Dirt detection equipment and robot
By combining a line laser and a camera with an infrared or color supplementary lighting module, the robot can efficiently identify dirt and avoid obstacles in complex environments, solving the problem of insufficient dirt detection in existing technologies and improving cleaning results.
Patent Information
- Application Number
- CN202422509983.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-17
- Publication Date
- 2025-10-21
- Estimated Expiration
- 2034-10-17
AI Technical Summary
Existing robotic cleaning equipment lacks dirt detection devices with simple structural designs that can effectively identify dirt, thus failing to meet users' actual cleaning needs.
It employs a combination of a line laser and a camera, along with an infrared fill light module or a color fill light device, to acquire image information through time-division multiplexing, thereby achieving obstacle and dirt detection, and the processor executes the detection method.
This enables robots to efficiently and accurately identify dirt and avoid obstacles in complex environments, improving cleaning quality and coverage.
Smart Images
Figure CN223461489U_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The utility model relates to the field of artificial intelligence, and specifically relates to a dirty detection device and robot. BACKGROUND
[0002] Robots gradually replace manual cleaning tasks with their efficient, accurate and continuous work capacity. The above-mentioned working environment is complex and variable, and the robot performs cleaning tasks more by using a global traversal cleaning mode. This cleaning mode lacks intelligent support, so that the robot uses an average and full coverage cleaning solution when facing different dirt, and cannot solve the actual cleaning needs of users.
[0003] Dirty detection technology is a technical means for detecting dirt and pollutants on the surface of an object or in an environment. It is widely used in manufacturing, service, medical and health, and environmental protection fields, aiming to protect public health and maintain environmental cleanliness.
[0004] With the continuous improvement of user needs, robots will inevitably become the current development trend by integrating dirty detection functions to support various ground materials, light and dirty recognition, autonomous decision-making of cleaning strategies, and improvement of cleaning quality and coverage on the basis of meeting basic functions such as navigation and obstacle avoidance. Therefore, it is an urgent problem to provide a dirty detection device with simple structure and effective dirty recognition. Utility model content
[0005] The main purpose of the utility model is to disclose a dirty detection device and robot to at least solve the problem that there is still a lack of a dirty detection device with simple structure and effective dirty recognition in the related art.
[0006] According to one aspect of the utility model, a dirty detection device is provided.
[0007] The dirty detection equipment according to the utility model includes: one or more line lasers for emitting laser lines to realize obstacle detection, wherein, when the dirty detection equipment includes multiple line lasers, at least two line lasers in the multiple line lasers emit intersecting laser lines; one or more first cameras with a first light supplementing module, and / or one or more second cameras without the first light supplementing module and one or more first light supplementing devices, wherein, the first camera and / or the second camera are used for time-division multiplexing to collect image information to realize obstacle detection and dirty detection respectively, the first light supplementing module is used for light supplementing the first camera collecting image information, and the first light supplementing device is used for light supplementing the second camera collecting image information; a processor is used for executing an obstacle detection method and a dirty detection method based on the image information collected by the first camera and / or the second camera in time-division multiplexing.
[0008] Preferably, the one or more first cameras with the first light supplementing module and / or the one or more second cameras without the first light supplementing module are infrared single-pass cameras, wherein a single-pass wave band of the infrared single-pass camera is lambda plus or minus 20 nm, wherein lambda is any wavelength value in the range of [800 nm, 1000 nm].
[0009] Preferably, the infrared single-pass camera is arranged at any installation angle in the range of [-30°, 30°] relative to the horizontal direction, and an angle range of a field of view angle of the infrared single-pass camera is [10°, 160°].
[0010] Preferably, when the dirty detection equipment includes the first camera, the first light supplementing module arranged in the first camera is an infrared light supplementing module, a wave band corresponding to the infrared light supplementing module is the same as a wave band corresponding to the infrared single-pass camera, and a coverage angle of the infrared light supplementing module in the horizontal direction is greater than a field of view angle of the infrared camera in the horizontal direction; when the dirty detection equipment includes the second camera and the first light supplementing device, the first light supplementing device is an independently arranged infrared light supplementing lamp, a wave band corresponding to the infrared light supplementing lamp is the same as a wave band corresponding to the infrared single-pass camera, and a coverage angle of the infrared light supplementing lamp in the horizontal direction is greater than a field of view angle of the infrared camera in the horizontal direction.
