Method, device, electronic device and storage medium for evaluating visual positioning algorithm

By generating simulated images and comparing them with the real environment positioning truth, evaluating the robustness of the visual positioning algorithm, the problem that visual positioning technology in the prior art is difficult to cover diverse scenarios, and improving the positioning performance of the autonomous driving system.

CN112699765BActive Publication Date: 2024-11-08BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF 11 Cites 0 Cited by

Patent Information

Application Number
CN202011558559.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-12-25
Publication Date
2024-11-08
Estimated Expiration
2040-12-25

AI Technical Summary

Technical Problem

Visual positioning technology in existing autonomous driving systems is difficult to cover various real natural scenes, which makes it difficult to evaluate the robustness of visual positioning algorithms in diverse scenarios.

Method used

By obtaining the real environment image and positioning truth value of the vehicle while driving, the image is processed to generate simulated images, including the overlay of the real environment image and the simulated scene, the visual positioning algorithm is input to calculate the positioning results, and compared with the truth value, and the algorithm is evaluated Great.

Benefits of technology

The evaluation ability of visual positioning algorithms in various scenarios is improved, the robustness and usability of visual positioning algorithms is ensured, and the positioning performance in diverse scenarios is enhanced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112699765B_ABST
    Figure CN112699765B_ABST
Patent Text Reader

Abstract

The present disclosure provides a method, device, electronic device and storage medium for evaluating a visual positioning algorithm, which relates to the field of autonomous driving technology, especially visual positioning technology. The implementation scheme is: a method for evaluating a visual positioning algorithm, comprising: obtaining an image of a real environment when a vehicle is driving, and a true positioning value of the vehicle; processing the image of the real environment to generate a simulated image, wherein the simulated image includes a superposition of the image of the real environment and the simulated scene; and inputting the simulated image into a visual positioning algorithm to calculate a positioning result, and comparing the positioning result with the true positioning value.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, in particular to visual positioning technology, and specifically to a method, device, electronic device, computer-readable storage medium, and computer program product for evaluating a visual positioning algorithm. Background Art

[0002] The positioning system is a basic function of the autonomous driving system, and plays a vital role in the perception of the vehicle's surrounding environment, the decision-making of vehicle movement, and planning and control. Visual positioning is one of the positioning systems and plays an important role in the positioning of the autonomous driving system.

[0003] The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art. Summary of the invention

[0004] The present disclosure provides a method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product for evaluating a visual positioning algorithm.

[0005] According to one aspect of the present disclosure, a method for evaluating a visual positioning algorithm is provided, comprising: acquiring an image of a real environment when a vehicle is traveling, and a true positioning value of the vehicle; processing the image of the real environment to generate a simulated image, wherein the simulated image comprises a superposition of the image of the real environment and a simulated scene; and inputting the simulated image into the visual positioning algorithm to calculate a positioning result, and comparing the positioning result with the true positioning value.

[0006] According to another aspect of the present disclosure, there is provided an apparatus for evaluating a visual positioning algorithm, comprising: a data acquisition module, configured to acquire an image of a real environment when a vehicle is traveling, and a true positioning value of the vehicle; an image processing module, configured to process the image of the real environment to generate a simulated image, wherein the simulated image comprises a superposition of the image of the real environment and a simulated scene; and an evaluation module, configured to input the simulated image into the visual positioning algorithm to calculate a positioning result, and compare the positioning result with the true positioning value.

[0007] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described above.

[0008] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method as described above.

[0009] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the above method when executed by a processor.

[0010] According to one or more embodiments of the present disclosure, rich scenes can be created for the evaluation of visual positioning algorithms, thereby improving the evaluation capability of visual positioning algorithms.

[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0013] Figure 1 A flow chart of a method for evaluating a visual positioning algorithm according to an embodiment of the present disclosure is shown;

[0014] 2(a) and 2(b) show an example of adding noise corresponding to a simulated scene to an image of a real environment according to an embodiment of the present disclosure;

[0015] Figure 3 A block diagram of a device for evaluating a visual positioning algorithm according to an embodiment of the present disclosure is shown;

[0016] Figure 4 A block diagram of a device for evaluating a visual positioning algorithm according to another embodiment of the present disclosure is shown;

[0017] Figure 5 A structural block diagram of an electronic device applicable to the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0018] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0019] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0020] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0021] In the visual positioning technology currently used in autonomous driving systems, the collection of the required on-board image information is restricted by various factors (such as legal regulations, rare natural scenes, etc.), making it difficult to cover various real natural scenes, and thus it is impossible to ensure the availability of the visual positioning algorithm used in the visual positioning technology for these scenes. The method for evaluating the visual positioning algorithm proposed in the present disclosure is intended to be used to evaluate the robustness of the visual positioning algorithm in various scenes to ensure the availability of the visual positioning algorithm for these scenes.

