Image acquisition system and robot

Abstract

The invention provides an image acquisition system and a robot, the image acquisition system comprises a first acquisition unit, a second acquisition unit and a processor, the image acquisition area of the first acquisition unit is a first area, the image acquisition area of the second acquisition unit is a second area, and the first area and the second area are overlapped. An image acquired by the first acquisition unit is a first image, an image acquired by the second acquisition unit is a second image, and the processor determines the distance of the object and the attribute of the object according to the first image and the second image. According to the image acquisition system, the recognition effect on the attribute of the object is enhanced on the basis of the prior art, and the image acquisition system has the functions of carrying out distance measurement on the object and recognizing the attribute of the object, so that the ability of the robot to cope with complex working conditions is improved.

Description

Technical Field

[0001] The present invention relates to the field of robot technology, and in particular to an image acquisition system and a robot. Background Art

[0002] In the prior art, some robots (such as lawn mowing robots, sweeping robots, etc.) use visual recognition to locate and navigate. The camera at the front end of the robot can capture images in front of the robot, and the robot recognizes objects and determines the distance of the objects based on the captured images. Although the robots in the prior art can recognize the general outline of objects and determine the distance of objects, the robots are not good at recognizing the attributes of objects and cannot cope with more complex working situations. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention provides an image acquisition system, which can determine the distance of an object and has a good recognition effect on the attributes of the object.

[0004] The present invention also provides a robot comprising the above image acquisition system.

[0005] According to an embodiment of the first aspect of the present invention, the image acquisition system includes: a first acquisition unit, whose image acquisition area is a first area, and the image acquired by the first acquisition unit is a first image; a second acquisition unit, whose image acquisition area is a second area, and the image acquired by the second acquisition unit is a second image, at least a portion of the first area and at least a portion of the second area overlap with each other to form an overlapping area; a processor, the first acquisition unit and the second acquisition unit are both communicatively connected to the processor, and the processor is configured as follows: the processor determines the distance between the object in the overlapping area and the first acquisition unit according to the first image, and determines the attribute of the object in the overlapping area according to the second image; or, the processor determines the distance between the object in the overlapping area and the first acquisition unit according to the first image, and determines the attribute of the object in the overlapping area according to the first image and the second image; or, the processor determines the distance between the object in the overlapping area and the first acquisition unit according to the first image and the second image, and determines the attribute of the object in the overlapping area according to at least one of the first image and the second image.

[0006] The image acquisition system according to the first aspect of the present invention has at least the following beneficial effects: the image acquisition system can also determine the distance of an object, and the image acquisition system has the functions of both measuring the distance of an object and identifying the attributes of the object, which is conducive to improving the robot's ability to cope with complex working situations. In addition, the image acquisition system of the present invention is configured to determine the attributes of an object by combining a visible light image with a non-visible light image, and the present invention enhances the recognition effect of the image acquisition system on the attributes of an object on the basis of the prior art.

[0007] According to some embodiments of the present invention, the second acquisition unit is a multispectral sensor, and the second image at least includes an image of the object under non-visible light.

[0008] According to some embodiments of the present invention, the first acquisition unit is a binocular camera, the first acquisition unit includes a first camera and a second camera that are spaced apart from each other, the image acquisition area of ​​the first camera is a third area, the image acquisition area of ​​the second camera is a fourth area, a portion of the third area overlaps with a portion of the fourth area, and the first area includes the third area and the fourth area.

[0009] According to some embodiments of the present invention, a line connecting the first camera and the second camera is a reference line, and the second acquisition unit is located on the reference line.

[0010] According to some embodiments of the present invention, it is characterized in that the line connecting the first camera and the second camera is a reference line, and the angle bisector of the horizontal field of view angle of the second acquisition unit is horizontally arranged and perpendicular to the reference line.

[0011] According to some embodiments of the present invention, a line connecting the first camera and the second camera is a reference line, and an angle between an angle bisector of a horizontal field of view angle of the second acquisition unit and the reference line is an acute angle or an obtuse angle.