[0011] Preferably, the dirty detection equipment includes a single line laser, and an infrared laser line emitted by the single line laser forms a light plane with a coverage angle range of [10°, 150°] and an angle range of an included angle between the light plane and the horizontal direction of [-30°, 0°].
[0012] Preferably, the dirt detection device comprises two line lasers arranged at intervals; the two line lasers emit infrared laser lines forming light planes perpendicular to the ground, and the laser lines emitted by the two line lasers intersect at a position in front of the two line lasers, forming an intersection angle in the range of [0°, 90°].
[0013] Preferably, the dirt detection device further comprises one or more third cameras provided with a second light supplementing module, and / or one or more fourth cameras without the second light supplementing module and one or more second light supplementing devices, wherein the third camera and the fourth camera are color cameras for time-division multiplexing to collect color image information to assist in realizing obstacle detection and dirt detection.
[0014] Preferably, the color camera is arranged at any installation angle in the range of [-30°, 30°] relative to the horizontal direction, and the angle range of the field of view of the color camera is [10°, 180°].
[0015] Preferably, when the dirt detection device comprises the third camera, the second light supplementing module arranged in the third camera is a full-band light supplementing module, and the coverage angle of the full-band light supplementing module is greater than the field of view of the color camera; when the dirt detection device comprises the fourth camera and the second light supplementing device, the second light supplementing device is a full-band light supplementing lamp independently arranged on the shell of the dirt detection device, and the coverage angle of the full-band light supplementing lamp is greater than the field of view of the color camera.
[0016] According to another aspect of the present application, a robot is provided.
[0017] The robot according to the present application comprises the dirt detection device according to any one of the above.
[0018] According to the present application, a dirt detection device with simple structure and capable of effectively identifying dirt is provided, which comprises one or more line lasers for emitting laser lines to realize obstacle detection; one or more first cameras with light supplementing function and / or one or more second cameras without light supplementing function, which time-division multiplex to collect image information when a processor executes an obstacle detection method and a dirt detection method; and the processor is used to execute the obstacle detection method and the dirt detection method based on the image information collected by the first camera and / or the second camera. BRIEF DESCRIPTION OF DRAWINGS
[0019] Figure 1This is a structural block diagram of a dirt detection device according to an embodiment of the present utility model;
[0020] Figure 2 1 is a structural diagram of a sensor module of a dirt detection device according to a preferred embodiment 1 of the present invention;
[0021] Figure 3 It is a structural schematic diagram of the sensor module of the dirt detection device according to the second preferred embodiment of the present utility model. DETAILED DESCRIPTION
[0022] The specific implementation of the present invention is described in detail below with reference to the accompanying drawings.
[0023] According to an embodiment of the present utility model, a dirt detection device is provided.
[0024] Figure 1 This is a flow chart of the dirt detection device according to an embodiment of the present utility model. Figure 1 As shown, the dirt detection device 1 includes: one or more line lasers ( Figure 1 n line lasers 10-1, 10-2, ..., 10-n are shown in the figure, which are used to emit laser lines to realize obstacle detection. When the dirt detection device includes multiple line lasers, the laser lines emitted by at least two of the multiple line lasers intersect; one or more first cameras 12 with a first fill light module 120, and / or one or more second cameras 14 without the first fill light module 120 and one or more first fill light devices 16 ( Figure 1 The figure shows a first camera 12 with a first fill light module 120, a second camera 14 without the first fill light module 120, and a first fill light device 16), wherein the first camera 12 and / or the second camera 14 are used to collect image information in a time-sharing multiplexing manner to respectively realize obstacle detection and dirt detection, the first fill light module 120 is used to fill light the first camera 12 that collects image information, and the first fill light device 16 is used to fill light the second camera that collects image information; the processor 18 is used to execute the obstacle detection method and the dirt detection method based on the image information collected by the first camera 12 and / or the second camera 14 in a time-sharing multiplexing manner.
