Positioning method and system, AGV and electronic device

Abstract

The application relates to the technical field of visual positioning, and provides a positioning method, a positioning system, an AGV (Automatic Guided Vehicle) and electronic equipment, wherein the positioning method is used for positioning a measured object in a target area, a monitoring camera is arranged in the target area, the positioning method comprises the following steps: acquiring a to-be-processed image containing the measured object, which is shot by the to-be-processed monitoring camera; determining depth information of the measured object and the to-be-processed monitoring camera based on the to-be-processed image; and determining position information of the measured object in the target area based on the depth information and a pose of the to-be-processed monitoring camera in a target area coordinate system. The application is used to solve the defects of the positioning method commonly used in the prior art, such as complicated construction, repeated arrangement of markers, and incapability of positioning in a degenerated scene, and realizes global positioning of the measured object in the target area based on the monitoring camera arranged in the target area, so that the AGV or materials can be positioned in a workshop or other scene.

Description

Technical Field

[0001] This invention relates to the field of visual positioning technology, and in particular to a positioning method, system, AGV (Automated Guided Vehicle) and electronic equipment. Background Technology

[0002] AGVs (Automated Guided Vehicles) are playing an increasingly important role in manufacturing and other fields due to their high efficiency, flexibility, and ability to reduce labor costs.

[0003] Positioning is one of the fundamental factors that enables AGVs to perform their functions. Depending on the application scenario of the AGV, commonly used positioning methods include: QR code positioning, reflective column positioning, magnetic positioning, color strip positioning, and laser SLAM (simultaneous localization and mapping) positioning.

[0004] However, QR code positioning, reflective column positioning, and color strip positioning all require the initial deployment of QR codes, reflective columns, or color strips, which is cumbersome and consumes a lot of manpower and resources. They also require frequent maintenance during use and have poor flexibility, requiring re-deployment if the route is modified. Magnetic positioning requires trenching in the ground, damaging the original ground, and also suffers from poor flexibility, requiring the re-deployment of magnetic tracks or magnetic nails after the route is modified. As for laser SLAM positioning, it has high requirements for the rate of environmental change, generally requiring that there cannot be significant environmental changes. In addition, there is a possibility that positioning may fail in degraded scenarios such as long corridors. Summary of the Invention

[0005] This invention provides a positioning method, system, AGV vehicle, and electronic device to solve the shortcomings of commonly used positioning methods in the prior art, such as cumbersome construction, repeated placement of markers, or inability to locate in degraded scenes. It realizes global positioning of the measured object in the target area based on the monitoring cameras deployed in the target area, which facilitates the positioning of AGV vehicles or materials in workshops and factories.

[0006] This invention provides a positioning method for locating a measured object within a target area, wherein surveillance cameras are arranged in the target area, and each location in the target area is covered by at least a preset number of surveillance cameras. The positioning method includes:

[0007] Acquire an image to be processed captured by a surveillance camera, wherein the surveillance camera to be processed is a surveillance camera that captures the object under test, and the image to be processed is an image containing the object under test;

[0008] Based on the image to be processed, determine the depth information of the object under test and the surveillance camera to be processed;

[0009] Based on the depth information and the pose of the surveillance camera to be processed in the target area coordinate system, the position information of the object under test in the target area is determined.

[0010] The positioning method according to the present invention further includes:

[0011] Based on the image to be processed, determine the heading angle information of the object under test;

[0012] Based on the heading angle information and the position information of the object under test, the pose of the object under test is determined.

[0013] According to the positioning method of the present invention, determining the heading angle information of the measured object based on the image to be processed includes:

[0014] The position information of the object under test within the target area, and the position information of the preset contour edge points of the object under test, wherein the preset contour edge points include at least two points, and are located at the front end and rear end of the object under test respectively;

[0015] The heading angle information is determined based on the position information of the preset contour edge points.

