Sentry mode activation / deactivation control method, apparatus, and electronic equipment

Abstract

The embodiments of this disclosure relate to the field of vehicle technology, and relate to a control method, apparatus, and electronic equipment for starting and stopping Sentry Mode. [Solution] This method includes the steps of: acquiring an initial image corresponding to each image channel when Sentry mode is activated; acquiring environmental information of the vehicle based on the initial image corresponding to each image channel; and turning off the image channel corresponding to the at least one target direction in response to the detection from the environmental information that an obstacle exists outside the vehicle and that the positional relationship between the obstacle and the vehicle in at least one target direction satisfies a preset positional condition, thereby solving the problem of high power consumption by Sentry mode in the vehicle.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle technology, and particularly to a control method, device, and electronic device for starting and stopping a centry mode.

Background Art

[0002] Currently, the centry mode of a vehicle has already become an important function in an intelligent cockpit and a vehicle safety system. By continuously monitoring the environment around the vehicle in a parked state, potential acts of vandalism and theft can be effectively prevented. However, in the actual application process, the centry mode of the vehicle faces a significant power consumption problem, so its large-scale popularization is restricted.

[0003] After the centry mode is started, all sensing channels continuously operate and analyze. However, in some special scenes, the data collected by some image channels cannot be effectively utilized for environmental perception, causing unnecessary resource waste.

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the centry mode of a vehicle, various sensors and cameras on the vehicle body monitor the vehicle and the surrounding environment in a parked state to obtain the safety status of the vehicle in real time. Since all image channels around the vehicle continuously operate, the power consumption is very high. However, detection in a specific scene is meaningless. For example, there is no or extremely low risk on the fence side where the vehicle is close, so there is no need to continuously detect.

[0005] In order to solve the above technical problems, the present disclosure provides a control method, device, and electronic device for starting and stopping a centry mode to solve the problem of high power consumption caused by the centry mode of a vehicle.

Means for Solving the Problems

[0006] The control method for starting and stopping Sentry Mode according to the first aspect of this disclosure is: When Sentry mode is activated, there is a step to acquire an initial image corresponding to each image channel, A step of acquiring vehicle environmental information based on the initial image corresponding to each image channel, The method includes the step of turning off an image channel corresponding to at least one target direction in response to the detection from environmental information that an obstacle exists outside the vehicle and that the positional relationship between the obstacle and the vehicle in at least one target direction satisfies a preset positional condition.

[0007] The Sentry Mode Start / Stop control device according to a second aspect of this disclosure is: The system includes multiple external cameras, and when Sentry Mode is activated, it includes an image acquisition component that collects initial images of the external environment using the camera corresponding to the image channel. The system includes one or more processors that, by executing instructions stored in memory, acquire environmental information of the vehicle based on an initial image corresponding to each image channel, and, in response to detecting from the environmental information that an obstacle exists outside the vehicle and that the positional relationship between the obstacle and the vehicle in at least one target direction satisfies a preset positional condition, turn off the image channel corresponding to at least one target direction.

[0008] An electronic device according to a third aspect of this disclosure includes one or more processors and a memory in which computer program instructions are stored, wherein when a computer program instruction is executed by the processor, the processor is instructed to execute a Sentry Mode startup / shutdown control method according to the first aspect.

[0009] A computer-readable storage medium according to a fourth aspect of this disclosure stores computer program instructions that, when executed by a processor, cause the processor to execute the Sentry Mode startup / shutdown control method according to the first aspect. [Effects of the Invention]

[0010] According to the Sentry Mode activation / deactivation control method described herein, when Sentry Mode is activated, an initial image corresponding to each image channel is acquired and the vehicle's environmental information is analyzed to identify obstacles present outside the vehicle. If the positional relationship between the obstacle and the vehicle in a specific target direction satisfies preset positional conditions, the image channel corresponding to that target direction is turned off. This method effectively avoids continuous image acquisition and processing in directions with no or extremely low risk, significantly reducing power consumption, extending the monitoring time while the vehicle is parked, and improving the practicality and user experience of Sentry Mode. [Brief explanation of the drawing]

[0011] The above and other purposes, features and advantages of this disclosure will become more apparent by describing the embodiments of this disclosure in more detail with reference to the drawings. The drawings are provided to provide a further understanding of the embodiments of this disclosure, constitute part of the specification, and are intended to be used in conjunction with the embodiments of this disclosure, and are not intended to limit this disclosure. In the drawings, the same reference numerals usually represent the same member or step. [Figure 1] This is a schematic block diagram of the structure of a control system for starting and stopping Sentry Mode according to one exemplary embodiment of the present disclosure. [Figure 2] A schematic diagram of the collection area according to one exemplary embodiment of the present disclosure. [Figure 3] This is a schematic flowchart of a control method for starting and stopping Sentry Mode according to one exemplary embodiment of the present disclosure. [Figure 4A] This is a schematic diagram illustrating the positional relationship between an obstacle and a vehicle according to one exemplary embodiment of the present disclosure. [Figure 4B] This is a schematic diagram illustrating the positional relationship between an obstacle and a vehicle according to another exemplary embodiment of the present disclosure. [Figure 5] This is a schematic flowchart of a control method for starting and stopping Sentry Mode according to another exemplary embodiment of the present disclosure. [Figure 6] A schematic flowchart of a control method for starting and stopping the center mode according to another exemplary embodiment of the present disclosure. [Figure 7] A schematic flowchart of a method for determining image quality according to an exemplary embodiment of the present disclosure. [Figure 8] A schematic flowchart of a method for obtaining an image quality category according to an exemplary embodiment of the present disclosure. [Figure 9] A schematic diagram of the positional relationship between an obstacle and a vehicle according to another exemplary embodiment of the present disclosure. [Figure 10] A schematic diagram of the length of an obstacle according to an exemplary embodiment of the present disclosure. [Figure 11] A schematic flowchart of a method for determining the relative position between an obstacle and a vehicle according to an exemplary embodiment of the present disclosure. [Figure 12] A schematic structural diagram of a control device for starting and stopping the center mode according to an exemplary embodiment of the present disclosure. [Figure 13] A schematic structural diagram of an electronic device according to an exemplary embodiment of the present disclosure.

Embodiments for Carrying Out the Invention

[0012] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the drawings. The described embodiments are only some of the embodiments of the present disclosure, not all of the embodiments. The present disclosure is not limited to the exemplary embodiments.

[0013] Unless otherwise specified, the scope of the present disclosure is not limited to the relative arrangements of the members and steps, mathematical formulas and numerical values described in these embodiments.

[0014] [Summary of the Application] The vehicle's entry mode effectively prevents potential vandalism and theft by continuously monitoring the environment around the vehicle while it is parked. Usually, the vehicle needs to continuously record using multiple cameras at the front, rear, and sides simultaneously, and the sensors, image processing devices, and related electronic systems of these cameras require continuous power supply. To analyze the screens captured by the cameras in real time to detect potential threats such as the approach of people and abnormal movements, it is necessary to maintain the operating state of the vehicle's high-performance computing chip. Therefore, while the entry mode can comprehensively guarantee the safety of the vehicle in its stationary state, continuous operation of components results in very high power consumption in the entry mode.

[0015] After the entry mode is activated, all sensing channels continuously operate and analyze. However, in some special scenarios, the data of some image channels cannot be effectively used for environmental perception, causing energy waste. For example, when the vehicle is parked with one side against a fixed obstacle, this side can be considered safe, so continuously detecting it is meaningless.