[0025] Figure 1The dirty detection device provided by the application has simple structure and can effectively identify dirt, and when the processor executes the obstacle detection method and the dirty detection method, the first camera and / or the second camera can collect image information in time-sharing multiplexing mode, so that the dirty detection device can detect obstacle information and dirty information, and the effective fusion of the robot obstacle avoidance function and the dirty detection function is realized.
[0026] The dirty detection method executed by the processor 18 can use various methods in the prior art to detect dirty spots, for example, a camera and image processing technology (edge detection algorithm, etc.) can be used to detect dirt on the surface of an object. Or a spectrum technology (including infrared spectrum, ultraviolet-visible spectrum, etc.) can be used to confirm the degree of dirt pollution according to the brightness value of the dirt in the image. A trained target detection model can also be used to realize dirty detection based on deep learning technology by pre-training the model with a large amount of data sets.
[0027] Preferably, the one or more first cameras 12 with the first light supplement module 120 and / or the one or more second cameras 14 without the first light supplement module 120 are infrared single-pass cameras, wherein the single-pass wavelength range of the infrared single-pass camera is λ±20nm, and λ is any wavelength value in the range of [800nm, 1000nm].
[0028] Preferably, the infrared single-pass camera can be set to any installation angle within the range of [-30°, 30°] relative to the horizontal direction, and the angle range of the field of view of the infrared single-pass camera can be [10°, 160°].
[0029] Preferably, when the dirty detection device includes the first camera, the first light supplement module provided in the first camera is an infrared light supplement module, the wavelength range corresponding to the infrared light supplement module is the same as the wavelength range corresponding to the infrared single-pass camera, and the coverage angle of the infrared light supplement module in the horizontal direction is greater than the field of view angle of the infrared camera in the horizontal direction; when the dirty detection device includes the second camera and the first light supplement device, the first light supplement device is an independently arranged infrared light supplement lamp, the wavelength range corresponding to the infrared light supplement lamp is the same as the wavelength range corresponding to the infrared single-pass camera, and the coverage angle of the infrared light supplement lamp in the horizontal direction is greater than the field of view angle of the infrared camera in the horizontal direction.
[0030] In the preferred implementation process, the above-mentioned dirt detection device can be provided with one or more cameras with light supplementing modules, which can self-supplement light, and no additional light supplementing device is needed to supplement light for the camera. The above-mentioned dirt detection device can also be provided with one or more cameras without light supplementing modules, which cannot self-supplement light, and an additional light supplementing device is needed to supplement light for the camera. The above-mentioned dirt detection device can also be provided with one or more cameras with light supplementing modules, one or more cameras without light supplementing modules, and a light supplementing device for the camera without light supplementing modules.
[0031] The prior art uses colored laser and ordinary lens, which is easily disturbed by environmental light and strong light, and is difficult to use in actual environment. The above-mentioned first camera and second camera in the present application can be provided as infrared single-pass cameras, the light supplementing module in the first camera can be provided as an infrared light supplementing module, and the light supplementing device for the second camera can be provided as an infrared light supplementing lamp. The infrared light supplementing module or the infrared light supplementing lamp can emit light invisible to the human eye, which irradiates on the liquid dirt or solid dirt, and these liquid dirt or solid dirt are captured by the infrared camera. Since the infrared light supplementing lamp, the infrared light supplementing module and the infrared camera adopt a single waveband, the influence of environmental light can be excluded, and the use reliability and environmental disturbance resistance are good.
[0032] Preferably, the above-mentioned dirt detection device can include a single line laser, and the infrared laser line emitted by the single line laser forms a light plane with an angle range of [10°, 150°] in the coverage angle and an angle range of [-30°, 0°] between the light plane and the horizontal direction.
