Geographic information data acquisition vehicle

Abstract

The invention discloses a geographic information data acquisition vehicle, relates to the technical field of geographic information data acquisition vehicles, and aims to solve the problem that data acquisition is incomplete when a data acquisition vehicle performs geographic information acquisition. According to the method, data from different sensors are fused by using a particle filtering method, advantages of various sensors can be comprehensively considered, uncertainty and errors of single sensor data are reduced, scene model construction is performed on fused feature information by using a neural network model algorithm, and the accuracy of scene modeling is improved. The standard geographic data model of the data acquisition area can be quickly and accurately generated. The system can reflect the change of an actual scene in real time, can adapt to various complex environments and scenes, and combines a satellite navigation sensor, a laser radar sensor, a camera, a millimeter wave radar and inertial navigation. Data including geographic positions, environment information, images and videos, dynamic states of target objects, body motion states and the like can be obtained.

Description

Technical Field

[0001] The invention relates to the technical field of geographic information data collection vehicles, in particular to a geographic information data collection vehicle. Background Art

[0002] A geographic information data collection vehicle, also known as a map collection vehicle or a data collection vehicle, is a special vehicle designed specifically for acquiring geographic information data.

[0003] The Chinese patent with the announcement number CN116878954B discloses a surveying and mapping geographic information data collection tool. The dislocation component is mainly set so that the compression plate has two states, one is the state of dislocation with the compression cylinder, and the other is the state of coaxial with the compression cylinder. This ensures that when the soil enters the compression cylinder, the compression plate will not interfere with the soil. On the other hand, when the compression plate moves vertically downward, it can squeeze and compress the soil in the compression cylinder, making the soil more compact and reducing the space volume occupied when storing soil samples. Although the above patent solves the problem of data collection, there are still the following problems in actual operation:

[0004] 1. The geographic data is not collected better, and the collected geographic data is not transmitted and managed more quickly, resulting in slow data transmission and reduced scene construction efficiency.

[0005] 2. The collected geographic information data is processed, resulting in poor data quality and failure of scene construction.

[0006] 3. The data collection equipment was not installed more completely, resulting in incomplete data collection. Summary of the invention

[0007] The purpose of the present invention is to provide a geographic information data collection vehicle, which uses a particle filter method to fuse data from different sensors, can comprehensively consider the advantages of various sensors, reduce the uncertainty and error of single sensor data, and use a neural network model algorithm to construct a scene model for the fused feature information, so as to quickly and accurately generate a standard geographic data model for the data collection area. It can reflect the changes in the actual scene in real time, can adapt to various complex environments and scenes, and can obtain data including geographic location, environmental information, images and videos, dynamic state of target objects, and body motion state by combining satellite navigation sensors, laser radar sensors, cameras, millimeter wave radars and inertial navigation, so as to solve the problems in the prior art.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A geographic information data collection vehicle comprises a main body and a geographic information data monitoring system, wherein a data collector is installed on the top of the main body, and a millimeter wave radar and an inertial navigation are arranged in the main body;

[0010] Geographic information data monitoring system for:

[0011] When the main body is traveling in the data collection area, the data collector on the top of the main body collects the geographic information data of the data collection area. After the geographic information data is collected, it is transmitted to the data processing center for data processing. After the geographic information data is processed, data analysis is performed, the analyzed data is stored in the memory, and displayed on the display terminal.

[0012] Preferably, the data collector includes a satellite navigation sensor, a lidar sensor, a camera and a lifter. The satellite navigation sensor is installed in front of the top of the main body, the lifter is installed at the top of the main body, and the camera is installed on the upper end of the lifter. At the same time, four cameras are provided, and the lidar sensor is installed on the top of the camera.

[0013] Preferably, the geographic information data monitoring system comprises:

[0014] Acquisition equipment detection unit, used for:

[0015] Before the main body collects data in the data collection area, it performs performance tests on the satellite navigation sensor, lidar sensor, camera, elevator, millimeter wave radar and inertial navigation;

[0016] Among them, the performance detection of satellite navigation sensors is to test the positioning accuracy, availability and compatibility of satellite navigation sensors;

[0017] The performance test of the LiDAR sensor is to test the ranging performance, angular resolution, angular accuracy and point cloud quality of the LiDAR sensor;

[0018] The performance test of the camera is to test the camera's resolution, color reproduction, focus speed, and low-light environment;

[0019] The performance test of the lifter is to test the function and load of the lifter;

[0020] The performance test of millimeter wave radar is to test the ranging accuracy, imaging resolution, power consumption and operating frequency range of millimeter wave radar;

[0021] The performance test of inertial navigation is to test the navigation parameters of inertial navigation;

[0022] After all tests are passed, the main body collects data in the data collection area.

[0023] Preferably, the geographic information data monitoring system further includes:

[0024] Acquisition data transmission unit, used for:

[0025] The main body collects geographic information data in the data collection area using satellite navigation sensors, lidar sensors, cameras, millimeter wave radars and inertial navigation, and transmits the collected geographic information data to the data processing center for data processing;

[0026] Among them, the satellite navigation sensor collects the geographic location information of the main body; the laser radar sensor collects the environmental information in the data collection area; the camera collects the image and video information in the data collection area; the millimeter wave radar collects the distance, relative speed, angle, position and shape information between the target object and the radar in the data collection area; the inertial navigation measures the linear acceleration and angular velocity information of the main body through the accelerometer and gyroscope sensors;

[0027] Satellite navigation sensors, lidar sensors, cameras, millimeter wave radars and inertial navigation complete the data collection in the data collection area to obtain geographic information data.

