TW201713920A - Pavement detecting method, pavement detecting device and pavement detecting system - Google Patents

Abstract

A pavement detecting method, a device and a system thereof are provided. The method includes: emitting a linear-shaped laser toward a pavement to be measured so a projection of the linear-shaped laser is projected on the pavement; obtaining a image of the pavement; determining whether the projection of the linear-shaped laser is a straight line via the image; if the projection of the linear-shaped laser is a straight line, determining that the pavement is a flat surface; if the projection of the linear-shaped laser is not a straight line, determining that the pavement is not a flat surface. Accordingly, the pavement detecting method, the device and the system thereof effectively detect whether the pavement is flat.

Description

Road surface inspection method, road surface inspection device and road surface inspection system

The present invention relates to a detection method, apparatus and system, and more particularly to a road surface detection method, apparatus and system.

Whether the road is level or not is not only related to the feeling of comfort of passers-by, but also related to traffic safety. The commonly used road flatness detection method is to use a straight gauge to manually calculate the height difference between each point in the inspection unit and the straight gauge, and calculate the standard deviation of the height difference to obtain the flatness information. However, such a method can only be applied to the inspection of the road level when the road is newly paved, and it is not possible to provide the safety information of the road ahead in time when the passerby is walking or driving.

On the other hand, it is not accurate enough to judge whether the road is flat or not by using the eyes or feelings of passers-by. In more detail, the passers-by may not be able to misjudge the level of the road, which may lead to accidents. Therefore, how to use the existing technology to instantly detect whether the road is flat or not to provide real-time information for passers-by is a subject worthy of study.

Based on the above, the present invention provides a road surface detecting method, apparatus and system. Under the combination of a smart electronic device with an optical camera lens and a laser light source, the optical camera lens can obtain a clear image and is low. Good road test results are obtained under computational complexity and calculation.

The invention provides a road surface detecting method suitable for detecting a road surface to be tested. This method includes the following steps. A linear laser is emitted on the road surface to be tested, so that the road surface to be tested includes a projection of a linear laser. Obtain an image of the road surface to be tested. Whether the projection of the linear laser is a straight line is determined by the acquired image. If the projection of the linear laser is a straight line, it is determined that the road surface to be tested is a flat road surface. If the projection of the linear laser is not a straight line, it is determined that the road surface to be tested is a non-flat road surface.

The invention provides a road surface detecting device suitable for detecting a road surface to be tested. The device includes a laser emitter, an image capture device, and a processor. The laser emitter is used to emit a linear laser on the road surface to be tested, so that the road surface to be tested includes a projection of the linear laser. The image capturing device is used to obtain an image of the road surface to be tested. The processor uses the image capturing device to acquire an image, and determines whether the projection of the linear laser is a straight line by the acquired image. If the processor determines that the projection of the linear laser is a straight line, the processor determines that the road surface to be tested is a flat road surface. If the processor determines that the projection of the linear laser beam is not a straight line, the processor determines that the road surface to be tested is a non-flat road surface.

The invention provides a road surface detecting system suitable for detecting a road surface to be tested. The system comprises a laser emitter and an electronic device, wherein the electronic device comprises an image capturing device and a processor. The laser emitter is used to emit a linear laser on the road surface to be tested, so that the road surface to be tested includes a projection of the linear laser. The image capturing device is used to obtain an image of the road surface to be tested. The processor is configured to acquire an image from the image capturing device, and determine, by the acquired image, whether the projection of the linear laser is a straight line. If the processor determines that the projection of the linear laser is a straight line, the processor determines that the road surface to be tested is a flat road surface. If the processor determines that the projection of the linear laser is not a straight line, the processor determines that the road surface to be tested is a non-flat road surface.

Based on the above, the above-described road surface detecting method, apparatus, and system can instantly determine whether the road surface to be tested is flat in a large number of environments, and has good detection performance.

The above described features and advantages of the invention will be apparent from the following description.

