A three-dimensional navigation method, system, device and medium for a vehicle

Abstract

The application discloses a kind of car stereoscopic navigation method, comprising: the situation around the vehicle body detected by 3D radar is collected by sensing module;Image information after processing is uploaded to cloud;The image combined with cloud information is transmitted to decision module, and the optimal path information of the navigation information of vehicle is made;After determining feasibility, generate navigation information;According to navigation information, generate prompt and path information display, finally navigation information and path information are displayed on the display of display module.The car stereoscopic navigation method provided by the application is more accurate, real-time, can help vehicle accurately find the road segment where it is located in complex road segment, avoid driver getting lost, so that driver fully understands surrounding state, judges road traffic condition in real time;Information exchange between vehicle and road is fed back to three-dimensional stereoscopic navigation, for monitoring road surface condition, guiding driver to select the best driving path.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile navigation, and in particular to a method, system, device and medium for automobile stereo navigation. Background Art

[0002] Navigation is the process of guiding a carrier safely and reliably from its starting point to its destination. It uses scientific principles and methods such as electricity, magnetism, optics, and mechanics to measure parameters related to the moment-by-moment position of moving objects such as airplanes in the air, ships at sea, submarines in the ocean, vehicles on land, and people, thereby achieving the positioning of the moving body and correctly guiding it from the starting point along the predetermined route to the destination safely, accurately, and economically. This technology is called navigation technology.

[0003] Navigation technologies can be categorized by their principles for obtaining navigation information, including radio navigation, satellite navigation, astronomical navigation, inertial navigation, terrain-aided navigation, integrated navigation, combined navigation, and landing systems specifically designed for aircraft and other aircraft. If a moving object's navigation and positioning data can be obtained solely by onboard navigation equipment, operating on the dead reckoning principle, this is called autonomous or self-contained navigation, such as inertial navigation. If the position of a moving object is determined solely by receiving navigation information broadcast from ground-based navigation stations or satellites, this is called dependent navigation, of which radio navigation and satellite navigation are typical examples. A navigation system is the general term for any combination of equipment capable of performing a specific navigation and positioning task. Examples include radio navigation systems, satellite navigation systems, astronomical navigation systems, inertial navigation systems, combined navigation systems, integrated navigation systems, terrain-aided navigation systems, and landing guidance and port navigation systems.

[0004] From an application perspective, car GPS navigation can be categorized into two types. The first involves vehicles equipped with independent GPS navigation devices for autonomous navigation. For example, the MS6000 system, developed by VDO, a global leader in navigation systems, integrates audio and navigation technology, using intuitive menus and an easy-to-use remote control. Simply enter your destination and select one of up to eight routes, and the system will guide you on your way. Directions are provided via voice prompts via the vehicle's speakers, and navigation images are displayed on a large color screen. Panasonic of Japan has released a multi-purpose car GPS navigation system equipped with a CD drive and a 5.8-inch TFT LCD. The second type involves vehicle location tracking and monitoring systems, which serve as public information services. These systems consist of an on-board GPS receiver and a GPS positioning and navigation unit at a monitoring center. They communicate using dedicated lines or public networks, providing navigation information, tracking and dispatching, security and anti-theft services, information query, and rescue services to vehicles. Examples of this type include Beijing's "Aoxing Skynet" GPS information service system and Nanjing's 110 emergency patrol car GPS system.

[0005] The two-dimensional plane navigation currently available on the market often cannot accurately locate the vehicle's position on complex roads; drivers do not understand the road conditions and the driving conditions of other vehicles. Summary of the Invention

[0006] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0007] In view of the above-mentioned problems, the present invention is proposed.

[0008] Therefore, the technical problem solved by the present invention is to optimize the problems that the existing navigation methods have the problem that the driver does not understand the road conditions and the driving conditions of other vehicles, and the two-dimensional plane navigation often cannot accurately locate the vehicle position on complex road sections.

