Road condition abnormity sensing and sharing method and system based on intelligent riding glasses

Abstract

The invention discloses a road condition abnormity sensing and sharing method and system based on intelligent riding glasses, and the method comprises the steps: collecting multi-source sensing data, such as three-axis acceleration, angular velocity, position information and front view images, through the intelligent riding glasses in a riding process; a bumpy road section, a bumpy road section and a road section with obstacles are identified by combining analysis of road conditions, and road condition event data representing abnormal positions, types and occurrence time of road conditions and corresponding riding directions are uploaded to a server side road condition event database; then, in the subsequent riding process, based on the current position of the subsequent rider, the preset riding route, the current speed and the riding posture, a road condition event within the preset distance range in front is obtained, reminding information is output on the riding intelligent glasses, and dynamic sensing, centralized management and on-demand early warning of the abnormal road condition in front are achieved; and the reminding opportunity and the reminding content are matched with the actual riding state.

Description

Technical Field

[0001] This invention relates to the field of smart cycling glasses, and in particular to a method, system, computer device, and storage medium for road condition anomaly perception and sharing based on smart cycling glasses. Background Technology

[0002] Currently, with the increasing popularity of road cycling, commuting cycling, and long-distance cycling, cyclists are spending extended periods on various road conditions, including urban roads, non-motorized vehicle lanes, mountain roads, and rural roads, leading to a growing reliance on cycling safety. Existing technologies, such as common cycling navigation devices and mobile cycling applications, primarily rely on electronic maps and satellite positioning information to provide cyclists with cycling data such as route planning, speed, mileage, and heart rate. Some solutions allow users to manually mark dangerous sections or accident-prone areas on the map for subsequent alerts.

[0003] However, these solutions based on static map information or manual annotation cannot reflect the real-time condition of the road surface, especially in timely detection of bumpy, potholed, or obstructed sections caused by road damage, temporary obstacles, or sudden construction. Existing systems rely on manual reporting for road condition updates, which has limited spatial and temporal accuracy. Furthermore, they typically rely on mobile phone screen prompts, failing to integrate them with the cyclist's head vision and current speed, resulting in untimely and unintuitive alerts. Cyclists may still encounter sudden road abnormalities while riding at high speeds, increasing the risk of emergency braking, skidding, or collisions with obstacles. Summary of the Invention

[0004] The purpose of this application is to propose a method, system, computer device, and storage medium for road condition anomaly perception and sharing based on smart cycling glasses, so as to solve the technical problem of providing cyclists with timely, accurate, and matching road condition anomaly reminders in a way that matches their cycling status.

[0005] To address the aforementioned technical problems, this application provides a method for road condition anomaly perception and sharing based on smart cycling glasses, employing the following technical solution: The smart cycling glasses worn by cyclists collect multi-source sensor data, including three-axis acceleration, angular velocity, position information, and forward view image. Based on the multi-source sensor data, the road surface condition of the current road segment is analyzed to identify whether there are any road condition anomalies. The road condition anomalies include at least bumpy road segments, pothole road segments, and road segments with obstacles. When a road condition anomaly is identified, road condition event data is generated. The road condition event data includes at least the spatial coordinates of the location where the road condition anomaly occurred, the anomaly type, the time of occurrence, and the corresponding riding direction. The traffic event data is uploaded to the traffic event database on the server side via a wireless communication network, and the traffic event data is stored and updated in the traffic event database. During the subsequent rider's ride, based on the current location of the subsequent rider and the preset riding route, road condition event data matching the preset riding route within a preset distance ahead of the subsequent rider is obtained from the road condition event database; Based on the acquired road condition event data and the current speed and riding posture of the subsequent riders, determine whether to issue a reminder and the corresponding reminder content; The display component and / or voice component of the cycling smart glasses output a warning message indicating abnormal road conditions ahead, prompting subsequent cyclists to take evasive action such as slowing down or taking an alternate route.

[0006] To address the aforementioned technical problems, this application also provides a road condition anomaly perception and sharing system based on smart cycling glasses, employing the following technical solution: The data acquisition module is configured to collect multi-source sensor data, including triaxial acceleration, angular velocity, position information, and forward view image, from the smart cycling glasses worn by cyclists. The generation module is configured to analyze the road surface condition of the current road segment based on the multi-source sensor data, identify whether there are road condition anomalies, the road condition anomalies include at least bumpy road segments, pothole road segments and road segments with obstacles, and generate road condition event data when road condition anomalies are identified, the road condition event data includes at least the spatial coordinates of the location where the road condition anomaly occurred, the anomaly type, the time of occurrence and the corresponding riding direction; The upload module is configured to upload the traffic event data to the traffic event database on the server side via a wireless communication network, and to store and update the traffic event data in the traffic event database. The acquisition module is configured to, during the riding process of a subsequent rider, acquire road condition event data that matches the preset riding route within a preset distance range ahead of the subsequent rider from the road condition event database, based on the current location of the subsequent rider and the preset riding route; The determination module is configured to determine whether to issue a reminder and the corresponding reminder content based on the acquired road condition event data and the current speed and current riding posture of the subsequent riders; The output module is configured to output warning information indicating abnormal road conditions ahead via the display component and / or voice component of the cycling smart glasses, so as to prompt the following riders to take evasive action such as slowing down or taking an alternate route.

[0007] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution: A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the road condition anomaly perception and sharing method based on cycling smart glasses as described above.

[0008] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below: A computer-readable storage medium storing computer-readable instructions, which, when executed by a processor, implement the steps of the road condition anomaly perception and sharing method based on cycling smart glasses as described above.