[0012] According to some embodiments of the present invention, the line between the first camera and the second camera is a baseline, the second acquisition unit is located outside the midpoint of the baseline, and the first camera, the second camera and the second acquisition unit are located on the same straight line.

[0013] According to some embodiments of the present invention, a line connecting the first camera and the second camera is a reference line, and the second acquisition unit is located above or below the reference line.

[0014] According to some embodiments of the present invention, a line connecting the first camera and the second camera is a reference line, and the second acquisition unit is located in front of or behind the reference line.

[0015] According to some embodiments of the present invention, the horizontal field of view angle of the first camera is θ1, 50°≤θ1≤180°; and / or the horizontal field of view angle of the second camera is θ2, 50°≤θ2≤180°; and / or the vertical field of view angle of the first camera is θ3, 30°≤θ3≤150°; and / or the vertical field of view angle of the second camera is θ4, 30°≤θ4≤150°.

[0016] According to some embodiments of the present invention, the horizontal field of view angle of the second acquisition unit is θ5, 50°≤θ5≤150°; and / or the vertical field of view angle of the second acquisition unit is θ6, 30°≤θ6≤150°.

[0017] According to some embodiments of the present invention, the first acquisition unit and the second acquisition unit are both configured as multispectral sensors, the first image includes an image of the object under visible light and an image of the object under non-visible light, and the second image includes an image of the object under visible light and an image of the object under non-visible light.

[0018] The robot according to the second embodiment of the present invention includes the image acquisition system as described in the first embodiment.

[0019] The robot according to the embodiment of the second aspect of the present invention has at least the following beneficial effects: the robot can judge the distance between the robot and objects in the environment and identify the properties of the objects, and the robot has a strong ability to cope with complex working situations.

[0020] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The present invention will be further described below with reference to the accompanying drawings and embodiments, wherein:

[0022] Figure 1 It is a front view of the image acquisition system according to the first embodiment of the present invention;

[0023] Figure 2 A top view of the image acquisition range of the image acquisition system of the first embodiment;

[0024] Figure 3 It is a left view of the image acquisition range of the image acquisition system of the first embodiment;

[0025] Figure 4 for Figure 1 A top view of the image acquisition range of the image acquisition system when the second acquisition unit is located at the midpoint and tilted to the right;

[0026] Figure 5 for Figure 1 A top view of the image acquisition range of the image acquisition system when the second acquisition unit is located at the midpoint and tilted to the left;

[0027] Figure 6 It is a front view of the image acquisition system in which the second acquisition unit is located on the reference line and on the left side of the midpoint in an embodiment of the present invention;

[0028] Figure 7 for Figure 6 A top view of the image acquisition range of the image acquisition system when the second acquisition unit is arranged forward;

[0029] Figure 8 for Figure 6 A top view of an image acquisition range of the image acquisition system when the second acquisition unit is tilted to the right;

[0030] Fig. 9 is a top view of the image acquisition range of the image acquisition system when the second acquisition unit is located on the right side of the midpoint and tilted to the left in an embodiment of the present invention;

[0031] Fig.10 is a top view of an image acquisition system in which the second acquisition unit is located on the right side of the second camera in an embodiment of the present invention;

[0032] Fig.11 for Fig.10 A top view of the image acquisition range of the image acquisition system when the second acquisition unit is arranged forward;

[0033] Fig.12 for Fig.10 A top view of the image acquisition range of the image acquisition system when the second acquisition unit is arranged to face right;

[0034] Fig.13 for Fig.10 A top view of an image acquisition range of the image acquisition system when the second acquisition unit is arranged to face left;

[0035] Fig.14 is a top view of an image acquisition system in which the second acquisition unit is located directly below the first camera in an embodiment of the present invention;

[0036] Fig.15 is a top view of an image acquisition system in which the second acquisition unit is located directly below the second camera in an embodiment of the present invention;

[0037] Fig.16 is a top view of the image acquisition system in which the second acquisition unit is located directly below the midpoint in an embodiment of the present invention;

