Nighttime risk avoidance method, device, equipment and storage medium

Abstract

The present invention relates to the technical field of wearable devices, and discloses a night-time danger avoidance method, apparatus, equipment, and storage medium. The method comprises: when detecting that the night-time light intensity is greater than a preset intensity threshold, identifying the current image to obtain the current object type; when the current object type is a vehicle type, judging based on monitoring parameters whether a target user has performed an evasive behavior within a preset time period; when the target user has not performed an evasive behavior within the preset time period, issuing a warning message and / or activating a lens color-changing property; through the above-mentioned method, judging based on monitoring parameters that the target user has not performed an evasive behavior within the preset time period, issuing a warning message and / or activating a lens color-changing property, thereby ensuring that a user is reminded when an abnormal situation occurs at night, so that the user can respond in a timely manner and avoid the occurrence of danger to the greatest extent.

Description

Technical Field

[0001] The present invention relates to the technical field of wearable devices, and in particular to a method, apparatus, device and storage medium for avoiding danger at night. Background Art

[0002] With the popularization of electronic products, more and more users like to use electronic products when walking on the road at night, for example, using mobile phones and tablets to play games, watch movies, etc. The above behaviors will make users lack awareness of real-time road conditions, and some drivers like to turn on high beams when driving on deserted roads at night. This behavior is particularly likely to make oncoming pedestrians dizzy. The above two situations are very likely to cause traffic accidents. In order to avoid the occurrence of the above traffic accidents, the current relevant risk avoidance method is to use reflective vests. However, when the driver turns on the high beams and the user is nearby, the user is not easy to be found, and reflective vests are generally not worn frequently as daily clothes. They can only play a role in special circumstances, and ordinary users will not wear them deliberately. Ultimately, when an abnormality occurs at night, it is still impossible to remind the user in time, resulting in frequent dangers.

[0003] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of the present invention is to provide a nighttime risk avoidance method, device, equipment and storage medium, aiming to solve the technical problem that the existing technology cannot promptly remind users of abnormal situations at night, resulting in frequent occurrence of dangers.

[0005] To achieve the above object, the present invention provides a method for avoiding danger at night, which comprises the following steps:

[0006] When it is detected that the nighttime light intensity is greater than a preset intensity threshold, identifying the current image to obtain the current object type;

[0007] When the current object type is a vehicle type, determining whether the target user has evasive behavior within a preset time period based on monitoring parameters;

[0008] If the target user does not dodge within a preset time period, an early warning message is issued and / or the lens color change property is activated.

[0009] Optionally, when detecting that the nighttime light intensity is greater than a preset intensity threshold, identifying the current image to obtain the current object type includes:

[0010] When it is detected that the nighttime light intensity is greater than a preset intensity threshold, the target camera device captures the object in front of the target user to obtain a current image;

[0011] The current image is identified using a preset image detection model to obtain the current object type.

[0012] Optionally, when the current object type is a vehicle type, determining whether the target user has an evasive behavior within a preset time period according to monitoring parameters includes:

[0013] When the current object type is a vehicle type, starting a warning state;

[0014] According to the monitoring parameters, the light intensity and light source position of the object in front, the rotation angle, movement position and current heart rate of the target user are obtained;

[0015] It is determined whether the target user has evasive behavior within a preset time period according to the light intensity, rotation angle, moving position and current heart rate.

[0016] Optionally, when the target user does not evade within a preset time period, issuing a warning message and / or initiating the lens color change property includes:

[0017] Determine the magnitude of the light source position change based on the light source position of the front object and the initial light source position;

[0018] If at least one of the following conditions is met: the light intensity of the object ahead is greater than the nighttime light intensity; the amplitude of the light source position change is less than a preset amplitude threshold; the rotation angle is less than a preset angle threshold; the moving position is not within a preset safety range; and the current heart rate is less than a preset heart rate threshold, it is determined that the target user has not engaged in evasive behavior within a preset time period and an emergency response state is initiated;

[0019] Sending a light warning message of target brightness and target frequency and / or activating the electrochromic change of the lenses of the AR glasses.

[0020] Optionally, after issuing the light warning information of the target brightness and target frequency and / or activating the lens color change property, the method further includes:

[0021] Get the current behavior status of the target user;

[0022] When the current behavior state is a non-dizzy state, determining whether the target user has an evasive behavior within a target time period;

[0023] When the target user has evasive behavior within the target time period, the emergency processing state is closed.

