A cycling interest event identification method, device, equipment and storage medium

Abstract

The application discloses a cycling interest event recognition method and device, equipment and a storage medium. In the cycling video recording process, cycling state data is calculated according to sensor data, cycling interest events are recognized in real time according to the cycling state data, and the strong and weak levels of the cycling interest events are divided. The corresponding cycling video clips of the cycling interest events are stored according to the strong and weak levels, so that when the storage space is insufficient, the cycling video clips of the weak level are automatically deleted, and the technical problems that the traditional sports camera needs to manually start and end the video recording function, the storage space is insufficient due to long cycling duration, and the cycling highlights cannot be recognized are solved.

Description

Technical Field

[0001] This application relates to the technical field, and in particular to a method, apparatus, device, and storage medium for identifying cycling interest events. Background Technology

[0002] A cycling camera is an electronic device used to record exciting moments while riding a bicycle or motorcycle.

[0003] Traditional action cameras typically require users to manually turn video recording on and off. However, cycling can sometimes last for extended periods, and high-definition videos require a lot of storage space, quickly leading to insufficient storage and the inability to continue recording. In addition, when encountering exciting moments while cycling or motorcycling, riders may not be able to concentrate and frequently turn the video recording function on and off, resulting in missing the chance to save those exciting moments. Summary of the Invention

[0004] This application provides a method, device, equipment, and storage medium for identifying cycling interest events, which solves the technical problems of traditional action cameras requiring manual start and stop of video recording, and insufficient storage space due to long cycling durations, making it impossible to identify exciting moments of cycling.

[0005] In view of the above, the first aspect of this application provides a method for identifying cycling interest events, the method comprising:

[0006] S1. During the recording of cycling videos, cycling status data is calculated based on sensor data;

[0007] S2. Identify at least one cycling interest event based on the cycling status data, and classify the strength level of the cycling interest event;

[0008] S3. Store the cycling video clips corresponding to the cycling interest events according to the strength level.

[0009] Optionally, step S1 specifically includes:

[0010] S11. During cycling video recording, sensor data is acquired based on IMU and GPS.

[0011] S12. Calculate riding status data such as turning angle, maximum turning speed, forward speed, slope, pitch angle, roll angle, and yaw angle based on the sensor data.

[0012] Optionally, step S2 specifically includes:

[0013] S21. Identify bending interest events based on the roll angle, and determine the strength level of the bending interest events;

[0014] S22. Identify sharp turn interest events based on the turning angle, maximum turning speed, and forward speed, and determine the strength level of the sharp turn interest events;

[0015] S23. Identify steep slope interest events and rapid slope change interest events based on the slope, and determine the strength level of the steep slope interest events and the rapid slope change interest events.

[0016] S24. Identify rapid acceleration and rapid deceleration interest events based on the forward speed, and determine the strength level of the rapid acceleration and rapid deceleration interest events.

[0017] Optionally, step S21 specifically includes:

[0018] N roll angles are identified in one recognition cycle;

[0019] The maximum roll angle is the maximum absolute value of all roll angles in the identification cycle.

[0020] The maximum roll angle is compared with a preset strength level threshold. If it is less than the roll angle corresponding to the weakest strength level, the identification period is not a bending interest event. Otherwise, the identification period is a bending interest event, and the strength level of the bending interest event is determined according to the comparison result between the maximum roll angle and the preset strength level threshold.

[0021] Optionally, step S22 specifically includes:

[0022] N yaw angles and forward speeds are identified in one identification cycle;

[0023] The turning angle is determined based on the maximum and minimum yaw angles during the identification cycle.

[0024] The maximum turning speed is determined based on the absolute value of the difference between adjacent yaw angles.

[0025] The forward speed, turning angle, and maximum turning speed are compared with preset strength level thresholds. If any one of them is less than the forward speed, turning angle, and maximum turning speed corresponding to the weakest strength level, then the identification period is not a sharp turn interest event; otherwise, the identification period is a sharp turn interest event. Based on the comparison results of the forward speed, turning angle, and maximum turning speed with the preset strength level thresholds, the minimum strength level is used to determine the strength level of the sharp turn interest event.