[0016] Embodiments of the present disclosure propose a new solution that can solve the problem of high power consumption in the above-mentioned entry mode. Specifically, embodiments of the present disclosure provide a control method, device, and electronic device for starting and stopping the entry mode. When the entry mode is started, initial images corresponding to each image channel are obtained, and vehicle environmental information is obtained based on the obtained initial images corresponding to each image channel. If the environmental information includes that there are obstacles outside the vehicle and the positional relationship between the obstacles and the vehicle in the target direction where the obstacles exist meets the preset position conditions, in the target direction where the obstacles exist, the vehicle can be considered safe. Therefore, the image channel in this target direction can be turned off to reduce the overall power consumption in the entry mode.

[0017] [Exemplary System] Figure 1 is a schematic diagram of the structure of a Sentry Mode startup / shutdown control system according to one exemplary embodiment of the present disclosure.

[0018] As shown in Figure 1, in one embodiment, the control system for starting and stopping the sentry mode may include an acquisition system 10 and a decision-making system 20, wherein the acquisition system 10 is connected to the decision-making system 20 in a communication manner and can exchange data with the decision-making system 20.

[0019] In one embodiment, the collection system 10 is for collecting environmental data around a vehicle, including video and / or images. The collection system 10 includes at least one camera, which may include at least one of a single-lens camera, a binocular camera, a trinocular camera, a wide-angle camera, or a fisheye camera, and the types of cameras are not limited in the embodiments of this disclosure. Thus, the collection system 10 can collect video or images around a vehicle.

[0020] In one example, the images collected by the collection system 10 may include objects around the vehicle (e.g., walls, fences, potted plants, pedestrians, animals, other vehicles, etc.).

[0021] The data collection system 10 may include at least one camera, which may be mounted at different locations on the vehicle to collect environmental data in different directions. For example, a camera may be mounted at the front of the vehicle to collect environmental data in front of the vehicle. A camera may be mounted at the rear of the vehicle to collect environmental data behind the vehicle. A camera may be mounted on the side of the vehicle to collect environmental data to the side of the vehicle.

[0022] The camera's capture area refers to the maximum range that the camera can capture, and it is determined by camera parameters such as the field of view (FOV) and shooting distance.

[0023] For example, if the camera's field of view and shooting distance are small, the camera's acquisition area is small. If the camera's field of view and shooting distance are large, the camera's acquisition area is also large.

[0024] Correspondingly, the total collection area of ​​the collection system 10 is the sum of the collection areas of each camera.

[0025] In one embodiment, the total collection area of ​​the collection system 10 can be an annular area centered on the vehicle. In this way, it is possible to ensure that environmental data around the vehicle is collected more comprehensively.

[0026] Figure 2 is a schematic diagram of a collection area according to one exemplary embodiment of the present disclosure.

[0027] As shown in Figure 2, in the embodiment of this disclosure, cameras are mounted on the front, rear, left, and right sides of the vehicle, respectively. The image acquisition range of each camera includes sector-shaped regions 11 to 14, and the total acquisition area is obtained by combining sector-shaped regions 11 to 14. By splicing the images captured in each direction, complete environmental information around the vehicle can be obtained.

[0028] In one embodiment, the decision-making system 20 may include one or more processors 201. The processors 201 may include, for example, general-purpose processors such as a central processing unit (CPU) and a graphics processing unit (GPU), or accelerated computing units such as a neural processing unit (NPU) designed for deep learning tasks, autonomous driving tasks, sentry mode tasks, etc.

[0029] In one embodiment, the decision-making system 20 may include one or more memories 202, which can store program instructions that the processor 201 can execute, and the processor 201 can perform the functions of the decision-making system 20 by loading and executing the program instructions in the memories 202.

[0030] Furthermore, memory 202 can also cache or store intermediate or result data generated during the operation of processor 201, as well as system files, application files, data files, etc. For example, memory 202 can store environmental data collected by collection system 10, etc.

[0031] For example, memory 202 may include volatile memory such as dynamic random access memory (DRAM) and static random access memory (SRAM), and may also include non-volatile memory such as read-only memory (ROM) and flash memory (NVM).

[0032] In one embodiment, the decision-making system 20 exchanges data with the acquisition system 10 to collect image data collected by the acquisition system 10, identifies obstacles present around the vehicle based on this image data, and controls the system to turn off the image channel corresponding to the target direction if the positional relationship between the obstacle and the vehicle in the target direction where the obstacle is located satisfies preset positional conditions, thereby effectively reducing overall power consumption in sentry mode.

[0033] The solutions relating to this disclosure are not limited to the embodiments mentioned above.

[0034] [Example Method] Figure 3 is a schematic flowchart of a control method for starting and stopping a Sentry Mode according to one exemplary embodiment of the present disclosure. This embodiment can be applied to electronic equipment, and as shown in Figure 3, the method includes steps S101 to S103.

[0035] In step S101, when Sentry Mode is activated, an initial image corresponding to each image channel is acquired.

[0036] Here, a channel refers to a logical set of hardware acquisition components, data transmission links, and software processing resources independently configured to realize a specific environmental sensing function, divided based on a particular monitoring direction in the vehicle's sentry mode. An image channel is merely a specific embodiment of a channel in the embodiments of this disclosure and includes channels whose core function is optical image acquisition and processing. An image channel is jointly comprised of a dedicated camera, an independent image data transmission path, a dedicated image data cache area, and independent image processing processes and computing resources that perform the acquisition, transmission, and processing of image signals. In other words, each image channel is a set of hardware and / or software resources for processing images, and exemplary, in sentry mode, there may be multiple image channels, each corresponding to one direction, for example, an image channel corresponding to the front of the vehicle, an image channel corresponding to the rear of the vehicle, an image channel corresponding to the left side of the vehicle, and an image channel corresponding to the right side of the vehicle. The initial image is an image acquired by the camera corresponding to the image channel, and exemplary, the camera may be a fisheye camera, etc.

[0037] According to the technical configuration of this step, when the vehicle's sentry mode is activated, initial images corresponding to each image channel are acquired, providing a complete and synchronized data source for subsequent environmental information analysis, thereby avoiding misjudgments due to incomplete images.

[0038] In step S102, vehicle environmental information is acquired based on the initial image corresponding to each image channel.

[0039] Here, environmental information refers to information about the surrounding environment outside the vehicle, and can be used to determine information such as the presence or absence of obstacles outside the vehicle, the location of obstacles, the size of obstacles, and the type of obstacles.

[0040] According to the technical configuration of this step, based on the initial image corresponding to each image channel, some environmental information from each direction outside the vehicle is acquired, and combined with the partial environmental information from each direction to acquire complete environmental information around the vehicle, providing a reliable basis for the decision to turn off subsequent image channels.

[0041] In step S103, the presence of an obstacle outside the vehicle is detected from the environmental information, and in response to the positional relationship between the obstacle and the vehicle in at least one target direction satisfying a preset positional condition, the image channel corresponding to at least one target direction is turned off.

[0042] In embodiments of this disclosure, the obstacle may be a fixed object outside the vehicle, such as a fence, wall, or potted plant. A fixed obstacle can be considered immovable if it is not affected by external influences. Pre-set positional conditions include, but are not limited to, that the distance between the obstacle and the vehicle is less than a pre-set distance threshold, and that the obstacle completely obstructs the vehicle in the target direction. The direction in which the obstacle exists is the direction corresponding to the image channel with respect to the vehicle, and is divided into the front, rear, left side and right side of the vehicle, etc. For example, the obstacle may be located in front of the vehicle, rear, or left side of the vehicle. Turning off the image channel includes stopping image acquisition and processing in the target direction, i.e., turning off the hardware and / or software corresponding to the image channel, thereby reducing power consumption.