FIG. 1A is a block diagram of a road surface detecting apparatus according to an exemplary embodiment of the invention. FIG. 1B is a block diagram of a processor according to an exemplary embodiment of the invention. FIG. 1C is a block diagram of a road surface detecting system according to an exemplary embodiment of the invention.

Referring to FIG. 1A, the road surface detecting device 100 includes a laser emitter 110, an image capturing device 130, and a processor 150. In the present exemplary embodiment, the laser emitter 110 is used to emit a linear laser, and the laser emitter 110 uses a red laser light source having a wavelength of 650 nanometers (nm), which is combined with a lenticular lens to generate a linear lightning. Shot, but the invention is not limited thereto. In another embodiment of the invention, the laser emitter 110 may also use a 532 nanometer (nm) green laser source with a specially constructed plane mirror to produce a linear laser. The invention does not limit the laser source of the laser emitter 110 and the means by which it produces a linear laser. In the present exemplary embodiment, the laser emitter 110 is coupled to the processor 150 and the processor 150 controls the operation of the laser emitter 110. It is noted that in another embodiment of the invention, the laser emitter 110 operates or is operated independently of the control of the processor 150.

In the exemplary embodiment, the image capturing device 130 is coupled to the processor 150 for capturing images. The image capturing device 130 includes, for example, a Charge Coupled Device (CCD) or a Complementary Metal-Oxide Semiconductor Image Sensor (CMOS Image Sensor).

In the present exemplary embodiment, the processor 150 is coupled to the laser emitter 110 and the image capturing device 130 for controlling the operation of the laser emitter 110 and the image capturing device 130 and obtaining the image capturing device 130 from the image capturing device 130. The image it captured. The processor 150 is, for example, a micro-controller, an embedded controller, a central processing unit (CPU) or the like, and the present invention is not limited thereto. Referring to FIG. 1B , in the exemplary embodiment, the processor 150 further includes a color filter module 151 , an image processing module 153 , and a determination module 155 .

In another exemplary embodiment of the present invention, the road surface detecting device 100 may further include a warning device 170. The alert device 170 is coupled to the processor 150 and is controlled by the processor 150 for its operation. Specifically, the alert device 170 is implemented, for example, by a device such as a light source or a horn. When the alert device 170 is a light source, the processor 150 can utilize the alert device 170 to emit flashing light as an alert. When the alert device 170 is a horn, the processor 150 can use the alert device 170 to sound a warning tone as an alert.

It should be noted that the road surface detecting device 100 illustrated in FIG. 1A can be implemented in an existing electronic device, such as a smart phone, a tablet computer, a notebook computer, or the like. In other words, the laser emitter 110, the image capturing device 130, the processor 150, and the alerting device 170 are all built into the electronic device, but the invention is not limited thereto. In another exemplary embodiment of the present invention, the present invention may also be as shown in FIG. 1C, and the electronic device 10 including the image capturing device 130 and the processor 150 is coupled with a laser independent of the electronic device 10. The transmitter 110 is implemented in the form of a road surface inspection system 1000. Specifically, in the present exemplary embodiment, the laser emitter 110 of the road surface detecting system 1000 is, for example, a laser pen, and the electronic device 10 is, for example, a smart phone or a tablet computer.

2 is a flow chart of a road surface detecting method according to an exemplary embodiment of the invention. The road surface detecting method of the present exemplary embodiment is applied to the road surface detecting device 100 and the road surface detecting system 1000 proposed in FIGS. 1A, 1B, and 1C. Referring to FIG. 1A, FIG. 1B, FIG. 1C and FIG. 2, in step S201, the laser emitter 110 emits a linear laser on the road surface to be tested, so that the road surface to be tested includes a projection of a linear laser. Next, in step S203, the image capturing device 130 obtains an image of the road surface to be tested.