[0009] Compared with the prior art, the embodiments of this application have the following main advantages: This application discloses a method for road condition anomaly perception and sharing based on cycling smart glasses. During cycling, the smart glasses collect multi-source sensor data, including three-axis acceleration, angular velocity, position information, and forward-view images. Combined with analysis of road conditions, it identifies bumpy sections, pothole sections, and sections with obstacles. Road condition event data representing the location, type, occurrence time, and corresponding cycling direction of the road condition anomaly is uploaded to a server-side road condition event database. Then, during subsequent cycling, based on the rider's current position, preset cycling route, current speed, and cycling posture, road condition events within a preset distance ahead are obtained and alerts are output to the cycling smart glasses. This achieves dynamic perception, centralized management, and on-demand warning of road condition anomalies, ensuring that the timing and content of the alerts match the actual cycling state. This allows for early guidance for riders to slow down or detour, significantly reducing the risk of emergency braking, skidding, falls, or collisions caused by sudden encounters with potholes, bumps, or obstacles. Overall, it solves the technical problem in existing technologies of providing timely, accurate, and time-matched road condition anomaly alerts to riders. Attached Figure Description

[0010] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart of an embodiment of the road condition anomaly perception and sharing method based on cycling smart glasses according to this application; Figure 2 This is a schematic diagram of a road condition anomaly perception and sharing system based on cycling smart glasses according to this application; Figure 3 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0013] refer to Figure 1 The diagram illustrates a flowchart of an embodiment of a road condition anomaly perception and sharing method based on cycling smart glasses according to this application. The method includes the following steps: Step S101: The cycling smart glasses worn by the cyclist collect multi-source sensor data including three-axis acceleration, angular velocity, position information and forward view image.

[0014] In this embodiment, the electronic device running on the road condition anomaly perception and sharing method based on cycling smart glasses can send or receive data via wired or wireless connection. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra wideband) connections, and other currently known or future-developed wireless connection methods.

[0015] In this embodiment, the cycling smart glasses worn by the cyclist integrate an inertial measurement unit (IMU), a satellite positioning module, and a forward-facing camera. The IMU typically includes a three-axis accelerometer and a three-axis gyroscope. The three-axis accelerometer measures the magnitude of linear acceleration in three mutually perpendicular directions within the glasses' own coordinate system, reflecting road vibrations and head movements during cycling. The angular velocity measures the rotational speed of the glasses around the three axes, characterizing changes in the cyclist's head posture. Location information is obtained through the integrated satellite positioning module, acquiring the cyclist's current latitude, longitude, and altitude. This information can be combined with an electronic map for road matching to determine the cyclist's precise location on the road. The forward-facing image is captured by a camera fixed to the front of the glasses frame at a preset frame rate, capturing the scene ahead of the road to identify objects and road surface features along the cycling path. The cycling smart glasses collect and timestamp the aforementioned multi-source sensor data using a unified time reference. For example, they collect triaxial acceleration and angular velocity at a sampling frequency of 100 times per second, and collect front view images at a frame rate of 10 frames per second, while simultaneously recording the position information corresponding to each sampling. This forms a multi-source sensor data sequence with a unified time axis, providing basic data for subsequent analysis.

[0016] Step S102: Analyze the road surface condition of the current road segment based on the multi-source sensor data, identify whether there is a road condition anomaly, the road condition anomaly includes at least a bumpy road segment, a pothole road segment and a road segment with obstacles, and generate road condition event data when a road condition anomaly is identified, the road condition event data includes at least the spatial coordinates of the location where the road condition anomaly occurred, the anomaly type, the time of occurrence and the corresponding riding direction.

[0017] In this embodiment, after collecting multi-source sensor data, the road surface condition of the current road segment is analyzed based on the multi-source sensor data to identify whether there are any road condition anomalies. In this embodiment, road surface condition can be understood as the smoothness of the road surface along the cyclist's path and whether there are any structural changes that affect safe passage. Road condition anomalies include at least bumpy sections, pothole sections, and sections with obstacles. Specifically, within a preset time window, the triaxial acceleration and angular velocity can be filtered and feature extracted to remove high-frequency noise and low-frequency drift components. Features such as the peak value of vertical acceleration, the root mean square value of acceleration, the energy distribution of the vibration spectrum, and the rate of change of angular velocity are calculated, and the judgment threshold is adaptively adjusted according to the cycling speed. For example, when riding at a speed of 25 km / h, if a large negative peak in vertical acceleration is detected within a short period of time, followed by a positive rebound, and the location information indicates that the location is on the same road, then the location can be determined to be a potholed section of road. If moderate amplitude and high frequency vibrations are detected in both vertical and horizontal acceleration over multiple consecutive sampling periods, while the angular velocity changes little, then the location can be determined to be a bumpy section of road. If a rock, roadblock, or fallen object is identified in the current view image by the object detection algorithm on the preset riding route, and it is accompanied by deceleration and slight vibration when approaching, then the section of road ahead can be determined to have obstacles. When any of the above-mentioned road condition anomalies are identified at a certain location, this embodiment generates corresponding road condition event data. The road condition event data includes at least the spatial coordinates of the location where the road condition anomaly occurs (e.g., latitude and longitude, road chain markers after map matching, and mileage along the road), the anomaly type (bumpy road section, pothole road section, or road section with obstacles), the time of occurrence, and the corresponding riding direction. The riding direction can be calculated based on continuous location information to obtain the azimuth angle of travel along the road, which is used to distinguish different reminder needs for the same location in two opposite directions of travel.