[0043] For example, turning an image channel in the target direction on or off does not affect the operation of image channels in other directions, so that other image channels in directions other than the target direction can continue to acquire initial images, monitor suspicious targets, and capture potential threats. For example, turning an image channel on or off does not affect the operation of other sensing channels in sentry mode, and sensing channels include, but are not limited to, laser radar channels and infrared sensor channels. A laser radar channel consists of a laser emitter, scanning mechanism, photoelectric detector, and processing unit, and can provide three-dimensional environmental information outside the vehicle. An infrared sensor channel consists of a thermal imager and signal processing unit, and can compensate for the lack of a visible light camera in a dark environment.

[0044] According to the technical configuration of this step, based on the environmental information obtained in step S102, it is determined whether or not to turn off an image channel in a certain direction. Specifically, if the presence of an obstacle outside the vehicle is detected from the environmental information, and it is determined that the positional relationship between the obstacle and the vehicle in at least one target direction satisfies a preset positional condition, then the vehicle is safe in this target direction (a situation with no risk or a very low risk). Therefore, the image channel in the target direction can be turned off, that is, the operation of the hardware of the image channel (e.g., camera sensor, etc.) and the operation of the software of the image channel (e.g., environmental information analysis, obstacle detection, etc.) can be stopped, thereby saving power from the source and effectively extending the monitoring time when the vehicle is parked.

[0045] In one feasible configuration, when Sentry Mode is activated, an initial image is acquired and environmental information based on the initial image is acquired. It is then possible to timely determine whether or not an obstacle can be detected from the environmental information. If an obstacle is detected and the positional relationship between the obstacle and the vehicle in the target direction where the obstacle exists satisfies preset positional conditions, the image channel corresponding to the target direction is quickly turned off, minimizing the time the image channel is on and reducing the power consumption of the hardware and / or software corresponding to that image channel.

[0046] In one feasible configuration, in extreme situations, obstacles may move due to external influences, for example, if the obstacle is a movable object such as a fence. Therefore, when the image channel in the target direction is turned off, the image channel is turned on after a predetermined interval to acquire an initial image, and it is determined whether or not an obstacle still exists in the direction corresponding to the image channel. If the presence of an obstacle is detected and the positional relationship between the obstacle and the vehicle in the direction corresponding to the image channel satisfies the predetermined positional conditions, the image channel is turned off again. This method ensures the safety of the vehicle in that direction and improves the monitoring accuracy in sentry mode.

[0047] In one implementable form, the method of the present disclosure further includes the step of detecting that the type of obstacle is a predefined fixed object type, which includes, but is not limited to, fences, walls, and ornamental plants, and it can be assumed that the height of the predefined fixed object type is sufficient to prevent a person from climbing over it and that a person cannot threaten the vehicle from above the obstacle. Thus, once it is determined that the positional relationship between the obstacle and the vehicle in at least one target direction satisfies predefined positional conditions, it can be assumed that a person cannot enter between the obstacle and the vehicle, the vehicle is safe in the target direction, and the image channel corresponding to at least one target direction can be turned off.

[0048] According to the technical configuration of the embodiment of this disclosure, when Sentry Mode is activated, an initial image corresponding to each image channel is acquired, and the vehicle's environmental information is analyzed to identify obstacles present outside the vehicle. If the positional relationship between the obstacle and the vehicle in a specific target direction satisfies preset positional conditions, the image channel corresponding to that target direction is turned off. In this manner, continuous image acquisition and processing in directions with no or extremely low risk can be effectively avoided, significantly reducing power consumption, extending the monitoring time while the vehicle is parked, and improving the practicality and user experience of Sentry Mode.

[0049] Figure 4A is a schematic diagram of the positional relationship between an obstacle and a vehicle according to one exemplary embodiment of the present disclosure, and Figure 4B is a schematic diagram of the positional relationship between an obstacle and a vehicle according to another exemplary embodiment of the present disclosure.

[0050] In one exemplary embodiment, it is detected that the environmental information includes multiple obstacles outside the vehicle. Referring to Figure 4A, there are obstacles to the left and in front of vehicle D, with obstacle A located in the target direction in front of vehicle D, and obstacle B located in the direction to the left of the vehicle. Once the positional relationship between obstacle A and vehicle D is determined, the positional relationship between obstacle A and vehicle D in front of the vehicle is determined. The positional relationship between obstacle B on the left side of the vehicle and vehicle D is determined, and it can be determined whether the positional relationship satisfies a preset positional condition. For example, if the projection of obstacle A onto the front of the vehicle completely covers the front portion of the vehicle, it can be considered that obstacle A completely shields vehicle D in front of the vehicle. If it is detected that the distance between obstacle A and vehicle D is smaller than a preset distance threshold, it can be considered that a person cannot enter between obstacle A and vehicle D. If obstacle A completely obscures vehicle D and a person cannot pass between obstacle A and vehicle D, then it can be considered that there is no threat in front of the vehicle. In this case, the positional relationship between obstacle A and vehicle D in front of the vehicle can be considered to satisfy the preset positional conditions, and the image channel in front of the vehicle can be turned off. By the same principle, if it is determined that the positional relationship between obstacle B and vehicle D on the left side of the vehicle does not satisfy the preset positional conditions, then the image channel on the left side of the vehicle can be left open.

[0051] In another exemplary embodiment, it is detected that there is one external obstacle in the environment, and referring to Figure 4B, the obstacle C is located diagonally in front of the vehicle D, and for example, the directions corresponding to each image channel include the front of the vehicle, the rear of the vehicle, the left side of the vehicle and the right side of the vehicle, in this case the initial images corresponding to the image channels for the front of the vehicle and the left side of the vehicle are part of the obstacle C, and therefore the target directions corresponding to the obstacle C include two: the front of the vehicle and the left side of the vehicle. It is determined whether the positional relationship between the obstacle C and the vehicle D in the front of the vehicle and the left side of the vehicle satisfies the preset positional conditions, and if the positional relationship between the obstacle C and the vehicle D in any of the target directions satisfies the preset positional conditions, the image channel corresponding to that target direction is turned off. For example, if the projection of the obstacle C toward the front of the vehicle completely covers the front portion of the vehicle, it can be considered that the obstacle C completely occludes the vehicle D in front of the vehicle. If it is detected that the distance between obstacle C and vehicle D in front of the vehicle is greater than a preset distance threshold, it can be assumed that a person could enter between obstacle C and vehicle D and potentially pose a threat to parts of the vehicle, such as the front. As can be seen from the above information, if obstacle C completely obscures vehicle D, but the distance between obstacle C and vehicle D is greater than a preset distance threshold, the positional relationship between obstacle C and vehicle D does not satisfy the preset positional conditions, and the image channel in front of the vehicle is not turned off.

[0052] The steps of detecting whether or not an obstacle exists outside the vehicle based on environmental information, and, if an obstacle exists, obtaining the positional relationship between the obstacle and the vehicle in at least one target direction corresponding to the obstacle, can be implemented by the following exemplary method.

