Kart rim speed timing system, method, equipment, medium and product

Abstract

The invention discloses a kart rim speed timing system, method and device, a medium and a product, and relates to the field of rim speed timing, and the system comprises a camera, an intelligent device and a head-up display module which are connected in sequence; the camera is arranged on the front nose wing of the kart, an anti-rolling frame or a helmet of a kart driver; the camera is used for collecting racing track videos; the intelligent equipment is arranged at the top of the front nose wing of the kart or on a helmet of a kart driver; the intelligent equipment is used for identifying markers on the racing track according to the racing track video and recording the time when the markers are detected in the current circle; determining a circle speed timing score according to the time when the marker is detected in the current circle; the head-up display module is arranged at the top of the front nose wing of the kart or on a helmet of a kart driver; and the head-up display module is used for displaying the ring speed timing score. According to the method, the kart driver can obtain the circle speed timing result in real time, so that the training efficiency is improved or a strategy is flexibly arranged in a competition.

Description

Technical Field

[0001] The present application relates to the field of lap time timing, and in particular, to a kart lap time timing system, method, device, medium and product. Background Art

[0002] Lap time timing is one of the most important links in motor racing. Whether in training or in a race, it is crucial for a driver to obtain lap time timing results in real time to improve the driver's skills. A kart (Kart / Karting / Go-Kart) is a junior and small formula racing car suitable for beginners. It has always been called the "cradle of Formula One drivers" and is expected to be included in the Olympic Games in the future. In 2021, China was included in the official Formula One driver seats, which has led to a rapid increase in the number of people participating in karting in China.

[0003] Currently, karts mainly use RFID (Radio Frequency Identification) technology for lap time timing. This technology requires installing a radio frequency tag (Tag) on the kart and burying a reader underground at the finish line of the track. In this way, whenever a kart passes the finish line, the reader will sense the radio frequency tag and start timing. When the kart passes the finish line again, the reader senses the tag again, and the time interval between the two inductions is the time taken for the kart to complete one lap. Then, the lap time timing result is displayed on a large screen in the rest area outside the track. This lap time timing system has problems of high cost and the inability to allow the driver of the kart to obtain the lap time timing result in real time.

[0004] Generally, the cost of a radio frequency tag and a reader is relatively high, and the construction cost of burying the reader underground is also relatively high. The entire lap time timing system costs tens of thousands or even hundreds of thousands of yuan. In addition, this system can only display the lap time timing results of each lap in a session after the driver finishes driving and leaves the track after at least completing one session of kart driving. One session of kart driving is generally 6 - 12 minutes, that is, the driver can view the lap time timing results at least every 6 minutes. If it is long-term practice or a race, the driver may only be able to view the results once every 1 - 2 hours or after the race ends. For a driver, obtaining lap time timing results in a timely manner is beneficial to improving training efficiency or flexibly arranging strategies in a race. Although some kart tracks install large screens in the track to display the lap time timing results in real time, it is very difficult for the driver to divert attention to the information on the large screen in the track when the kart is driving at high speed. In addition, this also poses a safety hazard. Summary of the Invention

[0005] The purpose of this application is to provide a kart lap time timing system, method, device, medium and product, which can enable kart drivers to obtain lap time timing results in real time, so as to improve training efficiency or flexibly arrange strategies in competitions.

[0006] To achieve the above object, this application provides the following solutions:

[0007] In the first aspect, this application provides a kart lap time timing system, including: an intelligent device, a camera and a head-up display module; both the camera and the head-up display module are connected to the intelligent device;

[0008] The camera is arranged on the front nose of the kart, on the roll cage or on the helmet of the kart driver; the camera is used to collect track videos;

[0009] The intelligent device is arranged on the top of the front nose of the kart or on the helmet of the kart driver; the intelligent device is used for:

[0010] Identify the markers on the track according to the track video, and record the time when the markers are detected in the current lap;

[0011] Determine the lap time timing result according to the time when the markers are detected in the current lap;

[0012] The head-up display module is arranged on the top of the front nose of the kart or on the helmet of the kart driver; the head-up display module is used to display the lap time timing result.

[0013] Optionally, it further includes: an earphone; the earphone is connected to the intelligent device; the earphone is used to voice broadcast the lap time timing result.

[0014] Optionally, the intelligent device includes: a first timing module;

[0015] The first timing module is used for:

[0016] Judge whether the current moment reaches the moment to start detecting markers;

[0017] If so, obtain the track video collected by the camera and detect whether there are markers in the track video;

[0018] If so, record the time when the markers are detected in the current lap, pause the marker detection, and calculate the next moment to start detecting markers;

[0019] Obtain lap time timing environment data;

[0020] According to the lap time timing environment data, use an error prediction model to predict the lap time timing result error; wherein, the error prediction model is obtained by training an extremely randomized tree model using a training data set.