[0026] Optionally, step S23 specifically includes:

[0027] N steep slopes were identified in one identification cycle;

[0028] The maximum absolute value of all steep slopes in the identification cycle is taken as the steepest slope.

[0029] The maximum slope difference is determined based on the maximum absolute value of the slope difference between preset intervals in the recognition period;

[0030] The maximum steep slope is compared with a preset strength level threshold. If it is less than the steep slope corresponding to the weakest strength level, the identification period is not an interest event of steep slopes. Otherwise, the identification period is an interest event of steep slopes. The strength level of the interest event of steep slopes is determined according to the comparison result between the maximum steep slope and the preset strength level threshold.

[0031] The maximum slope difference is compared with a preset strength level threshold. If it is less than the steep slope difference corresponding to the weakest strength level, the identification period is not a slope change interest event. Otherwise, the identification period is a slope change interest event, and the strength level of the slope change interest event is determined according to the comparison result between the maximum slope difference and the preset strength level threshold.

[0032] Optionally, step S24 specifically includes:

[0033] N forward speeds are identified in one recognition cycle;

[0034] The maximum forward speed difference is determined based on the absolute value of the difference between preset interval forward speeds;

[0035] The maximum forward speed difference is compared with a preset strength level threshold. If it is less than the forward speed difference corresponding to the weakest strength level, the identification period is not a rapid acceleration or rapid deceleration interest event. Otherwise, the identification period is a rapid acceleration or rapid deceleration interest event, and the strength level of the rapid acceleration or rapid deceleration interest event is determined according to the comparison result between the maximum forward speed difference and the preset strength level threshold.

[0036] A second aspect of this application provides a cycling interest event recognition device, the device comprising:

[0037] The computing unit is used to calculate cycling status data based on sensor data during cycling video recording.

[0038] The identification unit is used to identify at least one cycling interest event based on the cycling status data, and to classify the strength level of the cycling interest event.

[0039] The storage unit is used to store cycling video clips corresponding to the cycling interest events according to the strength level.

[0040] A third aspect of this application provides a cycling interest event recognition device, the device comprising a processor and a memory:

[0041] The memory is used to store program code and transmit the program code to the processor;

[0042] The processor is configured to execute the steps of the cycling interest event recognition method as described in the first aspect above, according to the instructions in the program code.

[0043] A fourth aspect of this application provides a computer-readable storage medium for storing program code for performing the steps of the cycling interest event recognition method described in the first aspect.

[0044] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0045] This application provides a method, device, equipment, and storage medium for identifying cycling interest events. During cycling video recording, cycling status data is calculated based on sensor data. Cycling interest events are identified in real time based on the cycling status data, and the strength levels of the cycling interest events are classified. Cycling video segments corresponding to the cycling interest events are stored according to their strength levels. When storage space is insufficient, weak-level cycling video segments are automatically deleted. This solves the technical problem that traditional action cameras require manual start and stop of video recording, and the long duration of cycling leads to insufficient storage space, making it impossible to identify exciting moments of cycling. Attached Figure Description

[0046] Figure 1 This is a flowchart of the cycling interest event recognition method in the embodiments of this application;

[0047] Figure 2 This is a schematic diagram of the structure of the cycling interest event recognition device in the embodiments of this application;

[0048] Figure 3 This is a schematic diagram of the structure of the cycling interest event recognition device in the embodiments of this application. Detailed Implementation

[0049] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0050] This application designs a method, device, equipment, and storage medium for recognizing cycling interest events, which solves the technical problems of traditional action cameras requiring manual start and stop of video recording, and insufficient storage space due to long cycling durations, making it impossible to recognize exciting moments of cycling.

[0051] For easier understanding, please refer to Figure 1 , Figure 1 This is a flowchart of the cycling interest event recognition method in the embodiments of this application, such as... Figure 1 As shown, specifically:

[0052] S1. During the recording of cycling videos, cycling status data is calculated based on sensor data;

[0053] Step S1 specifically includes:

[0054] S11. During cycling video recording, sensor data is acquired based on IMU and GPS.