[0024] Optionally, when the current behavior state is a non-dizzy state, after determining whether the target user has an evasive behavior within a target time period, the method further includes:

[0025] If the target user does not evade during the target time period, the current image is analyzed to obtain the direction of the oncoming vehicle and environmental parameters;

[0026] An external sound warning message of a target frequency is sent out according to the direction of the oncoming vehicle and the environmental parameters.

[0027] Optionally, after issuing the foreign sound warning information of the target frequency according to the oncoming vehicle direction and the environmental parameters, the method further includes:

[0028] Turn off the emergency processing mode and continue to obtain nighttime light data;

[0029] When the intensity of the nighttime illumination data within the second preset time is greater than a preset intensity threshold, the lens color change attribute is reset, the light warning information is turned off, and an early warning prompt information is issued.

[0030] In addition, to achieve the above-mentioned purpose, the present invention further provides a nighttime escape device, which comprises:

[0031] A detection module, configured to identify the current image and obtain the current object type when detecting that the nighttime light intensity is greater than a preset intensity threshold;

[0032] a judgment module, configured to judge, when the current object type is a vehicle type, whether the target user has performed an evasive behavior within a preset time period based on monitoring parameters;

[0033] The early warning module is used to issue an early warning message and / or activate the lens color change property when the target user has evasive behavior within a preset time period.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also proposes a night-time avoidance device, which includes: a memory, a processor, and a night-time avoidance program stored on the memory and runnable on the processor, and the night-time avoidance program is configured to implement the night-time avoidance method described above.

[0035] In addition, to achieve the above-mentioned purpose, the present invention further proposes a storage medium, on which a nighttime risk avoidance program is stored. When the nighttime risk avoidance program is executed by a processor, the nighttime risk avoidance method described above is implemented.

[0036] The night-time danger avoidance method proposed in the present invention obtains the current object type by identifying the current image when detecting that the night-time light intensity is greater than a preset intensity threshold; when the current object type is a vehicle type, it is judged based on monitoring parameters whether the target user has dodged behavior within a preset time period; when the target user has not dodged behavior within the preset time period, an early warning message is issued and / or the lens color-changing property is activated; through the above-mentioned method, it is determined based on monitoring parameters that the target user has not dodged behavior within the preset time period, and an early warning message is issued and / or the lens color-changing property is activated, thereby ensuring that the user is reminded when an abnormal situation occurs at night, so that the user can respond in time and avoid the occurrence of danger to the greatest extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a structural diagram of a nighttime risk avoidance device in a hardware operating environment involved in an embodiment of the present invention;

[0038] Figure 2 This is a flow chart of a first embodiment of the nighttime risk avoidance method of the present invention;

[0039] Figure 3 This is a schematic structural diagram of AR glasses according to an embodiment of a nighttime risk avoidance method of the present invention;

[0040] Figure 4 This is a schematic diagram of the overall process of an embodiment of a nighttime risk avoidance method of the present invention;

[0041] Figure 5 This is a flow chart of a second embodiment of the nighttime risk avoidance method of the present invention;

[0042] Figure 6 A schematic diagram of a principle model for determining whether there is an evasive action according to an embodiment of a nighttime risk avoidance method of the present invention;

[0043] Figure 7 This is a schematic diagram of the functional modules of the first embodiment of the nighttime escape device of the present invention.

[0044] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0045] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0046] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of night-time risk avoidance equipment in the hardware operating environment involved in the embodiment of the present invention.

[0047] like Figure 1As shown, the night shelter device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may optionally also be a storage device independent of the aforementioned processor 1001.

[0048] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the night shelter equipment, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0049] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a nighttime risk avoidance program.

[0050] exist Figure 1 In the night escape device shown, the network interface 1004 is mainly used for data communication with the network integration platform workstation; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the night escape device of the present invention can be set in the night escape device, and the night escape device calls the night escape program stored in the memory 1005 through the processor 1001, and executes the night escape method provided by the embodiment of the present invention.

[0051] Based on the above hardware structure, an embodiment of the nighttime risk avoidance method of the present invention is proposed.

