CN116691502B

CN116691502B - Safety detection method and device for vehicle environment, electronic equipment and storage medium

Info

Publication number: CN116691502B
Application number: CN202310960156.3A
Authority: CN
Inventors: 徐放
Original assignee: Beijing Xinchi Semiconductor Technology Co ltd
Current assignee: Beijing Xinchi Semiconductor Technology Co ltd
Priority date: 2023-08-01
Filing date: 2023-08-01
Publication date: 2023-11-10
Anticipated expiration: 2043-08-01
Also published as: CN116691502A

Abstract

The disclosure provides a safety detection method and device for a vehicle environment, electronic equipment and a storage medium, and relates to the technical field of safe driving. The method comprises the following steps: the first processor core triggers the image acquisition device to acquire images to obtain first image data; transmitting a start instruction to the second processor core through an inter-core communication mechanism; before the operating system corresponding to the second processor core is not completely started, determining whether to send alarm information according to the first image data; the first processor core and the second processor core belong to the same multi-core heterogeneous chip; the alarm information is used for indicating that the environment where the electronic equipment applying the multi-core heterogeneous chip is located has risks; the resource release request characterizes a full boot of the operating system. Therefore, before the operating system is completely started, the first processor core triggers the image collector to collect images and detect the images, so that the collected images and the risk detection time are advanced; the problem that the image cannot be acquired in time and the risk is detected after the electronic equipment is started is solved.

Description

Safety detection method and device for vehicle environment, electronic equipment and storage medium

Technical Field

The disclosure relates to the technical field of safe driving, and in particular relates to a method and device for detecting safety of a vehicle environment, electronic equipment and a storage medium.

Background

For the environmental safety when the vehicle is started, theoretically, a driver turns around the vehicle before the vehicle is started, and whether the surrounding environment of the vehicle has a problem or not is confirmed to restart the vehicle, for example, whether an animal or a child exists behind the vehicle or in the blind area of the driver or not is confirmed, so that damage to the animal or the child is avoided. However, even if the safety of the surrounding environment of the vehicle is confirmed in advance, if a person suddenly rushes out after the vehicle is started, a safety problem may be caused.

With the continuous development of technology, safety mechanisms in various scenes of vehicle driving are gradually perfected. In order to facilitate the driver to immediately know whether the surrounding environment of the vehicle is safe or not when the vehicle is started, a scheme for detecting whether the surrounding environment of the vehicle is safe or not is provided in the related art, after the driver starts the vehicle, a vehicle driving control system and a vehicle-mounted android system are started, the starting process of the vehicle-mounted android system generally needs at least 10 seconds(s) or longer, the starting speed is slower than that of the vehicle driving control system, the driver can control the vehicle to run after the vehicle driving control system is started, and at the moment, if the vehicle-mounted android system is not started, a camera cannot be started for image acquisition and display; safety issues may also occur during this time for the vehicle driving field.

Disclosure of Invention

The present disclosure provides a method, an apparatus, an electronic device, and a storage medium for detecting safety of a vehicle environment, so as to at least solve the above technical problems in the prior art.

In a first aspect, an embodiment of the present disclosure provides a method for detecting safety of a vehicle environment, the method including:

the first processor core triggers the image acquisition device to acquire images to obtain first image data;

the first processor core sends a starting instruction to the second processor core through an inter-core communication mechanism; the starting instruction is used for indicating the second processor core to start an operating system corresponding to the second processor core, and the first processor core and the second processor core belong to the same multi-core heterogeneous chip;

before the operating system is not completely started, the first processor core determines whether to send alarm information according to the first image data; the alarm information is used for indicating that the environment where the electronic equipment applying the multi-core heterogeneous chip is located is at risk;

until the first processor core receives a resource release request sent by the second processor core through an inter-core communication mechanism, the first processor core releases the image collector resource; the resource release request characterizes the operating system to be fully booted.

In the above scheme, the determining whether to send the alarm information according to the first image data includes:

determining whether the first image data meets a safety precaution condition;

if the first image data meets the safety precaution condition, the first processor core sends alarm information and stores the first image data;

and if the first image data does not meet the safety precaution condition, the first processor core stores the first image data.

In the above scheme, the determining whether the first image data meets a safety precaution condition includes:

processing the first image data by using an image recognition model to obtain a processing result of the image recognition model; the processing result comprises at least one of the following:

whether the safety early warning condition is met;

whether a target object exists in the first image data;

the type of the target object;

image data marked with the target object;

the location of the target object relative to the electronic device.

In the above aspect, the first image data includes: at least two areas of image data and the corresponding identification of the image data of each area;

the method further comprises the steps of:

determining an identifier corresponding to the image data of each region in the image data of the at least two regions; the identifier is used for representing the position of the area relative to the electronic equipment and/or an image collector identifier corresponding to the image data of the area;

Determining the adjacent relation of any two image data in the image data of at least two areas according to the identification corresponding to the image data of each area;

combining the image data of the at least two areas according to the adjacent relation to obtain combined image data;

and displaying the combined image data.

In the above scheme, the method further comprises:

determining the image data of a first area meeting the safety early warning condition in the image data of the at least two areas and the identification corresponding to the image data of the first area;

determining the azimuth of the first area relative to the electronic equipment according to the identification corresponding to the image data of the first area;

displaying the image data of the first region and the orientation of the first region relative to the electronic device.

In the above aspect, after the first processor core releases the image collector resource, the method further includes:

triggering the image collector to collect images to obtain second image data;

and determining whether to send alarm information according to the second image data, and/or storing the second image data.

In the above scheme, the method further comprises:

Determining third image data before the electronic device is shut down;

and after the electronic equipment is restarted, determining whether to send alarm information according to the third image data, and/or determining whether to send alarm information according to the third image data and fourth image data acquired after the electronic equipment is restarted.

In the above aspect, the method further comprises at least one of:

if the first processor core sends an alarm message, the first processor core releases resources for sending the alarm message based on the resource release request;

after the first processor core releases the image collector resources, the first processor core sends third prompt information to the second processor core through an inter-core communication mechanism, and the third prompt information characterizes that the image collector resources are released.

In the above solution, the determining, by the first processor core, whether to send the alarm information according to the first image data includes:

the first processor core sending first image data to a detector; the detector is a device used for detecting image data in the multi-core heterogeneous chip;

the detector determines whether the first image data meets a safety precaution condition based on the first image data, and sends a detection result to the first processor core; the detection result represents whether the first image data meets a safety early warning condition or not;

And the first processor core determines whether to send alarm information according to the detection result.