[0033] Preferably, the above-mentioned dirt detection device can include two line lasers arranged at intervals, and the infrared laser lines emitted by the two line lasers form light planes perpendicular to the ground. The laser lines emitted by the two line lasers intersect at a position in front of the two line lasers, and the intersection angle formed by the two line lasers has an angle range of [0°, 90°].
[0034] In the preferred implementation process, the above-mentioned dirt detection device can be provided with a single line laser, and the processor in the above-mentioned dirt detection device executes an obstacle detection method, which mainly relies on the laser triangulation method, which is a technology for measuring the distance by measuring the time (i.e. the flight time) of the laser beam from emission to reflection by the object or by measuring the change of the reflection angle. Specifically, the single line laser radar emits a laser beam, which is reflected back when it encounters an obstacle. The laser radar measures the flight time of the laser beam or the change of the reflection angle, and calculates the distance between the laser radar and the obstacle by combining the known speed of light. This technology has the characteristics of high precision and high reliability, and makes the single line laser radar widely used in obstacle detection.
[0035] In the preferred implementation process, the above-mentioned dirt detection device can also be provided with a plurality of line lasers, and if a plurality of line lasers are provided, at least two line lasers of the plurality of line lasers emit intersecting laser lines. For example, the 3D structured light technology usually adopts the intersecting line laser scheme, that is, two line lasers arranged on both sides are simultaneously excited to emit line lasers, and the line lasers emitted by the two line lasers intersect. In the application of obstacle detection, the 3D structured light technology can accurately measure the depth information of the object surface by emitting and receiving light, and further construct a three-dimensional model of the object. By analyzing these three-dimensional models, the position and shape of the obstacle can be effectively identified and located, thereby realizing obstacle detection.
[0036] By adopting the intersecting line laser scheme, a stereo map is established by at least two intersecting laser lines and the movement of the robot, and the height and distance are accurately measured, so as to provide more accurate three-dimensional obstacle avoidance information. The intersecting double-line laser obstacle avoidance technology has the advantages of millimeter-level high precision, low cost, high stability, and strong anti-environmental light interference ability.
[0037] Preferably, the laser emitted by the line laser can be visible light or non-visible light, and preferably, infrared light can be used. The wavelength band of the infrared light can be the same as that of the infrared single-pass camera. Since a single wavelength band of infrared light is used, the influence of environmental light can be excluded, and the use reliability and anti-environmental interference performance are reliable.
[0038] Preferably, the above-mentioned dirt detection device can also include one or more third cameras with a second light supplementing module, and / or one or more fourth cameras without the above-mentioned second light supplementing module and one or more second light supplementing devices, wherein the third camera and the fourth camera are color cameras, and are used for time-division multiplexing to collect color image information, so as to assist in realizing obstacle detection and dirt detection.
[0039] Preferably, the color camera is arranged at any installation angle within the range of [-30°, 30°] relative to the horizontal direction, and the angle range of the field of view angle of the color camera is [10°, 180°].
[0040] The working principle of the color camera mainly bases on the working of the photosensitive element and the mixing of three primary colors. The light signal is converted into an electric signal by the photosensitive element, and the light is divided into three channels of red, green and blue by a color filter. Finally, the final color image signal is synthesized according to the signals of the three channels. The color camera is used for collecting color images, and the color camera can provide high-definition and rich-color images. In the present application, a color camera can also be provided in the dirt detection device. In some special scenes, such as a reflective scene, the color camera collects image information, which is used to assist in obstacle recognition and dirt recognition, and more effectively realizes the functions of obstacle avoidance and dirt detection. In the specific implementation process, the color camera can be provided as one or multiple, and the color camera can adopt a camera with a full-waveband light supplementing module or a camera without a full-waveband light supplementing module, but one or more independently provided full-waveband light supplementing lamps need to be added.
