Depth camera and robot for identifying ground

Abstract

The utility model discloses a depth camera and robot for identifying the ground, and the camera is characterized in that the camera comprises an array laser which is used for projecting structured light spots; the first receiver is used for receiving a first reflection signal of the structured light spot; the second receiver is used for receiving a second reflection signal of the structured light spot; wherein the exposure parameters of the first receiver and the second receiver are different; and the processor is used for controlling the array laser, the first receiver and the second receiver to work synchronously, generating a first image according to the first reflected signal, generating a second image according to the second reflected signal, and fusing the first image and the second image into a third image. According to the utility model, the acquisition of a large-range depth image can be realized without complicated image processing in the later period.

Description

Technical Field

[0001] The utility model relates to the technical field of robots, and in particular to a depth camera for identifying the ground and a robot. Background Art

[0002] The difficulties faced by depth cameras when working at both close and long distances mainly include the following aspects:

[0003] 1. Light and exposure issues

[0004] Long-distance measurement: To achieve long-distance depth data acquisition, depth cameras typically need to increase the projector power within the eye-safe range. However, excessive power can lead to overexposure when acquiring data from close-range scenes, making it impossible to properly acquire close-range depth data.

[0005] Close-range measurement: When the power of the depth camera is reduced to meet the needs of acquiring close-range scene data, the detection distance is correspondingly reduced due to the reduction in power, resulting in the inability to obtain long-range depth data.

[0006] 2. Measurement Accuracy and Resolution

[0007] Increased errors at long distances: When a depth camera is measuring at long distances, the increased distance of light propagation and the complexity of the reflecting surface may cause increased errors, affecting measurement accuracy.

[0008] Resolution limitation: The resolution of the depth camera is limited. When the measurement distance is far, the actual spatial size corresponding to the unit pixel increases, which may lead to a decrease in the resolution of the depth information.

[0009] 3. Environmental adaptability

[0010] Light changes: Depth cameras are very sensitive to ambient lighting. Light changes can cause significant image deviations, which in turn affects the matching accuracy of depth measurements or even cause matching failures.

[0011] Complex environmental interference: In complex environments such as direct strong sunlight, large changes in ambient light, smoke or dust, the ranging performance of the depth camera may be affected, resulting in reduced ranging accuracy or malfunction.

[0012] Depth cameras in robots, especially those in low-profile environments like robot vacuums, often capture both distant and ground-level data. Because the ground is so close to the depth camera, the signal is too strong, easily causing overexposure. Further distance data can suffer from insufficient lighting, leading to the need for depth cameras specifically designed for low-altitude applications.

[0013] The disclosure of the above background technology content is only used to assist in understanding the inventive concept and technical solution of the utility model. It does not necessarily belong to the prior art of this patent application. In the absence of clear evidence that the above content has been disclosed on the filing date of this patent application, the above background technology should not be used to evaluate the novelty and creativity of this application. Utility Model Content

[0014] To this end, the utility model sets a transparent cover at the front end of the receiver, and processes the transparent cover to make the transmittance different, so that the ground and foreground can obtain appropriate exposure settings, thereby obtaining clear images, and without the need for complex subsequent image processing, it is possible to obtain a wide range of depth images.

[0015] In a first aspect, the present invention provides a depth camera for identifying the ground, characterized by comprising:

[0016] Array laser, used to project structured light spots;

[0017] a first receiver, configured to receive a first reflection signal of the structured light spot;

[0018] a second receiver, configured to receive a second reflection signal of the structured light spot; wherein the exposure parameters of the first receiver and the second receiver are different;

[0019] A processor is used to control the array laser, the first receiver, and the second receiver to operate synchronously, generate a first image according to the first reflected signal, generate a second image according to the second reflected signal, and fuse the first image and the second image into a third image.

[0020] Optionally, the depth camera for identifying the ground is characterized in that exposure parameters of the first receiver and the second receiver are different.

[0021] Optionally, the depth camera for identifying the ground is characterized in that the array laser, the first receiver and the second receiver are on the same straight line.

[0022] Optionally, the depth camera for identifying the ground is characterized in that the ratio of the first distance between the array laser and the first receiver to the second distance between the array laser and the second receiver is [0.8, 1.2].

[0023] Optionally, the depth camera for identifying the ground is characterized in that a line connecting the array laser, the first receiver and the second receiver is parallel to the ground.

[0024] Optionally, the depth camera for identifying the ground is characterized in that the FOV of the first receiver is the same as that of the second receiver.