[0038] Fig.17 It is a left view of the image acquisition range of the image acquisition system when the second acquisition unit is located below the first acquisition unit in the embodiment of the present invention;

[0039] Fig.18 It is a left view of the image acquisition range of the image acquisition system when the second acquisition unit is located above the first acquisition unit in the embodiment of the present invention;

[0040] Fig.19 is a top view of the image acquisition range of the image acquisition system when the second acquisition unit is located behind the first acquisition unit in the embodiment of the present invention;

[0041] Fig. 20 is a top view of the image acquisition range of the image acquisition system when the second acquisition unit is located in front of the first acquisition unit in an embodiment of the present invention;

[0042] Fig.21 Schematic diagram of a robot in one embodiment of the present invention.

[0043] Reference numerals:

[0044] 101-image acquisition system, 102-first acquisition unit, 103-first camera, 104-second camera, 105-second acquisition unit;

[0045] 201 - first area, 202 - second area, 203 - third area, 204 - fourth area, 205 - overlapping area;

[0046] 301-baseline, 302-midpoint, 303-first angle bisector, 304-second angle bisector, 305-third angle bisector;

[0047] 401-robot, 402-housing, 403-driving wheel. DETAILED DESCRIPTION

[0048] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0049] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0050] In the description of the present invention, "several" means more than one, "many" means more than two, "greater than", "less than", "exceed", etc. are understood to exclude the number itself, and "above", "below", "within", etc. are understood to include the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0051] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0052] Figure 1 and Figure 2 The image acquisition system 101 of the first embodiment of the present invention is shown. The image acquisition system 101 of the first embodiment includes a first acquisition unit 102, a second acquisition unit 105 and a processor. Figure 1 The positional relationship between the first acquisition unit 102 and the second acquisition unit 105 in the first embodiment is shown. The processor is not shown in the figure. The processor is used to process image data. The first acquisition unit 102 can acquire images of objects located in the first area 201 under visible light, and the second acquisition unit 105 can acquire images of objects located in the second area 202 under non-visible light and visible light. Figure 2 As shown, the image acquisition area of ​​the first acquisition unit 102 is the first area 201, the image acquisition area of ​​the second acquisition unit 105 is the second area 202, the first area 201 is located in front of the first acquisition unit 102, and the second acquisition area is located in front of the second acquisition area.

[0053] In the first embodiment, the first acquisition unit 102 is set as a binocular camera, and the first acquisition unit 102 includes a first camera 103 and a second camera 104 that are spaced apart from each other. The image acquisition area of ​​the first camera 103 is the third area 203, and the image acquisition area of ​​the second camera 104 is the fourth area 204. A portion of the third area 203 and a portion of the fourth area 204 overlap with each other, and both the third area 203 and the fourth area 204 overlap with the second area 202. Correspondingly, the first area 201 includes the third area 203 and the fourth area 204. In addition, the first camera 103 and the second camera 104 can both be set as black and white cameras, or both can be set as RGB cameras. In other embodiments, the first acquisition unit 102 can also include only one camera, which can be set as a depth camera.

[0054] In the first embodiment, the second acquisition unit 105 is configured as a multispectral sensor. The multispectral sensor can acquire images under visible light, near infrared light (NIR), and images under non-visible light in other bands (such as ultraviolet light, short-wave infrared light, etc.). The bands that the multispectral sensor can use are not listed here one by one.