[0009] To solve the above technical problems, the present invention provides the following technical solutions: a three-dimensional vehicle navigation method, comprising:

[0010] The perception module collects the surrounding conditions of the vehicle body detected by the 3D radar;

[0011] Upload the processed image information to the cloud and obtain cloud information through big data;

[0012] The image combined with cloud information is transmitted to the decision-making module to make the optimal path information for the vehicle's navigation information;

[0013] Analyze and judge the path information, and generate navigation information after determining feasibility;

[0014] Prompts and path information are generated based on the navigation information, and finally the navigation information and path information are displayed on the display of the display module.

[0015] The vehicle stereo navigation method of the present invention is characterized in that: the acquisition of the surrounding conditions of the vehicle body detected by the 3D radar includes: image extraction through a first-stage differential operator, and after analysis and detection, obtaining edge width pixels of the image again through the zero crossing of a second-stage differential operator; simultaneously, identifying noise interference, and if the perception module perceives a suspected noise factor that seriously affects the quality of the remote sensing image, directly analyzing the suspected noise factor;

[0016] When the noise description does not conform to the probability distribution and probability density distribution, the influencing factors are ignored and the collected information is uploaded to the cloud;

[0017] When the noise description conforms to the probability distribution and probability density distribution, the influencing factor is determined to be noise interference. Until all suspected noise factors no longer conform to the probability distribution and probability density distribution, the image information after noise removal is uploaded to the cloud.

[0018] If the perception module does not perceive any suspected noise factors that seriously affect the quality of the remote sensing image, the image information will be directly uploaded to the cloud.

[0019] The vehicle 3D navigation method of the present invention is characterized in that: the acquisition of cloud information through big data includes: uploading image information collected by the perception module to the cloud while obtaining GPS positioning information of the collected image, thereby achieving all-round network connection between the vehicle and the cloud platform, between vehicles, and between vehicles and roads;

[0020] If the location information is uploaded late, the location information will be corrected based on the route and vehicle speed;

[0021] If the location information is uploaded without delay or the location information has been corrected, the image information obtained by other data sources is locked in the cloud;

[0022] When the time interval between the information obtained from other data sources and the current information is within the average interval of this road section, the navigation information of the scene is predicted using the information obtained from other data sources;

[0023] When the time interval between the information obtained from other data sources and the current information is not within the average interval of this road section, an unknown factor prompt will be made when predicting the navigation information based on the time interval between the information obtained from other data sources.

[0024] The vehicle 3D navigation method of the present invention is characterized in that: the step of obtaining cloud information further comprises: obtaining altitude information while obtaining the plane position of the data source, thereby matching the 3D position; and determining the specific position according to the driving direction;

[0025] If the actual road conditions corresponding to the acquired height and driving direction do not match the corresponding three-dimensional positioning, the three-dimensional positioning is performed again;

[0026] If the actual road conditions corresponding to the acquired altitude and driving direction are consistent with the three-dimensional positioning, the accuracy of the three-dimensional positioning is recognized.

[0027] The vehicle stereo navigation method of the present invention is characterized in that: the image combined with the cloud information is transmitted to the decision module, including: further screening the image information and confirming the path;

[0028] If any factor that has no impact on driving safety appears in the cloud information, it will be ignored;

[0029] If factors that affect driving safety appear in the cloud information, the navigation path will be simulated based on the impact and factors.

[0030] The vehicle 3D navigation method of the present invention is characterized in that: the confirmation of the path further comprises: when there are factors that affect driving safety, the path is selected based on the degree of impact on safety;

[0031] If it is determined that the original driving route has no serious impact on driving safety, describe the influencing factors;

[0032] When the user chooses to avoid this factor, all such affected sections will be excluded and a route without such influence will be simulated;

[0033] When the user chooses to ignore this factor, the decision module will treat such factors as normal in this use and simulate the optimal path;

[0034] If the user does not select whether to avoid the factor, the default option is to ignore the factor.