[0053] In one feasible form, based on environmental information, it is determined whether or not an obstacle exists in the direction corresponding to each image channel, and assuming that an obstacle exists in at least one target direction, the target direction in which the obstacle exists and the positional relationship between the obstacle and the vehicle in the target direction are determined. In this embodiment, it is checked whether or not an obstacle exists in the direction corresponding to each image channel, and if an obstacle exists in one or more target directions, the positional information of the obstacle and the vehicle in the target direction is analyzed to ensure the independence of each direction, and a failure of obstacle detection in one direction (for example, due to poor quality of the initial image) does not affect the analysis of other directions.

[0054] In another feasible form, environmental information is used to detect whether or not an obstacle exists outside the vehicle. If an obstacle is detected outside the vehicle from the environmental information, the target direction in which the obstacle is located and the positional relationship between the obstacle and the vehicle in that target direction are determined based on the environmental information. In this embodiment, first, the environment around the vehicle is analyzed as a whole to determine in one step whether or not an obstacle exists outside the vehicle. If an obstacle exists, the environmental information is used to accurately determine one or more target directions in which the obstacle is located. The positional relationship between the obstacle and the vehicle is determined for each target direction. Global obstacle detection is completed in one step, and for complex obstacles spanning multiple directions, this embodiment can directly identify the overall contour of the obstacle from a global perspective and accurately determine the direction corresponding to the obstacle, its spatial positional relationship with the vehicle, etc.

[0055] Figure 5 is a schematic flowchart of a control method for starting and stopping Sentry Mode according to another exemplary embodiment of the present disclosure.

[0056] As shown in Figure 5, in one embodiment, the method of the present disclosure further includes steps S104 to S105 after step S102.

[0057] In step S104, if an obstacle is detected from the environmental information and the positional relationship between the obstacle and the vehicle in the target direction satisfies the pre-set positional conditions, an initial image corresponding to the target direction is determined.

[0058] According to the technical configuration of this step, if an obstacle is detected from environmental information to be present outside the vehicle, but the positional relationship between the obstacle and the vehicle in the target direction where the obstacle is located does not satisfy the pre-set positional conditions, an initial image corresponding to the target direction is determined, and it becomes easier to decide whether or not to turn off the image channel for the target direction corresponding to the initial image based on the subsequent initial image.

[0059] In step S105, in response to the initial image quality being unacceptable, the image channel in the target direction corresponding to the initial image is turned off.

[0060] Here, image quality refers to the quality of the initial image itself (e.g., sharpness), and poor image quality means that the image fails to meet the basic quality standards necessary for effective monitoring and analysis, such as blurring, overexposure, underexposure, or large areas of the image being obscured by a covering (e.g., most of the image appearing in the same or similar tone, such as black).

[0061] According to the technical configuration of this step, if it is detected that the image quality of the initial image is unacceptable, it can be considered that the image quality of the initial image is poor and effective monitoring, identification, and analysis cannot be performed. Therefore, the image channel in the target direction corresponding to the initial image can be turned off to reduce power consumption.

[0062] In the technical configuration of the embodiments of this disclosure, if an obstacle is detected outside the vehicle from environmental information, but the positional relationship between the obstacle and the vehicle in the target direction does not satisfy the preset positional conditions, there may be a risk to the vehicle in the target direction, and further inspection is performed to determine whether the quality of the initial image corresponding to the target direction is acceptable. If the quality of the initial image is unacceptable, it can be assumed that effective identification and analysis cannot be performed based on the initial image. Therefore, by turning off the image channel corresponding to the initial image, continuous and ineffective analysis of low-quality and worthless initial images can be avoided, thereby saving computing resources and power.

[0063] In one feasible configuration, if an obstacle is detected from environmental information and the positional relationship between the obstacle and the vehicle in the target direction satisfies pre-set positional conditions, an initial image corresponding to the target direction is determined. If the image quality of the initial image is satisfactory, the image channel for the target direction corresponding to the initial image is kept on, and the movement in the target direction is continuously monitored to detect hazards in a timely manner.

[0064] In one feasible configuration, when Sentry Mode is activated, if the image quality of the initial image is deemed acceptable, the image channel corresponding to the initial image is kept ON. Due to reasons such as changes in weather, at some point, the quality of the initial image collected by the camera corresponding to the image channel becomes poor, making effective monitoring and identification impossible. For example, 10 minutes after keeping the image channel corresponding to the initial image ON, the camera is obscured over a large area by snowfall. Therefore, by setting a first predetermined time and keeping the image channel corresponding to the initial image ON, the initial image at the current time can be acquired at the interval of the first predetermined time, the image quality of the initial image can be detected, and it can be determined in a timely manner whether the image quality of the latest initial image is acceptable or not. If the image quality of the initial image is unacceptable, the image channel corresponding to the initial image can be turned OFF to reduce unnecessary power consumption and improve the effectiveness of monitoring by Sentry Mode. Following the same principle, after turning OFF the image channel corresponding to the initial image, a second predetermined time can be set, and at the interval of the second predetermined time, the image channel can be turned ON again to acquire the initial image at the current time using the image channel, the image quality of the initial image can be detected, and based on the quality, it can be determined whether or not it is necessary to turn OFF the image channel.

[0065] Figure 6 is a schematic flowchart of a control method for starting and stopping Sentry Mode according to another exemplary embodiment of the present disclosure.

[0066] As shown in Figure 6, in one embodiment, the method of the present disclosure further includes steps S106 to S107 after step S102.

[0067] In step S106, if no obstacles are detected outside the vehicle from the environmental information, initial images corresponding to each direction outside the vehicle are determined.

[0068] Here, the phrase "when no obstacle is detected outside the vehicle" can mean that no obstacle exists outside the vehicle, or it can mean that it is not possible to determine whether or not an obstacle exists outside the vehicle from the environmental information acquired based on each initial image. For example, in situations where the initial image is blurry, it is not possible to determine whether or not an obstacle exists outside the vehicle.

[0069] According to the technical configuration of this step, if, after analyzing environmental information, it is determined that no obstacles are detected outside the vehicle, initial images from each direction outside the vehicle can be acquired and analyzed to provide a data basis for subsequent image quality analysis, thereby ensuring the effectiveness of the sentry mode in each direction.

[0070] In step S107, in response to the image quality of at least one initial image being unacceptable, the image channel in the direction corresponding to the initial image is turned off.

[0071] According to the technical configuration of this step, if the quality of the initial image in a certain direction is unsatisfactory, it can be considered that the initial image cannot effectively support the sentry mode's identification function. Therefore, the image channel in the direction corresponding to the initial image can be turned off to reduce power consumption due to unnecessary image acquisition and processing.

[0072] In the embodiments of this disclosure, if no obstacles are detected outside the vehicle from the environmental information, it is determined whether there are any image channels that can be turned off based on the quality of the initial image. If the quality of the initial image is unacceptable, power waste in sentry mode can be avoided by turning off the image channel in the direction corresponding to the initial image and turning off the invalid image channel.

[0073] In one feasible configuration, if no obstacles are detected outside the vehicle from the environmental information, initial images corresponding to each direction outside the vehicle are determined. If the image quality of the initial images is satisfactory, the image channel for the target direction corresponding to the initial image is kept on, and movement in the target direction is continuously monitored to detect hazards in a timely manner.

[0074] Figure 7 is a schematic flowchart of a method for determining image quality according to one exemplary embodiment of the present disclosure.

[0075] As shown in Figure 7, in one embodiment, steps S108 to S110 are further included before step S107, and the method for determining image quality in the embodiment of this disclosure may be before step S105. The following are specific solutions for steps S108 to S110.

[0076] In step S108, the image quality categories of multiple pixel points within a predefined central region of the initial image are obtained.

