Cycling warning methods, devices, equipment and storage media

Abstract

This invention relates to the field of smart device technology and discloses a cycling warning method, device, equipment, and storage medium. The method includes: when a traffic control image is detected, determining the rate of change of the speed detection frame of a vehicle behind the target user; determining the current distance between the target user and the vehicle; and issuing a warning to the target user based on the rate of change of the speed detection frame and the current distance. Through this method, when a traffic control image is detected, the rate of change of the speed detection frame of the vehicle behind the target user is calculated using speed detection frame change parameters. Then, based on the rate of change of the speed detection frame and the current distance, it is determined whether the target user is in danger. If so, a warning is issued to the target user, thereby enabling timely warnings to the user and preventing danger.

Description

Technical Field

[0001] This invention relates to the field of smart device technology, and in particular to cycling warning methods, devices, equipment, and storage media. Background Technology

[0002] With the increasing awareness of health and environmental protection, cycling has become one of the best ways for people to travel. However, when cyclists pass through traffic intersections, obstructions such as buildings and pedestrians can affect the visibility of drivers of nearby vehicles, making it easy for drivers to overlook the presence of cyclists. On the other hand, traffic rules in some areas are not standardized enough, and the traffic flow between cyclists and vehicles is not coordinated enough. For example, right-turning vehicles are prone to collisions with cyclists going straight, causing danger.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a cycling warning method, device, equipment, and storage medium, aiming to solve the technical problem of how to provide timely warnings to users and avoid dangerous situations.

[0005] To achieve the above objectives, the present invention provides a cycling warning method, which includes the following steps:

[0006] When a traffic control image is detected, determine the rate of change of the speed detection box of the vehicle image behind the target user;

[0007] Determine the current distance between the target user and the vehicle.

[0008] The target user is given an early warning based on the rate of change of the speed detection frame and the current distance.

[0009] Optionally, before determining the rate of change of the speed detection box of the vehicle image behind the target user when detecting a traffic control image, the method further includes:

[0010] Obtain road images of the area in front of the target user's location;

[0011] Feature extraction is performed on the road image of the area ahead to obtain the road image features of the area ahead;

[0012] The road image features of the area ahead are identified using a target traffic control and identification model;

[0013] The identification results determine whether a traffic control image has been detected.

[0014] Optionally, determining the rate of change of the speed detection box of the vehicle image behind the target user when detecting a traffic control image includes:

[0015] When a traffic control image is detected, the rear-view camera of the smart device is activated;

[0016] The size of the current speed detection box on the rear-view camera device is obtained from the image of the vehicle behind the target user at the current moment.

[0017] The initial speed detection frame size of the image of the vehicle behind the target user at the initial moment is obtained on the rear-view camera device;

[0018] Calculate the change time of the velocity detection box based on the current time and the initial time;

[0019] Calculate the change in velocity detection box size based on the size of the previous velocity detection box and the initial velocity detection box size;

[0020] The rate of change of the speed detection frame of the vehicle behind the target user is calculated based on the change time and the change magnitude of the speed detection frame.

[0021] Optionally, determining the current distance between the target user and the driving vehicle includes:

[0022] The vehicle is detected using a target 3D detection model to obtain the vehicle's center coordinates, driving parameters, and attribute information in the target coordinate system.

[0023] The current distance between the target user and the vehicle is determined based on the center coordinates, driving parameters, and attribute information.

[0024] Optionally, the step of issuing a warning to the target user based on the rate of change of the speed detection frame and the current distance includes:

[0025] When the rate of change of the speed detection frame is greater than or equal to a preset rate of change threshold, it is determined whether the current distance is less than a preset safe distance threshold.

[0026] When the current distance is less than a preset safe distance threshold, the target user is alerted through the target component of the smart device.

