A method and system for special scene positioning based on a binocular structured light camera

Abstract

The present invention relates to the technical field of vehicle status recognition, and more specifically, to a method and system for special scenario positioning based on a binocular structured light camera. The solution includes using an in-vehicle light intensity detector to determine whether binocular mode switching is required. Without switching to binocular mode, only conventional detection results are generated based on the captured data of the camera. When binocular mode is required, the current vehicle speed is judged to perform active projection illumination, and echo recording information is generated. Motion compensation is performed according to the echo recording information to obtain the target object, and triangulation ranging and coordinate transformation are performed on the target object to form the lane position. This solution selects a structured light binocular camera and combines special materials. The projector actively irradiates encoded special light onto the object, and the camera is used to detect and analyze the actively emitted light, receive and collect the echo information of the structured light irradiating the special medium on the road, and accurate detection distance information can be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle status recognition, and more specifically, to a method and system for special scenario positioning based on a binocular structured light camera. Background Art

[0002] Detecting road information based on passive detection instruments such as cameras, being limited by the fact that cameras are non-active detection instruments, is extremely vulnerable to factors such as weather and environment, resulting in information loss. And using lidar for joint detection to supplement the camera also has problems that lidar is relatively expensive, daily maintenance is not yet mature, it cannot be widely promoted in a short time, and the problem of difficult joint calculation of point cloud and image is relatively large.

[0003] Before the technology of the present invention, the prior art could not take into account the ranging and active light source capabilities of lidar while retaining the low price and other characteristics of the camera, and there were the following problems: adopting passive detection, it was easy to lose information on the lane, resulting in the vehicle being unable to run; second, some solutions adopted the fusion of lidar and camera, which was expensive. Summary of the Invention

[0004] In view of the above problems, the present invention proposes a method and system for special scenario positioning based on a binocular structured light camera. A structured light binocular camera is selected, and in combination with special materials, a projector actively irradiates encoded special light onto an object, and a camera is used to detect and analyze the actively emitted light, and the echo information of the structured light irradiating a special medium on the road is received and collected, so as to achieve accurate detection of distance information.

[0005] According to the first aspect of an embodiment of the present invention, a method for special scenario positioning based on a binocular structured light camera is provided.

[0006] In one or more embodiments, preferably, the method for special scenario positioning based on a binocular structured light camera includes:

[0007] Judging whether binocular mode switching is required through an in-vehicle light intensity detector, and generating a conventional detection result only based on the captured data of the camera without switching the binocular mode;

[0008] When binocular mode is required, judging the current vehicle speed for active irradiation by the projector to generate echo record information;

[0009] Performing motion compensation according to the echo record information to generate first compensation data;

[0010] Performing intensity correction according to the first compensation data to generate second compensation data;

[0011] Determine the area based on the second compensation data to obtain the target object, where the material arranged in the target area is a high-reflectivity material;

[0012] Perform triangulation ranging and coordinate transformation on the target object to form a lane position.

[0013] In one or more embodiments, preferably, the vehicle-mounted light intensity detector is used to determine whether to switch to the binocular mode. Without switching the binocular mode, a conventional detection result is generated only based on the captured data of the camera, which specifically includes:

[0014] Configure a light intensity detector outside the vehicle to obtain the light intensity of the current area in real time as the illuminance;

[0015] When it is determined that the illuminance satisfies the first calculation formula, start timing for insufficient illumination. When it does not satisfy the first calculation formula, set the insufficient illumination timing to 0;

[0016] When the insufficient illumination timing and the illuminance satisfy the second calculation formula, switch to the binocular mode. If not, start the traditional mode;

[0017] In the traditional mode, directly perform data processing through the camera to generate a conventional detection result;

[0018] The first calculation formula is:

[0019] G < Y

[0020] where G is the illuminance and Y is a preset judgment margin;

[0021] The second calculation formula is:

[0022]

[0023] where T is the insufficient illumination timing and C is a preset duration margin.

[0024] In one or more embodiments, preferably, when the binocular mode is required, the current vehicle speed is judged to perform active projection illumination by the projector to generate echo recording information, which specifically includes:

[0025] After entering the binocular mode, judge whether the current vehicle speed satisfies the third calculation formula;

[0026] If it does not satisfy the third calculation formula, issue a vehicle speed adjustment command and wait for the vehicle speed to satisfy the third calculation formula before starting the projector;

[0027] If the condition is met, directly start the projector to scan the surrounding area and obtain the target space. In the target space, the driving lane lines are covered with special materials.

