the preselected action is identified, detecting whether an object to be avoided exists in a selected range; the selected range is a preset interval with the vehicle as the center; and if the object to be avoided exists, limiting the vehicle door to be opened.

In some embodiments, the method is applied to a door opening collision avoidance system, which comprises a plurality of microwave sensors disposed at both ends of a vehicle body side having a vehicle door; the step of detecting whether the object to be avoided exists comprises the following steps: determining a target vehicle door to which the preselected action is directed; controlling a target sensor to detect whether the object to be avoided exists in the selected range; wherein the target sensor is a microwave sensor provided at the vehicle body side having the target door.

In some embodiments, the preselected action comprises a turn-around action, and the step of determining a target vehicle door to which the preselected action is directed comprises: acquiring multiframe in-vehicle picture information for recording the postures of the turning motion at each stage; calculating the spacing distance between the in-vehicle personnel making the turning motion and each vehicle door according to the acquired multiframe in-vehicle picture information; and determining the corresponding door with the minimum spacing distance as the target door.

In some embodiments, the preselected action comprises a turn-around action, and the step of determining a target vehicle door to which the preselected action is directed further comprises: acquiring multiframe in-vehicle picture information for recording the postures of the turning motion at each stage; according to the obtained multiframe picture information in the vehicle, obtaining the spacing distance and the turning direction between the personnel in the vehicle making the turning motion and each vehicle door; acquiring the corresponding vehicle door with the minimum spacing distance to serve as a vehicle door to be selected; and when a plurality of the candidate vehicle doors exist, taking the candidate vehicle door pointed by the turning direction as the target vehicle door.

In some embodiments, the step of detecting, by the control target sensor, whether the object to be avoided is present within the selected range includes: detecting a target object which is present in a detection area of the target sensor and is located in the selected range; if the target object moves towards the wave source of the target inductor, determining that the target object is the object to be avoided; and if the target object moves away from the wave source of the target inductor, judging that the target object is not the object to be avoided.

In some embodiments, the door drive collision avoidance system further comprises a blind zone monitoring unit disposed at a rear of the vehicle, the method further comprising: if the object to be avoided is not detected, starting the blind area monitoring unit to detect the moving object; when the moving object is not detected, opening the target vehicle door according to a door opening instruction triggered by the vehicle interior personnel; when the moving object is detected, acquiring a distance value between the moving object and the tail of the vehicle; and prompting the personnel in the vehicle to pay attention to the risk of opening the vehicle door when the distance value does not exceed a preset safe distance.

In some embodiments, the method further comprises: when the distance value does not exceed a preset safety distance and the door opening instruction is detected to be triggered by the person in the vehicle, controlling the target sensor arranged adjacent to the tail of the vehicle to start monitoring; judging whether the moving object enters a detection area of the target sensor or not according to a monitoring result of the target sensor arranged near the tail of the vehicle and a monitoring result of the blind area monitoring unit; if so, reducing the opening speed of the target vehicle door to a preset safe speed and limiting the maximum opening angle of the target vehicle door to a safe avoidance angle.

In some embodiments, the step of collecting the in-vehicle picture information includes: and when the vehicle is switched from a moving state to a static state, starting the collection of the picture information in the vehicle.

In some embodiments, the step of collecting the in-vehicle picture information includes: acquiring a service order which is bound with a vehicle and is in an execution state; wherein the service order includes destination information; when the vehicle speed is detected to be less than the preset speed per hour, comparing the current position information with the destination information; and if the distance between the current position information and the destination information is smaller than a preset distance, starting the collection of the picture information in the vehicle.

In a second aspect, an embodiment of the present invention further provides a door crash prevention device, including: the acquisition module is used for acquiring the picture information in the vehicle; the identification module is used for identifying whether people in the vehicle make a preselected action or not based on the in-vehicle picture information; wherein the pre-selected action is an action for representing the intention of the person in the vehicle to drive the vehicle door; the detection module is used for detecting whether an object to be avoided exists in a selected range when the preselected action is identified; the selected range is a preset interval with the vehicle as the center; and the control module is used for limiting the opening of the vehicle door if the object to be avoided exists.

In some embodiments, the device is applied to a door-opening collision avoidance system, which includes a plurality of microwave sensors disposed at both ends of a vehicle body side having a vehicle door; the detection module further comprises: the determining submodule is used for determining a target vehicle door pointed by the preselected action; the control submodule is used for controlling the target sensor to detect whether the object to be avoided exists in the selected range; wherein the target sensor is a microwave sensor provided at the vehicle body side having the target door.

In some embodiments, the preselected action comprises a turn-around action, the determination submodule being specifically configured to: acquiring multiframe in-vehicle picture information for recording the postures of the turning motion at each stage; calculating the spacing distance between the in-vehicle personnel making the turning motion and each vehicle door according to the acquired multiframe in-vehicle picture information; and determining the corresponding door with the minimum spacing distance as the target door.

In some embodiments, the preselected action comprises a turn-around action, the determination submodule being specifically configured to: acquiring multiframe in-vehicle picture information for recording the postures of the turning motion at each stage; according to the obtained multiframe picture information in the vehicle, obtaining the spacing distance and the turning direction between the personnel in the vehicle making the turning motion and each vehicle door; acquiring the corresponding vehicle door with the minimum spacing distance to serve as a vehicle door to be selected; and when a plurality of the candidate vehicle doors exist, taking the candidate vehicle door pointed by the turning direction as the target vehicle door.

In some embodiments, the preselected action comprises a turn-around action, the detection module comprising: the detection submodule is used for detecting a target object which appears in a detection area of the target sensor and is positioned in the selected range; the judgment sub-module is used for judging that the target object is the object to be avoided if the target object moves towards the wave source of the target inductor; the judgment sub-module is further configured to judge that the target object is not the object to be avoided if the target object moves away from the wave source of the target sensor.