[0055] S12. Calculates riding status data such as turning angle, maximum turning speed, forward speed, gradient, pitch angle, roll angle, and yaw angle based on sensor data.

[0056] It should be noted that speed can be obtained via GPS during cycling video recording. Gradient can be calculated using longitude, latitude, and altitude information: specifically, the altitude difference A is calculated using the altitude at two points in time, and the horizontal distance B is calculated using the longitude and latitude at two points in time, resulting in the gradient α = arctan(A / B); where longitude and latitude are obtained from GPS, and altitude can be obtained from GPS or calculated from barometer readings. Roll angle (also known as left and right tilt angle) and yaw angle can be calculated using IMU data: first, the device's attitude quaternions are calculated using accelerometers and / or gyroscopes, then the quaternions are converted to Euler angles (pitch, yaw, and roll angles) using OpenCV's Quad::toEulerAngles function.

[0057] S2. Identify at least one cycling interest event based on cycling status data, and classify the strength level of the cycling interest event;

[0058] It should be noted that, assuming the interest event recognition period is N seconds, that is, interest event recognition is performed once every N seconds, and one recognition period can recognize multiple types of interest events, including cornering; assuming the frequency of riding status data is 1Hz, that is, riding status data is calculated once per second.

[0059] Step S2 specifically includes:

[0060] S21. Identify bending interest events based on roll angle and determine the strength level of the bending interest events;

[0061] Step S21 is as follows:

[0062] N roll angles are identified in one recognition cycle;

[0063] The maximum roll angle is the maximum absolute value of all roll angles in the identification cycle.

[0064] Compare the maximum roll angle with the preset strong / weak level threshold. If it is less than the roll angle corresponding to the weakest strong / weak level, the recognition period is not a bending interest event; otherwise, the recognition period is a bending interest event, and the strong / weak level of the bending interest event is determined according to the comparison result between the maximum roll angle and the preset strong / weak level threshold.

[0065] It should be noted that there are N roll angle values in each recognition period, denoted as Roll1, Roll2, …, RollN. The maximum roll angle Rollmax in this recognition period is the maximum value of the absolute values of all roll angles in the period:

[0066] Divide the events into M strong / weak levels, denoted as L1, L2, …, LM, where LM is the strongest and L1 is the weakest, corresponding to M roll angle thresholds RollL1, RollL2, …, RollLM respectively.

[0067] If Rollmax < RollL1, then this period is not a bending interest event; if RollL1 ≤ Rollmax < RollL2, then this period is a bending interest event, and the event level is L1; if RollL2 ≤ Rollmax < RollL3, then this period is a bending interest event, and the event level is L2; and so on.

[0068] S22. Identify the sharp turn interest event according to the turning angle, maximum turning speed, and forward speed, and determine the strong / weak level of the sharp turn interest event;

[0069] The specific steps of S22 are as follows:

[0070] Identify N yaw angles and forward speed in one recognition period;

[0071] Determine the turning angle according to the maximum yaw angle and minimum yaw angle in the recognition period;

[0072] Determine the maximum turning speed according to the absolute value of the difference between adjacent yaw angles;

[0073] Compare the forward speed, turning angle, and maximum turning speed with the preset strong / weak level threshold respectively. If any one of them is less than the forward speed, turning angle, and maximum turning speed corresponding to the weakest strong / weak level, the recognition period is not a sharp turn interest event; otherwise, the recognition period is a sharp turn interest event, and the minimum strong / weak level is determined as the strong / weak level of the sharp turn interest event according to the comparison results of the forward speed, turning angle, and maximum turning speed with the preset strong / weak level threshold.

