Laser radar intensity calibration method, system and device and storage medium

Abstract

The embodiment of the invention provides a laser radar intensity calibration method, system and device and a storage medium, and the method comprises the steps: obtaining the original data of a target region collected by a laser radar, the original data comprises a plurality of original data sets, and each original data set corresponds to a sub-region in the target region; selecting one of the plurality of original data sets as a target data set; calibrating the target data set to obtain a calibration result; acquiring a test data set; obtaining a calibration data set based on the test data set and the calibration result; based on the calibration data set, judging whether the calibration result meets requirements or not; and outputting the calibration result in response to the condition that the calibration result meets the requirement.

Description

Technical Field

[0001] The present invention relates to the field of laser radar technology, and in particular to a laser radar intensity calibration method, system, device and storage medium. Background Art

[0002] LiDAR is a sensor capable of autonomous detection. LiDAR can create a three-dimensional representation of the surrounding environment by emitting laser beams. LiDAR emits a laser beam into the environment, which is reflected back to the LiDAR from the surrounding environment. LiDAR creates a point cloud corresponding to the three-dimensional representation of the surrounding environment by measuring the flight time and signal strength of the returned laser beam. The signal strength of the returned laser beam is not only related to the reflectivity of the detected object, but also depends on many other factors, such as the distance from the LiDAR to the detected object, the incident angle of the laser beam, the temperature of the surrounding environment, the power level of the channel emitting the laser beam, and other factors (for example, the alignment between the LiDAR's transmitter and detector), so that different laser beams reflected from the same material will produce different signal intensities. Therefore, it is necessary to calibrate the intensity of the returned laser beam.

[0003] Therefore, it is hoped that a lidar intensity calibration method can be provided to achieve efficient and accurate lidar intensity calibration. Summary of the invention

[0004] An embodiment of the present specification provides a laser radar intensity calibration method, including: obtaining raw data of a target area collected by a laser radar, the raw data including multiple raw data sets, each of the raw data sets corresponding to a sub-area in the target area; selecting one of the multiple raw data sets as a target data set; calibrating the target data set to obtain a calibration result; obtaining a test data set; obtaining a calibration data set based on the test data set and the calibration result; based on the calibration data set, determining whether the calibration result meets the requirements; and in response to the calibration result meeting the requirements, outputting the calibration result.

[0005] The embodiment of the present specification also provides a laser radar intensity calibration system, including: an acquisition module, used to acquire original data of a target area collected by a laser radar, the original data including multiple original data sets, each of the original data sets corresponding to a sub-area in the target area, and the acquisition module is also used to acquire a test data set; a selection module, used to select one of the multiple original data sets as a target data set; a calibration module, used to calibrate the target data set to obtain a calibration result; a determination module, used to obtain a calibration data set based on the test data set and the calibration result; a judgment module, used to judge whether the calibration result meets the requirements based on the calibration data set; a response module, used to output the calibration result in response to the calibration result meeting the requirements.

[0006] An embodiment of the present specification also provides a laser radar intensity calibration device, including a processor, and the processor is used for the laser radar intensity calibration method described in any embodiment of the present specification.

[0007] An embodiment of the present specification also provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the laser radar intensity calibration method described in any embodiment of the specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1A is a schematic diagram of an application scenario of a laser intensity calibration system according to some embodiments of this specification;

[0010] Figure 1B is an exemplary structural block diagram of a laser radar according to some embodiments of this specification;

[0011] Figure 2 is an exemplary module diagram of a laser radar intensity calibration system according to some embodiments of this specification;

[0012] Figure 3 is an exemplary flow chart of a laser radar intensity calibration method according to some embodiments of this specification;

[0013] Figure 4 is an exemplary flow chart for determining whether a calibration result meets the requirements according to some embodiments of this specification;

[0014] Figure 5is an exemplary flow chart for determining whether a calibration result meets the requirements according to some embodiments of this specification;

[0015] Figure 6 This is an exemplary flowchart for determining whether the calibration results meet the requirements according to some embodiments of this specification. DETAILED DESCRIPTION

[0016] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0017] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0018] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0019] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0020] Figure 1A It is a schematic diagram of an application scenario of a laser intensity calibration system according to some embodiments of this specification.

[0021] The system and method in this specification can be applied to the scene of laser intensity calibration. The calibration results can be applied to application scenarios using laser intensity, such as intelligent mobile control (e.g., autonomous driving, robots, etc.), detection, identification, resolution, positioning and tracking of targets. Autonomous driving can include pure unmanned driving scenarios without a driver, assisted driving modules in vehicles and other scenarios. The assisted driving module in the vehicle can autonomously control the vehicle's driving, and can also output driving prompts to the driver. The vehicle can be applied to land, sea, aerospace, etc., or any combination thereof. The vehicle may include taxis, private cars, ride-sharing, shared vehicles, buses, trains, motor vehicles, high-speed railways, subways, ships, airplanes, spacecraft, hot air balloons, bicycles, tricycles, motorcycles, etc., or any combination thereof. In some embodiments, the laser intensity calibration system 100 can achieve efficient and accurate laser intensity calibration by implementing the methods and / or processes disclosed in this specification, and obtain accurate calibration results to improve the accuracy of the operation of the downstream application calibration results. For example, during the process of autonomous driving, positioning, perception, prediction, and motion planning can be performed using the calibration results obtained by the methods and / or processes disclosed in this specification to improve the accuracy of autonomous driving control and the safety of driving operations.

[0022] In some embodiments, Figure 1A As shown, the laser intensity calibration system 100 may include a laser radar 110 , a processing device 120 , a user terminal 130 , a storage device 140 and a network 150 .

[0023] The laser radar 110 emits a laser beam into the environment, which is reflected by the surrounding environment and returns to the laser radar 110. The laser radar 110 outputs data points based on the signal of the returned laser beam. The data points are combined to create a point cloud corresponding to a three-dimensional representation of the surrounding environment. The data point includes the distance of the laser radar from the detected surface (e.g., a road), which is determined by measuring the flight time, which is the time between the laser radar emitting the laser beam and receiving the returned laser beam. The data point also includes the intensity value of the signal corresponding to each returned laser beam. The laser radar 110 may include a positioning module for determining the position of the laser radar. For details on the specific structure of the laser radar 110, see Figure 1B and its related description.