[0035] If it is determined that the original driving route has a serious impact on driving safety, it will automatically switch to other priority routes until the impact on driving safety is no longer serious, and the reason for changing the route will be generated.

[0036] The vehicle stereo navigation method of the present invention is characterized in that: navigation information and path information are displayed on a display module, and the path simulated by the decision module is dynamically simulated to obtain a high-resolution real image;

[0037] If the display mode is selected as 3D display when the vehicle is started, the system will not automatically remind you to change the display mode during the entire process.

[0038] If the display mode is selected as 2D display when the vehicle is started, the positioning information display will immediately execute a 3D display mode switching request to the user before entering a complex 3D road section;

[0039] When the user does not make a selection, the preset mode is executed according to the pre-set settings.

[0040] A three-dimensional automobile navigation system, characterized by comprising:

[0041] The perception module collects the surrounding conditions of the vehicle body detected by the 3D radar and uploads the processed image information to the cloud;

[0042] The decision-making module simulates the vehicle's navigation path based on the information fed back by the cloud;

[0043] The display module dynamically presents the path information simulated by the decision module.

[0044] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0045] A computer-readable storage medium stores a computer program thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the methods of the present invention.

[0046] The beneficial effects of the present invention are as follows: the automobile stereo navigation method provided by the present invention uses computer vision technology combined with vehicle networking technology to achieve three-dimensional navigation, which is more accurate and real-time than traditional technologies. It can help vehicles accurately find the road section they are on on complex roads, preventing drivers from getting lost; the communication between vehicles is fed back into the three-dimensional navigation in real time, including information such as vehicle position and driving speed, so that the driver can fully understand the surrounding conditions and judge the road traffic conditions in real time; the information exchange between the vehicle and the road is fed back into the three-dimensional navigation to monitor the road surface conditions and guide the driver to choose the best driving path. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0048] Figure 1 An overall flow chart of a vehicle stereo navigation method provided by the first embodiment of the present invention;

[0049] Figure 2 An operation diagram of a car stereo navigation system provided by a second embodiment of the present invention;

[0050] Figure 3 A functional schematic diagram of a decision module in a car stereo navigation system provided by a second embodiment of the present invention;

[0051] Figure 4 An overall conceptual diagram of a vehicle stereo navigation method provided by a second embodiment of the present invention;

[0052] Figure 5 A three-dimensional positioning determination function diagram of a vehicle stereo navigation method provided by a second embodiment of the present invention;

[0053] Figure 6 A schematic diagram of a path planning function of a three-dimensional vehicle navigation method provided by a second embodiment of the present invention;

[0054] Figure 7 A schematic diagram of display mode switching operation in a vehicle stereo navigation method provided by a second embodiment of the present invention;

[0055] Figure 8 1 is an internal structure diagram of a computer device in two embodiments of the present invention. DETAILED DESCRIPTION

[0056] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0059] The present invention is described in detail with reference to schematic diagrams. For ease of illustration, cross-sectional views of device structures may be partially enlarged and not to scale when describing embodiments of the present invention. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0060] In the description of the present invention, it should be noted that the terms "upper, lower, inner, and outer" and other references to orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0061] In this disclosure, unless otherwise specified or limited, the terms "mounted, connected, and connected" should be understood broadly. For example, they may refer to fixed, removable, or integral connections. They may also refer to mechanical, electrical, or direct connections, indirect connections through an intermediary, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure.

[0062] Example 1

[0063] Reference Figure 1 , as an embodiment of the present invention, provides a vehicle stereo navigation method, comprising:

[0064] S1: The perception module collects the surrounding conditions of the vehicle body detected by the 3D radar;

[0065] Furthermore, computer vision technology image preprocessing: In the application of computer vision technology, image preprocessing is performed before template matching. The final required image is processed based on a specific template, and its accuracy is judged based on the resolution of the image output.