FIG. 3 is a schematic diagram of an image of a road surface to be tested according to an exemplary embodiment of the invention. Referring to FIG. 3, the laser emitter 110 emits a linear laser beam to the road surface to be tested, so that the linear laser beam forms a projection on the road surface to be tested. Next, the processor 150 controls the image capturing device 130 to capture the image 300 of the road surface to be tested. The image 300 includes at least a projection 330 of the road surface 310 to be tested and a linear laser. In various embodiments, the image 300 may further include any object or environment that appears in the image capturing range of the image capturing device 130, such as a guardrail, a tree, or a sky. The processor 150 acquires the image 300 from the image capturing device 130 to perform a subsequent process of road surface detection.

Referring back to FIG. 1A, FIG. 1B, FIG. 1C and FIG. 2, in step S205, the processor 150 determines whether the projection of the linear laser is a straight line by the image acquired by the image capturing device. FIG. 4 is a flow chart for determining whether a projection of a linear laser is a straight line by an image according to an exemplary embodiment of the invention. As shown in FIG. 4, in step S2051, the color filter module 151 of the processor 150 filters the image as a target image according to the set wavelength retention range. Next, in S2053, the image processing module 153 of the processor 150 performs pre-image processing on the target image to obtain a binary image including the area to be tested. It should be noted that in the exemplary embodiment, the pre-image processing includes binarization processing and edge detection. Finally, in step S2055, the determination module 155 of the processor 150 determines whether the projection 330 of the linear laser is a straight line by the obtained binary image.

FIG. 5 is a schematic diagram of a target image according to an exemplary embodiment of the invention. Referring to FIG. 5, in the present exemplary embodiment, the laser light source of the laser emitter 110 is, for example, a 650 nanometer (nm) red laser light source, so the processor 150 receives the image capturing device 130. After the image 300, the color filter module 151 sets a wavelength-limited range of fault-tolerant buffer centering on 650 nanometers (nm), for example, 645 nm to 655 nm, and filters the image 300 using the wavelength retention range. The color in the image 300 corresponding to the wavelength retention range mentioned above is filtered out. In other words, the color filter module 151 is used in the present exemplary embodiment to filter out other components in the image 300 to preserve the projection 330 of the linear laser. In the present exemplary embodiment, after filtering by the color filter module 151, for example, a target image 500 of a projection 330 containing only a linear laser is obtained. In the present exemplary embodiment, if the color of the pixel of the target image 500 does not correspond to the wavelength retention range, the color filter module 151 of the processor 150 sets the pixel to be black, but the present invention is not limited thereto. In another embodiment of the present invention, the color filter module 151 can also set the aforementioned pixels to be white or other colors.

As shown in FIG. 4, after acquiring the target image 500, the image processing module 153 then performs pre-image processing on the target image 500. FIG. 6A is a schematic diagram of a grayscale image according to an exemplary embodiment of the invention. FIG. 6B is a schematic diagram of a binarized image according to an exemplary embodiment of the invention. FIG. 6C is a schematic diagram of a binary image according to an exemplary embodiment of the invention.

First, referring to FIG. 6A, after the color filter module 151 filters the image 300 into the target image 500, the image processing module 153 converts the target image 500 into a grayscale image 600. Specifically, in the exemplary embodiment, the image processing module 153 converts the red, green, and blue (RGB) values of each pixel in the target image 500 into grayscale values using a conversion formula. The conversion formula is, for example, 0.2999*r+0.587*g+0.114*b. It is worth noting that r, g, and b correspond to the R value, the G value, and the B value of the RGB color code, respectively. In the different embodiments of the present invention, the image processing module 153 may also convert the target image 500 into a grayscale image by using other conversion formulas, and the present invention does not limit the manner of grayscale conversion.

Referring to FIG. 6B, in the exemplary embodiment, after the image processing module 153 converts the target image 500 into the grayscale image 600, the grayscale image 600 is then binarized into a binarized image 602. . Specifically, the image processing module 153 sets a grayscale threshold value for binarizing each pixel in the grayscale image 600. The method for setting the grayscale threshold is, for example, a bimodal method. The present invention is not limited thereto, the P-tile method, the Iterative Method, or the Otsu Method. In the exemplary embodiment, the image processing module 153 sets the grayscale image in the grayscale image 600 to a grayscale maximum value, such as white, and grayscale in the grayscale image 600. A pixel whose value is smaller than the set grayscale threshold value is set to a grayscale minimum value, for example, black, thereby obtaining a binarized image 602.

