User driving condition test case construction method and computer readable storage medium

Abstract

The user driving condition test case construction method comprises the following steps: connecting a user vehicle through a cloud server to obtain vehicle uploading data, and generating a user driving fragment set according to the vehicle uploading data, each user driving fragment in the user driving fragment set comprises vehicle upload data between the adjacent power-on signal and power-off signal, and the vehicle upload data comprises vehicle body operation data and environment data; a test terminal is connected with a cloud server, the cloud server obtains a user driving fragment set, and the test terminal performs feature value extraction on each user driving fragment in the user driving fragment set; the test terminal performs clustering analysis on the user driving fragment set according to the feature values of the user driving fragments to determine a plurality of basic user driving fragments; and the test terminal determines working condition coefficients of the multiple basic user driving segments according to a preset working condition interval and the multiple basic user driving segments, and generates a user driving working condition test case set.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle driving characteristic evaluation test in a test phase, and in particular to a method for constructing a user driving condition test case. Background Art

[0002] The current driving characteristics evaluation test is a subjective evaluation test developed based on function-oriented development, in which the evaluation items guided by the test are all based on the accumulated experience of the driver's driving conditions and driving behavior. However, this test evaluation is highly dependent on the driver's driving experience and subjective feelings. Therefore, in order to better meet the driving needs of Chinese users and reduce driving-related complaints and claims from Chinese users, it is necessary to summarize the driving behavior habits of Chinese users to optimize the test, and to carry out relevant tests for the subsequent independently developed Jetta J01, J02, HEV, PHEV and other projects to find problems in advance and prevent them from flowing into users. However, there is currently no corresponding user driving condition library corresponding to the driving conditions of Chinese users, and there is no detailed and accurate method to well summarize the driving condition space of Chinese users. There are typical conditions or special conditions of users that have not been tested, which causes after-sales complaints and even claims. Summary of the invention

[0003] To solve at least one aspect of the above technical problems, the present invention provides a method for constructing a user driving condition test case, comprising: connecting a user vehicle through a cloud server to obtain vehicle uploaded data, and generating a user driving segment set according to the vehicle uploaded data, wherein each user driving segment in the user driving segment set includes the vehicle uploaded data between adjacent power-on signals and power-off signals, and the vehicle uploaded data includes vehicle body operation data and environmental data; connecting the cloud server through a test terminal to obtain the user driving segment set, and the test terminal extracts feature values ​​for each user driving segment in the user driving segment set; the test terminal performs cluster analysis on the user driving segment set according to the feature values ​​of the user driving segments to determine a plurality of basic user driving segments; the test terminal determines the operating condition coefficients of a plurality of basic user driving segments respectively according to a preset operating condition interval and the plurality of basic user driving segments, and generates a user driving condition test case set, wherein each user driving condition test case in the user driving condition test case set includes a basic user driving segment and its corresponding operating condition coefficient.

[0004] Preferably, the method further comprises: receiving a test case update instruction input by a user through the test terminal, the test terminal reacquiring the user driving segment set in response to the test case update instruction, and generating an updated user driving condition test case set.

[0005] Preferably, the step of connecting the user vehicle to obtain the vehicle uploaded data through the cloud server also includes: the cloud server includes a preset collection cycle, and the user vehicle outputs the vehicle uploaded data to the cloud server based on the preset collection cycle.

[0006] Preferably, the vehicle body operation data includes time, vehicle speed, mileage, throttle, brake, slope, steering wheel angle, gear position, the environmental data includes temperature, humidity and altitude, and the characteristic values ​​of the user's driving segment include average vehicle speed, maximum vehicle speed, total time, mileage, idle time percentage, coasting time percentage, deceleration time percentage, average acceleration, maximum acceleration, average deceleration, maximum deceleration, average temperature, average humidity and average altitude.

[0007] Preferably, the step of performing cluster analysis on the user traveling segment set according to the characteristic values ​​of the user traveling segments to determine multiple basic user traveling segments also includes: using a K-means algorithm to perform cluster analysis on the user traveling segment set based on the characteristic values, and using the elbow rule to determine the corresponding cluster number and user traveling segment cluster of the user traveling segment set; and taking the user traveling segment with the closest centroid value to each user traveling segment cluster as the basic user traveling segment.

