Method and system for evaluating playback quality of vehicle-mounted displays

Abstract

The present invention relates to the technical field of playback quality monitoring, specifically to a method and system for evaluating the playback quality of an in-vehicle display, comprising the following steps: acquiring an in-vehicle display signal, extracting the signal's amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, performing time series segmentation, extracting a set of characteristic parameters within each time window, and obtaining a display signal feature data set. In the present invention, a systematic evaluation of playback quality is achieved by extracting and analyzing the multidimensional features of the in-vehicle display signal. The calculation of feature offset trends enhances the ability to identify abnormal signal fluctuations. Combined with the analysis of the time axis offset rate, the accuracy of detecting playback signal synchronization is improved, enabling the identification of short-term jitter and sudden offsets. By comparing frame sequence time curves, abnormal playback frame rate fluctuations are accurately determined. Combined with the measurement and evaluation of color offsets, the comprehensiveness of playback quality evaluation is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of playback quality monitoring, and in particular to a playback quality evaluation method and system for a vehicle-mounted display. Background Art

[0002] The field of playback quality monitoring technology includes quality assessment of multiple aspects of signal transmission, image display, and audio output of audio and video playback devices. The core content of this technical field is to ensure that the playback devices can stably output high-quality audio and video signals in a variety of usage environments, including playback signal integrity detection, playback device fault diagnosis, display parameter adjustment, and playback data analysis. The overall playback quality monitoring technology involves multiple links such as signal acquisition, error correction, and display adaptation. The playback quality is measured by acquiring the playback signal and combining it with bit error rate analysis, color calibration, and brightness detection. The display stability is evaluated using image resolution measurement and frame rate statistics to ensure the normal operation of the playback device in various environments.

[0003] Among them, the playback quality assessment method of the vehicle-mounted display refers to the technology for analyzing and evaluating the playback quality of the vehicle-mounted display device under different working conditions. The patent subject covers the measurement of multiple parameters such as brightness uniformity, color reproduction, and contrast of the display content of the vehicle-mounted display, and combines signal waveform analysis, pixel detection, and refresh rate monitoring to determine the playback quality. Usually, an image acquisition device is used to obtain the playback content, and the collected data is analyzed through an image processing algorithm to detect color deviation, flickering, and blur problems that occur during playback. Abnormal data is corrected in combination with error compensation methods to ensure that the vehicle-mounted display can maintain good playback effects in complex environments.

[0004] Traditional in-vehicle display playback quality assessment technology mainly relies on single data point evaluation methods such as bit error rate analysis, color calibration, and brightness detection to monitor playback signal quality. It fails to achieve systematic analysis of signal fluctuation trends, resulting in a one-sided assessment of playback signal quality. Signal integrity detection relies on static characteristics such as bit error rate and cannot dynamically evaluate signal waveform offsets, making it difficult to identify short-term jitter and sudden distortion. Synchronization detection lacks time axis offset trend analysis and only performs statistics on frame rate, which easily misses frame skipping problems caused by short-term frame rate fluctuations, affecting playback stability. The color offset assessment method is mainly based on global color calibration and cannot accurately locate the color change area, resulting in local color deviation of the playback screen being difficult to identify, affecting the comprehensiveness of playback quality assessment. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, the embodiments of the present invention provide a method and system for evaluating the playback quality of an in-vehicle display. The technical solution is as follows:

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for evaluating the playback quality of an in-vehicle display, comprising the following steps:

[0007] S1: Obtain the vehicle display signal, extract the signal's amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, perform time series segmentation, extract the feature parameter set within each time window, and obtain the display signal feature dataset;

[0008] S2: Based on the display signal feature data set, by comparing the amplitude, frequency, and energy characteristics of each type of signal with those in a preset standard signal waveform library, calculating the feature offset value of the signal in each time window, calculating the offset trend of the signal waveform, and obtaining the signal waveform feature offset value;

[0009] S3: Based on the signal waveform characteristic offset value, extract the timestamp sequence of the playback signal from the display signal, calculate the time interval between adjacent frames, calculate the relative offset of the current timestamp, and calculate the time axis offset rate of the playback signal in multiple time windows by statistically analyzing the offset trend to obtain the time axis offset rate;

[0010] S4: Based on the time axis offset rate, extract the frame sequence time curve of the playback signal, calculate the playback time interval between adjacent frames, analyze the fluctuation characteristics of the time interval between frames, identify the time period with abnormal fluctuation, detect frame skipping, and obtain the frame skipping detection result.

[0011] As a further solution of the present invention, the display signal feature data set includes amplitude features, frequency features, and energy distribution features. The signal waveform feature offset value is specifically the amplitude offset, frequency offset, and energy feature offset. The time axis offset rate includes the adjacent frame time interval offset rate, the global time axis drift rate, and the time series cumulative offset rate. The frame skipping detection result includes the frame skipping frequency, frame skipping time period, and frame skipping type.

[0012] As a further solution of the present invention, the steps of obtaining an on-board display signal, extracting the signal's amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, performing time series segmentation, and extracting a set of characteristic parameters within each time window to obtain a display signal feature data set are as follows:

[0013] S101: Acquire the vehicle display signal, extract the amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, perform time sorting on each data item, and obtain the basic data set of the display signal;

[0014] S102: Based on the display signal basic data set, the data is divided into time windows, and the signal mean, fluctuation amplitude, and frequency stability in each window are calculated to obtain time series division data;

[0015] S103: Based on the time-series partitioned data, extract multiple characteristic parameters in each time window, including amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, to obtain a display signal characteristic data set.

[0016] As a further solution of the present invention, based on the display signal feature data set, by comparing the amplitude, frequency, and energy characteristics of each type of signal with those in a preset standard signal waveform library, calculating the characteristic offset value of the signal in each time window, calculating the offset trend of the signal waveform, and obtaining the signal waveform feature offset value, the specific steps are:

[0017] S201: Based on the display signal feature data set, the amplitude, frequency, and energy features in each time window are obtained, and reference data of the corresponding signal type in the standard signal waveform library are called to compare the amplitude, main frequency distribution, and energy change trend of the signal in each time window, calculate the feature difference of each time window, and obtain the signal feature offset matrix;

[0018] S202: Based on the signal feature offset matrix, analyze the feature offset amplitude of each time window, calculate the rate of change of the offset features in multiple time windows, and calculate the change curve of the offset value in the time series to extract the trend information of the signal fluctuation and obtain the signal offset trend curve;

[0019] S203: Based on the signal deviation trend curve, the stability of the waveform characteristics is calculated, the frequency deviation range, amplitude fluctuation range, and energy loss level of the signal are analyzed, the degree of signal deviation is calculated, and the signal waveform characteristic deviation value is obtained.