[0028] Start the camera to obtain and record the echo information as the echo record information.

[0029] The third calculation formula is:

[0030] V<D

[0031] Where V is the current vehicle speed and D is the low-speed margin.

[0032] In one or more embodiments, preferably, performing motion compensation based on the echo record information to generate first compensation data specifically includes:

[0033] Set the detection period and the minimum processing interval.

[0034] Obtain the rotation and translation within the adjacent minimum processing interval through the sensors on the vehicle.

[0035] Compensate the echo information according to the current rotation and translation to form the first compensation data.

[0036] In one or more embodiments, preferably, performing intensity correction based on the first compensation data to generate second compensation data specifically includes:

[0037] After obtaining the first compensation data, extract the emission angle, emission time, and the returned echo intensity.

[0038] According to the emission angle, emission time, and the returned echo intensity, combine with the reflection characteristics of the corresponding material to judge the distance of each position as the second compensation data.

[0039] In one or more embodiments, preferably, performing area determination based on the second compensation data to obtain the target object, where the material arranged in the target area is a high-reflectivity material, specifically includes:

[0040] According to the second compensation data, the echo intensity of each position can be directly corresponding.

[0041] Calculate the gradient number of adjacent positions according to the echo intensity. When there is a large gradient, it is considered as the boundary of the target area.

[0042] Obtain the target object according to the boundary of the target area.

[0043] In one or more embodiments, preferably, performing triangulation ranging and coordinate transformation on the target object to form the lane position, specifically includes:

[0044] Perform boundary expansion based on the target object to form a target area with a preset shape;

[0045] Perform triangulation ranging based on the target area with the preset shape to form the corresponding lane position.

[0046] According to the second aspect of the embodiments of the present invention, a system for special scene positioning based on a binocular structured light camera is provided.

[0047] In one or more embodiments, preferably, the system for special scene positioning based on a binocular structured light camera includes:

[0048] A mode selection module, configured to determine whether binocular mode switching is required through an in-vehicle light intensity detector, and generate a conventional detection result only based on the captured data of the camera without switching the binocular mode;

[0049] A binocular mode operation module, configured to actively irradiate with a projector when binocular mode is required, and generate echo record information by judging the current vehicle speed;

[0050] A first compensation module, configured to perform motion compensation based on the echo record information to generate first compensation data;

[0051] A second compensation module, configured to perform intensity correction based on the first compensation data to generate second compensation data;

[0052] A target object module, configured to determine an area based on the second compensation data to obtain a target object, wherein the material arranged in the target area is a high-reflectivity material;

[0053] An information confirmation module, configured to perform triangulation ranging and coordinate transformation on the target object to form a lane position.

[0054] According to the third aspect of the embodiments of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described in any one of the first aspects of the embodiments of the present invention is implemented.

[0055] According to the fourth aspect of the embodiments of the present invention, an electronic device is provided, including a memory and a processor, where the memory is used to store one or more computer program instructions, and when the one or more computer program instructions are executed by the processor, the method described in any one of the first aspects of the embodiments of the present invention is implemented.

[0056] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0057] According to the solution of the present invention, by utilizing the characteristics of structured light, active detection can be carried out in special scenarios, so as not to lose the information on the lane and cause the vehicle to be unable to run. Relying on special materials and the acquired echo information, through a series of algorithm processing and precise analysis of deep learning, high-precision positioning ability is achieved.

[0058] The solution of the present invention has higher practicability, is cheaper than the fusion of lidar and camera in price, and the camera in the structured light camera can be reused.

[0059] Other features and advantages of the present invention will be described in the following specification, and part of them will become obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the written specification, claims, and drawings.

[0060] The technical solution of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the following drawings are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0062] Figure 1 It is a flowchart of a method for special scenario positioning based on a binocular structured light camera according to an embodiment of the present invention.

[0063] Figure 2 It is a flowchart of judging whether binocular mode switching is required through an in-vehicle light intensity detector in a method for special scenario positioning based on a binocular structured light camera according to an embodiment of the present invention, and generating a conventional detection result only based on the shooting data of the camera without switching the binocular mode.