[0027] Optionally, the target component includes a left-side component and a right-side component;

[0028] The step of issuing a warning to the target user via the target component of the smart device when the current distance is less than a preset safe distance threshold includes:

[0029] When the current distance is less than a preset safe distance threshold, the relative direction between the vehicle and the target user is determined;

[0030] When the relative direction is left, a vehicle icon flashes continuously on the left side of the smart device, and a warning message indicating danger on the left is issued.

[0031] When the relative direction is to the right, a vehicle icon flashes continuously on the right side of the smart device, and a warning message indicating that there is danger on the right side is issued.

[0032] Optionally, after the current distance is less than a preset safe distance threshold, the method further includes:

[0033] Obtain the current size of the traffic control image detection box and the previous size of the traffic control image detection box;

[0034] The rate of change of the traffic control image detection frame size is calculated based on the current traffic control image detection frame size and the previous traffic control image detection frame size.

[0035] When the rate of change of the size of the traffic control image detection box is less than the target rate of change threshold, the traffic control image is identified to obtain the road line that is allowed to pass ahead;

[0036] When the permitted road ahead is a right-turn lane, no warning is given to the target user.

[0037] Furthermore, to achieve the above objectives, the present invention also proposes a cycling warning device, the cycling warning device comprising:

[0038] The detection module is used to determine the rate of change of the speed detection box of the vehicle image behind the target user when a traffic control image is detected.

[0039] The determination module is used to determine the current distance between the target user and the moving vehicle;

[0040] The early warning module is used to issue an early warning to the target user based on the size of the speed detection box and the current distance.

[0041] In addition, to achieve the above objectives, the present invention also proposes a cycling warning device, which includes: a memory, a processor, and a cycling warning program stored in the memory and executable on the processor, the cycling warning program being configured to implement the cycling warning method as described above.

[0042] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a cycling warning program, which, when executed by a processor, implements the cycling warning method as described above.

[0043] The cycling warning method proposed in this invention determines the rate of change of the speed detection frame of the vehicle behind the target user when a traffic control image is detected; determines the current distance between the target user and the vehicle; and issues a warning to the target user based on the rate of change of the speed detection frame and the current distance. In this way, when a traffic control image is detected, the rate of change of the speed detection frame of the vehicle behind the target user is calculated using speed detection frame change parameters. Then, based on the rate of change of the speed detection frame and the current distance, it is determined whether the target user is in danger. If so, a warning is issued to the target user, thereby enabling timely warnings to the user and preventing danger. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of the structure of a cycling warning device in the hardware operating environment involved in the embodiments of the present invention;

[0045] Figure 2 This is a flowchart illustrating the first embodiment of the cycling warning method of the present invention;

[0046] Figure 3 This is a flowchart illustrating the second embodiment of the cycling warning method of the present invention;

[0047] Figure 4 This is a schematic diagram of the overall process of an embodiment of the cycling warning method of the present invention;

[0048] Figure 5 This is a schematic diagram of the functional modules of the first embodiment of the cycling warning device of the present invention.

[0049] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0050] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0051] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a cycling warning device in the hardware operating environment of an embodiment of the present invention.

[0052] like Figure 1As shown, the cycling warning 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. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0053] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the cycling warning device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0054] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a cycling warning program.

[0055] exist Figure 1 In the cycling warning device shown, the network interface 1004 is mainly used for data communication with the network integrated platform workstation; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the cycling warning device of the present invention can be set in the cycling warning device, and the cycling warning device calls the cycling warning program stored in the memory 1005 through the processor 1001 and executes the cycling warning method provided in the embodiment of the present invention.

[0056] Based on the above hardware structure, an embodiment of the cycling warning method of the present invention is proposed.

[0057] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the cycling warning method of the present invention.

[0058] In a first embodiment, the cycling warning method includes the following steps:

[0059] Step S10: When a traffic control image is detected, determine the rate of change of the speed detection box of the vehicle image behind the target user.