[0020] As a further solution of the present invention, based on the signal waveform characteristic offset value, a timestamp sequence of the playback signal is extracted from the display signal, the time interval between adjacent frames is calculated, the relative offset of the current timestamp is calculated, and the time axis offset rate of the playback signal in multiple time windows is calculated by statistically analyzing the offset trend. The steps of obtaining the time axis offset rate are specifically as follows:

[0021] S301: extracting a timestamp sequence of a playback signal from display signal data based on the signal waveform characteristic offset value, sorting the timestamps, and calculating the time intervals between adjacent timestamps to obtain a playback signal time interval sequence;

[0022] S302: Based on the playback signal time interval sequence, calculate the time interval change rate in each time window, extract the relative offset of the time interval, and analyze the time offset trend in multiple time windows to obtain the playback signal time offset trend;

[0023] S303: Based on the time offset trend of the playback signal, calculate the time axis offset rate of the playback signal in multiple time windows to obtain the time axis offset rate.

[0024] As a further solution of the present invention, based on the time axis offset rate, extracting a frame sequence time curve of the playback signal, calculating the playback time interval between adjacent frames, analyzing the fluctuation characteristics of the inter-frame time interval, identifying the time period with abnormal fluctuation, detecting frame skipping, and obtaining the frame skipping detection result are specifically as follows:

[0025] S401: Based on the time axis offset rate, frame sequence time data of the playback signal is obtained, the playback time interval between adjacent frames is calculated, and a frame sequence time curve is drawn to obtain frame sequence time curve data;

[0026] S402: Based on the frame sequence time curve data, calculate the fluctuation amplitude of the time interval between adjacent frames, calculate the time interval change rate, extract the abnormal time period, detect the frame skipping period, and obtain the frame skipping fluctuation abnormal interval;

[0027] S403: Based on the abnormal frame skipping fluctuation interval, the frame loss ratio is calculated according to the frame skipping frequency, and the changing trend of the frame skipping situation is analyzed to obtain a frame skipping detection result.

[0028] As a further solution of the present invention, the specific formula for calculating the frame loss ratio based on the frame skipping frequency is:

[0029]

[0030] Calculate the frame loss ratio;

[0031] Among them, R f represents the frame loss ratio, M′ represents the total number of frames, and F j′ represents the timestamp of the j′th frame, F j′-1 Represents the timestamp of the previous frame, T s represents the ideal frame interval, and j′ is the index of the frame.

[0032] As a further embodiment of the present invention, the method further comprises:

[0033] S5: Based on the frame skipping detection results, using an image acquisition device, detecting color shifts in multiple areas of the display, calculating a color accuracy score, and evaluating the display's playback quality based on inter-frame fluctuations and signal waveform quality to obtain a playback quality score.

[0034] The playback quality score specifically refers to the signal waveform quality score, the time axis stability score, and the comprehensive display playback quality score.

[0035] As a further solution of the present invention, based on the frame skipping detection results, an image acquisition device is used to detect color shifts in multiple areas of the display, calculate a color accuracy score, and evaluate the display's playback quality based on inter-frame fluctuations and signal waveform quality. The steps for obtaining the playback quality score are specifically as follows:

[0036] S501: Based on the frame skipping detection result, using an image acquisition device, color data is collected in multiple areas of the display, color channel spectral values ​​of each area are extracted, and the degree of color deviation between color channels is calculated. The degree of color deviation at multiple locations is calculated by comparing with a color standard reference value to obtain color deviation detection data;

[0037] S502: Calculating the offset of multiple areas of the display in each color channel based on the color offset detection data, evaluating the degree of color offset of the display, and obtaining a color accuracy scoring result;

[0038] S503: Based on the color accuracy scoring result, combined with inter-frame fluctuations and signal waveform quality, evaluate the playback quality of the display to obtain a playback quality score;

[0039] The specific formula for evaluating the display's playback quality is:

[0040]

[0041] Calculate the comprehensive playback quality score;

[0042] Among them, Q s is the comprehensive playback quality score, β1 is the weight coefficient corresponding to the color accuracy score, β2 is the weight coefficient corresponding to the inter-frame fluctuation score, and β3 is the weight coefficient corresponding to the signal waveform quality score. X1 represents the color accuracy score of the display, X2 represents the inter-frame fluctuation score, and X3 represents the signal waveform quality score.

[0043] On the other hand, a system for evaluating the playback quality of an in-vehicle display is provided. The system is applied to the method for evaluating the playback quality of an in-vehicle display. The system includes:

[0044] The signal feature extraction module extracts the amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps from the vehicle display signal to divide the signal into time windows. It then establishes a feature parameter set within each time window to generate a display signal feature dataset.

[0045] The signal offset analysis module extracts the standard signal amplitude, frequency, and energy characteristics from the standard signal waveform library based on the display signal feature data set, calculates the amplitude error, frequency offset, and energy loss ratio in each time window, analyzes the signal offset trend, calculates the fluctuation of the offset rate, and obtains the signal waveform feature offset value;

[0046] The time axis offset detection module extracts the timestamp sequence of the playback signal based on the signal waveform characteristic offset value, calculates the time interval between adjacent frames, identifies the time points of abnormal intervals, analyzes the time axis drift trend in multiple time windows, and obtains the time axis offset rate;

[0047] The frame skipping identification module extracts the frame sequence time curve of the playback signal based on the time axis offset rate, calculates the playback time interval between adjacent frames, and detects frame skipping in real time by analyzing the time period when the time interval changes abnormally, thereby obtaining a frame skipping detection result;

[0048] Based on the frame skipping detection results, the playback quality assessment module uses an image acquisition device to detect the color deviation of multiple areas of the display, calculates the color accuracy score of the display, and combines the inter-frame fluctuation characteristics and signal waveform quality data to evaluate the playback quality of the vehicle display and obtain a playback quality score.