In some embodiments, the door-opening collision avoidance system further includes a blind zone monitoring unit disposed at a rear of the vehicle, and the apparatus further includes: the detection module is further configured to start the blind area monitoring unit to detect a moving object if the object to be avoided is not detected; the control module is further used for opening the target vehicle door according to a door opening instruction triggered by the vehicle interior personnel when the moving object is not detected; the acquisition module is used for acquiring a distance value between the moving object and the tail of the vehicle when the moving object is detected; and the prompting module is used for prompting the personnel in the vehicle to pay attention to the risk of opening the vehicle door when the distance value is not more than the preset safe distance.

In some embodiments, the apparatus further comprises: the detection module is further used for controlling the target sensor arranged adjacent to the tail of the vehicle to start monitoring when the distance value does not exceed a preset safe distance and the door opening instruction is detected to be triggered by the person in the vehicle; the judging module is used for judging whether the moving object enters a detection area of the target sensor or not according to a monitoring result of the target sensor arranged near the tail of the vehicle and a monitoring result of the blind area monitoring unit; the control module is used for reducing the opening speed of the target vehicle door to a preset safe speed and limiting the maximum opening angle of the target vehicle door to a safe avoiding angle when the moving object is judged to enter the detection area of the target sensor.

In some embodiments, the acquisition module is specifically configured to: and when the vehicle is switched from a moving state to a static state, starting the collection of the picture information in the vehicle.

In some embodiments, the acquisition module is specifically configured to: acquiring a service order which is bound with a vehicle and is in an execution state; wherein the service order includes destination information; when the vehicle speed is detected to be less than the preset speed per hour, comparing the current position information with the destination information; and if the distance between the current position information and the destination information is smaller than a preset distance, starting the collection of the picture information in the vehicle.

In a third aspect, an embodiment of the present invention further provides a door-opening collision avoidance system, including: the anti-collision system comprises a processor, a storage medium, a bus, a vehicle door controller, a collection device and a microwave sensor, wherein machine readable instructions executable by the processor are stored in the storage medium, when the anti-collision system for the vehicle door is operated, the processor and the storage medium are communicated through the bus, and the processor executes the machine readable instructions to control the vehicle door controller, the collection device and the microwave sensor to cooperatively execute the steps of the method in any one aspect.

In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the method in any one of the above aspects.

Based on any one of the aspects, the driving door anti-collision method provided by the embodiment of the invention identifies whether people in the vehicle make a preselected action representing the door opening intention or not based on the collected image information in the vehicle, and automatically detects whether an object to be avoided exists or not based on the fact that the identified preselected action is triggered in a selected range. Because the object to be avoided is the object which can be collided when the vehicle door is opened, when the object to be avoided exists, the vehicle door is limited to be opened, and the occurrence of collision accidents can be effectively avoided. That is, after the intention of opening the vehicle door of a person in the vehicle is recognized, whether the object to be avoided exists or not is automatically detected and avoided, so that the potential safety hazard that collision accidents are easily caused by opening the vehicle door is solved, and the use safety of the vehicle is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 is a schematic structural diagram illustrating a door-opening collision avoidance system according to an embodiment of the present application;

FIG. 2 is a diagram illustrating an example of an embodiment of a door-opening collision avoidance system applied to a sedan;

fig. 3 shows one of the flowcharts of a driving door collision avoidance method provided by the embodiment of the present application;

fig. 4 is a flowchart illustrating a specific method of step S103 in a method for preventing a door from being bumped according to an embodiment of the present application;

FIG. 5 is a flowchart illustrating a specific method of step S103-1 provided in the embodiments of the present application;

FIG. 6 is a flowchart illustrating another specific method of step S103-1 provided in the embodiments of the present application;

FIG. 7 is a flowchart illustrating a specific method of step S103-2 provided by an embodiment of the present application;

fig. 8 illustrates a second flowchart of a driving door collision avoidance method according to an embodiment of the present application;

fig. 9 shows a third flowchart of a driving door collision avoidance method according to an embodiment of the present application;

fig. 10 shows a schematic diagram of a door opening collision avoidance device provided by an embodiment of the application.

Detailed Description

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.

In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

In order to enable a person skilled in the art to use the present disclosure, the following embodiments are given in connection with a specific application scenario "sedans". It will be apparent to those skilled in the art that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the application. Although the present application is described primarily in the context of a door-opening collision avoidance method as applied to a "sedan", it should be understood that this is only one exemplary embodiment and may also be applied to buses, net appointments, and the like.

It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.

The Positioning technology used in the present application may be based on a Global Positioning System (GPS), a Global Navigation Satellite System (GLONASS), a COMPASS Navigation System (COMPASS), a galileo Positioning System, a Quasi-Zenith Satellite System (QZSS), a Wireless Fidelity (WiFi) Positioning technology, or the like, or any combination thereof. One or more of the above-described positioning systems may be used interchangeably in this application.

One aspect of the present application relates to a door crash avoidance system. The system can automatically start the detection of the object to be avoided by detecting the driving behavior intention of the person in the vehicle, and limit the opening of the vehicle door when the object to be avoided is detected, so that the potential safety hazard that collision accidents are easily caused by opening the vehicle door is solved, and the use safety of the vehicle is improved.

It is noted that prior to the filing of the present application, some solutions have employed data collected by a sensor mounted to a door handle to determine whether a user has an intention to open the door. Obviously, the probability of the misjudgment is high, and meanwhile, the timeliness of the judgment is poor, and enough time is not provided for detecting whether a quick approach target exists near the vehicle, so that the actual implementation effect is not good. In other arrangements, sound discrimination is used to determine whether there are approaching people around the vehicle. Obviously, the method has a very high misjudgment rate in a noisy environment, and cannot achieve the expected effect. However, the driving door anti-collision method provided by the application not only can accurately detect the intention of a user to drive the vehicle door, but also can accurately judge whether objects which are easy to cause collision exist around the vehicle to approach, so that the collision accident caused by driving the vehicle door can be reliably avoided.