[0066] After image preprocessing, the binary edge image can be extracted from the image, further improving the image processing effect. After a certain period of innovation and development, the image preprocessing technology in current computer vision technology has developed into a one-stage differential operator and a two-stage differential operator. That is, the image is first extracted through the one-stage differential operator, and after analysis and detection, the zero crossing of the two-stage differential operator is used again to obtain the edge width pixels of the image.

[0067] It should be noted that while extracting the image, noise interference is identified. If the perception module perceives a suspected noise factor that seriously affects the quality of the remote sensing image, the suspected noise factor is directly analyzed; when the noise description does not conform to the probability distribution and probability density distribution, the influencing factor is ignored and the collected information is uploaded to the cloud; when the noise description conforms to the probability distribution and probability density distribution, the influencing factor is determined to be noise interference; until all suspected noise factors do not conform to the probability distribution and probability density distribution, the image information after noise removal is uploaded to the cloud; if the perception module does not perceive a suspected noise factor that seriously affects the quality of the remote sensing image, the image information is directly uploaded to the cloud.

[0068] It should also be noted that image noise refers to unnecessary or redundant interfering information present in image data. The presence of noise severely impacts the quality of remote sensing images and, therefore, must be corrected before image enhancement and classification processes. Any factor in an image that hinders the perception of information is considered image noise. Noise can theoretically be defined as "random error that is unpredictable and can only be understood using probabilistic statistics." Therefore, it is appropriate to view image noise as a multidimensional random process, and the method for describing noise can be borrowed from that of random processes, namely, using their probability distribution function and probability density distribution function.

[0069] In this way, the image refinement step can be omitted, a more impressive edge effect can be obtained, and the accuracy of the final result can be better guaranteed. Moreover, under the meticulous detection link, the precision of the image processing program will be greatly improved, which gives it a huge application advantage in three-dimensional image presentation.

[0070] S2: Upload the processed image information to the cloud and obtain cloud information through big data;

[0071] Furthermore, when uploading the image information collected by the perception module to the cloud, the GPS positioning information of the collected image is obtained, realizing a full range of network connections between the vehicle and the cloud platform, vehicle to vehicle, and vehicle to road;

[0072] If the location information is uploaded late, the location information will be corrected based on the route and vehicle speed;

[0073] If the location information is uploaded without delay or the location information has been corrected, the image information obtained by other data sources is locked in the cloud;

[0074] When the time interval between the information obtained from other data sources and the current information is within the average interval of this road section, the navigation information of the scene is predicted using the information obtained from other data sources;

[0075] When the time interval between the information obtained from other data sources and the current information is not within the average interval of this road section, an unknown factor prompt will be made when predicting the navigation information based on the time interval between the information obtained from other data sources.

[0076] It should be noted that the unknown factor prompt specifically refers to danger prediction. For example, if there is no data source transmitting road conditions on path a after a heavy snowfall, then it is judged that path a has a large instability factor within the city clearance efficiency time.

[0077] Acquiring cloud information further includes: acquiring altitude information while acquiring the plane position of the data source, thereby matching the three-dimensional position; and determining the specific position according to the driving direction;

[0078] If the actual road conditions corresponding to the acquired height and driving direction do not match the corresponding three-dimensional positioning, the three-dimensional positioning is performed again;

[0079] If the actual road conditions corresponding to the acquired altitude and driving direction are consistent with the three-dimensional positioning, the accuracy of the three-dimensional positioning is recognized.

[0080] It should be noted that the driving direction is different at different heights at the same location. Overpasses and mountain roads are not built in the same direction at different heights at the same location, so it is reasonable to use height and driving direction to determine positioning.

[0081] It should also be noted that uploading data to the cloud implements the Internet of Vehicles (IoV) information and communication technology, enabling comprehensive network connectivity between vehicles and cloud platforms, vehicles and other vehicles, and vehicles and roads. IoV utilizes sensor technology to perceive vehicle status information, and leverages wireless communication networks and modern intelligent information processing technologies to achieve intelligent traffic management, smart decision-making for traffic information services, and intelligent vehicle control.