[0028] Preferably, the data collection and transmission unit is further used for:

[0029] Confirm the data transmission volume of geographic information data;

[0030] Wherein, the geographic information data is divided into a number of data segments of the same length;

[0031] Determine the amount of geographic information data to be transmitted based on the number of data segments;

[0032] There are no fewer than four transmission channels for geographic information data to be transmitted to data processing;

[0033] Confirm the remaining capacity of each transmission channel;

[0034] A transmission channel whose transmission volume is less than the remaining capacity of the channel is selected as the transmission channel for geographic information data.

[0035] Preferably, the geographic information data monitoring system further includes:

[0036] Transmission data processing unit, used for:

[0037] The data processing center will unify the format of the received geographic information data;

[0038] After the format is unified, the data obtained by the lidar sensor and millimeter wave radar are filtered and denoised;

[0039] Perform image preprocessing on the data acquired by the camera;

[0040] The image preprocessing is to optimize the image data in the acquired geographic information data.

[0041] Preferably, the transmission data processing unit is further used for:

[0042] Convert image data in geographic information data into grayscale images;

[0043] The grayscale image is filtered using the mean filtering method, and a filtered image is obtained after the filtering is completed;

[0044] Map the pixel values ​​of the filtered image from the range of 0-255 to the range of 0-1, and obtain a normalized image after the mapping is completed;

[0045] The normalized image is smoothed and sharpened, and after the smoothing and sharpening are completed, the grayscale distribution of the image is adjusted, and after the grayscale distribution is completed, a distribution image is obtained;

[0046] Convert the distribution image into an image of a balanced histogram through grayscale transformation;

[0047] Finally, the standard image captured by the camera is obtained.

[0048] Preferably, the transmission data processing unit further includes:

[0049] A grayscale image extraction module, used to extract the grayscale image corresponding to the image data after the image data in the geographic information data is converted into a grayscale image;

[0050] A first grayscale value extraction module, used to extract the grayscale value corresponding to each pixel block in the grayscale image corresponding to the image data;

[0051] A grayscale value difference acquisition module, used to acquire the grayscale value difference between the grayscale values ​​of every two adjacent pixel blocks using the grayscale value corresponding to each pixel block;

[0052] The grayscale difference coefficient acquisition module is used to obtain the grayscale difference coefficient by using the grayscale value difference between the grayscale values ​​of each two adjacent pixel blocks, wherein the grayscale difference coefficient is obtained by the following formula:

[0053]

[0054] Among them, S represents the grayscale difference coefficient; n represents the total number of groups corresponding to each two adjacent pixel blocks; H ci H represents the grayscale value difference between the grayscale values ​​of two adjacent pixel blocks in the i-th group; zi H represents the grayscale median value corresponding to the grayscale values ​​of two adjacent pixel blocks in the i-th group; miniH represents the gray value corresponding to the pixel block with the lower gray value in the i-th group of two adjacent pixel blocks; x represents the median grayscale value corresponding to all pixel blocks contained in the grayscale image; exp represents an exponential function with e as the base;

[0055] The grayscale adjustment module is used to compare the grayscale value difference between the grayscale values ​​of each two adjacent pixel blocks with the grayscale difference coefficient, obtain a target pixel block for grayscale adjustment according to the comparison result, and perform grayscale adjustment on the target pixel block.

[0056] Preferably, the grayscale adjustment module includes:

[0057] A comparison module, used for comparing the grayscale value difference between the grayscale values ​​of each two adjacent pixel blocks with the grayscale difference coefficient to obtain a comparison result;

[0058] A target pixel block acquisition module is used for extracting a pixel block with a lower grayscale value from the two adjacent pixel blocks whose grayscale values ​​are lower than the preset grayscale difference coefficient as a target pixel block when the comparison result indicates that the grayscale value difference between the grayscale values ​​of each two adjacent pixel blocks is lower than a preset grayscale difference coefficient;

[0059] A second grayscale value extraction module, used to extract grayscale values ​​of all adjacent pixel blocks of the target pixel block;

[0060] A maximum and minimum difference acquisition module, used to acquire the maximum and minimum difference between the grayscale value of the target pixel block and the grayscale values ​​of all adjacent pixel blocks by using the grayscale values ​​of all adjacent pixel blocks of the target pixel block;

[0061] The target grayscale value acquisition module is used to obtain the target grayscale value of the target pixel block by using the maximum difference value and the minimum difference value, wherein the target grayscale value is obtained by the following formula:

[0062]

[0063] Among them, H b Indicates the target grayscale value corresponding to the target pixel block; H cmax and H cmin They represent the maximum and minimum differences between the grayscale values ​​of the target pixel block and the grayscale values ​​of all adjacent pixel blocks respectively; S represents the grayscale difference coefficient;

[0064] The grayscale value adjustment execution module is used to perform grayscale adjustment on the target pixel block according to the target grayscale value to obtain an adjusted target pixel block.