[0049] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0050] By extracting and analyzing the multi-dimensional features of on-board display signals, a systematic evaluation of playback quality is achieved. The calculation of feature offset trends enhances the ability to identify abnormal signal fluctuations. Combined with the analysis of time axis offset rate, the accuracy of detecting playback signal synchronization is improved, and short-term jitter and sudden offsets can be identified. By comparing the time curves of frame sequences, abnormal playback frame rate fluctuations can be accurately determined. Combined with the measurement and evaluation of color offset, the comprehensiveness of playback quality assessment is optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0052] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0053] Figure 2 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0054] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0055] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0056] In the embodiments of the present invention, the terms "image" and "picture" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same. The terms "of," "corresponding," and "corresponding" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same.

[0057] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0058] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0059] See also Figure 1 The present invention provides a technical solution, a method for evaluating the playback quality of a vehicle-mounted display, comprising the following steps:

[0060] S1: Obtain the vehicle display signal, extract the signal's amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, perform time series segmentation, extract the feature parameter set within each time window, and obtain the display signal feature dataset;

[0061] S2: Based on the display signal feature data set, by comparing the amplitude, frequency, and energy characteristics of each type of signal with the preset standard signal waveform library, the characteristic offset value of the signal in each time window is calculated, the offset trend of the signal waveform is calculated, and the signal waveform characteristic offset value is obtained;

[0062] S3: Based on the signal waveform characteristic offset value, extract the timestamp sequence of the playback signal from the display signal, calculate the time interval between adjacent frames, calculate the relative offset of the current timestamp, and calculate the time axis offset rate of the playback signal in multiple time windows by statistically analyzing the offset trend to obtain the time axis offset rate;

[0063] S4: Based on the time axis offset rate, extract the frame sequence time curve of the playback signal, calculate the playback time interval between adjacent frames, analyze the fluctuation characteristics of the time interval between frames, identify the time period with abnormal fluctuation, detect frame skipping, and obtain the frame skipping detection result;

[0064] S5: Based on the frame skipping detection results, use image acquisition equipment to detect color deviation in multiple areas of the display, calculate the color accuracy score, and combine the inter-frame fluctuations and signal waveform quality to evaluate the display's playback quality and obtain a playback quality score.

[0065] The display signal feature data set includes amplitude features, frequency features, and energy distribution features. The signal waveform feature offset values ​​specifically include amplitude offset, frequency offset, and energy feature offset. The time axis offset rate includes the offset rate of the time interval between adjacent frames, the global time axis drift rate, and the time series cumulative offset rate. The frame skipping detection results include the frame skipping frequency, frame skipping time period, and frame skipping type. The playback quality score specifically refers to the signal waveform quality score, the time axis stability score, and the comprehensive display playback quality score.

[0066] The steps for obtaining the vehicle display signal, extracting the signal's amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, performing time series segmentation, and extracting the feature parameter set within each time window to obtain the display signal feature dataset are as follows:

[0067] S101: Acquire the vehicle display signal, extract the amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, perform time sorting on each data item, and obtain the basic data set of the display signal;

[0068] Acquire the on-board display signal, parse the received signal data, and extract the signal's amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps as key parameters. Amplitude is used to characterize signal strength, frequency reflects the periodic changes in the signal, energy distribution describes the energy characteristics of the signal in different time periods, color channel spectral characteristics are used to identify color information, and inter-frame timestamps are used to calculate playback timing stability. All parameters are sorted in chronological order to establish time series data. For amplitude, extract the amplitude of the signal at each moment, construct an amplitude time series, and calculate the amplitude change rate. Use the relative change calculation method to calculate the change rate of the amplitude values ​​between two adjacent moments. The formula is as follows:

[0069]

[0070] Among them, R A is the amplitude change rate, A t is the amplitude value at the current moment, A t-1 is the amplitude value of the previous moment. If the amplitude value A at a certain moment t=1.2V, the amplitude value at the previous moment is A t-1 =1.0V, then the amplitude change rate is calculated to be

[0071]

[0072] Similarly, for frequency, the signal spectrum is analyzed through Fourier transform, the main frequency and harmonic components are extracted, and the spectrum energy ratio is calculated. For energy distribution, the signal energy within a certain time window is accumulated, and the total energy ratio is calculated using cumulative distribution. For color channel spectral characteristics, the RGB channel intensity is analyzed, and the color saturation and brightness values ​​are calculated. For inter-frame timestamps, the time interval between adjacent frames is calculated, and the uniformity of the playback timing is determined. After all data are analyzed and time-sorted, a basic display signal data set is established for subsequent analysis.

[0073] S102: Based on the basic data set of the display signal, the data is divided into time windows, and the signal mean, fluctuation amplitude, and frequency stability in each window are calculated to obtain time series division data;

[0074] Based on the basic data set of the display signal, the window is divided according to the time dimension, and the time window length T is set. w , and divide the data into blocks, and calculate the mean, fluctuation amplitude and frequency stability of the signal in each window. For the calculation of the signal mean, the amplitude values ​​of all sampling points in the window are summed and divided by the number of sampling points. The calculation formula is as follows:

[0075]

[0076] Among them, A mean is the average amplitude value in the window, A i is the amplitude value of the i-th sampling point, and N is the number of sampling points in the window. Assuming there are 5 sampling points in the window, and their amplitude values ​​are 1.0V, 1.1V, 0.9V, 1.2V, and 1.0V respectively, the average amplitude value is calculated as

[0077]

[0078] For fluctuation amplitude, the standard deviation of the amplitude within each window is calculated and used as a quantitative indicator of the degree of fluctuation. A fluctuation threshold ΔA is set. When the standard deviation exceeds ΔA, the signal in that window is marked as fluctuating violently. For frequency stability, the dominant frequency value within the window is extracted and the relative deviation of the dominant frequency is calculated. The relative deviation is defined as the difference between the dominant frequency of the current window and the dominant frequency of the previous window divided by the dominant frequency of the previous window. If the relative deviation exceeds the set threshold Δf, the signal within the window is considered to have frequency drift. After all windows are calculated, all window characteristic parameters are stored to form time series partitioning data.