[0021] Determine the lap timing result of the current lap based on the lap timing result error, the time when the marker is detected in the current lap, and the time when the marker was detected in the previous lap, and return "Determine whether the current moment has reached the moment to start detecting the marker" until the kart has completed N laps.

[0022] Optionally, it further includes: a GNSS receiver; the GNSS receiver is connected to the smart device;

[0023] The GNSS receiver is used to receive the positioning signal of the kart.

[0024] Optionally, the smart device includes: a second timing module;

[0025] The second timing module is used for:

[0026] Determine whether the current moment has reached the moment to start determining whether the kart has crossed the finish line;

[0027] If so, obtain the positioning signal of the kart, and determine whether the kart has crossed the finish line according to the positioning signal;

[0028] If so, record the finish line crossing time of the current lap, pause determining whether the kart has crossed the finish line, and calculate the next moment to start determining whether the kart has crossed the finish line;

[0029] Determine the lap timing result of the current lap based on the finish line crossing time of the current lap and the finish line crossing time of the previous lap, and return "Determine whether the current moment has reached the moment to start determining whether the kart has crossed the finish line" until the kart has completed N laps.

[0030] In a second aspect, the present application provides a kart lap timing method. The kart lap timing method is applied to the above-mentioned kart lap timing system. The kart lap timing method includes:

[0031] Determine whether the current moment has reached the moment to start detecting the marker;

[0032] If so, obtain the track video collected by the camera, and detect whether there is a marker in the track video;

[0033] If so, record the time when the marker is detected in the current lap, pause the marker detection, and calculate the next moment to start detecting the marker;

[0034] Obtain the lap timing environment data;

[0035] According to the lap timing environment data, use the error prediction model to predict the lap timing result error; wherein, the error prediction model is obtained by training the extremely randomized tree model using the training data set;

[0036] Determine the lap time timing result of the current lap based on the lap time timing error, the time when the marker is detected in the current lap, and the time when the marker was detected in the previous lap, and return "Determine whether the current moment has reached the moment to start detecting the marker" until the kart has completed N laps.

[0037] In a third aspect, the present application provides a kart lap time timing method. The kart lap time timing method is applied to the above-mentioned kart lap time timing system. The kart lap time timing method includes:

[0038] Determine whether the current moment has reached the moment to start determining whether the kart has crossed the finish line;

[0039] If so, obtain the positioning signal of the kart, and determine whether the kart has crossed the finish line according to the positioning signal;

[0040] If so, record the finish line crossing moment of the current lap, pause determining whether the kart has crossed the finish line, and calculate the next moment to start determining whether the kart has crossed the finish line;

[0041] Determine the lap time timing result of the current lap based on the finish line crossing moment of the current lap and the finish line crossing moment of the previous lap, and return "Determine whether the current moment has reached the moment to start determining whether the kart has crossed the finish line" until the kart has completed N laps.

[0042] In a fourth aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program to implement the kart lap time timing method described in any one of the above.

[0043] In a fifth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the kart lap time timing method described in any one of the above.

[0044] In a sixth aspect, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the kart lap time timing method described in any one of the above.

[0045] According to the specific embodiments provided by the present application, the present application has the following technical effects:

[0046] The present application provides a kart lap speed timing system, method, device, medium and product. The system includes: an intelligent device, a camera and a head-up display module; the camera and the head-up display module are both connected to the intelligent device; the camera is arranged on the front nose of the kart, on the roll cage or on the helmet of the kart driver; the camera is used to collect track videos; the intelligent device is arranged on the top of the front nose of the kart or on the helmet of the kart driver; the intelligent device is used for: identifying markers on the track according to the track videos and recording the time when the markers are detected in the current lap; determining the lap speed timing result according to the time when the markers are detected in the current lap; the head-up display module is arranged on the top of the front nose of the kart or on the helmet of the kart driver; the head-up display module is used to display the lap speed timing result. The present application enables the kart driver to obtain the lap speed timing result in real time, so as to improve the training efficiency or flexibly arrange strategies in the competition. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 Schematic structural diagram of a kart lap speed timing system provided by an embodiment of the present application;

[0049] Figure 2 Side view of the smart phone installation solution provided by an embodiment of the present application;

[0050] Figure 3 Axonometric view of the smart phone installation solution provided by an embodiment of the present application;

[0051] Figure 4 Side view of the smart phone combined with HUD installation solution provided by an embodiment of the present application;