[0065] Preferably, the geographic information data monitoring system further includes:

[0066] Processing data analysis unit for:

[0067] Extract features from the processed data obtained by satellite navigation sensors, lidar sensors, cameras, millimeter wave radars and inertial navigation;

[0068] Among them, the processed data obtained by the laser radar sensor is extracted from the point cloud data of the laser radar to extract ground features and object features; ground features include elevation and curvature; object features include shape and size;

[0069] The standard images acquired by the camera are used with image recognition technology to extract data on road signs, traffic lights, vehicles, and pedestrians;

[0070] Analyze the reflected wave frequency changes in the processed data obtained by the millimeter wave radar, and extract the distance, relative speed and direction between the main body and other vehicles in the data collection area;

[0071] Extract the position, velocity, acceleration and attitude data of the main body from the inertial navigation and satellite navigation sensors;

[0072] The data extracted from satellite navigation sensors, lidar sensors, cameras, millimeter-wave radars and inertial navigation are fused with feature information through particle filtering method;

[0073] After the feature information is fused, the acquisition scene model is constructed through the neural network model algorithm;

[0074] After the collection scene model is constructed, the standard geographic data model of the data collection area is obtained.

[0075] And import the standard geographic data model into the display terminal for display.

[0076] Compared with the prior art, the present invention has the following beneficial effects:

[0077] 1. The geographic information data collection vehicle provided by the present invention can obtain data including geographic location, environmental information, images and videos, dynamic state of target objects, and body motion state by combining satellite navigation sensors, lidar sensors, cameras, millimeter wave radars and inertial navigation. By confirming the remaining channel capacity of each transmission channel and selecting appropriate transmission channels for data transmission, the stability and reliability of data during the transmission process can be ensured.

[0078] 2. The geographic information data collection vehicle provided by the present invention performs data filtering and denoising on the data acquired by the laser radar sensor and the millimeter wave radar, which can effectively eliminate or reduce the noise and interference in the original data. This helps to improve the accuracy and reliability of the data, and can improve the overall data processing efficiency by optimizing the image processing process, reducing unnecessary calculation steps and redundant data.

[0079] 3. The geographic information data collection vehicle provided by the present invention uses the particle filter method to fuse data from different sensors, which can comprehensively consider the advantages of various sensors, reduce the uncertainty and error of single sensor data, thereby improving the accuracy of the overall data, and use the neural network model algorithm to construct a scene model for the fused feature information, which can quickly and accurately generate a standard geographic data model of the data collection area. This model not only has a high degree of accuracy, but also can reflect the changes in the actual scene in real time, and can adapt to various complex environments and scenes. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 It is a front view structural schematic diagram of the geographic information data collection vehicle of the present invention;

[0081] Figure 2 It is a side view structural diagram of the geographic information data collection vehicle of the present invention;

[0082] Figure 3 It is a schematic diagram of the geographic information data acquisition module of the present invention;

[0083] Figure 4 It is a schematic diagram of the flow of the geographic information data collection method of the present invention.

[0084] In the figure: 1. Main body; 2. Data collector; 21. Satellite navigation sensor; 22. LiDAR sensor; 23. Camera; 24. Lifter. DETAILED DESCRIPTION

[0085] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0086] In order to solve the problem in the prior art that the collection equipment is not installed more perfectly when collecting geographic information data, resulting in incomplete data collection, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions:

[0087] A geographic information data collection vehicle comprises a main body 1 and a geographic information data monitoring system, wherein a data collector 2 is installed on the top of the main body 1, and a millimeter wave radar and an inertial navigation are arranged in the main body 1;

[0088] Geographic information data monitoring system for:

[0089] When the main body 1 is traveling in the data collection area, the data collector 2 at the top of the main body 1 collects the geographic information data of the data collection area. After the geographic information data is collected, it is transmitted to the data processing center for data processing. After the geographic information data is processed, data analysis is performed, and the analyzed data is stored in the memory and displayed on the display terminal.

[0090] The data collector 2 includes a satellite navigation sensor 21, a lidar sensor 22, a camera 23 and a lifter 24. The satellite navigation sensor 21 is installed in front of the top of the main body 1, the lifter 24 is installed at the top of the main body 1, and the camera 23 is installed on the upper end of the lifter 24. At the same time, four cameras 23 are provided, and the lidar sensor 22 is installed on the top of the camera 23.

[0091] Specifically, the satellite navigation sensor 21, the laser radar sensor 22, the camera 23 and the lifter 24 are integrated. The combination of these sensors and devices can obtain rich environmental information. The design of the lifter 24 allows the height of the camera 23 and the laser radar sensor 22 to be adjusted, which is very useful for different environments and application requirements. There are four cameras 23, which provide all-round visual information. This design can reduce blind spots and improve the comprehensiveness and accuracy of data collection. The satellite navigation sensor 21 provides accurate position and speed information, the laser radar sensor 22 can generate high-precision three-dimensional point cloud data, and the camera 23 can capture high-definition image information. The fusion of these high-precision data can provide a solid foundation for subsequent data analysis and processing. The camera and laser radar sensor are installed at a higher position, which reduces the possibility of being blocked by ground obstacles or low vegetation and improves the safety of data collection.