[0024] The processing device 120 can be used to process data and / or information from at least one component of the laser intensity calibration system 100 or an external data source (e.g., a cloud data center). For example, the processing device 120 can perform intensity calibration based on the point cloud data acquired by the laser radar 110 to generate a calibration result. In some embodiments, the processing device 120 may include a central processing unit (CPU), a digital signal processor (DSP), a system on a chip (SoC), a microcontroller unit (MCU), a computer, a user console, etc., or any combination thereof. In some embodiments, the processing device 120 may include a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processing device 120 may be local or remote. In some embodiments, the processing device 120 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc., or any combination thereof. In some embodiments, the processing device 120 may be integrated or included in one or more other components of the laser intensity calibration system 100 (e.g., the user terminal 130 or the laser radar 110).

[0025] The user terminal 130 can enable the user to interact with the laser intensity calibration system 100. For example, the user terminal 130 can display the calibration results to the user. For another example, the user terminal 130 can display the point cloud image data before and after calibration to the user. In some embodiments, the user terminal 130 can include a mobile device, a tablet computer, a laptop computer, other devices with input and / or output functions, etc., or any combination thereof.

[0026] The storage device 140 can be used to store data, instructions and / or any other information. For example, the storage device can store calibration results, point cloud data, etc. In some embodiments, the storage device may include a random access memory (RAM), a read-only memory (ROM), a large capacity memory, a removable memory, a volatile read-write memory, etc. or any combination thereof. In some embodiments, the storage device can be integrated or included in one or more other components of the laser intensity calibration system 100 (e.g., the processing device 120, the user terminal 130, or the laser radar 110, etc.).

[0027] The network 150 can facilitate the exchange of information and / or data. In some embodiments, one or more components of the laser intensity calibration system 100 (e.g., the laser radar 110, the processing device 120, the user end 130, the storage device 140) can send information and / or data to other components of the laser intensity calibration system 100 through the network 150. For example, the laser radar 110 can send point cloud data to the processing device 120 via the network 150. For another example, the processing device 120 can send calibration results to the laser radar 110, the storage device 140 and / or the user end 130 via the network 150. In some embodiments, the network 150 may include any one or more of a wired network or a wireless network. In some embodiments, the network 150 may include a cable network, an optical fiber network, a telecommunications network, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network (ZigBee), a near field communication (NFC), an in-device bus, an in-device line, a cable connection, etc. or any combination thereof. In some embodiments, the network connection between the components of the laser intensity calibration system 100 can adopt one of the above methods or multiple methods. In some embodiments, the network can be a point-to-point, shared, centralized, or other topological structure or a combination of multiple topological structures.

[0028] In some embodiments, the laser intensity calibration system 100 may further include a positioning system 160. The positioning system 160 may include one or more satellites, such as satellite 160-1, satellite 160-2, and satellite 160-3. In some embodiments, the positioning system 160 may be a global positioning system (GPS), a global navigation satellite system (GLONASS), a compass navigation system (COMPASS), a Beidou navigation satellite system, a Galileo positioning system, a quasi-zenith satellite system (QZSS), etc. The positioning system 160 may send navigation signals to the user terminal 130 and / or the positioning module in the laser radar 110 via a wireless connection.

[0029] It is worth noting that the laser intensity calibration system 100 is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various changes and modifications can be made according to the description of this specification. For example, the laser intensity calibration system 100 may also include a database, an information source, etc. For another example, the laser intensity calibration system 100 may be implemented on other devices to achieve similar or different functions. However, these changes and modifications will not deviate from the scope of this specification.

[0030] Figure 1B is an exemplary structural block diagram of a laser radar according to some embodiments of this specification. Figure 1BAs shown, the laser radar 110 includes multiple channels, for example, channels 1-n. Each channel includes a laser emitter (for example, 111, 121) and a detector (for example, 121, 122). The detector includes a readout circuit (for example, 113, 123) and a sensor (for example, 114, 124).

[0031] The laser transmitter emits a laser beam into the environment, which is reflected by the surrounding environment and returns to the sensor (e.g., a photodetector) in the detector. The sensor provides the signal of the returned laser beam to the readout circuit, which outputs a data point (e.g., data point 1-n) based on the signal of the returned laser beam. The data point includes the distance of the laser radar from the detected surface (e.g., road), which is determined by the readout circuit by measuring the flight time, which is the time between the laser transmitter emitting the laser beam and the sensor receiving the returned laser beam. The data point also includes the intensity value of the signal corresponding to each returned laser beam. The intensity of the signal of the returned laser beam can provide information about the surface of the object reflecting the laser beam. The intensity value of the signal of the returned laser beam is not only related to the reflectivity of the detected object, but also depends on many other factors, such as the distance from the laser radar to the detected object, the incident angle of the laser beam, the temperature of the surrounding environment, the power level of the channel emitting the laser beam, and other factors (e.g., the alignment between the laser transmitter and the detector of the laser radar), so that different laser beams reflected from the same material will produce different signal intensities. Therefore, the intensity of the returning laser beam needs to be calibrated.The data points output by each channel (eg, data points 1-n) are combined to create a point cloud corresponding to a three-dimensional representation of the surrounding environment.

[0032] Figure 2 It is an exemplary module diagram of a laser radar intensity calibration system according to some embodiments of this specification.

[0033] In some embodiments, the laser radar intensity calibration system 200 may be implemented by the processing device 120. The laser radar intensity calibration system 200 may include an acquisition module 210, a selection module 220, a calibration module 230, a determination module 240, a judgment module 250, and a response module 260.

[0034] The acquisition module 210 is used to acquire the original data of the target area collected by the laser radar, and the original data includes multiple original data sets, each of which corresponds to a sub-area in the target area. In some embodiments, the acquisition module 210 can also be used to acquire a test data set.

[0035] The selection module 220 is configured to select one of the multiple original data sets as a target data set. In some embodiments, the selection module 220 may randomly select one of the multiple original data sets as a target data set.

[0036] The calibration module 230 is used to calibrate the target data set to obtain a calibration result. In some embodiments, the calibration module can calibrate the target data set using an unsupervised or semi-supervised method.