[0018] Step S103: Upload the traffic event data to the traffic event database on the server side via a wireless communication network, and store and update the traffic event data in the traffic event database.

[0019] In this embodiment, after generating traffic event data, the data is uploaded to a traffic event database on the server side via a wireless communication module built into the cycling smart glasses. The wireless communication module can use existing communication methods such as cellular mobile communication, Wi-Fi, or low-power wide-area network (LPWAN) to send locally cached traffic events in batches to the server when the background network is available. The server-side has a database system specifically designed to store and manage large amounts of traffic event data. In this database, traffic event data can be categorized and stored according to road number, spatial coordinate grid, anomaly type, and time index. Existing records are updated when new events arrive; for example, multiple traffic events with similar spatial locations and anomaly types can be merged, and the number of reports and the most recent occurrence time can be recorded to form a stable traffic anomaly record. In this way, traffic event data can be effectively stored and updated in the traffic event database, maintaining the timeliness and reliability of the data.

[0020] Step S104: During the subsequent rider's ride, based on the current position of the subsequent rider and the preset riding route, obtain road condition event data that matches the preset riding route within a preset distance range ahead of the subsequent rider from the road condition event database.

[0021] In this embodiment, during the subsequent cyclist's ride, the smart cycling glasses also collect their own location information and riding direction in real time, and obtain a preset riding route based on the riding route pre-set by the cyclist when using the navigation function. Based on the subsequent cyclist's current location and the preset riding route, this embodiment retrieves road condition event data matching the preset riding route within a preset distance range ahead of the subsequent cyclist from the road condition event database. Specifically, the server can search for confirmed road condition anomaly records within a range of 100 to 300 meters ahead of the subsequent cyclist, based on the current road chain identifier and mileage along the road, and further filter records consistent with the subsequent cyclist's direction of travel. For cases with branching or multiple optional routes, road condition anomaly records corresponding to the planned road sequence in the preset riding route can be filtered out and sorted by distance, and the filtering results are returned to the smart cycling glasses terminal in the form of compressed data packets. This query method based on current location and preset riding route ensures that the subsequent cyclist obtains road condition anomalies that they will actually encounter on their forward path, rather than other road information unrelated to them.

[0022] Step S105: Based on the acquired road condition event data and the current speed and riding posture of the subsequent cyclist, determine whether to issue a reminder and the corresponding reminder content.

[0023] After acquiring road condition event data ahead, this embodiment determines whether to issue a warning and the corresponding warning content based on the acquired road condition event data, the current speed of subsequent cyclists, and their current riding posture. The current speed can be calculated from the change in location information over time. The current riding posture can be estimated by analyzing the components of triaxial acceleration and angular velocity in the direction of gravity, as well as the head tilt angle, for example, distinguishing whether the cyclist is in a normal seated riding posture, standing pedaling, or emergency braking posture. This embodiment calculates the safe braking distance based on the current speed and a preset safe braking deceleration, and determines a reasonable warning distance based on the type and severity of the road condition anomaly. When the distance between the road condition anomaly location and the current location is less than the warning distance but greater than the minimum warning distance, a warning is deemed necessary; conversely, if the distance is too far or the riding speed is very low, a warning may be temporarily withheld or only a weak warning may be indicated. The alert content is generated based on the type and severity of anomalies in the road condition event data. For example, for potholes, a "pothole ahead, please slow down" alert can be generated. For sections with obstacles, a "obstacle ahead, please detour" alert can be generated. The severity and advance distance can be appropriately increased depending on the riding posture during rapid acceleration or downhill conditions.

[0024] In step S106, the display component and / or voice component of the cycling smart glasses output a warning message indicating abnormal road conditions ahead, so as to prompt the following riders to take evasive action such as slowing down or taking an alternate route.

[0025] After determining the need for a reminder and the specific content of the reminder, this embodiment uses the display component and / or voice component of the cycling smart glasses to output a reminder message indicating abnormal road conditions ahead, prompting subsequent cyclists to take evasive action such as slowing down or taking an alternate route. The display component can be a display screen integrated into the lens or frame, used to overlay a road diagram and road condition markers on the cyclist's field of vision. For example, it can mark the location of the road condition abnormality with a prominent icon on the display track of a preset cycling route, and display the type of abnormality and distance information in text form next to the icon. The voice component can be a built-in speaker or bone conduction sound device, used to prompt the cyclist about the type of road condition abnormality ahead and the suggested actions in a voice broadcast. Since the reminder message appears directly in the cyclist's field of vision and auditory channels, the cyclist can obtain information about abnormal road conditions ahead without taking their eyes off the road or operating their phone, thereby slowing down, changing their trajectory, or avoiding obstacles in advance during actual cycling, significantly reducing the risk of falls or collisions caused by suddenly encountering potholes, bumps, or obstacles. By continuously executing the above steps, this invention utilizes multi-source sensor data collected by smart cycling glasses during cycling to achieve real-time perception, sharing, and forward warning of abnormal road conditions, solving the technical problem in the prior art of providing timely, accurate, and matching reminders of abnormal road conditions to cyclists in a way that matches their cycling status.

[0026] This application utilizes smart cycling glasses to collect multi-source sensor data, including triaxial acceleration, angular velocity, position information, and forward-view images, during cycling. Combined with road condition analysis, it identifies bumpy, potholed, and obstacle-prone sections. Road condition event data, representing the location, type, time of occurrence, and corresponding cycling direction of road anomalies, is uploaded to a server-side road condition event database. Subsequently, based on the rider's current position, preset route, current speed, and cycling posture, road condition events within a preset distance ahead are obtained and displayed on the smart cycling glasses as alerts. This achieves dynamic perception, centralized management, and on-demand warning of road condition anomalies, ensuring that the timing and content of alerts match the actual cycling state. This allows for advance guidance for riders to slow down or detour, significantly reducing the risk of emergency braking, skidding, falls, or collisions caused by sudden encounters with potholes, bumps, or obstacles. Overall, it solves the technical problem in existing technologies of providing timely, accurate, and time-matched road condition alerts to riders.