[0008] Preferably, the operating condition coefficient is any one or more combinations of vehicle speed, slope, braking, throttle, turning angle, ambient temperature, altitude and temperature.

[0009] Preferably, the operating condition coefficient also includes any one or more combinations of a temperature time curve, a turning angle time curve, a throttle time curve, a braking time curve, a slope time curve and a vehicle speed time curve.

[0010] On the other hand, a computer-readable storage medium is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method for constructing a user driving condition test case as described above is executed.

[0011] The method for constructing a user driving condition test case disclosed in the present invention has the following beneficial effects: by using the vehicle upload data between a power-on signal and a power-off signal as a user driving segment, the driving condition data of a complete driving behavior of the user can be collected, and by clustering the user driving condition segment data, typical user driving behavior can be obtained, and the construction problem of typical user driving condition test cases can be further solved. Furthermore, based on the real-time upload data of the user vehicle, the test case set can be updated in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to better understand the above and other purposes, features, advantages and functions of the present invention, reference may be made to the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings refer to the same components. It should be understood by those skilled in the art that the accompanying drawings are intended to schematically illustrate the preferred embodiments of the present invention and have no limiting effect on the scope of the present invention, and the components in the drawings are not drawn to scale.

[0013] Figure 1 A schematic diagram of the process of constructing a user driving condition test case according to an embodiment of the present invention is shown;

[0014] Figure 2 A K clustering schematic diagram of a method for constructing a user driving condition test case according to an embodiment of the present invention is shown;

[0015] Figure 3 A schematic diagram of the elbow rule according to the method for constructing a user driving condition test case according to an embodiment of the present invention is shown;

[0016] Figure 4 A structural block diagram of a method for constructing a user driving condition test case according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0017] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0018] As used herein, the term "including" and its variations mean open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "based at least in part on". The terms "an example embodiment" and "an embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0019] In order to at least partially solve one or more of the above-mentioned problems and other potential problems, an embodiment of the present disclosure proposes a method for constructing a user driving condition test case, including: connecting a user vehicle through a cloud server to obtain vehicle uploaded data, and generating a user driving segment set based on the vehicle uploaded data, each user driving segment in the user driving segment set includes the vehicle uploaded data between adjacent power-on signals and power-off signals, and the vehicle uploaded data includes vehicle body operation data and environmental data; connecting a cloud server through a test terminal to obtain the user driving segment set, the test terminal extracts feature values ​​for each user driving segment in the user driving segment set; the test terminal performs cluster analysis on the user driving segment set according to the feature values ​​of the user driving segments to determine multiple basic user driving segments; the test terminal determines the operating condition coefficients of multiple basic user driving segments respectively according to the preset operating condition interval and the multiple basic user driving segments, and generates a user driving condition test case set, each user driving condition test case in the user driving condition test case set includes a basic user driving segment and its corresponding operating condition coefficient.

[0020] Specifically, Figure 1 As shown, the manufacturer of the user's vehicle communicates with the user's vehicle through the cloud server to receive the vehicle's uploaded data. The period of the vehicle's uploaded data is set by the user, or the vehicle's uploaded data is received in response to the collection instruction of the cloud server. It can be understood by those skilled in the art that the number of user vehicles connected to the cloud server is very large, and each user's vehicle corresponds to a user tag. The cloud server identifies the corresponding vehicle's uploaded data according to the user tag. The cloud server also includes a memory and a processor. The memory is used to store the received vehicle's uploaded data, and the processor is used to generate a user's driving segment according to the stored vehicle's uploaded data.