[0060] It should be noted that the execution subject in this embodiment is a cycling warning device, but it can also be other devices that can achieve the same or similar functions, such as a smart device controller. This embodiment does not limit this, and in this embodiment, a smart device controller will be used as an example for explanation.

[0061] It should be understood that traffic control images refer to images used for traffic control, including but not limited to traffic light images and images of traffic police directing traffic. These traffic control images can be acquired by the front-view camera of a smart device, such as AR glasses. The front-view camera can be a front-view camera, and the target user can be a cyclist. The speed detection frame change rate refers to the rate of change of the speed detection frame of a vehicle behind the target user on the rear-view camera of the smart device. The greater the rate of change of the speed detection frame, the faster the vehicle behind is traveling.

[0062] Furthermore, before step S10, the method further includes: acquiring a road image of the area ahead of the target user's location; extracting features from the road image ahead to obtain road image features; identifying the road image features ahead using a target traffic control recognition model; and determining whether a traffic control image has been detected based on the recognition results.

[0063] It is understood that the road image ahead refers to the road image at the target user's location. This road image ahead is acquired by the forward-facing camera of the smart device. The road image ahead includes, but is not limited to, images of pedestrians, vehicles, and road traffic in the area ahead. The target traffic control recognition model refers to the model used to determine whether the road image contains a traffic control image. This target traffic control recognition model can be the YOLOX recognition model. After obtaining the features of the road image ahead, the target traffic control recognition model is used to identify the features of the road image ahead. Then, based on the recognition result, it is determined whether a traffic control image has been detected. If so, it indicates that there is traffic control on the road ahead.

[0064] Further, step S10 includes: when a traffic control image is detected, activating the rear-view camera device of the smart device; acquiring the current speed detection frame size of the image of the vehicle behind the target user at the current moment on the rear-view camera device; acquiring the initial speed detection frame size of the image of the vehicle behind the target user at the initial moment on the rear-view camera device; calculating the speed detection frame change time based on the current moment and the initial moment; calculating the speed detection frame change magnitude based on the previous speed detection frame size and the initial speed detection frame size; and calculating the speed detection frame change rate of the vehicle behind the target user based on the speed detection frame change time and the speed detection frame change magnitude.

[0065] It should be understood that the rear-view camera of the smart device is activated when a traffic control image is detected, and not activated otherwise. This rear-view camera can be a rear-view camera. To improve the user experience, when the smart device is AR glasses, the rear-view camera can be set at the junction of the temple and the head of the glasses. After activating the rear-view camera, the current speed detection frame size of the image of the vehicle behind the target user at the current moment and the initial speed detection frame size of the image of the vehicle behind the target user at the initial moment are obtained through the rear-view camera. The speed detection frame change time refers to the time taken for the speed detection frame to change from the initial speed detection frame size to the current speed detection frame size, and the speed detection frame change magnitude refers to the change in the speed detection frame from the initial moment to the current moment. Then, the speed detection frame change time and speed detection frame change magnitude are used to calculate the speed detection frame change rate of the vehicle behind the target user.

[0066] It should be noted that if the speed detection frame size of the vehicle image behind the target user does not change within a preset time period, it indicates that the vehicle is stationary. In this case, the vehicle image will be filtered out from the images of vehicles behind the target user. In addition, the images captured by the rearview camera will not be displayed on the smart device to avoid interfering with the target user's field of vision.

[0067] Step S20: Determine the current distance between the target user and the vehicle.

[0068] It is understandable that the current distance refers to the distance between the target user and the vehicle at the current moment. When the current distance is less than the preset safe distance threshold, it indicates that the target user and the vehicle are relatively close.

[0069] Further, step S20 includes: detecting the driving vehicle using a target 3D detection model to obtain the center coordinates, driving parameters, and attribute information of the driving vehicle in the target coordinate system; and determining the current distance between the target user and the driving vehicle based on the center coordinates, driving parameters, and attribute information.

