Apparatus and method for detecting liquid on a surface, vehicle and mobile device

Abstract

An apparatus for detecting liquid on a surface is provided. The apparatus includes interface circuitry configured to receive image data representing a multispectral image of the surface. Additionally, the apparatus includes processing circuitry configured to determine, based on the multispectral image, for each pixel of the multispectral image three respective reflec- tance values of the surface at three different wavelengths. The processing circuitry is further configured to combine for each pixel of the multispectral image the three respective reflec- tance values to a respective combined value. In addition, the processing circuitry is config- ured to perform for each pixel of the multispectral image a normalization process on the respective combined value to obtain a respective normalized value. The processing circuitry is further configured to determine information about the presence of liquid on the surface based on the normalized values.

Description

[0001] APPARATUS AND METHOD FOR DETECTING LIQUID ON A SURFACE, VEHICLE AND MOBILE DEVICE

[0002] Field

[0003] The present disclosure relates to the detection of liquid on surfaces. In particular, examples of the present disclosure relate to an apparatus and a method for detecting liquid on a surface, a vehicle and a mobile device.

[0004] Background

[0005] Surfaces such as, e.g., streets or floors in buildings may be covered with liquids such as, e.g., water or oil. The presence of liquid changes various characteristics of the surface. For example, the presence of liquid on a street influences the grip of a vehicle tire to the street surface and may lead to accidents or dangerous situations. In order to avoid such accidents or dangerous situations, it would be preferred to be able to detect or measure the presence of liquids on surfaces such as streets, floors, or tire treads.

[0006] Hence, there may be a demand for detection of liquid on surfaces.

[0007] Summary

[0008] This demand is met by an apparatus for detecting liquid on a surface, a method for detecting liquid on a surface, a vehicle, a mobile device, a non-transitory machine-readable medium and a program in accordance with the independent claims. Advantageous embodiments are addressed by the dependent claims.

[0009] According to a first aspect, the present disclosure provides an apparatus for detecting liquid on a surface. The apparatus comprises interface circuitry configured to receive image data representing a multi spectral image of the surface. Additionally, the apparatus comprises processing circuitry configured to determine, based on the multispectral image, for each pixel of the multispectral image three respective reflectance values of the surface at three different wavelengths. The processing circuitry is further configured to combine for each pixel of the multispectral image the three respective reflectance values to a respective combined value. In addition, the processing circuitry is configured to perform for each pixel of the multispectral image a normalization process on the respective combined value to obtain a respective normalized value. The processing circuitry is further configured to determine information about the presence of liquid on the surface based on the normalized values.

[0010] According to a second aspect, the present disclosure provides a vehicle comprising one or more tire and an apparatus for detecting liquid on a surface according to the first aspect. The surface is a tread of one of the one or more tire. The vehicle additionally comprises control circuitry configured to control operation of the vehicle based on the information about the presence of liquid on the surface.

[0011] According to a third aspect, the present disclosure provides a mobile device comprising an apparatus for detecting liquid on a surface according to the first aspect, and one or more processor configured to control a display of the mobile device to output a graphical representation derived from the information about the presence of liquid on the surface.

[0012] According to a fourth aspect, the present disclosure provides method for detecting liquid on a surface. The method comprises receiving image data representing a multispectral image of the surface. In addition, the method comprises determining, based on the multispectral image, for each pixel of the multispectral image three respective reflectance values of the surface at three different wavelengths. Further, the method comprises combining for each pixel of the multispectral image the three respective reflectance values to a respective combined value. The method additionally comprises performing for each pixel of the multispectral image a normalization process on the respective combined value to obtain a respective normalized value. Further, the method comprises determining information about the presence of liquid on the surface based on the normalized values.

[0013] According to a fifth aspect, the present disclosure provides a non-transitory machine- readable medium having stored thereon a program having a program code for performing the method according to the fourth aspect, when the program is executed on a processor or a programmable hardware. According to a sixth aspect, the present disclosure provides a program having a program code for performing the method according to the fourth aspect, when the program is executed on a processor or a programmable hardware.

[0014] Brief description of the Figures

[0015] Some examples of apparatuses and / or methods will be described in the following by way of example only, and with reference to the accompanying figures, in which

[0016] Fig. 1 illustrates an example of an apparatus for detecting liquid on a surface;

[0017] Fig. 2 illustrates an example of a tire;

[0018] Fig. 3 illustrates exemplary spectral courses of the reflectance under different conditions for a first tire;

[0019] Fig. 4 illustrates exemplary spectral courses of the reflectance under different conditions for a second tire;

[0020] Fig. 5 illustrates a diagram of exemplary combined values for different tires under different conditions;

[0021] Fig. 6 illustrates another example of an apparatus for detecting liquid on a surface;

[0022] Fig. 7 illustrates an example of a vehicle;

[0023] Fig. 8 illustrates an example of a multispectral camera;

[0024] Fig. 9 illustrates an example of a mobile device; and

[0025] Fig. 10 illustrates a flowchart of an example of a method for detecting liquid on a surface.

[0026] Detailed Description Some examples are now described in more detail with reference to the enclosed figures. However, other possible examples are not limited to the features of these embodiments described in detail. Other examples may include modifications of the features as well as equivalents and alternatives to the features. Furthermore, the terminology used herein to describe certain examples should not be restrictive of further possible examples.

[0027] Throughout the description of the figures same or similar reference numerals refer to same or similar elements and / or features, which may be identical or implemented in a modified form while providing the same or a similar function. The thickness of lines, layers and / or areas in the figures may also be exaggerated for clarification.

[0028] When two elements A and B are combined using an “or”, this is to be understood as disclosing all possible combinations, i.e. only A, only B as well as A and B, unless expressly defined otherwise in the individual case. As an alternative wording for the same combinations, "at least one of A and B" or "A and / or B" may be used. This applies equivalently to combinations of more than two elements.

[0029] If a singular form, such as “a”, “an” and “the” is used and the use of only a single element is not defined as mandatory either explicitly or implicitly, further examples may also use several elements to implement the same function. If a function is described below as implemented using multiple elements, further examples may implement the same function using a single element or a single processing entity. It is further understood that the terms "include", "including", "comprise" and / or "comprising", when used, describe the presence of the specified features, integers, steps, operations, processes, elements, components and / or a group thereof, but do not exclude the presence or addition of one or more other features, integers, steps, operations, processes, elements, components and / or a group thereof.