[0021] The vehicle upload data received by the cloud server through the user vehicle is continuous. In some embodiments, the user vehicle continuously transmits the vehicle upload data to the cloud server. The cloud server sets an interception period and intercepts the continuous vehicle upload data of the user vehicle based on the interception period. For example, the continuous vehicle upload data is intercepted with 1s as the time node. Signal analysis is performed on the intercepted vehicle upload data. The vehicle upload data includes a power-on signal and a power-off signal. The vehicle upload data between the power-on signal and the power-off signal is determined as a user driving segment through the timing of the intercepted vehicle upload data. The user driving segment also includes all the vehicle body operation data and environmental data between the power-on signal and the power-off signal of the user vehicle. The cloud server divides the vehicle upload data of each user vehicle among all the received user vehicles into user driving segments based on the timing of the power-on signal and the power-off signal, and generates a user driving segment set.

[0022] The test terminal includes a communication module, a processing module and a storage module. The test terminal is connected to the cloud server for communication, and the test terminal receives the user driving segment set through the cloud server. The test terminal generates a user driving condition test case based on the user driving segment set.

[0023] The test terminal extracts feature values ​​from the vehicle uploaded data of each user driving segment in the user driving segment set. The test terminal determines or calculates the feature value of each user driving segment according to a preset feature value extraction rule. The preset feature value extraction rule includes a calculation object and a calculation method. Specifically, the preset feature value extraction rule can be set according to actual needs.

[0024] The test terminal performs cluster analysis on the user travel segment set based on the extracted feature values, determines the number of clusters of the user travel segment set, and uses the center value corresponding to each cluster as the basic user travel segment. The number of the multiple basic user travel segments determined by the test terminal is equal to the number of clusters.

[0025] The working condition coefficient of the basic user driving segment is determined based on the preset working condition interval and the vehicle uploaded data of each basic user driving segment. The preset working condition interval is an interval division based on the specific values ​​of each body operation data and environmental data in the vehicle uploaded data, and the working condition coefficient is the coefficient value corresponding to each preset working condition interval. According to the specific values ​​of the vehicle uploaded data of each basic user driving segment, the corresponding preset working condition interval can be determined, thereby determining its working condition coefficient.

[0026] In some embodiments, it also includes: receiving a test case update instruction input by a user through a test terminal, the test terminal reacquiring a user driving segment set in response to the test case update instruction, and generating an updated user driving condition test case set.

[0027] Specifically, the cloud server receives and stores the vehicle upload data of the user's vehicle in real time, and the cloud server updates the user's driving segment set in real time based on the received vehicle upload data. The test terminal connects to the cloud server to receive the user's driving segment set in response to the test case update instruction. The test terminal can update the user's driving segment set in response to the test case update instruction.

[0028] In another embodiment, the cloud server receives and stores the vehicle upload data of the user's vehicle in real time, the cloud server receives the test case update instruction through the test terminal, and the cloud server generates an updated user driving segment set in response to the test case update instruction, and further outputs the updated user driving segment set to the test terminal.

[0029] In some embodiments, the step of connecting the user vehicle to obtain the vehicle uploaded data through the cloud server also includes: the cloud server includes a preset collection cycle, and the user vehicle outputs the vehicle uploaded data to the cloud server based on the preset collection cycle.

[0030] Specifically, the cloud server outputs a preset collection cycle to the user vehicle, and the user vehicle outputs the vehicle upload data in response to the preset collection cycle. The vehicle long-transmission data is the continuous vehicle body operation data and environmental data collected by the user vehicle itself within the preset collection cycle. The preset collection cycle can realize the periodic data transmission of the cloud server and the user vehicle transmission data, which can avoid the data processing load of the cloud server caused by real-time transmission.

[0031] In some embodiments, the vehicle operation data includes time, speed, mileage, throttle, brake, slope, steering wheel angle, gear position, the environmental data includes temperature, humidity and altitude, and the characteristic values ​​of the user's driving segments include average speed, maximum speed, total time, mileage, idle time percentage, coasting time percentage, deceleration time percentage, average acceleration, maximum acceleration, average deceleration, maximum deceleration, average temperature, average humidity and average altitude.

