CN117237506B - Method for generating simulated laser point cloud image by aerial image - Google Patents
Method for generating simulated laser point cloud image by aerial image Download PDFInfo
- Publication number
- CN117237506B CN117237506B CN202311518175.7A CN202311518175A CN117237506B CN 117237506 B CN117237506 B CN 117237506B CN 202311518175 A CN202311518175 A CN 202311518175A CN 117237506 B CN117237506 B CN 117237506B
- Authority
- CN
- China
- Prior art keywords
- image
- point cloud
- images
- laser point
- rgb
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 12
- 230000007797 corrosion Effects 0.000 claims abstract description 5
- 238000005260 corrosion Methods 0.000 claims abstract description 5
- 230000000694 effects Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 230000001172 regenerating effect Effects 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 abstract description 5
- 238000012549 training Methods 0.000 abstract description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Image Processing (AREA)
Abstract
本发明涉及模拟图像生成技术领域，具体提供一种航拍图像生成模拟激光点云图像的方法，利用无人机搭载可见光载荷，航拍获取RGB图像，将RGB图像转化为Y通道图像，对Y通道进行二值化、腐蚀以及不同程度的膨胀处理，并将最终膨胀图像与原始Y通道图像进行叠加后，投影到所述RGB图像，再根据需模拟的激光雷达分辨率，调整图像分辨率，生成模拟激光点云图像。本发明通过对航拍图像进行处理，模拟激光雷达获得的激光点云图像，能够实时生成模拟激光点云图像，供学员观看，避免了初学者直接进行激光点云系统的实务操作，显著降低了激光点云雷达操作手的训练成本。
The present invention relates to the technical field of simulated image generation, and specifically provides a method for generating simulated laser point cloud images from aerial images. UAVs are used to carry visible light loads, aerial photography is used to obtain RGB images, the RGB images are converted into Y channel images, and the Y channel is processed Binarization, corrosion, and expansion processing to varying degrees, and superimposing the final expansion image with the original Y channel image, then projecting it to the RGB image, and then adjusting the image resolution according to the lidar resolution to be simulated to generate a simulation Laser point cloud image. By processing aerial images and simulating laser point cloud images obtained by lidar, the present invention can generate simulated laser point cloud images in real time for students to view, avoiding beginners from directly performing practical operations on the laser point cloud system, and significantly reducing the cost of laser point clouds. Training costs for point cloud radar operators.
Description
Technical Field
The invention relates to the technical field of simulated image generation, and particularly provides a method for generating a simulated laser point cloud image by using an aerial image suitable for an unmanned aerial vehicle system.
Background
For most beginners operating laser point clouds, the operation of a laser point cloud system is too complex, if the laser point cloud system is directly and practically operated, the laser point cloud system is easily damaged, the cost of the packaging equipment of the laser point cloud system is high, and the training cost is increased by using the packaging equipment for training. Therefore, in the initial learning process, the learner should be prevented from directly performing actual operations, the damage probability of the equipment is reduced, and a method capable of acquiring the simulated laser point cloud image with low cost is required for the learner to perform observation learning.
Disclosure of Invention
The invention provides a method for generating a simulated laser point cloud image by aerial photographing of an image, which is used for obtaining a target image by unmanned aerial vehicle, processing the target image and simulating the laser point cloud image, so that a learner is prevented from directly operating a laser point cloud system.
The invention provides a method for generating a simulated laser point cloud image by an aerial image, which comprises the following steps:
s1: the unmanned aerial vehicle aerial photographs are obtained to obtain RGB images, and the flying height of the unmanned aerial vehicle is calculated;
s2: performing analog processing on the RGB image, including:
converting R, G, B channels of the RGB image into Y channels to obtain Y channel images, wherein R, G, B sequentially represents the values of red, green and blue channels, and Y represents the brightness value;
detecting a closed region in the Y channel image, and increasing Y in the closed region to simulate the reflection intensity of the laser radar;
projecting the processed Y channel image to an RGB image to obtain a pseudo-color image;
s3: and adjusting the resolution of the pseudo-color image according to the laser radar resolution to be simulated, and generating a simulated laser point cloud image.
Preferably, at the moment when the unmanned aerial vehicle acquires the RGB image, the flying height of the unmanned aerial vehicle is measured for a plurality of times, and an average value is obtained.