[0092] In order to solve the problem that the existing technology does not collect geographic data better and does not manage the collected geographic data more quickly, which makes the data transmission speed too slow and reduces the efficiency of scene construction, please refer to Figure 1-Figure 4 , this embodiment provides the following technical solutions:

[0093] Geographic information data monitoring system, including:

[0094] Acquisition equipment detection unit, used for:

[0095] Before the main body 1 collects data in the data collection area, the satellite navigation sensor 21, the laser radar sensor 22, the camera 23, the lifter 24, the millimeter wave radar and the inertial navigation are tested for performance;

[0096] The performance detection of the satellite navigation sensor 21 is to test the positioning accuracy, availability and compatibility of the satellite navigation sensor 21;

[0097] The performance test of the laser radar sensor 22 is to test the ranging performance, angular resolution, angular accuracy and point cloud quality of the laser radar sensor 22;

[0098] The performance test of the camera 23 is to test the resolution, color reproduction, focusing speed, and low-light environment of the camera 23;

[0099] The performance test of the lifter 24 is to test the function and load of the lifter 24;

[0100] The performance test of millimeter wave radar is to test the ranging accuracy, imaging resolution, power consumption and operating frequency range of millimeter wave radar;

[0101] The performance test of inertial navigation is to test the navigation parameters of inertial navigation;

[0102] After all tests are passed, the main body 1 collects data in the data collection area.

[0103] Specifically, performance testing can ensure the accuracy and reliability of each sensor and device, thereby ensuring the accuracy and reliability of the collected geographic information data. It can ensure the normal operation of the equipment during the data collection process, avoid downtime or data loss due to equipment failure, thereby improving the efficiency of data collection, and promptly discover and repair equipment problems to avoid accumulation of problems leading to major overhauls or replacements of equipment, thereby reducing equipment maintenance costs. Performance testing of equipment before data collection can promptly discover and repair potential faults or problems, avoiding data collection failures or inaccurate data due to equipment failures.

[0104] The geographic information data monitoring system also includes:

[0105] Acquisition data transmission unit, used for:

[0106] The main body 1 collects geographic information data in the data collection area using a satellite navigation sensor 21, a laser radar sensor 22, a camera 23, a millimeter wave radar and an inertial navigation, and transmits the collected geographic information data to a data processing center for data processing;

[0107] Among them, the satellite navigation sensor 21 collects the geographical location information of the body 1; the laser radar sensor 22 collects the environmental information in the data collection area; the camera 23 collects the image and video information in the data collection area; the millimeter wave radar collects the distance, relative speed, angle, position and shape information between the target object and the radar in the data collection area; the inertial navigation measures the linear acceleration and angular velocity information of the body 1 through the accelerometer and gyroscope sensor;

[0108] The satellite navigation sensor 21, the laser radar sensor 22, the camera 23, the millimeter wave radar and the inertial navigation complete the data collection in the data collection area to obtain geographic information data;

[0109] Confirm the data transmission volume of geographic information data;

[0110] Wherein, the geographic information data is divided into a number of data segments of the same length;

[0111] Determine the amount of geographic information data to be transmitted based on the number of data segments;

[0112] There are no fewer than four transmission channels for geographic information data to be transmitted to data processing;

[0113] Confirm the remaining capacity of each transmission channel;

[0114] A transmission channel whose transmission volume is less than the remaining capacity of the channel is selected as the transmission channel for geographic information data.

[0115] Specifically, by combining satellite navigation sensors, lidar sensors, cameras, millimeter-wave radars and inertial navigation, data including geographic location, environmental information, images and videos, dynamic state of target objects and motion state of the subject can be obtained. This variety of data provides rich materials for subsequent geographic information processing and analysis. Satellite navigation sensors provide high-precision geographic location information, which is essential for geographic information systems that require precise location data. Lidar sensors and millimeter-wave radars can obtain three-dimensional structure and dynamic information of the environment, and cameras can provide rich visual information. These sensors are used in combination to fully perceive the environmental conditions of the data collection area, improve the integrity and accuracy of data collection, and inertial navigation can achieve autonomous navigation and positioning by measuring the linear acceleration and angular velocity information of the subject. This is of great significance for data collection in areas where GPS signals are interfered with or cannot be covered. By dividing geographic information data into several data segments of the same length and confirming the transmission volume based on the number of data segments, this method can ensure that data is effectively managed and utilized during transmission. At the same time, selecting a transmission channel with a transmission volume less than the remaining capacity of the channel as the transmission channel for geographic information data can avoid data congestion and transmission delay, thereby improving the efficiency of data transmission. By confirming the remaining capacity of each transmission channel and selecting an appropriate transmission channel for data transmission, the stability and reliability of data during transmission can be ensured. This helps reduce the risk of data loss and damage and ensures the integrity and accuracy of data.