[0079] S103: Based on the time series data, multiple feature parameters are extracted in each time window, including amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, to obtain a display signal feature dataset;

[0080] Based on the time series data, multiple characteristic parameters are extracted within each time window, including amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps. For amplitude, the maximum, minimum, and mean values ​​within the window are extracted, and the difference between the maximum and minimum amplitudes is calculated as the amplitude variation range. The formula is as follows:

[0081] ΔA=A max -A min ;

[0082] Among them, ΔA is the amplitude variation range, A max is the maximum amplitude value in the window, A min is the minimum amplitude value in the window. If the maximum amplitude value in the window is 1.3V and the minimum amplitude value is 0.8V, the amplitude variation range is calculated to be

[0083] ΔA=1.3-0.8=0.5V;

[0084] For frequency, the main frequency and harmonic components are calculated, and the main frequency ratio is calculated using spectral energy distribution. If the main frequency ratio is lower than the threshold ΔP, the window is considered to have main frequency interference. For energy distribution, the energy release rate per unit time within the window is calculated, and the energy uniformity index is calculated. If the energy uniformity index is lower than the set threshold ΔE, it indicates that the signal energy distribution within the window is uneven. For color channel spectral characteristics, the RGB color channel mean and standard deviation are calculated, and the color deviation index is calculated. If the color deviation index exceeds the set threshold ΔC, color distortion is considered to exist within the window. For inter-frame timestamps, the inter-frame time jitter is calculated, the standard deviation of the timestamp is calculated, and the frame rate stability index is calculated. After all feature parameters are extracted, a display signal feature dataset is formed.

[0085] Based on the display signal feature data set, by comparing the amplitude, frequency, and energy characteristics of each type of signal with the preset standard signal waveform library, the characteristic offset value of the signal in each time window is calculated, and the offset trend of the signal waveform is calculated. The specific steps for obtaining the signal waveform characteristic offset value are as follows:

[0086] S201: Based on the display signal feature data set, the amplitude, frequency, and energy features in each time window are obtained, and reference data of the corresponding signal type in the standard signal waveform library are called to compare the amplitude, main frequency distribution, and energy change trend of the signal in each time window. The feature difference of each time window is calculated to obtain the signal feature offset matrix;

[0087] Based on the display signal feature data set, the amplitude, frequency, and energy features of each time window are extracted, and the reference data in the standard signal waveform library is called to obtain the benchmark parameters of the corresponding signal type. The amplitude feature is calculated by determining the amplitude range by the maximum, minimum, and mean values ​​within the window. The frequency feature is calculated from the signal's main frequency and harmonic energy ratio. The energy feature calculates the energy change by integrating the power per unit time within the window. After all calculations are completed, the feature value of each time window is compared with the benchmark parameters of the standard signal to calculate the amplitude difference, main frequency offset, and energy change rate. The calculation formula for the amplitude difference is as follows:

[0088] ΔA=A sig -A ref ;

[0089] Where ΔA is the amplitude offset, A sig is the mean amplitude of the current time window, A ref is the amplitude mean of the corresponding signal type in the standard signal waveform library. If the amplitude mean in the current window is 1.2V, and the amplitude mean of the standard signal is 1.0V, then the calculated value is

[0090] ΔA=1.2-1.0=0.2V;

[0091] Similarly, the main frequency offset calculates the deviation between the main frequency in the window and the main frequency of the reference signal, and the energy change rate calculates the ratio of the energy release rate of the current signal per unit time to the energy release rate of the reference signal. When the energy change rate exceeds the set threshold ΔE, it is considered that the energy change of the current window signal is abnormal. After all feature comparison calculations are completed, the signal feature offset matrix is ​​formed.

[0092] S202: Based on the signal feature offset matrix, analyze the feature offset amplitude of each time window, calculate the rate of change of the offset features in multiple time windows, and compile statistics on the change curve of the offset value in the time series to extract the trend information of the signal fluctuation and obtain the signal offset trend curve;

[0093] Based on the signal feature offset matrix, the amplitude of the feature offset in each time window is analyzed, and the feature offset rate in multiple time windows is calculated. The offset value change curve in the time series is statistically analyzed. The feature offset amplitude is determined by calculating the ratio of the feature offset of the current window to the offset change of the adjacent window. The calculation formula is as follows:

[0094]

[0095] Among them, R ΔA is the amplitude deviation rate, ΔA t is the amplitude offset of the current window, ΔA t-1is the amplitude offset of the previous window. If the amplitude offset of a window is 0.3V and the amplitude offset of the previous window is 0.2V, the amplitude offset rate is calculated to be

[0096]

[0097] Similarly, the main frequency change rate and energy loss rate are calculated, the signal offset in each time window is analyzed, and the trend of feature offset change in the time series is statistically analyzed. If the offset change trend exceeds the set stability threshold ΔS, the signal fluctuation is judged to be abnormal. After all features are calculated, a signal offset trend curve is generated.

[0098] S203: Based on the signal deviation trend curve, calculate the stability of the waveform characteristics, analyze the frequency deviation range, amplitude fluctuation range, and energy loss level of the signal, calculate the signal deviation degree, and obtain the signal waveform characteristic deviation value;

[0099] Based on the signal deviation trend curve, the stability of the signal waveform characteristics is calculated, and the frequency deviation range, amplitude fluctuation range, and energy loss level of the signal are analyzed to calculate the overall deviation of the signal. The frequency deviation range is determined by calculating the relative deviation of the main frequency, the amplitude fluctuation range is calculated by normalizing the difference between the maximum and minimum amplitudes in the window, and the energy loss level is calculated by calculating the ratio of signal energy reduction. The energy loss rate is calculated as follows:

[0100]

[0101] Among them, L E is the energy loss rate, E ref is the energy value of the standard signal, E sig is the energy value of the current signal. If the energy per unit time of the standard signal is 5J and the energy per unit time of the current signal is 4J, then the calculated value is

[0102]

[0103] When the signal deviation exceeds the preset stability limit ΔW, it is considered that the signal has a large fluctuation and the abnormal window is marked. After all calculations are completed, the signal waveform characteristic deviation value is formed.

[0104] Based on the signal waveform characteristic offset value, the timestamp sequence of the playback signal is extracted from the display signal. The time interval between adjacent frames is calculated, and the relative offset of the current timestamp is calculated. By statistically analyzing the offset trend, the time axis offset rate of the playback signal in multiple time windows is calculated. The specific steps for obtaining the time axis offset rate are as follows:

[0105] S301: extracting a timestamp sequence of a playback signal from display signal data based on a signal waveform characteristic offset value, sorting the timestamps, and calculating the time intervals between adjacent timestamps to obtain a playback signal time interval sequence;

[0106] Based on the signal waveform characteristic offset value, the timestamp sequence of the playback signal is extracted from the display signal data. The timestamp data is sorted, and the time intervals between adjacent timestamps are calculated. When extracting timestamp data, the display signal data is first traversed, the timestamp information of each frame is filtered out, and duplicate or abnormal timestamps are removed. For example, some signal data may have abnormal timestamp records due to external interference, such as mutations or data loss. In this case, the timestamps need to be judged for their rationality to ensure data integrity and consistency.