[0016] The positioning method according to the present invention further includes:

[0017] Obtain a location request for the object under test;

[0018] In response to the positioning request, an image acquisition command is sent to the monitoring camera, and all objects to be measured within the target area are searched.

[0019] The features extracted from each of the objects to be tested are matched with the preset features of the objects to be tested, and after a successful match, a preset number of the surveillance cameras to be processed are determined from the surveillance cameras.

[0020] The positioning method according to the present invention further includes:

[0021] The pose of the object under test, determined based on the image to be processed, is iteratively optimized.

[0022] The pose of the object under test, determined based on the iterative optimization, is taken as the final pose of the object under test.

[0023] The present invention also provides a positioning system, comprising: an image acquisition module, a communication module, and a processing module;

[0024] The image acquisition module is a surveillance camera arranged in the target area, used to capture images in the target area, and each location in the target area is covered by at least a preset number of the surveillance cameras;

[0025] The communication module is connected to the monitoring camera and the processing module respectively, and is used for information interaction between the monitoring camera and the processing module;

[0026] The processing module is used to acquire the image to be processed captured by the surveillance camera, determine the depth information of the object under test and the surveillance camera under test based on the image to be processed, and determine the position information of the object under test in the target area based on the depth information and the pose of the surveillance camera under test in the target area coordinate system. The surveillance camera under test is the surveillance camera that captured the object under test, and the image to be processed is an image containing the object under test.

[0027] According to the positioning system of the present invention, the monitoring camera is a binocular camera and / or an RGBD camera.

[0028] The present invention also provides an AGV trolley positioned by the positioning method described above.

[0029] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the positioning method as described above.

[0030] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the positioning method as described above.

[0031] This invention provides a positioning method, system, AGV (Automated Guided Vehicle), and electronic equipment. By using surveillance cameras deployed in target areas such as workshops and factories, it acquires images containing the object to be measured. Then, based on the image to be processed, it determines the depth information between the object and the surveillance camera that captured the image. Finally, based on the depth information of the object and the surveillance camera and the pose of the surveillance camera in the target area coordinate system, it determines the position information of the object within the target area. This achieves global positioning of AGVs and materials using existing surveillance cameras in target areas such as workshops and factories. This technology enables the positioning of the measured material using a fixed-pose and global vision system, making the positioning less affected by the environment and eliminating concerns about jitter and other issues. It also avoids the hassle of setting up QR codes, reflective pillars, and other markings, saving manpower and resources. Furthermore, it can locate the measured object in degraded environments such as long corridors. Therefore, it can be used to fuse this global positioning when the self-positioning of moving measured objects such as AGVs fails, thereby increasing the stability and robustness of the AGV positioning system. It can also be used to locate fixed-position measured objects such as materials for navigation of AGVs and other transport vehicles. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0033] Figure 1 This is a flowchart illustrating the positioning method provided in an embodiment of the present invention;

[0034] Figure 2 This is a flowchart illustrating the positioning of AGV vehicle A using the positioning method provided in this embodiment of the invention.

[0035] Figure 3 This is a schematic diagram of the positioning system provided in an embodiment of the present invention;

[0036] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0038] The following is combined with Figure 1 and Figure 2 The present invention describes a positioning method that can be executed by software and / or hardware in electronic devices such as computers, tablets, and mobile phones.

[0039] The positioning method provided in this embodiment of the invention is used to locate a measured object within a target area, wherein a surveillance camera is arranged in the target area, and each location in the target area is covered by at least a preset number of the surveillance cameras.

[0040] Understandably, for target areas such as workshops and factories, surveillance cameras are generally placed on the ceiling of the workshop or factory. Since the monitoring area of ​​each surveillance camera is limited, multiple surveillance cameras are deployed to achieve full coverage of the target area by overlapping the monitoring areas of each surveillance camera.

[0041] Based on this, the positioning of AGVs, materials, etc., can be achieved through surveillance cameras already deployed in the target area. This not only enables global positioning of the measured objects within the target area based on vision, but also avoids the hassle of deploying QR codes, color strips, etc. Furthermore, by using images captured by surveillance cameras for global positioning of the measured objects, the problem of being unable to locate objects in degraded environments can also be avoided.