Fig. 1 is a schematic structural diagram of a door-opening collision avoidance system 100 according to an embodiment of the present disclosure. For example, the door drive collision avoidance system 100 may be used with transportation vehicles such as taxis, private cars, shared cars, net appointments, buses, and the like. The door drive collision avoidance system 100 may include a processor, a storage medium, a bus, a door controller, a collection device, and a plurality of microwave sensors.

The Processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.

The storage medium is used for storing programs or data, such as programs corresponding to the door opening anti-collision device. The storage medium may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.

In some embodiments, the processor and the storage medium may be integrated in the same chip, and are conveniently installed in a vehicle, and at the same time, the vehicle door controller, the acquisition device and the microwave sensor communicate with the processor through a bus, so that the processor can execute machine-readable instructions stored in the storage medium and control the vehicle door controller, the acquisition device and the microwave sensor to cooperatively execute the driving door collision avoidance method.

In some embodiments, the processor, the storage medium, the vehicle door controller, the collection device and the plurality of microwave sensors may further communicate with each other through a bus, so that the processor may execute machine-readable instructions stored in the storage medium and control the vehicle door controller, the collection device and the microwave sensors to cooperatively execute the vehicle door driving anti-collision method.

The vehicle door controller is used for controlling the opening and closing state, the opening and closing speed, the maximum included angle between the opened vehicle door and the vehicle body and the like. In some embodiments, the door controller may be electrically connected to the rotating motor and the lock of each door. The rotating motor is used for controlling an opening and closing included angle between the vehicle door and the vehicle body, and the vehicle lock is used for controlling the opening and locking states of the vehicle door.

The collecting device can be a camera and is used for collecting picture information in the vehicle. The above-mentioned acquisition equipment can be one or more, sets up in the carriage to ensure that the space is located in the field of view of acquisition equipment in the vehicle. Further, in some embodiments, doors are included in the field of view of the capture device to confirm the relative positional relationship between the occupant and each door.

In some embodiments, if the field of view of one acquisition device can contain all the spaces where people may be present in the compartment, one acquisition device may be provided, and vice versa. Of course, for vehicles with less doors such as buses and buses but with scattered personnel positions in the carriage, the collecting device can be only arranged near the doors.

For example, two cameras may be installed in a two-compartment car, one for collecting image information of a front row in the car and one for collecting image information of a rear row in the car. The collected image information of the front row in the vehicle may include a front door, and the collected information of the rear row in the vehicle may include a rear door. As another example, the collection device of a bus or a bus is disposed in a waiting get-off area near a door of the vehicle.

In addition, different acquisition devices correspond to different storage sections in the storage medium and are used for storing the image data acquired by the acquisition devices.

The microwave inductor can be arranged outside the vehicle body, has the characteristics of strong radio frequency interference resistance and no influence of temperature, humidity, light, airflow, dust and the like, and can be arranged in non-metal shells of plastic, glass, wood and the like with certain thickness. The microwave sensor operates on the principle of using the doppler effect, in which the wavelength of the reflected wave is constant if the obstacle is stationary, shorter than the wavelength of the wave source if the obstacle moves toward the wave source, and longer than the wavelength of the wave source if the obstacle moves away from the wave source, and a change in wavelength means a change in frequency. Therefore, the microwave sensors can be installed at the corners of the vehicle and hidden in the non-metal structure of the vehicle (such as the vehicle lamp), and the detection area of each microwave sensor is a sector area with the microwave sensor as the vertex and the angle of 120 degrees. The detection distance is between 1 and 50 m. In some embodiments, the microwave sensors are disposed at two ends of a vehicle body side having a door, such as a sedan shown in fig. 2, and a microwave sensor 1 and a microwave sensor 2 are respectively mounted at two ends of a first vehicle body side, the microwave sensor 1 is used for detecting an object approaching the vehicle from a vehicle head direction and going past the first vehicle body side, and the microwave sensor 2 is used for detecting an object approaching the vehicle from a vehicle tail direction and going past the first vehicle body side. A microwave sensor 3 and a microwave sensor 4 are mounted on both ends of the second body side, respectively. The microwave sensor 3 is used to detect an object approaching the vehicle from the vehicle front direction and going to pass by the second vehicle body side, and the microwave sensor 4 is used to detect an object approaching the vehicle from the vehicle rear direction and going to pass by the second vehicle body side. So set up, be convenient for detect more comprehensively from the object that the locomotive direction is close to the vehicle and from the object that the rear of a vehicle direction is close to the vehicle.

Of course, for a vehicle (for example, a bus or a bus) having only one vehicle body side provided with a door, only the microwave inductors need to be arranged at two ends of the vehicle body side.

The door-driving collision avoidance method provided by the embodiment of the present application will be described in detail below with reference to the content described in the door-driving collision avoidance system 100 shown in fig. 1.

Referring to fig. 3, a schematic flow chart of a method for preventing a door from being crashed according to an embodiment of the present disclosure is shown, where the method may be executed by a processor in the door crash prevention system 100, and the specific execution process includes:

and S101, acquiring picture information in the vehicle.

The in-vehicle picture information may be a presentation of a field of view corresponding to a collection device installed in the vehicle compartment. The acquisition equipment is arranged in the carriage, and if the person in the vehicle is positioned in the visual field of the acquisition equipment, the person in the vehicle can appear in the picture information in the vehicle acquired by the acquisition equipment.

And S102, identifying whether the person in the vehicle performs a preselected action or not based on the picture information in the vehicle.

The pre-selected action is an action for representing the intention of a person in the vehicle to drive the vehicle door. For example, a turning motion, a side face motion, a position moving motion, and the like.