[0064] Figure 3 It is a flowchart of actively irradiating by a projector according to the current vehicle speed to generate echo record information in a method for special scenario positioning based on a binocular structured light camera according to an embodiment of the present invention when binocular mode is required.

[0065] Figure 4 It is a flowchart of performing motion compensation according to the echo record information to generate first compensation data in a method for special scenario positioning based on a binocular structured light camera according to an embodiment of the present invention.

[0066] Figure 5It is a flowchart of intensity correction based on the first compensation data to generate the second compensation data in a method for special scene positioning based on a binocular structured light camera according to an embodiment of the present invention.

[0067] Figure 6 It is a flowchart of determining a region based on the second compensation data to obtain a target object in a method for special scene positioning based on a binocular structured light camera according to an embodiment of the present invention, wherein the material arranged in the target region is a high-reflectivity material.

[0068] Figure 7 It is a flowchart of performing triangulation ranging and coordinate transformation on the target object to form a lane position in a method for special scene positioning based on a binocular structured light camera according to an embodiment of the present invention.

[0069] Figure 8 It is a structural diagram of a system for special scene positioning based on a binocular structured light camera according to an embodiment of the present invention.

[0070] Figure 9 It is a structural diagram of an electronic device in an embodiment of the present invention. Detailed implementation manners

[0071] In some processes described in the specification, claims and above-mentioned drawings of the present invention, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0072] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0073] Detecting road information based on passive detection instruments such as cameras. Limited by the fact that cameras are non-active detection instruments, they are extremely vulnerable to factors such as weather and environment, resulting in information loss. Using lidar for joint detection to supplement cameras, there are also problems that lidar is relatively expensive, daily maintenance is not yet mature, it cannot be widely promoted in a short time, and the problem of difficult joint calculation of point cloud and pictures.

[0074] Before the technology of the present invention, the prior art could not take into account the ranging and active light source capabilities of lidar while retaining the low price and other characteristics of cameras, and there were the following problems: Using passive detection, it is easy to lose information on the lane, resulting in the vehicle being unable to run; Second, some solutions use the fusion of lidar and cameras, which are expensive.

[0075] In an embodiment of the present invention, a method and system for special scene positioning based on a binocular structured light camera are provided. This solution selects a structured light binocular camera and combines special materials. The projector actively irradiates encoded special light onto the object, and the camera detects and analyzes the actively emitted light, and receives and collects the echo information of the structured light irradiating the special medium on the road, and can achieve accurate detection distance information.

[0076] According to the first aspect of the embodiment of the present invention, a method for special scene positioning based on a binocular structured light camera is provided.

[0077] Figure 1 It is a flowchart of a method for special scene positioning based on a binocular structured light camera according to an embodiment of the present invention.

[0078] In one or more embodiments, preferably, the method for special scene positioning based on a binocular structured light camera includes:

[0079] S101. Determine whether to switch to the binocular mode through an in-vehicle light intensity detector, and generate a conventional detection result only based on the shooting data of the camera without switching the binocular mode;

[0080] S102. When the binocular mode needs to be switched, determine the current vehicle speed and perform active irradiation by the projector to generate echo record information;

[0081] S103. Perform motion compensation according to the echo record information to generate first compensation data;

[0082] S104. Perform intensity correction according to the first compensation data to generate second compensation data;

[0083] S105. Determine the area according to the second compensation data to obtain the target object, wherein the material arranged in the target area is a high reflectivity material;

[0084] S106. Perform triangulation ranging and coordinate transformation on the target object to form a lane position.

[0085] In an embodiment of the present invention, a binocular structured light camera is installed on a mobile carrier. When in certain special scenarios (such as rainy days, nights, tunnels, etc., environments with poor light), the projector actively detects and obtains physical information of a specific area through the camera. After receiving the data, the physical data is analyzed according to preset parameters and algorithms to determine information such as the position of the carrier. This solution uses intensity information to quickly determine the target area without the need for semantic analysis of the entire space, which can reduce the algorithm complexity. In addition, based on structured light and special materials, distance information can be obtained through the position of the special materials, and the camera can be reused, meeting the requirements for working in special environments.

[0086] Figure 2 It is a flowchart of a method for special scenario positioning based on a binocular structured light camera in an embodiment of the present invention, which uses an in-vehicle light intensity detector to determine whether to switch to the binocular mode and generate a conventional detection result only based on the captured data of the camera without switching the binocular mode.