[0052] Figure 5 Side view of the embedded system installation solution provided by an embodiment of the present application;

[0053] Figure 6 Axonometric view of the embedded system installation solution provided by an embodiment of the present application;

[0054] Figure 7 Schematic diagram of the camera collecting track video data in real time and identifying markers on the track provided by an embodiment of the present application;

[0055] Figure 8 Schematic diagram of representing the track area with a plane rectangular coordinate system provided by an embodiment of the present application;

[0056] Figure 9 Schematic diagram of taking two points on the finish line of the track provided by an embodiment of the present application;

[0057] Figure 10 Schematic diagram of the finish line judgment method Ⅰ provided by an embodiment of the present application;

[0058] Figure 11 Schematic diagram of the finish line judgment method Ⅱ provided by an embodiment of the present application;

[0059] Figure 12 Schematic diagram of the finish line judgment method Ⅲ provided by an embodiment of the present application;

[0060] Figure 13 Schematic diagram of the implementation of the smartphone solution provided by an embodiment of the present application;

[0061] Figure 14 Schematic diagram of the model training process provided by an embodiment of the present application;

[0062] Figure 15 Schematic diagram of the structure of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0063] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0064] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0065] In an exemplary embodiment, as Figure 1 shown, a kart lap time timing system is provided, including: a smart device, a camera, and a head-up display module; both the camera and the head-up display module are connected to the smart device.

[0066] The camera is disposed on the front nose of the kart, on the roll cage, or on the helmet of the kart driver; the camera is used to collect track videos.

[0067] The smart device is disposed on the top of the front nose of the kart or on the helmet of the kart driver; the smart device is used for:

[0068] Identifying markers on the track according to the track video and recording the time when the markers are detected in the current lap.

[0069] Determine the lap time based on the detected marker time of the current lap.

[0070] The head-up display module is arranged on the top of the front nose of the kart or on the helmet of the kart driver; the head-up display module is used to display the lap time.

[0071] As an optional implementation, it further includes: headphones; the headphones are connected to the smart device; the headphones are used to voice broadcast the lap time.

[0072] As an optional implementation, it further includes: a GNSS receiver; the GNSS receiver is connected to the smart device.

[0073] The GNSS receiver is used to receive the positioning signal of the kart.

[0074] In practical applications, the kart is equipped with a smart device installed with a lap time calculation program. The smart device can be a smartphone or an embedded system. There are two solutions according to different devices. ① Smartphone solution: The smartphone can be installed on the top of the front nose of the kart through a fixed bracket (i.e., Solution A) or on the helmet of the driver (kart driver) (i.e., Solution B), as Figure 2 and Figure 3 shown. It is also possible to add a HUD (Head-Up Display) module. Install the smartphone on the top of the front nose of the kart and install the HUD module on the driver's helmet through a fixed bracket. The goggles of the helmet can also be modified into a HUD, as Figure 4 shown. The smartphone and the HUD can be connected by wire or wirelessly to transmit and display data. The built-in camera and GNSS (Global Navigation Satellite System) receiver of the mobile phone are used as input ends, and a better-performing camera and GNSS receiver can also be externally connected. The mobile phone screen, the headphones connected to the mobile phone, and the HUD module are used as output ends. ② Embedded system solution, as Figure 5 and Figure 6Shown as follows: The host of the embedded system is installed at a position that does not affect the driver's driving (such as the back side of the kart seat), and the host is connected to a camera, a GNSS receiver, a HUD module, and a headset. The camera can be installed on the top of the front nose of the kart (i.e., Camera Solution A), on the roll cage (not shown in the figure), on the driver's helmet (i.e., Camera Solution B), and other suitable positions for shooting. The camera and the GNSS receiver serve as input ends. The HUD can be installed on the top of the front nose of the kart (i.e., HUD Solution A) or on the driver's helmet (i.e., HUD Solution B) through a fixed bracket, or the goggles of the helmet can be modified into a HUD (i.e., HUD Solution C). The HUD and the headset serve as output ends.

[0075] The camera at the input end collects the track video data in real time and transmits it to the lap timing program, which identifies the markers on the track in the video (such as the track finish line, the gantry, etc.). As Figure 7 shown, based on the recognition result, the lap timing function can be realized by combining the positioning data of the GNSS. When used on an indoor track, since the positioning signal provided by the GNSS cannot be received indoors, the lap timing program only uses the timing module A (the first timing module) for timing and notifies the driver of the timing result in real time through the output end. When used on an outdoor track, the lap timing program can use the timing module A and the timing module B (the second timing module) for timing respectively, and finally perform weighted averaging on the timing results and notify the driver of the results in real time through the output end. It can also only use the timing module A or the timing module B for timing.