[0082] S3: The image combined with cloud information is transmitted to the decision-making module to make the optimal path information for the vehicle's navigation information.

[0083] After further screening of the image information, the path is confirmed;

[0084] If any factor that has no impact on driving safety appears in the cloud information, it will be ignored;

[0085] If factors that affect driving safety appear in the cloud information, the navigation path will be simulated based on the impact and factors.

[0086] When there are factors that affect driving safety, the route is selected based on the degree of impact on safety;

[0087] If it is determined that the original driving route has no serious impact on driving safety, describe the influencing factors;

[0088] When the user chooses to avoid this factor, all such affected sections will be excluded and a route without such influence will be simulated;

[0089] When the user chooses to ignore this factor, the decision module will treat such factors as normal in this use and simulate the optimal path;

[0090] If the user does not select whether to avoid the factor, the default option is to ignore the factor.

[0091] If it is determined that the original driving route has a serious impact on driving safety, it will automatically switch to other priority routes until the impact on driving safety is no longer serious, and the reason for changing the route will be generated.

[0092] It should be noted that user safety is paramount when planning navigation routes. While ensuring basic safety, different users may react differently to the same road conditions. Therefore, routes are planned based on user judgment and preferences.

[0093] At the same time, when the system automatically changes the path, it generates a reason to ensure the user's understanding and basic judgment of the path.

[0094] S4: Generate prompts and path information displays based on the navigation information, and finally display the navigation information and path information on a display of the display module.

[0095] The navigation information and path information are displayed on the display module, and the path simulated by the decision module is dynamically simulated to obtain a high-resolution real image;

[0096] If the display mode is selected as 3D display when the vehicle is started, the system will not automatically remind you to change the display mode during the entire process.

[0097] If the display mode is selected as 2D display when the vehicle is started, the positioning information display will immediately execute a 3D display mode switching request to the user before entering a complex 3D road section;

[0098] When the user does not make a selection, the preset mode is executed according to the pre-set settings.

[0099] It should be noted that some users are not used to using three-dimensional navigation on flat roads, but are accustomed to two-dimensional navigation; however, when about to enter a complex three-dimensional road section, the advantages and stability and accuracy of three-dimensional navigation become prominent, so users in two-dimensional mode are requested to switch modes.

[0100] At the same time, if the user does not make a selection, the mode switching cannot be forced, and the switching of the preset mode is executed or not according to the user's customized preset.

[0101] It's also worth noting that data collection and monitoring are performed using computers that simulate human vision. After acquiring the image, the computer dynamically simulates it to produce a high-resolution, realistic image, ultimately achieving a three-dimensional image. This dynamic image simulation is then compared and analyzed with the actual surrounding vehicle conditions, roads, and buildings to obtain highly accurate data.

[0102] This embodiment further provides a computing device, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method proposed in the above embodiment.

[0103] This embodiment further provides a storage medium storing a computer program, which, when executed by a processor, implements a vehicle stereo navigation method as proposed in the above embodiment.

[0104] The storage medium proposed in this embodiment and the automobile stereo navigation method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0105] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, database, or other media used in the embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory, magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory, magnetic random access memory, ferroelectric memory, phase change memory, graphene memory, etc. Volatile memory may include random access memory or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory or dynamic random access memory, etc. The database involved in the embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchain.

[0106] The processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., but are not limited thereto.

[0107] Example 2

[0108] Reference Figure 2-8 , which is an embodiment of the present invention, provides a car stereo navigation method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0109] This patent utilizes the vehicle's T-BOX for data collection and stores CAN data in the IoV cloud as a data foundation. Three-dimensional navigation relies on onboard cameras for signal acquisition and utilizes computer vision techniques for image preprocessing and scene reconstruction to establish 3D navigation. Cloud-based data, serving as the foundation for 3D navigation, feeds real-time information from vehicle-to-vehicle communication and vehicle-to-road traffic into the 3D navigation system. This allows drivers to accurately locate their vehicle on complex roads through 3D navigation, providing a comprehensive understanding of traffic conditions and guiding them to choose the optimal route.