[0037] The determination module 240 is used to obtain a calibration data set based on the target data set and the calibration result.

[0038] The judgment module 250 is used to judge whether the calibration result meets the requirements based on the calibration data set. In some embodiments, the judgment module 250 can determine at least one calibration image data of the sub-area corresponding to the calibration data set based on the calibration data set; determine the contrast of each calibration image data based on at least one calibration image data; and judge whether the calibration result meets the requirements based on the contrast. In some embodiments, the judgment module 250 can determine a first histogram based on at least one calibration image data, and judge whether the calibration result meets the requirements based on the first histogram. In some embodiments, the judgment module 250 can identify an object in at least one calibration image data to obtain a first recognition result; and judge whether the calibration result meets the requirements based on the first recognition result.

[0039] The response module 260 is used to output the calibration result in response to the calibration result meeting the requirement.

[0040] It should be noted that the above description of the laser radar intensity calibration system and its modules is only for convenience of description and does not limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 2 The acquisition module 210, selection module 220, calibration module 230, determination module 240, judgment module 250 and response module 260 disclosed in the specification can be different modules in a system, or a module can realize the functions of two or more modules mentioned above. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this specification.

[0041] Figure 3 is an exemplary flow chart of a laser radar intensity calibration method according to some embodiments of this specification. Figure 3 As shown, the process 300 may include the following steps. In some embodiments, the process 300 may be executed by the processing device 120 or a component thereof (eg, the laser radar intensity calibration system 200 implemented on the processing device 120).

[0042] Step 310 , obtaining raw data of the target area collected by the laser radar, wherein the raw data includes a plurality of raw data sets, each of which corresponds to a sub-area in the target area. In some embodiments, this step may be performed by the acquisition module 210 .

[0043] The target area may refer to an area used for data collection. In some embodiments, the target area may be an indoor area or an outdoor area. In some embodiments, the target area may include one or more road sections. For example, the target area may include one or more straight roads or curved roads. Preferably, the target area may be a straight road. When the target area is a straight road, the subsequent processing process of determining whether the calibration result meets the requirements can be made more convenient and accurate, the amount of data processing and the difficulty of data processing are reduced, and the efficiency of intensity calibration is improved. In some embodiments, the target area may include multiple sub-areas, and the sub-area is a partial area in the target area. For example, when the target area includes multiple road sections, the sub-area may be one of the multiple road sections. Exemplarily, the sub-area may be a road between two intersections. For another example, when the target area includes multiple buildings, the sub-area may be one of the multiple buildings.

[0044] The original data refers to the parameter data of the target area. In some embodiments, the original data may include multiple data points, each of which has characteristic parameters, such as the position corresponding to the data point, the time of acquisition, the information of the corresponding laser beam (such as the angle of incidence, the distance between the laser radar and the reflector, the intensity of the returning laser beam, etc.). The characteristic parameters of each data point are combined to obtain the information of the road section, such as the length of the road surface, the width of the road surface, the communication signs drawn on the road surface, the characteristics of the traffic signs (such as size, outline, shape, category), etc. In some embodiments, the original data may include multiple original data sets, each of which corresponds to a sub-area in the target area. That is, each sub-area in the target area corresponds to an original data set in the original data, and each original data set represents the road section information of a sub-area.

[0045] In some embodiments, laser radar can be used to collect raw data of the target area. For example, the laser radar can be held or mounted on a carrier (e.g., a vehicle), and repeatedly walked or drove within the range of the target area so that the laser radar can comprehensively collect raw data of the target area. In some embodiments, a positioning device can be carried and moved synchronously with the laser radar. When the laser radar is used to collect raw data of the target area, the positioning device can also be used to locate the laser radar at the same time to determine the collection trajectory. The location and / or corresponding time of the data point in the raw data can be determined according to the collection trajectory. The positioning device can be integrated in the laser radar, or it can be an external device (e.g., a vehicle-mounted positioning device, a positioning module in the user end, etc.). In some embodiments, autonomous driving vehicles, robots, etc. can collect raw data of the target area through the positioning device and laser radar set by themselves during the movement of the target area, and upload it to the processing device 120. Therefore, the processing device 120 can also obtain the raw data of the target area automatically uploaded by the autonomous driving vehicle, robot, etc.

[0046] Step 320 , selecting one of the multiple original data sets as the target data set. In some embodiments, this step may be performed by the selection module 220 .

[0047] The target data set may be an original data set used for laser radar intensity calibration. The target data set may reflect characteristic parameters of data before calibration. In some embodiments, the target data set may be any data set in the original data set.

[0048] In some embodiments, the target data set corresponds to a sub-area in the target area. The sub-area corresponding to the target data set may include a road surface, the length and width of the road surface are respectively greater than the length threshold and the width threshold; and a traffic sign is drawn on the road surface. In some embodiments, the length threshold and the width threshold can be set according to actual conditions. Exemplarily, the length threshold can be 5 meters, 10 meters, 20 meters, 30 meters, 50 meters, 100 meters, 200 meters, 500 meters, etc., and the width threshold can be 2 meters, 3 meters, 4 meters, 5 meters, etc. In some embodiments, the traffic sign may include but is not limited to: lane lines, arrows, stop lines, crosswalks, etc. It can be known that the reflectivity of the material of the traffic sign is usually very different from the reflectivity of the road surface material. Therefore, the intensity of the data point corresponding to the traffic sign area is also very different from the intensity of the data point corresponding to the ordinary road surface area, so that the traffic sign can be clearly distinguished from the ordinary road surface in the image display.

[0049] By setting the length threshold and width threshold of the road surface, it can be ensured that the road surface is a section where vehicles can travel normally, thereby improving the accuracy and reliability of subsequent calibration results. In addition, it is required that the sub-area corresponding to the target data set includes the road surface, the length and width of the road surface are respectively greater than the length threshold and the width threshold, and there are traffic signs on the road surface. On the one hand, the quality of the data used for subsequent calibration can be improved and the number of iterations can be reduced; on the other hand, due to the low data requirements, the requirements for data collection and screening are not high, thereby reducing the difficulty of data collection and screening.

[0050] In some embodiments, one of the multiple original data sets may be randomly selected as the target data set.