[0076] As an optional implementation manner, the intelligent device includes: a first timing module.

[0077] The first timing module is used for:

[0078] judging whether the current moment reaches the moment to start detecting markers.

[0079] If so, obtain the track video collected by the camera and detect whether there are markers in the track video.

[0080] If so, record the time when the marker is detected in the current lap, pause the marker detection, and calculate the next moment to start detecting markers.

[0081] Obtain the lap timing environment data.

[0082] According to the lap timing environment data, use the error prediction model to predict the error of the lap timing result; wherein, the error prediction model is obtained by training the extremely randomized trees model using the training data set.

[0083] Based on the lap time timing result error, the time when the marker is detected in the current lap, and the time when the marker was detected in the previous lap, determine the lap time timing result of the current lap, and return "judge whether the current moment has reached the moment to start detecting the marker", until the kart has completed N laps.

[0084] The timing module A is a lap time timing that comprehensively combines object detection based on machine vision and error correction based on machine learning.

[0085] After the kart enters the track and the lap time timing program starts, the program uses the object detection function based on machine vision to detect the markers preset on the track in real time through the camera. When a marker is detected, record the time. At the same time, the object detection function pauses for a period of time to avoid repeated detection in a short time, and the specific time length can be preset according to the characteristics of the track. When the object detection function resumes and the lap time timing program detects a marker again, record the time and calculate the time difference from the previous time when the marker was detected, which is the timing result of this lap. The lap time timing program continues to run and repeats the above process to time each lap of the kart on the track until the program ends. Multiple markers can be preset on the same track, and the lap time timing program will detect each marker and time them separately. After the timing for all markers is completed, take the average of all timing results as the final result.

[0086] Build a machine learning model to predict the timing error caused by factors such as light, visibility, and interference from other objects on the track. The timing result is corrected by adding the predicted error value to obtain a more accurate lap time. First, collect the lap time timing environment data. Whenever the lap time timing program obtains a timing result, collect the lap time timing environment data, including but not limited to the date and time at that moment, light, visibility, GNSS positioning data of the kart (only applicable to outdoor tracks), driving direction of the kart, speed of the kart, delay time and frame rate of the target detection function, position, resolution, and sensitivity of the camera, etc. Then collect the error data. Compare the timing result calculated by the lap time timing program for each lap with the timing result obtained by manual timing with a stopwatch or the timing result of the track timing system, that is, find the difference, and calculate the error value of the timing result for each lap. Combine the lap time timing environment data and the error value of the timing result to form a training sample set for machine learning. When the number of training samples is relatively small, select the Extra-Trees model in machine learning for training and prediction. The prediction algorithm of the Extra-Trees will construct multiple decision trees {#1, #2,..., #N}, and each decision tree is constructed independently; when each tree splits at a node, a random subset of features is selected to evaluate the split point; each decision tree independently makes a prediction based on the input lap time timing environment data to generate its own prediction output; finally, the prediction outputs of all decision trees are collected and then averaged to generate the prediction result of the error value of the final timing result. When the number of training samples is relatively large, models such as Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BiLSTM), and Transformer can be selected for training and prediction. These models can also be combined to construct a more complex deep learning model for training and prediction.

[0087] Define the t+1 moment as the next moment after the current moment t, and the t-1 moment as the previous moment before the current moment t. Let i represent the i-th lap of the kart driving on the track, i = 0, 1, 2, 3,.... For the marker ω, let T i ω represent the lap time timing result of the i-th lap calculated based on the detection of the marker ω, that is, the time taken for the kart to complete the i-th lap. Let the error value of the timing result be ε i ω , the duration of pausing the detection of the marker ω be H, and the moment of starting the detection of the marker ω be u ω。When the lap timer program is started and the kart enters the track, set i←0, which is recorded as the 0th lap. The specific steps for the timing module A to perform lap timing are as follows.

[0088] Step 1: At time t, determine whether the detection of the marker ω is in a paused state, i.e., t < u ω ? If "yes", then execute Step 1; if "no", then execute Step 2.

[0089] Step 2: Detect whether there is a marker ω in the track video obtained by the camera. If "yes", then execute Step 3; if "no", then execute Step 2.

[0090] Step 3: Record the current time as t i ω , pause the detection of the marker ω, and calculate u ω = t i ω + H. If i ≥ 1, then execute Step 4; if i is 0, then execute Step 5.