[0116] In order to solve the problem in the existing technology that the collected geographic information data is not processed, resulting in poor data quality and failure of scene construction, please refer to Figure 1-Figure 4 , this embodiment provides the following technical solutions:

[0117] The geographic information data monitoring system also includes:

[0118] Transmission data processing unit, used for:

[0119] The data processing center will unify the format of the received geographic information data;

[0120] After the format is unified, the data acquired by the laser radar sensor 22 and the millimeter wave radar are filtered and denoised;

[0121] Perform image preprocessing on the data acquired by the camera 23;

[0122] The image preprocessing is to optimize the image data in the acquired geographic information data.

[0123] Convert image data in geographic information data into grayscale images;

[0124] The grayscale image is filtered using the mean filtering method, and a filtered image is obtained after the filtering is completed;

[0125] Map the pixel values ​​of the filtered image from the range of 0-255 to the range of 0-1, and obtain a normalized image after the mapping is completed;

[0126] The normalized image is smoothed and sharpened, and after the smoothing and sharpening are completed, the grayscale distribution of the image is adjusted, and after the grayscale distribution is completed, a distribution image is obtained;

[0127] Convert the distribution image into an image of a balanced histogram through grayscale transformation;

[0128] Finally, a standard image captured by the camera 23 is obtained.

[0129] Specifically, by unifying the format of the received geographic information data, the consistency and processability of the data are ensured. Data filtering and denoising are performed on the data obtained by the lidar sensor and the millimeter wave radar, which can effectively eliminate or reduce the noise and interference in the original data. This helps to improve the accuracy and reliability of the data and provide high-quality data support for subsequent analysis and application. A series of preprocessing operations such as grayscale, filtering, normalization, smoothing, sharpening and grayscale distribution adjustment are performed on the image data obtained by the camera, which can significantly optimize the image quality and improve the readability and usability of the image information. Through grayscale transformation and equalization histogram processing, the contrast of the image can be improved, and the details in the image can be clearer, which is convenient for subsequent analysis and recognition. This is very important for extracting geographic information features from image data. The steps of filtering, denoising and image optimization in the preprocessing process can not only improve the data quality, but also enhance the robustness of the subsequent processing algorithm. This enables the algorithm to better cope with complex and changing data environments, improve the stability and reliability of the overall system, and improve the overall data processing efficiency by optimizing the image processing process, reducing unnecessary calculation steps and redundant data. This helps to reduce system resource consumption and improve the real-time performance and response speed of the system.

[0130] Specifically, the transmission data processing unit further includes:

[0131] A grayscale image extraction module, used to extract the grayscale image corresponding to the image data after the image data in the geographic information data is converted into a grayscale image;

[0132] A first grayscale value extraction module, used to extract the grayscale value corresponding to each pixel block in the grayscale image corresponding to the image data;

[0133] A grayscale value difference acquisition module, used to acquire the grayscale value difference between the grayscale values ​​of every two adjacent pixel blocks using the grayscale value corresponding to each pixel block;

[0134] The grayscale difference coefficient acquisition module is used to obtain the grayscale difference coefficient by using the grayscale value difference between the grayscale values ​​of each two adjacent pixel blocks, wherein the grayscale difference coefficient is obtained by the following formula:

[0135]

[0136] Among them, S represents the grayscale difference coefficient; n represents the total number of groups corresponding to each two adjacent pixel blocks; H ci H represents the grayscale value difference between the grayscale values ​​of two adjacent pixel blocks in the i-th group; zi H represents the grayscale median value corresponding to the grayscale values ​​of two adjacent pixel blocks in the i-th group; mini H represents the gray value corresponding to the pixel block with the lower gray value in the i-th group of two adjacent pixel blocks; x represents the median grayscale value corresponding to all pixel blocks contained in the grayscale image; exp represents an exponential function with e as the base;

[0137] The grayscale adjustment module is used to compare the grayscale value difference between the grayscale values ​​of each two adjacent pixel blocks with the grayscale difference coefficient, obtain a target pixel block for grayscale adjustment according to the comparison result, and perform grayscale adjustment on the target pixel block.

[0138] The technical effect of the above technical solution is: through the grayscale image extraction module, the image data in the geographic information data is converted into a grayscale image. This process simplifies the image information, removes the interference of color on subsequent processing, and makes subsequent processing more focused on the brightness information and spatial structure of the image, which is conducive to improving the efficiency and accuracy of subsequent processing.

[0139] The first grayscale value extraction module and the grayscale value difference acquisition module work together to accurately capture the grayscale value changes between each pixel block in the image and its adjacent pixel blocks. This fine-grained grayscale value analysis helps to identify details such as edges and textures in the image, providing an important basis for subsequent feature extraction or image analysis.

[0140] The grayscale difference coefficient acquisition module uses a complex formula to calculate the grayscale difference coefficient, which comprehensively considers multiple factors such as the grayscale value difference of adjacent pixel blocks, the grayscale median, and the grayscale median of the entire image, achieving a balanced consideration of the local and global features of the image. The grayscale adjustment module adaptively adjusts the grayscale of the target pixel block based on this coefficient, which can effectively improve the contrast of the image, enhance the visual effect of the image, and retain important detail information.

[0141] By calculating the grayscale difference coefficient and adjusting the grayscale accordingly, this technical solution can also suppress the noise in the image to a certain extent. Because noise often appears as a sudden change in grayscale value, this technical solution can weaken the influence of noise and make the image clearer by smoothing the grayscale value changes between adjacent pixel blocks.