[0027] In some optional implementations of this embodiment, the step of analyzing the road surface condition of the current road segment based on the multi-source sensor data and identifying whether there are any abnormal road conditions includes: The acquired triaxial acceleration and angular velocity data are time-aligned and filtered to remove high-frequency noise and low-frequency drift. The vibration intensity characteristics and angular velocity change characteristics are calculated within a sliding time window using a preset detection cycle. When the vibration intensity characteristic and the angular velocity change characteristic simultaneously meet the determination conditions corresponding to bumpy road sections, pothole road sections, or road sections with obstacles, it is determined that there is a corresponding type of road condition anomaly in the current road section and corresponding road condition event data is generated.

[0028] In this embodiment, after the cycling smart glasses collect triaxial acceleration and angular velocity, the processing unit first performs time alignment on the data from different sensor channels. Since the sampling frequencies of the accelerometer, gyroscope, and other sensors may differ, the processing unit can unify the data from each channel to the same sampling time using timestamp interpolation or resampling. Subsequently, the aligned data is filtered, using common signal processing methods such as bandpass filters or wavelet filters to remove high-frequency electronic noise and low-frequency drift components, ensuring that the remaining signal primarily reflects the vibration characteristics caused by the road surface. Based on this, the continuously sampled data is segmented and statistically analyzed within a sliding time window with a preset detection cycle. The sliding time window refers to moving and calculating the data along the time axis in a fixed-length window (e.g., 1 second or 2 seconds), with each window moving a small segment to ensure the continuity and real-time nature of the detection. Within each time window, the processing unit calculates vibration intensity characteristics (e.g., root mean square value of acceleration, peak-to-peak value, or energy in a specific frequency band) and angular velocity change characteristics (e.g., the average absolute value of the first-order difference of angular velocity). These characteristics reflect the degree of vibration caused by the road surface and changes in head posture during cycling. Pre-defined criteria are established for bumpy road sections, potholed road sections, and road sections with obstacles, each corresponding to the aforementioned characteristics. For example, bumpy road sections correspond to medium-amplitude, continuous vibration characteristics; potholed road sections correspond to sudden, high-amplitude vibration characteristics within a short period; and road sections with obstacles are typically accompanied by specific types of vibration and deceleration patterns. When the vibration intensity and angular velocity change characteristics within a certain time window simultaneously meet a certain type of criterion, the processing unit can determine that the current road section has a corresponding type of road condition anomaly and generate corresponding road condition event data at that location. The detection results of that time window are then archived as an event record for uploading and sharing.

[0029] This application performs time alignment and filtering on the collected triaxial acceleration and angular velocity during the steps of analyzing road conditions and identifying road anomalies. Vibration intensity characteristics and angular velocity change characteristics are calculated within a sliding time window. Road condition event data is only generated when these characteristics simultaneously meet the criteria corresponding to bumpy road sections, pothole sections, or the presence of obstacles. This ensures that the identification of road condition anomalies is based on a pre-processed stable feature sequence rather than single-point instantaneous data, thereby improving the robustness and sensitivity of road condition anomaly detection. It also reduces false alarms caused by sensor noise, natural head movement, or short-term operations, making the road condition events uploaded to the road condition event database more reliable and providing an accurate data foundation for subsequent sharing and early warning.

[0030] In some optional implementations of this embodiment, the step of determining that the current road segment has a corresponding type of road condition anomaly and generating corresponding road condition event data when the vibration intensity characteristic and the angular velocity change characteristic simultaneously satisfy the determination conditions corresponding to a bumpy road segment, a potholed road segment, or a road segment with obstacles includes: Adjust the judgment thresholds corresponding to the vibration intensity feature and the angular velocity change feature according to the current velocity; Based on the proportion of the components of triaxial acceleration in the vertical and horizontal directions, continuous high-amplitude vertical acceleration changes are identified as pothole sections, and medium-amplitude and high-frequency vibrations are identified as bumpy sections. When significant deceleration is detected during vibration and a physical target on the preset riding route is detected in the forward view image, the current road segment is determined to be a road segment with obstacles.

[0031] In this embodiment, since the vibration manifestations of the same actual road surface defects differ at different riding speeds, to avoid misjudgment or missed judgment in low-speed or high-speed scenarios, the processing unit dynamically adjusts the judgment thresholds corresponding to the vibration intensity characteristics and angular velocity change characteristics based on the current speed. For example, the judgment threshold is appropriately lowered when riding at high speeds so that smaller potholes can be identified, while the threshold is appropriately raised when riding at low speeds to avoid misidentifying small vibrations caused by normal starting or operation as abnormal road conditions. To distinguish between bumpy road sections and pothole sections, the processing unit decomposes the triaxial acceleration into vertical and horizontal components. By analyzing the ratio and change pattern of the vertical and horizontal components, when continuous high-amplitude vertical acceleration changes are observed in a short period of time, while the horizontal acceleration changes are relatively small and exhibit a "sudden impact followed by a rebound" pattern, the current road section can be determined to be a pothole section. When both vertical and horizontal acceleration exhibit moderate-amplitude but high-frequency vibrations that persist for a period of time, the road section can be determined to be a bumpy road section, such as riding on a rough gravel road or continuous speed bumps. For road sections with obstacles, the processing unit monitors changes in riding speed while analyzing vibration characteristics. When a significant deceleration is detected before or after approaching a certain position, and a physical target is identified on the preset riding route through the target detection algorithm in the front view image (e.g., identifying stones, fallen roadblocks, or other vehicle debris occupying the center of the lane), the current road section can be determined as a road section with obstacles, thus distinguishing it from ordinary bumps or potholes.