[0042] Furthermore, the preset number can be flexibly set according to the actual required positioning accuracy, etc. It is known that the more images of the object being measured taken from different angles, the more accurate the position information of the object being measured determined by the images. However, the cost will also increase as the number of surveillance cameras increases. Therefore, in the positioning method provided by the embodiments of the present invention, the preset number is preferably set to 3. That is, by adjusting the shooting angle of each surveillance camera already arranged in the target area, each position in the target area is covered by the shooting area of ​​at least 3 surveillance cameras at the same time. Moreover, the 3 surveillance cameras can preferably shoot from different angles, thereby reducing the cost of using the positioning method provided by the embodiments of the present invention and improving the positioning accuracy of the object being measured.

[0043] like Figure 1 As shown, the positioning method provided in this embodiment of the invention includes the following steps:

[0044] 101. Obtain the images captured by the surveillance cameras to be processed;

[0045] Specifically, the surveillance camera to be processed is the surveillance camera that has captured the object under test, the image to be processed is an image containing the object under test, and the number of surveillance cameras that can capture the object under test is at least a preset number. Therefore, the images to be processed that can be obtained include at least a preset number of images.

[0046] 102. Based on the image to be processed, determine the depth information of the object under test and the surveillance camera to be processed;

[0047] Specifically, to ensure monitoring effectiveness, surveillance cameras are installed at a relatively high position, such as on the top or near the top of walls in target areas like workshops or factories. Therefore, the image to be processed, captured by the surveillance camera, is a top-down view of the object being measured, taken from above. By analyzing the image, the distance between the object and the surveillance camera can be obtained, i.e., the depth information of the object relative to the surveillance camera.

[0048] 103. Based on the depth information and the pose of the surveillance camera to be processed in the target area coordinate system, determine the position information of the measured object in the target area.

[0049] Specifically, taking the workshop as the target area as an example, after the surveillance camera is installed, the position of the surveillance camera in the workshop can be obtained through the workshop construction drawings and survey results, that is, the transformation relationship between the coordinate system of the surveillance camera and the coordinate system of the workshop.

[0050] More specifically, given the distance between the object being measured and the surveillance camera to be processed, as well as the location of the surveillance camera to be processed within the target area, the location of the object being measured within the target area can be further determined, thus achieving the localization of the object being measured.

[0051] The positioning method provided in this invention utilizes images of AGV vehicles, materials, and other objects captured by existing surveillance cameras within the target area. Only the shooting angle of the surveillance cameras monitoring the target area needs adjustment, without requiring any site modifications, to achieve global positioning of the objects. This method is easy to implement, has low operating costs, and the surveillance cameras, being positioned high, are less prone to damage, reducing maintenance costs. Furthermore, since the surveillance cameras can achieve full coverage of the target area, local changes within the target area have minimal impact on positioning. Compared to laser SLAM positioning, it reduces the susceptibility to environmental changes; and compared to QR code positioning and reflective column positioning, it avoids the hassle of rearranging markers.

[0052] Furthermore, the positioning method provided in this embodiment of the invention analyzes the images captured by the surveillance camera to locate the object under test, avoiding the need to install a positioning system on the object under test. Since the position of the surveillance camera in the target area is fixed, it is less affected by the environment and there is no need to worry about problems such as shaking, thus ensuring the consistency and stability of positioning. Moreover, when there are a large number of objects under test in the target area, the number of visual positioning sensors can be reduced, thereby further reducing the positioning cost.

[0053] Taking a workshop or factory as the target area and an AGV (Automated Guided Vehicle) moving within the workshop or factory as an example, in one embodiment, the AGV can be stopped after its positioning is lost during operation. The positioning method provided by this invention can be used to locate the AGV and send its pose to the AGV for fusion positioning, thereby increasing the stability and robustness of the AGV positioning.