[0087] Such as Figure 2 shown, in one or more embodiments, preferably, the method of using an in-vehicle light intensity detector to determine whether to switch to the binocular mode and generate a conventional detection result only based on the captured data of the camera without switching the binocular mode specifically includes:

[0088] S201. Configure a light intensity detector outside the vehicle to obtain the current light intensity of the area in real-time as the illuminance.

[0089] S202. When the illuminance satisfies the first calculation formula, start timing for non-compliance with the light, and when it does not satisfy the first calculation formula, set the non-compliance with the light timing to 0.

[0090] S203. When the non-compliance with the light timing and the illuminance satisfy the second calculation formula, switch to the binocular mode; if not, start the traditional mode.

[0091] S204. Directly perform data processing through the camera in the traditional mode to generate a conventional detection result.

[0092] The first calculation formula is:

[0093] G < Y

[0094] where G is the illuminance and Y is a preset judgment margin.

[0095] The second calculation formula is:

[0096]

[0097] Among them, T is the timing when the light illumination does not meet the standard, and C is the preset duration margin.

[0098] In an embodiment of the present invention, to implement this solution, a light intensity detector is equipped in the vehicle. When it is detected that the light intensity in the current area does not meet the set minimum value, for example, the previous state is a normal monocular situation, and when the condition of the light intensity meter <1000 lx is satisfied continuously for 1 s, the structured light algorithm is started. The reason for this is to consider the physical process of the structured light effect and the requirements of the device itself. The reflection process may be affected by the external ambient light more. In order to reduce interference, this threshold is set to ensure accuracy. When the light intensity is high, the camera can be used without turning on the structured light mode.

[0099] Figure 3 It is a flowchart of generating echo recording information by actively irradiating a projector by judging the current vehicle speed when a binocular mode is required in a method for special scene positioning based on a binocular structured light camera according to an embodiment of the present invention.

[0100] Such as Figure 3 As shown, in one or more embodiments, preferably, when a binocular mode is required, judging the current vehicle speed to actively irradiate the projector and generate echo recording information specifically includes:

[0101] S301. After entering the binocular mode, judge whether the current vehicle speed meets the third calculation formula;

[0102] S302. If the third calculation formula is not met, issue a vehicle speed adjustment command and wait for the vehicle speed to meet the third calculation formula before starting the projector;

[0103] S303. If it is met, directly start the projector to scan the surrounding area to obtain the target space. Among them, in the target space, the driving lane line is covered with a special material;

[0104] S304. Start the camera to obtain and record the echo information as the echo recording information;

[0105] The third calculation formula is:

[0106] V < D

[0107] Among them, V is the current vehicle speed and D is the low-speed margin.

[0108] In an embodiment of the present invention, the vehicle speed is set to a constant speed of 10 - 20 km / s. The reason is that the structured light camera generally has a limited detection distance and is vulnerable to strong external background light interference. It is usually used indoors in an environment with relatively dim background light, and more restrictive conditions are required for outdoor use. At the same time, considering structured light cameras based on different principles, it takes a certain period of time to act on the target object and process data for a period of time to generate road information (relatively poor real-time performance). If the vehicle speed is too fast, the scanning quality will be low, which is not conducive to fitting.

[0109] Figure 4 It is a flowchart of generating first compensation data by performing motion compensation according to the echo recording information in a method for special scene positioning based on a binocular structured light camera according to an embodiment of the present invention.

[0110] As Figure 4 shown, in one or more embodiments, preferably, the generating first compensation data by performing motion compensation according to the echo recording information specifically includes:

[0111] S401. Set a detection period and a minimum processing interval;

[0112] S402. Obtain the rotation and translation within the adjacent minimum processing interval through sensors on the vehicle;

[0113] S403. Compensate the echo information according to the current rotation and translation to form the first compensation data.

[0114] In an embodiment of the present invention, for a detection period T, a minimum processing time ΔT is set. The rotation and translation situations at two moments can be known through the equipment on the vehicle. The transformation matrix at each moment between T and T - 1 is obtained, and the specific rotation matrix at each moment is linearly interpolated. After determining the rotation matrix, all the data is transformed into the coordinate system at the T - 1 moment for analysis in combination with the previously calibrated internal parameters.

[0115] Figure 5 It is a flowchart of generating second compensation data by performing intensity correction according to the first compensation data in a method for special scene positioning based on a binocular structured light camera according to an embodiment of the present invention.