In a second aspect, an embodiment of the present disclosure provides a safety detection apparatus for a vehicle environment, including: the multi-core heterogeneous chip comprises a first processor core and a second processor core; the first processor core includes a first processing module; wherein,

the first processing module is used for triggering the image acquisition device to acquire images so as to obtain first image data; transmitting a start instruction to the second processor core through an inter-core communication mechanism; the starting instruction is used for indicating the second processor core to start an operating system corresponding to the second processor core;

the first processing module is further configured to determine, according to the first image data, whether to send alarm information before the operating system is not completely started; the alarm information is used for indicating that the environment where the electronic equipment applying the multi-core heterogeneous chip is located is at risk;

the first processing module is further configured to release the image collector resource until the first processor core receives a resource release request sent by the second processor core through an inter-core communication mechanism; the resource release request characterizes the operating system to be fully booted.

In the above scheme, the first processing module is configured to determine whether the first image data meets a safety pre-warning condition;

if the first image data meets the safety early warning condition, sending warning information and storing the first image data;

and if the first image data does not meet the safety precaution condition, storing the first image data.

In the above scheme, the first processing module is specifically configured to process the first image data by using an image recognition model, so as to obtain a processing result of the image recognition model; the processing result comprises at least one of the following:

whether the safety early warning condition is met;

whether a target object exists in the first image data;

the type of the target object;

image data marked with the target object;

the location of the target object relative to the electronic device.

the apparatus further comprises a second processing module for:

and displaying the combined image data.

In the above solution, the apparatus further includes a third processing module, configured to:

In the above scheme, the device further includes a fourth processing module, configured to trigger the image collector to perform image collection after the first processor core releases the image collector resource, so as to obtain second image data;

In the above scheme, the device further comprises a fifth processing module, configured to determine third image data before the electronic device is stopped and flameout;

the device further comprises a sixth processing module, which is used for determining whether to send the alarm information according to the third image data after the electronic equipment is restarted, and/or determining whether to send the alarm information according to the third image data and fourth image data acquired after the electronic equipment is restarted.

In the above solution, if the first processor core sends an alarm message, the first processing module is further configured to release a resource for sending the alarm message based on the resource release request;

after the first processor core releases the image collector resources, the first processing module is further configured to send third hint information to the second processor core through an inter-core communication mechanism, where the third hint information characterizes that the image collector resources have been released.

In the above aspect, the device further includes a detector; the detector is a device used for detecting image data in the multi-core heterogeneous chip;

the first processing module is used for sending the first image data to the detector;

The detector is used for determining whether the first image data meets a safety early warning condition or not based on the first image data and sending a detection result to the first processing module; the detection result represents whether the first image data meets a safety early warning condition or not;

the first processing module is further configured to determine whether to send alarm information according to the detection result.

In a third aspect, an embodiment of the present disclosure provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of detecting the safety of a vehicle environment of any one of the above.

In a fourth aspect, embodiments of the present disclosure provide a component on a traffic device, the component comprising a chip capable of performing the method of detecting safety of a vehicle environment as described in any one of the above.

In a fifth aspect, embodiments of the present disclosure provide a traffic device including a chip capable of performing the method of detecting safety of a vehicle environment described in any one of the above.

In a sixth aspect, the presently disclosed embodiments provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a safety detection method of a vehicle environment according to any one of the above.

The embodiment of the disclosure provides a method, a device, electronic equipment and a storage medium for detecting safety of a vehicle environment, wherein the method comprises the following steps: the first processor core triggers the image acquisition device to acquire images to obtain first image data; the first processor core sends a starting instruction to the second processor core through an inter-core communication mechanism; the starting instruction is used for indicating the second processor core to start an operating system corresponding to the second processor core, and the first processor core and the second processor core belong to the same multi-core heterogeneous chip; before the operating system is not completely started, the first processor core determines whether to send alarm information according to the first image data; the alarm information is used for indicating that the environment where the electronic equipment applying the multi-core heterogeneous chip is located has risks; until the first processor core receives a resource release request sent by the second processor core through an inter-core communication mechanism, the first processor core releases the image collector resource; the resource release request characterizes a full boot of the operating system. Therefore, before the operating system corresponding to the second processor core is completely started, the first processor core triggers the image collector to collect images and detect the images, so that the time for collecting the images and detecting the environment of the electronic equipment is advanced, and the safety of the environment of the electronic equipment is further ensured.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

Fig. 1 is a schematic implementation flow diagram of a method for detecting safety of a vehicle environment according to an embodiment of the disclosure;

fig. 2 illustrates a second implementation flow diagram of a method for detecting safety of a vehicle environment according to an embodiment of the disclosure;

fig. 3 illustrates a third implementation flow diagram of a method for detecting safety of a vehicle environment according to an embodiment of the disclosure;

FIG. 4 is a schematic diagram of a safety detection device for a vehicle environment according to an embodiment of the present disclosure;

fig. 5 shows a schematic structural diagram of an electronic device according to an embodiment of the disclosure.

Detailed Description

In order to make the objects, features and advantages of the present disclosure more comprehensible, the technical solutions in the embodiments of the present disclosure will be clearly described in conjunction with the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, but not all embodiments. Based on the embodiments in this disclosure, all other embodiments that a person skilled in the art would obtain without making any inventive effort are within the scope of protection of this disclosure.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.

In the following description, the terms "first", "second", and the like are merely used to distinguish between similar objects and do not represent a particular ordering of the objects, it being understood that the "first", "second", or the like may be interchanged with one another, if permitted, to enable embodiments of the disclosure described herein to be implemented in an order other than that illustrated or described herein.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The terminology used in the present disclosure is for the purpose of describing embodiments of the present disclosure only and is not intended to be limiting of the present disclosure.

It should be understood that, in various embodiments of the present disclosure, the size of the sequence number of each implementation process does not mean that the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

Before explaining the embodiments of the present disclosure in further detail, terms and terminology involved in the embodiments of the present disclosure are explained, and the terms and terminology involved in the embodiments of the present disclosure are applicable to the following explanation.

Fig. 1 is a schematic implementation flow diagram of a method for detecting safety of a vehicle environment according to an embodiment of the disclosure; as shown in fig. 1, the method includes:

step 101, triggering an image acquisition device by a first processor core to acquire an image to obtain first image data;

wherein the first image data may include: image data of a single sheet;

the first image data may further include: video image data, the video image data comprising: and (3) multi-frame image data.