[0051] One of multiple original data sets is randomly selected as the target data set. There is no special requirement for the original data, and there is no need to manually screen the original data, thus saving human resources.

[0052] Step 330 , calibrate the target data set to obtain a calibration result. In some embodiments, this step may be performed by the calibration module 230 .

[0053] The calibration result may be a mapping table with laser beams as units, and the mapping table includes a mapping relationship between the parameters corresponding to each laser beam and the intensity after calibration (or conversion). For example, the parameters corresponding to the laser beam include one or a combination of the incident angle corresponding to the laser beam, the distance from the laser radar to the surface of the object (for example, a point on an ordinary road surface or a traffic sign surface), the original intensity, etc. For another example, the parameters corresponding to the laser beam further include one or a combination of the temperature of the surrounding environment when the laser beam is emitted, the power level of the channel emitting the laser beam, the alignment between the emitter and the detector corresponding to the laser beam, etc.

[0054] In some embodiments, the target data set can be calibrated using an unsupervised or semi-supervised calibration method. As an example, the unsupervised calibration method can be: SLAM processing the point cloud data in the target data set to obtain the optimized pose of each frame; extracting the point cloud data of the road surface, and extracting the road surface point cloud covered by the acquisition trajectory according to the pose of each frame and the positional relationship between the laser radar and the vehicle to form a point cloud set; finding the Gaussian parameters of each line, and for the point cloud set, calculating the intensity mean and standard deviation corresponding to each line; mapping the intensity value of each line to the same Gaussian distribution, and mapping the Gaussian distribution corresponding to the intensity value of each line to a set Gaussian distribution, obtaining a mapping table, and thus obtaining the calibration result.

[0055] It should be noted that the calibration method in this specification is not limited to unsupervised or semi-supervised calibration methods. In other embodiments, other feasible calibration methods may also be used. This specification does not specifically limit the specific calibration method.

[0056] Step 340 , obtaining a test data set. In some embodiments, this step may be performed by the obtaining module 210 .

[0057] A test data set refers to a data set used to test whether the calibration result meets the requirements. In some embodiments, the test data set may be at least one of the multiple original data sets. For example, the test data set may be a target data set. For another example, the test data set may be other data sets in the original data set except the target data set. In some embodiments, the test data set may be other point cloud data collected by the same type of laser radar as the original data set. In some embodiments, the test data set may be collected by a laser radar. For the specific content of data collection and acquisition, please refer to step 310, which will not be repeated here.

[0058] In some embodiments, a calibration result may correspond to data collected by one type of laser radar. Calibration results obtained based on data collected by different types of laser radars have their own corresponding mapping tables. In this case, the original data set and the test data set may be collected by the same type of laser radar.

[0059] Step 350 , based on the test data set and the calibration result, obtain a calibration data set. In some embodiments, this step may be performed by the determination module 240 .

[0060] The calibration data set refers to the data set corresponding to the test data set obtained by converting the original intensity of the point cloud data in the test data set to the calibration intensity according to the calibration result. The calibration data set can reflect the characteristic parameters of the calibrated data. The characteristic parameters in the test data set are calibrated to obtain the characteristic parameters of the calibration data set, and the characteristic parameters in the test data set correspond one to one to the characteristic parameters in the calibration data set. The calibration result determines the conversion relationship between the characteristic parameters of the two data sets. For example, any point cloud data in the test data set has the original intensity, and after conversion by the calibration result, the calibrated intensity in the corresponding calibration data set can be obtained. The original intensity is the intensity of the point cloud data before calibration, and the calibrated intensity is the intensity of the point cloud data after calibration. That is, any point cloud data has the original intensity and the calibrated intensity, and the conversion relationship between the original intensity and the calibrated intensity is determined by the calibration result.

[0061] Step 360 , based on the calibration data set, determine whether the calibration result meets the requirements. In some embodiments, this step can be performed by the determination module 250 .

[0062] In some embodiments, at least one calibration image data may be determined based on the calibration data set, so as to judge whether the calibration result meets the requirements according to the calibration image data.

[0063] The calibration image data may refer to a frame of data determined based on the calibration data set. In some embodiments, a frame of data may correspond to data collected by the laser radar rotating one circle. The laser radar may continuously rotate to collect test data, and the test data set includes at least one frame of test data. Correspondingly, the calibration data set also includes at least one frame of calibration data. At least one calibration image data may be generated based on a frame of data. In some embodiments, the calibration image data may be point cloud data. In some embodiments, the calibration image data may be a frame of image generated based on point cloud data. The calibration image data may reflect the road surface conditions of the sub-area after calibration. For example, the calibration image data may reflect the length of the road surface after calibration, the width of the road surface, the traffic signs on the road surface, and the parameters of the traffic signs (such as category, size, shape profile, strength, etc.). In some embodiments, it may be determined whether the calibration result meets the requirements based on the clarity and accuracy of the traffic signs reflected in the calibration image data.

[0064] In some embodiments, an image classification model may be used to determine whether the calibration result meets the requirements. In some embodiments, the image classification model may include, but is not limited to, a combination of one or more of a support vector machine model, a logistic regression model, a naive Bayesian classification model, a Gaussian distribution Bayesian classification model, a decision tree model, a random forest model, a KNN classification model, and a neural network model.

[0065] In some embodiments, the image classification model can be obtained through training. The input of the image classification model is the at least one calibrated image data, and the output is whether the at least one calibrated image data meets the standard (or the probability of meeting the standard). The training labels are manually labeled calibrated image data that meet the standard (positive samples) and calibrated image data that do not meet the standard (negative samples). The image classification model can train an initial image classification model based on a large amount of calibrated image data with training labels. Specifically, the calibrated image data with labels can be input into the initial image classification model to obtain the output result of the initial image classification model. The parameters of the initial image classification model are updated through training until the trained intermediate image classification model meets the preset conditions, and the trained image classification model is obtained. Among them, the preset conditions can be that the loss function is less than a threshold, converges, or the training cycle reaches a threshold.