[0116] As Figure 5 shown, in one or more embodiments, preferably, the generating second compensation data by performing intensity correction according to the first compensation data specifically includes:

[0117] S501. After obtaining the first compensation data, extract the emission angle, emission time, and the returned echo intensity therein;

[0118] S502. Determine the distance of each position based on the emission angle, emission time, and the returned echo intensity, in combination with the reflection characteristics of the corresponding material, as the second compensation data.

[0119] In the embodiments of the present invention, the device itself records relevant emission angles, emission times, and returned echo intensities. Then, the detection distance is calculated through the built-in algorithm of the structured light camera. After obtaining these values, based on the echo equation corrected by the corrected data (the original equation is based on physical modeling, but it is difficult to meet in many cases. Therefore, considering data correction, using a standard diffuse reflection plate and adjustable lighting conditions in the laboratory environment, detecting the reflection conditions at different distances and angles, correcting the basic formula with data and fitting curves, and finally establishing the corresponding relationship between intensity and reflectivity), the detected data can be converted to a standardized distance, making the data have clear physical meanings and facilitating subsequent analysis based on information such as reflectivity.

[0120] Figure 6 It is a flowchart of determining a target object based on the second compensation data in a method for special scene positioning based on a binocular structured light camera according to an embodiment of the present invention, where the material arranged in the target area is a high-reflectivity material.

[0121] As Figure 6 shown, in one or more embodiments, preferably, determining a target object based on the second compensation data, where the material arranged in the target area is a high-reflectivity material, specifically includes:

[0122] S601. The echo intensity of each position can be directly corresponded according to the second compensation data;

[0123] S602. Calculate the gradient numbering of adjacent positions according to the echo intensity. When there is a large gradient, it is considered the boundary of the target area;

[0124] S603. Obtain the target object according to the boundary of the target area.

[0125] In the embodiments of the present invention, the analysis area in the data is determined. When the light wave sent acts on the special material, a large intensity value will be generated, which is quite different from the normal ground reflection situation. It can be directly divided through the threshold measured in the laboratory to complete the selection of the area of interest. These contents are completed during the optical calibration process of the device and a dedicated calibration table will be generated, which can improve the accuracy and processing speed. Through the light (intensity) meter detection, when the ambient light intensity is too low to support the camera detection, the projector is used for active illumination. When the light irradiates the special material, the camera receives special optical coding information, thereby distinguishing objects such as lane lines and quickly determining the target area.

[0126] Figure 7 It is a flowchart of triangulation ranging and coordinate transformation for the target object to form a lane position in a method for special scenario positioning based on a binocular structured light camera according to an embodiment of the present invention.

[0127] As Figure 7 shown, in one or more embodiments, preferably, the triangulation ranging and coordinate transformation for the target object to form a lane position specifically includes:

[0128] S701. Perform boundary expansion according to the target object to form a target area with a preset shape;

[0129] S702. Perform triangulation ranging according to the target area with the preset shape to form a corresponding lane position.

[0130] In an embodiment of the present invention, relevant data is imported into the structured light solution model. First, through a decoding algorithm, the information of the special encoded light is demodulated. Then, according to the relationship between pixels and spatial coordinates, coordinate system conversion is performed to convert the pixel coordinate system into a set world coordinate system (which can be set, and the northeast celestial convention coordinate system is recommended), and the corresponding relationship is analyzed through an algorithm. Based on the triangulation ranging method, distance information is determined. The processed data (coordinate information, intensity information, distance information, etc. converted to the world coordinate system, and the data exists in the form of point cloud at this time) is input into the deep learning module, the data is converted into a tensor form, the coordinate position is recorded, and it enters a similar deep learning model training. Finally, the lane line is fitted, the lane line information and distance are integrated, and combined with the map.

[0131] According to the second aspect of the embodiment of the present invention, a system for special scenario positioning based on a binocular structured light camera is provided.

[0132] Figure 8 It is a structural diagram of a system for special scenario positioning based on a binocular structured light camera according to an embodiment of the present invention.