[0030] Fig- 1 illustrates an exemplary apparatus 100 for detecting liquid 135 on a surface 130. The surface 130 may be any plane or curved face of any body or thing. For example, the surface 130 may be the surface of a road, the surface of a floor inside or outside a building, the surface of a furniture such as a table, or a tread of a tire. However, it is to be noted that the surface 130 is not limited to the foregoing examples. The liquid 135 may be any fluid that has no independent shape but has a definite volume and does not expand indefinitely and that is only slightly compressible. For example, the liquid 135 may be water, motor oil, lube oil or gasoline. However, it is to be noted that the liquid 135 is not limited to the foregoing examples.

[0031] The apparatus 100 comprises at least interface circuitry 110 and processing circuitry 120. The processing circuitry 120 is coupled to the interface circuitry 110. The interface circuitry 110 is configured to receive image data 101 representing (indicating, encoded with) a multi- spectral image of the surface 130. The multispectral image is a collection of a plurality of image layers (i.e. N > 2 image layers) of the same scene (i.e. the surface 130), each of them acquired at a particular wavelength or wavelength range (band). In other words, the multispectral image depicts the same scene (i.e. the surface 130) at a plurality of different wavelengths or wavelength ranges (i.e. N > 2 different wavelengths or wavelength ranges). The multispectral image comprises a plurality of pixels (i.e. M > 2 pixels) representing (indicating, encoded with) the spectral data. The image data 101 may be received from various sources as will be explained later.

[0032] The processing circuitry 120 is configured to receive and process the image data 101. For example, the processing circuitry 120 may be a single dedicated processor, a single shared processor, or a plurality of individual processors, some of which or all of which may be shared, a digital signal processor (DSP) hardware, an application specific integrated circuit (ASIC), a neuromorphic processor or a field programmable gate array (FPGA). The processing circuitry 120 may optionally be coupled to, e.g., read only memory (ROM) for storing software, random access memory (RAM) and / or non-volatile memory. Optionally, the apparatus 100 may comprise further circuitry.

[0033] In particular, the processing circuitry 120 is configured to determine, based on the multispectral image, for each pixel of the multispectral image three respective reflectance values of the surface at (for) three different wavelengths. In other words, for each pixel i of the multispectral image, the processing circuitry 120 is configured to determine three reflectance values v^2>iand v^3>iat the three different wavelengths A2and A3. The respective reflectance values for the pixels of the multispectral image may be determined according to conventional methods known to the skilled person. For example, the pixel values of the individual pixels of the multispectral image may be converted to reflectance values according to the following mathematical expression:vAj,i ~ Gj ■ DN + Bj (1) with Gj denoting a specific gain value for the wavelength Ay or a wavelength range containing the wavelength y, DN denoting the pixel value of the respective pixel (e.g. a n-bit digital number) and Bj denoting a specific bias for the wavelength y or a wavelength range containing the wavelength y. However, it is to be noted the present disclosure is not limited to the above example. Any other conventional method for converting pixel values to reflectance values may be used as well.

[0034] The processing circuitry 120 is further configured to combine for each pixel of the multi- spectral image the three respective reflectance values to a respective combined value. In other words, the processing circuitry 120 is configured to determine a respective combined value Vcomb,iv^lii, v^2ii, v^3ii') for each pixel i of the multispectral image. The three respective reflectance values for each pixel i of the multispectral image may be combined in various ways. For example, one or more of the three respective reflectance values for each pixel i of the multispectral image may be multiplied with each other, divided by each other, added to each other or subtracted from each other. Furthermore, various mathematical operations may be performed one or more of the three respective reflectance values for each pixel i of the multispectral image in the course of combining the three respective reflectance values for each pixel i of the multispectral image to the respective combined value Vcomb i. For example, the processing circuitry 120 may be configured to combine for each pixel i of the multispectral image the three respective reflectance values V1y, V2y and V3y to the respective combined value Vcomb ias follows:

[0035] However, it is to be noted that the present disclosure is not limited thereto. The three respective reflectance values v^2iiand v^3iifor the respective pixel of the multispectral image may, in general, be combined in any suitable manner.

[0036] In addition, the processing circuitry 120 is configured to perform for each pixel of the multispectral image a normalization process on the respective combined value to obtain a respective normalized value. The normalization process is a process that changes the range of pos- sible values for the respective combined value such that the obtained normalized values are within a target value range.

[0037] The processing circuitry 120 is further configured to determine information 102 about the presence of liquid on the surface 130 based on the normalized values. The information 102 about the presence of liquid 135 on the surface 130 may be manifold. For example, the information about the presence of liquid 135 on the surface 130 may indicate whether or not liquid 135 is present on the surface 130 (i.e. indicate that the liquid 135 is present or that no liquid is present on the surface). Alternatively or additionally, the information 102 about the presence of liquid 135 on the surface 130 may indicate characteristics of the liquid 135 such as a type of the liquid. For example, the information 102 about the presence of liquid 135 on the surface 130 may indicate that the liquid 135 is water, motor oil or lube oil. However, it is to be noted that the present disclosure is not limited thereto. Other types of liquid may be indicated as well by the information 102. The processing circuitry 120 may output and / or internally process the information 102 about the presence of liquid on the surface 130.

[0038] The presence of liquid 135 on the surface 130 changes the spectral reflectance of the surface 130. By determining the reflectance at three different wavelengths from the multi spectral image and combining the respective reflectance values, various information regarding the presence of the liquid 135 on the surface 135 may be obtained. Furthermore, by normalizing the combined values, the proposed detection of liquid 135 on the surface 130 may be made (substantially) independent from structure of the surface 130. The obtained information 102 about the presence of liquid on the surface 130 may be used for various use cases as will be explained later.

[0039] A more detailed example of the proposed detection of liquid on a surface will be given in the following with reference to Figs. 2 to 5. In this example, the surface is a tread of a tire.

[0040] Fig- 2 illustrates an exemplary tire 200. Various fluids may be present on a tread 210 of the tire 200. This is exemplary illustrated in Fig. 2. A first (measurement) region 220 of the tread 210 is not covered with liquid. A second (measurement) region 230 of the tread 210 is covered with a first liquid. A third (measurement) region 240 of the tread 210 is covered with a second liquid. The first liquid may, e.g., be water, whereas the second liquid may, e.g., be a motor oil, a lube oil or gasoline. The spectral reflectance of the tire’s tread 210 is changing if a liquid is located on its surface. This is exemplarily illustrated in Fig. 3 and Fig. 4.

[0041] Fig- 3 illustrates a diagram 300 of the spectral course (curve) of the reflectance under different conditions for a first tire. The abscissa of the diagram 300 denotes the analyzed wavelength in units of nm. The ordinate of the diagram denotes the reflectance of the tire’s tread in units of % for the respective wavelength.