[0041] Preferably, when the above-mentioned dirt detection device comprises: the above-mentioned third camera, the above-mentioned second light supplementing module provided in the above-mentioned third camera is a full-waveband light supplementing module, and the coverage angle of the above-mentioned full-waveband light supplementing module is greater than the field of view angle of the color camera; when the above-mentioned dirt detection device comprises: the above-mentioned fourth camera and the above-mentioned second light supplementing device, the above-mentioned second light supplementing device is a full-waveband light supplementing lamp independently provided on the shell of the dirt detection device, and the coverage angle of the above-mentioned full-waveband light supplementing lamp is greater than the field of view angle of the color camera.
[0042] The line laser, the first camera and / or the second camera, the third camera and / or the fourth camera, the first light supplementing device and the second light supplementing device can be packaged by a shell made of plastic material, metal material or other materials to form a sensor module. The line laser, the first camera and / or the second camera, the third camera and / or the fourth camera, the first light supplementing device and the second light supplementing device can be embedded into the shell of the sensor module. A certain number of through holes are formed in the positions of the shell matched with the above-mentioned devices, so that the above-mentioned devices can emit light to the outside of the dirt detection device or receive light from the outside. The processor of the dirt detection device can be arranged inside the shell of the above-mentioned sensor module. Of course, the processor can also be arranged outside the shell of the above-mentioned sensor module and connected with the sensor module. For example, the processor can be arranged on a mainboard, and the processor on the mainboard is connected with the sensor module through a flexible printed circuit (FPC).
[0043] The present application does not limit the position layout of the line laser, the first camera and / or the second camera, the third camera and / or the fourth camera, the first light supplementing device, the second light supplementing device and the processor in the above-mentioned dirt detection device. Any position layout mode is within the protection scope of the present application.
[0044] The above preferred embodiments are further described in combination with the embodiments of the following Figure 2 and Figure 3 .
[0045] Figure 2 is a structural schematic view of a sensor module of the dirt detection device according to the preferred embodiment one of the present application. As shown in the figure, Figure 2 the sensor module comprises: a line laser 20 for emitting single-line laser; an infrared camera 22 for time-division multiplexing collection of image information, and used for realizing dirt detection and obstacle detection respectively, the infrared camera does not have an infrared light supplementing module; an infrared light supplementing lamp 24 for supplementing light to the infrared camera 22, which usually supplements light to the infrared camera 22 when the infrared camera 22 is used for dirt detection; a color camera 26 for time-division multiplexing collection of color image information, and used for assisting realization of obstacle detection and dirt detection; and a full-waveband light supplementing lamp 28 for supplementing light to the color camera 26 in full waveband. Among them, the line laser 20, the infrared camera 22, the infrared light supplementing lamp 24, the color camera 26, and the full-waveband light supplementing lamp 28 are all encapsulated by a shell 29 of the dirt detection device.
[0046] The processor of the dirt detection device can be arranged inside the above sensor module, and the processor can also be arranged outside the sensor module and connected with the sensor module. Figure 2 The processor is not shown in the figure.
[0047] It should be noted that, Figure 2 only one embodiment of the dirt detection device, the present application does not limit the position layout of the line laser 20, the infrared camera 22, the infrared light supplementing lamp 24, the color camera 26, and the full-waveband light supplementing lamp 28 encapsulated on the shell 29 in the above dirt detection device, and any position layout adjustment mode is within the protection scope of the present application.
[0048] Figure 3 is a structural schematic view of a dirt detection device according to the preferred embodiment two of the present application. As shown in the figure, Figure 3As shown, the dirt detection device comprises two line lasers 30_1 and 30_2 for emitting line lasers; an infrared camera 32 for collecting image information in time division multiplexing, which is used to realize dirt detection and obstacle detection, and the infrared camera does not have an infrared light supplement module; an infrared light supplement lamp 34 for supplementing light to the infrared camera 32, which usually supplements light to the infrared camera 32 when the infrared camera 32 is used for dirt detection; a color camera 36 for collecting color image information in time division multiplexing to assist in realizing obstacle detection and dirt detection, and a full-waveband light supplement lamp 38 for supplementing light to the color camera 36 in full waveband. Among them, the above-mentioned line lasers 30_1 and 30_2, the infrared camera 32, the infrared light supplement lamp 34, the color camera 36, and the full-waveband light supplement lamp 38 are all packaged by the shell 39 of the dirt detection device. As shown in the figure, Figure 3 As shown, one line laser 30_1 and 30_2 are arranged on each end of the shell 39, and the two ends form a certain angle (greater than 0° and less than 90°) with the middle part of the shell 39, so that the laser lines emitted by the line lasers 30_1 and 30_2 intersect.