[0074] It should be noted that sharp turn interest events can be identified by turning angle, maximum turning speed, and forward speed. Assuming the current event recognition period contains N yaw angle values, denoted as Yaw1, Yaw2, ..., YawN, find the maximum and minimum yaw angles, denoted as Yawmax and Yawmin respectively. Then, the turning angle TurnAngle = Yawmax - Yawmin. The turning speed, i.e., the rate of change of the yaw angle, can be obtained by subtracting the previous yaw angle from the current yaw angle and taking the absolute value, i.e., ΔYawi = abs(Yawi - Yawi-1). Therefore, the maximum turning speed ΔYawmax = max(ΔYaw1, ΔYaw2, ..., ΔYawN). Similarly, the event is divided into M strength levels. Each level has a corresponding turning angle, maximum turning speed, and forward speed threshold. The strength level of the turning angle, maximum turning speed, and forward speed is determined by this. The minimum value of the three levels is taken as the level of the sharp turn event. For example, if the levels of turning angle, maximum turning speed, and forward speed are L1, L3, and L2 respectively, then the level of the sharp turn interest event is L1.

[0075] S23. Identify steep slope interest events and rapidly changing slope interest events based on slope gradient, and determine the strength level of steep slope interest events and rapidly changing slope interest events.

[0076] Step S23 is as follows:

[0077] N steep slopes were identified in one identification cycle;

[0078] The maximum absolute value of all steep slopes in the identification cycle is taken as the steepest slope.

[0079] The maximum slope difference is determined based on the maximum absolute value of the slope difference between preset intervals in the recognition period;

[0080] The maximum steep slope is compared with the preset strength level threshold. If it is less than the steep slope corresponding to the weakest strength level, the identification period is not an interest event of steep slope. Otherwise, the identification period is an interest event of steep slope. The strength level of the interest event of steep slope is determined according to the comparison result between the maximum steep slope and the preset strength level threshold.

[0081] The maximum slope difference is compared with the preset strength level threshold. If it is less than the steep slope difference corresponding to the weakest strength level, the identification period is not a slope change interest event. Otherwise, the identification period is a slope change interest event, and the strength level of the slope change interest event is determined according to the comparison result between the maximum slope difference and the preset strength level threshold.

[0082] The uphill and downhill interest events can be identified by slope. Similar to the cornering interest event, calculate the maximum value of the absolute slope Slopemax in the current recognition cycle. Set M slope thresholds. If SlopeLi ≤ Slopemax < SlopeLi+1, then the uphill and downhill interest event level in this cycle is i.

[0083] The interest event of rapid slope change can be identified by slope. In the current recognition cycle, calculate the slope difference ΔSlopei = Slopei - Slopei-k between each slope Slopei and the slope Slopei-k k seconds before it. Usually, k is 1 - 3 seconds. Calculate the maximum value of the absolute slope difference ΔSlopemax. Set M thresholds. If ΔSlopeLi ≤ ΔSlopemax < ΔSlopeLi+1, then the interest event level of rapid slope change in this cycle is i.

[0084] S24. Identify the rapid acceleration and rapid deceleration interest events according to the forward speed, and determine the strength levels of the rapid acceleration and rapid deceleration interest events.

[0085] Step S24 is specifically as follows:

[0086] Identify N forward speeds in one recognition cycle;

[0087] Determine the maximum forward speed difference according to the absolute value of the difference between the preset interval forward speeds;

[0088] Compare the maximum forward speed difference with the preset strength level threshold. If it is less than the forward speed difference corresponding to the weakest strength level, then the recognition cycle is not a rapid acceleration and rapid deceleration interest event. Otherwise, the recognition cycle is a rapid acceleration and rapid deceleration interest event, and determine the strength levels of the rapid acceleration and rapid deceleration interest events according to the comparison result of the maximum forward speed difference and the preset strength level threshold.

[0089] It should be noted that the rapid acceleration and rapid deceleration interest events can be identified by the forward speed. In the current recognition cycle, calculate the speed difference ΔVelocityi = Velocityi - Velocityi-j between each forward speed Velocityi and the forward speed Velocityi-j j seconds before it. Usually, j is 1 - 3 seconds. Calculate the maximum value of the speed difference ΔVelocitymax. Set M thresholds. If ΔVelocityLi ≤ ΔVelocitymax < ΔVelocityLi+1, then the rapid acceleration interest event level in this cycle is i.

