Monocular Image-Based Path Navigation Method, Apparatus, Device, and Storage Medium

Abstract

The present invention relates to the technical field of remote path navigation, and particularly to a path navigation method, device, equipment and storage medium based on a monocular image. The method acquires an image of the current pose of a moving vehicle collected by a camera, and determines a path planning area in the image according to the movable range of the moving vehicle; and generates a navigation path from the moving vehicle to the target position in the path planning area according to the point coordinates of the target position in the image coordinate system and a path planning algorithm. Through the above method, the path planning distance of the user is limited by the path planning area, so that the actual moving distance of the moving vehicle is within an acceptable error range, avoiding excessive yaw of the moving vehicle due to excessive error; and the navigation path is directly generated in the path planning area in the image through the path planning algorithm, reducing the calculation amount, accelerating the path calculation speed, and making the path display more convenient.

Description

Technical Field

[0001] The present invention relates to the technical field of remote path navigation, and particularly to a path navigation method, device, equipment and storage medium based on a monocular image. Background Art

[0002] In remote vehicle dispatching, an operator generates a navigation path by clicking on the road surface in an image, and a path tracking algorithm enables the vehicle to automatically move to near the target point, achieving semi-automatic movement and reducing errors caused by manual operations or delays in remote control.

[0003] In the prior art, a bird's-eye view method is mostly used for real-time path planning. First, the road surface conditions collected in the image are converted into a bird's-eye view, and then the path is calculated. However, converting the image into a bird's-eye view requires a large amount of computing power and occupies a large amount of CPU resources, resulting in delays in path generation and problems such as untimely path calculation and update. Therefore, how to solve the low efficiency of existing remote navigation path generation has become an urgent technical problem to be solved. Summary of the Invention

[0004] The main objective of the present invention is to provide a path navigation method, device, equipment and storage medium based on a monocular image, aiming to solve the technical problem of low efficiency of existing remote navigation path generation.

[0005] To achieve the above objective, the present invention provides a path navigation method based on a monocular image. The path navigation method based on a monocular image includes: obtaining an image of the current pose of a moving vehicle collected by a camera, and determining a path planning area in the image according to the movable range of the moving vehicle; generating a navigation path from the moving vehicle to the target position in the path planning area according to the point coordinates of the target position in the image coordinate system and a path planning algorithm; and driving the moving vehicle to move towards the target position according to the navigation path and a path tracking algorithm.

[0006] In addition, to achieve the above objective, the present invention also provides a path navigation device based on a monocular image. The path navigation device based on a monocular image includes: a path planning area determination module, configured to obtain an image of the current pose of a moving vehicle collected by a camera, and determine a path planning area in the image according to the movable range of the moving vehicle; a navigation path generation module, configured to generate a navigation path from the moving vehicle to the target position in the path planning area according to the point coordinates of the target position in the image coordinate system and a path planning algorithm; and a moving vehicle driving module, configured to drive the moving vehicle to move towards the target position according to the navigation path and a path tracking algorithm.

[0007] In addition, to achieve the above object, the present invention further provides a path navigation device based on a monocular image. The path navigation device based on a monocular image includes a processor, a memory, and a path navigation program based on a monocular image stored on the memory and executable by the processor. When the path navigation program based on a monocular image is executed by the processor, the steps of the path navigation method based on a monocular image as described above are implemented.

[0008] In addition, to achieve the above object, the present invention further provides a computer-readable storage medium. A path navigation program based on a monocular image is stored on the computer-readable storage medium. When the path navigation program based on a monocular image is executed by a processor, the steps of the path navigation method based on a monocular image as described above are implemented.