The above-mentioned vehicle interior personnel are personnel located in the vehicle compartment, and can be drivers or passengers.

In some embodiments, an image recognition strategy may be utilized to identify whether a person is present in the in-vehicle picture information. If the person exists, whether the action of the person is a preselected action is further identified based on the in-vehicle picture information continuously acquired by the same acquisition equipment.

And step S103, detecting whether an object to be avoided exists in a selected range when the preselected action is identified.

The selected range is a preset interval with the vehicle as the center. For example, the selected range may encompass a range of set distances anteroposterior.

The object to be avoided is an object which is judged in advance that collision is easy to occur when a person in the automobile opens the automobile door, such as an automobile pedestrian, a non-motor vehicle or other vehicles.

In some embodiments, after the preselected action is identified, the microwave sensor is activated within a selected range to detect the presence of an object to be avoided.

And step S104, if the object to be avoided exists, limiting the vehicle door to be opened.

In some embodiments, when the detection result of the microwave sensor shows that the object to be avoided exists, the processor controls the vehicle door controller to prohibit the vehicle door from being opened until the object to be avoided disappears.

That is, the driving door anti-collision method provided by the embodiment of the invention can autonomously start the detection of the object to be avoided by detecting the driving door behavior intention of the person in the vehicle, and prohibit the vehicle door from being opened when the object to be avoided is detected, thereby reducing the collision risk between the opened vehicle door and the external moving object and improving the safety of the vehicle use.

The details of embodiments of the invention are described below:

it can be understood that the judgment of whether the person in the vehicle has the intention of opening the door depends on the collection and analysis of the picture information in the vehicle.

In some embodiments, the step S101 may be to collect the in-vehicle picture information during the whole running process of the vehicle. Under this embodiment, can ensure that all actions of personnel in the car can effectively catch, improve the accuracy of discerning the preselected action.

In other embodiments, the step S101 may also be triggering to start the collection of the in-vehicle picture information under a specific condition. It will be appreciated that an occupant of the vehicle will only make an effective action indicative of the intent to drive the door when it is desired to exit the vehicle. Meanwhile, the collection and analysis of the picture information in the vehicle need to occupy a large amount of system resources. Therefore, under the embodiment, the calculation amount can be effectively reduced, and unnecessary system resource occupation caused by long-time and continuous in-vehicle picture information acquisition and analysis is avoided.

The specific conditions can be set according to the objective condition that the passengers in the vehicle need to get off the vehicle.

In some embodiments, different specific conditions may be set in different scenarios.

For example, for a private car scene, the specific condition may be that the vehicle is detected to be switched from a moving state to a stationary state (the vehicle speed gradually decreases), and the collection of the in-car picture information is started. In addition, the vehicle returns to the normal motion state, and the collection of the picture information in the vehicle is stopped.

For another example, for a network appointment scenario, the specific condition may be to obtain a service order bound to the vehicle and in an executing state. And when the vehicle speed is detected to be less than the preset speed per hour, comparing the current position information with the destination information displayed in the service order. And if the distance between the current position information and the destination information is less than the preset distance, starting the acquisition of the picture information in the vehicle. In addition, after the service order is finished, the vehicle returns to the normal motion state, and the collection of the in-vehicle picture information is stopped. In addition, under the condition that no service order bound with the vehicle and in an execution state exists, the specific condition can also be that the vehicle is detected to be switched from a motion state to a static state, the collection of the in-vehicle picture information is started, the vehicle is recovered to a normal motion state, and the collection of the in-vehicle picture information is stopped.

It should be noted that the current position information may be acquired in real time by using a positioning technology. The service order may be a network appointment service order, which includes information related to a service providing side and a service receiving side (both drivers and conductors), and also includes information of a start position and a destination corresponding to the service.

For another example, for a bus scene, the specific condition may be that when the vehicle speed is detected to be less than the preset speed per hour, the current location information is compared with the stop location information on the operation route. And if the distance between the current position information and the station position information is less than the preset distance, starting the acquisition of the picture information in the vehicle.

In some embodiments, the specific conditions may be set according to objective rules.

For example, the specific condition may be that when the vehicle speed is detected to be less than a preset speed per hour, the distance between the vehicle and the road side is detected, and if the distance is less than a given value, the collection of the in-vehicle picture information is started. It will be appreciated that the manner in which the detection of the distance between the vehicle and the roadside is achieved may be: the camera is arranged on the outer side of the vehicle body and used for collecting image information of the environment where the vehicle is located. When the camera acquires image information containing the curb, the distance between the vehicle and the curb is calculated based on the image.

In some embodiments, the step S102 may be a motion recognition using a deep learning model obtained by a pre-selection training. However, motion recognition is significantly different from conventional image recognition. It will be appreciated that there is consistency in the actions and that the same gesture may exist in different actions. Therefore, the accuracy of identification can be really ensured only by combining multiple frames of in-vehicle picture information.

In some embodiments, the step S102 may be:

firstly, recognizing each frame of in-vehicle picture information in which the in-vehicle person appears by sequentially utilizing a first learning model to determine the posture information of each in-vehicle person in each frame of in-vehicle picture information. It is to be understood that the first learning model is a model trained in advance for recognizing the posture of the person. The posture information may include information on the position, angle, height, etc. of each limb.

Secondly, the acquisition time point of each frame of the in-vehicle picture information is used as a time tag of the corresponding posture information, the posture information corresponding to the personnel in the same vehicle is sorted according to the time tag, the time difference between two adjacent posture information is calculated, the sequence between the posture information of the personnel in the same vehicle and the time difference between the posture information are input into a second learning model, and the action type is output. It is to be understood that the first learning model is a model trained in advance for recognizing correspondence between the gesture order, the gesture time difference, and the motion type.

And finally, judging whether the action type is a preselected action.