[0077] Here, the pre-defined central region is the central region defined in advance for the initial image, which is the core part of the initial image, and the image quality category of the pre-defined central region can be used as the image quality category of the initial image. The size and shape of the pre-defined central region can be set according to the actual situation; for example, if the camera taking the initial image is a fisheye camera, the pre-defined central region can be set to a circle. The image quality category refers to the pixel-level quality category (for example, categories such as low light due to insufficient ambient light, water marks due to water droplets on the camera, blurred images due to focus failure or camera shake, occlusion due to mud, snow, or attached objects on the camera, overexposure of the screen due to strong light, and normal).

[0078] According to the technical configuration of this step, in order to determine the overall image quality of a predetermined central region, the image quality categories of multiple pixel points included in the predetermined central region within the initial image are obtained.

[0079] In step S109, based on the image quality categories of multiple pixel points, a target pixel point for a predetermined image quality category is determined from among the multiple pixel points.

[0080] Here, the pre-set image quality category is a pre-set image quality category and may include abnormal categories such as low light, water spots, blur, occlusion, and overexposure.

[0081] According to the technical configuration of this step, target pixel points belonging to a predetermined image quality category are selected from pixel points within a predetermined central region. Since these target pixel points affect image quality, they can be used as the basis for determining whether or not the image quality is acceptable.

[0082] In step S110, the initial image quality is determined to be unacceptable if the ratio of the number of target pixel points to the total number of pixel points in a preset central region is greater than a preset threshold.

[0083] Here, the pre-set threshold can be set according to the actual situation, and in the embodiments of this disclosure, the pre-set threshold is not specifically limited; for example, the pre-set threshold can be 0.8.

[0084] According to the technical configuration of this step, if the ratio of the number of target pixel points to the total number of pixel points in a preset central region is greater than a preset threshold, it indicates that the pixel points in most of the preset central region belong to the abnormal category, and it can be determined that the image quality of the initial image is unacceptable based on the assumption that the image quality of the preset central region is unacceptable. By converting this into a ratio index that can calculate whether the image quality is unacceptable, the accuracy of turning off the image channel corresponding to the initial image based on the unacceptable image quality of the initial image becomes higher.

[0085] In the technical configuration of the embodiments of this disclosure, the initial image is quantitatively determined to be acceptable or unacceptable by pixel-level image quality analysis. Specifically, the image quality category of pixel points within a preset central region of the initial image is obtained, target pixel points belonging to the preset image quality category are selected, and the number of target pixel points is compared with the total number of pixel points within the preset central region. This allows for a unified and reproducible standard for judging image quality, thereby improving the reliability of decision-making. Based on pixel-level image quality classification, multiple complex image quality problems such as occlusion, blurring, overexposure, and low light can be addressed simultaneously, and image channels that cannot be effectively monitored and analyzed due to unacceptable image quality can be accurately identified.

[0086] Figure 8 is a schematic flowchart of a method for acquiring image quality categories according to one exemplary embodiment of the present disclosure.

[0087] As shown in Figure 8, in one embodiment, step S108 may include steps S1080 and S1081.

[0088] In step S1080, the trained image quality classification model is used to classify the initial image to obtain the image quality category for each pixel point in the initial image.

[0089] Here, the image quality classification model can be trained using the first sample image for each image quality category and the image quality category label corresponding to the first sample image. Image quality category labels include, but are not limited to, low-light labels, water stain labels, occlusion labels, blur labels, and normal labels. This training method ensures high accuracy and reliability of the classification results of the image quality classification model. The image quality classification model can perform pixel-level image quality classification on the input image to obtain the image quality category for each pixel point of the input image. Image quality classification models include, but are not limited to, fully convolutional neural networks (FCNs) and recurrent neural networks (RNNs).

[0090] According to the technical configuration of this step, a trained image quality classification model can be used to classify the image quality of the initial image and obtain the image quality category for each pixel point in the initial image, thereby easily obtaining the image quality category for the pixel points in a pre-defined central region in a subsequent step.

[0091] In step S1081, the image quality categories of multiple pixel points within a pre-defined central region of the initial image are obtained.

[0092] According to the technical configuration of this step, the image quality categories of multiple pixel points within a predetermined central region are obtained from the image quality category of each pixel point in the acquired initial image.

[0093] According to the technical configuration of the embodiment of this disclosure, a trained image quality classification model is used to perform pixel-level image quality classification on the entire initial image to obtain the image quality category for each pixel point. By easily reading the image quality category for each pixel point within a pre-set central region, the quality status of core regions requiring attention can be quickly identified, improving the efficiency and comprehensiveness (inclusiveness) of the processing.

[0094] Figure 9 is a schematic diagram of the positional relationship between an obstacle and a vehicle according to another exemplary embodiment of the present disclosure.

[0095] In one exemplary embodiment, the pre-set positional conditions include whether the obstacle completely obscures the vehicle in the target direction, and whether the distance between the obstacle and the vehicle in the target direction is less than a pre-set distance threshold.

[0096] The pre-set positional conditions include two criteria, enabling adaptive activation and deactivation of the sentry mode image channel through the determination of a dual physical spatial relationship. When one side of the vehicle is completely obscured by an obstacle and the vehicle is very close to the obstacle, it can be assumed that there is no threat in that direction, and continuous detection is meaningless. However, conventional systems would still operate continuously, leading to power waste. In the examples of this disclosure, the pre-set positional relationship limits whether the obstacle completely obscures the vehicle and whether the distance between the obstacle and the vehicle is less than a pre-set distance threshold. If the positional relationship between the obstacle and the vehicle satisfies the pre-set positional relationship, the image channel in the direction where the obstacle is located can be turned off to reduce power waste.

[0097] As shown in Figures 9(1) to 9(3), the obstacle E is located in front of the vehicle D. Figure 9(1) shows the case where the obstacle E completely obscures the vehicle D, while Figures 9(2) and 9(3) show the case where the obstacle E does not completely obscure the vehicle D.

[0098] In one exemplary embodiment, the distance between the obstacle and the vehicle may be the longest distance between the obstacle and the vehicle, or the average of the distances between the obstacle and several preset positions on the vehicle. For example, if obstacle E and the vehicle are parallel, the vertical distance between obstacle E and the vehicle can be determined. Alternatively, for example, distance measurement points for the vehicle may be pre-set in each direction. If the target direction is in front of the vehicle, the center points of the two headlights and the center point of the license plate may be set as distance measurement points. The distance between the center points of the two headlights and the center point of the license plate and the obstacle may be obtained, and then the average of the three distance values ​​may be taken to determine the distance between the obstacle and the vehicle. Naturally, this example is merely one possible example and does not limit the technical configuration of the present disclosure in any way.

[0099] For example, whether an obstacle completely obscures a vehicle in front of it depends on the length and position of the obstacle. As shown in Figure 9(2), if the projection length of obstacle E onto the front of the vehicle is greater than the width of vehicle D, then it is determined whether obstacle E completely obscures vehicle D based on the relative position of obstacle E and vehicle D. For example, a coordinate system is constructed with vehicle D as the reference point, and the positional relationship between vehicle D and obstacle E is determined based on the horizontal and vertical coordinates. The coordinates (X21,Y21) and (X22,Y22) of both ends of obstacle E in front of the vehicle are obtained, and the value of |X22-X21| is the projection length of the obstacle onto the front of the vehicle. Then, the coordinates (x11,Y11) and (x12,Y12) of both ends of vehicle D are obtained, and the value of |x12-x11| is the width of vehicle D. Therefore, if |X22-X21|>|x12-x11|, then the projection length of obstacle E onto the front of the vehicle is greater than the width of vehicle D. If X22 > x12 and X21 > x11, then we can conclude that the obstacle E is located to the right and in front of vehicle D and does not completely obscure vehicle D. Here, the coordinates of both ends of vehicle D can refer to the widest point of the vehicle body, for example, the outermost part of the external rearview mirrors on both sides of vehicle D. As shown in Figure 9 (3), if the length of the projection of obstacle E onto the front of the vehicle is less than or equal to the width of vehicle D, then we can conclude that obstacle E cannot completely obscure vehicle D.