[0133] In one or more embodiments, preferably, the system for special scenario positioning based on a binocular structured light camera includes:

[0134] A mode selection module 801, configured to determine whether binocular mode switching is required through an in-vehicle light intensity detector, and generate a conventional detection result only based on the captured data of the camera without switching the binocular mode;

[0135] A binocular mode operation module 802, configured to actively irradiate the projector by judging the current vehicle speed when binocular mode is required, and generate echo recording information;

[0136] The first compensation module 803 is configured to perform motion compensation based on the echo recording information to generate first compensation data;

[0137] The second compensation module 804 is configured to perform intensity correction based on the first compensation data to generate second compensation data;

[0138] The target object module 805 is configured to determine a region based on the second compensation data to obtain a target object, wherein the material arranged in the target region is a high-reflectivity material;

[0139] The information confirmation module 806 is configured to perform triangulation ranging and coordinate transformation on the target object to form a lane position.

[0140] In an embodiment of the present invention, through a series of modular designs, a system applicable to different structures is implemented. The system can achieve closed-loop, reliable, and efficient execution through acquisition, analysis, and control. Based on the structured light camera composed of a projector and a camera, the projector actively irradiates special encoded light onto the object, and the camera detects and analyzes the actively emitted light, receives and collects the echo information of the structured light irradiating on the special medium on the road, analyzes the pixel intensity, and relies on deep learning algorithms to process the pixel intensity information into road information applicable to fields such as intelligent vehicles, autonomous driving, and vehicle-road collaboration; and obtains the detection distance information through light encoding and pixel relationships.

[0141] According to a third aspect of an embodiment of the present invention, there is provided a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described in any one of the first aspects of the embodiments of the present invention is implemented.

[0142] According to a fourth aspect of an embodiment of the present invention, there is provided an electronic device. Figure 9 It is a structural diagram of an electronic device in an embodiment of the present invention. Figure 9 The shown electronic device is a device for special scenario positioning based on a general binocular structured light camera. The electronic device can be a device such as a smart phone or a tablet computer. As shown, the electronic device 900 includes a processor 901 and a memory 902. Among them, the processor 901 is electrically connected to the memory 902. The processor 901 is the control center of the terminal 900, connects various parts of the entire terminal through various interfaces and lines, executes various functions of the terminal and processes data by running or calling the computer program stored in the memory 902, and by calling the data stored in the memory 902, thereby performing overall monitoring of the terminal.

[0143] In this embodiment, the processor 901 in the electronic device 900 will load the instructions corresponding to the processes of one or more computer programs into the memory 902 according to the following steps, and the processor 901 will run the computer programs stored in the memory 902 to implement various functions: Determine whether binocular mode switching is required through the vehicle-mounted light intensity detector, and generate a conventional detection result only based on the captured data of the camera without switching the binocular mode; When binocular mode is required, judge the current vehicle speed to perform active projection illumination by the projector, and generate echo recording information; Perform motion compensation according to the echo recording information to generate first compensation data; Perform intensity correction according to the first compensation data to generate second compensation data; Determine the area according to the second compensation data to obtain the target object, where the material arranged in the target area is a high-reflectivity material; Perform triangulation ranging and coordinate transformation on the target object to form the lane position.

[0144] The memory 902 can be used to store computer programs and data. The computer programs stored in the memory 902 contain instructions that can be executed in the processor. The computer programs can form various functional modules. The processor 901 executes various functional applications and data processing by calling the computer programs stored in the memory 902.

[0145] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0146] The solution of the present invention utilizes the characteristics of structured light and can actively detect in special scenarios, so as not to lose the information on the lane and cause the vehicle to be unable to run. Relying on special materials and the obtained echo information, through a series of algorithm processing and precise analysis of deep learning, high-precision positioning ability is achieved.

[0147] The solution of the present invention has higher practicability, is cheaper than the fusion of lidar and camera in price, and can reuse the camera in the structured light camera.

[0148] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0149] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0150] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0151] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0152] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for special scene positioning based on a binocular structured light camera, characterized in that, The method includes: Judging whether binocular mode switching is required through an in-vehicle light intensity detector, and generating a conventional detection result only based on the captured data of the camera without switching the binocular mode; When binocular mode is required, judging the current vehicle speed to perform active projection illumination by the projector, and generating echo recording information; Performing motion compensation according to the echo recording information to generate first compensation data; Performing intensity correction according to the first compensation data to generate second compensation data; Determining a region according to the second compensation data to obtain a target object, wherein the material arranged on the target object is a high-reflectivity material; Performing triangulation ranging and coordinate transformation on the target object to form a lane position; Among them, the performing intensity correction according to the first compensation data to generate second compensation data specifically includes: After obtaining the first compensation data, extracting the emission angle, emission time, and returned echo intensity therein; Judging the distance of each position according to the emission angle, emission time, and returned echo intensity, in combination with the reflection characteristics of the corresponding material, as the second compensation data.