[0142] Since this technical solution can accurately adjust the grayscale distribution of the image, making the features in the image more prominent and easier to identify, it can improve the accuracy and efficiency of analysis in subsequent image analysis, target detection, feature extraction and other tasks. This is of great significance for various application scenarios based on geographic information (such as urban planning, environmental monitoring, disaster assessment, etc.).

[0143] In summary, this technical solution achieves optimized processing of image data in geographic information data through a series of sophisticated grayscale processing steps, improves the quality of images and the accuracy of subsequent analysis, and has significant technical effects and broad application prospects.

[0144] Specifically, the grayscale adjustment module includes:

[0145] A comparison module, used for comparing the grayscale value difference between the grayscale values ​​of each two adjacent pixel blocks with the grayscale difference coefficient to obtain a comparison result;

[0146] A target pixel block acquisition module is used for extracting a pixel block with a lower grayscale value from the two adjacent pixel blocks whose grayscale values ​​are lower than the preset grayscale difference coefficient as a target pixel block when the comparison result indicates that the grayscale value difference between the grayscale values ​​of each two adjacent pixel blocks is lower than a preset grayscale difference coefficient;

[0147] A second grayscale value extraction module, used to extract grayscale values ​​of all adjacent pixel blocks of the target pixel block;

[0148] A maximum and minimum difference acquisition module, used to acquire the maximum and minimum difference between the grayscale value of the target pixel block and the grayscale values ​​of all adjacent pixel blocks by using the grayscale values ​​of all adjacent pixel blocks of the target pixel block;

[0149] The target grayscale value acquisition module is used to obtain the target grayscale value of the target pixel block by using the maximum difference value and the minimum difference value, wherein the target grayscale value is obtained by the following formula:

[0150]

[0151] Among them, H b Indicates the target grayscale value corresponding to the target pixel block; H cmax and H cminThey represent the maximum and minimum differences between the grayscale values ​​of the target pixel block and the grayscale values ​​of all adjacent pixel blocks respectively; S represents the grayscale difference coefficient;

[0152] The grayscale value adjustment execution module is used to perform grayscale adjustment on the target pixel block according to the target grayscale value to obtain an adjusted target pixel block.

[0153] The technical effect of the above technical solution is: through the comparison module and the target pixel block acquisition module, the technical solution can automatically identify those areas in the image with low local contrast (that is, the gray value difference between adjacent pixel blocks is lower than the preset gray value difference coefficient), and use the pixel blocks with low gray values ​​in these areas as target pixel blocks for further processing. This adaptive selection mechanism ensures that the processing process can be carried out according to the specific situation in the image, avoiding the over-enhancement or over-smoothing problems that may be caused by global unified processing.

[0154] The maximum and minimum difference acquisition module and the target grayscale acquisition module calculate the grayscale value difference between the target pixel block and all its adjacent pixel blocks, and calculate the target grayscale value based on these differences and the grayscale difference coefficient. This method not only considers the relationship between the target pixel block and a single adjacent pixel block, but also comprehensively considers its overall relationship with all surrounding adjacent pixel blocks, thereby achieving more refined and accurate grayscale adjustment.

[0155] The above technical solution can enhance the local contrast of the image while retaining the detailed information in the image as much as possible. In particular, for those pixel blocks with low grayscale values ​​and in low-contrast areas, by adjusting their grayscale values, their contrast with surrounding pixel blocks is improved, making them more clearly visible.

[0156] Since this technical solution is based on the gray value difference between pixel blocks, it can suppress noise and artifacts in the image to a certain extent. Because noise and artifacts often appear as random fluctuations or mutations in gray values, this technical solution can weaken the impact of these adverse factors by smoothing the gray value changes between adjacent pixel blocks.

[0157] After the grayscale adjustment process, the local contrast of the image is enhanced, the detail information is retained, and the noise and artifacts are suppressed, thereby improving the overall quality and visual effect of the image. This has positive significance for subsequent image analysis, processing or display tasks.

[0158] In summary, this technical solution achieves adaptive enhancement of the local contrast of the image through a series of fine grayscale adjustment steps, while retaining the detail information in the image and reducing the influence of noise and artifacts, ultimately improving the image quality and visual effect.

[0159] The geographic information data monitoring system also includes:

[0160] Processing data analysis unit for:

[0161] Extract features from the processed data obtained by the satellite navigation sensor 21, the laser radar sensor 22, the camera 23, the millimeter wave radar and the inertial navigation;

[0162] The processed data acquired by the laser radar sensor 22 is extracted from the point cloud data of the laser radar to extract ground features and object features; ground features include elevation and curvature; object features include shape and size;

[0163] The standard image acquired by the camera 23 is used to extract road signs, traffic lights, vehicles, and pedestrian data using image recognition technology;

[0164] Analyze the change in the reflected wave frequency in the processed data obtained by the millimeter wave radar, and extract the distance, relative speed and direction between the main body 1 and other vehicles in the data collection area;

[0165] Extracting the position, velocity, acceleration and attitude data of the main body 1 from the inertial navigation and satellite navigation sensor 21;

[0166] The data extracted from the satellite navigation sensor 21, the laser radar sensor 22, the camera 23, the millimeter wave radar and the inertial navigation are fused with feature information by using a particle filtering method;

[0167] After the feature information is fused, the acquisition scene model is constructed through the neural network model algorithm;

[0168] After the collection scene model is constructed, the standard geographic data model of the data collection area is obtained.