[0009] The present invention provides a path navigation method based on a monocular image. The method acquires an image of the current pose of a moving vehicle collected by a camera, and determines a path planning area in the image according to the movable range of the moving vehicle; generates a navigation path from the moving vehicle to a target position in the path planning area according to the point coordinates of the target position in the image coordinate system and a path planning algorithm; and drives the moving vehicle to move towards the target position according to the navigation path and a path tracking algorithm. By the above method, according to the movable range of the moving vehicle, a path planning area is generated in the image, enabling the user to clarify the current state of the moving vehicle and the road conditions according to the change of the path planning area; by limiting the path planning area, on the premise of ensuring the accuracy of the moving distance of the path planning, the user can be made to clarify the position area that the moving vehicle can reach in the current pose state, thus making it more convenient for the user to plan the path of the moving vehicle; through the path planning algorithm, the navigation path from the moving vehicle to the target position can be directly calculated and the navigation path can be directly displayed in the path planning area without operations such as converting to a bird's-eye view, reducing the calculation amount, accelerating the path calculation speed, and making the path display more convenient, solving the technical problem of low efficiency in generating remote navigation paths in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a schematic diagram of the hardware structure of the path navigation device based on a monocular image involved in the embodiment solution of the present invention;

[0011] Figure 2 It is a schematic flowchart of the first embodiment of the path navigation method based on a monocular image of the present invention;

[0012] Figure 3 It is a schematic flowchart of the second embodiment of the path navigation method based on a monocular image of the present invention;

[0013] Figure 4Schematic flowchart of the third embodiment of the path navigation method based on monocular images according to the present invention;

[0014] Figure 5 Schematic diagram of functional modules of the first embodiment of the path navigation device based on monocular images according to the present invention.

[0015] The implementation, functional features and advantages of the objectives of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0016] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0017] The path navigation method based on monocular images involved in the embodiments of the present invention is mainly applied to a path navigation device based on monocular images, and the path navigation device based on monocular images may be a device with display and processing functions such as a PC, a portable computer, a mobile terminal, etc.

[0018] Referring to Figure 1 , Figure 1 is a schematic diagram of the hardware structure of the path navigation device based on monocular images involved in the solution of the embodiments of the present invention. In the embodiments of the present invention, the path navigation device based on monocular images may include a processor 1001 (such as a CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components; the user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface); the memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory, and the memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0019] Those skilled in the art can understand that Figure 1 the hardware structure shown in does not constitute a limitation on the path navigation device based on monocular images, and may include more or fewer components than shown in the figure, or combine some components, or different component arrangements.

[0020] Continuing to refer to Figure 1 , Figure 1 the memory 1005 as a computer-readable storage medium in may include an operating system, a network communication module, and a path navigation program based on monocular images.

[0021] In Figure 1Among them, the network communication module is mainly used to connect to the server and communicate with the server for data; while the processor 1001 can call the path navigation program based on monocular images stored in the memory 1005 and execute the path navigation method based on monocular images provided in the embodiments of the present invention.

[0022] The embodiments of the present invention provide a path navigation method based on monocular images.

[0023] Refer to Figure 2 , Figure 2 which is a schematic flowchart of the first embodiment of the path navigation method based on monocular images of the present invention.

[0024] In this embodiment, the path navigation method based on monocular images includes the following steps:

[0025] Step S10: Obtain an image of the current pose of the moving vehicle collected by the camera, and determine a path planning area in the image according to the movable range of the moving vehicle;

[0026] In this embodiment, to ensure more accurate and comprehensive calculation of the path of the moving vehicle, the camera can be fixedly installed in the middle of the front end of the moving vehicle, so that the images on both sides of the forward direction of the moving vehicle collected by the camera are evenly distributed. According to the basic data (maximum steering angle, moving speed, etc.) of the moving vehicle obtained by pre-training, combined with the image of the current pose of the moving vehicle collected by the camera, calculate the movable range of the moving vehicle at the current pose.

[0027] It can be understood that the moving vehicle can be a movable vehicle such as a vehicle or a mobile robot.