Step 102, a first processor core sends a starting instruction to a second processor core through an inter-core communication mechanism;

the starting instruction is used for indicating the second processor core to start an operating system corresponding to the second processor core; the first processor core and the second processor core belong to the same multi-core heterogeneous chip.

Step 103, before the operating system is not completely started, the first processor core determines whether to send alarm information according to the first image data;

The alarm information is used for indicating that the environment where the electronic equipment applying the multi-core heterogeneous chip is located is at risk;

104, until the first processor core receives a resource release request sent by the second processor core through an inter-core communication mechanism, the first processor core releases the image collector resource;

wherein the resource release request characterizes the operating system to be fully started.

Specifically, the resource release request may or may not include information about completion of starting the operating system, that is, the information may be sent out, which itself represents completion of starting the operating system, where the operating system is complete, and represents that the operating system has a capability of taking over the image collector and is capable of processing image information collected by the image collector, that is, an application program, a process or a thread of image collection and image processing is started, or operates normally.

In an embodiment of the disclosure, the electronic device may be a vehicle, and the risk of the environment where the electronic device is located may specifically refer to that there are animals, children, obstacles, etc. that may cause a danger around the location where the vehicle is started or near the vehicle.

The safety detection method for the vehicle environment, provided by the embodiment of the disclosure, can be used for detecting the safety of the environment around the position where the vehicle is started, in particular to the blind area range of a driver and the like; by detecting whether animals, obstacles, children and the like exist around the vehicle and giving corresponding warning information, damage caused in the starting process of the vehicle is avoided.

The method provided by the embodiment of the disclosure can be applied to a multi-core heterogeneous System on Chip (SoC) of a vehicle.

The system-in-chip may be a semiconductor device packaged together and may include a single wafer (Die), or may include multiple wafers, which may be the same or different, and may include chips designed and fabricated by chip-on-chip (chip) technology.

The multi-core heterogeneous chip may also be referred to as a heterogeneous multi-core chip, and includes a plurality of computing cores therein, where the computing cores include at least two architectures. The multi-core heterogeneous chip can be configured into a plurality of mutually isolated domains, each domain is a hardware set comprising at least one computing core and other hardware resources, the computing cores are divided into large cores and small cores, the hardware set where the large cores are positioned is suitable for a large-scale operating system which has strong running performance and needs great computation force, and the large-scale operating system is suitable for processing various tasks with complex logic; the hardware set where the corelet is located is suitable for a safer minioperating system with low running performance, and information is transmitted between different hardware sets through inter-core communication channels.

The hardware set may be understood as a set of hardware sets formed by a central processor or a central processor cluster, an interrupt controller, a clock controller, and other hardware resources in the multi-core heterogeneous chip, and a memory space, where each set of hardware sets can be configured to independently support the operation of an operating system.

The multi-core heterogeneous chip system-on-chip is simply referred to as a multi-core heterogeneous chip in the present disclosure, and it should be understood that the multi-core heterogeneous chip in the present disclosure specifically refers to a multi-core heterogeneous chip system-on-chip or a heterogeneous multi-core chip system-on-chip, including the features of the multi-core heterogeneous chip and the system-on-chip described above.

In the embodiment of the disclosure, the time consumed for triggering the image collector to collect the image and triggering the second processor core to start may be in millisecond level; the execution order of the steps 101 and 102 may be arbitrary as allowed. In an example, the first processor core may trigger the image collector to collect an image, and then send a start instruction to the second processor core through the inter-core communication mechanism; in another example, the first processor core may send a start instruction to the second processor core through an inter-core communication mechanism, and then trigger the image collector to collect an image; in yet another example, the first processor core may send a startup instruction to the second processor core through an inter-core communication mechanism while triggering the image acquisition by the image acquisition device. In practical application, the design of the execution sequence of the steps 101 and 102 may be any one of the above, or may be designed by a developer according to a specific scene or selected by a user based on own needs.

In an embodiment of the disclosure, the multi-core heterogeneous chip at least includes the first processor core and the second processor core. The first processor core and the second processor core are two processor cores with different architectures.

The first processor core may be a small core, and the first processor core has the characteristics of high starting speed and the like. The first processor core may not run an operating system, but may also run some small operating systems, such as an RTOS system. It should be noted that, since the first processor core may not run an operating system or run some small operating systems, the first processor core has a characteristic of fast start-up speed.

The second processor core may be a large core, and the second processor core has features of being suitable for a large operating system with strong running performance and strong computing power. The second processor core may run some large operating systems, such as Linux systems, android systems.

Here, the first processor core may be started at a higher speed than the second processor core.

In some embodiments, the first processor core and the second processor core communicate with each other through an inter-core communication mechanism. Because of the information communication requirements among different hardware domains, the communication mode is called inter-core communication, and has more advantages compared with the communication between chips, such as no need of transmitting signals to the outside of the chip, and the safety and the speed are greatly improved. Inter-core communication takes many forms, such as Mailbox mechanisms, which are suitable for transmitting instructions, and shared memory mechanisms, which are suitable for sharing data. I.e. the first processor core and the second processor core may communicate based on a Mailbox mechanism inside the multi-core heterogeneous chip.

Mailboxes are a mechanism or data structure for communication between different processor cores. It may be used to communicate messages and trigger events between different processors, cores or hardware modules.

Mailbox can be seen as a shared, bi-directional communication interface that contains one or more registers for storing messages or control information. The sender can write the messages into the register of the Mailbox, and the receiver can read the messages and perform corresponding processing, i.e. the sender can achieve the purpose of controlling the receiver or instructing the receiver to perform corresponding operations by writing the messages or control information into the register of the Mailbox.

In semiconductor chips, mailboxes are typically used for communication between processors, for example between a multi-core processor, a system-on-a-chip or a plurality of separate functional modules. Through the Mailbox mechanism, different processing units can cooperatively work, share data, synchronously operate and trigger events, thereby realizing more efficient system cooperation and resource sharing.

It is noted that the implementation of the Mailbox may vary depending on the chip architecture, communication protocol or design requirements, but in general it is present for achieving reliable, efficient communication and data exchange between the processing units.

In some embodiments, the image collector may be a camera, a pan-around camera, an infrared camera, or the like, for collecting image data of surrounding objects.

The number of the image collectors can be one or more, and the plurality refers to two or more. For example, the image collectors are cameras, the number of the cameras is four, and image data in four directions of front, rear, left and right of the vehicle are respectively collected.