[0169] And import the standard geographic data model into the display terminal for display.

[0170] Specifically, the particle filter method is used to fuse data from different sensors, which can comprehensively consider the advantages of various sensors, reduce the uncertainty and error of single sensor data, and thus improve the accuracy of the overall data. By extracting ground features and object features from the point cloud data of the lidar, combined with information such as road signs and traffic lights obtained by the camera, and the measurement of the distance, relative speed and direction between vehicles by the millimeter wave radar, the key features of the data collection area can be fully captured, and the scene model can be constructed by using the neural network model algorithm for the fused feature information, which can quickly and accurately generate a standard geographic data model for the data collection area. This model is not only highly accurate, but also can reflect the changes in the actual scene in real time, and can adapt to various complex environments and scenes. Whether it is urban roads, highways or rural roads, it can effectively collect data and build scenes. At the same time, the fusion of multiple sensors also improves the robustness of the system. Even if a sensor fails or the data is abnormal, other sensors can provide effective data support.

[0171] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0172] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A geographic information data collection vehicle, comprising a body (1) and a geographic information data monitoring system, characterized in that: A data collector (2) is installed on the top of the body (1), and a millimeter wave radar and an inertial navigation system are arranged inside the body (1); Geographic information data monitoring system for: When the main body (1) is traveling in the data collection area, the data collector (2) at the top of the main body (1) collects geographic information data of the data collection area. After the geographic information data is collected, it is transmitted to the data processing center for data processing. After the geographic information data is processed, data analysis is performed, and the analyzed data is stored in a memory and displayed on a display terminal.

2. A geographic information data collection vehicle according to claim 1, characterized in that: The data collector (2) comprises a satellite navigation sensor (21), a laser radar sensor (22), a camera (23) and a lifter (24); the satellite navigation sensor (21) is mounted in front of the top of the body (1); the lifter (24) is mounted on the top of the body (1); the camera (23) is mounted on the top of the lifter (24); four cameras (23) are provided, and the laser radar sensor (22) is mounted on the top of the camera (23).

3. A geographic information data collection vehicle according to claim 2, characterized in that: The geographic information data monitoring system comprises: Acquisition equipment detection unit, used for: Before the main body (1) collects data in the data collection area, the satellite navigation sensor (21), the laser radar sensor (22), the camera (23), the elevator (24), the millimeter wave radar and the inertial navigation are tested for performance; The performance detection of the satellite navigation sensor (21) is to test the positioning accuracy, availability and compatibility of the satellite navigation sensor (21); The performance detection of the laser radar sensor (22) is to test the ranging performance, angular resolution, angular accuracy and point cloud quality of the laser radar sensor (22); The performance test of the camera (23) is to test the camera (23) in terms of resolution, color reproduction, focusing speed, and low-light environment; The performance test of the lifter (24) is to test the function and load of the lifter (24); The performance test of millimeter wave radar is to test the ranging accuracy, imaging resolution, power consumption and operating frequency range of millimeter wave radar; The performance test of inertial navigation is to test the navigation parameters of inertial navigation; After all tests are passed, the main body (1) performs data collection in the data collection area.

4. A geographic information data collection vehicle according to claim 3, characterized in that: The geographic information data monitoring system further includes: Acquisition data transmission unit, used for: The main body (1) collects geographic information data in the data collection area using a satellite navigation sensor (21), a laser radar sensor (22), a camera (23), a millimeter wave radar and an inertial navigation, and transmits the collected geographic information data to a data processing center for data processing; The satellite navigation sensor (21) collects geographical location information of the main body (1); the laser radar sensor (22) collects environmental information in the data collection area; the camera (23) collects image and video information in the data collection area; the millimeter wave radar collects the distance, relative speed, angle, position and shape information between the target object and the radar in the data collection area; the inertial navigation measures the linear acceleration and angular velocity information of the main body (1) through the accelerometer and gyroscope sensors; The satellite navigation sensor (21), the laser radar sensor (22), the camera (23), the millimeter wave radar and the inertial navigation complete the data collection in the data collection area to obtain geographic information data.

5. A geographic information data collection vehicle according to claim 4, characterized in that: The data collection and transmission unit is further used for: Confirm the data transmission volume of geographic information data; Wherein, the geographic information data is divided into a number of data segments of the same length; Determine the amount of geographic information data to be transmitted based on the number of data segments; There are no fewer than four transmission channels for geographic information data to be transmitted to data processing; Confirm the remaining capacity of each transmission channel; A transmission channel whose transmission volume is less than the remaining capacity of the channel is selected as the transmission channel for geographic information data.

6. A geographic information data collection vehicle according to claim 5, characterized in that: The geographic information data monitoring system further includes: Transmission data processing unit, used for: The data processing center will unify the format of the received geographic information data; After the format is unified, the data acquired by the laser radar sensor (22) and the millimeter wave radar are filtered and denoised; Performing image preprocessing on the data acquired by the camera (23); The image preprocessing is to optimize the image data in the acquired geographic information data.