[0090] Calculate the negative velocity difference ΔVelocityMinusi = -ΔVelocityi, calculate the maximum negative velocity difference ΔVelocityMinusmax, set M thresholds, and if ΔVelocityMinusLi ≤ ΔVelocityMinusmax < ΔVelocityMinusLi+1, then the level of the rapid deceleration interest event in this cycle is i.

[0091] S3. Store cycling video clips corresponding to cycling interest events according to their strength level.

[0092] It should be noted that if at least one event is identified in the current recognition cycle, the corresponding video segment for that cycle is saved. The event level of this video segment is the maximum value of all event levels in that recognition cycle. For example, if a sharp turn is identified as level L1, a rapid acceleration as level L3, and a steep incline or descent as level L2, then the event level for that recognition cycle is L3. If there is insufficient storage space or an excessive number of video segments, the video segment with the lowest event level among the previously saved events will be deleted.

[0093] Furthermore, it also includes:

[0094] After the trip, the cycling video clips will be combined into a short video.

[0095] Based on the user-defined short video length, the required number of cycling video clips (X) is determined, and the X cycling video clips with the highest event level are selected to synthesize the short video. Alternatively, the user can specify the desired event types and their corresponding quantities for the short video, and the video clips with the highest event level within each event type are selected and synthesized based on the user's settings.

[0096] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of the cycling interest event recognition device in the embodiments of this application, as shown below. Figure 2 As shown, specifically:

[0097] The computing unit 201 is used to calculate cycling status data based on sensor data during the cycling video recording process;

[0098] The identification unit 202 is used to identify at least one cycling interest event based on cycling status data and classify the strength level of the cycling interest event.

[0099] Storage unit 203 is used to store cycling video clips corresponding to cycling interest events according to their strength level.

[0100] This application also provides another cycling interest event recognition device, such as... Figure 3As shown, for ease of explanation, only the parts related to the embodiments of this application are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of this application. The terminal can be any terminal device including mobile phones, tablets, personal digital assistants (PDAs), point-of-sales terminals (POS), in-vehicle computers, etc. Taking a mobile phone as an example:

[0101] Figure 3 This is a block diagram illustrating a portion of the structure of a mobile phone related to the terminal provided in the embodiments of this application. (Reference) Figure 3 The mobile phone includes: a radio frequency (RF) circuit 1010, a memory 1020, an input unit 1030, a display unit 1040, a sensor 1050, an audio circuit 1060, a wireless fidelity (WiFi) module 1070, a processor 1080, and a power supply 1090, etc. Those skilled in the art will understand that... Figure 3 The mobile phone structure shown does not constitute a limitation on the mobile phone and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0102] The following is combined with Figure 3 A detailed introduction to each component of a mobile phone:

[0103] The RF circuit 1010 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and processes it with the processor 1080; additionally, it transmits uplink data to the base station. Typically, the RF circuit 1010 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier (LNA), a duplexer, etc. Furthermore, the RF circuit 1010 can also communicate wirelessly with networks and other devices. The aforementioned wireless communications may use any communication standard or protocol, including but not limited to Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, and Short Messaging Service (SMS).

[0104] The memory 1020 can be used to store software programs and modules. The processor 1080 executes various mobile phone functions and data processing by running the software programs and modules stored in the memory 1020. The memory 1020 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 1020 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0105] The input unit 1030 can be used to receive input numerical or character information, and to generate key signal inputs related to user settings and function control of the mobile phone. Specifically, the input unit 1030 may include a touch panel 1031 and other input devices 1032. The touch panel 1031, also known as a touch screen, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel 1031), and drive the corresponding connection devices according to a pre-set program. Optionally, the touch panel 1031 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 1080, and can also receive and execute commands sent by the processor 1080. In addition, the touch panel 1031 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 1031, the input unit 1030 may also include other input devices 1032. Specifically, other input devices 1032 may include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0106] The display unit 1040 can be used to display information input by the user or information provided to the user, as well as various menus of the mobile phone. The display unit 1040 may include a display panel 1041, which may optionally be configured as a Liquid Crystal Display (LCD), Organic Light-Emitting Diode (OLED), or similar display panel 1041. Further, a touch panel 1031 may cover the display panel 1041. When the touch panel 1031 detects a touch operation on or near it, it transmits the information to the processor 1080 to determine the type of touch event. Subsequently, the processor 1080 provides corresponding visual output on the display panel 1041 according to the type of touch event. Although in Figure 3 In this embodiment, the touch panel 1031 and the display panel 1041 are two separate components to realize the input and output functions of the mobile phone. However, in some embodiments, the touch panel 1031 and the display panel 1041 can be integrated to realize the input and output functions of the mobile phone.