[0052] Reference Figure 2 , Figure 2 2 is a flow chart of the first embodiment of the nighttime risk avoidance method of the present invention.

[0053] In a first embodiment, the nighttime risk avoidance method includes the following steps:

[0054] Step S10: When it is detected that the nighttime light intensity is greater than a preset intensity threshold, the current image is identified to obtain the current object type.

[0055] It should be noted that the executor of this embodiment is a night-time risk avoidance device, and it can also be other devices that can achieve the same or similar functions, such as AR glasses, etc. This embodiment does not limit this. In this embodiment, AR glasses are used as an example for illustration.

[0056] Understandably, the reference Figure 3 , Figure 3 This is a structural diagram of AR glasses, which specifically includes a central processor for signal processing, peripheral devices including an RGB camera for collecting images of oncoming vehicles, a natural light sensor for detecting night light intensity, LED lights for warning oncoming vehicles, an inertial sensor for sensing user actions, and a speaker for reminding the target user. The speaker is located on the temple of the AR glasses, the inertial sensor is located on the temple of the AR glasses, and the RGB camera and natural light sensor are both located in the frame of the AR glasses.

[0057] It should be understood that night light intensity refers to the light intensity of night lights detected by the natural light sensor. When the night light intensity is greater than the preset intensity threshold, it indicates that the night light is strong light. At this time, the target camera device is synchronously started to capture the image of the object in front, and then the current object type is identified through the current image. The current object type refers to the type of the object in front of the target user.

[0058] Furthermore, step S10 includes: when it is detected that the night light intensity is greater than a preset intensity threshold, photographing the object in front of the target user through the target camera device to obtain a current image; and identifying the current image through a preset image detection model to obtain the current object type.

[0059] It can be understood that the current image refers to the image of the object in front of the target user. The target device camera can be an RGB camera. The preset image detection model refers to a model for identifying the type of object. The preset image detection model is built into the AR glasses. After the recognition is completed, the current object type is obtained.

[0060] Step S20: When the current object type is a vehicle type, it is determined based on monitoring parameters whether the target user has evasive behavior within a preset time period.

[0061] It can be understood that vehicle types include but are not limited to cars, motorcycles, and electric vehicles. After identifying the current object type, it is determined whether the current object type belongs to the vehicle type. If so, the early warning state is activated, and the monitoring parameters are used to continue to determine whether the user has evasive behavior within the preset time period. The monitoring parameters include the monitoring parameters of the object in front and the monitoring parameters of the target user. The preset time period can be 0.1s.

[0062] Furthermore, step S20 includes: when the current object type is a vehicle type, starting a warning state; obtaining the light intensity and light source position of the front object, the turning angle, moving position and current heart rate of the target user based on the monitoring parameters; and judging whether the target user has evasive behavior within a preset time period based on the light intensity, turning angle, moving position and current heart rate.

[0063] It should be understood that light intensity refers to the light intensity of the object in front at the current moment. Similarly, light source position refers to the source position of the light. The current intensity and light source position are monitoring parameters of the object in front. The rotation angle refers to the angle at which the target user rotates when the light appears. Similarly, the moving position refers to the position of the target user after moving when the light appears. The current heart rate refers to the heart rate of the target user. The rotation angle, moving position and current heart rate are monitoring parameters of the target user. Then, based on the light intensity, rotation angle, moving position and current heart rate, it is judged whether the target user has evasive behavior within the preset time period.

[0064] Step S30: When the target user does not evade within a preset time period, a warning message is issued and / or the lens color change property is activated.

[0065] It should be understood that when it is determined that the target user has not engaged in evasive behavior within a preset time period, in order to avoid accidents, the target user is reminded by a warning message and / or by activating the lens color-changing property. The warning message can be a high-brightness, high-frequency flashing red light by an LED light to remind objects in front to avoid pedestrians. The lens color-changing property is activated to avoid the influence of strong light on the target user's vision. The lens color-changing property can be the electrochromic property of the AR glasses lens.