[0028] Specifically, the camera collects an image of the current pose of the moving vehicle in real time and transmits it to the remote control end in real time. The control end can establish an image coordinate system and obtain the point coordinates of each pixel in the image coordinate system according to the resolution of the image. For example, taking the upper left corner pixel of the image as (0, 0) and the lower right corner pixel as (1, 1), the image coordinates of each pixel can be calculated according to the resolution of the image. According to the pre-trained parameters of the moving vehicle and the preset scale accuracy, determine the position coordinates that the moving vehicle can reach in the image coordinate system, so as to generate a path planning area, and the path planning area is updated in real time according to the change of the current pose of the moving vehicle.

[0029] Step S20: Generate a navigation path from the moving vehicle to the target position in the path planning area according to the point coordinates of the target position in the image coordinate system and the path planning algorithm;

[0030] In this embodiment, a two-dimensional image coordinate system is established based on the image captured by the camera. Each pixel of the image serves as a coordinate point. According to the internal and external parameters of the camera, the scale is calculated, that is, the actual scale corresponding to each pixel of the image. According to the coordinates of the target position in the image coordinate system, through the path planning algorithm, the image coordinate system is converted into the vehicle coordinate system, and the coordinate position of the target position relative to the camera in the vehicle coordinate system is calculated. Then, in combination with the current rotation angle of the moving vehicle, the true coordinates of the target position relative to the moving vehicle in the vehicle coordinate system are calculated. Correspondingly, the straight-line distance from the current position of the moving vehicle to the target position is calculated in the vehicle coordinate system, and the navigation path is displayed within the path planning area in the image coordinate system. Among them, the navigation path is displayed as a straight line from the coordinate point of the moving vehicle in the image coordinate system to the corresponding coordinate point of the target position.

[0031] In this embodiment, the path planning algorithm is obtained by adding the camera-to-vehicle coordinate system conversion algorithm to the existing pixel-to-camera coordinate system pose algorithm, resulting in the pixel-to-vehicle body coordinate system pose algorithm. Therefore, when the control terminal selects the target position in the path planning area defined in the image, the corresponding navigation path can be directly generated in the image.

[0032] Step S30, drive the moving vehicle to move towards the target position according to the navigation path and the path tracking algorithm.

[0033] In this embodiment, the control terminal sends the navigation path to the moving vehicle, and drives the moving vehicle to control the steering angle through the path tracking algorithm, and tracks the navigation path in real time, thereby driving the moving vehicle to move towards the target position.

[0034] Among them, the path tracking algorithm adopted in this application can be an existing control algorithm, such as a control algorithm designed based on PID control, Stanley control, or model predictive control, etc.

[0035] This embodiment provides a path navigation method based on a monocular image. The method acquires an image of the current pose of a moving vehicle collected by a camera, and determines a path planning area in the image according to the movable range of the moving vehicle; generates a navigation path from the moving vehicle to a target position in the path planning area according to the point coordinates of the target position in the image coordinate system and a path planning algorithm; and drives the moving vehicle to move towards the target position according to the navigation path and a path tracking algorithm. In the above manner, according to the movable range of the moving vehicle, the present invention generates a path planning area in the image, enabling the user to clarify the current state of the moving vehicle and the road conditions according to the change of the path planning area; by limiting the path planning area, it is possible to make the user clarify the position area that the moving vehicle can reach in the current pose state on the premise of ensuring the accuracy of the moving distance of the path planning, thus facilitating the user's path planning of the moving vehicle more; through the path planning algorithm, the navigation path from the moving vehicle to the target position can be directly calculated and the navigation path is directly displayed in the path planning area without operations such as converting to a bird's-eye view, reducing the calculation amount, accelerating the path calculation speed, and making the path display more convenient, solving the technical problem of low efficiency in generating remote navigation paths in the prior art.

[0036] Refer to Figure 3 , Figure 3 which is a schematic flowchart of the second embodiment of the path navigation method based on a monocular image of the present invention.