[0107] The mobile phone may also include at least one sensor 1050, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 1041 according to the ambient light level, and the proximity sensor can turn off the display panel 1041 and / or the backlight when the phone is moved to the ear. As a type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used for applications that recognize the phone's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition-related functions (such as pedometer, taps), etc. Other sensors that may be configured in the mobile phone, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0108] The audio circuit 1060, speaker 1061, and microphone 1062 provide an audio interface between the user and the mobile phone. The audio circuit 1060 converts the received audio data into electrical signals and transmits them to the speaker 1061, where the speaker 1061 converts them into sound signals for output. On the other hand, the microphone 1062 converts the collected sound signals into electrical signals, which are then received by the audio circuit 1060, converted into audio data, and then processed by the processor 1080 before being transmitted via the RF circuit 1010 to, for example, another mobile phone, or the audio data can be output to the memory 1020 for further processing.

[0109] WiFi is a short-range wireless transmission technology. Through the WiFi module 1070, mobile phones can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 3 The WiFi module 1070 is shown, but it is understood that it is not an essential component of a mobile phone and can be omitted as needed without changing the essence of the invention.

[0110] The processor 1080 is the control center of the mobile phone, connecting various parts of the phone through various interfaces and lines. It executes software programs and / or modules stored in the memory 1020 and calls data stored in the memory 1020 to perform various functions and process data, thereby providing overall monitoring of the phone. Optionally, the processor 1080 may include one or more processing units; preferably, the processor 1080 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 1080.

[0111] The mobile phone also includes a power supply 1090 (such as a battery) that supplies power to various components. Preferably, the power supply can be logically connected to the processor 1080 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0112] Although not shown, mobile phones may also include a camera, Bluetooth module, etc., which will not be described in detail here.

[0113] In this embodiment of the application, the processor 1080 included in the terminal also has the following functions:

[0114] S1. During the recording of cycling videos, cycling status data is calculated based on sensor data;

[0115] S2. Identify at least one cycling interest event based on cycling status data, and classify the strength level of the cycling interest event;

[0116] S3. Store cycling video clips corresponding to cycling interest events according to their strength level.

[0117] This application also provides a computer-readable storage medium for storing program code that executes any one of the implementation methods for identifying cycling interest events described in the foregoing embodiments.

[0118] This application provides a method, device, equipment, and storage medium for identifying cycling interest events. During cycling video recording, cycling status data is calculated based on sensor data. Cycling interest events are identified in real time based on the cycling status data, and the strength levels of the cycling interest events are classified. Cycling video segments corresponding to the strength levels of the cycling interest events are stored. When storage space is insufficient, weak-level cycling video segments are automatically deleted. This solves the technical problem that traditional action cameras require manual start and stop of video recording, and the long duration of cycling leads to insufficient storage space, making it impossible to identify exciting moments of cycling.