[0066] Understandably, the reference Figure 4 , Figure 4Schematic diagram of the overall process, specifically: when it is detected that the night light intensity is greater than the preset intensity threshold, the RGB camera is started to take pictures, and the AR glasses enter the warning state. Then, in the warning state, it is judged whether the target user has evasive behavior within the preset time period based on the monitoring parameters collected by the inertial sensor. If so, the warning state is ended. If not, the emergency treatment state is started, and the electrochromic properties of the lens are started, the LED light flashes at high brightness and high frequency, and then the monitoring parameters collected by the inertial sensor are continued to be read, and it is judged whether the target user has evasive behavior within the preset time period. If so, the emergency treatment state is ended and the reset state is entered. If not, it is judged whether the target user is in a dizzy state. If so, the best evasive position is determined according to the current image, and the target user is reminded to evade through a high volume of the speaker. If the evasion is successful, the reset state is entered, and the night light ahead is continuously read. After determining that there is no vehicle ahead, the LED flashing is canceled, the electrochromic properties are reset, and the target user is reminded to be vigilant through voice.

[0067] This embodiment identifies the current image and obtains the current object type when it detects that the night-time light intensity is greater than a preset intensity threshold; when the current object type is a vehicle type, it is determined based on monitoring parameters whether the target user has evasive behavior within a preset time period; when the target user has not evaded behavior within the preset time period, an early warning message is issued and / or the lens color change property is activated; through the above-mentioned method, it is determined based on monitoring parameters that the target user has not evaded behavior within the preset time period, and an early warning message is issued and / or the lens color change property is activated, thereby ensuring that the user is reminded when an abnormal situation occurs at night, so that the user can respond in time and avoid the occurrence of danger to the greatest extent.

[0068] In one embodiment, if Figure 5 Based on the first embodiment, a second embodiment of the nighttime risk avoidance method of the present invention is proposed. Step S30 includes:

[0069] Step S301 : determining a light source position change amplitude according to the light source position of the front object and the initial light source position.

[0070] It should be understood that the initial light source position refers to the light source position when the night light appears for the first time, and the light source position change amplitude refers to the amplitude from the initial light source position to the light source position of the object in front. For example, the initial light source position is the middle position, and the light source position of the object in front is the side position, that is, the light source position change amplitude is determined based on the middle position and the side position.

[0071] Step S302: When at least one of the following conditions is met: the light intensity of the object in front is greater than the night light intensity, the amplitude of the change in the light source position is less than the preset amplitude threshold, the rotation angle is less than the preset angle threshold, the moving position is not within the preset safety range, and the current heart rate is less than the preset heart rate threshold, it is determined that the target user has no evasive behavior within the preset time period, and the emergency processing state is initiated.

[0072] It can be understood that the rotation angle and moving position can be detected by inertial sensors. After obtaining the light intensity of the object in front, the change amplitude of the light source position, the rotation angle, the moving position and the current heart rate, it is necessary to meet at least one of the following conditions: the light intensity of the object in front is greater than the night light intensity, the change amplitude of the light source position is less than the preset amplitude threshold, the rotation angle is less than the preset angle threshold, the moving position is not within the preset safety range, and the current heart rate is less than the preset heart rate threshold. If the light intensity of the object in front is greater than the night light intensity and the change amplitude of the light source position is less than the preset amplitude threshold, it indicates that the light intensity has not weakened. If the rotation angle is less than the preset angle threshold and the moving position is not within the preset safety range, it indicates that the target user has not moved. If the current heart rate is less than the preset heart rate threshold, it indicates that the target user has not been frightened, which indirectly reflects that the target user is not aware of the danger ahead. When at least one of the above conditions is met, it indicates that the target user has not dodged within the preset time period. At this time, the emergency processing state needs to be activated, and the above data will be continuously acquired in the early warning state until the target user is out of danger.

[0073] It should be understood that reference Figure 6 , Figure 6 A schematic diagram of a principle model for determining whether there is evasive behavior is shown as follows: There is a metal ball in a closed iron box. The movement of the sensor causes the metal ball to move, which in turn collides with the metal box wall and generates stress. The magnitude of the stress is used to determine the speed of the metal ball and the metal wall it collides with, thereby detecting the direction of movement. In the specific case of this embodiment, the target user may perform two body avoidance actions. One action is dodging, that is, quickly dodging to one side. In this case, the movement speed is relatively fast. In the model, the stress generated on the side wall is very high. In this case, the IMU will show a particularly sharp peak during the data transmission process. The other action is jumping, that is, dodging in a certain direction. In this case, the IMU will read motion data in two different directions. However, compared with movement in one direction, the "stress" is smaller, but the overall motion direction is definitely achieved by the Z-axis (vertical) direction + a certain horizontal direction. After obtaining these two different motion data, it can be accurately determined that the user is dodging, that is, the evasive behavior has occurred.