In other embodiments, in order to reduce the amount of calculation, step S102 may further be:

firstly, identifying each frame of in-vehicle picture information in which the in-vehicle person appears by using a first learning model so as to determine the posture information of each in-vehicle person in each frame of in-vehicle picture information.

Secondly, when the difference between the posture information corresponding to two adjacent pieces of in-vehicle picture information exceeds a preset value, determining the previous in-vehicle picture information in the two adjacent pieces of in-vehicle picture information as a first image, determining the subsequent in-vehicle picture information in the two adjacent pieces of in-vehicle picture information as a second image, inputting the posture information corresponding to the first image and the second image into a third learning model, and outputting the predicted reference posture after the specified time interval.

It can be understood that the sample data acquisition mode used for training the third learning model is as follows: in a plurality of groups of images showing the preselected action, each group of images are sorted according to the acquisition time, and a first sample image, a second sample image and a third sample image in each group of images are respectively searched according to the sequence from front to back. The acquisition time of the first sample image and the acquisition time of the second sample image are adjacent, and the pose information between the first sample image and the second sample image exceeds a preset value. The first sample image is acquired earlier in time than the second sample image. And the acquisition time of the third sample image is after that of the second sample image, the acquisition time difference between the third sample image and the second sample image is a specified time interval, the corresponding relation between the pose information corresponding to the first sample image and the pose information corresponding to the second sample image is used as sample data, and the pose information corresponding to the third sample image is used as a sample label. Therefore, the third learning model obtained by training the sample data can output the reference posture according to the two input pose information.

And finally, comparing the pose information corresponding to the in-vehicle picture information with the reference pose at the specified time interval after the acquisition time of the second image, if the difference between the two poses does not exceed a preset value, judging that the preselected action is identified, otherwise, judging that the preselected action is not identified. The mode makes full use of the continuity of the motion on the time axis, and saves a large amount of calculated amount while accurately identifying whether the personnel in the vehicle make the preselected motion.

After the situation that the person in the vehicle has the intention of getting off the vehicle is judged, the processor automatically controls the microwave sensor to start to work, and whether an object to be avoided exists or not is detected within a selected range.

For vehicles with doors on both sides, there are situations where a person in the vehicle only opens one door. In view of the above situation, in order to reasonably utilize the microwave sensor, it is avoided that unnecessary microwave sensor activation increases the analysis computation amount. In some embodiments, as shown in fig. 4, the step S103 may include the following sub-steps:

substep S103-1, a target vehicle door to which the preselected action is directed is determined.

The target vehicle door is a vehicle door which is determined according to the pre-selection action and is required to be opened by the vehicle interior personnel. There is usually a correlation between the preselected action made by a person having a need to open a door and the door that he wants to open. For example, when the pre-selection movement is a turning movement, the turning direction corresponding to the turning movement will point to the vehicle door that the vehicle occupant wants to open. For another example, when the preselected action is a side face action, the face of the person in the vehicle faces the door to be opened after the person in the vehicle has made the side face action. For another example, when the pre-selection action is a moving position action, the person in the vehicle approaches the vehicle door to be opened after the moving position action is performed.

The above-described manner of determining the target door is mainly described below by taking the preselected action as the turning action as an example, and the manner of determining the door by taking other actions as the preselected action is relatively simple, for example, the door facing after face turning is the target door, and further, for example, the door closest to the moving distance is the target door.

In some embodiments, as shown in fig. 5, the above sub-step S103-1 may include the following steps:

and a substep S103-1-1, acquiring multiframe in-vehicle picture information for recording the postures of each stage of the turning motion.

In some embodiments, since it is recognized whether the same in-vehicle person performs the turning motion or not can be realized only by matching the pieces of in-vehicle picture information, after the in-vehicle person is recognized to perform the turning motion, the in-vehicle picture information contributing to the recognition of the turning motion is taken as an acquisition object. That is, the in-vehicle picture information recorded with the pose of each phase of the turning motion is taken as an acquisition object.

And a substep S103-1-2, calculating the spacing distance between the person in the vehicle and each vehicle door making the turning motion according to the acquired multi-frame in-vehicle picture information.

In some embodiments, a virtual coordinate system related to the camera coordinate system is first established according to the field of view of the acquisition device, and the position information of each vehicle door under the virtual coordinate system is determined. It is understood that the field of view of the capturing device may be fixed, and therefore, the camera coordinate system may establish a corresponding relationship with the real space, and the camera coordinate system may establish a relationship with the virtual coordinate system, so that the vehicle door position information may be mapped into the virtual coordinate system through the camera coordinate system, thereby obtaining the position information of each vehicle door under the virtual coordinate system.

Then, the position of the person in the vehicle who makes the turn-around motion in the in-vehicle screen information is mapped to the virtual coordinate system.

And finally, calculating the distance between the vehicle interior personnel making the turning motion and each vehicle door according to the position information of each vehicle door in the virtual coordinate system and the position information of the vehicle interior personnel making the turning motion.

And a substep S103-1-3, determining the corresponding door with the minimum spacing distance as the target door.

For example, if the distance a from the front right door, the distance b from the front left door, the distance c from the rear right door, and the distance d from the rear left door are the same, and c is the smallest among a, b, c, and d, then the rear right door is determined as the target door.

In some embodiments, as shown in fig. 6, the sub-step S103-1 may further include the following steps:

and a substep S103-1-4 of obtaining multiframe in-vehicle picture information for recording the postures of the turning motion at each stage.

In some embodiments, the principle of the above substep S103-1-4 can be referred to the substep S103-1-1, and will not be described herein again.

And a substep S103-1-5, obtaining the spacing distance and the turning direction between the vehicle interior personnel making the turning motion and each vehicle door according to the obtained multiframe vehicle interior picture information.

In some embodiments, reference may be made to the substep S103-1-2 for a manner of obtaining the separation distance between the vehicle interior person who makes the turn-around motion and each vehicle door in the substep S103-1-5, which is not described herein again.