In some embodiments, determining whether to transmit alert information based on the first image data includes:

determining whether the first image data meets a safety precaution condition;

Here, the alarm information may include, but is not limited to, any one of the following:

an alarm sound;

an alert image or alert icon;

alarm indicator light.

The alarm sound can be played through a buzzer; the alarm image or the alarm icon can be presented through any display screen (such as a central control screen, a vehicle-mounted display screen and the like) of the electronic equipment; the alarm indicator light may be presented by a double flashing module, a relay, etc.

It should be noted that, the multi-core heterogeneous chip may be connected to a buzzer, a display screen, a dual flash module, a relay, etc. so as to send corresponding content to any one of the buzzer, the display screen, the dual flash module, and the relay.

Here, if the number of the image collectors is plural, the first image data includes image data respectively collected by each of the image collectors. Each of the image data may include a single piece of image data, and may further include video image data including: multi-frame image data; that is, each image data may include one or more frames of images.

Correspondingly, storing the first image data includes: and storing the image data acquired by each camera corresponding to the identification of the camera. Therefore, when the image data are called, the camera is directly known to acquire each image data, and then according to the deployment position of the camera on the vehicle, the area or direction of the vehicle can be known to reflect the image data.

In some embodiments, the determining whether the first image data satisfies a security pre-warning condition includes:

Whether the safety early warning condition is met;

whether a target object exists in the first image data;

the type of the target object;

image data marked with the target object;

the location of the target object relative to the electronic device.

Here, the image recognition model may include at least one of:

a model for determining whether the first image data satisfies a safety precaution condition;

a model for determining whether there is a target object in the first image data;

a model for determining a type of the target object;

a model for marking and outputting a target object in the first image data;

a model for determining a position of a target object relative to the electronic device.

Wherein the target object may be an object, an animal, a human, etc. The electronic device may be a vehicle or the like.

For example, the processing results include at least one of:

the first image data meets the safety precaution condition;

the first image data has a target object, such as an animal;

the type of the target object is an animal;

image data labeled with the target object, such as image data of a delineating or labeling animal;

the position of the target object relative to the electronic device, such as on the left side of the electronic device, on the right side of the electronic device by 1 meter, etc.

Any model can be an existing model, or can be obtained by training a developer through a training sample set and a neural network, and the mode of obtaining the model is not limited.

In an example, a first training sample set may be obtained in advance, where the first training sample set includes a plurality of training samples and a label corresponding to each training sample, where the training samples are images, and the labels are those that meet or do not meet a safety pre-warning condition; and training a preset neural network by using the first training sample set to obtain a trained neural network as a model for determining whether the first image data meets the safety early warning condition.

In another example, a second training sample set may be obtained in advance, where the second training sample set includes a plurality of training samples and a label corresponding to each training sample, and the training samples are images, and the labels are types of target objects; and training a preset neural network by using the second training sample set to obtain a trained neural network as a model for determining the type of the target object.

Of course, the above training process is merely provided as an example, and other manners of actually obtaining the model may be employed. It can be appreciated that the image recognition model may further include other models, and the image recognition model may be adjusted based on actual requirements, which is not limited herein by the model and the method used to obtain the model.

In some embodiments, the first image data comprises: at least two areas of image data and the corresponding identification of the image data of each area;

the method further comprises the steps of:

and displaying the combined image data.

Specifically, the image data of the at least two regions may refer to image data within regions of two or more directions of the vehicle.

The identification of the image data for each region may be used to characterize the orientation of the region relative to the electronic device, e.g., left, right, front, back, etc.;

the identifier corresponding to the image data of each region may be used to represent the identifier of the image collector corresponding to the image data of the region, for example, the first camera, the second camera, the third camera, the fourth camera, etc., and the region corresponding to each camera may be determined in advance.

For example, the image collector is a camera, and the number of cameras is four; the first image data may include:

the image data collected by the first camera can specifically comprise multi-frame images; the first camera can be used for collecting image data of the left side of the vehicle; that is, the first image data may include: image data of the left area;

the image data collected by the second camera can specifically comprise multi-frame images; the second camera can be used for collecting image data of the right side of the vehicle; that is, the first image data may include: image data of the right area;

the image data collected by the third camera can specifically comprise multi-frame images; the third camera can be used for collecting image data of the front side of the vehicle; that is, the first image data may include: image data of the front side area;

the image data collected by the fourth camera can specifically comprise multi-frame images; the fourth camera can be used for collecting image data of the rear side of the vehicle; that is, the first image data may include: image data of the rear side area.

In practical application, according to the identification corresponding to the image data of each region, the adjacent relation of any two image data in the image data of at least two regions can be determined. For example, there are four cameras, an image on the front side is adjacent to an image on the left side, an image on the left side is adjacent to an image on the rear side, an image on the rear side is adjacent to an image on the right side, and an image on the right side is adjacent to an image on the front side. It should be noted that the above description is only an example, and the actual application may be represented by other characters, such as A, B, C, D, etc., and the corresponding areas of A, B, C, D, etc. are preset; the description is not intended to be limiting.

After determining the adjacent relation of any two image data in the image data of at least two areas, the image data of at least two areas can be combined according to the adjacent relation to obtain combined image data, and the combined image data is displayed. If the number of the image collectors is enough to acquire the image data around the vehicle, the combined image data can be 360-degree looking-around image data, namely, the environment around the vehicle is presented.

Specifically, in an example, an identification corresponding to image data of each of the at least two regions may be determined by the first processor core; determining the adjacent relation of any two image data in the image data of at least two areas according to the identification corresponding to the image data of each area; combining the image data of the at least two areas according to the adjacent relation to obtain combined image data; and then sending the combined image data to a display screen for display.

In another example, the first image data may be sent by the first processor core to one image processor, and the image processor determines an identification corresponding to the image data of each of the at least two regions of image data; determining the adjacent relation of any two image data in the image data of at least two areas according to the identification corresponding to the image data of each area; combining the image data of the at least two areas according to the adjacent relation to obtain combined image data; and then the combined image data is sent to a first processor core, and the first processor core sends the combined image data to a display screen for display.

the method may further comprise:

processing the first image data by using an image merging model to obtain merged image data;

and displaying the combined image data.

Here, the image merging model is used to merge image data of at least two areas. The rule of merging can be determined based on actual requirements, for example, merging 360-degree looking around images, merging images of any two adjacent regions, and the like. The image merging model can be an existing model or can be obtained by training a neural network in advance, and the mode of obtaining the image merging model is not limited.