[0055] like Figure 2 As shown, at least a portion of the first area 201 and at least a portion of the second area 202 overlap each other, and the area where the first area 201 and the second area 202 overlap each other is the overlapping area 205. The overlapping area 205 is equivalent to the intersection of the first area 201 and the second area 202, and the overlapping area 205 is both a part of the first area 201 and a part of the second area 202. The processor can determine the distance between the object in the overlapping area 205 and the first acquisition unit 102 according to the first image. In this embodiment, the first acquisition unit 102 is set as a binocular camera, and the processor can measure the distance of the object in the overlapping area 205 according to the principle of binocular ranging. In addition, the processor can also determine the attributes of the object in the overlapping area 205 according to the second image. The attributes of the object may include the size, shape, reflectivity, material, type, etc. of the object. In the present invention, the attributes of the object can also be understood as the type of the object. The attributes of the object can be specifically identified as whether the object is grass, stone, metal, water, etc. The reflection effect of an object on light of different wavelengths is related to the material of the object itself. If the image acquired by the second acquisition unit 105 under visible light is called a "second visible light image", and the image acquired by the second acquisition unit 105 under non-visible light is called a "second non-visible light image", then the display effect of the object in the second visible light image and the display effect in the second visible light image may be different. For example, the display effects of the object in the two images are different in terms of brightness, grayscale, color, etc. By analyzing and comparing the display effects of the same object in the second visible light image and the second non-visible light image, the material of the object can be determined, and thus the type of the object can be determined.

[0056] In the prior art, the robot's camera can usually only capture images under visible light, but the properties of some objects are difficult to identify under visible light images. If the properties of the object cannot be accurately identified, the robot may make wrong actions. For example, a lawnmower robot mistakenly identifies a plant that needs to be cut as a hard obstacle, so the lawnmower robot will avoid the plant and fail to complete the mowing task. This is particularly true when there are many different objects in the robot's working environment.

[0057] The image acquisition system 101 of the first embodiment is provided with a second acquisition unit 105 capable of acquiring visible light images and non-visible light images, which enhances the recognition effect of the image acquisition system 101 on the attributes of an object on the basis of the prior art. In addition, the image acquisition system 101 of the first embodiment can also determine the distance of an object. The image acquisition system 101 has the functions of both measuring the distance to an object and recognizing the attributes of the object, which is conducive to improving the ability of the robot 401 to cope with complex working situations.

[0058] As described above, the first acquisition unit 102 in the first embodiment is set as a binocular camera, and the processor measures the distance by the principle of binocular ranging. Compared with using a single camera to measure the distance, using binocular ranging to measure the distance of an object does not rely on estimation, which is conducive to improving the accuracy of ranging.

[0059] In other embodiments, the second acquisition unit 105 may not be configured as a multispectral sensor. For example, the multispectral sensor in the first embodiment is replaced by an infrared camera (i.e., the second acquisition unit 105 is configured as an infrared camera), and the infrared camera is used to acquire images of objects under infrared light. Accordingly, at this time, the second acquisition unit 105 only acquires images of objects under non-visible light, and the processor is configured as follows: the processor determines the properties of the object in the overlapping area 205 based on the first image and the second image; and the method for determining the distance of the object in the overlapping area 205 is the same as that in the first embodiment. Among them, the method of "the processor determines the properties of the object in the overlapping area 205 based on the first image and the second image" is similar to the method in which the processor determines the properties of the object based on the second visible light image and the second non-visible light image in the first embodiment, and will not be repeated here.

[0060] Alternatively, in some other embodiments, the first acquisition unit 102 and the second acquisition unit 105 are both configured as multispectral sensors, and the first acquisition unit 102 and the second acquisition unit 105 are both capable of acquiring images of the object under visible light and non-visible light. In this case, the combination of the first acquisition unit 102 and the second acquisition unit 105 is equivalent to a binocular camera composed of two multispectral sensors. Accordingly, the processor is configured as follows: the processor jointly determines the distance between the object in the overlapping area 205 and the first acquisition unit 102 according to the first image and the second image (the distance can also be determined using the principle of binocular ranging). In addition, since the first image and the second image both include images of the object under visible light and under non-visible light, the processor can determine the properties of the object only according to the first image, or can determine the properties of the object only according to the second image, or can jointly determine the properties of the object according to the first image and the second image.

[0061] It should be noted that if the first acquisition unit 102 and the second acquisition unit 105 are both configured as multispectral sensors, the first acquisition unit 102 and the second acquisition unit 105 may be distributed in the vertical direction, in the front-to-back direction, or in the left-to-right direction.