[0066] In some embodiments, if the calibration result is of poor quality, it may result in different detection results in the current frame and the next frame in the calibration image data. For example, a pass sign is detected in the current frame, but not in the next frame. For another example, the detection results of the same pass sign detected in the current frame and the next frame are different, such as the position, shape, outline, size, etc. of the pass sign are different. Therefore, it is possible to judge whether the calibration result meets the requirements based on the detection results of multiple consecutive frames. In some embodiments, two or more consecutive frames of image data in the calibration image data may be obtained, and the two or more consecutive frames of image data may be detected; and it is judged whether the same pass sign is present in the two or more consecutive frames of image data. When the same pass sign is not detected in the two or more consecutive frames of image data, it may be judged that the calibration result does not meet the requirements. When the same pass sign is detected in the two or more consecutive frames of image data, the similarity between the pass signs in the two or more consecutive frames of image data is further judged, so as to judge whether the calibration result meets the requirements based on the similarity. When the similarity between the passage signs in two or more consecutive frames of image data is greater than or equal to the preset similarity threshold, it can be judged that the calibration result meets the requirements; when the similarity between the passage signs in two or more consecutive frames of image data is less than the preset similarity threshold, it can be judged that the calibration result does not meet the requirements.

[0067] In some embodiments, other methods can also be used to determine whether the calibration result meets the requirements. Figure 4-Figure 6 , and its related description.

[0068] Step 370 : In response to the calibration result meeting the requirement, output the calibration result. In some embodiments, this step may be performed by the response module 260 .

[0069] In some embodiments, when the determination result in step 360 is that the calibration result meets the requirements, the calibration result may be output.

[0070] In some embodiments, when the judgment result in step 350 is that the calibration result does not meet the requirements, the process 300 can return to step 320. The selection module 220 reselects an original data set from multiple original data sets as a new target data set. Then, step 330, step 340 and step 350 are performed in sequence until the judgment result in step 350 is that the calibration result meets the requirements, and the response module 260 outputs the calibration result. In some embodiments, there may be noisy data in the original data set. When the noisy data is selected as the target data set, the calibration result obtained through steps 330, step 340 and step 350 may not meet the requirements. At this time, it can return to step 320 to reselect an original data set as the target data set, and then perform steps 330, step 340 and step 350 in sequence, and cycle in sequence until the judgment result in step 350 is that the calibration result meets the requirements (at this time, there is basically no noise in the target data set, or the noise is so small that it can be ignored).

[0071] The laser intensity calibration method described in the embodiments of this specification can automatically determine whether the calibration result meets the requirements on noisy data, thereby improving the degree of automation of calibration. The laser intensity calibration method described in the embodiments of this specification has a high degree of automation and can directly output the calibration result after inputting the original data of the target area without manual intervention.

[0072] It should be noted that the above description of process 300 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 300 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0073] Figure 4 is an exemplary flow chart for determining whether the calibration results meet the requirements according to some embodiments of this specification. Figure 4 As shown, the process 400 may include the following steps. In some embodiments, the process 400 may be executed by the determination module 240 .

[0074] Step 410: Determine at least one calibration image data based on the calibration data set.

[0075] For details about calibrating image data, see Figure 3 The relevant description of step 360 is not repeated here.

[0076] Step 420: Determine the contrast of each calibration image data based on the at least one calibration image data.

[0077] Contrast can refer to the level of different brightness between the maximum brightness and the minimum brightness in the calibration image data. Contrast can reflect the size of the brightness difference in the calibration image data. For example, the greater the brightness difference, the greater the contrast; the smaller the brightness difference, the smaller the contrast. When the brightness difference is large, the traffic signs on the road surface in the calibration image data are more obvious.

[0078] In some embodiments, the contrast of each calibration image data may be determined. In some embodiments, when the calibration image data includes multiple frames of data, the contrast of each frame of data may be determined.

[0079] Step 430: determine whether the calibration result meets the requirement according to the contrast.

[0080] In some embodiments, the relationship between the contrast of the calibration image data and the contrast threshold can be determined to determine whether the calibration result meets the requirements. For example, when the contrast of the calibration image data is greater than or equal to the contrast threshold, the calibration result is determined to meet the requirements; otherwise, the calibration result does not meet the requirements.

[0081] In some embodiments, when the calibration image data includes multiple frames of image data, the relationship between the contrast of each frame of image data and the contrast threshold can be determined separately, and then the judgment results of all frame data are combined to determine whether the calibration result meets the requirements. For example, if the ratio of the number of frames of image data with a contrast greater than or equal to the contrast threshold to the total number of frames exceeds a set value (for example, 80%, 90%, 95%, etc.), it can be determined that the calibration result meets the requirements; otherwise, the calibration result does not meet the requirements. In some embodiments, it can be determined whether the calibration result meets the requirements based on the difference value (such as a ratio or a difference) between the contrast of the calibration image data and the image data corresponding to the test data set (such as the original image data described later). For example, the larger the difference value, the higher the image quality of the calibration image data after calibration compared to the image quality before calibration. If the contrast difference value is greater than or equal to the contrast threshold, it can be determined that the calibration result meets the requirements; otherwise, the calibration result does not meet the requirements.

[0082] It should be noted that the above description of process 400 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 400 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0083] Figure 5 is an exemplary flow chart for determining whether the calibration results meet the requirements according to some embodiments of this specification. Figure 5 As shown, the process 500 may include the following steps. In some embodiments, the process 500 may be executed by the determination module 240 .

[0084] Step 510: Determine at least one calibration image data based on the calibration data set.

[0085] For details about calibrating image data, see Figure 3 The relevant description of step 360 is not repeated here.

[0086] Step 520: determine a first histogram based on the at least one calibration image data, wherein the abscissa of the first histogram is the brightness value or the intensity value, and the ordinate is the number of pixels.

[0087] The first histogram may be a brightness histogram. The first histogram may reflect the brightness of the calibrated image data after calibration. In some embodiments, since the pixel values ​​in the calibration image data are determined based on the point cloud intensity, the horizontal coordinate of the first histogram may also be an intensity value. The number of pixels corresponding to the brightness (or intensity) interval (for example, the number of pixels in the image data or the number of data points in the point cloud data) may be reflected in the first histogram, so as to determine whether the calibration result meets the requirements. For example, the higher the bulge of a brightness (or intensity) interval in the first histogram, the more pixels there are in the brightness (or intensity) interval; the lower the bulge of a brightness (or intensity) interval in the first histogram, the fewer pixels there are in the brightness (or intensity) interval.