[0091] Step 4: Collect lap timing environmental data, input these data into the machine learning model, and predict the error value ε of the timing result i ω , calculate T i ω = t i ω - t i-1 ω + ε i ω . Execute Step 5.

[0092] Step 5: Determine whether the program ends? If "yes", execute Step 6; if "no", set i←i + 1, enter the next moment of time t, i.e., t←t + 1 moment, and execute Step 1.

[0093] Step 6: End this process.

[0094] To prevent the situation where the lap timing fails due to an error in the detection of a marker in a certain lap (for example, the marker is never detected), multiple markers can be preset for the same track. As long as at least one marker is successfully detected and the timing is completed in one lap. When multiple markers are preset for a track, let the number of markers be m and m > 1, which is represented by the set O = {obj1, obj2,...,, obj m}, and the lap timing program will execute the above Steps 1 - 6 for each marker obj k in O in the i-th lap. The number of markers that are successfully detected and the timing is completed is n, which is represented by the set Ω = {ω1, ω2,...,, ω n} is represented, then n ≤ m and When all the timing results of the i-th lap are calculated for all the markers in Ω (j = 1, 2,..., n), the following formula is used to calculate the average value of all the timing results as the final lap speed timing result of this lap

[0095]

[0096] As an optional implementation manner, the intelligent device includes: a second timing module;

[0097] The second timing module is used for:

[0098] Judge whether the current moment reaches the moment to start judging whether the kart crosses the finish line.

[0099] If so, obtain the positioning signal of the kart, and judge whether the kart crosses the finish line according to the positioning signal.

[0100] If so, record the crossing time of the current lap, pause judging whether the kart crosses the finish line, and calculate the next moment to start judging whether the kart crosses the finish line.

[0101] Determine the lap speed timing result of the current lap according to the crossing time of the current lap and the crossing time of the previous lap, and return to "Judge whether the current moment reaches the moment to start judging whether the kart crosses the finish line" until the kart finishes N laps.

[0102] Timing module B is lap speed timing based on GNSS positioning data.

[0103] Within the area of the kart track, ignoring the curvature of the earth's surface, the track area is approximately regarded as a plane, then the track area can be represented by a plane rectangular coordinate system xOy, as Figure 8 shown, the positions of the kart and the markers on the track can be represented by points on the coordinate system. Define the longitude as the X-axis and the latitude as the Y-axis, then any point P on the track is located by the combination of its longitude x and latitude y provided by GNSS, that is, P(x, y). Take 2 points A(x a , y a ) and B(x b , y b ) on the finish line of the track, which are respectively near the leftmost and rightmost ends of the finish line, as Figure 9 shown, and the line connecting the two points is parallel to the finish line. The longitude and latitude of these two points can be obtained by methods such as on-site measurement, on-site acquisition of GNSS positioning data, and measurement with tools on the electronic map. Let K(x k t , y k t) is the coordinate of the kart at the current moment t, and ε is the allowed error value. The finish line does not necessarily have to be the one marked on the track. Two points on the track can be selected to define a custom finish line.

[0104] The lap time timing program obtains the positioning signal of the kart provided by GNSS in real time at each moment. Based on the latitude and longitude of the kart at that moment (positioning signal), it determines whether the kart has crossed the finish line through calculation, and thus conducts lap time timing. There are three methods for judging whether the kart has crossed the finish line as follows.

[0105] Crossing the finish line judgment method Ⅰ: A method for judging that the kart has crossed the finish line based on distance comparison.

[0106] Let L be the distance between points A and B, then L 2 =(x a -x b ) 2 +(y a -y b ) 2 . Let d a t be the distance between the kart and point A at time t, then (d a t ) 2 =(x a -x k t ) 2 +(y a -y k t ) 2 . Let d b t be the distance between the kart and point B at time t, then (d b t ) 2 =(x b -x k t ) 2 +(y b -y k t ) 2 .

[0107] When the kart is driving on the track, the lap time timing program obtains the latitude and longitude of the current kart in real time through the GNSS receiver at the input end, that is, the coordinate K(x k t , y k t ) of the kart in the plane rectangular coordinate system xOy, and calculates (d a t ) 2 and (d bt ) 2 By checking whether the condition |[(d a t ) 2 +(d b t ) 2 -2×d a t ×d b t -L 2 |≤ε is satisfied, it is determined whether the kart crosses the finish line at time t, as Figure 10 shown.

[0108] Finish line judgment method II: A method for judging whether a kart crosses the finish line based on the minimum distance.