In some embodiments, the manner of obtaining the turning direction in the above sub-step S103-1-5 may be:

firstly, dividing acquired multiframe in-vehicle picture information into a plurality of sets, so that the in-vehicle picture information in the same set is continuous in acquisition time and the difference between posture information of different in-vehicle picture information does not exceed a preset value; the difference between the attitude information between the in-vehicle picture information in different sets exceeds a preset value. And secondly, reconstructing the in-vehicle personnel performing turning motions presented in the in-vehicle image information based on the in-vehicle image information in each set respectively to obtain a plurality of reconstruction models and corresponding pose data thereof. And thirdly, sequencing the plurality of reconstruction models according to the sequence of the acquisition time of the in-vehicle picture information used in reconstruction. Then, a specific point cloud region (such as a point cloud region representing the left shoulder of a person) is determined from the reconstruction model arranged at the first position, and then the pose data of the specific point cloud region is tracked on the reconstruction model arranged behind the specific point cloud region. And finally, determining the turning direction by using the pose data change condition of the specific point cloud area on the arranged reconstruction model.

And a substep S103-1-6, obtaining the corresponding vehicle door with the minimum spacing distance as a vehicle door to be selected.

If only one candidate door exists, the candidate door is directly taken as the target door, and the process goes to the substep S103-1-2. If there are more than one candidate doors, then the process proceeds to substeps S103-1-7.

And a substep S103-1-7, taking the vehicle door to be selected pointed by the turning direction as the target vehicle door.

And a substep S103-2, controlling the target sensor to detect whether the object to be avoided exists in the selected range.

The target sensor is a microwave sensor provided on a vehicle body side having a target door. It is understood that when the target vehicle door is located on the same vehicle body side, the microwave sensor disposed on the other side does not work. By only starting the target sensor, the detection pertinence can be achieved, and unnecessary detection result analysis can be avoided. Taking fig. 2 as an example, if the target vehicle door is a vehicle door a, only the microwave sensors 1 and 2 need to be activated to realize the targeted detection, which not only reduces the unnecessary workload, but also avoids the interference of the detection result on the other side.

In addition, the detection zone of microwave inductor is relatively wide among the practical application, promptly, can exist and detect that this object can not collide with the door of opening when an object is close to the vehicle, however, this just can cause and judge the erroneous judgement when whether there is the object of waiting to dodge.

In order to avoid the occurrence of false judgment, in some embodiments, as shown in fig. 7, the sub-step S103-2 may include:

in sub-step S103-2-1, a target object within a selected range and appearing in a detection zone of the target sensor is detected.

In some embodiments, the selected range is an area relative to the vehicle, which is established by centering on the vehicle itself, and the target sensor may detect a position relationship between an object and a person relative to the vehicle, so that it may be determined whether an object appearing in a detection area of the target sensor is within the selected range, and further, whether the target object exists may be determined.

And a substep S103-2-2, if the target object moves towards the wave source of the target sensor, determining that the target object is an object to be avoided.

The above-mentioned wave source movement towards the target sensor may be understood as a decrease in the distance between the target object and the target sensor detecting the target object over time.

And a substep S103-2-3, if the target object moves away from the wave source of the target sensor, judging that the target object is not the object to be avoided.

The above-mentioned distant may be understood as the distance between the target object and the target sensor that detects the target object increases with time.

As can be seen from fig. 2, although microwave sensors are disposed at four corners of a vehicle, a blind area still exists at the tail of the vehicle, and if a pedestrian or a non-motor vehicle in the blind area suddenly flees, a collision may occur while the door is opened.

To ameliorate this problem, in some embodiments, the door drive collision avoidance system further includes a blind zone monitoring unit disposed at the rear of the vehicle, the blind zone monitoring unit also communicating with the processor via the bus. The blind area monitoring unit can also be a camera and has a distance measuring function. Further, as shown in fig. 8, the method further includes:

step S201, if the object to be avoided is not detected, the blind area monitoring unit is started to detect the moving object.

And step S202, when the moving object is not detected, opening the target vehicle door according to a door opening instruction triggered by the vehicle interior personnel. Therefore, the vehicle door can be normally opened by the personnel in the vehicle.

In step S203, when the moving object is detected, a distance value between the moving object and the vehicle tail is obtained.

In some embodiments, the distance value between the vehicle tail and the moving object can be estimated by utilizing the proportion of the moving object in the visual field of the blind area monitoring unit.

And step S204, prompting the personnel in the vehicle to pay attention to the risk of opening the vehicle door when the distance value does not exceed the preset safe distance.

For example, the voice prompt "there is a car behind, please take care when opening the car door".

In some embodiments, on the basis of the door opening collision avoidance method shown in fig. 8, as shown in fig. 9, the door opening collision avoidance method may further include:

and S205, controlling a target sensor arranged near the tail of the vehicle to start monitoring when the distance value does not exceed a preset safe distance and the vehicle interior personnel are detected to trigger the door opening instruction.

After the microwave sensor is installed on the vehicle, the microwave sensor whose installation distance from the vehicle tail is smaller than the preset value can be determined as the microwave sensor arranged near the vehicle tail, and meanwhile, the target sensor arranged near the vehicle tail can be understood as the microwave sensor whose installation distance from the vehicle tail is smaller than the specified value. Thus, after the target sensor is determined, the target sensor disposed adjacent to the tail of the vehicle can be determined accordingly.

The specified value can be determined according to the distribution of the microwave sensors on the vehicle body, and the specified value can ensure that the microwave sensors arranged near the tail exist in the microwave sensors and the microwave sensors not arranged near the tail exist in the microwave sensors. For example, the microwave sensors 2 and 4 in fig. 2 may be defined as those disposed adjacent to the vehicle rear, and the microwave sensors 1 and 3 are not those disposed adjacent to the vehicle rear.