[0054] In another embodiment, when the location of the target point of the AGV, such as the location of the pallet docking with the AGV, is unknown, the positioning method provided in this embodiment of the invention can be used to determine the location of the target point, and then the location of the target point can be sent to the AGV, thereby making production more flexible.

[0055] Based on the above embodiments, the positioning method provided by the present invention further includes:

[0056] Based on the image to be processed, determine the heading angle information of the object under test;

[0057] Based on the heading angle information and the position information of the object under test, the pose of the object under test is determined.

[0058] Understandably, for AGVs and other objects moving within a target area, after determining the position information of the object, it is also necessary to determine the direction of movement of the object.

[0059] Specifically, the heading angle information of the object under test can be determined through the image to be processed. By combining the heading angle information and the position information, the pose of the object under test can be determined, which facilitates subsequent fusion or scheduling.

[0060] Based on the above embodiments, determining the heading angle information of the measured object based on the image to be processed includes:

[0061] Based on the position information of the object under test within the target area, the position information of the preset contour edge points of the object under test is determined. The preset contour edge points include at least two points, which are located at the front end and rear end of the object under test, respectively.

[0062] The heading angle information is determined based on the position information of the preset contour edge points.

[0063] Specifically, by extracting the contour features of the object under test from the image to be processed, and then determining the heading angle information of the object under test based on the position information of the contour features.

[0064] More specifically, taking the AGV (Automated Guided Vehicle) as an example, suppose the preset contour edge points are located at two positions: 45° to the left front and 45° to the right rear of the AGV's center point. After determining the AGV's position information, since the poses of the AGV's center point and contour edge points are fixed, geometric methods can be used to calculate the position information of the preset contour edge points from the AGV's center point. Then, using the position information of the preset contour edge points, geometric methods can be used to determine the AGV's heading angle. That is, by extracting the contour features of the AGV to distinguish the head and tail of the AGV, and then determining the AGV's heading angle based on the orientation of the head and tail.

[0065] Based on the above embodiments, the positioning method provided by the present invention further includes:

[0066] Obtain a location request for the object under test;

[0067] In response to the positioning request, an image acquisition command is sent to the monitoring camera, and all objects to be measured within the target area are searched.

[0068] The features extracted from each of the objects to be tested are matched with the preset features of the objects to be tested, and after a successful match, a preset number of the surveillance cameras to be processed are determined from the surveillance cameras.

[0069] It is understandable that for target areas such as workshops and factories, there are usually more than one AGV vehicle or other object being measured. For AGV vehicles of the same model, their appearance is the same, and it is difficult to distinguish between different AGV vehicles through images.

[0070] Specifically, by setting different preset features on each object to be measured within the target area, when a positioning request for a specific object is received, the features of all objects to be measured found within the target area can be compared with the preset features of the object to be located to determine whether the object to be located is within the target area. If the object to be located is determined to be within the target area, a preset number of monitoring cameras to be processed are further identified, i.e., monitoring cameras that can capture images of the object to be located, so that the object to be located can be located subsequently by acquiring the images captured by the monitoring cameras to be processed.

[0071] More specifically, by sending image acquisition instructions to the surveillance camera only after receiving a positioning request for the object under test, the surveillance camera can be used for normal monitoring when there is no positioning requirement for the object under test, thereby ensuring reliable monitoring of the target area.

[0072] Furthermore, the preset features set for each object to be tested can be implemented in various ways, such as setting the objects to be tested to different colors, placing different QR codes or reflective markings on each object to be tested.

[0073] Taking an AGV (Automated Guided Vehicle) as the object being measured, considering that the AGV may place materials on top for lifting or other operations, marking the top of the AGV would be inconvenient for distinguishing between different AGVs. In one embodiment, by installing lights on the AGVs, different colored lights are projected onto the ground in the direction of the AGV's movement when the lights are turned on, or the lights form the AGV's number, thus facilitating the differentiation of each AGV.