Referring to FIG. 6C, after the image processing module 153 converts the grayscale image 600 into the binarized image 602, the binarized image 602 is then edge-detected to reduce the amount of data and find the binarized image. The boundary of the projection 330 corresponding to the linear laser in 602. In an embodiment of the present invention, the image processing module 153 uses the Canny Edge Detector for edge detection, for example, but the present invention does not limit the edge detection method. In various embodiments, it is also possible to perform edge detection using a Roberts Cross Operator, a Prewitt Operator, or other similar operand. In the present exemplary embodiment, after the binarized image 602 passes the edge detection, the binary image 604 is obtained.

As shown in FIG. 6C, in the present exemplary embodiment, the binary image 604 obtained by the pre-image processing includes the area to be tested A corresponding to the projection 330 of the linear laser and the edge B to be tested. Next, the determination module 155 determines whether the projection 330 of the linear laser is a straight line by the binary image 604.

In an exemplary embodiment of the present invention, the determination module 155 uses Hough Line Transformation on the binary image 604 to determine whether the projection 330 of the linear laser is a straight line. FIG. 7 is a flow chart showing whether a projection of a linear laser is a straight line by a binary image according to an exemplary embodiment of the present invention. FIG. 8 is a schematic diagram of a Hough line conversion detecting method according to an exemplary embodiment of the present invention. Referring to FIG. 7 and FIG. 8, first, in step S701, the determination module 155 performs a Hough line conversion on the binary image 604 to detect the binary image 604. Next, in step S703, the determining module 155 determines whether the area A to be tested in the binary image 604 conforms to a single line segment or a plurality of line segments. If the result of the determination is a single line segment, then in step S705, the determination module 155 determines that the projection 330 of the linear laser is a straight line. If the result of the determination is a plurality of line segments, then in step S707, the determination module 155 determines that the projection 330 of the linear laser is not a straight line.

For example, FIG. 8(a) is the same as the binary image 604, which includes the area A1 to be tested, and the determination module 155 can detect the image of FIG. 8(a) by using the Hough line conversion method. Image of 8(b). That is to say, after the detection by the Hough line conversion method in Fig. 8(a), it can be judged that two parallel lines including L1 and L2 are included. However, since a single line segment having a width includes two parallel lines after edge detection, it can be determined that the area to be tested A1 in FIG. 8(a) is a standard conforming to a single line segment, so the determination module 155 determines the area A1 to be tested. The projection of the corresponding linear laser is a straight line. It should be noted that, in the present exemplary embodiment, since the light source used is a linear laser, the area to be tested A1 has a width, but the width thereof is not enough for the detection of the Hough line to determine the area A1 to be tested. The ends of the points are straight lines.

In another embodiment, if the binary image is partially recessed in the area to be tested A2 as shown in FIG. 8(c), the determination module 155 detects the image using the Hough line conversion method. After c), an image as shown in Fig. 8(d) can be obtained. That is to say, after the detection by the Hough line conversion method in FIG. 8(c), it can be judged that L1 and L2 and L3 and L4 are parallel lines. According to the above analysis, the two sets of parallel lines correspond to the two line segments having the width, so it can be determined that the area to be tested A2 in Fig. 8(c) is in conformity with a plurality of line segments, and does not conform to the criterion of a single line segment. At this time, the determination module 155 determines that the projection of the linear laser corresponding to the area A2 to be tested is not a straight line.

In the foregoing plurality of exemplary embodiments, the road surface detecting method, apparatus, and system employ Hough line conversion to determine whether the projection 230 of the linear laser is a straight line, but the present invention is not limited thereto. FIG. 9 is a flow chart for determining whether a projection of a linear laser is a straight line by a binary image according to another exemplary embodiment of the present invention. FIG. 10 is a schematic diagram of an equal difference detection method according to another exemplary embodiment of the present invention. Referring to FIG. 9 and FIG. 10, in another exemplary embodiment of the present invention, the determination module 155 determines whether the projection 330 of the linear laser is a straight line by the binary image 604 using the isometric detection method.