[0107] During the data sorting process, all timestamps are sorted in ascending order to ensure the correctness of the time axis and avoid data disorder affecting the timing analysis of the playback signal. For example, if the original timestamp sequence is {5.016, 5.048, 5.032, 5.064}, it needs to be adjusted to {5.016, 5.032, 5.048, 5.064} to ensure the correct arrangement of the data in the time dimension.

[0108] When calculating the time interval between adjacent timestamps, the calculation method of setting the time interval ΔT between adjacent frames is as follows:

[0109] ΔT i =T i -T i-1 ;

[0110] Where, ΔT i is the playback time interval between the i-th frame and the i-1-th frame, T i is the timestamp of the current frame, T i-1 is the timestamp of the previous frame. For example, if the timestamp of a frame is 5.032 seconds and the timestamp of the previous frame is 5.016 seconds, the time interval of the frame is calculated to be

[0111] ΔT = 5.032 - 5.016 = 0.016 seconds;

[0112] Traverse all frames, calculate the time interval between each adjacent frame, and finally obtain the playback signal time interval sequence for subsequent time axis stability analysis.

[0113] S302: Based on the playback signal time interval sequence, calculate the time interval change rate in each time window, extract the relative offset of the time interval, and analyze the time offset trend in multiple time windows to obtain the playback signal time offset trend;

[0114] Based on the time interval sequence of the playback signal, the time interval change rate within each time window is calculated, the relative offset of the time interval is extracted, and the time offset trend within multiple time windows is analyzed. The time window is divided using the fixed length principle, for example, every 10 frames is a window, so as to observe the time axis stability in different time periods. For each time window, the mean ΔT of all time intervals within the window is calculated. win , and then compare the changes in the mean time intervals between adjacent windows.

[0115] The time interval rate of change is calculated as follows:

[0116]

[0117] Among them, R ΔT Indicates the rate of change of time interval, ΔT t is the mean time interval within the current window, ΔT t-1 is the mean time interval of the previous window. For example, if the mean time interval of a time window is 0.017 seconds, and the mean time interval of the previous window is 0.016 seconds, then the calculated value is

[0118]

[0119] If the rate of change exceeds the set threshold R th , then it is determined that the window has abnormal timing fluctuations. For example, if R th =5%, then the fluctuation anomaly of the window is marked and recorded. In addition, in order to extract the time offset trend, the time interval changes in multiple windows are calculated and the change trend curve of the time axis is drawn.

[0120] Finally, based on the change information of all time windows, the time offset trend of the playback signal is obtained to further calculate the overall stability of the time axis.

[0121] S303: Calculating the time axis offset rate of the playback signal in multiple time windows based on the time offset trend of the playback signal to obtain the time axis offset rate;

[0122] Based on the playback signal's time drift trend, the time axis drift rate of the playback signal within multiple time windows is calculated to quantify the overall temporal stability of the playback signal. The time axis drift rate is used to measure the stability of the playback signal. If the drift rate is too large, it means that the playback signal is experiencing abnormalities such as lag and frame skipping.

[0123] Time axis offset rate S T The calculation is as follows:

[0124]

[0125] Among them, ST Indicates the time axis offset rate, ΔT t is the time interval of the t-th window, is the global time interval mean, and N is the number of windows. For example, if the time interval means in 5 time windows are 0.016, 0.017, 0.016, 0.018, and 0.017 seconds respectively, the global mean is calculated as

[0126]

[0127] Calculate the time axis offset rate

[0128]

[0129] If S T Exceeds the set threshold S th , it means that the stability of the playback signal on the time axis is poor. For example, if S th =0.0005, the current calculation result indicates that the signal's time axis offset exceeds the acceptable range. Finally, the time axis offset rate is obtained to measure the overall time synchronization and stability of the playback signal.

[0130] Based on the time axis offset rate, the frame sequence time curve of the playback signal is extracted, the playback time interval of adjacent frames is calculated, the fluctuation characteristics of the time interval between frames are analyzed, the time period with abnormal fluctuation is identified, and the frame skipping is detected. The specific steps for obtaining the frame skipping detection result are as follows:

[0131] S401: Based on the time axis offset rate, frame sequence time data of the playback signal is obtained, the playback time interval between adjacent frames is calculated, and a frame sequence time curve is drawn to obtain frame sequence time curve data;

[0132] Based on the time axis offset rate, the frame sequence time data of the playback signal is acquired, and the playback timestamp of each frame is extracted. The timestamp data is then preprocessed to remove outliers and ensure correct data order. First, the timestamps corresponding to all frames are extracted from the playback signal dataset and arranged in chronological order to avoid timestamp confusion caused by signal interference or data acquisition delays. An outlier filtering mechanism is used to remove duplicate timestamps or timestamp data with sudden jumps. For example, the time interval between adjacent timestamps is determined to be too small or too large, and a reasonable range is set to avoid subsequent calculation errors caused by data anomalies. After the timestamps are sorted, the time interval between adjacent frames is calculated, that is, the difference between the timestamps of each frame and the previous frame. The time interval calculation requires traversing the entire timestamp sequence and ensuring that no frames are missed or skipped. For example, if the timestamps of adjacent frames are 3.016 seconds, 3.032 seconds, 3.048 seconds, and 3.064 seconds, the time intervals between adjacent frames are calculated to be 0.016 seconds, 0.016 seconds, and 0.016 seconds, respectively. If the time interval of a certain frame deviates significantly from the expected range, for example, it is higher than the reasonable upper limit of the normal playback frame rate, then the frame has a playback anomaly or frame skipping situation, and further analysis is required in subsequent steps. After the calculation is completed, a frame sequence time curve is constructed based on the timestamp and time interval data, and the data is normalized for subsequent analysis. The frame sequence time curve is used to intuitively show the changing trend of the playback signal on the time axis, with the horizontal axis being the frame index and the vertical axis being the playback time interval. The smoothness of the curve data reflects the stability of the playback signal. If there is an obvious mutation point, it indicates that there is frame skipping or unstable playback in this time period. Finally, the frame sequence time curve data is obtained and used as the basic data for subsequent frame skipping detection and playback quality assessment.