[0049] The processor of the dirt detection device can be arranged inside the above-mentioned sensor module, and the processor can also be arranged outside the sensor module and connected with the sensor module. Figure 3 The processor is not shown in the figure.
[0050] It should be noted that, Figure 3 Only one embodiment of the dirt detection device, the present application does not limit the position layout of the two line lasers 30_1 and 30_2, the infrared camera 32, the infrared light supplement lamp 34, the color camera 36, and the full-waveband light supplement lamp 38 on the shell 39 in the above-mentioned dirt detection device, and any position layout adjustment method is within the protection scope of the present application.
[0051] Among them, Figure 2 And Figure 3The single-pass waveband of the infrared camera can be lambda+ / -20nm, and lambda can be any one of the wavelength values in [800nm, 1000nm]. The waveband of the infrared light supplementing lamp is the same as the waveband of the infrared single-pass camera. For example, the single-pass waveband of the infrared camera is 900+ / -20nm, and the single-pass waveband of the infrared light supplementing lamp is 900+ / -20nm. The coverage angle of the infrared light supplementing lamp in the horizontal direction is greater than the field of view angle of the infrared camera in the horizontal direction. The infrared light supplementing lamp emits infrared light invisible to the human eye, and the infrared light is irradiated on the liquid or solid dirt. Part of the infrared light is absorbed by the liquid or solid dirt, and part of the infrared light is diffusely reflected. The reflected infrared light carries the contour and temperature information of the object. The reflected infrared light is focused by the lens and captured by the infrared light receiver of the infrared single-pass camera. The infrared light receiver converts the infrared light into an electrical signal to provide raw data for subsequent image processing. The image processor of the infrared single-pass camera amplifies, filters, enhances and processes the received electrical signal, and finally converts it into visual image information. Since the infrared light supplementing lamp and the infrared camera adopt a single waveband, the influence of ambient light can be excluded, and the reliability and anti-environmental interference performance are good.
[0052] According to the robot embodiment of the present application, a robot is provided.
[0053] According to the robot embodiment of the present application, a robot is provided.
[0054] When the robot with the dirt detection device of the present embodiment is moving, the one or more line lasers of the dirt detection device arranged on the robot are used to emit laser lines to realize obstacle detection. When the processor executes the obstacle detection method and the dirt detection method, the camera (for example, the infrared camera) can collect image information by time multiplexing, and the light supplementing module or the light supplementing lamp provides light for the camera. The dirt detection device can detect both obstacle information and dirt information, so as to realize effective integration of the robot obstacle avoidance function and the dirt detection function.
[0055] It should be noted that any preferred embodiment of the dirt detection device arranged in the robot described above can refer to the description of Figures 1 to 3 , and will not be repeated here.
[0056] In summary, with the above-mentioned embodiments of the utility model provide, when the processor executes the obstacle detection method and the dirty detection method, the infrared camera can collect image information by time multiplexing, the dirty detection equipment can detect obstacle information and can detect dirty information, so that the effective fusion of the robot obstacle avoidance function and the dirty detection function is realized. Because the single waveband infrared fill light and the infrared camera are adopted, the influence of the environmental light can be excluded, and the reliable usability and the anti-environmental interference performance are possessed. In some special scenes, for example, the color camera collects image information in the reflective scene, is used for assisting the obstacle identification and the dirty identification, more effectively realizes the obstacle avoidance and the dirty detection function.
[0057] The above disclosure is only a few specific embodiments of the utility model, but the utility model is not limited to this, any person skilled in the art can think of the change and should fall into the protection scope of the utility model.