[0088] Step 530: Determine whether the calibration result meets the requirement according to the first histogram.

[0089] In some embodiments, judging whether the calibration result meets the requirements based on the first histogram may include: determining a horizontal coordinate threshold of the first histogram; dividing the first histogram into a first area and a second area based on the horizontal coordinate threshold, wherein the horizontal coordinate of the first area is less than the horizontal coordinate threshold, and the horizontal coordinate of the second area is greater than or equal to the horizontal coordinate threshold; determining the area under the curve corresponding to the second area; judging whether the calibration result meets the requirements based on the area under the curve corresponding to the second area.

[0090] In some embodiments, the abscissa threshold of the first histogram is related to the accuracy of the division of the first region and the second region, thereby affecting the accuracy of the calibration result judgment. In some embodiments, the abscissa threshold can be set manually. In some embodiments, the abscissa threshold can also be determined according to a machine learning model. In some embodiments, the machine learning model may include but is not limited to a Gaussian distribution Bayesian model, a decision tree model, a random forest model, a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, or a combination of one or more thereof.

[0091] In some embodiments, since the abscissa of the first region is less than the abscissa threshold and the abscissa of the second region is greater than the abscissa threshold, the first region is a low brightness region and the second region is a high brightness region. The area under the curve corresponding to the first region, the area under the curve corresponding to the second region, and the total area under the curve corresponding to the first histogram can be calculated respectively.

[0092] In some embodiments, it is possible to determine whether the calibration result meets the requirements based on the area under the curve corresponding to the second region. When the area under the curve corresponding to the second region is greater than the area threshold, it means that there are more pixels in the second region, and the corresponding calibration image data shows more and more detailed road features, such as more traffic signs on the road and clearer lines. At this point, it can be determined that the calibration result meets the requirements. In some embodiments, the area threshold can be set manually or determined based on a machine learning model.

[0093] In some embodiments, it is possible to determine whether the calibration result meets the requirements based on the difference between the area under the curve corresponding to the second region and the area under the curve corresponding to the first region (recorded as the first difference value). In some embodiments, the difference value may be a ratio or a difference. When the first difference value is greater than or equal to the first difference value threshold, it means that there are more pixels with high brightness in the first histogram, and the corresponding calibration image data shows more and more detailed road features, such as more traffic signs on the road surface and clearer lines. At this point, it can be determined that the calibration result meets the requirements.

[0094] In some embodiments, whether the calibration result meets the requirements can be judged according to the difference value (recorded as the second difference value) between the area under the curve corresponding to the second region and the total area under the curve corresponding to the first histogram. When the second difference value is greater than or equal to the second difference value threshold, it means that there are more pixels with high brightness in the first histogram, and the corresponding calibration image data shows more and more detailed road features, such as more traffic signs on the road surface and clearer lines. At this time, it can be judged that the calibration result meets the requirements.

[0095] It should be noted that the first difference value threshold and the second difference value threshold can be set manually or determined according to a machine learning model. The first difference value threshold and the second difference value threshold can be reasonably set according to actual conditions or application scenario requirements, and are not further limited here.

[0096] Whether the calibration result meets the requirements is judged according to the area under the curve corresponding to the second region. The accuracy of the judgment result can be improved by reasonably setting the corresponding thresholds (such as the horizontal axis threshold, the first difference value threshold, and the second difference value threshold).

[0097] In some embodiments, judging whether the calibration result meets the requirements based on the first histogram may also include: generating at least one original image data based on the target data set, each original image data corresponds to one of the at least one calibration image data; determining a second histogram based on the at least one original image data; judging whether the calibration result meets the requirements based on the first histogram and the second histogram.

[0098] The original image data may refer to a frame of data determined based on the target data set. In some embodiments, the original image data may be point cloud data. In some embodiments, the original image data may also be a frame of image generated based on point cloud data. The original image data may reflect the road surface conditions of the sub-area before calibration. For example, the original image data may reflect the road surface length, road surface width, and traffic signs (such as size, contour, strength, etc.) on the road surface before calibration.

[0099] Similar to the first histogram, the horizontal axis of the second histogram is the brightness value or the intensity value, and the vertical axis is the number of pixels. The second histogram can be a brightness histogram. The second histogram can reflect the brightness of the original image data before calibration. The second histogram can reflect the number of pixels corresponding to the brightness (or intensity) interval in the original image data before calibration.

[0100] Similar to the division of regions in the first histogram, the second histogram can be divided into a third region and a fourth region according to the abscissa threshold, the abscissa of the third region is less than the abscissa threshold, and the abscissa of the fourth region is greater than the abscissa threshold. The third region is a low brightness region, and the fourth region is a high brightness region. In some embodiments, the area under the curve corresponding to the third region, the area under the curve corresponding to the fourth region, and the total area under the curve corresponding to the second histogram can be calculated respectively.

[0101] In some embodiments, it is possible to determine whether the calibration result meets the requirements based on the area under the curve corresponding to the second area and the area under the curve corresponding to the fourth area. For example, it is possible to determine whether the calibration result meets the requirements based on the difference value (recorded as the third difference value) between the area under the curve corresponding to the second area and the area under the curve corresponding to the fourth area. When the third difference value is greater than or equal to the third difference value threshold (it can be understood that the third difference value threshold is greater than 1), it means that the area of ​​the high-brightness area in the calibration image data after calibration is increased compared to the area of ​​the high-brightness area in the original image data before calibration. Compared with the original image data before calibration, the road surface features displayed in the calibration image data after calibration are more and more detailed, such as more traffic signs on the road surface and clearer lines. At this time, it can be determined that the calibration result meets the requirements. It can be understood that the total area under the curve corresponding to the second histogram is the same or substantially the same as the total area under the curve corresponding to the first histogram.