[0133] S402: Based on the frame sequence time curve data, calculate the fluctuation amplitude of the time interval between adjacent frames, calculate the time interval change rate, extract the abnormal time period, detect the frame skipping period, and obtain the frame skipping fluctuation abnormal interval;

[0134] Based on the frame sequence time curve data, the fluctuation amplitude of the time interval between adjacent frames is calculated, the time interval change rate is counted, and the abnormal time period is extracted to identify the frame skipping period. The fluctuation amplitude calculation is based on the mean value of the time interval between frames. The standard deviation σ is used to determine whether a frame time interval significantly deviates from the normal range. The formula for calculating the standard deviation is as follows:

[0135]

[0136] Where N is the number of frames in the time window, ΔT i is the time interval of the i-th frame, is the mean time interval of all frames. For example, if the time interval in a time window is {0.016, 0.018, 0.016, 0.020, 0.017}, the calculated mean is

[0137]

[0138] Calculate the standard deviation as

[0139]

[0140] If a frame time interval exceeds For example, setting the threshold σ th =2×0.0016=0.0032, the frame time interval is considered abnormal and the frame skipping period is recorded. Finally, the abnormal frame skipping fluctuation interval is obtained for subsequent frame loss analysis.

[0141] S403: Based on the abnormal frame skipping fluctuation interval, the frame loss ratio is calculated according to the frame skipping frequency, and the changing trend of the frame skipping situation is analyzed to obtain the frame skipping detection result;

[0142] The specific formula for calculating the frame loss ratio based on the frame skipping frequency is:

[0143]

[0144] Calculate the frame loss ratio;

[0145] Among them, R f represents the frame loss ratio, M′ represents the total number of frames, and F j′ represents the timestamp of the j′th frame, F j′-1 Represents the timestamp of the previous frame, T s represents the ideal frame interval, and j′ is the index of the frame.

[0146] formula:

[0147]

[0148] Detailed explanation of the formula and the process of formula calculation and derivation:

[0149] The formula is used to calculate the proportion of frame loss due to frame skipping during the playback process of the in-vehicle display to the total playback time. The result is used in the evaluation process of the frame skipping detection results;

[0150] Parameter meaning and setting value:

[0151] R f The frame loss ratio reflects the percentage of effective playback time lost due to frame skipping during playback to the total playback time;

[0152] M′ represents the total number of frames. The time window is set to 0.1 seconds. Under the standard frame rate of 60 FPS, M′=6;

[0153] F j′ Indicates the timestamp of the j′th frame, and sets the timestamp data F1 = 0ms, F2 = 18ms, F3 = 35ms, F4 = 53ms, F5 = 70ms, and F6 = 88ms;

[0154] T s For the ideal frame interval, set T s =16.67ms.

[0155] Substitute the parameters into the formula for calculation:

[0156]

[0157] R f =0.016+0.004+0.016+0.004+0.016=0.056;

[0158] Calculate R f =0.056, that is, within this time window, the frame loss ratio due to frame skipping or playback time offset is 5.6%. This value is used to further evaluate the frame skipping detection result.

[0159] Based on the frame skipping detection results, use image acquisition equipment to detect color shift in multiple areas of the display, calculate the color accuracy score, and combine the inter-frame fluctuations and signal waveform quality to evaluate the display's playback quality. The specific steps for obtaining the playback quality score are as follows:

[0160] S501: Based on the frame skipping detection results, using an image acquisition device, color data is collected from multiple areas of the display, color channel spectral values ​​of each area are extracted, and the degree of color shift between color channels is calculated. The degree of color shift at multiple locations is calculated by comparing with color standard reference values ​​to obtain color shift detection data;

[0161] Based on the frame skipping detection results, an image acquisition device is used to collect color data from multiple areas of the display. The color channel spectral values ​​of each area are extracted, and the degree of color shift between the color channels is calculated. This is then compared to color standard reference values ​​to calculate the degree of color shift at multiple locations. During the data acquisition process, the image acquisition device's exposure parameters are first set to match the display's brightness range to prevent color distortion caused by over- or underexposure. The image acquisition device is then fixed to multiple preset sampling points, such as the four corners of the screen, the center area, and evenly distributed grid points. The color data collected at each point includes the spectral reflectance of the red, green, and blue (RGB) channels, and their spectral energy distribution is recorded.

[0162] When calculating the degree of color deviation between color channels, the standard color reference value C is used. ref Compare and calculate the color offset ΔC of each pixel:

[0163]

[0164] Among them, R, G, B represent the red, green, and blue channel spectral values ​​of the current acquisition point respectively. ref ,G ref ,B ref For example, if the RGB value of a certain acquisition point is (220, 200, 190) and the standard reference value is (230, 210, 200), then the calculation is:

[0165]

[0166] The color shift is calculated by traversing all measurement points, and a color shift heat map is formed to finally obtain the color shift detection data.

[0167] S502: Calculating the color shift amount of each color channel in multiple areas of the display based on the color shift detection data, evaluating the degree of color shift of the display, and obtaining a color accuracy score result;

[0168] Based on the color shift detection data, the offset of multiple areas of the display in each color channel is calculated to evaluate the degree of color shift of the display. For the color shift of different areas, the color shift mean ΔC and standard deviation σ are calculated to determine whether the color shift exceeds the allowable range. The formula for calculating the regional color shift mean is as follows:

[0169]

[0170] Where N is the number of measurement areas, ΔC i is the color deviation of the ith region. For example, if the color deviation values ​​of the five measurement regions are {15.2, 16.5, 18.3, 14.7, 17.1}, the mean is calculated as:

[0171]

[0172] When judging the degree of color shift, set the color shift threshold ΔC th For example, if the standard allowable range is 15.0, areas exceeding this threshold are considered to have severe color shift. When calculating the color uniformity index, the standard deviation σ is used to calculate the distribution of color shift. If σ is too large, it indicates an uneven distribution of color shifts. Finally, the regional mean, standard deviation, and threshold are combined to obtain a color accuracy score for subsequent playback quality analysis.