[0110] The following demonstrates this through path simulation of the simulation scenario.

[0111] Scenario 1: A path with a 3D positioning height of 10m and an east-west navigation direction;

[0112] The actual three-dimensional positioning height of the car is a path of 20m, and the direction in the navigation is north-south.

[0113] When the car is driving on the path, the positioning information shows a three-dimensional height dimension of 10m. At this time, based on the car's driving path, it is judged that the actual road of the car is north-south instead of east-west. The three-dimensional positioning is judged to be inaccurate and the three-dimensional positioning is corrected.

[0114] After positioning and route confirmation, the output is a path with the actual three-dimensional positioning height of the car at 20m, running in a north-south direction.

[0115] Scenario 2: Application of the present invention in complex scenarios;

[0116] The vehicle is traveling toward the top of a mountain. Heavy snow fell the previous night, and the city's road maintenance efforts prevented the mountain road from being cleared of snow. However, the cloud detected road condition information for this section uploaded by other data sources, indicating that this section poses a minor impact on vehicle safety.

[0117] When the vehicle drives down a mountain in 2D navigation mode, the system will pop up a prompt to switch to 3D navigation display;

[0118] User-defined default switch to 3D display;

[0119] The system automatically switches to three-dimensional navigation display mode and reminds the user of road conditions. If the user chooses to ignore this factor, the system will provide specific image prompts of snow accumulation and slippery road hazards on the road section based on the cloud information of the Internet of Vehicles, providing early warning.

[0120] Table 1 shows the navigation accuracy comparison between the present invention and traditional navigation in complex three-dimensional road conditions in mountainous cities for 10 times:

[0121] Table 1:

[0122] frequency The present invention Traditional navigation 1 precise precise 2 precise Deviation 3 precise precise 4 precise Deviation 5 precise Deviation 6 Deviation Deviation 7 precise precise 8 precise Deviation 9 precise precise 10 precise precise

[0123] It can be seen that the navigation accuracy of the present invention for complex three-dimensional road sections is significantly higher than that of the traditional method.

[0124] Table 2 shows the navigation accuracy comparison between the present invention and traditional navigation in simple two-dimensional road conditions for 10 times:

[0125] Table 2:

[0126] frequency The present invention Traditional navigation 1 precise precise 2 precise precise 3 precise precise 4 precise precise 5 precise precise 6 precise precise 7 precise precise 8 precise precise 9 precise precise 10 precise precise

[0127] It can be seen that in the two-dimensional navigation mode, the accuracy of the present invention is not inferior to that of the traditional two-dimensional navigation.

[0128] Table 3 compares the navigation accuracy of the present invention in 3D mode with that of traditional 2D navigation in simple 2D road conditions for 10 times:

[0129] Table 3:

[0130] frequency The present invention Traditional navigation 1 precise precise 2 precise precise 3 precise precise 4 precise precise 5 precise precise 6 precise precise 7 precise precise 8 precise precise 9 precise precise 10 precise precise

[0131] It can be seen that in the navigation of the three-dimensional mode, the accuracy of the present invention is not inferior to that of the traditional two-dimensional navigation.