First, in step S901, the determination module 155 provides a reference line in the binary image 604. The reference line is, for example, a line parallel to one of the edges of the binary image 404. Next, in step S903, in the area A to be measured corresponding to the projection 330 of the linear laser, the determination module 155 obtains a plurality of points to be measured equidistantly along the direction in which the edge line extends. In step S905, the determination module 155 further obtains a plurality of deviation distances from the plurality of points to be measured to the reference line, and then in step S907, the determination module 155 determines whether the plurality of deviation distances are equivariant. If the plurality of deviation distances have the same difference, then in step S909, the determination module 155 determines that the projection of the linear laser is a straight line. On the other hand, if the plurality of deviation distances do not have the same difference, then in step S911, the determination module 155 determines that the projection of the linear laser is not a straight line.

For example, referring to FIG. 10, the determining module 155 coordinates the pixels in the binary image 604, and the size of the binary image 604 is, for example, 360*240 pixels, and the coordinates of the bottom left pixel of the binary image 604 are Yes (0,0), and the pixel in the top right corner will be (360,240). The reference line BL is parallel to the x-axis, so n points x1 to xn are equally spaced along the x-axis, and n pieces of points P1 to Pn whose x-coordinates are x1 to xn, respectively, are taken in the area A. Next, a plurality of deviation distances D1 to Dn from P1 to Pn to the reference line BL are obtained, and the unit of D1 to Dn is, for example, a pixel. And then it is determined whether D1~Dn is an arithmetic progression. If the deviation distances D1~Dn are equal difference series, the determination module 155 should determine that the projection 330 of the linear laser is a straight line; if the deviation distances D1~Dn are not equal In the sequence, the decision module 155 should determine that the projection 330 of the linear laser is not a straight line. The above n can be taken as an arbitrary natural number, and the larger the value of n, the higher the accuracy or resolution of the judgment. It is worth mentioning that, as shown in Fig. 6, since the projection 330 of the linear laser also has a certain width, when determining whether D1~Dn is an arithmetic progression, an error tolerance value should be set as the judgment D1. Whether ~Dn is an error that can be tolerated when it is an arithmetic progression.

Referring back to FIG. 1A, FIG. 1B, FIG. 1C and FIG. 2, the processor 150 determines whether the projection 330 of the linear laser is a straight line by the color filter module 151, the image processing module 153, and the determination module 155. If the projection 330 of the linear laser is a straight line, then in step S207, the processor 150 determines that the road surface to be tested is a flat road surface. On the other hand, if the projection of the linear laser is not a straight line, then in step S209, the processor 150 determines that the road surface to be tested is a non-flat road surface. When it is determined that the road surface to be tested is a non-flat road surface, the processor 150 further controls the warning device 170 to issue an alert.

It should be noted that, in an exemplary embodiment of the present invention, the color filter module 151, the image processing module 153, and the determination module 155 in the processor 150 are, for example, a plurality of software programs executed by the processor 150. However, in other embodiments, the color filter module 151, the image processing module 153, and the determination module 155 can also be implemented by multiple sets of physical circuits.

In summary, in the road surface detecting method, device and system proposed by the present invention, since the laser light is used as the indicating light source, even when the light is insufficient at night, the user can be assisted in judging the pit on the road, and further It ensures the safety of traffic. In addition, the present invention utilizes image processing technology to extract the portion of the image corresponding to the laser light, and only needs to analyze the line of the laser light to determine the flatness of the road, which is detected by other techniques. The method of tunneling on the road, the invention can achieve good detection effect in the lower image processing complexity and calculation amount under the combination of laser light.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention, and any one of ordinary skill in the art can make some changes and refinements without departing from the spirit and scope of the present invention. The scope of the invention is defined by the scope of the appended claims.