7. A geographic information data collection vehicle according to claim 6, characterized in that: The transmission data processing unit is further used for: Convert image data in geographic information data into grayscale images; The grayscale image is filtered using the mean filtering method, and a filtered image is obtained after the filtering is completed; Map the pixel values ​​of the filtered image from the range of 0-255 to the range of 0-1, and obtain a normalized image after the mapping is completed; The normalized image is smoothed and sharpened, and after the smoothing and sharpening are completed, the grayscale distribution of the image is adjusted, and after the grayscale distribution is completed, a distribution image is obtained; Convert the distribution image into an image of a balanced histogram through grayscale transformation; Finally, a standard image captured by the camera (23) is obtained.

8. A geographic information data collection vehicle according to claim 6, characterized in that: The transmission data processing unit further includes: A grayscale image extraction module, used to extract the grayscale image corresponding to the image data after the image data in the geographic information data is converted into a grayscale image; A first grayscale value extraction module, used to extract the grayscale value corresponding to each pixel block in the grayscale image corresponding to the image data; A grayscale value difference acquisition module, used to acquire the grayscale value difference between the grayscale values ​​of every two adjacent pixel blocks using the grayscale value corresponding to each pixel block; The grayscale difference coefficient acquisition module is used to obtain the grayscale difference coefficient by using the grayscale value difference between the grayscale values ​​of each two adjacent pixel blocks, wherein the grayscale difference coefficient is obtained by the following formula: Among them, S represents the grayscale difference coefficient; n represents the total number of groups corresponding to each two adjacent pixel blocks; H ci H represents the grayscale value difference between the grayscale values ​​of two adjacent pixel blocks in the i-th group; zi H represents the grayscale median value corresponding to the grayscale values ​​of two adjacent pixel blocks in the i-th group; mini H represents the gray value corresponding to the pixel block with the lower gray value in the i-th group of two adjacent pixel blocks; x represents the median grayscale value corresponding to all pixel blocks contained in the grayscale image; exp represents an exponential function with e as the base; The grayscale adjustment module is used to compare the grayscale value difference between the grayscale values ​​of each two adjacent pixel blocks with the grayscale difference coefficient, obtain a target pixel block for grayscale adjustment according to the comparison result, and perform grayscale adjustment on the target pixel block.

9. A geographic information data collection vehicle according to claim 8, characterized in that: The grayscale adjustment module comprises: A comparison module, used for comparing the grayscale value difference between the grayscale values ​​of each two adjacent pixel blocks with the grayscale difference coefficient to obtain a comparison result; A target pixel block acquisition module is used for extracting a pixel block with a lower grayscale value from the two adjacent pixel blocks whose grayscale values ​​are lower than the preset grayscale difference coefficient as a target pixel block when the comparison result indicates that the grayscale value difference between the grayscale values ​​of each two adjacent pixel blocks is lower than a preset grayscale difference coefficient; A second grayscale value extraction module, used to extract grayscale values ​​of all adjacent pixel blocks of the target pixel block; A maximum and minimum difference acquisition module, used to acquire the maximum and minimum difference between the grayscale value of the target pixel block and the grayscale values ​​of all adjacent pixel blocks by using the grayscale values ​​of all adjacent pixel blocks of the target pixel block; The target grayscale value acquisition module is used to obtain the target grayscale value of the target pixel block by using the maximum difference value and the minimum difference value, wherein the target grayscale value is obtained by the following formula: Among them, H b Indicates the target grayscale value corresponding to the target pixel block; H cmax and H cmin They represent the maximum and minimum differences between the grayscale values ​​of the target pixel block and the grayscale values ​​of all adjacent pixel blocks respectively; S represents the grayscale difference coefficient; The grayscale value adjustment execution module is used to perform grayscale adjustment on the target pixel block according to the target grayscale value to obtain an adjusted target pixel block.

10. The geographic information data collection vehicle according to claim 7, characterized in that: The geographic information data monitoring system further includes: Processing data analysis unit for: Extracting features from the processed data obtained by the satellite navigation sensor (21), the laser radar sensor (22), the camera (23), the millimeter wave radar and the inertial navigation; The processed data acquired by the laser radar sensor (22) is extracted from the point cloud data of the laser radar to extract ground features and object features; the ground features include elevation and curvature; the object features include shape and size; Using image recognition technology to extract road signs, traffic lights, vehicles, and pedestrian data from the standard image captured by the camera (23); Analyze the change in the reflected wave frequency in the processed data obtained by the millimeter wave radar, and extract the distance, relative speed and direction between the main body (1) and other vehicles in the data collection area; Extracting the position, velocity, acceleration and attitude data of the main body (1) from the inertial navigation and satellite navigation sensor (21); The data extracted from the satellite navigation sensor (21), the laser radar sensor (22), the camera (23), the millimeter wave radar and the inertial navigation are fused with feature information by using a particle filtering method; After the feature information is fused, the acquisition scene model is constructed through the neural network model algorithm; After the collection scene model is constructed, the standard geographic data model of the data collection area is obtained. And import the standard geographic data model into the display terminal for display.

Images