[0062] Figure 2 and Figure 3 1 shows the field of view of the first acquisition unit 102 and the second acquisition unit 105. Figure 2 As shown, to ensure that the first acquisition unit 102 has a suitable image acquisition width in the left and right directions, if the horizontal field angle of the first camera 103 is recorded as θ1, then 50°≤θ1≤180°; if the horizontal field angle of the second camera 104 is recorded as θ2, then 50°≤θ2≤180°. θ1 and θ2 can be equal or unequal. Similarly, Figure 3 As shown, to ensure that the first acquisition unit 102 has a suitable image acquisition height in the vertical direction, the vertical field of view of the first camera 103 is θ3, 30°≤θ3≤150°; the vertical field of view of the second camera 104 is θ4, 30°≤θ4≤150°. θ3 and θ4 can be equal or unequal. Figure 3 In the embodiment shown, θ4 is not shown in the figure. Figure 3 From the perspective of , θ4 coincides with θ3.

[0063] It should be noted that the field of view angle refers to the angle formed by the two edges of the maximum range of the image of the object to be measured that can pass through the lens, with the lens of the optical instrument as the vertex. Figure 2 As shown, the two sides of the horizontal field of view of the first camera 103 are the left edge and the right edge of the third area 203, and the two sides of the horizontal field of view of the second camera 104 are the left edge and the right edge of the fourth area 204. Figure 3 As shown, the two sides of the vertical field of view of the first camera 103 are the upper edge and the lower edge of the third area 203, and the two sides of the vertical field of view of the second camera 104 are the upper edge and the lower edge of the fourth area 204. Figure 3 As shown, the third area 203 and the fourth area 204 may be completely overlapped at a left viewing angle.

[0064] like Figure 2 As shown, to ensure that the second acquisition unit 105 has a suitable image acquisition width in the left and right directions, if the horizontal field angle of the second acquisition unit 105 is recorded as θ5, then 50°≤θ5≤150°. Similarly, Figure 3As shown, to ensure that the second acquisition unit 105 has a suitable image acquisition width in the vertical direction, if the vertical field angle of the second acquisition unit 105 is recorded as θ6, then 30°≤θ6≤150°.

[0065] In order to facilitate the robot 401 to measure the distance of objects near the ground, the first collection component and the second collection component can be arranged to face downward. Figure 3 As shown, the angular bisector (first angular bisector 303) of the vertical field of view of the first acquisition unit 102 is tilted downward, and the end of the first angular bisector 303 close to the first acquisition unit 102 is higher than the end of the first angular bisector 303 away from the first acquisition unit 102. Similarly, in order to facilitate the robot 401 to identify objects near the ground, the angular bisector (second angular bisector 304) of the vertical field of view of the second acquisition unit 105 is tilted downward, and the two ends of the second angular bisector 304 close to the second acquisition unit 105 are higher than the end of the second angular bisector 304 away from the second acquisition unit 105.

[0066] like Figure 2 As shown, in the first embodiment, the line connecting the first camera 103 and the second camera 104 is the reference line 301, the reference line 301 is a line segment, and the second acquisition unit 105 (multi-spectral sensor) is arranged on the reference line 301. In addition, the angular bisector (third angular bisector 305) of the horizontal field of view angle of the second acquisition unit 105 is arranged horizontally, the third angular bisector 305 extends in the front-to-back direction, and the third angular bisector 305 is perpendicular to the reference line 301. This arrangement can also be understood as the lens of the second acquisition unit 105 is not tilted to the left or right. Under this arrangement, the overlapping area 205 is larger, and the image acquisition system 101 can perform image acquisition, ranging and recognition on objects within a larger range.

[0067] In addition, since the second acquisition unit 105 is located between the first camera 103 and the second camera 104, the total installation space required for the first acquisition unit 102 and the second acquisition unit 105 is small, which facilitates the installation of the first acquisition unit 102 and the second acquisition unit 105 on a small robot 401 or other equipment. It should be noted that "the line connecting the first camera 103 and the second camera 104" refers to the line connecting the center of the lens of the first camera 103 and the center of the lens of the second camera 104; "the second acquisition unit 105 is arranged on the reference line 301" means that the center of the lens of the second acquisition unit 105 is located on the reference line 301.