[0119] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0120] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0121] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0122] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0123] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0124] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0125] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0126] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A cycling interest event identification method characterized by, The method comprises the following steps: S1, calculating the riding state data according to the sensor data during the recording process of the riding video; S2, identifying at least one riding interest event according to the riding state data and dividing the strong and weak levels of the riding interest event; S3, storing the corresponding riding video segments of the riding interest event according to the strong and weak levels; The step S1 specifically comprises: S11, obtaining the sensor data according to the IMU and GPS during the recording process of the riding video; S12, calculating the riding state data of the turning angle, the maximum turning speed, the forward speed, the slope, the pitch angle, the roll angle and the yaw angle based on the sensor data; The step S2 specifically comprises: S21, identifying the bending interest event according to the roll angle and determining the strong and weak levels of the bending interest event; S22, identifying the sharp turning interest event according to the turning angle, the maximum turning speed and the forward speed and determining the strong and weak levels of the sharp turning interest event; S23, identifying the steep up and down slope interest event and the slope rapid change interest event according to the slope and determining the strong and weak levels of the steep up and down slope interest event and the slope rapid change interest event; S24, identifying the sharp acceleration and deceleration interest event according to the forward speed and determining the strong and weak levels of the sharp acceleration and deceleration interest event; The step S21 specifically comprises: identifying N roll angles in an identification period; taking the maximum value of the absolute values of all the roll angles in the identification period as the maximum roll angle; comparing the maximum roll angle with the preset strong and weak level threshold value, if the maximum roll angle is less than the roll angle corresponding to the weakest strong and weak level, the identification period is not the bending interest event, otherwise, the identification period is the bending interest event, and the strong and weak levels of the bending interest event are determined according to the comparison result of the maximum roll angle and the preset strong and weak level threshold value; The step S22 specifically comprises: identifying N yaw angles and forward speeds in an identification period; determining the turning angle according to the maximum yaw angle and the minimum yaw angle in the identification period; determining the maximum turning speed according to the absolute values of the differences between the adjacent yaw angles; comparing the forward speed, the turning angle and the maximum turning speed with the preset strong and weak level threshold value respectively, if any one of the forward speed, the turning angle and the maximum turning speed is less than the forward speed, the turning angle and the maximum turning speed corresponding to the weakest strong and weak level, the identification period is not the sharp turning interest event, otherwise, the identification period is the sharp turning interest event, and the minimum strong and weak level is determined as the strong and weak levels of the sharp turning interest event according to the comparison result of the forward speed, the turning angle and the maximum turning speed and the preset strong and weak level threshold value; The step S23 specifically comprises: identifying N steep slopes in an identification period; taking the maximum value of the absolute values of all the steep slopes in the identification period as the maximum steep slope; determining the maximum slope difference according to the maximum value of the absolute values of the differences between the slopes at the preset intervals in the identification period; The maximum steep slope is compared with a preset strength level threshold value. If the maximum steep slope is less than a steep slope corresponding to a weakest strength level, it is determined that the period is not an up-and-down steep slope interesting event. Otherwise, it is determined that the period is an up-and-down steep slope interesting event. The strength level of the up-and-down steep slope interesting event is determined according to the comparison result of the maximum steep slope and the preset strength level threshold value. The maximum slope difference is compared with a preset strength level threshold value. If the maximum slope difference is less than a slope difference corresponding to a weakest strength level, it is determined that the period is not a slope rapid change interesting event. Otherwise, it is determined that the period is a slope rapid change interesting event. The strength level of the slope rapid change interesting event is determined according to the comparison result of the maximum slope difference and the preset strength level threshold value. The step S24 is specifically: N forward speeds are identified in one identification period. The maximum forward speed difference is determined according to absolute values of difference between preset interval forward speeds. The maximum forward speed difference is compared with a preset strength level threshold value. If the maximum forward speed difference is less than a forward speed difference corresponding to a weakest strength level, it is determined that the period is not an urgent acceleration and urgent deceleration interesting event. Otherwise, it is determined that the period is an urgent acceleration and urgent deceleration interesting event. The strength level of the urgent acceleration and urgent deceleration interesting event is determined according to the comparison result of the maximum forward speed difference and the preset strength level threshold value.