[0109] Take a point C(x c , y c )(Point C can be one of points A and B) on any straight section of the track. Let d c t be the distance between the kart and point C at time t. Then (d c t ) 2 =(x c -x k t ) 2 +(y c -y k t ) 2 . When the kart is running on the track, the lap timer program obtains the longitude and latitude of the current kart in real time through the GNSS receiver at the input end, that is, the coordinates K(x k t , y k t ) of the kart in the plane rectangular coordinate system xOy, calculates (d c t ) 2 , and records (d c t ) 2 and the time t at this moment. When (d c t ) 2 appears the minimum value min(d c t ) 2 , it can be determined that the kart crosses the finish line as Figure 11 shown, and the time t c t ) 2 corresponding to the recorded min(d minThat is the moment when the kart crosses the finish line.

[0110] Crossing line judgment method III: A method for judging whether a kart crosses the finish line based on a straight-line equation.

[0111] Through the coordinates (x a , y a ) and (x b , y b ) of two points A and B, a straight-line equation ax + by + c = 0 in the plane rectangular coordinate system xOy can be calculated. This equation corresponds to the function f(x, y) = ax + by + c.

[0112] Define the t - 1 moment as the previous moment of the current moment t. When the kart is running on the track, the lap timer program obtains the longitude and latitude of the current kart in real time through the GNSS receiver at the input end, that is, the coordinates K(x k t , y k t ) of the kart in the plane rectangular coordinate system xOy. To judge whether the kart crosses the finish line, first substitute the coordinates (x k t , y k t ) of the kart at the t moment and the coordinates (x k t-1 , y k t-1 ) of the kart at the previous moment (t - 1 moment) into the function f(x, y) to calculate the values of the function. By checking whether the condition f(x k t , y k t ) × f(x k t-1 , y k t-1 ) ≤ 0 is satisfied, it is judged whether the kart crosses (just presses on) the finish line at the t moment (see Figure 12 ).

[0113] When f(x k t , y k t ) × f(x k t-1 , y k t-1 ) ≤ 0, that is, the kart is on both sides of the finish line at the current moment and the previous moment (or the kart just presses on the finish line at one moment), which means the kart has crossed the finish line.

[0114] Define the moment t + 1 as the next moment after moment t, and the moment t - 1 as the previous moment before moment t. Let i represent the i-th lap that the kart runs on the track, where i = 0, 1, 2, 3,.... Let T i G represent the lap speed timing result of the i-th lap calculated based on the GNSS positioning data, that is, the time it takes for the kart to complete the i-th lap. The duration for pausing the judgment of whether the kart crosses the finish line is H, and the moment for starting the judgment of whether the kart crosses the finish line is u G . When the lap speed timing program is started and the kart enters the track, let i ← 0, which is recorded as the 0-th lap. The specific steps for the timing module B to perform lap speed timing are as follows.

[0115] Step 1: At moment t, check whether the judgment of the kart crossing the finish line is in a paused state, that is, t < u G ? If "yes", then execute Step 1; if "no", then execute Step 2.

[0116] Step 2: Apply the finish line judgment method Ⅰ / Ⅱ / Ⅲ to judge whether the kart crosses the finish line. If "yes", then execute Step 3; if "no", then execute Step 2.

[0117] Step 3: Record the current finish line moment as t i G , pause the judgment of whether the kart crosses the finish line, and calculate u G = t i G + H. If i ≥ 1, then execute Step 4; if i is 0, then execute Step 5.

[0118] Step 4: Calculate T i G = t i G - t i-1 G . Execute Step 5.

[0119] Step 5: Judge whether the program ends? If "yes", execute Step 6; if "no", let i ← i + 1, enter the next moment after moment t, that is, t ← t + 1 moment, and execute Step 1.

[0120] Step 6: End this process.

[0121] In order to improve the accuracy and reliability of timing, 2 or 3 finish line judgment methods (Ⅰ, Ⅱ, Ⅲ) can be applied simultaneously in one lap to perform lap speed timing respectively. When all the timing results are obtained, take the average of these results as the final lap speed timing result of this lap.

[0122] In an embodiment, a basic implementation and testing of a method for kart lap timing by identifying markers on the track were carried out. A lap timing program was developed based on the Android system of a smartphone, and lap timing was performed by identifying the finish line. The smartphone was installed on the top of the front nose of the kart as shown in Figure 13 . The built-in camera of the phone was used as the input end, and the lap timing results were output through the phone screen and the headphones connected to the phone. The YOLOv8 model was selected to implement the object detection function based on machine vision, and the YOLOv8 model was trained with kart pictures and marker pictures on the track collected online, as shown in Figure 14 . A 10-lap test was carried out on the school playground, and the average error of the lap timing results was 0.0316 seconds, as shown in Table 1.