[0173] S503: Based on the color accuracy scoring result, combined with the inter-frame fluctuation and signal waveform quality, the display playback quality is evaluated to obtain a playback quality score;

[0174] The specific formula for evaluating the display's playback quality is:

[0175]

[0176] Calculate the comprehensive playback quality score;

[0177] Among them, Q s is the comprehensive playback quality score, β1 is the weight coefficient corresponding to the color accuracy score, β2 is the weight coefficient corresponding to the inter-frame fluctuation score, and β3 is the weight coefficient corresponding to the signal waveform quality score. X1 represents the color accuracy score of the display, X2 represents the inter-frame fluctuation score, and X3 represents the signal waveform quality score.

[0178] formula:

[0179]

[0180] Detailed explanation of the formula and calculation process:

[0181] The formula is used to calculate a comprehensive playback quality score, and the result is used to evaluate the overall playback quality performance of the display;

[0182] Parameter meaning and setting value:

[0183] X1 represents the color accuracy score of the display, set X1 = 85;

[0184] X2 represents the inter-frame fluctuation score, set X2 = 72;

[0185] X3 represents the signal waveform quality score, set X3 = 78;

[0186] β1, β2, and β3 are parameter weights. The color accuracy score weight β1 is set to 0.4, the inter-frame fluctuation score weight β2 is set to 0.3, and the signal waveform quality score weight β3 is set to 0.3.

[0187] Substitute the parameters into the formula for calculation:

[0188] β1X1=0.4×85=34;

[0189] β2X2=0.3×72=21.6;

[0190] β3X3=0.3×78=23.4;

[0191]

[0192] Results s=79 indicates the overall playback quality score of the monitor, reflecting the performance of the monitor under comprehensive evaluation of multiple parameters.

[0193] See also Figure 2 , a playback quality assessment system for a vehicle-mounted display, the playback quality assessment system for a vehicle-mounted display is used to execute the above-mentioned playback quality assessment method for the vehicle-mounted display, and the system includes:

[0194] The signal feature extraction module extracts the amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps from the vehicle display signal to divide the signal into time windows. It then establishes a feature parameter set within each time window to generate a display signal feature dataset.

[0195] The signal offset analysis module extracts the standard signal amplitude, frequency, and energy characteristics from the standard signal waveform library based on the display signal feature data set, calculates the amplitude error, frequency offset, and energy loss ratio in each time window, analyzes the signal offset trend, calculates the fluctuation of the offset rate, and obtains the signal waveform feature offset value;

[0196] The time axis offset detection module extracts the timestamp sequence of the playback signal based on the signal waveform feature offset value, calculates the time interval between adjacent frames, identifies the time points of abnormal intervals, analyzes the time axis drift trend in multiple time windows, and obtains the time axis offset rate;

[0197] The frame skipping identification module extracts the frame sequence time curve of the playback signal based on the time axis offset rate, calculates the playback time interval between adjacent frames, and detects frame skipping in real time by analyzing the time period with abnormal time interval changes to obtain the frame skipping detection results;

[0198] Based on the frame skipping detection results, the playback quality assessment module uses image acquisition equipment to detect color deviation in multiple areas of the display, calculates the color accuracy score of the display, and combines the inter-frame fluctuation characteristics and signal waveform quality data to evaluate the playback quality of the vehicle display and obtain a playback quality score.

[0199] The above embodiments can be implemented in whole or in part through software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0200] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0201] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0202] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0203] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0204] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0205] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0206] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0207] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0208] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0209] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for evaluating the playback quality of an in-vehicle display, characterized in that: The method comprises: S1: Obtain the vehicle display signal, extract the signal's amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, perform time series segmentation, extract the feature parameter set within each time window, and obtain the display signal feature dataset; The display signal feature data set includes amplitude features, frequency features, and energy distribution features; S2: Based on the display signal feature data set, by comparing the amplitude, frequency, and energy characteristics of each type of signal with those in a preset standard signal waveform library, calculating the feature offset value of the signal in each time window, calculating the offset trend of the signal waveform, and obtaining the signal waveform feature offset value; S3: Based on the signal waveform characteristic offset value, extract the timestamp sequence of the playback signal from the display signal, calculate the time interval between adjacent frames, calculate the relative offset of the current timestamp, and calculate the time axis offset rate of the playback signal in multiple time windows by statistically analyzing the offset trend to obtain the time axis offset rate; S4: extracting a frame sequence time curve of the playback signal based on the time axis offset rate, calculating the playback time interval between adjacent frames, analyzing the fluctuation characteristics of the time interval between frames, identifying the time period with abnormal fluctuation, detecting frame skipping, and obtaining a frame skipping detection result; S5: Based on the frame skipping detection results, use an image acquisition device to detect color deviation in multiple areas of the display, calculate a color accuracy score, and evaluate the display's playback quality based on inter-frame fluctuations and signal waveform quality to obtain a playback quality score.

2. The playback quality evaluation method of an in-vehicle display according to claim 1, characterized in that: The signal waveform feature offset value specifically includes the amplitude offset, frequency offset, and energy feature offset; the time axis offset rate includes the adjacent frame time interval offset rate, the global time axis drift rate, and the time series cumulative offset rate; the frame skipping detection result includes the frame skipping frequency, frame skipping time period, and frame skipping type; the playback quality score specifically refers to the signal waveform quality score, the time axis stability score, and the comprehensive display playback quality score.

3. The playback quality evaluation method of a vehicle-mounted display according to claim 1, characterized in that: The steps for obtaining the vehicle display signal, extracting the signal's amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, performing time series segmentation, and extracting the feature parameter set within each time window to obtain the display signal feature dataset are as follows: S101: Acquire the vehicle display signal, extract the amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, perform time sorting on each data item, and obtain the basic data set of the display signal; S102: Based on the display signal basic data set, the data is divided into time windows, and the signal mean, fluctuation amplitude, and frequency stability in each window are calculated to obtain time series division data; S103: Based on the time-series partitioned data, extract multiple characteristic parameters in each time window, including amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps, to obtain a display signal characteristic data set.