[0042] Five spectral courses 310, ..., 350 are illustrated in the diagram 300. The spectral course 310 represents a situation in which no liquid is present on the tire’s tread (i.e. the tire is not covered with liquid). The spectral course 320 represents a situation in which water is present on the tire’s tread. The spectral course 330 represents a situation in which a first lube oil is present on the tire’s tread. The spectral course 340 represents a situation in which a second lube oil, which is different from the first lube oil, is present on the tire’s tread. The spectral course 350 represents a situation in which a motor oil is present on the tire’s tread.

[0043] As can be seen from the spectral courses 310, ..., 350, the spectral reflectance of the tire’s tread changes significantly if liquid is present on the tread, and also varies between different liquids.

[0044] Fig- 4 illustrates an equivalent diagram 400 for a second tire, which is different from the first tire. The abscissa of the diagram 400 denotes the analyzed wavelength in units of nm. The ordinate of the diagram denotes the reflectance of the tire’s tread in units of % for the respective wavelength.

[0045] Four spectral courses 410, ..., 440 are illustrated in the diagram 400. The spectral course 410 represents a situation in which no liquid is present on the tire’s tread (i.e. the tire is not covered with liquid). The spectral course 420 represents a situation in which water is present on the tire’s tread. The spectral course 430 represents a situation in which the second lube oil is present on the tire’s tread. The spectral course 440 represents a situation in which the motor oil is present on the tire’s tread. Similar to the spectral courses illustrated in Fig. 3, also the spectral courses 410, 440 indicate that the spectral reflectance of the tire’s tread changes significantly if liquid is present on the tread, and also varies between different liquids. The proposed detection of liquid on a surface is based on these effects.

[0046] As indicated in Fig. 3 and Fig. 4, three different wavelengths of the reflectance spectrum are used for detecting liquid on the tire’s tread according to the present disclosure. In the example of Fig. 3 and Fig. 4, the wavelengths are v^lti= 456 nm, v^2ii= 420 nm and v^3>i= 350 nm. However, it is to be noted that the present disclosure is not limited thereto. In case the surface is a tread of a tire, a first one of the three different wavelengths may be between 450 nm and 460 nm, a second one of the three different wavelengths may be between 415 nm and 425 nm, and a third one of the three different wavelengths may be between 345 nm and 355 nm. In general, independent from the type of the surface, at least one of the three different wavelengths may be 380 nm or less, and at least one of the three different wavelengths may be in the range of 380 nm to 750 nm. In other words, at least one of the three different wavelengths may be in the ultraviolet spectrum, and at least one of the three different wavelengths may be in the visible spectrum.

[0047] The reflectance values at the three wavelengths = 456 nm, v^2>i= 420 nm and = 350 nm are determined pixelwise from a respective multispectral image of the respective tire’s tread as described above in connection with Fig. 1 for an arbitrary surface. The three reflectance values per pixel are combined to obtain a respective combined value for each pixel of the respective multispectral image.

[0048] The following Table 1 shows the respective combined value Vcomb ifor a pixel i of the respective multispectral image for five different tires in different situations. In one situation, no liquid is present on the respective tire (i.e. the tire is dry). In another situation, water is present on the respective tire. In still another situation, the first lube oil is present on the respective tire. In a further situation, the second lube oil is present on the respective tire. In a still further situation, motor oil is present on the respective tire. The respective combined values for the pixel i of the respective multispectral image are obtained according to the above mathematical expression (2).

[0049] Table 1

[0050] A few systematics are evident from Table 1 for all tires. The combined values obtained when water is present on the treads are always lower than the combined values obtained when no liquid is present on the treads (i.e. when the tires are dry). The combined values obtained when no liquid is present on the treads are always between the combined values obtained when water is present on the treads and the combined values obtained when oil (lube oil or motor oil) is present on the treads. The combined values obtained when oil (lube oil or motor oil) is present on the treads are always higher than the combined values obtained when no liquid is present on the treads and the combined values obtained when water is present.

[0051] This is graphically illustrated in Fig. 5. Fig. 5 illustrates a diagram 500. The abscissa of the diagram 500 denotes the tires listed in Table 1. The ordinate of the diagram denotes the combined values. The combined values obtained when water is present on the treads are in the first area 510, the combined values obtained when no liquid is present on the treads are in the second area 520 and the combined values obtained when oil is present on the treads are in the third area 530. The second area 520 is arranged between the first area 510 and the third area 530.

[0052] As is evident from Table 1 and Fig. 5, the combined values for the same condition (e.g. dry, water, oil) are in the same range, but slightly different between the five different tires. Therefore, the combined values cannot simply be classified. In order to enable classification, the combined values are subject to a normalization to obtain a respective normalized value. For example, the combined values for each tire may be divided by a respective refer- ence value for the respective tire. In the following Table 2, an example is given in which the respective combined value when no liquid is present on the tread is used as respective reference value for the respective tire:

[0053] Table 2

[0054] As can be seen from Table 2, the normalized values of the different tires are smaller than 1.00 when water is present on the treads, and larger than 1.00 when oil is present on the treads. Accordingly, it may be determined by thresholding a) whether liquid is present on the respective tread and / or b) which type of liquid is present on the respective tread.

[0055] Referring back to the more general example of Fig. 1, when performing the normalization process on the respective combined value, the processing circuitry 120 may be configured to divide the respective combined value for each pixel of the multispectral image by a reference value. Similar to what is described above for the more specific tire example of Fig. 5 in detail, the reference value may be an expected value for the combined value in case no liquid is present on the surface. The reference value may, e.g., be the combined value determined in a reference measurement for which the condition of the surface is known, i.e., for which it is known that no liquid is present on the surface. The reference value may be stored in memory circuitry of the apparatus 100 or a memory circuitry accessible by the processing circuitry 120.

[0056] Since the normalized values are within specific value ranges in case no liquid is present on the surface 130 and also in case certain types of liquids are present on the surface 130, the normalized values allow classification. For example, for determining the information 102 about the presence of liquid on the surface 130, the processing circuitry 120 may be configured to determine a number of pixels of the multispectral image for which the respective normalized value is outside a first value range. Further, the processing circuitry 120 may be configured to determine, as the information about the presence of liquid, that liquid is present on the surface if the number of pixels for which the respective normalized value is outside the first value range is above a first threshold value.

[0057] Referring back to the tire example of Table 2, the normalized value is 1.00 in case that no liquid is present on the respective tire tread. Accordingly, the first value range may, e.g., be from 0.95 to 1.05, from 0.98 to 1.02 or from 0.97 to 1.10. However, it is to be noted that the foregoing values are merely exemplary value ranges. Other suitable value ranges may be used as well. Further, it is to be noted that other value ranges may be used for surfaces other than tire treads.