[0025] Optionally, the depth camera for identifying the ground is characterized in that the first image and the second image have the same size.

[0026] Optionally, the depth camera for identifying the ground is characterized by further comprising:

[0027] The polarizer is located on the light incident side of the first receiver to filter out the influence of stray light and reduce the intensity of light reflected from the ground.

[0028] In a second aspect, the utility model provides a robot, characterized in that it comprises any one of the aforementioned depth cameras for identifying the ground.

[0029] Optionally, the robot is characterized in that the depth camera for identifying the ground is arranged in front of the robot, and the light projected forward and downward is irradiated on the ground.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] In the utility model, a first receiver and a second receiver are provided to respectively receive the reflected signals of the array laser, and different exposure parameters are set for the first receiver and the second receiver. The images generated by the first receiver and the second receiver are fused, so that one image is overexposed while the other image is clear, thereby obtaining a third image that can be clear in various scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without inventive work. By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, purposes and advantages of the present invention will become more apparent:

[0033] Figure 1 This is a schematic structural diagram of a depth camera for identifying the ground in an embodiment of the present utility model;

[0034] Figure 2 This is a schematic diagram of a shooting scene in an embodiment of the present utility model;

[0035] Figure 3 This is a schematic diagram of a shooting effect in an embodiment of the present utility model;

[0036] Figure 4 It is another structure schematic view of the depth camera for identifying ground in the embodiment of the utility model.

[0037] 1-array laser;

[0038] 2-first receiver;

[0039] 3-second receiver;

[0040] 4-processor;

[0041] 5-polarizer; DETAILED DESCRIPTION

[0042] The utility model will be described in detail below in combination with specific embodiments. The following embodiments will help the person skilled in the art to further understand the utility model, but do not limit the utility model in any form. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the utility model, a number of variations and improvements can be made. These all belong to the protection scope of the utility model.

[0043] The terms "first", "second", "third", "fourth" and the like in the description and claims of the utility model and the above-mentioned drawings (if any) are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the utility model described herein, for example, can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to the clearly listed steps or units, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0044] The depth camera for identifying ground provided by the embodiment of the utility model aims at solving the problems in the prior art.

[0045] The technical solutions of the utility model and how the technical solutions of the application solve the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the utility model will be described below in combination with the drawings.

[0046] The utility model sets a transparent cover at the front end of the receiver, and processes the transparent cover to make the transmittance different, so that the ground and the foreground can obtain appropriate exposure settings, thereby obtaining clear images, and achieving the acquisition of wide-range depth images without the need for complex post-processing of the image.

[0047] Figure 1 This is a schematic diagram of the structure of a depth camera for identifying the ground in an embodiment of the present utility model. Figure 1 As shown, in an embodiment of the present invention, a depth camera for identifying the ground includes:

[0048] Array laser 1, used for projecting structured light spots;

[0049] Specifically, the primary function of the laser array is to project structured light spots. These carefully designed structured light spots typically feature specific coded patterns, such as stripe structured light, coded structured light, or speckle structured light. Part of these patterns are projected onto the ground, while part is projected onto the target object above the ground. Once projected onto the ground or above the ground, the light spots will deform depending on the depth of the ground.

[0050] The first receiver 2 is configured to receive a first reflection signal of the structured light spot.

[0051] Specifically, the first receiver is used to receive the first reflection signals from the structured light spot projected by the array laser. These reflection signals contain depth information about the ground and objects on it. The first receiver's exposure parameters are pre-set to ensure that it can capture a clear image of the structured light spot reflected from the ground and objects on it.

[0052] The second receiver 3 is configured to receive a second reflection signal of the structured light spot.

[0053] Specifically, the exposure parameters of the first receiver and the second receiver are different. The second receiver is similar to the first receiver and is also used to receive the reflection signal of the structured light spot, but its exposure parameters are different from those of the first receiver. This difference enables the second receiver to capture image information different from that of the first receiver, thereby increasing the information redundancy and robustness of the depth camera. The exposure parameters of the second receiver are set independently and complement those of the first receiver. This setting ensures that under different lighting conditions or at different depths, at least one receiver can capture clear image information. Especially for depth cameras with a lower height, the ground occupies a relatively large area in the image, and the area is large. When objects on the ground obtain a clearer image, the ground is often overexposed and a clear image cannot be obtained. At this time, one of the first receiver and the second receiver is used to obtain an image of the ground, and the other is used to obtain an image of an object on the ground.