[0070] It should be understood that after identifying the vehicle behind the target user, the vehicle is defined as a cube. The cube is then detected by the target 3D detection model to obtain the vehicle's center coordinates, driving parameters, and attribute information in the target coordinate system. The driving parameters can be the heading angle, and the attribute information can be the length, height, and width. Then, the current distance between the target user and the vehicle is determined based on the center coordinates, driving parameters, and attribute information.

[0071] Step S30: Issue a warning to the target user based on the rate of change of the speed detection frame and the current distance.

[0072] It should be understood that after determining the rate of change of the speed detection frame and the current distance, the target component of the smart device is controlled to issue a warning to the target user, so as to remind the target user to slow down in a timely manner.

[0073] It should be noted that after issuing a warning to the target user, the system will also determine the rate of change of the speed detection box of the vehicle image behind the target user at the next moment; determine the target distance between the target user and the vehicle; and stop issuing the warning when the rate of change of the speed detection box of the vehicle image behind the target user at the next moment is less than a preset rate of change threshold and / or the target distance is greater than or equal to a preset safe distance threshold.

[0074] Understandably, after issuing a warning to the target user, it is necessary to continue to determine the rate of change of the speed detection box of the vehicle image behind the target user and the target distance between the target user and the vehicle at the next moment. If either the rate of change of the speed detection box of the vehicle image behind the target user is less than a preset rate of change threshold or the target distance is greater than or equal to a preset safe distance threshold, it indicates that there is no danger behind the target user, and the warning is stopped at this time to improve the user's experience.

[0075] This embodiment determines the rate of change of the speed detection frame of the vehicle behind the target user when a traffic control image is detected; determines the current distance between the target user and the vehicle; and issues a warning to the target user based on the rate of change of the speed detection frame and the current distance. Through this method, when a traffic control image is detected, the rate of change of the speed detection frame of the vehicle behind the target user is calculated using speed detection frame change parameters. Then, based on the rate of change of the speed detection frame and the current distance, it is determined whether the target user is in danger. If so, a warning is issued to the target user, thereby enabling timely warnings to the user and preventing danger from occurring.

[0076] In one embodiment, such as Figure 3 The second embodiment of the cycling warning method of the present invention, based on the first embodiment, includes step S30, which includes:

[0077] Step S301: When the rate of change of the speed detection frame is greater than or equal to a preset rate of change threshold, determine whether the current distance is less than a preset safe distance threshold.

[0078] It should be understood that when the rate of change of the speed detection box is greater than or equal to the preset rate of change threshold, it indicates that the speed of the vehicle behind the target is relatively fast. At this time, it is necessary to continue to determine whether the current distance is less than the preset safe distance threshold.

[0079] Step S302: When the current distance is less than a preset safe distance threshold, a warning is issued to the target user through the target component of the smart device.

[0080] Understandably, when the current distance is determined to be less than the preset safe distance threshold, it is determined that there is danger behind the target user. At this time, the target component of the control smart device will issue a warning to the target user. The target component includes a left component and a right component. The target component can be a lens. Accordingly, the left component can be the left lens and the right component can be the right lens.

[0081] Further, step S302 includes: when the current distance is less than a preset safe distance threshold, determining the relative direction between the driving vehicle and the target user; when the relative direction is to the left, continuously flashing a vehicle icon on the left side of the smart device and issuing a warning message indicating danger on the left; when the relative direction is to the right, continuously flashing a vehicle icon on the right side of the smart device and issuing a warning message indicating danger on the right.

[0082] It should be understood that relative direction refers to the direction of the vehicle behind the target user relative to the target user. Specifically, it determines whether the vehicle is to the left or right rear of the target user, using the target user as a reference. If the relative direction is left, and the vehicle is determined to be to the left rear of the target user, it indicates a danger to the left rear of the target user. In this case, a vehicle icon flashes continuously on the left side of the smart device, along with a warning message indicating danger on the left, alerting the target user to the danger on their left. Conversely, if the relative direction is right, and the vehicle is determined to be to the right rear of the target user, it indicates a danger to the right rear of the target user. In this way, the target user is promptly alerted.