[0037] Based on the above Figure 2 illustrated embodiment, in this embodiment, the step S10 specifically includes:

[0038] Step S11, determine the length vertices of the path planning area according to the maximum rotation angle of the current pose of the moving vehicle;

[0039] In this embodiment, the path planning area is composed of four vertices. Since the camera is fixedly installed on the moving vehicle and the shooting angle of the camera rotates synchronously with the rotation of the moving vehicle, the position of the moving vehicle in the image coordinate system is fixed, and one of the vertices of the path planning area is the coordinate point of the moving vehicle in the image coordinate system. According to the data of the moving vehicle pre-trained, the maximum rotation angle of the moving vehicle can be obtained. According to the maximum rotation angle when the position of the moving vehicle is fixed, the x-axis coordinates of the maximum vertices on both sides of the moving vehicle can be obtained as the x-axis coordinates of the length vertices.

[0040] Step S12, determine the maximum area coordinates of the path planning area according to the internal and external parameters of the camera and a preset scale accuracy, and determine the width vertices of the path planning area according to the maximum area coordinates;

[0041] Further, the step S12 specifically includes:

[0042] Obtain the position coordinates of the midpoint of the last row of pixels of the resolution in the image coordinate system according to the resolution of the image, and use it as the starting coordinate of the mobile vehicle in the image coordinate system;

[0043] According to the internal and external parameters of the camera and the preset scale accuracy, using the starting coordinate as the reference coordinate point, calculate the movement coordinates in the image coordinate system corresponding to the point of the maximum movement distance of the mobile vehicle;

[0044] Use the starting coordinate and the movement coordinate as the width vertices of the path planning area.

[0045] In this embodiment, the point coordinates of the mobile vehicle in the image coordinate system are fixed. To ensure that the remote control terminal can observe the road conditions and environmental information in the forward direction of the mobile vehicle more comprehensively, the camera can be fixedly installed at the middle position of the front end of the mobile vehicle, and the camera height can be set according to actual needs; at this time, the x-axis coordinate corresponding to the mobile vehicle in the image coordinate system is the position coordinate of the middle column of pixels, and because there may be a certain pitch angle in the camera installation, and at the same time, in order to make full use of the captured image of the camera, the pixel point corresponding to the last row of pixels in the middle column of pixels of the image is used as the fixed coordinate point of the mobile vehicle in the image coordinate system.

[0046] According to the internal and external parameters of the camera, measure the height of the camera relative to the road surface, calculate the actual distance corresponding to each pixel of the image, and determine the calculation error range according to the preset scale accuracy. Within the acceptable error range, determine the coordinates of the available pixel points in the image coordinate system, and combine the x-axis coordinate of the length vertex to determine the y-axis coordinate of the length vertex, so as to determine the image coordinates of the two length vertices.

[0047] Use the coordinate point of the mobile vehicle in the image coordinate system as one of the width vertices, and the x-axis coordinate of the other width vertex is within the x-axis coordinates of the two length vertices. The y-axis coordinate of the other width vertex can be set according to the preset scale accuracy and the actual scene requirements. For example, if there is a long, straight and obstacle-free area in the scene, the coordinates of this width vertex can be set at a position far from the mobile vehicle in this area, but the farther the position is from the current position of the mobile vehicle, the lower the actual distance accuracy represented by its navigation path.

[0048] Step S13, determine the path planning area according to the length vertex and the width vertex.

[0049] In this embodiment, the four vertices are connected in a straight line in sequence to form a closed area as the path planning area. The size of the path planning area is updated in real time as the mobile vehicle moves and its pose changes. For example, when the mobile vehicle is stationary or moving in a straight line, and when the mobile vehicle is steered, the camera rotates synchronously with the mobile vehicle, and the shooting area biases towards one side of the mobile vehicle. At this time, the body of the mobile vehicle may not have completed the steering yet. Therefore, within the range of the displayed picture, the movable range of the mobile vehicle will decrease. At this time, the path planning area will be adjusted and updated in real time according to the path planning algorithm to adapt to the path planning area corresponding to the current position of the mobile vehicle.