[0132] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A 3D car navigation method, characterized in that: include: The perception module collects the surrounding conditions of the vehicle body detected by the 3D radar; Upload the processed image information to the cloud and obtain cloud information through big data; The image combined with cloud information is transmitted to the decision-making module to make the optimal path information for the vehicle's navigation information; Analyze and judge the path information, and generate navigation information after determining feasibility; generating prompts and path information displays based on the navigation information, and ultimately displaying the navigation information and path information on a display of a display module; The acquisition of cloud information through big data includes: uploading the image information collected by the perception module to the cloud while obtaining GPS positioning information of the collected image, thereby achieving all-round network connection between the vehicle and the cloud platform, between vehicles and vehicles, and between vehicles and roads; If the location information is uploaded late, the location information will be corrected based on the route and vehicle speed; If the location information is uploaded without delay or the location information has been corrected, the image information obtained by other data sources is locked in the cloud; When the time interval between the information obtained from other data sources and the current information is within the average interval of this road section, the navigation information is predicted using the information obtained from other data sources; When the time interval between the information obtained from other data sources and the current information is not within the average interval of this road section, an unknown factor prompt will be made when predicting navigation information based on the time interval between the information obtained from other data sources; Acquiring cloud information further includes: acquiring altitude information while acquiring the plane position of the data source, thereby matching the three-dimensional position; and determining the specific position according to the driving direction; If the actual road conditions corresponding to the acquired height and driving direction do not match the corresponding three-dimensional positioning, the three-dimensional positioning is performed again; If the actual road conditions corresponding to the acquired altitude and driving direction are consistent with the three-dimensional positioning, the accuracy of the three-dimensional positioning is recognized.

2. The vehicle stereo navigation method according to claim 1, wherein: The acquisition of the surrounding conditions of the vehicle body detected by the 3D radar includes: image extraction through a first-stage differential operator, and after analysis and detection, obtaining the edge width pixels of the image again through the zero crossing of a second-stage differential operator; at the same time, identifying noise interference. If the perception module perceives suspected noise factors that seriously affect the quality of the remote sensing image, the suspected noise factors are directly analyzed; When the noise description does not conform to the probability distribution and probability density distribution, the influencing factors are ignored and the collected information is uploaded to the cloud; When the noise description conforms to the probability distribution and probability density distribution, the influencing factor is determined to be noise interference. Until all suspected noise factors no longer conform to the probability distribution and probability density distribution, the image information after noise removal is uploaded to the cloud. If the perception module does not perceive any suspected noise factors that seriously affect the quality of the remote sensing image, the image information will be directly uploaded to the cloud.

3. The vehicle stereo navigation method according to claim 2, wherein: The image combined with the cloud information is transmitted to the decision module, including: confirming the path after further screening the image information; If any factor that has no impact on driving safety appears in the cloud information, it will be ignored; If factors that affect driving safety appear in the cloud information, the navigation path will be simulated based on the impact and factors.

4. The vehicle stereo navigation method according to claim 3, wherein: The confirmation of the path further includes: when there are factors that affect driving safety, determining and selecting a path based on the degree of impact on safety; If it is determined that the original driving route has no serious impact on driving safety, describe the influencing factors; When the user chooses to avoid this factor, all such affected sections will be excluded and a route without such influence will be simulated; When the user chooses to ignore this factor, the decision module will treat such factors as normal in this use and simulate the optimal path; If the user does not select whether to avoid the factor, the default option is to ignore the factor. If it is determined that the original driving route has a serious impact on driving safety, it will automatically switch to other priority routes until the impact on driving safety is no longer serious, and the reason for changing the route will be generated.

5. The vehicle stereo navigation method according to claim 4, wherein: The navigation information and path information are displayed on the display module, and the path simulated by the decision module is dynamically simulated to obtain a high-resolution real image; If the display mode is selected as 3D display when the vehicle is started, the system will not automatically remind you to change the display mode during the entire process. If the display mode is selected as 2D display when the vehicle is started, the positioning information display will immediately execute a 3D display mode switching request to the user before entering a complex 3D road section; When the user does not make a selection, the preset mode is executed according to the pre-set settings.

6. A car stereo navigation system, characterized in that: include: The perception module collects the surrounding conditions of the vehicle body detected by the 3D radar and uploads the processed image information to the cloud; The decision-making module simulates the vehicle's navigation path based on the information fed back by the cloud; The display module dynamically presents the path information simulated by the decision module.

7. A computer device comprising: memory and processor; The memory stores a computer program, and is characterized in that the processor implements the steps of the method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images