[0083] Furthermore, after the current distance is less than a preset safe distance threshold, the method further includes: obtaining the size of the traffic control image detection frame at the current moment and the size of the traffic control image detection frame at the previous moment; calculating the rate of change of the traffic control image detection frame size based on the size of the traffic control image detection frame at the current moment and the size of the traffic control image detection frame at the previous moment; when the rate of change of the traffic control image detection frame size is less than a target rate of change threshold, recognizing the traffic control image to obtain the road line that is allowed to pass ahead; and not issuing a warning to the target user when the road line that is allowed to pass ahead is a right turn road line.

[0084] It is understandable that the traffic control image detection box size refers to the size of the detection box used to detect traffic control images. The rate of change of the traffic control image detection box size is calculated based on the current and previous times. Then, it is determined whether the rate of change of the traffic control image detection box size is less than the target rate of change threshold. If so, it indicates that the target user is stationary. At this time, the traffic control image is identified by the target road line recognition model to obtain the road line that is allowed to pass ahead. Then, it is determined whether the road line that is allowed to pass ahead is a right turn road line. If so, it indicates that the target user is waiting at the intersection ahead and the vehicle behind is turning right. At this time, there is no danger to the target user, that is, no warning is given to the target user, thus avoiding the occurrence of false warnings.

[0085] refer to Figure 4 , Figure 4The overall process is illustrated below: After the smart device is started, it determines whether a traffic control image has been detected. If so, it controls the rear-view camera of the smart device to start and determines the rate of change of the speed detection box of the vehicle image behind the target user through the rear-view camera. It also determines the current distance between the target user and the vehicle through the target 3D detection model. Then, it determines whether the rate of change of the speed detection box is greater than or equal to a preset rate of change threshold and whether the current distance is less than a preset safe distance threshold. If both of the above conditions are met, it continues to determine whether the road line that allows passage ahead is a right-turn road line. If so, no warning is issued to the target user. If not, a warning is issued to the target user through the target component of the smart device.

[0086] This embodiment determines whether the current distance is less than a preset safe distance threshold when the rate of change of the speed detection frame is greater than or equal to a preset rate of change threshold; when the current distance is less than the preset safe distance threshold, the target device of the smart device issues a warning to the target user; through the above method, when it is determined that the rate of change of the speed detection frame is greater than or equal to the preset rate of change threshold and the current distance is less than the preset safe distance threshold, it is determined that there is danger behind the target user. At this time, the target device of the smart device issues a warning to the target user, thereby timely reminding the target user to slow down to avoid the occurrence of danger.

[0087] Furthermore, this embodiment of the invention also proposes a storage medium storing a cycling warning program, which, when executed by a processor, implements the steps of the cycling warning method described above.

[0088] Since this storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0089] In addition, refer to Figure 5 The present invention also proposes a cycling warning device, which includes:

[0090] The detection module 10 is used to determine the rate of change of the speed detection box of the vehicle image behind the target user when a traffic control image is detected.

[0091] The determination module 20 is used to determine the current distance between the target user and the driving vehicle.

[0092] The early warning module 30 is used to issue an early warning to the target user based on the size of the speed detection box and the current distance.

[0093] This embodiment determines the rate of change of the speed detection frame of the vehicle behind the target user when a traffic control image is detected; determines the current distance between the target user and the vehicle; and issues a warning to the target user based on the rate of change of the speed detection frame and the current distance. Through this method, when a traffic control image is detected, the rate of change of the speed detection frame of the vehicle behind the target user is calculated using speed detection frame change parameters. Then, based on the rate of change of the speed detection frame and the current distance, it is determined whether the target user is in danger. If so, a warning is issued to the target user, thereby enabling timely warnings to the user and preventing danger from occurring.