[0058] The number of pixels for which the respective normalized value is outside the first value range indicates to which extent the surface 130 is covered with liquid. Further, the number of pixels depends to a certain extent on the size of the multispectral image. Therefore, the first threshold value may depend (may be selected based) on the size of the multispectral image. For example, if the total number of pixels Ptotaiof the multispectral image is:

[0059] Ptotai = Px ' Py (3) with Pxdenoting the width of the multispectral image in pixels and Pydenoting the height of the multispectral image in pixels, the first threshold value Pthresh,i may be selected as:

[0060] Pthresh,! ' Ptotai (4) with 0 < A < 1. For example, A may be at least 0.25, 0.5, 0.75 or 0.9 according to some examples.

[0061] Analogously, the processing circuitry 120 may be configured to determine, as the information about the presence of liquid, that no liquid is present on the surface 130 if the number of pixels for which the respective normalized value is outside the first value range is below a second threshold value. Like the first threshold value, the second threshold value may depend (may be selected based) on the size of the multispectral image. For example, the second threshold value Pthresh,2 may be selected as:

[0062] Pthresh,2 ' Pfotal (^) with 0 < B . For example, B may be at maximum 0.01, 0.02, 0.05, 0.10 or 0.15 according to some examples.

[0063] The processing circuitry 120 may be further configured to control the interface circuitry 110 to output an alert message if it is determined that liquid is present on the surface 130. The alert message indicates that liquid is present on the surface 130. The alert message may, e.g., be output to a user device (equipment, terminal) for informing user about the presence of liquid on the surface such that the user may take appropriate actions. Similarly, the alert message may, e.g., be output to control circuitry of a device comprising or being related to the surface 130 such that the control circuitry may take appropriate actions. A detailed example will be given further below.

[0064] As described above, the normalized values not only allow to determine whether or not liquid is present on the surface 130, the normalized values further allow to determine the type of the liquid. This will be explained in the following.

[0065] For example, for determining the information 102 about the presence of liquid on the surface 130, the processing circuitry 120 may be configured to determine a first number of pixels of the multispectral image for which the respective normalized value is within a second value range. Further, the processing circuitry 120 may be configured to determine, as the information 102 about the presence of liquid, that liquid of a first type is present on the surface 130 if the first number of pixels is above a third threshold value.

[0066] Referring back to the tire example of Table 2, the normalized value is smaller than 1.00 in case that water is present on the respective tire tread. Accordingly, the second value range may, e.g., be from 0.00 to 0.90, from 0.00 to 0.95 or from 0.00 to 0.97. However, it is to be noted that the foregoing values are merely exemplary value ranges. Other suitable value ranges may be used as well. Further, it is to be noted that other value ranges may be used for surfaces other than tire treads.

[0067] The number of pixels for which the respective normalized value is within the second value range indicates to which extent the surface 130 is covered with the first liquid. Like the first threshold value and the second threshold value, the third threshold value may depend (may be selected based) on the size of the multispectral image. For example, the third threshold value Pthresh,3 may be selected as:

[0068] Pthresh,3 ' Pfotal (6) with 0 < C < 1. For example, C may be at least 0.25, 0.5, 0.75 or 0.9 according to some examples.

[0069] The processing circuitry 120 may be further configured to control the interface circuitry 110 to output a first alert message if it is determined that liquid of the first type is present on the surface 130. The first alert message indicates that liquid of the first type is present on the surface 130. For example, the first alert message may indicate that water is present on the surface 130 (e.g. a tread of a tire). The first alert message may, e.g., be output to a user device (equipment, terminal) for informing user about the presence of liquid of the first type on the surface such that the user may take appropriate actions. Similarly, the first alert message may, e.g., be output to control circuitry of a device comprising or being related to the surface 130 such that the control circuitry may take appropriate actions.

[0070] Analogously, for determining the information 102 about the presence of liquid on the surface 130, the processing circuitry 120 may be configured to determine a second number of pixels of the multispectral image for which the respective normalized value is within a third value range. The second value range is different from the first value range. According to examples, the first value range and the second value range do not overlap. Furthermore, the first value range and the second value range may be separated by at least one value inbetween the first value range and the second value range. Further, the processing circuitry 120 may be configured to determine, as the information 102 about the presence of liquid, that liquid of a second type is present on the surface if the second number of pixels is above a fourth threshold value. Referring back to the tire example of Table 2, the normalized value is larger than 1.00 in case that oil is present on the respective tire tread. Accordingly, the third value range may, e.g., be from 1.02 to 20.00, from 1.10 to 50.00 or from 1.20 to infinity. However, it is to be noted that the foregoing values are merely exemplary value ranges. Other suitable value ranges may be used as well. Further, it is to be noted that other value ranges may be used for surfaces other than tire treads.

[0071] The number of pixels for which the respective normalized value is within the third value range indicates to which extent the surface 130 is covered with the second liquid. Like the first to third threshold values, the fourth threshold value may depend (may be selected based) on the size of the multispectral image. For example, the fourth threshold value Pthresh,4 may be selected as:

[0072] Pfhresh,4- D ' Pfotal ( ) with 0 < D < 1. For example, D may be at least 0.25, 0.5, 0.75 or 0.9 according to some examples.

[0073] The processing circuitry 120 may be further configured to control the interface circuitry 110 to output a second alert message if it is determined that liquid of the second type is present on the surface 130. The second alert message indicates that liquid of the second type is present on the surface 130. For example, the second alert message may indicate that oil is present on the surface 130 (e.g. a tread of a tire). The second alert message may, e.g., be output to a user device (equipment, terminal) for informing user about the presence of liquid of the second type on the surface such that the user may take appropriate actions. Similarly, the second alert message may, e.g., be output to control circuitry of a device comprising or being related to the surface 130 such that the control circuitry may take appropriate actions.

[0074] According to examples, the processing circuitry 120 may be further configured to control the interface circuitry 110 to output a third alert message if a sum of the first number of pixels and the second number of pixels is above a fifth threshold value. The third alert message indicates that liquid of the first type and liquid of the second type is present on the surface 130. The sum of the first number of pixels and the second number of pixels indicates to which extent the surface 130 is covered with the first liquid and the second liquid. Like the first to fourth threshold values, the fifth threshold value may depend (may be selected based) on the size of the multispectral image. For example, the fifth threshold value Pthresh,5 may be selected as:

[0075] Pthresh,5 E ' Pfotal (8) with 0 < E < 1. For example, D may be at least 0.25, 0.5, 0.75 or 0.9 according to some examples.

[0076] For example, the third alert message may indicate that water and oil are present on the surface 130 (e.g. a tread of a tire). The third alert message may, e.g., be output to a user device (equipment, terminal) for informing user about the presence of liquid of the first type and liquid of the second type on the surface such that the user may take appropriate actions. Similarly, the third alert message may, e.g., be output to control circuitry of a device comprising or being related to the surface 130 such that the control circuitry may take appropriate actions.