[0032] Specifically, the user's driving segment includes multiple groups of vehicle body operation data and environmental data, and the time interval between each group of vehicle body operation data and environmental data is 1s. The total time of the user's driving segment can be determined according to the time information in each group of vehicle body operation data in the user's driving segment. The characteristic value average speed of the user's driving segment is obtained by calculating the average value of the vehicle speed of the multiple groups of vehicle body data operation data in the user's driving segment, and the average acceleration, average deceleration, etc. are calculated in the same way. At the same time, the idle state is judged by the gear position and the vehicle end, and the idle time and the proportion of idle time are further determined. In some embodiments, the vehicle body operation data also includes acceleration, and the average acceleration is calculated by the acceleration of multiple groups of vehicle body operation data in the user's driving segment. In another embodiment, the acceleration is calculated by the speed of each group of vehicle body operation data, and the maximum acceleration and the calculated average acceleration are further determined. Similarly, the maximum deceleration and the calculated average deceleration are determined.

[0033] In some embodiments, the step of performing cluster analysis on a user traveling segment set according to the feature values ​​of the user traveling segments to determine a plurality of basic user traveling segments also includes: performing cluster analysis on the user traveling segment set based on the feature values ​​using a K-means algorithm, and determining the corresponding number of clusters and user traveling segment clusters of the user traveling segment set using the elbow rule; and taking the user traveling segment with the closest centroid value to each user traveling segment cluster as the basic user traveling segment.

[0034] Specifically, the K-means algorithm performs cluster analysis on user driving segments. Perform cluster analysis on user driving segments to obtain user driving segment clusters and centroid values, and calculate the loss function for each cluster cluster; determine the cluster number K of the user driving segment set by the axis rule: change the cluster number, calculate the loss function, and the inflection point is the recommended cluster number K, such as Figure 2 A user driving segment cluster is defined as a user driving condition classification, the user driving segment closest to the centroid value is defined as the basic user driving segment under the corresponding category, and the set of basic user driving segments is defined as the basic user driving condition.

[0035] In some embodiments, the operating condition coefficient is a combination of any one or more of vehicle speed, slope, braking, throttle, corner, ambient temperature, altitude and temperature.

[0036] Specifically, the operating coefficient value of each basic user driving segment is determined based on the vehicle uploaded data of the basic user driving segment. The preset operating condition intervals include vehicle speed interval, slope interval, braking interval, throttle interval, corner interval, ambient temperature interval, altitude interval and temperature interval. The operating coefficient value is determined based on the value of each operating condition interval.

[0037] As shown in Table 1, when the vehicle speed in the basic user driving segment is 0, the operating coefficient corresponding to the vehicle speed interval is V1; when the vehicle speed is in the range of 0 to 10, the operating coefficient corresponding to the vehicle speed interval is V2, and so on.

[0038] As shown in Table 2, for the non-slope driving condition, when the environmental slope in the basic user driving segment is 0° to 5°, the operating condition coefficient corresponding to the slope interval is S6; for the downhill driving condition, when the environmental slope is below -20°, the operating condition coefficient corresponding to the slope interval is S1; for the uphill driving condition, when the environmental slope is above 20°, the operating condition coefficient corresponding to the slope interval is S10, and so on.

[0039] Table 1 User vehicle speed conditions

[0040]

[0041] Table 2 User slope conditions

[0042]

[0043] As shown in Table 3, for the driving condition without braking, when the braking interval in the basic user driving segment is 0, the operating condition coefficient corresponding to the braking interval is D1; ​​for the driving condition of light braking, when the braking interval is between 0-10, the operating condition coefficient corresponding to the braking interval is D2; for the driving condition of medium braking, when the braking interval is between 40-50, the operating condition coefficient corresponding to the braking interval is D6; for the driving condition of deep braking, when the braking interval is between 80-90, the operating condition coefficient corresponding to the braking interval is D10, and so on.

[0044] As shown in Table 4, for the no-accelerator condition, when the throttle interval in the basic user driving segment is 0, the operating condition coefficient corresponding to the throttle interval is A1; for the light-accelerator driving condition, when the throttle interval is between 0-10, the operating condition coefficient corresponding to the throttle interval is A2; for the medium-accelerator driving condition, when the throttle interval is between 40-50, the operating condition coefficient corresponding to the throttle interval is A6; for the deep-accelerator driving condition, when the throttle interval is between 80-90, the operating condition coefficient corresponding to the throttle interval is A10, and so on.