In some embodiments, the method further comprises:

Here, the image data of the at least two regions may refer to image data in regions of two or more directions of the vehicle.

In order to more accurately identify which region may have risks, that is, determine which region of image data satisfies a security early warning condition, the multi-core heterogeneous chip may use an image recognition model to process the image data of each region in the first image data, so as to obtain a processing result corresponding to the image data of each region, that is, determine whether each region satisfies the security early warning condition, whether the image data of each region has a target object, a type of the target object, image data marked with the target object, a position of the target object relative to the electronic device, and the like;

and then, determining the image data of the area (such as the first area) meeting the safety precaution condition and the identification corresponding to the image data of the first area in the image data of the at least two areas according to the processing result. And determining the azimuth of the first area relative to the electronic equipment according to the determined identification corresponding to the image data of the first area with the risk.

Finally, the image data of the first area with risk and the azimuth of the first area relative to the electronic equipment can be accurately displayed, so that a driver can know the risk existing in the current driving environment more quickly and check the risk, and user experience is improved.

Specifically, in an example, the first processor core may determine, from among the image data of the at least two areas, the image data of the first area satisfying the safety precaution condition and the identification corresponding to the image data of the first area; determining the azimuth of the first area relative to the electronic equipment according to the identification corresponding to the image data of the first area; and displaying the image data of the first area and the orientation of the first area relative to the electronic equipment through a display screen.

In another example, the first processor core may send the first image data to an image processor, and the image processor determines, from among the image data of the at least two areas, the image data of the first area satisfying the safety precaution condition and the identification corresponding to the image data of the first area; determining the azimuth of the first area relative to the electronic equipment according to the identification corresponding to the image data of the first area; and then sending the determined result to a first processor core, and sending the image data of the first area and the azimuth of the first area relative to the electronic equipment to a display screen for display by the first processor core.

In yet another example, the first image data may be invoked and processed by the second processor core upon full startup.

It is to be appreciated that the above operations may be performed by any IP core (e.g., the first processor core, the second processor core, the image processor, etc. described above) or multiple IP cores in a multi-core heterogeneous chip in conjunction, and the specific execution body is not limited herein.

In some embodiments, after the first processor core releases the image collector resources, the method further comprises:

triggering the image collector to collect images to obtain second image data;

Specifically, after the operating system of the second processor core is completely started, the second processor core sends a resource release request to the first processor core through an inter-core communication mechanism, and the first processor core releases the image collector resource according to the resource release request.

After the first processor core releases the image collector resources, the multi-core heterogeneous chip can trigger the image collector again to collect images so as to obtain second image data; and determining whether to send alarm information according to the second image data, and/or storing the second image data.

In one example, the image acquisition may be re-triggered by the second processor core for image acquisition; in another example, the image acquisition may be re-triggered by the first processor core for image acquisition; in yet another example, the image collector may be re-triggered to collect images by any device with a triggering function (such as other IP cores) in the multi-core heterogeneous chip; the description is not intended to be limiting.

In one example, it may be determined by a second processor core whether to send alert information based on the second image data; in another example, it may be determined by the first processor core whether to send alert information based on the second image data; in yet another example, whether to send the alarm information may be determined by any device having an image detection function in the multi-core heterogeneous chip according to the second image data; the description is not intended to be limiting.

The specific manner of determining whether to send the alarm information according to the second image data may refer to the above manner of determining whether to send the alarm information according to the first image data, for example, an image recognition model is adopted, which is not described herein.

Storing the second image data may include: and sending the second image data to a storage module for storage.

In some embodiments, the second image data may include: at least two areas of image data and the corresponding identification of the image data of each area;

accordingly, the method may further include: merging image data of at least two areas, displaying the merged image data, and the like.

For example, the method may further comprise:

determining an identifier corresponding to the image data of each region in the image data of at least two regions included in the second image data; the identifier is used for representing the position of the area relative to the electronic equipment and/or an image collector identifier corresponding to the image data of the area;

and displaying the combined image data.

The specific manner may refer to the operation performed according to the first image data, and will not be described herein.

In some embodiments, the method further comprises:

determining third image data before the electronic device is shut down;

Specifically, in an example, the third image data may be image data of an environment in which the electronic device is located. When the vehicle is stopped and flameout for the previous time, the image collector can collect third image data of the surrounding environment of the electronic equipment, and after the electronic equipment is restarted, the first processor core directly determines whether to send alarm information according to the third image data, and/or determines whether to send alarm information according to the third image data and fourth image data collected after the electronic equipment is restarted.

In another example, to improve the image detection efficiency, the third image data may be image data of a specific area of the environment where the electronic device is located; the specific area may be an area where risk is liable to occur, for example, a driver blind area and a vehicle bottom. After the electronic equipment is restarted, the first processor core directly determines whether to send the alarm information according to the third image data, and/or determines whether to send the alarm information according to the third image data and fourth image data acquired after the electronic equipment is restarted. Therefore, whether the blind area and the vehicle bottom are at risk or not is rapidly determined through the third image data, namely whether the warning information needs to be sent or not is determined according to the third image data, the image recognition speed is increased, and the safety of vehicle starting is further improved.

In one example, the third image data may be determined by the second processor core before the electronic device is shut down; and after the electronic equipment is restarted, the first processor core determines whether to send the alarm information according to the third image data, and/or determines whether to send the alarm information according to the third image data and fourth image data acquired after the electronic equipment is restarted.

In another example, the third image data may be determined by the first processor core before the electronic device is shut down; and after the electronic equipment is restarted, determining whether to send alarm information according to the third image data, and/or determining whether to send alarm information according to the third image data and fourth image data acquired after the electronic equipment is restarted.

In some embodiments, the method may include:

determining third image data before the electronic device is shut down;

identifying the third image data by using an image identification model to obtain a detection result;

if the detection result indicates that the environment where the electronic equipment is located does not have a target object, the environment where the electronic equipment is located is considered to have no risk;

If the detection result represents that the environment where the electronic equipment is located has a target object, the environment where the electronic equipment is located is considered to have risk, and the existing target object is marked;

after the electronic equipment is restarted, determining whether to send alarm information according to the detection result and fourth image data acquired after restarting.