Preferably, in S2, the R, G, B channel of the RGB image is converted to the Y channel using the following formula:
。
preferably, in S2, the closed region in the Y-channel image is detected by binarization, and the average brightness mean of the Y-channel image is used as a threshold for binarization to obtain a binary image BW as follows:
。
preferably, the process of increasing Y in the closed region in S2 is as follows:
carrying out corrosion treatment on the binary image BW;
expanding the corroded binary images to different degrees, and sequentially obtaining binary images, namely, pengzhang1, pengzhang2, pengzhang3 and pengzhang4 from small to large in expansion degree;
regenerating the expanded binary image into a uint8 type image, wherein the images are as follows:
averaging the generated uint8 type image to obtain a final expansion imageThe method comprises the following steps:；
y-channel image and final inflation imageThe superposition is carried out, and an concave-convex effect image aotu simulating the reflection intensity of the laser point cloud image is formed as follows: />；
And if the superposed numerical value is larger than 255, assigning 225 to the superposed numerical value.
Preferably, the image aotu is projected onto the RGB image to obtain a pseudo-color image weicaise, and a projection formula of a R, G, B channel of the pseudo-color image weicaise is as follows:
compared with the prior art, the invention has the following beneficial effects:
according to the invention, the unmanned aerial vehicle is used for carrying the low-cost visible light load, the unmanned aerial vehicle is used for shooting the aerial image, the aerial image is processed by the method provided by the invention, the laser point cloud image obtained by the laser radar is simulated, the simulated laser point cloud image can be generated in real time for a learner to watch, the practical operation of the laser point cloud system by the beginner is avoided, and the training cost of the laser point Yun Lei for an operator is obviously reduced. In addition, the method has small operand, can be operated on an onboard computer, and has better popularization prospect.
Drawings
FIG. 1 is a flow chart of a method for generating a simulated laser point cloud image from an aerial image provided in accordance with an embodiment of the present invention;
FIG. 2 is an aerial acquired RGB image provided in accordance with an embodiment of the present invention;
FIG. 3 is a Y-channel image obtained by RGB conversion in S2 provided in accordance with an embodiment of the present invention;
fig. 4 is a binary image BW obtained by the binarization detection in S2 according to an embodiment of the present invention;
FIG. 5 is a binary image after corrosion in S2 provided in accordance with an embodiment of the present invention;
FIG. 6 is a image of the inflated pengzhang1 in S2 provided in accordance with an embodiment of the present invention;
FIG. 7 is a post-expansion pengzhang2 image in S2 provided in accordance with an embodiment of the present invention;
FIG. 8 is a post-expansion pengzhang3 image in S2 provided in accordance with an embodiment of the present invention;
FIG. 9 is a post-expansion pengzhang4 image in S2 provided in accordance with an embodiment of the present invention;
FIG. 10 is a view of regenerating the after_pengzhang1 image of the uint8 type in S2 according to an embodiment of the present invention;
FIG. 11 is a view of regenerating an after_pengzhang2 image of the uint8 type in S2 according to an embodiment of the present invention;
FIG. 12 is a view of regenerating the after_pengzhang3 image of the uint8 type in S2 according to an embodiment of the present invention;
FIG. 13 is an after_pengzhang4 image of the uint8 type regenerated in S2 according to an embodiment of the present invention;
FIG. 14 is a final dilated image obtained after averaging in S2 provided in accordance with embodiments of the present invention;
fig. 15 is a concave-convex effect image reflecting the reflection intensity in S2 provided according to the embodiment of the present invention;
FIG. 16 is a pseudo color image in S2 provided in accordance with an embodiment of the present invention;
fig. 17 is a simulated laser point cloud image with final resolution adjustment provided in accordance with an embodiment of the present invention.
Detailed Description
Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the following description, like modules are denoted by like reference numerals. In the case of the same reference numerals, their names and functions are also the same. Therefore, a detailed description thereof will not be repeated.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not to be construed as limiting the invention.