[0100] For example, a laser radar positioning method can be used to determine the positional relationship between an obstacle and a vehicle. Specifically, a laser radar is installed around the vehicle. The laser radar in front of the vehicle measures information such as the distance, direction, and reflectance of the obstacle to generate a three-dimensional point cloud model. This model allows for the acquisition of information such as the specific position of the obstacle in space, the relative position of the obstacle and the vehicle, and the outer contour of the obstacle. It also allows for the acquisition of information such as whether the obstacle completely obscures the vehicle and the distance between the obstacle and the vehicle, thereby determining the positional relationship between the obstacle and the vehicle.

[0101] In one exemplary embodiment, referring to Figure 4B, when the positions of obstacle C and vehicle D form a certain angle, obstacle C is located diagonally in front of vehicle D, and the target direction corresponding to obstacle C includes the front and left side of the vehicle. Therefore, when determining whether obstacle C completely obscures vehicle D in the direction in which obstacle C is located, the determination includes two directions: specifically, whether obstacle C completely obscures vehicle D in front of the vehicle, and whether obstacle C completely obscures vehicle D on the left side of the vehicle. As shown in Figure 4B, obstacle C completely obscures vehicle D in front of the vehicle, but obstacle C does not completely obscure vehicle D on the left side of the vehicle. Furthermore, the distance between obstacle C and vehicle D can be the maximum distance between obstacle C and the vehicle.

[0102] For example, the length of the projection of an obstacle onto the front of the vehicle is obtained, and if the projection length is greater than the width of the vehicle, it is determined whether the obstacle completely obstructs the vehicle based on the relative position of the obstacle and the vehicle. For details on determining whether the obstacle completely obstructs the vehicle based on the relative position of the obstacle and the vehicle, please refer to the previously described embodiment, and a detailed explanation will be omitted here. Naturally, if the projection length of the obstacle is less than or equal to the width of the vehicle, it can be determined that the obstacle does not completely obstruct the vehicle.

[0103] In one implementable form, the length of an obstacle can be determined based on environmental information obtained from each initial image and can also be understood as the length of the obstacle within the range that can be captured by the vehicle's camera. For example, if the obstacle is a wall, the vehicle's camera can only capture a portion of the wall, and the length of the obstacle in the embodiment of this disclosure is the length of only the captured portion of the wall.

[0104] Figure 10 is a schematic diagram of the length of an obstacle according to one exemplary embodiment of the present disclosure.

[0105] To further illustrate the size of the obstacle in the embodiments of this disclosure, as shown in Figure 10, in the camera field of view corresponding to each image channel, i.e., in the sector regions 11 to 14, the length of the obstacle F is L2, not the full length L3 of the obstacle. Based on the length L2, the size relationship between the obstacle and the width of the vehicle is determined.

[0106] Figure 11 is a schematic flowchart of a method for determining the relative position between an obstacle and a vehicle according to one exemplary embodiment of the present disclosure.

[0107] As shown in Figure 11, in one embodiment, the method of the present disclosure further includes steps S111 to S115 after step S102.

[0108] In step S111, a trained obstacle detection model is used to detect obstacles from a global overview map corresponding to environmental information and obtain the detection results.

[0109] Here, the global overhead view is obtained by splicing initial images from multiple image channels. For example, initial images are acquired using surround-view fisheye cameras on the front, rear, left, and right sides of the vehicle. Distortion correction is applied to the initial images, a homography matrix (H) is constructed based on the camera imaging model, and local overhead views are obtained in each direction by mapping the image pixel coordinates (u,v) to the ground plane coordinates (X,Y) = H-1(u,v) using inverse perspective transformation. Geometric alignment and color fusion are performed on the overlapping regions of the projection results (i.e., local overhead views) in each direction to generate a global overhead view centered on the vehicle. The global overhead view can provide an overhead view coordinate system as a unified overhead space feature.

[0110] For example, the homography matrix (H) is given by equation (1) below.

number

[0111] Here, s is the scale factor, K is the camera intrinsic parameter matrix, R is the rotation matrix, and t is the translation vector.

[0112] Obstacle detection models can be trained using second sample images of various obstacles and obstacle labels corresponding to those second sample images. Obstacle labels include, but are not limited to, walls, bollards, fences, and potted plants. Detection results may include whether or not an obstacle was detected from a global overview, the target direction in which the obstacle exists, the location information of the obstacle, and of course, the type of obstacle. Obstacle detection models include, but are not limited to, convolutional neural network models.

[0113] In step S111, the overhead view provides a god view, resolving overlap issues caused by different camera viewpoints, thereby making obstacle detection and subsequent geometric relationship analysis more accurate and intuitive. The trained obstacle detection model can detect obstacles from a global overhead view corresponding to environmental information, automatically and in real time identifying multiple types of obstacles, and is highly adaptable and accurate as it does not require manual rule setting.

[0114] In step S112, if the detection results include the presence of an obstacle outside the vehicle, the target direction of the obstacle and the location information of the obstacle are determined based on the detection results.

[0115] Here, the target direction in which an obstacle exists includes multiple cases. Referring to Figures 4A, 4B, and 9, the target direction in which obstacle C exists includes two locations: in front of the vehicle and to the left of the vehicle, while the target direction in which obstacle E exists is only in front of the vehicle.

[0116] According to this embodiment, if the detection result includes the presence of an obstacle outside the vehicle, the detected obstacle is associated with a direction corresponding to a specific image channel to obtain the specific position of the obstacle in the overhead coordinate system.

[0117] In this step, the specific target of the risk analysis is clarified. For example, since it has been identified that the obstacle is located on the left side of the vehicle, all subsequent analyses will focus on the left side, providing clear objectivity for decision-making.

[0118] In one implementable form of this disclosure, the detection result further includes the type of obstacle, and if the type of obstacle is a predefined fixed object type, the height of the obstacle can be considered sufficient to prevent a person from climbing over it. Thus, the target direction in which the obstacle exists and the location information of the obstacle are determined to facilitate subsequent determination of the positional relationship between the vehicle and the obstacle.

[0119] In step S113, the vehicle's position information, vehicle size information, and obstacle size information are determined based on the global overview.

[0120] Here, vehicle size information includes the vehicle's length and width. Obstacle size information refers to the size information on the side closest to the vehicle; see Figures 4A, 4B, 9, and 10. In the embodiments of this disclosure, obstacle size information is determined based on the global overview obtained from each initial image.

[0121] According to the embodiment of this step, vehicle position information, vehicle size information, and obstacle size information can be obtained in the same coordinate system of the overhead view. The global overhead view eliminates problems such as perspective distortion, and the contours, sizes, and relative positional relationships of vehicles and obstacles can be processed quantitatively, leading to more accurate subsequent decisions.

[0122] In step S114, it is determined whether the obstacle completely obscures the vehicle in the target direction, based on the location information of the obstacle, the size information of the obstacle, the location information of the vehicle, and the size information of the vehicle.