In some implementation classes, in a scene that the distance value does not exceed the preset safe distance and the vehicle interior personnel trigger the door opening instruction, a target sensor arranged near the tail of the vehicle can be utilized to monitor whether the moving object is fleeed out from one side of the door.

And step S206, judging whether the moving object enters the detection area of the target sensor or not according to the monitoring result of the target sensor arranged near the tail of the vehicle and the monitoring result of the blind area monitoring unit.

For example, it is shown from the monitoring result of the target sensor and the monitoring result of the blind area monitoring unit that the originally moving object can only be monitored by the blind area monitoring unit, but if the moving object can be monitored by the target sensor and the blind area monitoring unit at the same time suddenly, it can be determined that the moving object has an attempt to enter the detection area of the target sensor, and it is determined that the moving object has an attempt to enter the detection area of the target sensor, and the process proceeds to step S207.

And step S207, reducing the opening speed of the target vehicle door to a preset safe speed and limiting the maximum opening angle of the target vehicle door to a safe avoidance angle.

And opening the target vehicle door to a safe avoiding angle by slowing on the premise of not receiving the closing of the target vehicle door by the vehicle interior personnel, and stopping. Avoid the door to open the back and collide with the motion object, also can signal the motion object speed reduction that the rear scurried, detour, in addition, observe the road conditions for more time of the interior personnel of opening the door, and then whether the decision temporarily closes the door and waits for better opportunity and open the door.

Based on the same inventive concept, the embodiment of the present application further provides a driving door anti-collision device corresponding to the driving door anti-collision method, and as the principle of solving the problem of the device in the embodiment of the present application is similar to that of the above-mentioned driving door anti-collision method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and repeated details are not repeated.

Referring to fig. 10, a schematic view of a door-opening anti-collision device provided in a fifth embodiment of the present application is shown, where the device includes: the device comprises an acquisition module, an identification module, a detection module and a control module.

And the acquisition module is used for acquiring the picture information in the vehicle.

The identification module is used for identifying whether people in the vehicle make a preselected action or not based on the in-vehicle picture information; wherein the pre-selected action is an action for characterizing the intention of the vehicle occupant to open the door.

The detection module is used for detecting whether an object to be avoided exists in a selected range when the preselected action is identified; wherein the selected range is a preset interval with the vehicle as the center.

And the control module is used for limiting the opening of the vehicle door if the object to be avoided exists.

Optionally, the device is applied to a driving door collision avoidance system, which includes a plurality of microwave sensors disposed at two ends of a vehicle body side having a vehicle door; the detection module further comprises:

the determining submodule is used for determining a target vehicle door pointed by the preselected action;

the control submodule is used for controlling the target sensor to detect whether the object to be avoided exists in the selected range; wherein the target sensor is a microwave sensor provided at the vehicle body side having the target door.

Optionally, the preselected action includes a turn-around action, and the determining sub-module is specifically configured to:

acquiring multiframe in-vehicle picture information for recording the postures of the turning motion at each stage;

calculating the spacing distance between the in-vehicle personnel making the turning motion and each vehicle door according to the acquired multiframe in-vehicle picture information;

and determining the corresponding door with the minimum spacing distance as the target door.

according to the obtained multiframe picture information in the vehicle, obtaining the spacing distance and the turning direction between the personnel in the vehicle making the turning motion and each vehicle door;

acquiring the corresponding vehicle door with the minimum spacing distance to serve as a vehicle door to be selected;

and when a plurality of the candidate vehicle doors exist, taking the candidate vehicle door pointed by the turning direction as the target vehicle door.

Optionally, the preselected action comprises a turn-around action, and the detection module comprises:

the detection submodule is used for detecting a target object which appears in a detection area of the target sensor and is positioned in the selected range;

the judgment sub-module is used for judging that the target object is the object to be avoided if the target object moves towards the wave source of the target inductor;

the judgment sub-module is further configured to judge that the target object is not the object to be avoided if the target object moves away from the wave source of the target sensor.

Optionally, the driving door collision avoidance system further includes a blind area monitoring unit disposed at the rear of the vehicle, and the device further includes:

the detection module is further configured to start the blind area monitoring unit to detect a moving object if the object to be avoided is not detected;

the control module is further used for opening the target vehicle door according to a door opening instruction triggered by the vehicle interior personnel when the moving object is not detected;

the acquisition module is used for acquiring a distance value between the moving object and the tail of the vehicle when the moving object is detected;

and the prompting module is used for prompting the personnel in the vehicle to pay attention to the risk of opening the vehicle door when the distance value is not more than the preset safe distance.

Optionally, the apparatus further comprises:

the detection module is further used for controlling the target sensor arranged adjacent to the tail of the vehicle to start monitoring when the distance value does not exceed a preset safe distance and the door opening instruction is detected to be triggered by the person in the vehicle;

the judging module is used for judging whether the moving object enters a detection area of the target sensor or not according to a monitoring result of the target sensor arranged near the tail of the vehicle and a monitoring result of the blind area monitoring unit;

the control module is used for reducing the opening speed of the target vehicle door to a preset safe speed and limiting the maximum opening angle of the target vehicle door to a safe avoiding angle when the moving object is judged to enter the detection area of the target sensor.

Optionally, the acquisition module is specifically configured to: and when the vehicle is switched from a moving state to a static state, starting the collection of the picture information in the vehicle.

Optionally, the acquisition module is specifically configured to: acquiring a service order which is bound with a vehicle and is in an execution state; wherein the service order includes destination information;

when the vehicle speed is detected to be less than the preset speed per hour, comparing the current position information with the destination information;

and if the distance between the current position information and the destination information is smaller than a preset distance, starting the collection of the picture information in the vehicle.

The embodiment of the application also provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the driving door anti-collision method are executed.