According to the method for generating the simulated laser point cloud image by the aerial image, provided by the embodiment of the invention, the simulated laser point cloud image obtained by the simulated radar is compiled on the airborne computer, calculated and processed, and is transmitted to the ground station through the radio link, so that the trainee on the ground station can watch and learn the laser point cloud image, the knowledge and cognition of the trainee on the laser point cloud image are enhanced, and as shown in fig. 1, the specific simulation process is as follows:
s1: the unmanned aerial vehicle performs aerial photography on the target area or the target object to obtain an RGB image of the target area or the target object shown in fig. 2, and at the moment of obtaining the RGB image by the unmanned aerial vehicle, the flying height of the unmanned aerial vehicle, namely the distance between the unmanned aerial vehicle and the ground, is measured for a plurality of times through technologies such as photoelectric ranging, the average value of the multi-measurement results is calculated as the final flying height, the measurement times are usually 5 times, and the measurement times and the measurement frequency can be adjusted simultaneously.
S2: on the unmanned aerial vehicle, the on-board computer carries out simulation processing on the RGB image according to a preset tool or algorithm, and specific simulation parameters can be preset or adjusted according to parameters of the laser radar to be simulated, and the specific process is as follows:
the R, G, B three primary color channels of the RGB image shown in fig. 2 were converted into Y channels, and a Y channel image shown in fig. 3 was obtained, in which R, G, B sequentially represents the values of the three primary color channels of red, green, and blue, and Y represents the luminance value. The R, G, B channel of the RGB image is converted to the Y channel as calculated:
。
and detecting a closed region in the Y-channel image by using an image processing algorithm, and carrying out uplift processing on the closed region, namely gradually increasing the value of Y in the closed region, so as to simulate the reflection intensity of the laser radar.
The occlusion region detection may be performed by a connected graph algorithm or binarization, morphological processing, or the like, and in this embodiment, the occlusion region in the Y-channel image is detected by binarization. In the binarization process, the brightness average mean of the Y-channel image is used as a binarization threshold value, the brightness values Y in the Y-channel image are judged one by one and assigned, and the assignment basis of the obtained binary image BW is as follows:
；
namely, the brightness values of all the points with the brightness value Y larger than the brightness average value mean are assigned to be 1, the brightness values of other points are assigned to be 0, and the binary image BW shown in fig. 4 is obtained after assignment.
The binary image BW shown in fig. 4 is subjected to corrosion treatment, and the binary image BW is subjected to smoothing operation, so that effects of noise reduction, detail removal, target region shrinkage and the like are realized, and the corroded image shown in fig. 5 is recorded as fushi.
The corroded binary image shown in fig. 5 is expanded to different degrees to realize area expansion, and the embodiment of the invention carries out expansion treatment of different degrees for 4 times to ensure the expansion effect, and the expanded binary image is obtained sequentially from small expansion degree to large expansion degree:
pengzhang1 as shown in fig. 6;
pengzhang2 as shown in fig. 7;
pengzhang3 as shown in fig. 8;
pengzhang4 as shown in fig. 9.
Performing image conversion on the expanded binary image according to the uint8 rule, and regenerating an image of the uint8 type, wherein the image comprises the following steps of:
as shown in the figure10, shown in the drawing。
As shown in fig. 11。
As shown in fig. 12。
As shown in fig. 13。
To prevent numerical value overflow, the four uint8 type images generated in the above-mentioned fig. 10 to 13 are averaged and averaged to obtain the final expanded imageThe specific calculation formula is as follows:；
the final inflation image obtained after the average calculation is shown in fig. 14.
The final expanded image will be shown in fig. 14The method is overlapped with the Y channel image shown in fig. 3 to realize mutual overlapping of image values, after the overlapping, an concave-convex effect image aotu simulating the reflection intensity of the laser point cloud image shown in fig. 15 is obtained, the image aotu realizes the uplift effect of a closed area, the concave-convex effect caused by different reflection intensities of the actual laser point cloud image is simulated, and the process of obtaining aotu through overlapping is expressed as follows:；
wherein, because the numerical summation is performed in the superposition process, the problem of numerical overflow may occur, and therefore, the overflow numerical value is additionally specified: if the superimposed value is greater than 255, the superimposed value is assigned 225.