[0032] This application achieves hierarchical classification and identification of different types of abnormal road conditions by dynamically adjusting the judgment thresholds of vibration intensity characteristics and angular velocity change characteristics based on the current speed when identifying bumpy road sections, pothole sections, and road sections with obstacles. It also distinguishes between continuous high-amplitude vertical acceleration changes and medium-amplitude high-frequency vibrations by combining the proportion of triaxial acceleration components in the vertical and horizontal directions. Furthermore, it determines the presence of obstacles by combining deceleration behavior with physical targets in the forward view image. This enables the system to adaptively distinguish between pothole sections, continuous bumpy road sections, and road sections occupied by obstacles at different riding speeds, thereby reducing the false judgment rate between different types while ensuring the detection rate. This provides accurate category information for matching different reminder strategies and risk avoidance suggestions according to the road condition type.

[0033] In some optional implementations of this embodiment, the steps of uploading the traffic event data to a traffic event database on the server side via a wireless communication network, and storing and updating the traffic event data in the traffic event database, include: Based on the spatial coordinates of the location where the road condition anomaly occurred in the road condition event data, multiple road condition event data are clustered in a preset spatial neighborhood, and road condition event data with similar spatial locations and the same anomaly type are merged into one road condition anomaly record. Based on the number of reports and the reporting time of the traffic event data corresponding to the same traffic anomaly record, the credibility and validity period of the traffic anomaly record are calculated, and the credibility and validity period are stored together with the traffic anomaly record in the traffic event database.

[0034] In this embodiment, after receiving road condition event data from multiple cycling smart glasses terminals, the server clusters the multiple road condition event data within a preset spatial neighborhood based on the spatial coordinates of the location where the road condition anomaly occurred. The preset spatial neighborhood can be defined as an area with a preset radius (e.g., 10 meters or 20 meters) centered on a certain event coordinate, or it can be a linear neighborhood based on road mileage coordinates. When the spatial locations of multiple road condition event data fall within the same spatial neighborhood and the anomaly type is the same (e.g., all are pothole sections), these road condition event data are merged into a single road condition anomaly record, thereby reducing duplicate information and forming a summary description of the anomaly at that location. Based on this, the server calculates the credibility and validity period of a road condition anomaly record according to the number of reports and the reporting time of the road condition event data corresponding to the same record. Credibility can be understood as the probability or confidence level of whether the road condition anomaly actually exists; for example, the more reports and the closer the most recent report time is to the current moment, the higher the credibility. The validity period can be automatically set according to the type of road condition anomaly and the most recent report time; for example, the validity period for temporary obstacles is shorter, while the validity period for road damage can be appropriately extended. The server stores the calculated credibility and validity period along with the road condition anomaly record in the road condition event database, so that subsequent queries can not only identify the location and type of the anomaly, but also determine whether it is appropriate to issue a warning to subsequent cyclists based on the credibility and validity period.

[0035] This application clusters multiple road condition event data within a preset spatial neighborhood based on the spatial coordinates of the location where the road condition anomaly occurred during the storage and updating process. Events with similar spatial locations and the same anomaly type are merged into road condition anomaly records. The credibility and validity period of the road condition anomaly records are calculated based on the number of reports and the reporting time of the corresponding road condition events and stored together. This enables the server to form sparse, stable road condition anomaly records with confidence attributes from a large number of scattered events. This reduces redundant storage and duplicate prompts, and enhances the reliability and timeliness of road condition anomaly information by introducing credibility and validity period, providing a basis for filtering false or disappeared anomalies when riders query later.

[0036] In some optional implementations of this embodiment, the step of obtaining road condition event data matching the preset cycling route within a preset distance ahead of the subsequent cyclist from the road condition event database based on the current position and preset cycling route of the subsequent cyclist during the subsequent cyclist's ride includes: Filter out abnormal road condition records from the road condition event database that have a credibility level not lower than a preset credibility threshold and are within the validity period; The warning distance is calculated based on the current speed of subsequent cyclists and the preset time margin; Based on the warning distance, identify road condition anomaly records that match the preset cycling route within a preset distance range ahead of the subsequent cyclist, and use these road condition anomaly records as road condition event data.

[0037] In this embodiment, after receiving the current location information and preset cycling route of the subsequent cyclist, the server first filters out abnormal road condition records from the road condition event database that have a credibility level not lower than a preset credibility threshold and are within their validity period, thereby eliminating those abnormal points that have been reported infrequently, are old, or have already been repaired. For example, the credibility threshold can be set to 0.6, retaining only records with a credibility level greater than or equal to 0.6. Subsequently, the warning distance is calculated based on the subsequent cyclist's current speed and a preset time margin. The preset time margin can be understood as the time required from when the cyclist receives the reminder to when they complete deceleration or detour, for example, set to 3 seconds or 5 seconds. The warning distance can then be determined by multiplying the current speed by the time margin and adding a certain safety margin. For example, at a speed of 20 km / h and a time margin of 5 seconds, the basic warning distance is approximately 30 meters, and adding a 5-meter safety margin yields 35 meters. According to the warning distance, the server searches for road condition anomaly records matching the preset cycling route within a preset distance ahead of the current position of subsequent cyclists. Matching the preset cycling route means that the road nodes or road segments containing these anomaly records are within the road sequence included in the preset route and are located after the current position in the direction of travel. Finally, the server returns these filtered road condition anomaly records as road condition event data to the cycling smart glasses of subsequent cyclists, ensuring that the terminal only processes reliable and valid road condition anomaly information within a limited distance ahead of itself.