[0123] According to the embodiment of this step, the relative positional relationship between the vehicle and the obstacle can be obtained based on the positional information of the obstacle and the positional information of the vehicle. Based on the relative positional relationship between the obstacle and the vehicle, the size information of the obstacle and the size information of the vehicle, it can be determined whether or not the obstacle completely obscures the vehicle in the target direction.

[0124] In one selectable embodiment, referring to Figure 9(1), whether or not obstacle E completely obscures vehicle D in the overhead coordinate system can be determined based on the coordinate information of obstacle E and vehicle D. For example, the horizontal coordinates of obstacle E and vehicle D can be used to determine whether or not obstacle E completely obscures vehicle D, and X11<x11かつX12> A x12 configuration indicates that obstacle E completely shields vehicle D. Naturally, this is merely an example and does not limit the technical configurations of the embodiments of this disclosure.

[0125] In step S115, based on the location information of the obstacle and the location information of the vehicle, it is determined whether the distance between the obstacle and the vehicle in the target direction is smaller than a preset distance threshold.

[0126] Here, the pre-set distance threshold provides a configurable safety parameter that can be adjusted according to different vehicle types and user preferences, balancing energy efficiency with safety redundancy, and this disclosure does not specifically limit the settings of the pre-set distance threshold.

[0127] According to this embodiment, based on the location information of the obstacle and the location information of the vehicle, it is determined whether the distance between the obstacle and the vehicle in the target direction is smaller than a preset distance threshold, and if a situation is identified where the obstacle is in close proximity to the vehicle, the adjacent physical space greatly restricts the potential for activity of the threat.

[0128] In the embodiments of this disclosure, a trained obstacle detection model detects obstacles from a global overview corresponding to environmental information and obtains detection results. If the detection results include the presence of an obstacle outside the vehicle, the target direction in which the obstacle exists and the location information of the obstacle are obtained. Then, based on the global overview, the vehicle's location information, vehicle size information, and obstacle size information are obtained. Subsequently, based on the obtained information, it is determined whether the obstacle completely obscures the vehicle in the target direction and whether the distance between the obstacle and the vehicle is smaller than a preset distance threshold. A dual-decision mechanism determines whether the vehicle is safe in the target direction. If the vehicle is safe, the image channel corresponding to the target direction can be turned off, thereby reducing power waste.

[0129] The solutions relating to this disclosure are not limited to the embodiments mentioned above.

[0130] [Example device] The above describes a control method for starting and stopping Sentry Mode according to an embodiment of the present disclosure. The control device for starting and stopping Sentry Mode may include corresponding hardware and software for realizing hardware functions in order to implement each function that performs this Sentry Mode starting and stopping control method.

[0131] As will be readily apparent to those skilled in the art, each embodiment of the disclosure can be implemented in hardware form or in a software-driven hardware configuration, in combination with the steps of the Sentry Mode activation / deactivation control methods described in each embodiment of the disclosure. Whether a function is performed in hardware or in a software-driven hardware configuration depends on the specific application and design constraints of the technical configuration. While experts in the art may implement the described functions using different methods for each specific application, such implementations do not exceed the scope of the disclosure.

[0132] Figure 12 is a schematic diagram of a control device for starting and stopping Sentry Mode according to one exemplary embodiment of the present disclosure.

[0133] As shown in Figure 12, in one embodiment, the Sentry Mode Start / Stop Control Device 100 is The system includes an image acquisition component 110 located outside the vehicle, which includes multiple cameras 111 configured to collect initial images of the outside of the vehicle with a camera 111 corresponding to an image channel when Sentry mode is activated, and one or more processors 120 that, by executing instructions stored in memory, acquire environmental information of the vehicle based on the initial images corresponding to each image channel, and in response to the detection from the environmental information that an obstacle exists outside the vehicle and that the positional relationship between the obstacle and the vehicle in at least one target direction satisfies a preset positional condition, turn off the image channel corresponding to at least one target direction.

[0134] In the technical configuration of the embodiments of this disclosure, the image acquisition component 110 acquires an initial image corresponding to each image channel when Sentry Mode is activated, and one or more processors 120 analyze the vehicle's environmental information to identify obstacles present outside the vehicle. If the positional relationship between the obstacle and the vehicle in a particular target direction satisfies preset positional conditions, the image channel corresponding to that target direction is turned off. This method effectively avoids continuous image acquisition and processing in directions with no or very low risk, significantly reducing power consumption, extending the monitoring time while the vehicle is parked, and improving the practicality and user experience of Sentry Mode.

[0135] In one exemplary embodiment, after acquiring vehicle environmental information based on the initial image corresponding to each image channel, the processor 120: The system is configured to execute instructions stored in memory, and if the presence of an obstacle outside the vehicle is detected from the environmental information and the positional relationship between the obstacle and the vehicle in the target direction satisfies preset positional conditions, an initial image corresponding to the target direction is determined, and in response to the image quality of the initial image being unacceptable, an operation is performed to turn off the image channel in the target direction corresponding to the initial image.

[0136] In one exemplary embodiment, after acquiring vehicle environmental information based on the initial image corresponding to each image channel, the processor 120: The system is configured to execute instructions stored in memory, and if no obstacles are detected outside the vehicle from the environmental information, to determine initial images corresponding to each direction outside the vehicle, and in response to at least one initial image having unacceptable image quality, to perform an operation to turn off the image channel for the direction corresponding to the initial image.

[0137] In one exemplary embodiment, in response to the image quality of at least one initial image being unacceptable, before turning off the image channel in the direction corresponding to the initial image, the processor 120: The system is configured to execute instructions stored in memory to obtain the image quality categories of multiple pixel points within a preset central region of an initial image, determine target pixel points for a preset image quality category from the multiple pixel points based on the image quality categories of the multiple pixel points, and determine that the image quality of the initial image is unacceptable in response to the ratio of the number of target pixel points to the total number of pixel points in the preset central region being greater than a preset threshold.

[0138] In one exemplary embodiment, the processor 120 is: The system is configured to execute instructions stored in memory to perform image quality classification on the initial image using a trained image quality classification model, obtain the image quality category for each pixel point in the initial image, and obtain the image quality categories for multiple pixel points within a pre-set central region of the image.

[0139] In one exemplary embodiment, after acquiring vehicle environmental information based on the initial image corresponding to each image channel, the processor 120: The system is configured to execute instructions stored in memory to detect obstacles from a global overview corresponding to the environmental information using a trained obstacle detection model and obtain detection results. If the detection results include the presence of an obstacle outside the vehicle, the system determines the target direction in which the obstacle is located and the location information of the obstacle based on the detection results. Based on the global overview, it determines the vehicle's location information, the vehicle's size information, and the obstacle's size information. Based on the obstacle's location information, the obstacle's size information, the vehicle's location information, and the vehicle's size information, it determines whether the obstacle completely obscures the vehicle in the target direction. Based on the obstacle's location information and the vehicle's location information, it determines whether the distance between the obstacle and the vehicle in the target direction is smaller than a preset distance threshold.

[0140] [Example electronic device] Figure 13 is a schematic diagram of an electronic device according to one exemplary embodiment of the present disclosure, the electronic device 1300 including at least one processor 1310 and memory 1320.

[0141] The processor 1310 may be a central processing unit (CPU) or another form of processing unit having data processing capability and / or instruction execution capability, and may control other components in the electronic device 1300 to perform a desired function.