[0074] Step S303: Send out a light warning message of target brightness and target frequency and / or activate the lenses of the AR glasses to perform electrochromism.

[0075] It should be understood that if the target user does not dodge within the preset time period, in order to avoid accidents to the target user, a light warning message with target brightness and target frequency is emitted to remind the objects in front to avoid pedestrians. The target brightness can be 150LM, and the target frequency can be 5120HZ. For example, a red flashing light of 150LM and 5120HZ is played by an LED light, and the lenses of the AR glasses are activated for electrochromism at the same time. The electrochromism of the lenses relies on the AR glasses, and compared with other ordinary glasses, the time it takes to change color when encountering strong light is extremely short, for example, 0.7 milliseconds. The electrochromism of the lenses of the AR glasses avoids the influence of strong light on the target user's vision.

[0076] Furthermore, after step S303, it also includes: obtaining the current behavior state of the target user; when the current behavior state is a non-dizzy state, determining whether the target user has evasive behavior within the target time period; when the target user has evasive behavior within the target time period, closing the emergency processing state.

[0077] It can be understood that the current behavior state refers to the behavior state of the target user after experiencing light intensity greater than the preset intensity threshold. Then, it is determined whether the current behavior state is a dizziness state. If so, it indicates that the target user is no longer able to dodge independently. If not, it is continued to determine whether the target user has dodge behavior within the target time period. If so, the emergency handling state is closed. The target time period can be 0.2s.

[0078] Furthermore, when the current behavior state is a non-dizzy state, after determining whether the target user has evasive behavior within the target time period, it also includes: if the target user has no evasive behavior within the target time period, analyzing the current image to obtain the direction of the oncoming vehicle and environmental parameters; and issuing an external sound warning message of a target frequency according to the oncoming vehicle direction and the environmental parameters.

[0079] It should be understood that when it is determined that the target user does not have any evasive behavior within the target time period, the oncoming direction and environmental parameters are analyzed based on the current image. The oncoming direction may be the left side of the target user, and the environmental parameters refer to the environmental parameters where the target user is located, which may be grass, etc. Then, an external sound warning message of the target frequency is issued according to the oncoming direction and environmental parameters to remind the user to dodge safely. For example, when the oncoming direction is on the left and the environmental parameter on the right is grass, the user is reminded to dodge to the right side of the grass through the external sound warning message of the target frequency.

[0080] Furthermore, after issuing the external sound warning information of the target frequency according to the direction of the oncoming vehicle and the environmental parameters, it also includes: turning off the emergency processing state and continuously acquiring nighttime lighting data; when the intensity of the nighttime lighting data within the second preset time is greater than the preset intensity threshold, resetting the lens color change attribute, turning off the light warning information and issuing a warning prompt message.

[0081] It is understandable that after the external sound warning information of the target frequency is issued, the emergency processing state is turned off, and then the night light data is continuously obtained, and it is determined whether the intensity of the night light data within the second preset time is greater than the preset intensity threshold. If not, it indicates that no strong light is generated within the second preset time. At this time, the lens color change attribute will be reset, the light warning information will be turned off, and a warning prompt message will be issued. The warning prompt message can be "There are many unexpected situations on the current road section. Please do not walk with your head down, and pay attention to the vehicles coming ahead!" The device that plays the warning prompt message can be a speaker.

[0082] This embodiment determines the amplitude of the light source position change based on the light source position of the object in front and the initial light source position; when at least one of the following conditions is met: the light intensity of the object in front is greater than the night light intensity, the amplitude of the light source position change is less than a preset amplitude threshold, the rotation angle is less than a preset angle threshold, the moving position is not within a preset safety range, and the current heart rate is less than a preset heart rate threshold, it is determined that the target user has not performed any evasive behavior within the preset time period, and the emergency processing state is activated; a light warning message of target brightness and target frequency is issued and / or the lenses of the AR glasses are activated for electrochromic change; through the above method, if it is determined that the target user has not performed any evasive behavior within the preset time period, a light warning message of target brightness and target frequency is issued to remind oncoming vehicles to pay attention to avoid pedestrians and / or the lenses of the AR glasses are activated for electrochromic change to avoid the influence of strong light on the user's vision, so as to avoid danger to the target user.