[0077] The image data 101 representing a multispectral image of the surface may be received by the interface circuitry 110 from circuitry or devices external to the apparatus 100 such as an external camera system. In other examples, such as the example illustrated in Fig. 1, the apparatus 100 may optionally comprise means for capturing the multispectral image.

[0078] The apparatus 100 illustrated in Fig. 1 may optionally further comprise an illumination element (illumination device, light source) 140 configured to illuminate the surface 130. This is exemplarily illustrated in Fig. 1, in which the illumination element 140 emits light 141 toward the surface 130.

[0079] The light 141 may be of any suitable wavelength. For example, the illumination element 140 may be configured to illuminate the surface 130 with light exhibiting the three different wavelengths that are analyzed in the multispectral image. The illumination element 140 may, e.g., be configured to illuminate the surface 130 at least with ultraviolet light (wave- length from approx. 100 nm to approx. 380 nm) and visible light (wavelength from approx. 380 nm to approx. 780 nm). In some examples, the illumination element 140 may be configured to additionally illuminate the surface 130 with infrared light (wavelength from approx. 780 nm to approx. 1 mm).

[0080] According to examples, the wavelength of the light 141 may be adjustable in order to examine a wavelength dependency of the surface characteristics of the surface 130. In addition to a known (e.g. predefined or adjusted) spectral distribution, the light 141 emitted by the illumination element 140 may exhibit a known (e.g. predefined or adjusted) opening angle and a known (e.g. predefined or adjusted) brightness. The illumination element 140 may illuminate a (e.g. wide and) contiguous area of the surface 130 or one or more individual section (e.g. one or more point) of the surface 130.

[0081] The illumination element 140 may comprise various components such as one or more light emitter, electronic circuitry and optics (e.g. one or more lenses for adjusting a shape or the opening angle of the light 141, one or more monochromator for adjusting the wavelength of the light 141, one or more optical filter for adjusting the wavelength of the light 141, etc.). The one or more light emitter may, e.g., be Light-Emitting Diodes (LEDs) and / or one laser diodes (e.g. one or more Vertical -Cavity Surface-Emitting Lasers, VCSELs). According to examples, a plurality of light emitters emitting light at different wavelengths may be provided and selectively activated to adjust the wavelength of the light 141 emitted by the illumination element 140. However, it is to be noted that the illumination element 140 may alternatively comprise more, less or other components than those exemplary components described above.

[0082] The apparatus 100 illustrated in Fig. 1 may optionally further comprise a (e.g. single) multi- spectral image sensor 150 configured to capture the surface 130 and generate the image data 101. The multispectral image sensor 150 is configured to measure light 151 of different wavelengths or wavelength ranges (i.e. T > 2 different wavelengths or wavelength ranges) simultaneously in order to generate the multispectral image. The multispectral image sensor 150 is sensitive to at least ultraviolet light and visible light.

[0083] In alternative examples, the apparatus 100 may comprise a plurality of image sensors rather than a single multispectral image sensor 150. The plurality of image sensors are configured to capture the surface 130 and jointly generate the image data 101. Each of the plurality of image sensors is sensitive to light of a different wavelength or wavelength range. At least one of the plurality of image sensors is sensitive to ultraviolet light, and at least one of the plurality of image sensors is sensitive to visible light.

[0084] Further optionally, the processing circuitry 120 may be configured to perform image enhancement processing on the spectral image. For examples, the processing circuitry 120 may be further configured to perform noise filtering on either a) the multispectral image prior to the determination of the three respective reflectance values or b) the combined values prior to performing the normalization process.

[0085] Fig- 6 illustrates another exemplary apparatus 600 for detecting liquid on a surface that uses noise filtering and further image enhancement. The apparatus 600 comprises a multispectral camera 610 configured to capture a surface such as a tread of a tire, and to generate the image data. As described above, the image data represent a multispectral image of the surface. As described above, three wavelengths in the spectral domain are enough for detecting liquids on a surface such as a tread of a tire. By using a multispectral camera with three channels an extension from a point-wise measurement to aerial measurement is possible and thus parts of tire or a whole tire can be analyzed. After capturing with the multispectral camera 610, the respective image or images are first processed by some camera internal functions such as, e.g., demosaicking, color filter corrections or illumination estimation / correction.

[0086] Processing circuitry 620 receives the image data via interface circuitry from the multispectral camera 610. The processing circuitry 620 applies the above mathematical expression (2) on a pixel level to the multispectral image. Per pixel of the multispectral image respective intensity (reflectance) values for the three wavelengths (e.g. 350nm, 420nm and 456nm) are available. Afterwards a normalization takes place by, e.g., dividing simply through a previously determined value for a dry surface (e.g. from a calibration or from a database). After normalization, a noise reduction is applied, followed by, e.g., thresholding for a simple classification. Pixels with a value smaller a threshold value (e.g. 1.00 as in the above examples or including a margin) are classified, e.g., as wet and pixels larger than the threshold value are, e.g., classified as oily. All other pixels are classified as dry. Then, the number of pixels per class (dry, wet, oily) are calculated and used as input for the subsequent evaluation process. A vehicle 700 using the proposed liquid detection is illustrated in Fig. 7. In general, a vehicle can be understood as a device (system) comprising one or more engine (e.g. one or more of a combustion engine, an electric engine, and a turbine) and one or more tire. The one or more tire may be driven by one or more engine. The vehicle 700 can therefore be both a passenger vehicle and a commercial vehicle. For example, the vehicle 700 may be a car (automobile), a truck, a motorcycle, a tractor or an airplane.

[0087] In the example of Fig. 7, four tires 710, 720, 730 and 740 are illustrated. However, it is to be noted that the present disclosure is not limited thereto. In general, the vehicle 700 may comprise one or more tire.

[0088] The vehicle 700 additionally comprises an apparatus 750 for detecting liquid on a surface according to the present disclosure. In the example of Fig. 7, the apparatus 750 is used to determine presence of liquids such as a water or oil on the respective tread of the tires 710, 720, 730 and 740. In other words, the apparatus 750 determines for each of the tires 710, 720, 730 and 740 information about the presence of liquid on the tread of the respective tire.

[0089] The image data representing the respective multi spectral image of the respective tread are provided by a respective multispectral camera 715, 725, 735 and 735 for each of the tires 710, 720, 730 and 740.