[0022] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0023] Figure 1 FIG. 4 is a flow chart showing a method for evaluating a visual positioning algorithm according to an embodiment of the present disclosure. Figure 1 As shown, the method for evaluating a visual positioning algorithm may include:

[0024] Step S101, acquiring an image of the real environment when the vehicle is traveling, and a true positioning value of the vehicle;

[0025] Step S102, processing the image of the real environment to generate a simulated image, wherein the simulated image includes a superposition of the image of the real environment and a simulated scene; and

[0026] Step S103: input the simulated image into the visual positioning algorithm to calculate a positioning result, and compare the positioning result with the positioning true value.

[0027] According to the method for evaluating the visual positioning algorithm of the embodiment of the present disclosure, the robustness of the visual positioning algorithm for various scenes can be judged by using the accurate positioning truth value in the real environment as the evaluation standard. By generating simulated images to simulate various scene images that are difficult to obtain in practice, a rich scene can be created for the evaluation of the visual positioning algorithm, thereby improving the evaluation capability of the visual positioning algorithm.

[0028] In this disclosure, "vehicle" means various autonomous driving systems such as unmanned vehicles. "Visual positioning algorithm" means the algorithm used to locate the vehicle using visual positioning technology. At present, different manufacturers may have their own unique visual positioning algorithms for the autonomous driving systems they produce. For example, the visual positioning algorithm may be the DA4AD algorithm (end-to-end deep attention perception feature-assisted visual positioning for autonomous driving).

[0029] Those skilled in the art will appreciate that these visual positioning algorithms are not limited in the present disclosure.

[0030] In order to evaluate the visual positioning algorithm, an evaluation criterion for the evaluation may be first obtained. In the present disclosure, the evaluation criterion may be referred to as a "positioning truth value". The positioning truth value may represent the trajectory of the vehicle while driving, that is, the position and / or posture at each moment while driving, or may also be referred to as a posture.

[0031] To this end, according to an embodiment of the present disclosure, in step S101, an image of the real environment when the vehicle is traveling and a true positioning value of the vehicle may be acquired.

[0032] Acquiring an image of the real environment when the vehicle is traveling may include acquiring an image of the road scene that the vehicle passes through when traveling, that is, the vehicle-mounted image information as described above. For example, the road scene may include a highway scene and an urban road scene. Urban road scenes may include, for example, tree-lined roads, tunnels, overpasses, etc. Urban road scenes may also include road scenes blocked by tall buildings, etc. More scene images may facilitate the creation of simulated images about more scene images in subsequent steps, so as to evaluate the robustness of the visual positioning algorithm in various scenarios.

[0033] Optionally, the image of the real environment can be taken in multiple directions by the vehicle's onboard camera device. Thus, it is possible to ensure that a more accurate positioning truth value is calculated as an evaluation criterion. In one example, the vehicle's onboard camera device can include 9 cameras within a 360-degree range to take images in 9 different directions.

[0034] After obtaining the image of the real environment when the vehicle is traveling, the true value of the positioning of the vehicle can also be obtained. As mentioned above, the true value of the positioning is used as an evaluation criterion, representing the trajectory of the vehicle when traveling, that is, the position and / or posture of the vehicle at each moment when traveling.

[0035] Optionally, the positioning truth value may be calculated based on the image of the real environment and the positioning information obtained by the sensor of the vehicle. Thus, a fusion positioning method can be used to obtain an accurate positioning truth value as an evaluation criterion.

[0036] In one example, the vehicle's sensor may be a global navigation satellite system GNSS sensor, which corresponds to the GNSS positioning method. In this case, the positioning truth value may be calculated by the following fusion positioning method. First, the position and posture of the vehicle at each moment during driving can be obtained from satellite and base station data through the GNSS positioning method, and its accuracy is generally at the centimeter level. Then, it can be optimized based on the on-board image information (i.e., the image of the real environment captured when the vehicle is driving) to further calculate a more accurate position and posture, i.e., the positioning truth value.