[0074] Based on the above embodiments, the positioning method provided by the present invention further includes:

[0075] The pose of the object under test, determined based on the image to be processed, is iteratively optimized.

[0076] The pose of the object under test, determined based on the iterative optimization, is taken as the final pose of the object under test.

[0077] Specifically, backend optimization is performed using the determined pose of the object under test and the pose of the surveillance camera used to capture images for determining the pose of the object under test, in order to obtain the final position information of the object under test, effectively ensuring the accuracy of the positioning results.

[0078] In one embodiment, based on the pose of the camera to be processed in the target area coordinate system, the intrinsic parameters of the camera to be processed and the corresponding distortion model, the position information of the object under test in the target area coordinate system, and the image to be processed, the final position information of the object under test in the target area coordinate system can be obtained by back-end iterative optimization through Bundle Adjustment.

[0079] In another embodiment, the specific process of locating AGV A using the positioning method provided in the above embodiments of the present invention is as follows: Figure 2 As shown, it includes the following steps:

[0080] 201. Determine the pose of the surveillance camera in the target area coordinate system;

[0081] 202. Obtain the positioning request for AGV vehicle A;

[0082] 203. Send image acquisition instructions to the monitoring camera and search for all AGVs within the target area;

[0083] 204. Extract the features of all the searched AGVs and match them with the preset features of AGV A;

[0084] 205. Determine if the match was successful; if yes, proceed to step 206; if no, return to step 202.

[0085] 206. Identify the surveillance camera to be processed, and have the camera acquire the image to be processed;

[0086] 207. Determine the depth information of the monitoring camera and AGV A based on the image to be processed;

[0087] 208. Based on depth information and the pose of the monitoring camera to be processed in the target area coordinate system, determine the position information of AGV A;

[0088] 209. Determine the position information of the preset contour edge points of AGV A;

[0089] 210. Determine the heading angle information of AGV A;

[0090] 211. Determine the position and orientation of AGV A;

[0091] 212. Perform backend iterative optimization based on Bundle Adjustment;

[0092] 213. Send the final pose of AGV A, which has been determined by backend iterative optimization, to AGV A.

[0093] Depend on Figure 2 As shown, when using the positioning method provided in this embodiment of the invention to position AGVs, there is no need to deploy a positioning system on the AGV. Instead, the image of the AGV is obtained by a monitoring camera fixedly installed in the target area such as the factory workshop, so as to determine the pose of the AGV. This ensures the consistency and stability of the positioning. In addition, for scenarios with a large number of AGVs, the number of visual positioning sensors can be reduced, thereby reducing the positioning cost. At the same time, the accuracy of the positioning results is ensured by combining front-end positioning and back-end optimization.

[0094] The following describes a positioning system provided by the present invention. The positioning system described below and the positioning method described above can be referred to in correspondence.

[0095] like Figure 3As shown, the positioning system provided by the present invention includes: an image acquisition module 310, a communication module 320, and a processing module 330;

[0096] The image acquisition module 310 is a surveillance camera arranged in the target area, used to capture images in the target area, and each location in the target area is covered by at least a preset number of the surveillance cameras;

[0097] The communication module 320 is connected to the monitoring camera and the processing module 330 respectively, and is used for information interaction between the monitoring camera and the processing module 330;

[0098] The processing module 330 is used to acquire an image to be processed captured by a surveillance camera, determine the depth information of the object under test and the surveillance camera under test based on the image to be processed, and determine the position information of the object under test in the target area based on the depth information and the pose of the surveillance camera under test in the target area coordinate system. The surveillance camera under test is the surveillance camera that captured the object under test, and the image to be processed is an image containing the object under test.

[0099] Specifically, the communication module is responsible for information exchange between the image acquisition module and the processing module. The image acquisition module and the processing module can communicate via USB. Furthermore, when the object under test is an object that needs to operate through positioning, such as an AGV or other robot, the communication module can also be responsible for communication between the object under test and the processing module. For example, the object under test and the processing module can communicate via network, such as 4G or 5G. In target areas with a small working area and poor network signal, radio, Bluetooth, and other radio transmission methods can be used for communication.