[0102] In some embodiments, it is possible to determine whether the calibration result meets the requirements based on the difference between the area under the curve corresponding to the second region and the area under the curve corresponding to the first region (i.e., the first difference value), and the difference between the area under the curve corresponding to the fourth region and the area under the curve corresponding to the third region (recorded as the fourth difference value). For example, when the ratio of the first difference value to the fourth difference value is greater than or equal to the fourth difference value threshold, it means that the area of ​​the high-brightness area in the calibration image data after calibration is increased compared to the area of ​​the high-brightness area in the original image data before calibration, and compared to the original image data before calibration, the road features displayed in the calibration image data after calibration are more numerous and detailed, such as more traffic signs on the road surface and clearer lines. At this point, it can be determined that the calibration result meets the requirements.

[0103] It should be noted that the third difference value threshold and the fourth difference value threshold can be set manually or determined according to a machine learning model. The sizes of the third difference value threshold and the fourth difference value threshold can be reasonably set according to actual conditions or application scenario requirements, and are not further limited here.

[0104] It should be noted that the above description of process 500 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 500 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0105] Whether the calibration result meets the requirements is judged by comparing the area under the curve corresponding to the high-brightness area before and after calibration. The accuracy of the judgment result can be improved by reasonably setting the corresponding thresholds (such as the third difference value threshold and the fourth difference value threshold).

[0106] Figure 6 is an exemplary flow chart for determining whether the calibration results meet the requirements according to some embodiments of this specification. Figure 6 As shown, the process 600 may include the following steps. In some embodiments, the process 600 may be executed by the determination module 240 .

[0107] Step 610: Determine at least one calibration image data based on the calibration data set.

[0108] For details about calibrating image data, see Figure 3 The relevant description of step 360 is not repeated here.

[0109] Step 620: Identify the object in the at least one calibration image data to obtain a first identification result.

[0110] The object in the calibration image data may refer to the traffic sign in the road surface of the corresponding sub-area. For example, the object may include a crosswalk, a lane line, an arrow, a stop line, etc. The first recognition result is the recognition result of the object in the calibration image data after calibration. The first recognition result may include information such as the category, quantity, size, shape, outline, position, etc. of the object recognized in the calibration image data after calibration. In some embodiments, the object may also include other road surface related elements. For example, buildings, traffic lights, street lights, fences, signs, pedestrians, and vehicles. In some embodiments, all objects and / or part of the objects in the calibration image data may be detected. The number and type of detected objects can be set according to actual needs.

[0111] In some embodiments, a neural network model or a grayscale method may be used to identify objects in the calibration image to obtain a first recognition result. In other embodiments, other feasible methods may also be used to identify objects in the calibration image, which is not specifically limited in this specification.

[0112] Step 630: Determine whether the calibration result meets the requirements based on the first recognition result.

[0113] In some embodiments, whether the calibration result meets the requirements can be judged based on the comparison results of the object recognition results in the image data before and after calibration (i.e., the comparison between the second recognition result below and the first recognition result above) (i.e., the comparison between the second recognition result below and the first recognition result above).

[0114] In some embodiments, judging whether the calibration result meets the requirements based on the first recognition result may include: generating at least one original image data based on the target data set, each original image data corresponds to one of the at least one calibration image data; identifying an object in the at least one original image data to obtain a second recognition result; judging whether the calibration result meets the requirements based on the first recognition result and the second recognition result.

[0115] The second recognition result is a recognition result of an object in the original image data before calibration. The second recognition result may include information such as the category, quantity, size, shape, outline, and position of the object recognized in the original image data before calibration.

[0116] In some embodiments, the first recognition result and the second recognition result can be compared, and whether the calibration result meets the requirements can be determined based on the comparison result. For example, the number of objects in the first recognition result and the second recognition result can be compared. When the number of objects in the first recognition result is greater than the number of objects in the second recognition result, the calibration result can be determined to meet the requirements. For another example, the differences in the categories, sizes, shapes, contours, and positions of the objects in the first recognition result and the second recognition result can be compared to determine whether the calibration result meets the requirements. Exemplarily, when the clarity of the contour of a specific object (such as an arrow) in the first recognition result is higher than the clarity of the contour of the same object in the second recognition result, the calibration result can be determined to meet the requirements. In some embodiments, one or more feature parameters (such as contour, size, shape, etc.) of an object in the first recognition result and the second recognition result can be compared, and whether the calibration result meets the requirements can be determined based on the comparison result. In some embodiments, one or more parameter features of multiple objects in the first recognition result and the second recognition result can also be compared, and the calibration result can be determined based on the comprehensive comparison results to determine whether the calibration result meets the requirements.

[0117] In some embodiments, the recognition result of the object in the calibrated image data after calibration can be compared with the true result, and whether the calibration result meets the requirements can be judged according to the comparison result. In some embodiments, judging whether the calibration result meets the requirements according to the first recognition result can include: obtaining the true value data of the object in at least one calibration image data; judging whether the calibration result meets the requirements according to the first recognition result and the true value data.

[0118] The true value data refers to the real actual data of the object. In some embodiments, the true value data of the object can be obtained by using a camera. In some embodiments, at least one camera image can be obtained by using a camera, and each calibration image data corresponds to one of the at least one camera image. The object in the at least one camera image is detected to obtain a third recognition result. The third recognition result can be used as the true value data of the object. In some embodiments, the first recognition result and the third recognition result can be compared, and whether the calibration result meets the requirements can be judged according to the comparison result. For example, the similarity of the position, size, contour, category, etc. of the same object in the first recognition result and the third recognition result can be compared to judge whether the calibration result meets the requirements. As an example, when the similarity between the size of the object in the first recognition result and the size of the same object in the third recognition result is greater than the similarity threshold (that is, the size of the object in the calibration image data is close to the true value data of the object), it can be judged that the calibration result meets the requirements. As an example, the similarity threshold can be 70%, 80%, 90%, 95%, etc.

[0119] In some embodiments, the true value data of the object can be obtained based on the test data set. In some embodiments, the feature parameters of the same object in the first recognition result can be determined based on the test data set, and the feature parameters are the true value data of the object. For example, if the first recognition result includes the position of the lane line, the target data set can be tested to determine the position of the lane line (i.e., the true value data of the lane line). Compare the position of the lane line in the first recognition result with the true value data of the lane line in the test data set. When the similarity between the position of the lane line in the first recognition result and the true value data of the lane line in the target data set is greater than the similarity threshold, it can be judged that the calibration result meets the requirements.