[0094] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0095] In addition, for technical details not described in detail in this embodiment, please refer to the cycling warning method provided in any embodiment of the present invention, which will not be repeated here.

[0096] In one embodiment, the detection module 10 is further configured to acquire a road image of the area ahead of the target user's location; extract features from the road image ahead to obtain road image features; identify the road image features ahead using a target traffic control recognition model; and determine whether a traffic control image has been detected based on the recognition result.

[0097] In one embodiment, the detection module 10 is further configured to, upon detecting a traffic control image, activate the rear-view camera of the smart device; acquire the current speed detection frame size of the image of the vehicle behind the target user on the rear-view camera at the current moment; acquire the initial speed detection frame size of the image of the vehicle behind the target user on the rear-view camera at the initial moment; calculate the speed detection frame change time based on the current moment and the initial moment; calculate the speed detection frame change magnitude based on the previous speed detection frame size and the initial speed detection frame size; and calculate the speed detection frame change rate of the vehicle behind the target user based on the speed detection frame change time and the speed detection frame change magnitude.

[0098] In one embodiment, the determining module 20 is further configured to detect the driving vehicle using a target 3D detection model, obtain the center coordinates, driving parameters, and attribute information of the driving vehicle in the target coordinate system, and determine the current distance between the target user and the driving vehicle based on the center coordinates, driving parameters, and attribute information.

[0099] In one embodiment, the warning module 30 is further configured to determine whether the current distance is less than a preset safe distance threshold when the rate of change of the speed detection frame is greater than or equal to a preset rate of change threshold; and to issue a warning to the target user through the target component of the smart device when the current distance is less than the preset safe distance threshold.

[0100] In one embodiment, the target component includes a left component and a right component; the warning module 30 is further configured to determine the relative direction between the driving vehicle and the target user when the current distance is less than a preset safe distance threshold; when the relative direction is to the left, continuously flashing a vehicle icon on the left component of the smart device and issuing a warning message indicating danger on the left; when the relative direction is to the right, continuously flashing a vehicle icon on the right component of the smart device and issuing a warning message indicating danger on the right.

[0101] In one embodiment, the warning module 30 is further configured to acquire the size of the traffic control image detection frame at the current moment and the size of the traffic control image detection frame at the previous moment; calculate the rate of change of the traffic control image detection frame size based on the size of the traffic control image detection frame at the current moment and the size of the traffic control image detection frame at the previous moment; when the rate of change of the traffic control image detection frame size is less than a target rate of change threshold, identify the traffic control image to obtain the road line that is allowed to pass ahead; and when the road line that is allowed to pass ahead is a right turn road line, no warning is issued to the target user.

[0102] Other embodiments or implementation methods of the cycling warning device described in this invention can be referred to the above-described method embodiments, and will not be repeated here.

[0103] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0104] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0105] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0106] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. 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. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, all-in-one platform workstation, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0107] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A cycling alert method, characterized by, The riding warning method comprises the following steps: When a traffic control image is detected, a speed detection frame change rate of a driving vehicle image behind a target user is determined, the traffic control image is collected by a front-view camera device of a smart device, and the speed detection frame change rate is a change rate of a speed detection frame of the driving vehicle behind the target user on a rear-view camera device of the smart device; A current distance between the target user and the driving vehicle is determined; The target user is warned according to the speed detection frame change rate and the current distance; The warning of the target user according to the speed detection frame change rate and the current distance comprises: When the speed detection frame change rate is greater than or equal to a preset change rate threshold, it is determined whether the current distance is less than a preset safety distance threshold; When the current distance is less than the preset safety distance threshold, the target user is warned by a target component of the smart device; After the current distance is less than the preset safety distance threshold, the following steps are further included: A traffic control image detection frame size at a current moment and a traffic control image detection frame size at a previous moment are obtained; A traffic control image detection frame size change rate is calculated according to the traffic control image detection frame size at the current moment and the traffic control image detection frame size at the previous moment; When the traffic control image detection frame size change rate is less than a target change rate threshold, a front passing road line is obtained by identifying the traffic control image; When the front passing road line is a right-turn road line, the target user is not warned.