[0045] Table 3 Braking operating range

[0046]

[0047] Table 4 User throttle operating conditions

[0048]

[0049] As shown in Table 5, for the straight driving condition, the steering wheel angle interval in the basic user driving segment is 0, and the operating condition coefficient corresponding to the steering wheel angle interval is A1; for the driving condition with a small steering angle, when the steering wheel angle interval is between 0-10, the operating condition coefficient corresponding to the steering wheel angle interval is A2; for the driving condition with a small steering angle, when the steering wheel angle interval is between 5-10, the operating condition coefficient corresponding to the steering wheel angle interval is A3; for the driving condition with a large steering angle, when the steering wheel angle interval is between 10-15, the operating condition coefficient corresponding to the steering wheel angle interval is A4; for the driving condition with a large steering angle, when the steering wheel angle interval is between 25-30, the operating condition coefficient corresponding to the steering wheel angle interval is C7, and so on.

[0050] Table 5 User steering wheel angle conditions

[0051]

[0052] As shown in Table 6, when the gear operating condition in the basic user-shaped driving segment is the reverse gear R, the operating condition coefficient corresponding to the gear interval is G1; when the gear operating condition is the parking gear P, the operating condition coefficient corresponding to the gear interval is G2; when the gear operating condition is D gear driving, the operating condition coefficient corresponding to the gear interval is G3, and other gears are shown in the table.

[0053] Table 6 User gear working conditions

[0054]

[0055] As shown in Table 7, when the gear operating condition in the basic user-shaped driving segment is 1st gear driving, the operating condition coefficient corresponding to the gear interval is SH1, when the gear operating condition is 2nd gear driving, the operating condition coefficient corresponding to the gear interval is SH2; when the gear operating condition is R gear driving, the operating condition coefficient corresponding to the gear interval is SHR, and other gears are shown in the table.

[0056] Table 7 User gear position SH condition (fuel vehicle)

[0057]

[0058] As shown in Table 8, for the engine speed operating conditions, under idle conditions, when the engine speed range in the basic user driving segment is 800-1000, the operating condition coefficient corresponding to the engine speed range is ES1; for low-speed driving conditions, when the engine speed range is between 1200-1500, the operating condition coefficient corresponding to the engine speed range is ES3; for medium-speed driving conditions, when the engine speed range is between 2000-2500, the operating condition coefficient corresponding to the engine speed range is ES5; for high-speed driving conditions, when the engine speed range is between 3000-4000, the operating condition coefficient corresponding to the engine speed range is ES7, and the operating condition coefficients corresponding to other operating ranges are shown in the chart.

[0059] Table 8 User engine speed conditions (fuel vehicle)

[0060]

[0061] As shown in Table 9, for the ambient temperature conditions, when the extremely cold interval in the basic user driving segment is below -35°C, the operating condition coefficient corresponding to the temperature interval is AT1; for the specific temperatures of the cold operating condition interval, the cold operating condition interval cold, the relatively cold operating condition interval, the cool operating condition interval, the relatively cool operating condition interval, the warm operating condition interval, the hot operating condition interval, and the extremely hot operating condition interval, the specific operating condition coefficients are determined according to Table 9.

[0062] Table 9 User ambient temperature conditions

[0063]

[0064] As shown in Table 10, for the altitude condition, the specific environmental altitude value in the basic user driving segment determines the altitude condition coefficient according to its corresponding interval.

[0065] Table 10 User altitude working conditions

[0066]

[0067] As shown in Table 11, for the ambient humidity condition, the ambient humidity condition intervals include extremely dry, relatively dry, dry, comfortably dry, slightly humid, slightly humid, humid, relatively humid, and extremely humid. The corresponding condition interval is determined according to the humidity value in the vehicle uploaded data of the basic user driving segment, and then the corresponding humidity condition coefficient is determined according to Table 11.