Specifically, the storage medium can be a general-purpose storage medium, such as a removable disk, a hard disk, or the like, and when executed, the computer program on the storage medium can execute the above-mentioned door-opening collision avoidance method.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, in order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, functional units in various embodiments of the present application may be integrated into one body, and the technical solution in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.

Claims

1. The driving door anti-collision method is applied to a driving door anti-collision system, the driving door anti-collision system comprises a processor, a storage medium, a bus, a vehicle door controller, a collection device and a plurality of microwave inductors, the microwave inductors are arranged at two ends of a vehicle body side with a vehicle door, and the driving door anti-collision method comprises the following steps:

the collecting equipment collects picture information in the vehicle;

the processor identifies whether people in the vehicle make a preselected action or not based on the in-vehicle picture information; wherein the pre-selected action is an action for representing the intention of the person in the vehicle to drive the vehicle door;

when the processor identifies the preselected action, determining a target vehicle door pointed by the preselected action within a selected range;

the processor controls the target sensor to detect whether an object to be avoided exists in the selected range; the target sensor is a microwave sensor arranged on the side of the vehicle body with the target vehicle door, and the selected range is a preset interval with the vehicle as the center;

and if the object to be avoided exists, the processor controls the vehicle door controller to limit the vehicle door to be opened.

2. The method of claim 1, wherein the preselected action comprises a turn-around action, and the step of determining a target vehicle door to which the preselected action is directed comprises:

3. The method of claim 1, wherein the preselected action comprises a turn-around action, and the step of determining a target vehicle door to which the preselected action is directed further comprises:

4. The method of claim 1, wherein the step of controlling the target sensor to detect the presence of the object to be avoided within the selected range comprises:

detecting a target object which is present in a detection area of the target sensor and is located in the selected range;

if the target object moves towards the wave source of the target inductor, determining that the target object is the object to be avoided;

and if the target object moves away from the wave source of the target inductor, judging that the target object is not the object to be avoided.

5. The method of claim 1, wherein the door opening collision avoidance system further comprises a blind zone monitoring unit disposed at a rear of the vehicle, the method further comprising:

if the object to be avoided is not detected, starting the blind area monitoring unit to detect the moving object;

when the moving object is not detected, opening the target vehicle door according to a door opening instruction triggered by the vehicle interior personnel;

when the moving object is detected, acquiring a distance value between the moving object and the tail of the vehicle;

and prompting the personnel in the vehicle to pay attention to the risk of opening the vehicle door when the distance value does not exceed a preset safe distance.

6. The method of claim 5, further comprising:

when the distance value does not exceed a preset safety distance and the door opening instruction is detected to be triggered by the person in the vehicle, controlling the target sensor arranged adjacent to the tail of the vehicle to start monitoring;

judging whether the moving object enters a detection area of the target sensor or not according to a monitoring result of the target sensor arranged near the tail of the vehicle and a monitoring result of the blind area monitoring unit;

if so, reducing the opening speed of the target vehicle door to a preset safe speed and limiting the maximum opening angle of the target vehicle door to a safe avoidance angle.

7. The method of claim 1, wherein the step of collecting in-vehicle picture information comprises:

and when the vehicle is switched from a moving state to a static state, starting the collection of the picture information in the vehicle.

8. The method of claim 1, wherein the step of collecting in-vehicle picture information comprises:

acquiring a service order which is bound with a vehicle and is in an execution state; wherein the service order includes destination information;

9. The utility model provides a driving door buffer stop, its characterized in that, the device is applied to driving door collision avoidance system, driving door collision avoidance system includes treater, storage medium, bus, door controller, collection equipment and a plurality of microwave inductor, the microwave inductor sets up in the both ends that have the automobile body side of door, driving door buffer stop includes:

the acquisition module is used for acquiring the picture information in the vehicle through the acquisition equipment;

the recognition module is used for recognizing whether people in the vehicle make a preselected action or not based on the in-vehicle picture information through the processor; wherein the pre-selected action is an action for representing the intention of the person in the vehicle to drive the vehicle door;

the detection module is used for determining a target vehicle door pointed by the preselected action within a selected range when the preselected action is recognized by the processor;

the detection module is also used for controlling the target sensor to detect whether an object to be avoided exists in the selected range through the processor; the target sensor is a microwave sensor arranged on the side of the vehicle body with the target vehicle door, and the selected range is a preset interval with the vehicle as the center;

and the control module is used for controlling the vehicle door controller to limit the vehicle door to be opened through the processor if the object to be avoided exists.

10. The apparatus of claim 9, wherein the preselected action comprises a turn-around action, the determination submodule being configured to:

11. The apparatus of claim 9, wherein the preselected action comprises a turn-around action, the determination submodule being configured to:

12. The apparatus of claim 9, wherein the preselected action comprises a turn-around action, and wherein the detection module comprises:

13. The apparatus of claim 9, wherein the door opening collision avoidance system further comprises a blind zone monitoring unit disposed at a rear of the vehicle, the apparatus further comprising:

14. The apparatus of claim 13, further comprising:

15. The apparatus of claim 9, wherein the acquisition module is specifically configured to: and when the vehicle is switched from a moving state to a static state, starting the collection of the picture information in the vehicle.

16. The apparatus of claim 9, wherein the acquisition module is specifically configured to: acquiring a service order which is bound with a vehicle and is in an execution state; wherein the service order includes destination information;

17. An opening door collision avoidance system, comprising: the system comprises a processor, a storage medium, a bus, a vehicle door controller, a collecting device and a microwave sensor, wherein the storage medium stores machine readable instructions executable by the processor, when the vehicle door collision avoidance system is operated, the processor and the storage medium are communicated through the bus, and the processor executes the machine readable instructions to control the vehicle door controller, the collecting device and the microwave sensor to cooperatively execute the steps of the method according to any one of claims 1 to 8.

18. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, is adapted to carry out the steps of the method according to any one of claims 1 to 8.