[0083] In addition, an embodiment of the present invention further provides a storage medium on which a nighttime risk avoidance program is stored. When the nighttime risk avoidance program is executed by a processor, the steps of the nighttime risk avoidance method described above are implemented.

[0084] Since the storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be described one by one here.

[0085] In addition, refer to Figure 7 The embodiment of the present invention further provides a nighttime safety device, which includes:

[0086] The detection module 10 is configured to identify the current image and obtain the current object type when detecting that the nighttime light intensity is greater than a preset intensity threshold.

[0087] The judgment module 20 is configured to judge whether the target user has evasive behavior within a preset time period according to monitoring parameters when the current object type is a vehicle type.

[0088] The warning module 30 is used to issue a warning message and / or activate the lens color change property when the target user has evasive behavior within a preset time period.

[0089] This embodiment identifies the current image and obtains the current object type when it detects that the night-time light intensity is greater than a preset intensity threshold; when the current object type is a vehicle type, it is determined based on monitoring parameters whether the target user has evasive behavior within a preset time period; when the target user has not evaded behavior within the preset time period, an early warning message is issued and / or the lens color change property is activated; through the above-mentioned method, it is determined based on monitoring parameters that the target user has not evaded behavior within the preset time period, and an early warning message is issued and / or the lens color change property is activated, thereby ensuring that the user is reminded when an abnormal situation occurs at night, so that the user can respond in time and avoid the occurrence of danger to the greatest extent.

[0090] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0091] In addition, for technical details not fully described in this embodiment, please refer to the nighttime risk avoidance method provided in any embodiment of the present invention, and will not be repeated here.

[0092] In one embodiment, the detection module 10 is further used to photograph the object in front of the target user through a target camera device to obtain a current image when it detects that the night light intensity is greater than a preset intensity threshold; and identify the current image through a preset image detection model to obtain the current object type.

[0093] In one embodiment, the judgment module 20 is also used to activate a warning state when the current object type is a vehicle type; obtain the light intensity and light source position of the front object, the turning angle, moving position and current heart rate of the target user based on the monitoring parameters; and judge whether the target user has evasive behavior within a preset time period based on the light intensity, turning angle, moving position and current heart rate.

[0094] In one embodiment, the early warning module 30 is further used to determine the amplitude of the change in the light source position based on the light source position of the object in front and the initial light source position; when at least one of the following conditions is met: the light intensity of the object in front is greater than the night light intensity, the amplitude of the change in the light source position is less than a preset amplitude threshold, the rotation angle is less than a preset angle threshold, the moving position is not within a preset safety range, and the current heart rate is less than a preset heart rate threshold, it is determined that the target user has no evasive behavior within a preset time period, and an emergency processing state is initiated; a light warning message of target brightness and target frequency is issued and / or the lenses of the AR glasses are activated for electrochromic change.

[0095] In one embodiment, the early warning module 30 is also used to obtain the current behavior state of the target user; when the current behavior state is a non-dizzy state, it is determined whether the target user has evasive behavior within the target time period; when the target user has evasive behavior within the target time period, the emergency processing state is closed.

[0096] In one embodiment, the warning module 30 is further used to analyze the current image to obtain the direction of the oncoming vehicle and environmental parameters when the target user does not evade during the target time period; and to issue an external sound warning message of the target frequency according to the oncoming vehicle direction and the environmental parameters.

[0097] In one embodiment, the early warning module 30 is also used to turn off the emergency processing state and continuously obtain nighttime lighting data; when the intensity of the nighttime lighting data within the second preset time is greater than a preset intensity threshold, the lens color change attribute is reset, the light warning information is turned off, and an early warning prompt message is issued.

[0098] Other embodiments or implementation methods of the nighttime shelter device of the present invention can refer to the above-mentioned method embodiments, which will not be repeated here.