Specifically, whether the environment where the electronic equipment is located is at risk or not is detected before stopping and flameout, if the detection result indicates that the risk is not present, the third image data and the fourth image data are directly compared, and if the third image data and the fourth image data are not different, the risk is directly considered to be absent, namely, an alarm message is not required to be sent; if the alarm information is different, the risk is directly considered to exist, namely, the alarm information needs to be sent. That is, if the surrounding is safe when the vehicle is stopped and flameout, the surrounding image is not added with the target object when the vehicle is started, and the vehicle can be rapidly judged to be safe.

If the detection result indicates that the risk exists, detecting whether a marked target object still exists in the fourth image data, and if the marked target object exists, directly considering that the risk exists, namely, sending an alarm message; if the target object is not present, the risk is considered to be absent, or detection is continued according to the fourth image data.

In an example, before the electronic device is shut down and flameout, determining third image data by the second processor core, and identifying the third image data by using an image identification model to obtain a detection result and sending the detection result to the first processor core; after the electronic equipment is restarted, the first processor core determines whether to send alarm information according to the detection result and fourth image data acquired after restarting.

In another example, a first processor core may determine third image data before the electronic device is parked and flameout, and identify the third image data using an image recognition model, resulting in a detection result; and after the electronic equipment is restarted, determining whether to send alarm information according to the detection result and fourth image data acquired after restarting.

In some embodiments, the method further comprises:

and if the first processor core sends the alarm message, the first processor core releases the resource for sending the alarm message based on the resource release request.

Specifically, the alert information may include, but is not limited to, one of: an alarm sound;

an alert image or alert icon;

Alarm indicator light.

The resources for sending the alert message may include, but are not limited to, one of: buzzer resources for playing alert tones;

display screen resources for displaying alert images or alert icons;

and presenting the double-flash module resource or the relay resource of the alarm indicator lamp.

Here, in order to avoid resource conflict occurring subsequently, the resources for transmitting the alarm message may be released together when the image collector resources are released, so as to be called again subsequently.

In some embodiments, the method further comprises:

Specifically, the first processor core can inform the second processor core after the image collector resources are released, so that the second processor core can know the release condition of the image collector resources in time, and the subsequent second processor core or other IP cores can call the image collector according to requirements.

If the first processor core releases the resource for sending the alarm message based on the resource release request, the third prompt information may further characterize that the resource for sending the alarm message is released.

In some embodiments, the first processor core determining whether to send alert information based on the first image data includes:

Specifically, the multi-core heterogeneous chip may have a detector therein for detecting the image data to determine whether the image data satisfies a safety expectation condition. If the multi-core heterogeneous chip is provided with a detector, the first processor core can send the first image data to the detector, the detector determines whether the first image data meets the safety early warning condition based on the first image data, and sends a detection result to the first processor core.

The manner in which the detector detects whether the first image data meets the safety precaution condition may be as described above, and the first image data is processed using the image recognition model to obtain a processing result, i.e. the collector may include the image recognition model.

The first image data, the second image data, the third image data, the fourth image data, the image data of each region, and the like may include single image data, and may further include video image data, where the video image data includes: multi-frame image data; that is, each image data may include one or more frames of images.

In some embodiments, the method may further comprise: and configuring a hardware domain of the multi-core heterogeneous chip.

Here, the hardware domain configuring the multi-core heterogeneous chip may be executed after step 101 and before step 102, or may be executed before step 101 and step 102, which is not limited herein.

Specifically, after the electronic device is powered on, the first processor core is started, hardware resources such as a double rate synchronous dynamic random access memory (DDR) and the like are initialized, the first processor core triggers the image collector to collect images, then configures a hardware domain, and then sends a starting instruction to the second processor core.

The configuration hardware domain may be that the first processor core reads configuration information, and relevant configuration is performed on a plurality of hardware domains isolated from each other on hardware formed by each processor core and the hardware set according to the configuration information.

According to the method provided by the embodiment of the disclosure, before the operating system corresponding to the second processor core is completely started, the first processor core triggers the image collector to collect the image and detect the image, so that the starting time of the image collector is shortened, the time for collecting the image and detecting the driving environment of the vehicle is shortened, and the safety of the driving environment of the vehicle is further guaranteed.

Fig. 2 illustrates a second implementation flow diagram of a method for detecting safety of a vehicle environment according to an embodiment of the disclosure; as shown in fig. 2, the method is applied to a multi-core heterogeneous chip; the multi-core heterogeneous chip includes a first processor core and a second processor core, the method comprising:

step 201, starting a first processor core after the electronic equipment is powered on, and opening a camera by the first processor core to obtain image data;

here, the number of cameras may be one or more, and the plurality may include two or more. The first processor core opens the camera, including: and respectively sending image acquisition instructions to each camera so that each camera acquires image data after being started and feeds the image data back to the first processor core.

The image data may include: image data collected by each camera respectively.

Step 202, initializing hardware resources such as DDR and the like;

step 203, the first processor core sends a start command to the second processor core;

here, the second processor core starts operation after receiving the start command, and the first processor core and the second processor core start operation independently.

Step 204, the first processor core judges whether a resource release request sent by the second processor core is received; if no resource release request is received, step 205 is entered, and if a resource release request is received, step 214 is entered;

here, as can be seen from the left time information of fig. 2, the second processor core needs at least 10 seconds, even more than 20 seconds, and the resource release request is issued after the second processor core is completely started for the operating system, so the first processor core does not receive the resource release request at the beginning, that is, the first processor core may first detect according to the acquired image data, and only execute step 205.

Step 205, a first processor core acquires image data through a camera; detecting according to the image data, and determining whether to send alarm information; when it is determined that the alarm information needs to be sent, step 206 is entered.

If the alarm information is determined not to be required to be sent, continuing to acquire the image data and detecting, and simultaneously detecting whether a resource release request sent by the second processor core is received.

Here, the first processor core may have an algorithm detection module, which detects according to the image data, and determines whether to send the alarm information; or, the multi-core heterogeneous chip may further have an algorithm detector, the first processor core transmits the image data to the algorithm detector, the algorithm detector detects according to the image data, determines whether to transmit the alarm information, and informs the first processor core of the determined result.

Here, the algorithm detection module or algorithm detector may detect image data using an image recognition model to determine whether to transmit alert information. The image recognition model is described in the method shown in fig. 1, and will not be described here.

For example, the algorithm detection module or algorithm detector may use an image recognition model to detect whether there is a target object in the image data, such as whether there is an animal, a child, or the like. If the target object exists in the image data, the alarm information is determined to be required to be sent.

Step 206, sending alarm information through an alarm module;

Here, the alarm information may include, but is not limited to, any one of the following: an alarm sound; an alert image or alert icon; alarm indicator light.