[0050] Referring to Figure 4 , Figure 4 which is a schematic flowchart of the third embodiment of the path navigation method based on monocular pictures according to the present invention.

[0051] Based on the above Figure 2 illustrated embodiment, in this embodiment, the step S20 specifically includes:

[0052] Step S21, converting the picture coordinate system to the vehicle coordinate system according to the internal and external parameters of the camera;

[0053] In this embodiment, both the picture coordinate system and the vehicle coordinate system are two-dimensional coordinate systems; the external parameters of the camera include the pose of the camera relative to the mobile vehicle (such as the x / y / z axis coordinates and rotation angles in the world coordinate system, etc.); the internal parameters of the camera include the optical center and focusing parameters of the camera, etc.

[0054] Specifically, there is a certain pitch angle when the camera is installed, so there is an angle between the picture coordinate system and the vehicle coordinate system. Since both the picture coordinate system and the vehicle coordinate system are two-dimensional coordinate systems, converting the picture coordinate system to the vehicle coordinate system is to vertically project the picture coordinate system onto the vehicle coordinate system.

[0055] Specifically, since the vehicle coordinate system is established on an ideal horizontal ground, according to the height of the camera from the horizontal ground and the internal and external parameters of the camera, the horizontal distance of the road surface points in a certain range area from the mobile vehicle can be calculated.

[0056] Among them, the internal parameters of the camera include the camera x-axis focus f x , the camera y-axis focus f y , the camera x-axis center point c x and the camera y-axis center point c y ; the external parameters of the camera include the angle of the camera relative to the vehicle (camera_angle) and the height of the camera relative to the vehicle (camera_height).

[0057] Understandably, due to projection errors, there is a certain error between the navigation path distance calculated by the path planning algorithm and the actual distance. Moreover, for points in the image coordinate system that are farther from the coordinate point corresponding to the mobile vehicle, the calculated actual distance error is greater. Therefore, it is necessary to limit the calculation range area according to the preset scale accuracy to make the error acceptable without affecting remote control. By combining this range area with the maximum turning angle of the mobile vehicle, the three active points of the path planning area can be calculated, thereby obtaining the path planning area, and the user's selectable area is limited by the path planning area to avoid the user misjudging the actual moving distance of the mobile vehicle due to excessive error, resulting in too large a deviation or damage to the navigation path of the mobile vehicle.

[0058] Specifically, according to the projection relationship between the vehicle coordinate system and the image coordinate system, the pixel points of the image coordinate system are corresponding to the coordinate grids of the vehicle coordinate system to obtain the actual distance corresponding to each pixel point, that is, the scale of the image.

[0059] In a specific embodiment, the conversion process between the image coordinate system and the vehicle coordinate system is as follows:

[0060]

[0061] where, image h is the height of the image; goal y is the y-axis value of the target point, in percentage of the image height; c y is the center point of the camera on the x-axis, in pixels; f y is the focus of the camera on the y-axis, in pixels; γ is the y-axis angle of the target point in the image coordinate system.

[0062] β = γ + camera a (2)

[0063] where, camera a is the angle of the camera relative to the vehicle; β is the y-axis angle of the target point in the vehicle coordinate system.

[0064] Therefore, the x coordinate of the target point in the vehicle coordinate system is:

[0065]

[0066] where, camera h is the height of the camera relative to the vehicle.

[0067] The y coordinate of the target point in the vehicle coordinate system is:

[0068]

[0069] where, goal xx is the numerical value of the target point on the x-axis, and the unit is the percentage of the picture width; c x xc is the center point of the camera on the x-axis, and the unit is pixel; f x xf is the camera focus on the x-axis, and the unit is pixel.

[0070] Thus, the conversion of the position coordinates of the target point from the picture coordinate system to the vehicle coordinate system is completed, so that the actual distance of the planned path can be calculated according to the scale of the vehicle coordinate system.