[0120] In some embodiments, the true value data of the object can be obtained from an existing map. For example, based on the existing map, the characteristic parameters of the same object in the first recognition result are obtained, and the characteristic parameters are the true value data of the object. For example, if the first recognition result includes the outline of an arrow, the outline of the arrow (i.e., the true value data of the arrow) can be determined based on the existing map. By comparing the outline of the arrow in the first recognition result with the true value data of the arrow in the existing map, when the similarity between the outline of the arrow in the first recognition result and the outline of the arrow in the target data set is greater than the similarity threshold, it can be determined that the calibration result meets the requirements.

[0121] In some embodiments, whether the calibration result meets the requirements can be determined based on the comparison results of one or more characteristic parameters of an object, or based on the comparison results of one or more characteristic parameters of multiple objects.

[0122] It should be noted that the above description of process 600 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 600 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0123] The laser radar intensity calibration method described in the embodiments of this specification can be used in various technical fields that use laser beam intensity. For example, intelligent mobile control (for example, autonomous driving, robots, etc.), detection, identification, resolution, positioning and tracking of targets. For example, for autonomous driving, the processing device can send the calibration results to the autonomous driving vehicle. After the vehicle receives the original point cloud data collected by the laser radar, it converts the intensity of the original point cloud data according to the calibration results to obtain calibration data, and then the vehicle performs autonomous driving control operations such as positioning, perception, prediction, and motion planning based on the calibration data. For another example, the processing device can send the calibration results to the laser radar, and the laser radar converts the signal intensity of the returned laser beam into the calibration intensity based on the calibration results, outputs the calibration point cloud data, and then the downstream device can operate according to the calibration point cloud data.

[0124] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0125] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0126] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0127] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0128] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0129] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0130] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A laser radar intensity calibration method, characterized in that: include: Acquire raw data of a target area collected by a laser radar, wherein the raw data includes a plurality of raw data sets, each of which corresponds to a sub-area in the target area; Selecting one of the multiple original data sets as a target data set; Calibrate the target data set to obtain a calibration result; Get the test dataset; Based on the test data set and the calibration result, a calibration data set is obtained; Based on the calibration data set, determining whether the calibration result meets the requirements; In response to the calibration result meeting the requirement, the calibration result is outputted.

2. The laser radar intensity calibration method according to claim 1, characterized in that: Also includes: In response to the calibration result not meeting the requirement, reselecting one of the original data sets as the target data set from the multiple original data sets.

3. The laser radar intensity calibration method according to claim 1, characterized in that: The selecting one of the plurality of original data sets as the target data set comprises: A data set is randomly selected from the multiple original data sets as the target data set.

4. The laser radar intensity calibration method according to claim 1, characterized in that: The sub-region corresponding to the target data set includes a road surface; the length and width of the road surface are respectively greater than a length threshold and a width threshold; and a traffic sign is drawn on the road surface.

5. The laser radar intensity calibration method according to claim 1, characterized in that: The determining, based on the calibration data set, whether the calibration result meets the requirement includes: Based on the calibration data set, determining at least one calibration image data; Determining a contrast of each of the calibration image data based on the at least one calibration image data; Whether the calibration result meets the requirement is determined according to the contrast.

6. The laser radar intensity calibration method according to claim 1, characterized in that: The determining, based on the calibration data set, whether the calibration result meets the requirement includes: Based on the calibration data set, determining at least one calibration image data; Determine a first histogram based on the at least one calibration image data, wherein the abscissa of the first histogram is a brightness value or an intensity value, and the ordinate is a number of pixels; According to the first histogram, it is determined whether the calibration result meets the requirements.

7. The laser radar intensity calibration method according to claim 6, characterized in that: The determining, according to the first histogram, whether the calibration result meets the requirement includes: Determining a horizontal coordinate threshold of the first histogram; Dividing the first histogram into a first region and a second region according to the abscissa threshold, the abscissa of the first region being less than the abscissa threshold, and the abscissa of the second region being greater than or equal to the abscissa threshold; determining an area under the curve corresponding to the second region; Whether the calibration result meets the requirement is determined according to the area under the curve corresponding to the second region.

8. The laser radar intensity calibration method according to claim 6, characterized in that: The determining, according to the first histogram, whether the calibration result meets the requirement includes: generating at least one original image data according to the test data set, each of the original image data corresponding to one of the at least one calibration image data; determining a second histogram based on the at least one original image data; According to the first histogram and the second histogram, it is determined whether the calibration result meets the requirements.

9. The laser radar intensity calibration method according to claim 1, characterized in that: The determining, based on the calibration data set, whether the calibration result meets the requirement includes: Based on the calibration data set, determining at least one calibration image data; Identify the object in the at least one calibration image data to obtain a first identification result; According to the first recognition result, determine whether the calibration result meets the requirements.

10. The laser radar intensity calibration method according to claim 9, characterized in that: The determining, based on the first recognition result, whether the calibration result meets the requirement includes: generating at least one original image data according to the test data set, each of the original image data corresponding to one of the at least one calibration image data; Recognize the object in the at least one original image data to obtain a second recognition result; Whether the calibration result meets the requirement is determined according to the first recognition result and the second recognition result.

11. The laser radar intensity calibration method according to claim 9, characterized in that: The determining, based on the first recognition result, whether the calibration result meets the requirement includes: Acquire true value data of the object in the at least one calibration image data; Whether the calibration result meets the requirements is determined according to the first recognition result and the true value data.

12. A laser radar intensity calibration system, characterized in that: include: An acquisition module, used to acquire raw data of a target area collected by a laser radar, wherein the raw data includes a plurality of raw data sets, each of which corresponds to a sub-area in the target area, and the acquisition module is also used to acquire a test data set; A selection module, configured to select one of the plurality of original data sets as a target data set; A calibration module, used to calibrate the target data set to obtain a calibration result; A determination module, configured to obtain a calibration data set based on the test data set and the calibration result; A judging module, used to judge whether the calibration result meets the requirements based on the calibration data set; The response module is used for outputting the calibration result in response to the calibration result meeting the requirement.

13. A laser radar intensity calibration device, comprising a processor, wherein the processor is used to execute the laser radar intensity calibration method according to any one of claims 1 to 11.

14. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the laser radar intensity calibration method according to any one of claims 1 to 11.

Images