[0038] This application achieves dual constraint selection of road condition anomaly records in the spatiotemporal dimensions when acquiring road condition event data during subsequent riders' rides. This ensures that the road condition anomalies pushed to subsequent riders are both currently existing and reliable anomalies, and are located within a reasonable distance ahead of the actual travel path. This avoids pushing road condition information that is irrelevant or too far away to subsequent riders, thus improving the targeting and effectiveness of road condition warnings.

[0039] In some optional implementations of this embodiment, the step of determining whether to issue a reminder and the corresponding reminder content based on the acquired road condition event data and the current speed and current riding posture of the subsequent cyclist includes: Calculate the safe braking distance based on the current speed of subsequent riders and the preset braking deceleration; If the distance between the location of the abnormal road condition record and the current location of the subsequent rider is less than the safe braking distance, it is determined that a reminder is needed; otherwise, it is determined that no reminder is needed. The corresponding alert content is determined based on the type and severity of the abnormality recorded in the road condition log.

[0040] In this embodiment, after obtaining a record of abnormal road conditions, the smart cycling glasses terminal calculates a safe braking distance based on the current speed of the subsequent cyclist and a preset braking deceleration. The preset braking deceleration can be set according to the comfortable deceleration range of a typical cyclist on a dry road surface, for example, 1.5 m / s to 2.5 m / s, and can also consider the braking capacity achievable under different riding postures. In actual calculation, a distance calculation formula based on uniformly decelerated motion can be used, converting the current speed to meters per second and substituting it into the formula to obtain the distance required for the cyclist to reduce their speed to a safe level at that deceleration. When the distance between the location of the abnormal road condition record and the current location of the subsequent cyclist is less than the safe braking distance, the terminal determines that if the cyclist is not immediately reminded to slow down, there may not be enough distance to complete safe braking, and therefore a reminder is required; conversely, when the distance is significantly greater than the safe braking distance, a reminder can be temporarily withheld to avoid premature prompting that could burden the cyclist's attention or lead to misjudgment. Once a warning is determined, the terminal determines the corresponding warning content based on the type and severity of the road condition anomaly record. For example, for severely potholed road sections, it can generate a warning such as "There is a severe pothole XX meters ahead, please slow down immediately." For moderately bumpy road sections, it can generate a warning such as "The road surface is uneven XX meters ahead, please control your speed." For road sections with obstacles, it can generate a warning such as "There is an obstacle XX meters ahead, please detour in advance." When the severity is high, it can use a stronger tone or repeat the warning multiple times.

[0041] This application determines whether to issue a warning and the corresponding warning content based on the acquired road condition event data and the current speed and riding posture of the cyclist. It calculates the safe braking distance based on the current speed and preset braking deceleration, and only determines that a warning is needed when the distance between the location of the road condition anomaly record and the current location is less than the safe braking distance. At the same time, it matches different warning content according to the anomaly type and severity of the road condition anomaly record. This makes the warning trigger condition directly reflect the distance required for the cyclist to safely decelerate or detour under the current conditions, and matches the warning content with the actual level of danger. This avoids "fatigue warnings" caused by warnings that are too early or too frequent, and avoids insufficient braking distance caused by warnings that are too late. It improves the consistency between early warning decision-making and riding safety capabilities, and makes the warnings more in line with the actual reaction needs of the cyclist.

[0042] In some optional implementations of this embodiment, the step of outputting warning information indicating abnormal road conditions ahead by the display component and / or voice component of the cycling smart glasses to prompt subsequent cyclists to take evasive action such as slowing down or taking an alternate route includes: The abnormal road condition location markers are superimposed on the display screen of the display component along the preset cycling route, and the abnormality type and text prompts for slowing down or detouring are displayed near the abnormal road condition location markers. When it is determined that a reminder is needed, a voice reminder message containing information on the type of road condition anomaly and the distance will be broadcast via the voice component.

[0043] In this embodiment, the display component of the cycling smart glasses can overlay a route trajectory representing a preset cycling route onto its display screen, such as displaying the current cycling direction in the form of lines or arrows. When an abnormal road condition is detected ahead, a road condition location marker is overlaid at the corresponding position on the route trajectory. This marker can be highlighted with a conspicuous icon or color, and a text prompt is overlaid near the location marker. The text content includes the type of abnormality and suggested deceleration or detour operations, such as "pothole - slow down" or "obstacle - detour". When it is determined that a reminder is needed based on the above judgment results, the voice component of the cycling smart glasses simultaneously broadcasts a voice reminder message containing the type of road condition abnormality and distance information, such as "pothole ahead 20 meters, please slow down". The voice content corresponds to the icons and text on the display screen, so that even if the cyclist does not deliberately look at the display screen, they can obtain key reminder information through hearing, thereby taking more timely hazard avoidance operations such as slowing down or detours during actual cycling, improving overall cycling safety.