[0068] The following will introduce other arrangements of the relative positions of the first acquisition unit 102 and the second acquisition unit 105. In the embodiments described below, the field of view angles of the first acquisition unit 102 and the second acquisition unit 105 can refer to the field of view angles in the first embodiment above, and will not be repeated below.

[0069] Figure 2 The embodiment shown (first embodiment) and Figure 6 In the embodiment shown, the second acquisition unit 105 is arranged on the reference line 301. Figure 2 As shown, the second acquisition unit 105 can be set at the midpoint 302 of the reference line 301, that is, the center of the second acquisition unit 105 coincides with the center of the reference line 301. This design is suitable for the image acquisition system 101 to perform image acquisition, distance measurement and recognition on the object in front. Figure 6 As shown, the second acquisition unit 105 can also be set on the left side of the midpoint 302 of the reference line 301. Figure 2 and Figure 7 , when the angle of the third triangle bisector 305 is the same, the second acquisition unit 105 is arranged on the left side of the midpoint 302 of the reference line 301 so that the overlapping area 205 is further outward. Therefore, the second acquisition unit 105 is also arranged on the left side of the midpoint 302 of the reference line 301, which is more suitable for the robot 401 integrated with the image acquisition system 101 to perform edge obstacle avoidance. In addition, in other embodiments not shown in the figure, the second acquisition unit 105 can also be arranged on the right side of the midpoint 302 of the reference line 301. This arrangement can also make the overlapping area 205 further outward, so as to be suitable for the robot 401 to perform edge obstacle avoidance.

[0070] like Figure 4 , Figure 5 As shown, in other embodiments, the second acquisition unit 105 is located on the reference line 301, and the angle between the third angle bisector 305 and the reference line 301 is an acute angle or an obtuse angle. This setting can also be understood as the lens of the second acquisition unit 105 tilting to the left or right. If the second acquisition unit 105 is located at the midpoint 302 of the reference line 301, then the lens of the second acquisition unit 105 is tilted to the left or right, and the overlapping area 205 is located on the left front side or the right front side of the total area (such as Figure 4 and Figure 5 As shown in FIG. 4 , this setting is conducive to the robot 401 to perform obstacle avoidance along the edge. The combination of the first area 201 and the second area 202 is the total area.

[0071] like Figure 8 As shown, if the second acquisition unit 105 is located on the left side of the reference line 301, then the lens of the second acquisition unit 105 is set to the right, which is suitable for the image acquisition system 101 to capture images of the object directly in front of the second acquisition unit 105. Fig. 9 As shown, if the second acquisition unit 105 is located on the right side of the reference line 301 , then the lens of the second acquisition unit 105 is set to face left, which is suitable for the image acquisition system 101 to acquire images of the object directly in front of the second acquisition unit 105 .

[0072] like Fig.10 , Fig.14 , Fig.15 and Fig.16 As shown, in some other embodiments, the second acquisition unit 105 may also be arranged outside the reference line 301 .

[0073] For example, see Fig.10 , the second acquisition unit 105, the first camera 103 and the second camera 104 can still be on the same straight line, but the second acquisition unit 105 is located on the left side of the first camera 103; this situation is equivalent to the center point of the second acquisition unit 105 being located on the extension line of the reference line 301. Figure 2 and Fig.11 By comparison, it can be seen that when the second acquisition unit 105 is oriented in the same direction, compared with the design in which the second acquisition unit 105 is located at the midpoint 302 of the reference line 301, the design in which the second acquisition unit 105 is located on the extension line of the reference line 301 is conducive to making the overlapping area 205 further outward, thereby facilitating the robot 401 to perform edge-to-edge obstacle avoidance. Similarly, in other embodiments not shown in the figure, the second acquisition unit 105 can also be located on the right side of the first camera 103, and the second acquisition unit 105, the first camera 103 and the second camera 104 can still be on the same straight line, which is also conducive to the robot 401 performing edge-to-edge obstacle avoidance.