[0037] Optionally, in addition to visual positioning, the fusion positioning method may also include a combination of multiple positioning methods such as LiDAR positioning, global navigation satellite system GNSS positioning, and inertial navigation positioning. Accordingly, the vehicle's sensors may include at least one of the following: LiDAR, global navigation satellite system GNSS, and inertial measurement unit IMU. Thus, different fusion positioning methods can be used to improve the accuracy of calculating the true positioning value as an evaluation criterion.

[0038] The various positioning methods in the fusion positioning method can have corresponding weights or credibility. As in the above example, visual positioning is used on the basis of GNSS positioning to obtain accurate position and pose, so the robustness of the visual positioning algorithm is also crucial.

[0039] As described above, in the current visual positioning technology, the collection of the required vehicle-mounted image information is restricted by various factors, and it is difficult to cover various real natural scenes. To this end, according to an embodiment of the present disclosure, in step S102, an image of the real environment can be processed to generate a simulated image, wherein the simulated image includes the superposition of the image of the real environment and the simulated scene. That is, the image of the real environment can be used to create certain scenes that are difficult to obtain through actual collection, thereby simulating the scene.

[0040] Optionally, processing the image of the real environment may include: adding noise corresponding to the simulated scene to the image of the real environment, thereby facilitating the simulation of various fault scenes and natural scenes that cannot be obtained through normal acquisition methods.

[0041] Optionally, the simulation scenario may include at least one of the following: sensor failure of the vehicle, electromagnetic interference to the vehicle, abnormal light, and abnormal weather. Thus, various failure scenarios and natural scenarios can be created to facilitate the evaluation of the robustness of the visual positioning algorithm for various scenarios.

[0042] In one example, for a scenario of simulating a sensor failure of a vehicle, for example, Gaussian noise can be added to an image of a real environment. Gaussian noise is noise whose probability density function follows a Gaussian distribution. In actual situations, the reason for the generation of Gaussian noise can be, for example, that the image sensor has been working for a long time, resulting in an overheated temperature. Therefore, a scenario in which the image sensor temperature is too high can be simulated by adding Gaussian noise to an image of a real environment. For example, this can be achieved by using the skimage function based on the python scripting language.

[0043] FIG2(a) and FIG2(b) show an example of adding noise corresponding to a simulated scene to an image of a real environment according to an embodiment of the present disclosure. FIG2(a) shows an image of a real environment acquired according to an embodiment of the present disclosure, and FIG2(b) shows an image after Gaussian noise is added to the image of the real environment. The examples shown in FIG2(a) and FIG2(b) may be a scene of a sensor failure of a simulated vehicle.

[0044] Generally speaking, vehicles rarely experience sensor failures during driving, so it is difficult to collect on-board image information related to sensor failures, and then it is difficult to evaluate the availability of the visual positioning algorithm in this scenario. However, according to the method for evaluating the visual positioning algorithm in the embodiment of the present disclosure, a simulated image can be created by adding noise corresponding to the simulated scene to the image of the real environment. This makes it easy to simulate various fault scenarios that cannot be obtained through normal acquisition methods.

[0045] In another example, electromagnetic interference to a vehicle can be simulated by adding, for example, periodic noise to an image of a real environment. In actual situations, electromagnetic interference may cause periodic noise, and interference by periodic noise may cause image abnormalities, and a common abnormality is strip-shaped water ripple interference. Therefore, a scene in which a vehicle is subjected to electromagnetic interference can be simulated by adding periodic noise to an image of a real environment. For example, this can be achieved by adding sinusoidal wave signal noise to a spatial domain image.

[0046] Those skilled in the art will appreciate that the examples of adding Gaussian noise and periodic noise as described above are merely illustrative examples. Depending on the scene to be simulated, other types of noise may also be added to the image of the real environment, as long as it corresponds to the scene to be simulated.

[0047] For example, you can also use salt and pepper noise. Salt and pepper noise, also known as impulse noise, randomly changes some pixel values ​​to produce black and white light and dark point noise. In actual situations, salt and pepper noise is often generated by image sensors, transmission channels, decoding processing, etc. Therefore, you can use salt and pepper noise to simulate faults related to these scenarios.

[0048] In other examples, abnormal light scenes such as morning and night can be simulated by adding noise to the image of the real environment to adjust the changes in ambient light. Abnormal weather conditions such as rainy days, foggy days, and haze can be simulated by adding noise corresponding to rainy days, foggy days, and haze to the image of the real environment. In addition, the performance of the noise can be adjusted accordingly according to the weather forecast of the meteorological station, such as rainfall and haze index.