The concave-convex effect image aotu shown in fig. 15 is projected onto the RGB image shown in fig. 2, and a pseudo-color image weibaise shown in fig. 16 is obtained by projection, so that simulation display is facilitated for students. The projection formula of the R, G, B channel of the pseudo-color image weicaise is as follows:
s3: according to the resolution of the laser radar which is required to be simulated, the resolution of the pseudo-color image weicaise is adjusted, the resolution reduction processing of the pseudo-color image weicaise is carried out to different degrees, and finally the simulated laser point cloud image Lidar shown in fig. 17 is obtained. The unmanned aerial vehicle is transmitted to the ground station through the radio link, so that students on the ground station can watch and learn, and the resolution of the output is automatically switched according to the flying height of the unmanned aerial vehicle, and the specific switching process is as follows:
setting the pixel value of the ith row and the jth column of the simulated laser point cloud image Lidar as Lidar i,j 。
When the unmanned aerial vehicle flight height is 1000m, the resolution is 0.8m.
When the unmanned aerial vehicle flight height is 500m, the resolution is 0.4m.
When the unmanned aerial vehicle flight height is 200m, the resolution is 0.2m.
When the resolution of the simulated laser point cloud image is 0.2m, combining every two pixels into 1 pixel, and reducing the resolution to 1/2 of the original image, wherein the method specifically comprises the following steps of:
；
when the resolution of the simulated laser point cloud image is 0.4m, every 4 pixels are combined into 1 pixel, the resolution is reduced to 1/4 of the original image, and the processing is specifically performed according to the following formula:
；
when the resolution of the simulated laser point cloud image is 0.8m, merging every 8 pixels into 1 pixel, reducing the resolution to 1/8 of the original image, and carrying out pixel merging processing according to the following formula:
。
while embodiments of the present invention have been illustrated and described above, it will be appreciated that the above described embodiments are illustrative and should not be construed as limiting the invention. Variations, modifications, alternatives and variations of the above-described embodiments may be made by those of ordinary skill in the art within the scope of the present invention.
The above embodiments of the present invention do not limit the scope of the present invention. Any other corresponding changes and modifications made in accordance with the technical idea of the present invention shall be included in the scope of the claims of the present invention.
Claims (3)
1. The method for generating the simulated laser point cloud image by the aerial image is characterized by comprising the following steps of:
s1: the unmanned aerial vehicle aerial photographs are obtained to obtain RGB images, and the flying height of the unmanned aerial vehicle is calculated;
s2: performing analog processing on the RGB image, including:
converting R, G, B channels of the RGB image into Y channels to obtain Y channel images, wherein R, G, B sequentially represents the values of red, green and blue channels, and Y represents the brightness value;
detecting a closed region in a Y-channel image, and increasing Y in the closed region to simulate the reflection intensity of a laser radar; the R, G, B channels of the RGB image were converted to Y channels using the following formula:
detecting a closed region in the Y-channel image by using binarization, taking the brightness average mean of the Y-channel image as a binarization threshold value, and obtaining a binary image BW as follows:
the process of increasing Y in the closed region is as follows:
carrying out corrosion treatment on the binary image BW;
expanding the corroded binary images to different degrees, and sequentially obtaining binary images, namely, pengzhang1, pengzhang2, pengzhang3 and pengzhang4 from small to large in expansion degree;
regenerating the expanded binary image into a uint8 type image, wherein the images are as follows:
；
；
；
；
averaging the generated uint8 type image to obtain a final expansion imageThe method comprises the following steps:
；
y-channel image and final inflation imageThe superposition is carried out, and an concave-convex effect image aotu simulating the reflection intensity of the laser point cloud image is formed as follows:
；
if the value after superposition is larger than 255, assigning 225 to the value after superposition;
projecting the processed Y channel image to the RGB image to obtain a pseudo-color image;
s3: and adjusting the resolution of the pseudo-color image according to the laser radar resolution to be simulated, and generating a simulated laser point cloud image.
2. The method for generating simulated laser point cloud images from aerial images of claim 1 wherein the flying height of the unmanned aerial vehicle is measured a plurality of times and averaged at the time the unmanned aerial vehicle acquires the RGB images.