[0074] based on Fig.10 The position of the second acquisition unit 105 shown in FIG. 1 is such that if the second acquisition unit 105 is tilted to the right, the overlapping area 205 is further outward (eg Fig.12 if the second acquisition unit 105 is tilted to the left, the overlapping area 205 is located directly in front of the midpoint 302, and the overlapping area 205 is larger.

[0075] like Figures 14 to 16 As shown in FIG. 1 , when the second acquisition unit 105 is disposed outside the reference line 301, the second acquisition unit 105 may also be located below the reference line 301. More specifically, the second acquisition unit 105 may be located directly below the midpoint 302 of the reference line 301 (eg, Fig.16 The second acquisition unit 105 may also be located directly below the first camera 103 or the second camera 104 (as shown in FIG. Fig.14 and Fig.15 As shown in Fig.17As shown, when the second acquisition unit 105 is located below the baseline 301, the second area 202 is at a lower position, and the second acquisition unit 105 can acquire clear images of objects near the ground, and the first area 201 is at a higher position, and the first acquisition unit 102 can acquire image information of farther objects.

[0076] It should be noted that the second acquisition unit 105 does not necessarily need to be located directly below the reference line 301. In other embodiments, the second acquisition unit 105 may also be located at the lower left or lower right of the reference line 301. Since the reference line 301 is a line connecting the first camera 103 and the second camera 104, the second acquisition unit 105 being located at the lower left of the reference line 301 means that the second acquisition unit 105 is located at the lower left of the first camera 103; the second acquisition unit 105 being located at the lower right of the reference line 301 means that the second acquisition unit 105 is located at the lower right of the second camera 104.

[0077] Similarly, in some other embodiments, the second acquisition unit 105 may be disposed above the reference line 301. More specifically, the second acquisition unit 105 may be located directly above the midpoint 302, or directly above the first camera 103 or the second camera 104. Fig.18 As shown, when the second acquisition unit 105 is located above the reference line 301, the second area 202 is at a higher position as a whole, and the second acquisition unit 105 is suitable for acquiring image information of distant objects; the first area 201 is at a lower position, and the distance between the first acquisition unit 102 and the ground is closer, so the first acquisition unit 102 can more accurately acquire image information of objects near the ground. It should be noted that the second acquisition unit 105 does not necessarily need to be located directly above the reference line 301. In other embodiments, the second acquisition unit 105 can also be located at the upper left or upper right of the reference line 301. The second acquisition unit 105 being located at the upper left of the reference line 301 means that the second acquisition unit 105 is located at the upper left of the first camera 103; the second acquisition unit 105 being located at the upper right of the reference line 301 means that the second acquisition unit 105 is located at the upper right of the second camera 104.

[0078] like Fig.19 and Fig. 20 As shown, in the case where the second acquisition unit 105 can be arranged outside the reference line 301, the second acquisition unit 105 can also be located in front of or behind the reference line 301, and when viewed from the front to the back, any one of the first camera 103 and the second camera 104 is staggered with the second acquisition unit 105. Fig. 20As shown, when the second acquisition unit 105 is located in front of the reference line 301, the second acquisition unit 105 is suitable for acquiring images of distant objects, and the first acquisition unit 102 is suitable for acquiring images of nearby objects. Fig.19 As shown, when the first acquisition unit 102 is located in front of the reference line 301, the first acquisition unit 102 is suitable for acquiring images of distant objects, and the second acquisition unit 105 is suitable for acquiring images of nearby objects.

[0079] The image acquisition system 101 in any of the above embodiments may be applied to a robot 401. The robot 401 may be a lawn mowing robot, a sweeping robot, a transporting robot, or the like. Fig.21 The robot 401 of the illustrated embodiment includes a housing 402, a driving wheel 403, a driving mechanism, and the above-mentioned image acquisition system 101. The first acquisition unit 102 and the second acquisition unit 105 are mounted on the outer surface of the housing 402, and the processor can be arranged inside the housing 402. The driving wheel 403 is connected to the housing 402, and the driving wheel 403 rotates under the drive of the driving mechanism, thereby moving the robot 401. The robot 401 may also include a controller, the processor is communicatively connected to the controller, and the controller is communicatively connected to the driving mechanism. The processor sends corresponding instructions to the controller according to the images acquired by the first acquisition unit 102 and the second acquisition unit 105, thereby controlling the movement of the robot 401.