[0090] Fig- 8 illustrates the multispectral camera 715 with more details. The other multispectral cameras may be identical to the multispectral camera 715. The multispectral camera 715 comprises an illumination element 716 configured to illuminate the tread 711 of the tire 710. Further, the multispectral camera 715 comprises a multispectral image sensor 717 configured to capture the tread 711 of the tire 710 and generate the image data for the tire 710. In case a liquid 770 such as water and / or oil is present on the tread 711 of the tire 710, the spectral reflectance of the tread 711 changes, which is noticeable in the captured spectral image of the tread 711.

[0091] Liquid on the treads of the 710, 720, 730 and 740 and, hence, the street negatively affects the grip of the respective tire to the street surface and may lead to accidents or dangerous situations. By means of the apparatus 750, the presence of liquid on the tires may be monitored automatically and in real-time.

[0092] The vehicle 700 additionally comprises control circuitry 760 configured to control operation of the vehicle 700 based on the information about the presence of liquid on the surface. In other words, the control circuitry 760 receives from the apparatus 750 information about the presence of liquid such as water or oil on the tread of the respective tire 710, 720, 730 and 740. Based on this information, the control circuitry 760 controls operation of the vehicle 700. Accordingly, accidents or dangerous situations may be avoided. Alternatively or additionally, the control circuitry 760 may be configured to control operation of the vehicle 700 based on alert messages output by the apparatus 750 (such as the alert messages described above).

[0093] For example, the control circuitry 760 may be configured to control the vehicle 700 to (automatically) output a visual, optical and / or haptic warning to a user of the vehicle 700 (e.g. the driver) in case it is determined by the apparatus 750 that liquid is present on one or more of the tires 710, 720, 730 and 740 so that the user can operate the vehicle 700 accordingly (e.g. by reducing the speed). That is, the vehicle 700 not only allows a contactless, real-time monitoring of whether liquid is present on one or more of the tires 710, 720, 730 and 740, it may further allow to automatically alert or inform the user of the vehicle in case liquid is on the tire. In other examples, the control circuitry 760 may be configured to control the vehicle 700 to reduce speed in case it is determined by the apparatus 750 that liquid is present on one or more of the tires 710, 720, 730 and 740. The reduction of speed may, e.g., be performed irrespective of whether the vehicle 700 drives autonomously or whether the user controls the vehicle 700. Accordingly, accidents or dangerous situations may be avoided.

[0094] In the example of Fig. 7, the apparatus 750 and the control circuitry 760 are illustrated as being part of a single control unit of the vehicle 700. For example, the apparatus 750 and the control circuitry 760 and may part of an Advanced Driver Assistance System (ADAS) of the vehicle 700. However, the present disclosure is not limited thereto. In other examples, the apparatus 750 and the control circuitry 760 may be provided as separate elements (units). For example, a respective apparatus 750 may be integrated in each of the 710, 720, 730 and 740. Another example using the proposed liquid detection is illustrated in Fig. 9. Fig. 9 illustrates a mobile device 900. In Fig. 9, the mobile device 900 is depicted as a mobile phone (smartphone). However, it is to be noted that the present disclosure is not limited thereto. In other examples, the mobile device 900 may be a tablet-computer, a laptop or a wearable such as a smartwatch.

[0095] The mobile device 900 comprises an apparatus 910 for detecting liquid on a surface according to the present disclosure. The apparatus 910 outputs information about the presence of liquid on the surface as described above. The image data representing the respective multi- spectral image of the surface are provided by a multispectral image sensor 930 of the mobile device 900. An illumination element 940 of the mobile device is configured to illuminate the surface.

[0096] The mobile device 900 additionally comprises one or more processor 920 (e.g. one or more application processor) configured to control a display 950 of the mobile device 900 to output a graphical representation derived from the information about the presence of liquid on the surface. For example, in case a user opens a dedicated application by pressing a corresponding symbol (icon) 960 on the display 950, the one or more processor 920 may control the display 950 to output a graphical representation derived from the information about the presence of liquid on the surface. The graphical representation may, e.g., comprise symbols, graphical elements, textual elements etc. for illustrating, based on the information about the presence of liquid on the surface, whether liquid is present on the surface and / or which type of liquid is present on the surface. Alternatively or additionally, the one or more processor 920 may be configured to derive the graphical representation at least in part from alert messages output by the apparatus 910 (such as the alert messages described above).

[0097] As illustrated in the lower part of Fig. 9, the mobile device 900 may, e.g., be used for manual liquid detection on a tire 970.

[0098] The mobile device 900 may comprise further elements such as, e.g., one or more antenna, one or more radio frequency transmitter, one or more radio frequency receiver, a modem, a baseband processor, memory, a connectivity module, a Near Field Communication (NFC) controller, an audio driver, a camera driver, sensors, removable memory, a power management integrated circuit or a smart battery. The wireless communication circuits of the mobile device 900 may be configured to operate according to one of the 3rd Generation Partnership Project (3GPP)-standardized mobile communication networks or systems. The mobile or wireless communication system may correspond to, for example, a 5thGeneration New Radio (5G NR), a Long-Term Evolution (LTE), an LTE-Advanced (LTE-A), High Speed Packet Access (HSPA), a Universal Mobile Telecommunication System (UMTS) or a UMTS Terrestrial Radio Access Network (UTRAN), an evolved-UTRAN (e-UTRAN), a Global System for Mobile communication (GSM), an Enhanced Data rates for GSM Evolution (EDGE) network, or a GSMZEDGE Radio Access Network (GERAN). Alternatively or additionally, the wireless communication circuits may be configured to operate according to mobile communication networks with different standards, for example, a Worldwide Inter-operability for Microwave Access (WIMAX) network IEEE 802.16 or Wireless Local Area Network (WLAN) IEEE 802.11, generally an Orthogonal Frequency Division Multiple Access (OFDMA) network, a Time Division Multiple Access (TDMA) network, a Code Division Multiple Access (CDMA) network, a Wideband-CDMA (WCDMA) network, a Frequency Division Multiple Access (FDMA) network, a Spatial Division Multiple Access (SDMA) network, etc.

[0099] For further highlighting the liquid detection described above, Fig. 10 illustrates a flowchart of a method 1000 for detecting liquid on a surface. The method 1000 comprises receiving 1002 image data representing a multispectral image of the surface. In addition, the method 1000 comprises determining 1004, based on the multispectral image, for each pixel of the multispectral image three respective reflectance values of the surface at three different wavelengths. Further, the method 1000 comprises combining 1006 for each pixel of the multispectral image the three respective reflectance values to a respective combined value. The method 1000 additionally comprises performing 1008 for each pixel of the multispectral image a normalization process on the respective combined value to obtain a respective normalized value. Further, the method 1000 comprises determining 1010 information about the presence of liquid on the surface based on the normalized values.