[0142] The memory 1320 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. The computer-readable storage media may store one or more computer program instructions, and the processor 1310 can implement the Sentry Mode startup / shutdown control method and / or other desired functions in each embodiment of the present disclosure by executing one or more computer program instructions.

[0143] As an example, the electronic device 1300 may further include input devices 1330 and output devices 1340 that are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0144] This input device 1330 may include, for example, a keyboard, a mouse, or the like.

[0145] This output device 1340 can output various types of information to the outside, and this output device 1340 may include, for example, a display, speaker, printer, communication network, and remote output devices connected thereto.

[0146] For simplicity, Figure 13 shows only some of the components relevant to this disclosure in the electronic device 1300, omitting components such as buses and input / output interfaces. Beyond that, the electronic device 1300 may further include any other appropriate components depending on the specific application.

[0147] [Examples of computer program products and computer-readable storage media] Embodiments of this disclosure provide a computer program product including computer program instructions, in addition to the methods and apparatus described above. When the computer program instructions are executed by a processor, the processor is caused to perform the steps of the Sentry Mode Start-up / Shut-Down control method in the various embodiments of this disclosure described in the “Exemplary Methods” portion above.

[0148] Computer program products can be created using one or any combination of programming languages ​​to produce program code for performing the operations of the embodiments of this disclosure, including object-oriented programming languages ​​such as Java and C++, and traditional procedural programming languages ​​such as the C language or similar programming languages. The program code may run entirely on a user computing device, partially on a user device, run as a standalone software package, run partially on a user computing device and partially on a remote computing device, or run entirely on a remote computing device or a server.

[0149] Furthermore, embodiments of this disclosure provide a computer-readable storage medium in which computer program instructions are stored. When the computer program instructions are executed by the processor, the processor is caused to perform the steps of the Sentry Mode Start-up / Shut-down control method in the various embodiments of this disclosure described in the “Exemplary Methods” portion above.

[0150] Any combination of one or more readable media can be used as a computer-readable storage medium. A readable medium can be a readable signal medium or a readable storage medium. A readable storage medium can include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any combination thereof. More specific examples (non-exclusive list) of readable storage media include electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0151] While the basic principles of this disclosure have been explained above with reference to specific examples, the advantages, merits, and effects mentioned in this disclosure are merely illustrative and not limiting, and these advantages, merits, and effects are not necessarily present in every example of this disclosure. Furthermore, the specific details of the above disclosure are merely illustrative and easy-to-understand effects and are not limiting, and the above details do not necessarily limit this disclosure to being realized by the above specific details.

[0152] Those skilled in the art can make various modifications and alterations to the present disclosure without departing from the spirit and scope of the present application. Thus, if such modifications and alterations of the present application fall within the claims of the present disclosure and the equivalent art thereto, the present disclosure also includes such modifications and alterations.

Claims

1. A Sentry Mode Start / Stop Control Method, wherein each step is executed by a Sentry Mode Start / Stop Control Device, When Sentry mode is activated, there is a step to acquire an initial image corresponding to each image channel, A step of acquiring vehicle environmental information based on the initial image corresponding to each image channel, The process includes the step of turning off an image channel corresponding to the at least one target direction in response to the detection from the environmental information that an obstacle exists outside the vehicle and that the positional relationship between the obstacle and the vehicle in at least one target direction satisfies a preset positional condition, A control method for starting and stopping Sentry Mode, characterized by the following features.

2. After the step of acquiring vehicle environmental information based on the initial image corresponding to each image channel, the Sentry Mode Start / Stop control method is as follows: If the presence of an obstacle outside the vehicle is detected from the environmental information and the positional relationship between the obstacle and the vehicle in the target direction satisfies a predetermined positional condition, the steps include determining an initial image corresponding to the target direction. The further step includes turning off the image channel in the target direction corresponding to the initial image in response to the initial image quality being unsatisfactory, The Sentry Mode Start-up / Stop-Down Control Method according to feature 1.

3. After the step of acquiring vehicle environmental information based on the initial image corresponding to each image channel, the Sentry Mode Start / Stop control method is as follows: If no obstacle is detected outside the vehicle from the environmental information, the steps include determining initial images corresponding to each direction outside the vehicle, The process further includes the step of turning off an image channel in the direction corresponding to the initial image in response to the image quality of at least one initial image being unacceptable. The Sentry Mode Start-up / Stop-Down Control Method according to feature 1.

4. In response to the image quality of at least one initial image being unacceptable, the Sentry Mode Start / Stop control method, before the step of turning off the image channel in the direction corresponding to the initial image, The steps include obtaining the image quality categories of multiple pixel points within a predefined central region of the initial image, A step of determining a target pixel point for a predetermined image quality category from the plurality of pixel points based on the image quality categories of the plurality of pixel points, The step further includes determining that the image quality of the initial image is unacceptable in response that the ratio of the number of target pixel points to the total number of pixel points in the preset central region is greater than a preset threshold, The control method for starting and stopping Sentry Mode according to feature 3.

5. The step of obtaining the image quality categories of multiple pixel points within a predetermined central region in the initial image is: The steps include: performing image quality classification on the initial image using a trained image quality classification model to obtain the image quality category for each pixel point in the initial image; The steps include obtaining the image quality categories of multiple pixel points within a predetermined central region in the initial image, The control method for starting and stopping Sentry Mode according to feature 4.

6. The aforementioned preset position conditions include whether the obstacle completely obscures the vehicle in the target direction, and whether the distance between the obstacle and the vehicle in the target direction is less than a preset distance threshold. The Sentry Mode Start-up / Stop-Down Control Method according to feature 1.

7. After the step of acquiring environmental information of the vehicle based on the initial image corresponding to each image channel, the Sentry Mode Start / Stop control method is as follows: The steps include: using a trained obstacle detection model to detect obstacles from a global overview corresponding to the environmental information and obtaining the detection results; If the detection result includes the presence of an obstacle outside the vehicle, the steps include determining the target direction in which the obstacle is located and the position information of the obstacle based on the detection result, The steps include determining the vehicle's location information, the vehicle's size information, and the obstacle's size information according to the global overview diagram, A step of determining whether the obstacle completely obstructs the vehicle in the target direction based on the location information of the obstacle, the size information of the obstacle, the location information of the vehicle, and the size information of the vehicle. The further step includes determining whether the distance between the obstacle and the vehicle in the target direction is less than a preset distance threshold, based on the location information of the obstacle and the location information of the vehicle. The control method for starting and stopping the Sentry Mode according to feature 6.

8. An image acquisition component located outside the vehicle includes multiple cameras configured to collect initial images of the outside of the vehicle with the camera corresponding to the image channel when Sentry mode is activated, The system includes one or more processors that, by executing instructions stored in memory, acquire environmental information of the vehicle based on an initial image corresponding to each image channel, and, in response to the detection from the environmental information that an obstacle exists outside the vehicle and that the positional relationship between the obstacle and the vehicle in at least one target direction satisfies a preset positional condition, turn off the image channel corresponding to the at least one target direction. A control device for starting and stopping Sentry Mode, characterized by the above.

9. An electronic device comprising one or more processors and memory in which computer program instructions are stored, When the computer program instruction is executed by the processor, the processor is instructed to execute the Sentry Mode startup / shutdown control method described in any one of claims 1 to 7. An electronic device characterized by the following features.

10. A computer-readable storage medium in which computer program instructions are stored, When the computer program instruction is executed by the processor, the processor is instructed to execute the Sentry Mode startup / shutdown control method described in any one of claims 1 to 7. A computer-readable storage medium characterized by the following features.

Images