[0080] In the description of the present invention, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

Claims

1. An image acquisition system, characterized in that: include: A first acquisition unit, whose image acquisition area is a first area, and the image acquired by the first acquisition unit is a first image; A second acquisition unit, whose image acquisition area is a second area, the image acquired by the second acquisition unit is a second image, and at least a part of the first area and at least a part of the second area overlap with each other to form an overlapping area; A processor, wherein the first acquisition unit and the second acquisition unit are both communicatively connected to the processor, and the processor is configured to: The processor determines the distance between the object in the overlapping area and the first acquisition unit according to the first image, and determines the attribute of the object in the overlapping area according to the second image; Alternatively, the processor determines the distance between the object in the overlapping area and the first acquisition unit according to the first image, and determines the attribute of the object in the overlapping area according to the first image and the second image; Alternatively, the processor determines the distance between the object in the overlapping area and the first acquisition unit based on the first image and the second image, and determines the attribute of the object in the overlapping area based on at least one of the first image and the second image.

2. The image acquisition system according to claim 1, characterized in that: The second acquisition unit is a multispectral sensor, and the second image at least includes an image of the object under non-visible light.

3. The image acquisition system according to claim 1, characterized in that: The first acquisition unit is a binocular camera, which includes a first camera and a second camera that are spaced apart from each other. The image acquisition area of ​​the first camera is the third area, and the image acquisition area of ​​the second camera is the fourth area. A portion of the third area overlaps with a portion of the fourth area, and the first area includes the third area and the fourth area.

4. The image acquisition system according to claim 3, characterized in that: A line connecting the first camera and the second camera is a reference line, and the second acquisition unit is located on the reference line.

5. The image acquisition system according to claim 3, characterized in that: A line connecting the first camera and the second camera is a reference line, and an angle bisector of a horizontal field of view angle of the second acquisition unit is perpendicular to the reference line.

6. The image acquisition system according to claim 3, characterized in that: The line connecting the first camera and the second camera is a reference line, and the angle between the angle bisector of the horizontal field of view angle of the second acquisition unit and the reference line is an acute angle or an obtuse angle.

7. The image acquisition system according to claim 3, characterized in that: A line connecting the first camera and the second camera is a reference line, the second acquisition unit is located outside a midpoint of the reference line, and the first camera, the second camera and the second acquisition unit are located on the same straight line.

8. The image acquisition system according to claim 3, characterized in that: A line connecting the first camera and the second camera is a reference line, and the second acquisition unit is located above or below the reference line.

9. The image acquisition system according to claim 3, characterized in that: A line connecting the first camera and the second camera is a reference line, and the second acquisition unit is located in front of or behind the reference line.

10. The image acquisition system according to claim 3, characterized in that: The horizontal field of view angle of the first camera is θ1, 50°≤θ1≤180°; And / or, the horizontal field of view angle of the second camera is θ2, 50°≤θ2≤180°; And / or, the vertical field of view angle of the first camera is θ3, 30°≤θ3≤150°; And / or, the vertical field of view angle of the second camera is θ4, 30°≤θ4≤150°.

11. The image acquisition system according to claim 3, characterized in that: The horizontal field angle of the second acquisition unit is θ5, 50°≤θ5≤150°; And / or, the vertical field of view angle of the second acquisition unit is θ6, 30°≤θ6≤150°.

12. The image acquisition system according to claim 1, characterized in that: The first acquisition unit and the second acquisition unit are both configured as multispectral sensors, the first image includes an image of the object under visible light and an image of the object under non-visible light, and the second image includes an image of the object under visible light and an image of the object under non-visible light.

13. A robot, characterized in that The invention comprises the image acquisition system as claimed in any one of claims 1 to 12.

Images