[0100] The positioning system provided in this invention acquires images containing the object to be measured using surveillance cameras deployed in target areas such as workshops and factories. Based on these images, it determines the depth information between the object and the surveillance camera that captured the image. Finally, based on the depth information of the object and the surveillance camera and the pose of the surveillance camera in the target area coordinate system, it determines the position information of the object within the target area. This achieves global positioning of AGVs and materials using existing surveillance cameras in target areas such as workshops and factories, thus realizing the use of fixed-line surveillance cameras. The global vision system positions the measured material with a fixed orientation, making the positioning less affected by the environment and eliminating concerns about jitter. It also avoids the hassle of setting up QR codes, reflective pillars, and other markings, saving manpower and resources. Furthermore, it can locate the measured object in degraded scenarios such as long corridors. Therefore, it can be used to integrate the global positioning when the self-positioning of moving measured objects such as AGVs fails, thereby increasing the stability and robustness of the positioning system for moving measured objects such as AGVs. It can also be used to locate measured objects in fixed positions, such as materials, to navigate the transportation of AGVs and other transport vehicles.

[0101] Based on the above embodiments, the surveillance camera is a binocular camera and / or an RGBD camera.

[0102] Specifically, by setting the surveillance camera to a binocular camera and / or an RGBD camera, it is easier to accurately determine the depth information between the object being measured and the surveillance camera.

[0103] Optionally, the processing module 330 is also used for:

[0104] Based on the image to be processed, determine the heading angle information of the object under test;

[0105] Based on the heading angle information and the position information of the object under test, the pose of the object under test is determined.

[0106] Alternatively, the processing module 330 is more specifically used for:

[0107] Based on the position information of the object under test within the target area, the position information of the preset contour edge points of the object under test is determined. The preset contour edge points include at least two points, which are located at the front end and rear end of the object under test, respectively.

[0108] The heading angle information is determined based on the position information of the preset contour edge points.

[0109] Optionally, the processing module 330 is also used for:

[0110] Obtain a location request for the object under test;

[0111] In response to the positioning request, an image acquisition command is sent to the monitoring camera, and all objects to be measured within the target area are searched.

[0112] The features extracted from each of the objects to be tested are matched with the preset features of the objects to be tested, and after a successful match, a preset number of the surveillance cameras to be processed are determined from the surveillance cameras.

[0113] Optionally, the processing module 330 is also used for:

[0114] The pose of the object under test, determined based on the image to be processed, is iteratively optimized.

[0115] The pose of the object under test, determined based on the iterative optimization, is taken as the final pose of the object under test.

[0116] This invention also provides an AGV (Automated Guided Vehicle) that is positioned using the positioning method described in any of the above embodiments.

[0117] It is understood that the AGV vehicle that uses the positioning method described in any of the above embodiments for positioning has all the advantages and technical effects of the positioning method described in any of the above embodiments, and will not be repeated here.

[0118] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a positioning method for locating a measured object within a target area. The target area is equipped with surveillance cameras, and each location within the target area is covered by at least a preset number of surveillance cameras. The positioning method includes: acquiring a to-be-processed image captured by a surveillance camera that has captured the measured object; determining depth information between the measured object and the surveillance camera based on the to-be-processed image; and determining the position information of the measured object within the target area based on the depth information and the pose of the surveillance camera in the target area coordinate system.

[0119] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to execute a positioning method provided by the above methods for positioning a measured object within a target area, wherein a surveillance camera is arranged in the target area, and each position in the target area is covered by at least a preset number of the surveillance cameras, the positioning method comprising: acquiring a to-be-processed image captured by a surveillance camera to be processed, the surveillance camera to be processed being a surveillance camera that captures the measured object, the image to be processed being an image containing the measured object; determining depth information of the measured object and the surveillance camera to be processed based on the image to be processed; and determining position information of the measured object within the target area based on the depth information and the pose of the surveillance camera to be processed in the coordinate system of the target area.