[0049] Other noise examples may include various noises such as Rayleigh noise, spatial position-dependent noise, mask noise, high-frequency noise, non-eccentric noise, comfort noise, etc. Those skilled in the art will appreciate that this document does not exhaust all the noises that can be used, and various noises have their specific causes and construction methods, and appropriate noises can be appropriately selected according to the desired simulated scene.

[0050] According to an embodiment of the present disclosure, after the simulation image is created, in step S103, the simulation image may be input into a visual positioning algorithm to calculate a positioning result, and the positioning result may be compared with a true positioning value.

[0051] Since the simulated image is an image with noise reflecting various scenes, after inputting it into the visual positioning algorithm, the positioning results corresponding to various scenes can be calculated accordingly. If the visual positioning algorithm is robust for a certain scene, the difference between the positioning result calculated by the simulated image of the scene and the previously calculated positioning true value should not be too large. Therefore, a threshold can also be set in advance to determine the difference between the positioning result and the positioning true value, and the threshold can reflect the tolerance for deviation.

[0052] Optionally, the method for evaluating the visual positioning algorithm may further include: determining the credibility of the visual positioning algorithm based on the difference between the positioning result and the positioning true value. Thus, a feedback mechanism for the evaluation result can be formed, so that the weight of the visual positioning algorithm can be accurately determined in the fusion positioning.

[0053] As described above, various positioning methods in the fusion positioning method including visual positioning, LiDAR positioning, GNSS positioning, inertial navigation positioning, etc. can have corresponding weights or credibility. Visual positioning is one of the mainstream solutions with economical price, so the robustness of the visual positioning algorithm is also crucial. If the result of the above comparison is that the difference between the positioning result calculated by the simulated image of the scene and the previously calculated positioning true value exceeds the threshold, it may indicate that the robustness of the visual positioning algorithm for the current scene is not strong. Therefore, the credibility of the visual positioning algorithm in the fusion positioning method can be appropriately reduced to reduce the probability that it may affect the positioning accuracy. On the contrary, if the result of the comparison is that the difference between the two is within the threshold, it may indicate that the visual positioning algorithm is robust for the current scene, thereby maintaining or improving the credibility of the visual positioning algorithm in the fusion positioning method.

[0054] According to the method for evaluating the visual positioning algorithm of the embodiment of the present disclosure, the robustness of the visual positioning algorithm for various scenes can be judged by using the accurate positioning truth value in the real environment as the evaluation standard. By generating simulated images to simulate various scene images that are difficult to obtain in practice, a rich scene can be created for the evaluation of the visual positioning algorithm, thereby improving the evaluation capability of the visual positioning algorithm.

[0055] According to another aspect of the present disclosure, a device for evaluating a visual positioning algorithm is also provided. Figure 3 FIG. 1 is a block diagram of an apparatus for evaluating a visual positioning algorithm according to an embodiment of the present disclosure. Figure 3 As shown, the apparatus 300 for evaluating a visual positioning algorithm may include:

[0056] The data acquisition module 301 is configured to acquire an image of the real environment when the vehicle is traveling, and a true value of the vehicle's positioning;

[0057] An image processing module 302 is configured to process an image of a real environment to generate a simulated image, wherein the simulated image includes a superposition of the image of the real environment and the simulated scene; and

[0058] The evaluation module 303 is configured to input the simulated image into the visual positioning algorithm to calculate the positioning result, and compare the positioning result with the positioning true value.

[0059] The operations of the above modules 301, 302 and 303 of the apparatus 300 for evaluating a visual positioning algorithm can be respectively combined with the above Figure 1 The operations of steps S101, S102, and S103 described above correspond to each other and will not be repeated here.

[0060] Optionally, the image of the real environment may be captured in multiple directions by an onboard camera device of the vehicle.

[0061] Optionally, the true positioning value may be calculated based on an image of the real environment and positioning information obtained by sensors of the vehicle.

[0062] Optionally, the sensor may include at least one of the following: a laser radar LiDAR, a global navigation satellite system GNSS, and an inertial measurement unit IMU.

[0063] Figure 4 FIG. 5 is a block diagram of a device for evaluating a visual positioning algorithm according to another embodiment of the present disclosure. Figure 4 The device 400 for evaluating the visual positioning algorithm may include a data acquisition module 401, an image processing module 402 and an evaluation module 403. The above modules 401, 402, 403 and the combination Figure 3 The operations of modules 301, 302 and 303 are similar and thus will not be described in detail here.