[0068] Table 11 User environmental humidity conditions

[0069]

[0070] As shown in Table 12, the time ratio of each operating condition coefficient combination in the basic user driving segment is divided into multiple subdivided operating conditions, and each subdivided operating condition corresponds to a set of different operating condition coefficient values. Each subdivided operating condition is a user driving condition test case.

[0071] Table 12 User driving test case set

[0072]

[0073] In some embodiments, the operating condition coefficient also includes any one or more combinations of a temperature time curve, a corner time curve, a throttle time curve, a braking time curve, a slope time curve and a vehicle speed time curve.

[0074] Specifically, Figure 2 As shown, a user driving condition test case set is generated based on the temperature time curve, corner time curve, throttle time curve, brake time curve, slope time curve and vehicle speed time curve of multiple basic user driving segments as the operating condition coefficients. When selecting the test case, a vehicle test or simulation test is performed according to each operating condition coefficient.

[0075] On the other hand, a computer-readable storage medium is provided, comprising a computer program, which, when executed by a processor, executes the method for constructing a user driving condition test case as described above.

[0076] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the present invention.

Claims

1. A method for constructing a user driving condition test case, characterized in that: include: Connecting the user vehicle through the cloud server to obtain the vehicle uploaded data, and generating a user driving segment set according to the vehicle uploaded data, each user driving segment in the user driving segment set includes the vehicle uploaded data between adjacent power-on signals and power-off signals, and the vehicle uploaded data includes vehicle body operation data and environment data; Connecting the cloud server via a test terminal to obtain the user driving segment set, wherein the test terminal extracts feature values ​​from each user driving segment in the user driving segment set; The test terminal performs cluster analysis on the user travel segment set according to the feature values ​​of the user travel segments to determine a plurality of basic user travel segments; The test terminal determines the operating condition coefficients of multiple basic user driving segments according to the preset operating condition interval and the multiple basic user driving segments, and generates a user driving operating condition test case set. Each user driving operating condition test case in the user driving operating condition test case set includes a basic user driving segment and its corresponding operating condition coefficient.

2. The method according to claim 1, characterized in that Also includes: The test terminal receives a test case update instruction input by a user, and the test terminal reacquires the user driving segment set in response to the test case update instruction, and generates an updated user driving condition test case set.

3. The method according to claim 2, characterized in that The step of connecting the user vehicle to obtain the vehicle uploaded data through the cloud server also includes: the cloud server includes a preset collection cycle, and the user vehicle outputs the vehicle uploaded data to the cloud server based on the preset collection cycle.

4. The method according to claim 3, characterized in that The vehicle operation data includes time, speed, mileage, throttle, brake, slope, steering wheel angle, and gear position; the environmental data includes temperature, humidity, and altitude; the characteristic values ​​of the user's driving segment include average speed, maximum speed, total time, mileage, idle time percentage, coasting time percentage, deceleration time percentage, average acceleration, maximum acceleration, average deceleration, maximum deceleration, average temperature, average humidity, and average altitude.

5. The method according to claim 4, characterized in that The step of performing cluster analysis on the user travel segment set according to the feature values ​​of the user travel segments to determine a plurality of basic user travel segments also includes: A K-means algorithm is used to perform cluster analysis on the user travel segment set based on the eigenvalues, and an elbow rule is used to determine the corresponding cluster number and user travel segment cluster of the user travel segment set; The user travel segment with the closest centroid value to each user travel segment cluster is taken as the basic user travel segment.

6. The method according to claim 5, characterized in that The operating condition coefficient is any one or more combinations of vehicle speed, slope, braking, throttle, turning angle, ambient temperature, altitude and temperature.

7. The method according to claim 6, characterized in that The operating condition coefficient also includes any one or more combinations of a temperature time curve, a turning angle time curve, a throttle time curve, a braking time curve, a slope time curve and a vehicle speed time curve.

8. A computer-readable storage medium, characterized in that: It includes a computer program, which, when run by a processor, executes the method for constructing a user driving condition test case as described in any one of claims 1 to 7.

Images