[0100] The method 1000 may allow to the presence of liquid on the surface. For example, the method 1000 may allow to whether or not liquid is present on the surface and / or to determine characteristics of the liquid such as a type of the liquid. More details and aspects of the method 1000 are explained in connection with the proposed technique or one or more examples described above (e.g. Fig. 1 to Fig. 9). The method 1000 may comprise one or more additional optional features corresponding to one or more aspects of the proposed technique or one or more examples described above.

[0101] Among other types of surface, the proposed technique may allow monitoring tires for liquids. If any abnormal liquids are detected on tires, an alert may inform the driver according to the present disclosure. A device (apparatus) for performing proposed technique may be a device built in any vehicle with tires or as well a mobile device for manual measuring. The device may optionally include technology like multispectral sensors.

[0102] The following examples pertain to further embodiments:

[0103] (1) An apparatus for detecting liquid on a surface, the apparatus comprising: interface circuitry configured to receive image data representing a multispectral image of the surface; and processing circuitry configured to: determine, based on the multispectral image, for each pixel of the multispectral image three respective reflectance values of the surface at three different wavelengths; combine for each pixel of the multispectral image the three respective reflectance values to a respective combined value; perform for each pixel of the multispectral image a normalization process on the respective combined value to obtain a respective normalized value; and determine information about the presence of liquid on the surface based on the normalized values.

[0104] (2) The apparatus of (1), wherein the processing circuitry is configured to combine for each pixel of the multispectral image the three respective reflectance values to the respective combined value as follows: with Vcomb idenoting the combined value for the i-th pixel of the multispectral image, and and v^3iidenoting the three reflectance values for the i-th pixel of the multispectral image. (3) The apparatus of (1) or (2), wherein, for determining the information about the presence of liquid on the surface, the processing circuitry is configured to: determine a number of pixels of the multispectral image for which the respective normalized value is outside a first value range; and determine, as the information about the presence of liquid, that liquid is present on the surface if the number of pixels for which the respective normalized value is outside the first value range is above a first threshold value.

[0105] (4) The apparatus of (1) or (2), wherein, for determining the information about the presence of liquid on the surface, the processing circuitry is configured to: determine a first number of pixels of the multispectral image for which the respective normalized value is within a first value range; and determine, as the information about the presence of liquid, that liquid of a first type is present on the surface if the first number of pixels is above a first threshold value.

[0106] (5) The apparatus of (4), wherein the processing circuitry is further configured to control the interface circuitry to output a first alert message if it is determined that liquid of the first type is present on the surface.

[0107] (6) The apparatus of (4) or (5), wherein, for determining the information about the presence of liquid on the surface, the processing circuitry is configured to: determine a second number of pixels of the multispectral image for which the respective normalized value is within a second value range, the second value range being different from the first value range; and determine, as the information about the presence of liquid, that liquid of a second type is present on the surface if the second number of pixels is above a second threshold value.

[0108] (7) The apparatus of (6), wherein the processing circuitry is further configured to control the interface circuitry to output a second alert message if it is determined that liquid of the second type is present on the surface. (8) The apparatus of (6) or (7), wherein the processing circuitry is further configured to control the interface circuitry to output a third alert message if a sum of the first number of pixels and the second number of pixels is above a third threshold value.

[0109] (9) The apparatus of any one of (1) to (8), wherein, when performing the normalization process on the respective combined value, the processing circuitry is configured to divide the respective combined value by a reference value.

[0110] (10) The apparatus of (9), wherein the reference value is an expected value for the combined value in case no liquid is present on the surface.

[0111] (11) The apparatus of any one of (1) to (10), wherein the processing circuitry is further configured to perform noise filtering on either the multispectral image prior to the determination of the three respective reflectance values or the combined values prior to performing the normalization process.

[0112] (12) The apparatus of any one of (1) to (11), wherein at least one of the three different wavelengths is 380 nm or less, and wherein at least one of the three different wavelengths is in the range of 380 nm to 750 nm.

[0113] (13) The apparatus of any one of (1) to (12), wherein the surface is a tread of a tire, and wherein a first one of the three different wavelengths is between 450 nm and 460 nm, wherein a second one of the three different wavelengths is between 415 nm and 425 nm, and wherein a third one of the three different wavelengths is between 345 nm and 355 nm.

[0114] (14) The apparatus of any one of (1) to (13), wherein the apparatus further comprises: an illumination element configured to illuminate the surface; and a single multispectral image sensor configured to capture the surface and generate the image data, wherein the multispectral image sensor is sensitive to at least ultraviolet light and visible light.

[0115] (15) The apparatus of any one of (1) to (13), wherein the apparatus further comprises: an illumination element configured to illuminate the surface; and a plurality of image sensors configured to capture the surface and jointly generate the image data, wherein each of the plurality of image sensors is sensitive to light of a different wavelength range, wherein at least one of the plurality of image sensors is sensitive to ultraviolet light, and wherein at least one of the plurality of image sensors is sensitive to visible light.

[0116] (16) A vehicle, comprising: one or more tire; an apparatus according to any one of (1) to (15), wherein the surface is a tread of one of the one or more tire; and control circuitry configured to control operation of the vehicle based on the information about the presence of liquid on the surface.

[0117] (17) A mobile device, comprising: an apparatus according to any one of (1) to (15); and one or more processor configured to control a display of the mobile device to output a graphical representation derived from the information about the presence of liquid on the surface.

[0118] (18) A method for detecting liquid on a surface, the method comprising: receiving image data representing a multi spectral image of the surface; and determining, based on the multispectral image, for each pixel of the multispectral image three respective reflectance values of the surface at three different wavelengths; combining for each pixel of the multispectral image the three respective reflectance values to a respective combined value; performing for each pixel of the multispectral image a normalization process on the respective combined value to obtain a respective normalized value; and determining information about the presence of liquid on the surface based on the normalized values.

[0119] (19) A non-transitory machine-readable medium having stored thereon a program having a program code for performing the method according to (18), when the program is executed on a processor or a programmable hardware. (20) A program having a program code for performing the method according to (18), when the program is executed on a processor or a programmable hardware.

[0120] The aspects and features described in relation to a particular one of the previous examples may also be combined with one or more of the further examples to replace an identical or similar feature of that further example or to additionally introduce the features into the further example.

[0121] Examples may further be or relate to a (computer) program including a program code to execute one or more of the above methods when the program is executed on a computer, processor or other programmable hardware component. Thus, steps, operations or processes of different ones of the methods described above may also be executed by programmed computers, processors or other programmable hardware components. Examples may also cover program storage devices, such as digital data storage media, which are machine-, processor- or computer-readable and encode and / or contain machine-executable, processorexecutable or computer-executable programs and instructions. Program storage devices may include or be digital storage devices, magnetic storage media such as magnetic disks and magnetic tapes, hard disk drives, or optically readable digital data storage media, for example. Other examples may also include computers, processors, control units, (field) programmable logic arrays ((F)PLAs), (F)PGA), graphics processor units (GPU), ASICs, integrated circuits (ICs) or system-on-a-chip (SoCs) systems programmed to execute the steps of the methods described above.