[0054] like Figure 2 As shown in , when the depth camera is positioned lower, the ground occupies a larger portion of the image. Figure 3 As shown, when a conventional laser projector is used for projection, the intensity of the reflected signal on the ground will be significantly greater than the intensity of the reflected signal in the distance.

[0055] Processor 4 is used to control the array laser, the first receiver and the second receiver to work synchronously, generate a first image according to the first reflection signal, generate a second image according to the second reflection signal, and fuse the first image and the second image into a third image.

[0056] Specifically, the processor is responsible for coordinating the synchronous work of various components and processing the received image information to generate the final depth image. The processor first controls the array laser to project the structured light spot, and synchronously triggers the first receiver and the second receiver to capture the image. Then, the processor generates the first image and the second image respectively based on the received first reflection signal and the second reflection signal. Then, the processor uses advanced algorithms to fuse the two images to eliminate noise, improve image quality and depth accuracy. Finally, the processor outputs the fused third image, which contains the three-dimensional spatial coordinates and depth information of the ground objects. It should be noted that the control of the first receiver and the second receiver by the processor is a conventional technical means, and the fusion of the first image and the second image is also an existing technology, and can be achieved using any fusion method in the existing technology.

[0057] In some embodiments, the first and second receivers have different exposure parameters. This design allows for different exposure parameters for different ground surfaces and target objects over a wide range of distances. The ground surface is closer to the depth camera and is prone to overexposure. Objects on the ground surface require a higher laser illumination intensity than the ground surface, and often create a scene where both the ground and the ground surface are difficult to see clearly at the same time. In a single exposure, when the ground objects are clear in the image, the ground surface is partially overexposed; when the ground surface is clear, the ground objects are underexposed. By setting the first and second receivers to different exposure parameters, respectively used to obtain information about the ground surface and objects on the ground surface, images with clear portions of each can be obtained. Furthermore, the image information captured by the two receivers differs in content. This difference provides more information redundancy for subsequent image processing and depth calculation, helping to improve the accuracy and robustness of depth images.

[0058] In some embodiments, the array laser, the first receiver, and the second receiver are on the same straight line. This embodiment makes the viewing angles of the first receiver and the second receiver closer, and the received reflected signals are more consistent, which can better perform fusion.

[0059] In some embodiments, a ratio of a first distance between the array laser and the first receiver to a second distance between the array laser and the second receiver is in the range [0.8, 1.2]. This embodiment allows the viewing angles of the first and second receivers to be closer, resulting in more consistent received reflected signals and better fusion.

[0060] In some embodiments, the line connecting the array laser, the first receiver, and the second receiver is parallel to the ground. This embodiment ensures that the ground is horizontal in both the first and second images, facilitating post-processing and simplifying the setup of the first and second receivers. This embodiment also ensures that the viewing angles of the first and second receivers are closer, resulting in more consistent received reflected signals and enabling better fusion.

[0061] In some embodiments, the first receiver and the second receiver have the same FOV. In this embodiment, the same FOV of the first receiver and the second receiver can better align the first image with the second image, allowing subsequent fusion to directly replace unclear image portions, reducing subsequent processing and improving efficiency.

[0062] In some embodiments, the first image and the second image have the same size. The same size of the first and second images can minimize the computational effort involved in fusing the third image, thereby quickly obtaining a clear third image and enabling clear images of both distant ground and distant objects.

[0063] In some embodiments, it also includes: a polarizer 5, which is located on the light incident side of the first receiver to filter out the influence of stray light and reduce the intensity of the reflected light from the ground. The polarizer is a thin film that can select polarized light of a specific frequency. Its working principle is to use the structure of the polarizer to absorb the component of light vibration in a specific direction, so that the light passing through the polarizer only contains the component of vibration in a specific direction. In a depth camera, the polarizer can filter out stray light that is inconsistent with the polarization direction, thereby reducing noise and interference in the image and improving the clarity and contrast of the image. The light reflected from the ground is usually partially linearly polarized, and the polarizer can absorb the light component perpendicular to the polarization direction, thereby reducing the intensity of the reflected light. This helps to reduce the impact of ground reflection on the image, especially under strong light conditions, and can reduce reflections and glare in the image, making the image more realistic and clear.

[0064] The present invention also provides an embodiment of a robot. It should be noted that the robot in this embodiment is only exemplary, and those skilled in the art will understand that all types of ground-moving robots can be applied to the present invention.

[0065] The robot integrates the depth camera in the aforementioned embodiments that can recognize the ground with high precision, high stability and strong environmental adaptability. Through the depth camera, the robot can capture and analyze the three-dimensional information of the ground environment in real time, providing key data support for the robot's navigation, obstacle avoidance, path planning and other tasks.