Claims
1. A soiling detection apparatus, characterized by, The device comprises: one or more line lasers for emitting laser lines to achieve obstacle detection, wherein when the dirt detection device comprises a plurality of line lasers, at least two line lasers of the plurality of line lasers emit laser lines that intersect; one or more first cameras with a first light supplementing module and / or one or more second cameras without the first light supplementing module and one or more first light supplementing devices, wherein the first cameras and / or the second cameras are used to time-division multiplex image information collection to achieve obstacle detection and dirt detection respectively, the first light supplementing module is used to supplement light for the first cameras collecting image information, and the first light supplementing devices are used to supplement light for the second cameras collecting image information; a processor for executing an obstacle detection method and a dirt detection method based on the image information collected by the first cameras and / or the second cameras in time-division multiplexing.
2. The dirt detection device according to claim 1, wherein the one or more first cameras with the first light supplementing module and / or the one or more second cameras without the first light supplementing module are infrared single-pass cameras, wherein a single-pass waveband of the infrared single-pass cameras is λ±20nm, and λ is any wavelength value in the range of [800nm, 1000nm].
3. The dirt detection device according to claim 2, wherein the infrared single-pass cameras are arranged at any installation angle in the range of [-30°, 30°] relative to the horizontal direction; an angle range of a field of view angle of the infrared single-pass cameras is [10°, 160°].
4. The dirt detection device according to claim 1, wherein when the dirt detection device comprises the first cameras, the first light supplementing module arranged in the first cameras is an infrared light supplementing module, a corresponding waveband of the infrared light supplementing module is the same as a corresponding waveband of the infrared single-pass cameras, and a coverage angle of the infrared light supplementing module in the horizontal direction is greater than a field of view angle of the infrared cameras in the horizontal direction; when the dirt detection device comprises the second cameras and the first light supplementing devices, the first light supplementing devices are independently arranged infrared light supplementing lamps, a corresponding waveband of the infrared light supplementing lamps is the same as a corresponding waveband of the infrared single-pass cameras, and a coverage angle of the infrared light supplementing lamps in the horizontal direction is greater than a field of view angle of the infrared cameras in the horizontal direction.
5. The soiling detection apparatus of claim 1, wherein The dirt detection device comprises a single line laser; an infrared laser line emitted by the single line laser forms a light plane with a coverage angle range of [10°, 150°] and an angle range of an included angle between the light plane and the horizontal direction of [-30°, 0°].
6. The soiling detection apparatus of claim 1, wherein The dirt detection device comprises two line lasers arranged at intervals; infrared laser lines emitted by the two line lasers form light planes that are perpendicular to the ground, the infrared laser lines emitted by the two line lasers intersect at a position in front of the two line lasers, and an angle range of an intersection angle formed by the infrared laser lines is [0°, 90°].
7. The soiling detection apparatus of claim 1, wherein The dirt detection device further comprises one or more third cameras provided with a second light supplementing module, and / or one or more fourth cameras not provided with the second light supplementing module and one or more second light supplementing devices, wherein the third and fourth cameras are color cameras configured to collect color image information in time division multiplexing manner to assist in obstacle detection and dirt detection.
8. The dirt detection device according to claim 7, characterized in that, the color camera is arranged at any installation angle within a range of [-30°, 30°] relative to the horizontal direction; an angle range of a field of view angle of the color camera is [10°, 180°].
9. The dirt detection device according to claim 7 or 8, characterized in that, when the dirt detection device comprises the third camera, the second light supplementing module arranged in the third camera is a full-waveband light supplementing module, and an angle range covered by the full-waveband light supplementing module is greater than a field of view angle of the color camera; when the dirt detection device comprises the fourth camera and the second light supplementing device, the second light supplementing device is a full-waveband light supplementing lamp independently arranged on an outer shell of the dirt detection device, and an angle range covered by the full-waveband light supplementing lamp is greater than a field of view angle of the color camera.
10. A robot, characterized in that The robot comprises the dirt detection device according to any one of claims 1 to 9.