The alarm sound can be played through a buzzer; the alarm image or the alarm icon can be presented through a display screen; the alarm indicator light may be presented by a double flashing module, a relay, etc. That is, the alarm module may include: buzzer, display screen, double flashing module, relay etc..

Step 207, displaying the image data;

here, displaying the image data includes at least one of:

sending the image picture corresponding to the target object to a display screen for display;

and combining the image data acquired by each camera to obtain combined image data, and sending the combined image data to a display screen for display.

Step 208, the image data is sent to a storage module for encoding and storage, so that the image data can be exported and used later.

Step 209, after the second processor core is started, initializing each hardware module normally in a boot or boot (boot) stage; the respective hardware modules may include: USB, clock, etc.

Step 210, starting a Linux kernel;

Step 211, initializing a process of an android environment (namely an android system);

step 212, after the android environments are all completed, entering an application program (APP) starting stage, and starting the camera APP.

Step 213, after the camera APP sends a resource release request to the first processor core, waiting for a response of the first processor core; if a release result message is received, step 215 is entered;

here, the resource release request is used for requesting the first processor core to release camera related resources;

and the release result message characterizes the released camera related resources.

The camera related resources include: camera resources, storage module resources, buzzer resources, display screen resources and the like. Wherein releasing memory module resources is specifically understood as releasing the portion of memory space stored therein.

Step 214, after receiving the resource release request, the first processor core releases (or closes) the camera related resource, and after releasing, sends a release result message to the second processor core to inform the second processor core that the camera related resource has been released.

Here, releasing (or closing) the camera-related resources may include: closing a display screen, closing a storage module, closing a camera and the like.

And step 215, after the second processor core receives the release result message, the second processor core continues to normally use related resources such as the camera according to the conventional flow, such as opening the camera and executing other actions for operating the camera.

As can be seen in conjunction with the figure 2 drawing, the android system-related time is as follows:

1s, before the Linux system is not started, the initial hardware configuration is carried out in about 1-2 s.

And 3s, indicating that the Linux system is started, and starting to start the android system.

10s the android system is being started, and the android system can be completely started in 10-30 s.

20s after android system, various non-system APP will start starting around this point in time.

Here, 1s, 3s, 10s, and 20s are not strict times, and some errors may occur.

By the method of the embodiment of the disclosure, before the operating system (namely the android system) corresponding to the second processor core is completely started, the first processor core triggers the image acquisition device to acquire the image and detect the image, the time can be about 1s, so that the starting time of the camera is greatly prolonged, the time for collecting the image and detecting the driving environment of the vehicle is advanced, and the safety of the driving environment of the vehicle is further ensured.

Fig. 3 illustrates a third implementation flow diagram of a method for detecting safety of a vehicle environment according to an embodiment of the disclosure; the method is applied to the multi-core heterogeneous chip; the multi-core heterogeneous chip includes a first processor core and a second processor core, the method comprising:

step 301, after the electronic device is powered on, a first processor core is started;

step 302, initializing hardware resources such as DDR and the like;

step 303, the first processor core sends a start command to the second processor core;

Step 304, the first processor core judges whether a resource release request sent by the second processor core is received; if no resource release request is received, go to step 305; if resource release is received the request then proceeds to step 314;

step 305, triggering a camera to acquire an image by a first processor core, and acquiring image data; detecting according to the image data, and determining whether to send alarm information; when it is determined that the alarm information needs to be sent, step 306 is entered.

Step 306, sending alarm information through an alarm module;

step 307, displaying the image data;

step 308, the image data is sent to a storage module for encoding and storage, so that the image data can be exported and used later.

Step 309, after the second processor core is started, initializing each hardware module normally in a boot or boot (boot) stage;

step 310, starting a Linux kernel;

step 311, initializing the android environment (namely an android system);

step 312, after the android environments are all completed, entering an application program (APP) starting stage, and starting the camera APP.

Step 313, after the camera APP sends a resource release request to the first processor core, waiting for a response of the first processor core; if a release result message is received, step 315 is entered;

in step 314, after receiving the resource release request, the first processor core releases (or closes) the camera related resource, and after releasing, sends a release result message to the second processor core to inform the second processor core that the camera related resource has been released.

And step 315, after receiving the release result message, the second processor core continues to normally use related resources such as the camera according to the conventional flow, such as opening the camera and executing other actions for operating the camera.

Unlike the embodiment shown in fig. 2, the first processor core of the embodiment shown in fig. 3 may first start the second processor core, and then trigger the camera to collect and detect the image, which may be completed within 1 s. The method shown in fig. 3 can also improve the starting time of the camera, so that the time for acquiring the image and detecting the driving environment of the vehicle is advanced, and the safety of the driving environment of the vehicle is further ensured.

FIG. 4 is a schematic diagram of a safety detection device for a vehicle environment according to an embodiment of the present disclosure; as shown in fig. 4, the safety detection device for a vehicle environment includes: the multi-core heterogeneous chip comprises a first processor core and a second processor core; the first processor core includes a first processing module; wherein,

In some embodiments, the first processing module is configured to determine whether the first image data meets a safety precaution condition;

In some embodiments, the first processing module is specifically configured to process the first image data by using an image recognition model, so as to obtain a processing result of the image recognition model; the processing result comprises at least one of the following:

Whether the safety early warning condition is met;

whether a target object exists in the first image data;

the type of the target object;

image data marked with the target object;

the location of the target object relative to the electronic device.

the apparatus further comprises a second processing module for:

and displaying the combined image data.

In some embodiments, the apparatus further comprises a third processing module for:

In some embodiments, the apparatus further comprises a fourth processing module configured to trigger the image collector to perform image collection after the first processor core releases the image collector resource, to obtain second image data;

In some embodiments, the apparatus further comprises a fifth processing module for determining third image data before the electronic device is shut down;

In some embodiments, if the first processor core sends an alarm message, the first processing module is further configured to release resources for sending the alarm message based on the resource release request;

In some embodiments, the apparatus further comprises a detector; the detector is a device used for detecting image data in the multi-core heterogeneous chip;

It should be noted that: the second processing module, third processing module, fourth processing module, fifth processing module, detector, etc. described above are not shown in fig. 4. It will be appreciated that, in the safety detection apparatus for a vehicle environment provided in the above embodiment, when implementing the safety detection method for a corresponding vehicle environment, the above processing may be distributed to be completed by different program modules as needed to complete all or part of the above-described processing. In addition, the apparatus provided in the foregoing embodiments and the embodiments of the corresponding methods belong to the same concept, and specific implementation processes of the apparatus and the embodiments of the methods are detailed in the method embodiments, which are not described herein again.