2. A cycling interest event identification apparatus characterized by, Comprise: A calculation unit configured to calculate cycling state data according to sensor data during a cycling video recording process; An identification unit configured to identify at least one cycling interesting event according to the cycling state data, and divide a strength level of the cycling interesting event; A storage unit configured to store a cycling video segment corresponding to the cycling interesting event according to the strength level; The calculation unit is specifically configured to: Obtain sensor data according to IMU and GPS during the cycling video recording process; Calculate cycling state data of a turning angle, a maximum turning speed, a forward speed, a slope, a pitch angle, a roll angle and a yaw angle based on the sensor data; The identification unit is specifically configured to: Identify a compression bend interesting event according to the roll angle, and determine a strength level of the compression bend interesting event; Specifically: N roll angles are identified in one identification period; A maximum roll angle is a maximum value of absolute values of all roll angles in the identification period; The maximum roll angle is compared with a preset strength level threshold value. If the maximum roll angle is less than a roll angle corresponding to a weakest strength level, it is determined that the identification period is not a compression bend interesting event. Otherwise, it is determined that the identification period is a compression bend interesting event. The strength level of the compression bend interesting event is determined according to the comparison result of the maximum roll angle and the preset strength level threshold value; An urgent turn interesting event is identified according to the turning angle, the maximum turning speed and the forward speed, and a strength level of the urgent turn interesting event is determined; Specifically: N yaw angles and forward speeds are identified in one identification period; A turning angle is determined according to a maximum yaw angle and a minimum yaw angle in the identification period; A maximum turning speed is determined according to absolute values of difference between adjacent yaw angles; The forward speed, the turning angle and the maximum turning speed are compared with preset strength grade thresholds respectively, if any one of them is less than the forward speed, the turning angle and the maximum turning speed corresponding to the weakest strength grade, the recognition period is not an acute turning interest event, otherwise, the recognition period is an acute turning interest event, and the minimum strength grade is determined as the strength grade of the acute turning interest event according to the comparison results of the forward speed, the turning angle and the maximum turning speed with the preset strength grade thresholds; The up-and-down steep slope interest event and the steep slope change interest event are identified according to the slope, and the strength grades of the up-and-down steep slope interest event and the steep slope change interest event are determined; Specifically, N steep slopes are identified in one recognition period; The maximum value of the absolute values of all the steep slopes in the recognition period is taken as the maximum steep slope; The maximum slope difference is determined according to the maximum value of the absolute values of the differences of the slopes between the preset intervals in the recognition period; The maximum steep slope is compared with the preset strength grade thresholds, if it is less than the steep slope corresponding to the weakest strength grade, the recognition period is not an up-and-down steep slope interest event, otherwise, the recognition period is an up-and-down steep slope interest event, and the strength grade of the up-and-down steep slope interest event is determined according to the comparison results of the maximum steep slope with the preset strength grade thresholds; The maximum slope difference is compared with the preset strength grade thresholds, if it is less than the steep slope difference corresponding to the weakest strength grade, the recognition period is not a steep slope change interest event, otherwise, the recognition period is a steep slope change interest event, and the strength grade of the steep slope change interest event is determined according to the comparison results of the maximum slope difference with the preset strength grade thresholds; The rapid acceleration and rapid deceleration interest events are identified according to the forward speed, and the strength grades of the rapid acceleration and rapid deceleration interest events are determined; Specifically, N forward speeds are identified in one recognition period; The maximum forward speed difference is determined according to the absolute values of the differences between the forward speeds of the preset intervals; The maximum forward speed difference is compared with the preset strength grade thresholds, if it is less than the forward speed difference corresponding to the weakest strength grade, the recognition period is not a rapid acceleration and rapid deceleration interest event, otherwise, the recognition period is a rapid acceleration and rapid deceleration interest event, and the strength grade of the rapid acceleration and rapid deceleration interest event is determined according to the comparison results of the maximum forward speed difference with the preset strength grade thresholds.

3. A cycling interest event identification device characterized by, The device comprises a processor and a memory: The memory is used to store program codes and transmit the program codes to the processor; The processor is used to execute the cycling interest event identification method according to the instructions in the program codes.

4. A computer-readable storage medium, characterized in that, The computer readable storage medium is used to store program codes, and the program codes are used to execute the cycling interest event identification method. The computer readable storage medium is used to store program codes, and the program codes are used to execute the cycling interest event identification method.

Images