[0044] This application achieves coordinated output of visual and voice prompts by overlaying abnormal road condition location markers along a preset cycling route on the display screen when the display component and / or voice component of the cycling smart glasses output reminder information. Near the markers, text prompts indicating the type of abnormality and suggesting slowing down or detouring are displayed. Simultaneously, when a reminder is deemed necessary, the voice component broadcasts a voice prompt containing information on the type and distance of the abnormal road condition. This allows cyclists to intuitively understand the location, type, and suggested actions of abnormal road conditions ahead through overlaid icons in their field of vision and voice broadcasts while maintaining a forward-looking gaze and hands on the handlebars. This reduces reliance on mobile phones or other terminals, minimizes distraction, and improves the efficiency of perceiving and avoiding dangerous road sections in actual cycling scenarios.

[0045] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0046] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by 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 steps in the flowcharts of the accompanying 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 some of the sub-steps or stages of other steps.

[0047] Further reference Figure 2 As a response to the above Figure 1 To implement the method shown, this application provides an embodiment of a road condition anomaly perception and sharing system based on cycling smart glasses. This system embodiment is similar to... Figure 1 Corresponding to the method embodiments shown, the system can be specifically applied to various electronic devices.

[0048] like Figure 2 As shown, the road condition anomaly perception and sharing system 200 based on cycling smart glasses described in this embodiment includes: a data acquisition module 201, a generation module 202, an upload module 203, an acquisition module 204, a determination module 205, and an output module 206. Wherein: The data acquisition module 201 is configured to collect multi-source sensor data, including triaxial acceleration, angular velocity, position information and forward view image, from the smart cycling glasses worn by the cyclist. The generation module 202 is configured to analyze the road surface condition of the current road segment based on the multi-source sensor data, identify whether there is a road condition anomaly, the road condition anomaly includes at least a bumpy road segment, a pothole road segment and a road segment with obstacles, and generate road condition event data when a road condition anomaly is identified, the road condition event data includes at least the spatial coordinates of the location where the road condition anomaly occurred, the anomaly type, the time of occurrence and the corresponding riding direction; The upload module 203 is configured to upload the traffic event data to the traffic event database on the server side via a wireless communication network, and to store and update the traffic event data in the traffic event database. The acquisition module 204 is configured to, during the riding process of a subsequent rider, acquire road condition event data that matches the preset riding route within a preset distance range ahead of the subsequent rider from the road condition event database, based on the current position of the subsequent rider and the preset riding route; The determination module 205 is configured to determine whether to issue a reminder and the corresponding reminder content based on the acquired road condition event data and the current speed and current riding posture of the subsequent rider; The output module 206 is configured to output a warning message indicating abnormal road conditions ahead via the display component and / or voice component of the cycling smart glasses, so as to prompt the following riders to take evasive action such as slowing down or detouring in advance.

[0049] The road condition anomaly perception and sharing system based on smart cycling glasses provided in this embodiment of the invention can realize all the processes of the road condition anomaly perception and sharing method based on smart cycling glasses in the above embodiments. The functions and technical effects of each module in the device are the same as those of the road condition anomaly perception and sharing method based on smart cycling glasses in the above embodiments, and will not be repeated here.

[0050] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0051] The computer device 3 includes a memory 31, a processor 32, and a network interface 33 that are interconnected via a system bus. It should be noted that only the computer device 3 with components 31-33 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0052] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0053] The memory 31 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 31 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In other embodiments, the memory 31 may also be an external storage device of the computer device 3, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 3. Of course, the memory 31 may also include both the internal storage unit and its external storage device of the computer device 3. In this embodiment, the memory 31 is typically used to store the operating system and various application software installed on the computer device 3, such as computer-readable instructions for a road condition anomaly perception and sharing method based on cycling smart glasses. In addition, the memory 31 can also be used to temporarily store various types of data that have been output or will be output.

[0054] In some embodiments, the processor 32 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 32 is typically used to control the overall operation of the computer device 3. In this embodiment, the processor 32 is used to execute computer-readable instructions stored in the memory 31 or to process data, for example, to execute the computer-readable instructions of the road condition anomaly perception and sharing method based on cycling smart glasses.

[0055] The network interface 33 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 3 and other electronic devices.

[0056] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the above-described method for road condition anomaly perception and sharing based on cycling smart glasses.

[0057] 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 this application, in essence, 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 ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0058] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for road condition anomaly perception and sharing based on smart cycling glasses, characterized in that, Includes the following steps: The smart cycling glasses worn by cyclists collect multi-source sensor data, including three-axis acceleration, angular velocity, position information, and forward view image. Based on the multi-source sensor data, the road surface condition of the current road segment is analyzed to identify whether there are any road condition anomalies. The road condition anomalies include at least bumpy road segments, pothole road segments, and road segments with obstacles. When a road condition anomaly is identified, road condition event data is generated. The road condition event data includes at least the spatial coordinates of the location where the road condition anomaly occurred, the anomaly type, the time of occurrence, and the corresponding riding direction. The traffic event data is uploaded to the traffic event database on the server side via a wireless communication network, and the traffic event data is stored and updated in the traffic event database. During the subsequent rider's ride, based on the current location of the subsequent rider and the preset riding route, road condition event data matching the preset riding route within a preset distance ahead of the subsequent rider is obtained from the road condition event database; Based on the acquired road condition event data and the current speed and riding posture of the subsequent riders, determine whether to issue a reminder and the corresponding reminder content; The display component and / or voice component of the cycling smart glasses output a warning message indicating abnormal road conditions ahead, prompting subsequent cyclists to take evasive action such as slowing down or taking an alternate route.