[0099] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0100] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0101] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, an integrated platform workstation, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0102] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for avoiding danger at night, characterized in that: The method for avoiding danger at night comprises the following steps: When it is detected that the nighttime light intensity is greater than a preset intensity threshold, the current image is identified to obtain the current object type; wherein the current image is an image obtained by photographing the object in front of the target user through the target camera device; When the current object type is a vehicle type, determining whether the target user has evasive behavior within a preset time period based on monitoring parameters; If the target user does not evade within a preset time period, a warning message is issued and / or the lens color change property is activated; When the current object type is a vehicle type, determining whether the target user has an evasive behavior within a preset time period according to the monitoring parameters includes: When the current object type is a vehicle type, starting a warning state; According to the monitoring parameters, the light intensity and light source position of the object in front, the rotation angle, movement position and current heart rate of the target user are obtained; It is determined whether the target user has evasive behavior within a preset time period based on the light intensity, rotation angle, moving position and current heart rate.

2. The nighttime risk avoidance method according to claim 1, wherein: When the nighttime light intensity is detected to be greater than a preset intensity threshold, the current image is identified to obtain the current object type, including: When it is detected that the nighttime light intensity is greater than a preset intensity threshold, the target camera device captures the object in front of the target user to obtain a current image; The current image is identified using a preset image detection model to obtain the current object type.

3. The nighttime risk avoidance method according to claim 1, wherein: When the target user does not evade within the preset time period, issuing a warning message and / or activating the lens color change property includes: Determine the magnitude of the light source position change based on the light source position of the front object and the initial light source position; If at least one of the following conditions is met: the light intensity of the object ahead is greater than the nighttime light intensity; the amplitude of the light source position change is less than a preset amplitude threshold; the rotation angle is less than a preset angle threshold; the moving position is not within a preset safety range; and the current heart rate is less than a preset heart rate threshold, it is determined that the target user has not engaged in evasive behavior within a preset time period and an emergency response state is initiated; Sending a light warning message of target brightness and target frequency and / or activating the electrochromic change of the lenses of the AR glasses.

4. The nighttime risk avoidance method according to claim 3, wherein: After issuing the light warning information of the target brightness and target frequency and / or starting the lenses of the AR glasses to perform electrochromism, the method further includes: Get the current behavior status of the target user; When the current behavior state is a non-dizzy state, determining whether the target user has an evasive behavior within a target time period; When the target user has evasive behavior within the target time period, the emergency processing state is closed.

5. The nighttime risk avoidance method according to claim 4, characterized in that: When the current behavior state is a non-dizzy state, after determining whether the target user has performed an evasive behavior within the target time period, the method further includes: If the target user does not evade during the target time period, the current image is analyzed to obtain the direction of the oncoming vehicle and environmental parameters; An external sound warning message of a target frequency is sent out according to the direction of the oncoming vehicle and the environmental parameters.

6. The nighttime risk avoidance method according to claim 5, characterized in that: After the foreign sound warning information of the target frequency is issued according to the oncoming vehicle direction and the environmental parameters, the method further includes: Turn off the emergency processing mode and continue to obtain nighttime light data; When the intensity of the nighttime illumination data within the second preset time is greater than a preset intensity threshold, the lens color change attribute is reset, the light warning information is turned off, and an early warning prompt information is issued.

7. A nighttime shelter, characterized in that: The nighttime safety device comprises: a detection module configured to identify a current image and determine a current object type when detecting that the nighttime light intensity is greater than a preset intensity threshold; wherein the current image is an image obtained by photographing an object in front of a target user using a target camera device; a judgment module, configured to judge, when the current object type is a vehicle type, whether the target user has performed an evasive behavior within a preset time period based on monitoring parameters; An early warning module, configured to issue an early warning message and / or activate the lens color change property when the target user exhibits evasive behavior within a preset time period; The judgment module is also used to activate the warning state when the current object type is a vehicle type; obtain the light intensity and light source position of the front object, the turning angle, moving position and current heart rate of the target user based on the monitoring parameters; and judge whether the target user has evasive behavior within a preset time period based on the light intensity, turning angle, moving position and current heart rate.

8. A nighttime shelter, characterized in that: The nighttime avoidance device includes: a memory, a processor, and a nighttime avoidance program stored in the memory and executable on the processor, wherein the nighttime avoidance program is configured to implement the nighttime avoidance method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a nighttime risk avoidance program, which, when executed by the processor, implements the nighttime risk avoidance method according to any one of claims 1 to 6.

Images