2. The cycling alert method of claim 1, wherein, Before the speed detection frame change rate of the driving vehicle image behind the target user is determined when the traffic control image is detected, the following steps are further included: A front area road image of a position where the target user is located is obtained; A front area road image feature is obtained by performing feature extraction on the front area road image; The front area road image feature is identified by a target traffic control identification model; It is determined whether the traffic control image is detected according to an identification result.

3. The cycling alert method of claim 1, wherein, When the traffic control image is detected, the rear-view camera device of the smart device is started; A current speed detection frame size of the driving vehicle image behind the target user on the rear-view camera device at a current moment is obtained; An initial speed detection frame size of the driving vehicle image behind the target user on the rear-view camera device at an initial moment is obtained; A speed detection frame change time is calculated according to the current moment and the initial moment; A speed detection frame change size is calculated according to the current speed detection frame size and the initial speed detection frame size; A speed detection frame change rate of the driving vehicle behind the target user is calculated according to the speed detection frame change time and the speed detection frame change size. The current distance between the target user and the driving vehicle is determined by the following steps:

4. The cycling alert method of claim 1, wherein, The driving vehicle is detected by a target 3D detection model to obtain a center coordinate, a driving parameter and attribute information of the driving vehicle in a target coordinate system; ​ Determine a current distance between the target user and the driving vehicle according to the center coordinates, the driving parameter, and the attribute information.

5. The cycling alert method of claim 1, wherein, The target component includes a left component and a right component. When the current distance is less than a preset safety distance threshold, the target component of the intelligent device warns the target user, including: When the current distance is less than a preset safety distance threshold, determine the relative direction of the driving vehicle and the target user; When the relative direction is a left direction, continuously flash a vehicle icon on the left component of the intelligent device and issue a warning prompt information that there is a danger on the left side; When the relative direction is a right direction, continuously flash a vehicle icon on the right component of the intelligent device and issue a warning prompt information that there is a danger on the right side.

6. A cycling warning device, characterised in that, The riding warning device includes: A detection module configured to determine a speed detection frame change rate of a driving vehicle image behind the target user when detecting a traffic control image, the traffic control image being captured by a front-view camera device of an intelligent device, and the speed detection frame change rate being a change rate of a speed detection frame of the driving vehicle behind the target user on a rear-view camera device of the intelligent device; A determination module configured to determine a current distance between the target user and the driving vehicle; A warning module configured to warn the target user according to the speed detection frame change rate and the current distance; The warning module is further configured to determine whether the current distance is less than a preset safety distance threshold when the speed detection frame change rate is greater than or equal to a preset change rate threshold, and warn the target user through a target component of the intelligent device when the current distance is less than the preset safety distance threshold. After the current distance is less than the preset safety distance threshold, obtain a traffic control image detection frame size at a current time and a traffic control image detection frame size at a previous time, calculate a traffic control image detection frame size change rate according to the traffic control image detection frame size at the current time and the traffic control image detection frame size at the previous time, identify the traffic control image to obtain a front allowed passing road line when the traffic control image detection frame size change rate is less than a target change rate threshold, and do not warn the target user when the front allowed passing road line is a right-turn road line.

7. A cycling warning device, characterised in that, The riding warning device includes a memory, a processor, and a riding warning program stored in the memory and executable on the processor, the riding warning program being configured to implement the riding warning method of any one of claims 1 to 5.

8. A storage medium, characterized by The storage medium stores a riding warning program, and the riding warning program is executed by the processor to implement the riding warning method of any one of claims 1 to 5.

Images