[0064] The image processing module 402 may further include a noise adding module 4020 , which may be configured to add noise corresponding to the simulated scene to the image of the real environment.

[0065] Optionally, the simulation scenario may include at least one of the following: sensor failure of the vehicle, electromagnetic interference to the vehicle, abnormal light, and abnormal weather.

[0066] The apparatus 400 for evaluating a visual positioning algorithm may further include a feedback module 404 , which may be configured to determine the credibility of the visual positioning algorithm based on a difference between a positioning result and a true positioning value.

[0067] According to another aspect of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described above.

[0068] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is further provided, wherein the computer instructions are used to enable the computer to execute the method as described above.

[0069] According to another aspect of the present disclosure, a computer program product is further provided, including a computer program, wherein the computer program implements the method as described above when executed by a processor.

[0070] refer to Figure 5 , a block diagram of an electronic device 500 that can be applied to the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0071] like Figure 5 As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0072] Multiple components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, an output unit 507, a storage unit 508 and a communication unit 509. The input unit 506 can be any type of device that can input information to the electronic device 500. The input unit 506 can receive input digital or character information, and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a trackpad, a trackball, a joystick, a microphone and / or a remote control. The output unit 507 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator and / or a printer. The storage unit 508 can include but is not limited to a disk, an optical disk. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver and / or a chipset, such as Bluetooth TM devices, 1302.11 devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0073] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as a method for evaluating a visual positioning algorithm. For example, in some embodiments, the method for evaluating a visual positioning algorithm may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the method for evaluating a visual positioning algorithm described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform a method for evaluating a visual positioning algorithm in any other appropriate manner (e.g., by means of firmware).

[0074] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0075] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0076] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0077] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0078] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0079] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0080] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0081] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A method for evaluating a visual positioning algorithm, comprising: Acquire an image of a real environment when the vehicle is traveling, and a true positioning value of the vehicle, wherein the image of the real environment includes an image of a road scene that the vehicle passes through when traveling, and the true positioning value is calculated based on the image of the real environment and positioning information obtained by a sensor of the vehicle; Generating a simulated image for simulating a scenario of sensor failure of the vehicle by adding Gaussian noise to the image of the real environment; and The simulated image is input into the visual positioning algorithm to calculate a positioning result, and the positioning result is compared with the positioning true value.

2. The method of claim 1, wherein: The image of the real environment is captured in multiple directions by the on-board camera equipment of the vehicle.

3. The method of claim 1, wherein: The sensor includes at least one of the following: a laser radar LiDAR, a global navigation satellite system GNSS, and an inertial measurement unit IMU.

4. The method of claim 1, further comprising: Based on the difference between the positioning result and the true positioning value, the credibility of the visual positioning algorithm is determined.

5. A device for evaluating a visual positioning algorithm, comprising: A data acquisition module, configured to acquire an image of a real environment when a vehicle is traveling, and a true positioning value of the vehicle, wherein the image of the real environment includes an image of a road scene that the vehicle passes through when traveling, and the true positioning value is calculated based on the image of the real environment and positioning information obtained by a sensor of the vehicle; an image processing module configured to generate a simulated image for simulating a scene of sensor failure of the vehicle by adding Gaussian noise to the image of the real environment; and The evaluation module is configured to input the simulated image into the visual positioning algorithm to calculate a positioning result, and compare the positioning result with the positioning true value.

6. The device according to claim 5, wherein: The image of the real environment is captured in multiple directions by the on-board camera equipment of the vehicle.

7. The device according to claim 5, wherein: The sensor includes at least one of the following: a laser radar LiDAR, a global navigation satellite system GNSS, and an inertial measurement unit IMU.

8. The device as claimed in claim 5 further comprises a feedback module, wherein the feedback module is configured to determine the credibility of the visual positioning algorithm based on the difference between the positioning result and the positioning true value.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-4.

11. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Citation Information

Patent Citations

  • Automatic license plate identification method based on deep convolutional neural network

    CN106709486A

  • Transport vehicle space positioning method and system based on inertia measurement assisted vision

    CN108051002A

  • Unmanned vehicle visual inspection robustness test method and system

    CN108268831A

  • Multisource perception positioning system suitable for smart networked car

    CN109405824A

  • Evaluation method, device, equipment and storage medium of laser radar positioning effect

    CN109459734A