[0123] Table 1 Statistical table of test results for lap timing by identifying the finish line

[0124] Stopwatch Timing (seconds) Lap Time Timing Program Timing (seconds) Error Value (seconds) 47.219 47.195 0.024 42.281 42.241 0.04 42.18 42.168 0.012 50.891 50.89 0.001 46.125 46.082 0.043 46.438 46.448 0.01 46.25 46.222 0.028 46.141 46.22 0.079 45.938 46.007 0.069 46.094 46.084 0.01 Average Error Value (seconds): 0.0316

[0125] This application proposes a method for kart lap timing that does not utilize the traditional Radio Frequency Identification (RFID) technology, but instead uses Computer Vision, Machine Learning, and Global Navigation Satellite System (GNSS). It also provides a system that enables the driver to obtain real-time lap timing results through voice, head-up display, and display screen. The lap timing method provided by this application can be implemented by developing a mobile phone App or corresponding programs on embedded devices. Fixing the camera of the mobile phone or the embedded device at positions such as the front nose of the kart, the roll cage, and the driver's helmet makes it convenient to use. The beneficial effect of this application is to provide a low-cost system that can provide real-time lap timing results for drivers. Traditional lap timing systems only allow drivers to obtain the results of each lap in a session (usually 6 - 12 minutes) after driving a kart. This application enables drivers to immediately obtain the result of each lap as soon as they complete a lap of driving. In this way, drivers can adjust the race line and driving style of the next lap in a timely manner based on this result, which is beneficial to improving training efficiency during training. That is, compared with the current kart lap timing system, drivers spend less training time to improve the same result. For example, assuming that the lap time improves by 0.5 seconds, the traditional lap timing system may require drivers to accumulate 2 hours of training, while this system may only require 1 hour of cumulative training. Since karting is a relatively expensive sport, with the price of a session ranging from dozens of yuan to two hundred yuan, improving training efficiency means reducing training costs. This lowers the threshold of the sport, enabling more people to participate in it, which is beneficial to the popularization and promotion of the sport, as well as the cultivation and reserve of professional talents in this sport. In addition, this application can also provide real-time lap timing results for drivers during kart races, and drivers can adjust and optimize subsequent race strategies based on the lap timing results at any time.

[0126] Based on the same inventive concept, an embodiment of this application also provides a kart lap timing method applied to the above-mentioned kart lap timing system. The solution provided by this method to solve the problem is similar to the solution described in the above system. Therefore, the specific limitations in the following embodiments of the kart lap timing method can refer to the limitations on the kart lap timing system in the above text and will not be elaborated here.

[0127] In an exemplary embodiment, a kart lap timing method is provided. The kart lap timing method is applied to the above-mentioned kart lap timing system and includes:

[0128] Determine whether the current moment has reached the moment to start detecting the marker.

[0129] If so, obtain the track video captured by the camera and detect whether there are markers in the track video.

[0130] If so, record the time when the marker is detected in the current lap, pause the marker detection, and calculate the next time to start detecting the marker.

[0131] Obtain the environmental data for lap time timing.

[0132] According to the environmental data for lap time timing, use the error prediction model to predict the error of the lap time timing result; wherein, the error prediction model is obtained by training the extremely randomized trees model using a training data set.

[0133] According to the error of the lap time timing result, the time when the marker is detected in the current lap, and the time when the marker was detected in the previous lap, determine the lap time timing result for the current lap, and return to "judge whether the current moment reaches the time to start detecting the marker" until the kart has completed N laps.

[0134] In an exemplary embodiment, a method for kart lap time timing is provided. The method for kart lap time timing is applied to the above-mentioned kart lap time timing system. The method for kart lap time timing includes:

[0135] Judge whether the current moment reaches the time to start judging whether the kart crosses the finish line.

[0136] If so, obtain the positioning signal of the kart and judge whether the kart crosses the finish line according to the positioning signal.

[0137] If so, record the time when the current lap crosses the finish line, pause judging whether the kart crosses the finish line, and calculate the next time to start judging whether the kart crosses the finish line.

[0138] According to the time when the current lap crosses the finish line and the time when the previous lap crossed the finish line, determine the lap time timing result for the current lap, and return to "judge whether the current moment reaches the time to start judging whether the kart crosses the finish line" until the kart has completed N laps.

[0139] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the above-mentioned method for kart lap time timing is implemented.

[0140] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the above-mentioned method for kart lap time timing is implemented.

[0141] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned method for kart lap time timing is implemented.

[0142] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as shown in Figure 15 . The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a kart lap timing method.