[0121] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements a positioning method for locating a measured object within a target area. The target area is provided with surveillance cameras, and each location within the target area is covered by at least a preset number of the surveillance cameras. The positioning method includes: acquiring a to-be-processed image captured by a surveillance camera, wherein the surveillance camera to be processed is one that captures the measured object, and the to-be-processed image is an image containing the measured object; determining depth information of the measured object and the surveillance camera to be processed based on the to-be-processed image; and determining the position information of the measured object within the target area based on the depth information and the pose of the surveillance camera to be processed in the coordinate system of the target area.

[0122] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0123] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A positioning method, characterized in that, For locating a measured object within a target area, wherein multiple surveillance cameras are arranged in the target area, and each location in the target area is covered by at least a preset number of surveillance cameras from different angles, the positioning method includes: Obtain a positioning request for the object under test; in response to the positioning request, send an image acquisition command to the monitoring camera and search for all objects under test within the target area; match the features extracted from each object under test with the preset features of the object under test, and after a successful match, determine a preset number of monitoring cameras to be processed from the monitoring cameras, wherein the monitoring cameras to be processed are the monitoring cameras that have captured images of the object under test. Acquire the image to be processed captured by the surveillance camera, wherein the image to be processed is an image containing the object under test; Based on the image to be processed, determine the depth information of the object under test and the surveillance camera to be processed; Based on the depth information and the pose of the surveillance camera to be processed in the target area coordinate system, the position information of the measured object in the target area is determined; Based on the image to be processed, the heading angle information of the object under test is determined; based on the heading angle information and the position information of the object under test, the pose of the object under test is determined. The pose of the object under test, determined based on the image to be processed, is iteratively optimized; the pose of the object under test, determined based on the iterative optimization, is taken as the final pose of the object under test.

2. The positioning method according to claim 1, characterized in that, Determining the heading angle information of the measured object based on the image to be processed includes: Based on the position information of the object under test within the target area, the position information of the preset contour edge points of the object under test is determined. The preset contour edge points include at least two points, which are located at the front end and rear end of the object under test, respectively. The heading angle information is determined based on the position information of the preset contour edge points.

3. A positioning system, characterized in that, include: Image acquisition module, communication module, and processing module; The image acquisition module consists of multiple surveillance cameras arranged in the target area to capture images within the target area, and each location within the target area is covered by at least a preset number of surveillance cameras from different angles; The communication module is connected to the monitoring camera and the processing module respectively, and is used for information interaction between the monitoring camera and the processing module; The processing module is used to acquire and respond to positioning requests for the object under test, send image acquisition instructions to the monitoring camera, and search for all objects under test within the target area. It matches the features extracted from each object under test with preset features of the object under test, and after successful matching, determines a preset number of monitoring cameras to be processed. The processing module is also used to acquire images to be processed captured by the monitoring cameras to be processed, determine the depth information of the object under test and the monitoring camera to be processed, as well as the heading angle information of the object under test, based on the images. Based on the depth information and the pose of the monitoring camera to be processed in the target area coordinate system, it determines the position information of the object under test within the target area. Based on the heading angle information and the position information of the object under test, it determines the pose of the object under test, iteratively optimizes the pose of the object under test, and uses the iteratively optimized pose of the object under test as the final pose of the object under test. The monitoring camera to be processed is the monitoring camera that captured the object under test, and the image to be processed is an image containing the object under test.

4. The positioning system according to claim 3, characterized in that, The surveillance camera is a binocular camera and / or an RGBD camera.

5. An AGV (Automated Guided Vehicle) trolley, characterized in that, Positioning is performed using the positioning method described in claim 1 or 2.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the positioning method as described in claim 1 or 2.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the positioning method as described in claim 1 or 2.

Images