[0122] It is further understood that the disclosure of several steps, processes, operations or functions disclosed in the description or claims shall not be construed to imply that these operations are necessarily dependent on the order described, unless explicitly stated in the individual case or necessary for technical reasons. Therefore, the previous description does not limit the execution of several steps or functions to a certain order. Furthermore, in further examples, a single step, function, process or operation may include and / or be broken up into several sub-steps, -functions, -processes or -operations.

[0123] If some aspects have been described in relation to a device or system, these aspects should also be understood as a description of the corresponding method. For example, a block, device or functional aspect of the device or system may correspond to a feature, such as a method step, of the corresponding method. Accordingly, aspects described in relation to a method shall also be understood as a description of a corresponding block, a corresponding element, a property or a functional feature of a corresponding device or a corresponding system.

[0124] The following claims are hereby incorporated in the detailed description, wherein each claim may stand on its own as a separate example. It should also be noted that although in the claims a dependent claim refers to a particular combination with one or more other claims, other examples may also include a combination of the dependent claim with the sub- ject matter of any other dependent or independent claim. Such combinations are hereby explicitly proposed, unless it is stated in the individual case that a particular combination is not intended. Furthermore, features of a claim should also be included for any other independent claim, even if that claim is not directly defined as dependent on that other independent claim.

Claims

ClaimsWhat is claimed is:

1. An apparatus for detecting liquid on a surface, the apparatus comprising: interface circuitry configured to receive image data representing a multispectral image of the surface; and processing circuitry configured to: determine, based on the multispectral image, for each pixel of the multispectral image three respective reflectance values of the surface at three different wavelengths; combine for each pixel of the multispectral image the three respective reflectance values to a respective combined value; perform for each pixel of the multispectral image a normalization process on the respective combined value to obtain a respective normalized value; and determine information about the presence of liquid on the surface based on the normalized values.

2. The apparatus of claim 1, wherein the processing circuitry is configured to combine for each pixel of the multispectral image the three respective reflectance values to the respective combined value as follows:with Vcomb idenoting the combined value for the i-th pixel of the multispectral image, andand v^3iidenoting the three reflectance values for the i-th pixel of the multispectral image.

3. The apparatus of claim 1, wherein, for determining the information about the presence of liquid on the surface, the processing circuitry is configured to: determine a number of pixels of the multispectral image for which the respective normalized value is outside a first value range; anddetermine, as the information about the presence of liquid, that liquid is present on the surface if the number of pixels for which the respective normalized value is outside the first value range is above a first threshold value.

4. The apparatus of claim 1, wherein, for determining the information about the presence of liquid on the surface, the processing circuitry is configured to: determine a first number of pixels of the multispectral image for which the respective normalized value is within a first value range; and determine, as the information about the presence of liquid, that liquid of a first type is present on the surface if the first number of pixels is above a first threshold value.

5. The apparatus of claim 4, wherein the processing circuitry is further configured to control the interface circuitry to output a first alert message if it is determined that liquid of the first type is present on the surface.

6. The apparatus of claim 4, wherein, for determining the information about the presence of liquid on the surface, the processing circuitry is configured to: determine a second number of pixels of the multispectral image for which the respective normalized value is within a second value range, the second value range being different from the first value range; and determine, as the information about the presence of liquid, that liquid of a second type is present on the surface if the second number of pixels is above a second threshold value.

7. The apparatus of claim 6, wherein the processing circuitry is further configured to control the interface circuitry to output a second alert message if it is determined that liquid of the second type is present on the surface.

8. The apparatus of claim 6, wherein the processing circuitry is further configured to control the interface circuitry to output a third alert message if a sum of the first number of pixels and the second number of pixels is above a third threshold value.

9. The apparatus of claim 1, wherein, when performing the normalization process on the respective combined value, the processing circuitry is configured to divide the respective combined value by a reference value.

10. The apparatus of claim 9, wherein the reference value is an expected value for the combined value in case no liquid is present on the surface.

11. The apparatus of claim 1, wherein the processing circuitry is further configured to perform noise filtering on either the multispectral image prior to the determination of the three respective reflectance values or the combined values prior to performing the normalization process.

12. The apparatus of claim 1, wherein at least one of the three different wavelengths is 380 nm or less, and wherein at least one of the three different wavelengths is in the range of 380 nm to 750 nm.

13. The apparatus of claim 1, wherein the surface is a tread of a tire, and wherein a first one of the three different wavelengths is between 450 nm and 460 nm, wherein a second one of the three different wavelengths is between 415 nm and 425 nm, and wherein a third one of the three different wavelengths is between 345 nm and 355 nm.

14. The apparatus of claim 1, wherein the apparatus further comprises: an illumination element configured to illuminate the surface; and a single multispectral image sensor configured to capture the surface and generate the image data, wherein the multispectral image sensor is sensitive to at least ultraviolet light and visible light.

15. The apparatus of claim 1, wherein the apparatus further comprises: an illumination element configured to illuminate the surface; and a plurality of image sensors configured to capture the surface and jointly generate the image data, wherein each of the plurality of image sensors is sensitive to light of a different wavelength range, wherein at least one of the plurality of image sensors is sensitive to ultraviolet light, and wherein at least one of the plurality of image sensors is sensitive to visible light.

16. A vehicle, comprising: one or more tire;an apparatus according to claim 1, wherein the surface is a tread of one of the one or more tire; and control circuitry configured to control operation of the vehicle based on the information about the presence of liquid on the surface.

17. A mobile device, comprising: an apparatus according to claim 1 ; and one or more processor configured to control a display of the mobile device to output a graphical representation derived from the information about the presence of liquid on the surface.

18. A method for detecting liquid on a surface, the method comprising: receiving image data representing a multispectral image of the surface; and determining, based on the multispectral image, for each pixel of the multispectral image three respective reflectance values of the surface at three different wavelengths; combining for each pixel of the multispectral image the three respective reflectance values to a respective combined value; performing for each pixel of the multispectral image a normalization process on the respective combined value to obtain a respective normalized value; and determining information about the presence of liquid on the surface based on the normalized values.

19. A non-transitory machine-readable medium having stored thereon a program having a program code for performing the method according to claim 18, when the program is executed on a processor or a programmable hardware.

20. A program having a program code for performing the method according to claim 18, when the program is executed on a processor or a programmable hardware.

Images