[0071] Step S22: Determine the real point coordinates corresponding to the target position in the vehicle coordinate system according to the target point coordinates of the target position in the picture coordinate system;

[0072] In this embodiment, after the picture coordinate system is converted to the vehicle coordinate system through the path planning algorithm, according to the corresponding relationship between the two coordinate systems and the actual scale corresponding to each pixel point in the picture coordinate system, the coordinate position of the target position relative to the moving vehicle in the vehicle coordinate system can be calculated, and the real point coordinates of the target position in the vehicle coordinate system can be obtained.

[0073] Further, before the step S22, it further includes:

[0074] Judge whether the point coordinates of the target position are within the path planning area;

[0075] If the point coordinates of the target position are not within the path planning area, an error is prompted;

[0076] If the point coordinates of the target position are within the path planning area, obtain the point coordinates of the target position in the picture coordinate system to calculate the real point coordinates corresponding to the target position in the vehicle coordinate system through the path planning algorithm.

[0077] In this embodiment, since the path planning area is a part of the picture area divided in the picture coordinate system, and the path planning area is updated and changed in real time. At the same time, in order to ensure the moving accuracy, the distance of each path planning will not be too long. Therefore, the user needs to continuously update the coordinate of the target position at the remote control end.

[0078] Specifically, the coordinates of the target position can be obtained by directly clicking on the target point in the image displayed on the remote control end or by inputting the coordinate position. Only when the coordinates of the target position are within the path planning area can the path planning algorithm perform path calculation. Therefore, when selecting the target position, it is necessary to judge the image coordinates of the target position. If the point coordinates of the target position are not within the path planning area, the system will prompt an error, which can be a sound prompt or a pop-up window prompt, etc., to remind the user of the operation error; if the point coordinates of the target position are within the path planning area, the path planning algorithm will calculate and generate a navigation path and display it within the path planning area of the image coordinate system.

[0079] Step S23: Generate the navigation path in the vehicle coordinate system according to the starting coordinates of the mobile vehicle in the vehicle coordinate system, the real point coordinates, and the path planning algorithm, and display the navigation path in the image coordinate system; wherein, the navigation path includes a moving direction and a moving distance.

[0080] In this embodiment, according to the path planning algorithm, the point coordinates of the target position are converted into the corresponding vehicle coordinate system, a straight-line path from the vehicle position to the target position is generated in the vehicle coordinate system, the straight-line distance from the vehicle position to the target position in the actual scenario is calculated, and the straight-line path of the mobile vehicle to the target position is displayed in the image coordinate system. The direction from the vehicle position to the target position is the straight-line direction of the navigation path, and the distance of the navigation path calculated in the vehicle coordinate system is the estimated moving distance.

[0081] Refer to Figure 5 , Figure 5 which is a schematic diagram of the functional modules of the first embodiment of the path navigation device based on a monocular image according to the present invention.

[0082] In this embodiment, the path navigation device based on a monocular image includes:

[0083] A path planning area determination module 10, configured to obtain an image of the current pose of the mobile vehicle collected by the camera, and determine a path planning area in the image according to the movable range of the mobile vehicle;

[0084] A navigation path generation module 20, configured to generate a navigation path of the mobile vehicle to the target position in the path planning area according to the point coordinates of the target position in the image coordinate system and the path planning algorithm;

[0085] A mobile vehicle driving module 30, configured to drive the mobile vehicle to move towards the target position according to the navigation path and the path tracking algorithm.

[0086] Further, the path planning area determination module 10 specifically includes:

[0087] A length vertex determination unit for determining the length vertices of the path planning area according to the maximum rotation angle of the current pose of the mobile vehicle;

[0088] A width vertex determination unit for determining the maximum area coordinates of the path planning area according to the internal and external parameters of the camera and the preset scale accuracy, and determining the width vertices of the path planning area according to the maximum area coordinates;

[0089] A path planning area determination unit for determining the path planning area according to the length vertices and the width vertices.