[0143] Those skilled in the art can understand that Figure 15 the structure shown in

[0144] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0145] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAMs), magnetoresistive random access memories (MRAMs), ferroelectric random access memories (FRAMs), phase change memories (PCMs), graphene memories, etc. Volatile memories can include random access memories (RAMs) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0146] The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0147] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0148] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The descriptions of the above embodiments are only used to help understand the methods and core ideas of the present application; at the same time, for those of ordinary skill in the art, according to the ideas of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A kart lap time timing system, characterized in that: include: A smart device, a camera and a head-up display module; the camera and the head-up display module are both connected to the smart device; The camera is arranged on the front nose of the kart, the roll cage or the helmet of the kart driver; the camera is used to collect the track video; The smart device is arranged on the top of the front nose of the kart or on the helmet of the kart driver; the smart device is used for: Identify the markers on the track according to the track video, and record the time when the markers are detected in the current lap; Determine a lap time result according to the time when the marker is detected in the current lap; The head-up display module is arranged on the top of the front nose of the kart or on the helmet of the kart driver; the head-up display module is used to display the lap time result.

2. The kart lap time timing system according to claim 1, characterized in that: Also includes: Earphones; the earphones are connected to the smart device; the earphones are used to voice broadcast the lap time results.

3. The kart lap time timing system according to claim 1, characterized in that: The smart device comprises: a first timing module; The first timing module is used for: Determine whether the current moment has reached the moment to start detecting the marker; If yes, obtain the track video captured by the camera, and detect whether there is a marker in the track video; If yes, then record the time when the marker is detected in the current circle, pause the marker detection, and calculate the next time to start the marker detection; Get lap time environment data; According to the lap time environment data, using an error prediction model, predicting the lap time performance error; wherein the error prediction model is obtained by training an extreme random tree model using a training data set; The lap time result of the current lap is determined according to the lap time result error, the time when the marker is detected in the current lap and the time when the marker is detected in the previous lap, and the "determine whether the current moment reaches the time to start marker detection" is returned until the kart completes N laps.

4. The kart lap time timing system according to claim 1, characterized in that: Also includes: GNSS receiver; The GNSS receiver is connected to the smart device; The GNSS receiver is used to receive the positioning signal of the go-kart.

5. The kart lap time timing system according to claim 4, characterized in that: The smart device further includes: a second timing module; The second timing module is used for: Determine whether the current moment has reached the time to start determining whether the kart has crossed the finish line; If yes, then obtaining the positioning signal of the kart, and judging whether the kart has crossed the finish line according to the positioning signal; If yes, then record the time when the current lap crosses the finish line, pause to determine whether the kart has crossed the finish line, and calculate the next time to start determining whether the kart has crossed the finish line; According to the current lap finish time and the previous lap finish time, the lap time result of the current lap is determined, and the "judgment of whether the current time reaches the start time to judge whether the kart has crossed the finish line" is returned until the kart completes N laps.

6. A kart lap time timing method, characterized in that: The kart lap time timing method is applied to the kart lap time timing system according to any one of claims 1 to 5, and the kart lap time timing method comprises: Determine whether the current moment has reached the moment to start detecting the marker; If yes, obtain the track video captured by the camera, and detect whether there is a marker in the track video; If yes, then record the time when the marker is detected in the current circle, pause the marker detection, and calculate the next time to start the marker detection; Get lap time environment data; According to the lap time environment data, using an error prediction model, predicting the lap time performance error; wherein the error prediction model is obtained by training an extreme random tree model using a training data set; The lap time result of the current lap is determined according to the lap time result error, the time when the marker is detected in the current lap and the time when the marker is detected in the previous lap, and the "determine whether the current moment reaches the time to start marker detection" is returned until the kart completes N laps.

7. A kart lap time timing method, characterized in that: The kart lap time timing method is applied to the kart lap time timing system according to any one of claims 1 to 5, and the kart lap time timing method comprises: Determine whether the current moment has reached the time to start determining whether the kart has crossed the finish line; If yes, then obtaining the positioning signal of the kart, and judging whether the kart has crossed the finish line according to the positioning signal; If yes, then record the time when the current lap crosses the finish line, pause to determine whether the kart has crossed the finish line, and calculate the next time to start determining whether the kart has crossed the finish line; According to the current lap finish time and the previous lap finish time, the lap time result of the current lap is determined, and the "judgment of whether the current time reaches the start time to judge whether the kart has crossed the finish line" is returned until the kart completes N laps.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the kart lap time timing method as claimed in claim 6 or 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the kart lap time timing method according to claim 6 or 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the kart lap time timing method described in claim 6 or 7 is implemented.

Images