4. The method for evaluating the playback quality of an in-vehicle display according to claim 1, wherein: Based on the display signal feature data set, by comparing the amplitude, frequency, and energy characteristics of each type of signal with those in a preset standard signal waveform library, calculating the characteristic offset value of the signal in each time window, calculating the offset trend of the signal waveform, and obtaining the signal waveform characteristic offset value, the specific steps are as follows: S201: Based on the display signal feature data set, the amplitude, frequency, and energy features in each time window are obtained, and reference data of the corresponding signal type in the standard signal waveform library are called to compare the amplitude, main frequency distribution, and energy change trend of the signal in each time window, calculate the feature difference of each time window, and obtain the signal feature offset matrix; S202: Based on the signal feature offset matrix, analyze the feature offset amplitude of each time window, calculate the rate of change of the offset features in multiple time windows, and calculate the change curve of the offset value in the time series to extract the trend information of the signal fluctuation and obtain the signal offset trend curve; S203: Based on the signal deviation trend curve, the stability of the waveform characteristics is calculated, the frequency deviation range, amplitude fluctuation range, and energy loss level of the signal are analyzed, the degree of signal deviation is calculated, and the signal waveform characteristic deviation value is obtained.

5. The method for evaluating the playback quality of an in-vehicle display according to claim 1, wherein: Based on the signal waveform characteristic offset value, extract the timestamp sequence of the playback signal from the display signal, calculate the time interval between adjacent frames, calculate the relative offset of the current timestamp, and calculate the time axis offset rate of the playback signal in multiple time windows by statistically analyzing the offset trend. The steps of obtaining the time axis offset rate are specifically as follows: S301: extracting a timestamp sequence of a playback signal from display signal data based on the signal waveform characteristic offset value, sorting the timestamps, and calculating the time intervals between adjacent timestamps to obtain a playback signal time interval sequence; S302: Based on the playback signal time interval sequence, calculate the time interval change rate in each time window, extract the relative offset of the time interval, and analyze the time offset trend in multiple time windows to obtain the playback signal time offset trend; S303: Based on the time offset trend of the playback signal, calculate the time axis offset rate of the playback signal in multiple time windows to obtain the time axis offset rate.

6. The method for evaluating the playback quality of an in-vehicle display according to claim 1, wherein: The steps of extracting a frame sequence time curve of a playback signal based on the time axis offset rate, calculating the playback time interval between adjacent frames, analyzing the fluctuation characteristics of the time interval between frames, identifying the time period with abnormal fluctuation, detecting frame skipping, and obtaining a frame skipping detection result are as follows: S401: Based on the time axis offset rate, frame sequence time data of the playback signal is obtained, the playback time interval between adjacent frames is calculated, and a frame sequence time curve is drawn to obtain frame sequence time curve data; S402: Based on the frame sequence time curve data, calculate the fluctuation amplitude of the time interval between adjacent frames, calculate the time interval change rate, extract the abnormal time period, detect the frame skipping period, and obtain the frame skipping fluctuation abnormal interval; S403: Based on the abnormal frame skipping fluctuation interval, the frame loss ratio is calculated according to the frame skipping frequency, and the changing trend of the frame skipping situation is analyzed to obtain a frame skipping detection result.

7. The method for evaluating the playback quality of an in-vehicle display according to claim 6, wherein: The specific formula for calculating the frame loss ratio based on the frame skipping frequency is: Calculate the frame loss ratio; Among them, R f represents the frame loss ratio, M′ represents the total number of frames, and F j′ represents the timestamp of the j′th frame, F j′-1 Represents the timestamp of the previous frame, T s represents the ideal frame interval, and j′ is the index of the frame.

8. The method for evaluating the playback quality of an in-vehicle display according to claim 1, wherein: Based on the frame skipping detection results, an image acquisition device is used to detect color shifts in multiple areas of the display, calculate a color accuracy score, and evaluate the display's playback quality based on inter-frame fluctuations and signal waveform quality. The specific steps for obtaining the playback quality score are as follows: S501: Based on the frame skipping detection result, using an image acquisition device, color data is collected in multiple areas of the display, color channel spectral values ​​of each area are extracted, and the degree of color deviation between color channels is calculated. The degree of color deviation at multiple locations is calculated by comparing with a color standard reference value to obtain color deviation detection data; S502: Calculating the offset of multiple areas of the display in each color channel based on the color offset detection data, evaluating the degree of color offset of the display, and obtaining a color accuracy scoring result; S503: Based on the color accuracy scoring result, combined with inter-frame fluctuations and signal waveform quality, evaluate the playback quality of the display to obtain a playback quality score; The specific formula for evaluating the display's playback quality is: Calculate the comprehensive playback quality score; Among them, Q s is the comprehensive playback quality score, β1 is the weight coefficient corresponding to the color accuracy score, β2 is the weight coefficient corresponding to the inter-frame fluctuation score, and β3 is the weight coefficient corresponding to the signal waveform quality score. X1 represents the color accuracy score of the display, X2 represents the inter-frame fluctuation score, and X3 represents the signal waveform quality score.

9. A playback quality assessment system for an in-vehicle display, characterized in that: The method for evaluating the playback quality of an in-vehicle display according to any one of claims 1 to 8, wherein the system comprises: The signal feature extraction module extracts the amplitude, frequency, energy distribution, color channel spectral characteristics, and inter-frame timestamps from the vehicle display signal to divide the signal into time windows. It then establishes a feature parameter set within each time window to generate a display signal feature dataset. The signal offset analysis module extracts the standard signal amplitude, frequency, and energy characteristics from the standard signal waveform library based on the display signal feature data set, calculates the amplitude error, frequency offset, and energy loss ratio in each time window, analyzes the signal offset trend, calculates the fluctuation of the offset rate, and obtains the signal waveform feature offset value; The time axis offset detection module extracts the timestamp sequence of the playback signal based on the signal waveform characteristic offset value, calculates the time interval between adjacent frames, identifies the time points of abnormal intervals, analyzes the time axis drift trend in multiple time windows, and obtains the time axis offset rate; The frame skipping identification module extracts the frame sequence time curve of the playback signal based on the time axis offset rate, calculates the playback time interval between adjacent frames, and detects frame skipping in real time by analyzing the time period when the time interval changes abnormally, thereby obtaining a frame skipping detection result; Based on the frame skipping detection results, the playback quality assessment module uses an image acquisition device to detect the color deviation of multiple areas of the display, calculates the color accuracy score of the display, and combines the inter-frame fluctuation characteristics and signal waveform quality data to evaluate the playback quality of the vehicle display and obtain a playback quality score.

Images