[0090] Further, the width vertex determination unit specifically includes:

[0091] A mobile vehicle coordinate determination subunit for obtaining the position coordinates of the midpoint of the last row of pixels of the resolution in the image coordinate system as the starting coordinate of the mobile vehicle in the image coordinate system according to the resolution of the image;

[0092] A mobile coordinate calculation subunit for calculating the mobile coordinates corresponding to the maximum mobile distance point of the mobile vehicle in the image coordinate system with the starting coordinate as the reference coordinate point according to the internal and external parameters of the camera and the preset scale accuracy;

[0093] A width vertex determination subunit for using the starting coordinate and the mobile coordinates as the width vertices of the path planning area.

[0094] Further, the navigation path generation module 20 specifically includes:

[0095] A coordinate system conversion unit for converting the image coordinate system to the vehicle coordinate system according to the internal and external parameters of the camera;

[0096] A target position coordinate determination unit for determining the real point coordinates corresponding to the target position in the vehicle coordinate system according to the target point coordinates of the target position in the image coordinate system;

[0097] A navigation path calculation unit for generating the navigation path in the vehicle coordinate system according to the starting coordinate of the mobile vehicle in the vehicle coordinate system, the real point coordinates, and the path planning algorithm, and displaying the navigation path in the image coordinate system; wherein, the navigation path includes a moving direction and a moving distance.

[0098] Further, the path navigation device based on a monocular image includes a target position coordinate judgment module, and the target position coordinate judgment module includes:

[0099] A target position coordinate determination unit, configured to determine whether the point coordinates of the target position are within the path planning area;

[0100] A target position error reminder unit, configured to prompt an error if the point coordinates of the target position are not within the path planning area;

[0101] A target position coordinate acquisition unit, configured to, if the point coordinates of the target position are within the path planning area, acquire the point coordinates of the target position in the image coordinate system, so as to calculate the corresponding real point coordinates of the target position in the vehicle coordinate system through a path planning algorithm.

[0102] Wherein, each module in the above-mentioned monocular image-based path navigation device corresponds to each step in the above-mentioned monocular image-based path navigation method embodiment, and its functions and implementation processes will not be elaborated here one by one.

[0103] In addition, an embodiment of the present invention also provides a computer-readable storage medium.

[0104] A monocular image-based path navigation program is stored on the computer-readable storage medium of the present invention. When the monocular image-based path navigation program is executed by a processor, the steps of the above-mentioned monocular image-based path navigation method are implemented.

[0105] Wherein, the method implemented when the monocular image-based path navigation program is executed can refer to each embodiment of the monocular image-based path navigation method of the present invention, which will not be elaborated here.

[0106] It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of another identical element in the process, method, article or system including the element.

[0107] The serial numbers of the above-mentioned embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0108] This application can be used in numerous general or specific computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0109] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, 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 is stored in a storage medium as described above (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to enable a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0110] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structural or equivalent process transformations made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, are equally included in the patent protection scope of the present invention.