100‧‧‧Pavement detection device
10‧‧‧Electronic devices
110‧‧‧Laser transmitter
130‧‧‧Image capture device
150‧‧‧ processor
151‧‧‧Color Filter Module
153‧‧‧Image Processing Module
155‧‧‧Judgement module
170‧‧‧ Warning device
1000‧‧‧Pavement Inspection System
Steps of S201, S203, S205, S207, S209‧‧‧ Pavement Detection Method
S2051, S2053, S2055‧‧‧Steps for judging whether the projection of the linear laser is a straight line by image
300‧‧‧ images
310‧‧‧Surface image to be tested
330‧‧‧Projection of linear laser
500‧‧‧ Target image
600‧‧‧ grayscale imagery
602‧‧‧ binarized image
604‧‧‧ binary image
S701, S703, S705, S707‧‧‧ Steps for judging whether the projection of the linear laser is a straight line by the binary image using the Hough line conversion detection method
S901, S903, S905, S907, S909, S911‧‧‧ Steps for judging whether the projection of the linear laser is a straight line by using the heterodyne detection method for the binary image
A, A1, A2‧‧‧ area to be tested
B‧‧‧ edge to be tested
L1, L2‧‧‧ parallel lines
L3, L4‧‧‧ parallel lines
BL‧‧‧ baseline
P1~Pn‧‧‧ points to be tested
D1~Dn‧‧‧ deviation distance
X1~xn‧‧‧x axis coordinates

FIG. 1A is a block diagram of a road surface detecting apparatus according to an exemplary embodiment of the invention. FIG. 1B is a block diagram of a processor according to an exemplary embodiment of the invention. FIG. 1C is a block diagram of a road surface detecting system according to an exemplary embodiment of the invention. 2 is a flow chart of a road surface detecting method according to an exemplary embodiment of the invention. FIG. 3 is a schematic diagram of an image of a road surface to be tested according to an exemplary embodiment of the invention. FIG. 4 is a flow chart for determining whether a projection of a linear laser is a straight line by an image according to an exemplary embodiment of the invention. FIG. 5 is a schematic diagram of a target image according to an exemplary embodiment of the invention. FIG. 6A is a schematic diagram of a grayscale image according to an exemplary embodiment of the invention. FIG. 6B is a schematic diagram of a binarized image according to an exemplary embodiment of the invention. FIG. 6C is a schematic diagram of a binary image according to an exemplary embodiment of the invention. FIG. 7 is a flow chart showing whether a projection of a linear laser is a straight line by a binary image according to an exemplary embodiment of the present invention. FIG. 8 is a schematic diagram of a Hough line conversion detecting method according to an exemplary embodiment of the present invention. FIG. 9 is a flow chart for determining whether a projection of a linear laser is a straight line by a binary image according to another exemplary embodiment of the present invention. FIG. 10 is a schematic diagram of an equal difference detection method according to another exemplary embodiment of the present invention.

Steps of S201, S203, S205, S207, S209‧‧‧ Pavement Detection Method

Claims (10)