[0066] The depth camera can accurately measure the distance between the robot and the ground obstacles, helping the robot achieve high-precision navigation. In complex environments, the robot can choose the optimal path according to the depth information to avoid collisions and ensure safe driving.

[0067] By analyzing the three-dimensional images captured by the depth camera, the robot can identify and avoid obstacles on the ground in real time. This allows the robot to maintain high efficiency and stable operation in complex and variable environments.

[0068] The depth camera has strong environmental adaptability and can work stably on different light and different material ground. This allows the robot to maintain excellent performance in various application scenarios.

[0069] Combined with the three-dimensional information captured by the depth camera, the robot can realize autonomous positioning and construct an accurate environmental map. This provides an important reference for the subsequent task execution of the robot, improving the intelligence level of the robot.

[0070] In the field of industrial automation, the robot can use the depth camera to achieve precise positioning, material handling, quality detection and other tasks. This helps to improve production efficiency, reduce labor costs and promote the intelligent upgrading of industrial manufacturing.

[0071] In the service field, the robot can use the depth camera to achieve intelligent navigation, path planning, human-computer interaction and other functions. This allows the robot to better adapt to various service scenarios and provide users with more convenient and efficient service experience.

[0072] In the field of agriculture, the robot can use the depth camera to achieve precise fertilization, weeding and harvesting. This helps to improve agricultural production efficiency, reduce pesticide use and promote the sustainable development of agricultural production.

[0073] In the field of exploration and rescue, the robot can use the depth camera to navigate and avoid obstacles in complex environments. This helps to protect the safety of rescue personnel, improve rescue efficiency and provide strong support for rescue operations.

[0074] In the smart home sector, robots use depth cameras to capture and analyze three-dimensional information about the ground environment, enabling high-precision navigation and positioning. This high-precision navigation and positioning capability allows robots to navigate freely in the complex and ever-changing environments of the home, avoiding collisions with obstacles such as furniture and walls, ensuring smooth operation, including cleaning.

[0075] The depth camera for identifying the ground is arranged in front of the robot, and projects light forward and downward onto the ground.

[0076] In summary, robots equipped with the above-mentioned ground depth recognition camera have advantages such as high-precision navigation, intelligent obstacle avoidance, and strong environmental adaptability. They have broad application prospects in industrial automation, service robots, agricultural robots, exploration and rescue, and other fields.

[0077] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. The above description of the disclosed embodiments enables professionals and technicians in this field to implement or use the utility model. Various modifications to these embodiments will be obvious to professionals and technicians in this field. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the utility model. Therefore, the utility model will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0078] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art may make various modifications or variations within the scope of the claims, which do not affect the essence of the present invention.

Claims

1. A depth camera for identifying the ground, characterized in that: include: Array laser, used to project structured light spots; a first receiver, configured to receive a first reflection signal of the structured light spot; a second receiver, configured to receive a second reflection signal of the structured light spot; wherein the exposure parameters of the first receiver and the second receiver are different; A processor is used to control the array laser, the first receiver, and the second receiver to operate synchronously, generate a first image according to the first reflected signal, generate a second image according to the second reflected signal, and fuse the first image and the second image into a third image.

2. The depth camera for ground recognition according to claim 1, characterized in that: The first receiver and the second receiver have different exposure parameters.

3. The depth camera for ground recognition according to claim 1, characterized in that: The array laser, the first receiver and the second receiver are on the same straight line.

4. The depth camera for ground recognition according to claim 3, characterized in that: A ratio of a first distance between the array laser and the first receiver to a second distance between the array laser and the second receiver is in the range of [0.8, 1.2].

5. The depth camera for identifying the ground according to claim 3, characterized in that: A line connecting the array laser, the first receiver, and the second receiver is parallel to the ground.

6. The depth camera for identifying the ground according to claim 1, characterized in that: The FOV of the first receiver is the same as that of the second receiver.

7. The depth camera for ground recognition according to claim 1, characterized in that: The first image and the second image have the same size.

8. The depth camera for ground recognition according to claim 1, characterized in that: Also includes: The polarizer is located on the light incident side of the first receiver to filter out the influence of stray light and reduce the intensity of light reflected from the ground.

9. A robot, characterized in that: A depth camera for identifying the ground comprising the device according to any one of claims 1 to 8.

10. A robot according to claim 9, characterized in that: The depth camera for identifying the ground is arranged in front of the robot, and projects light forward and downward onto the ground.

Images