2. The method for road condition anomaly perception and sharing based on cycling smart glasses according to claim 1, characterized in that, The step of analyzing the road surface condition of the current road segment based on the multi-source sensor data and identifying whether there are any abnormal road conditions includes: The acquired triaxial acceleration and angular velocity data are time-aligned and filtered to remove high-frequency noise and low-frequency drift. The vibration intensity characteristics and angular velocity change characteristics are calculated within a sliding time window using a preset detection cycle. When the vibration intensity characteristic and the angular velocity change characteristic simultaneously meet the determination conditions corresponding to bumpy road sections, pothole road sections, or road sections with obstacles, it is determined that there is a corresponding type of road condition anomaly in the current road section and corresponding road condition event data is generated.

3. The method for road condition anomaly perception and sharing based on cycling smart glasses according to claim 2, characterized in that, The step of determining that the current road segment has a corresponding type of road condition anomaly and generating corresponding road condition event data when the vibration intensity characteristic and the angular velocity change characteristic simultaneously meet the judgment conditions corresponding to bumpy road segments, pothole road segments, or the presence of obstacles includes: Adjust the judgment thresholds corresponding to the vibration intensity feature and the angular velocity change feature according to the current velocity; Based on the proportion of the components of triaxial acceleration in the vertical and horizontal directions, continuous high-amplitude vertical acceleration changes are identified as pothole sections, and medium-amplitude and high-frequency vibrations are identified as bumpy sections. When significant deceleration is detected during vibration and a physical target on the preset riding route is detected in the forward view image, the current road segment is determined to be a road segment with obstacles.

4. The method for road condition anomaly perception and sharing based on cycling smart glasses according to claim 1, characterized in that, The steps of uploading the traffic event data to the traffic event database on the server side via a wireless communication network, and storing and updating the traffic event data in the traffic event database, include: Based on the spatial coordinates of the location where the road condition anomaly occurred in the road condition event data, multiple road condition event data are clustered in a preset spatial neighborhood, and road condition event data with similar spatial locations and the same anomaly type are merged into one road condition anomaly record. Based on the number of reports and the reporting time of the traffic event data corresponding to the same traffic anomaly record, the credibility and validity period of the traffic anomaly record are calculated, and the credibility and validity period are stored together with the traffic anomaly record in the traffic event database.

5. The method for road condition anomaly perception and sharing based on cycling smart glasses according to claim 1, characterized in that, The step of retrieving road condition event data matching the preset cycling route within a preset distance ahead of the subsequent cyclist from the road condition event database, based on the current location and preset cycling route of the subsequent cyclist, includes: Filter out abnormal road condition records from the road condition event database that have a credibility level not lower than a preset credibility threshold and are within the validity period; The warning distance is calculated based on the current speed of subsequent cyclists and the preset time margin; Based on the warning distance, identify road condition anomaly records that match the preset cycling route within a preset distance range ahead of the subsequent cyclist, and use these road condition anomaly records as road condition event data.

6. The method for road condition anomaly perception and sharing based on cycling smart glasses according to claim 1, characterized in that, The step of determining whether to issue a reminder and the corresponding reminder content based on the acquired road condition event data and the current speed and riding posture of the subsequent cyclist includes: Calculate the safe braking distance based on the current speed of subsequent riders and the preset braking deceleration; If the distance between the location of the abnormal road condition record and the current location of the subsequent rider is less than the safe braking distance, it is determined that a reminder is needed; otherwise, it is determined that no reminder is needed. The corresponding alert content is determined based on the type and severity of the abnormality recorded in the road condition log.

7. The method for road condition anomaly perception and sharing based on cycling smart glasses according to claim 1, characterized in that, The step of outputting a warning message indicating abnormal road conditions ahead by the display component and / or voice component of the cycling smart glasses to prompt subsequent cyclists to take evasive action such as slowing down or taking an alternate route includes: The abnormal road condition location markers are superimposed on the display screen of the display component along the preset cycling route, and the abnormality type and text prompts for slowing down or detouring are displayed near the abnormal road condition location markers. When it is determined that a reminder is needed, a voice reminder message containing information on the type of road condition anomaly and the distance will be broadcast via the voice component.

8. A road condition anomaly perception and sharing system based on smart cycling glasses, characterized in that, include: The data acquisition module is configured to collect multi-source sensor data, including triaxial acceleration, angular velocity, position information, and forward view image, from the smart cycling glasses worn by cyclists. The generation module is configured to analyze the road surface condition of the current road segment based on the multi-source sensor data, identify whether there are road condition anomalies, the road condition anomalies include at least bumpy road segments, pothole road segments and road segments with obstacles, and generate road condition event data when road condition anomalies are identified, the road condition event data includes at least the spatial coordinates of the location where the road condition anomaly occurred, the anomaly type, the time of occurrence and the corresponding riding direction; The upload module is configured to upload the traffic event data to the traffic event database on the server side via a wireless communication network, and to store and update the traffic event data in the traffic event database. The acquisition module is configured to, during the riding process of a subsequent rider, acquire road condition event data that matches the preset riding route within a preset distance range ahead of the subsequent rider from the road condition event database, based on the current location of the subsequent rider and the preset riding route; The determination module is configured to determine whether to issue a reminder and the corresponding reminder content based on the acquired road condition event data and the current speed and current riding posture of the subsequent riders; The output module is configured to output warning information indicating abnormal road conditions ahead via the display component and / or voice component of the cycling smart glasses, so as to prompt the following riders to take evasive action such as slowing down or taking an alternate route.

9. A computer device, characterized in that, The system includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the road condition anomaly perception and sharing method based on cycling smart glasses as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the road condition anomaly perception and sharing method based on cycling smart glasses as described in any one of claims 1 to 7.

Images