Claims

1. A path navigation method based on monocular images, characterized in that The steps of the method include: Obtain a picture of the current pose of the moving vehicle collected by the camera, and determine a path planning area in the picture according to the movable range of the moving vehicle, including: Determine the length vertices of the path planning area according to the maximum turning angle of the current pose of the moving vehicle; Determine the maximum area coordinates of the path planning area according to the internal and external parameters of the camera and the preset scale accuracy, and determine the width vertices of the path planning area according to the maximum area coordinates, including: Obtain the position coordinates of the midpoint of the last row of pixels of the resolution in the picture coordinate system according to the resolution of the picture, as the starting point coordinates of the moving vehicle in the picture coordinate system; According to the internal and external parameters of the camera and the preset scale accuracy, calculate the moving coordinates corresponding to the maximum moving distance point of the moving vehicle in the picture coordinate system with the starting point coordinates as the reference coordinate point; Use the starting point coordinates and the moving coordinates as the width vertices of the path planning area; Determine the path planning area according to the length vertices and the width vertices; Generate a navigation path from the moving vehicle to the target position in the path planning area according to the point coordinates of the target position in the picture coordinate system and the path planning algorithm, including: Convert the picture coordinate system to the vehicle coordinate system according to the internal and external parameters of the camera; Determine the real point coordinates corresponding to the target position in the vehicle coordinate system according to the target point coordinates of the target position in the picture coordinate system, including: Judge whether the point coordinates of the target position are within the path planning area; If the point coordinates of the target position are not within the path planning area, an error is prompted; If the point coordinates of the target position are within the path planning area, obtain the point coordinates of the target position in the picture coordinate system to calculate the real point coordinates corresponding to the target position in the vehicle coordinate system through the path planning algorithm; Generate the navigation path in the vehicle coordinate system according to the starting coordinates of the moving vehicle in the vehicle coordinate system, the real point coordinates and the path planning algorithm, and display the navigation path in the picture coordinate system; wherein, the navigation path includes a moving direction and a moving distance; Drive the moving vehicle to move towards the target position according to the navigation path and the path tracking algorithm.

2. A path navigation device based on a monocular image, characterized in that, The path navigation device based on a monocular picture includes: A path planning area determination module, configured to obtain a picture of the current pose of the moving vehicle collected by the camera, and determine a path planning area in the picture according to the movable range of the moving vehicle, including: Determine the length vertices of the path planning area according to the maximum turning angle of the current pose of the moving vehicle; Determine the maximum area coordinates of the path planning area according to the internal and external parameters of the camera and the preset scale accuracy, and determine the width vertices of the path planning area according to the maximum area coordinates, including: Obtain the position coordinates of the midpoint of the last row of pixels of the resolution in the image coordinate system according to the resolution of the image, and use it as the starting coordinate of the mobile vehicle in the image coordinate system; Calculate the movement coordinates corresponding to the maximum movement distance point of the mobile vehicle in the image coordinate system with the starting coordinate as the reference coordinate point according to the internal and external parameters of the camera and the preset scale accuracy; Use the starting coordinate and the movement coordinate as the width vertices of the path planning area; Determine the path planning area according to the length vertices and the width vertices; The navigation path generation module is used to generate the navigation path of the mobile vehicle to the target position in the path planning area according to the point coordinates of the target position in the image coordinate system and the path planning algorithm, including: Convert the image coordinate system to the vehicle coordinate system according to the internal and external parameters of the camera; judge whether the point coordinates of the target position are within the path planning area; If the point coordinates of the target position are not within the path planning area, an error is prompted; If the point coordinates of the target position are within the path planning area, obtain the point coordinates of the target position in the image coordinate system to calculate the real point coordinates corresponding to the target position in the vehicle coordinate system through the path planning algorithm; Generate the navigation path in the vehicle coordinate system according to the starting coordinate of the mobile vehicle in the vehicle coordinate system, the real point coordinates and the path planning algorithm, and display the navigation path in the image coordinate system; wherein, the navigation path includes the movement direction and the movement distance; The mobile vehicle driving module is used to drive the mobile vehicle to move towards the target position according to the navigation path and the path tracking algorithm.

3. A path navigation device based on a monocular image, characterized in that, The path navigation device based on a monocular image includes a processor, a memory, and a path navigation program based on a monocular image stored on the memory and executable by the processor. When the path navigation program based on a monocular image is executed by the processor, it implements a path navigation method based on a monocular image as described in claim 1.

4. A computer-readable storage medium, characterized in that, A path navigation program based on a monocular image is stored on the computer-readable storage medium. When the path navigation program based on a monocular image is executed by a processor, it implements a path navigation method based on a monocular image as described in claim 1.

Images