A road surface detecting method is suitable for detecting a road surface to be tested, the road surface detecting method comprising: transmitting a linear laser to a road surface to be tested, so that the road surface to be tested includes a projection of the linear laser; An image of the road surface; determining, by the image, whether the projection of the linear laser is a straight line; if the projection of the linear laser is a straight line, determining that the road surface to be tested is a flat road surface; and if the linear lightning The projection of the shot is not a straight line, and it is determined that the road surface to be tested is a non-flat road surface. The road surface detecting method of claim 1, wherein the road surface detecting method further comprises: issuing a warning signal if the surface to be tested is determined to be the non-flat surface. The method for detecting a road surface according to claim 1, wherein the step of determining whether the projection of the linear laser is a straight line by the image comprises: filtering the image into a target image according to a wavelength retention range, wherein The wavelength retention range includes the wavelength of the linear laser, and the wavelength of the linear laser includes 650 nm; performing a pre-image processing on the target image to obtain a binary image, wherein the pre-image processing includes a Binarization processing and an edge detection, the binary image includes a region to be tested, and the region to be tested corresponds to the projection of the linear laser; and the binary image is determined by the binary image Whether the projection is a straight line. The method for detecting a road surface according to claim 3, wherein the step of determining whether the projection of the linear laser is a straight line by the binary image comprises: using a Hough line conversion to detect the binary image The binary image; if the area to be tested in the binary image conforms to a single line segment, determining that the projection of the linear laser is a straight line; and if the area to be tested in the binary image conforms to multiple line segments And determining that the projection of the linear laser is not a straight line. The method for detecting a road surface according to claim 3, wherein the step of determining whether the projection of the linear laser is a straight line by the binary image comprises: providing a reference line, wherein the reference line is parallel to the image One side line; on the area to be tested, along the extending direction of the edge line, obtain a plurality of points to be measured equidistantly; obtain a plurality of deviation distances between the points to be measured and the reference line; determine the deviations Whether the distances are equidistant; if the deviation distances are equidistant, the projection of the linear laser is judged to be a straight line; and if the deviation distances are not equidistant, the linear laser is judged This projection is not a straight line. A road surface detecting device is adapted to detect a road surface to be tested, the road surface detecting device comprising: a laser emitter that emits a linear laser beam on the road surface to be tested, so that the road surface to be tested includes one of the linear laser beams An image capturing device that acquires an image of the road surface to be tested; and a processor coupled to the image capturing device for acquiring the image, and determining the projection of the linear laser by the image Whether it is a straight line, wherein if the processor determines that the projection of the linear laser is a straight line, the processor determines that the road surface to be tested is a flat road surface, wherein if the processor determines that the projection of the linear laser is not If it is a straight line, the processor determines that the road surface to be tested is a non-flat road surface. The road surface detecting device of claim 6, wherein the road surface detecting device further comprises: a warning device coupled to the processor, wherein if the processor determines that the road surface to be tested is an uneven road surface, The warning device is activated to send a warning signal, and the processor comprises: a color filtering module, filtering the image into a target image according to a wavelength retention range, wherein the wavelength retention range includes the wavelength of the linear laser, The wavelength of the linear laser includes 650 nm; an image processing module performs a pre-image processing on the target image to obtain a binary image, wherein the pre-image processing includes a binarization process and an edge detection The binary image includes a region to be tested, and the region to be tested corresponds to the projection of the linear laser; and a determining module determines, by the binary image, whether the projection of the linear laser is straight line. The road surface detecting device of claim 7, wherein the determining module uses a Hough line conversion for the binary image to detect the binary image, if the area to be tested in the binary image corresponds to a single line segment, the determining module determines that the projection of the linear laser is a straight line, and if the area to be tested in the binary image conforms to a plurality of line segments, determining that the projection of the linear laser is not a straight line . The road surface detecting device of claim 7, wherein the determining module provides a reference line, and the reference line is parallel to one side of the image, and the determining module is on the area to be tested along the edge line. An extending direction, obtaining a plurality of points to be measured equidistantly, and obtaining a plurality of deviation distances between the points to be measured and the reference line, the determining module determining whether the deviation distances have an equidistance, if The determining module determines that the projection of the linear laser is a straight line, and if the deviation distances are not equidistant, the determining module determines the linear laser This projection is not a straight line. A road surface detecting system is suitable for a road surface to be tested, the road surface detecting system comprising: a laser emitter that emits a linear laser beam on the road surface to be tested, so that the road surface to be tested includes a projection of the linear laser beam And an electronic device comprising: an image capturing device for obtaining an image of the road surface to be tested; and a processor coupled to the image capturing device for acquiring the image, and determining the line by the image Whether the projection of the laser is a straight line, wherein if the processor determines that the projection of the linear laser is a straight line, the processor determines that the road surface to be tested is a flat road surface, wherein if the processor determines the line shape The projection of the laser is not a straight line, and the processor determines that the road surface to be tested is a non-flat road surface.