2. The method for special scene positioning based on a binocular structured light camera according to claim 1, characterized in that, The judging whether binocular mode switching is required through an in-vehicle light intensity detector, and generating a conventional detection result only based on the captured data of the camera without switching the binocular mode specifically includes: Configuring an illuminance detector outside the vehicle to obtain the current light intensity of the area in real time as the illuminance; When it is judged that the illuminance satisfies the first calculation formula, starting to time the non-compliance of the illuminance, and when it does not satisfy the first calculation formula, setting the non-compliance of the illuminance timing to 0; When the non-compliance of the illuminance timing and the illuminance satisfy the second calculation formula, switching to the binocular mode, and if not, starting the traditional mode, wherein the traditional mode generates a conventional detection result only based on the captured data of the camera; Directly performing data processing through the camera in the traditional mode to generate a conventional detection result; The first calculation formula is: G < Y Among them, G is the illuminance, and Y is a preset judgment margin; The second calculation formula is: Among them, T is the non-compliance of the illuminance timing, and C is a preset duration margin.

3. The method for special scene positioning based on a binocular structured light camera according to claim 2, characterized in that, The judging the current vehicle speed to perform active projection illumination by the projector when binocular mode is required, and generating echo recording information specifically includes: After entering the binocular mode, judging whether the current vehicle speed satisfies the third calculation formula; If the third calculation formula is not satisfied, then issuing a vehicle speed adjustment command and waiting for the vehicle speed to satisfy the third calculation formula before starting the projector; If it is satisfied, directly start the projector to scan the surrounding area to obtain a target space, wherein in the target space, the driving lane line is covered with a special material; Starting the camera to obtain and record the echo information as the echo recording information; The third calculation formula is: V < D Among them, V is the current vehicle speed, and D is a low-speed margin.

4. A method for special scene positioning based on a binocular structured light camera according to claim 3, characterized in that, The performing motion compensation according to the echo recording information to generate first compensation data specifically includes: Setting a detection period and a minimum processing interval; Obtaining the rotation and translation within the adjacent minimum processing interval through the sensors on the vehicle; Compensate the echo information according to the current rotation and translation to form the first compensation data.

5. A method for special scene positioning based on a binocular structured light camera according to claim 1, characterized in that, Perform region determination according to the second compensation data to obtain a target object, where the material arranged on the target object is a high-reflectivity material, specifically including: The echo intensity corresponding to each position can be directly obtained according to the second compensation data; Calculate the gradient number of adjacent positions according to the echo intensity. When there is a large gradient, it is considered the boundary of the target area; Obtain the target object according to the boundary of the target area.

6. The method for special scene positioning based on a binocular structured light camera according to claim 1, characterized in that Perform triangulation ranging and coordinate transformation on the target object to form a lane position, specifically including: Expand the boundary according to the target object to form a target area with a preset shape; Perform triangulation ranging according to the target area with the preset shape to form a corresponding lane position.

7. A system for special scene positioning based on a binocular structured light camera, characterized in that, The system is used to implement the method described in any one of claims 1-6. The system includes: A mode selection module for judging whether binocular mode switching is required through an in-vehicle light intensity detector, and generating a conventional detection result only based on the captured data of the camera without switching the binocular mode; A binocular mode operation module for actively irradiating the projector by judging the current vehicle speed when binocular mode is required, and generating echo record information; A first compensation module for performing motion compensation according to the echo record information to generate first compensation data; A second compensation module for performing intensity correction according to the first compensation data to generate second compensation data; A target object module for performing region determination according to the second compensation data to obtain a target object, where the material arranged on the target object is a high-reflectivity material; An information confirmation module for performing triangulation ranging and coordinate transformation on the target object to form a lane position.

8. A computer-readable storage medium storing computer program instructions thereon, characterized in that, The computer program instructions, when executed by a processor, implement the method described in any one of claims 1-6.

9. An electronic device, comprising a memory and a processor, characterized in that, The memory is used to store one or more computer program instructions, where the one or more computer program instructions are executed by the processor to implement the method described in any one of claims 1-6.

Images