The embodiment of the disclosure also provides a component on the traffic equipment, wherein the component comprises a chip, and the chip can execute the safety detection method of the vehicle environment.

In some embodiments, the component may be a circuit board level component, a vehicle electrical system level component, or a vehicle assembly component. As examples, the components may be an engine, a chassis, a body, and electrical and electronic equipment of a vehicle. Among them, the electric and electronic devices of the vehicle may include a headlight for illumination, a management device controlling the engine, a center control device receiving broadcasting, navigation, listening to music, entertainment, etc.

The embodiment of the disclosure also provides a traffic device, which comprises a chip, wherein the chip can execute the safety detection method of the vehicle environment. The chip may be a multi-core heterogeneous chip, and the traffic equipment includes, but is not limited to, balance cars, buses, trains, and the like.

The disclosed embodiments provide a computer readable storage medium having stored therein executable instructions that, when executed by a processor, will trigger the processor to perform the method of detecting the safety of a vehicle environment provided by the disclosed embodiments.

In some embodiments, the computer readable storage medium may be Ferroelectric Random Access Memory (FRAM), read-Only Memory (ROM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable ROM, EPROM), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), flash Memory, magnetic surface Memory, optical disk, or CD-ROM; but may be a variety of devices including one or any combination of the above memories.

In some embodiments, the executable instructions may be in the form of programs, software modules, scripts, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and they may be deployed in any form, including as stand-alone programs or as modules, models, subroutines, or other units suitable for use in a computing environment.

As an example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices located at one site or, alternatively, distributed across multiple sites and interconnected by a communication network.

Embodiments of the present disclosure provide a computer program product comprising computer programs/instructions which, when executed by a processor, implement the method of safety detection of a vehicle environment described in the present disclosure.

Fig. 5 shows a schematic structural diagram of an electronic device according to an embodiment of the disclosure, as shown in fig. 5, the electronic device 50 includes: a processor 501 and a memory 502 for storing a computer program capable of running on the processor; the processor 501 is configured to execute the method for detecting the safety of the vehicle environment provided by the embodiment of the present disclosure when running the computer program.

In practical applications, the electronic device 50 may further include: at least one network interface 503. The various components in the electronic device 50 are coupled together by a bus system 504. It is to be appreciated that bus system 504 is employed to enable connected communications between these components. The bus system 504 includes a power bus, a control bus, and a status signal bus in addition to the data bus. But for clarity of illustration, the various buses are labeled as bus system 504 in fig. 5. The number of the processors 501 may be at least one. The network interface 503 is used for wired or wireless communication between the electronic device 50 and other devices.

The memory 502 in the disclosed embodiments is used to store various types of data to support the operation of the electronic device 50.

The methods disclosed in the embodiments of the present disclosure described above may be applied to the processor 501 or implemented by the processor 501. The processor 501 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuitry in hardware or instructions in software in the processor 501. The Processor 501 may be a general purpose Processor, a DiGital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The processor 501 may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present disclosure. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present disclosure may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in the decoded processor. The software modules may be located in a storage medium in memory 502 and processor 501 reads information in memory 502 to perform the steps of the method described above in connection with its hardware.

In some embodiments, the electronic device 50 may be implemented by one or more application specific integrated circuits (ASIC, application Specific Integrated Circuit), DSPs, programmable logic devices (PLD, programmable Logic Device), complex programmable logic devices (CPLD, complex Programmable Logic Device), field programmable gate arrays (FPGA, field-Programmable Gate Array), general purpose processors, controllers, microcontrollers (MCU, micro Controller Unit), microprocessors (Microprocessor), or other electronic components for performing the aforementioned methods.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

The foregoing is merely specific embodiments of the disclosure, but the protection scope of the disclosure is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the disclosure, and it is intended to cover the scope of the disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A method of detecting safety of a vehicle environment, the method comprising:

after the first processor core triggers the image collector to collect the image, the first processor core sends a starting instruction to the second processor core through an inter-core communication mechanism; the starting instruction is used for indicating the second processor core to start an operating system corresponding to the second processor core, and the first processor core and the second processor core belong to the same multi-core heterogeneous chip;

Until the first processor core receives a resource release request sent by the second processor core through an inter-core communication mechanism, the first processor core releases the image collector resource; the resource release request characterizes the operating system to be completely started;

the method further comprises at least one of:

2. The method of claim 1, wherein determining whether to transmit alert information based on the first image data comprises:

determining whether the first image data meets a safety precaution condition;

3. The method of claim 2, wherein the determining whether the first image data satisfies a security pre-warning condition comprises:

whether the safety early warning condition is met;

whether a target object exists in the first image data;

the type of the target object;

image data marked with the target object;

the location of the target object relative to the electronic device.

4. The method according to claim 1 or 2, wherein the first image data comprises: at least two areas of image data and the corresponding identification of the image data of each area;

the method further comprises the steps of:

and displaying the combined image data.

5. The method according to claim 4, wherein the method further comprises:

6. The method of claim 1, wherein after the first processor core releases image collector resources, the method further comprises:

triggering the image collector to collect images to obtain second image data;

7. The method according to claim 1, wherein the method further comprises:

determining third image data before the electronic device is shut down;

8. The method of claim 1, wherein the first processor core determining whether to send alert information based on the first image data comprises:

9. A safety inspection device for a vehicle environment, the device comprising: the multi-core heterogeneous chip comprises a first processor core and a second processor core; the first processor core includes a first processing module; wherein,

The first processing module is used for triggering the image acquisition device to acquire images so as to obtain first image data; after the first processor core triggers the image collector to collect the image, a starting instruction is sent to the second processor core through an inter-core communication mechanism; the starting instruction is used for indicating the second processor core to start an operating system corresponding to the second processor core;

the first processing module is further configured to release the image collector resource until the first processor core receives a resource release request sent by the second processor core through an inter-core communication mechanism; the resource release request characterizes the operating system to be completely started;

if the first processor core sends an alarm message, the first processing module is further configured to release a resource for sending the alarm message based on the resource release request;

10. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

11. A component on a traffic device, characterized in that it comprises a chip capable of implementing the method according to any one of claims 1 to 8.

12. A traffic device, characterized in that it comprises a chip capable of implementing the method of any one of claims 1 to 8.

13. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 8.