3. The method for generating a simulated laser point cloud image from an aerial image of claim 2 wherein an image aotu is projected onto said RGB image to obtain a pseudo-color image weicaise, the projection formula of R, G, B channels of the pseudo-color image weicaise is as follows:
；
；
。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311518175.7A CN117237506B (en) | 2023-11-15 | 2023-11-15 | Method for generating simulated laser point cloud image by aerial image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311518175.7A CN117237506B (en) | 2023-11-15 | 2023-11-15 | Method for generating simulated laser point cloud image by aerial image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117237506A CN117237506A (en) | 2023-12-15 |
| CN117237506B true CN117237506B (en) | 2024-02-02 |
Family
ID=89084743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311518175.7A Active CN117237506B (en) | 2023-11-15 | 2023-11-15 | Method for generating simulated laser point cloud image by aerial image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117237506B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104574405A (en) * | 2015-01-15 | 2015-04-29 | 北京天航华创科技股份有限公司 | Color image threshold segmentation method based on Lab space |
| WO2020020146A1 (en) * | 2018-07-25 | 2020-01-30 | 深圳市商汤科技有限公司 | Method and apparatus for processing laser radar sparse depth map, device, and medium |
| CN111915662A (en) * | 2019-05-07 | 2020-11-10 | 北京京东尚科信息技术有限公司 | Three-dimensional laser point cloud data preprocessing method and device |
| CN112087985A (en) * | 2018-05-10 | 2020-12-15 | 3M创新有限公司 | Simulated orthodontic treatment via real-time enhanced visualization |
| CN115171096A (en) * | 2022-07-27 | 2022-10-11 | 上海应用技术大学 | 3D target detection method based on RGB image and laser point cloud fusion |
| CN116245717A (en) * | 2023-05-10 | 2023-06-09 | 长春理工大学 | Method for generating simulated SAR radar image by aerial image |
| CN117058051A (en) * | 2023-07-17 | 2023-11-14 | 中国电子科技集团公司第二十七研究所 | Method and device based on fusion of laser point cloud and low-light-level image |
-
2023
- 2023-11-15 CN CN202311518175.7A patent/CN117237506B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104574405A (en) * | 2015-01-15 | 2015-04-29 | 北京天航华创科技股份有限公司 | Color image threshold segmentation method based on Lab space |
| CN112087985A (en) * | 2018-05-10 | 2020-12-15 | 3M创新有限公司 | Simulated orthodontic treatment via real-time enhanced visualization |
| WO2020020146A1 (en) * | 2018-07-25 | 2020-01-30 | 深圳市商汤科技有限公司 | Method and apparatus for processing laser radar sparse depth map, device, and medium |
| CN111915662A (en) * | 2019-05-07 | 2020-11-10 | 北京京东尚科信息技术有限公司 | Three-dimensional laser point cloud data preprocessing method and device |
| CN115171096A (en) * | 2022-07-27 | 2022-10-11 | 上海应用技术大学 | 3D target detection method based on RGB image and laser point cloud fusion |
| CN116245717A (en) * | 2023-05-10 | 2023-06-09 | 长春理工大学 | Method for generating simulated SAR radar image by aerial image |
| CN117058051A (en) * | 2023-07-17 | 2023-11-14 | 中国电子科技集团公司第二十七研究所 | Method and device based on fusion of laser point cloud and low-light-level image |
Non-Patent Citations (1)
| Title |
|---|
| 视觉与激光点云融合的深度图像获取方法;王东敏;彭永胜;李永乐;;军事交通学院学报(10);83-87 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117237506A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113610044A (en) | 4D mmWave 3D target detection method and system based on self-attention mechanism | |
| CN114140672A (en) | A target detection network system and method for multi-sensor data fusion in rainy and snowy weather scenarios | |
| CN113240670B (en) | Image segmentation method for object to be worked in live working scene | |
| CN113920101A (en) | Object detection method, device, device and storage medium | |
| CN114155265A (en) | 3D LiDAR road point cloud segmentation method based on YOLACT | |
| US20240062460A1 (en) | Freestyle acquisition method for high-dimensional material | |
| Ren et al. | Environment influences on uncertainty of object detection for automated driving systems | |
| CN117237506B (en) | Method for generating simulated laser point cloud image by aerial image | |
| CN116403186A (en) | Automatic driving three-dimensional target detection method based on FPN Swin Transformer and Pointernet++ | |
| JP6232933B2 (en) | Radiation distortion correction apparatus, road environment recognition apparatus, radial distortion correction method and program | |
| CN110738668B (en) | Method and system for intelligently controlling high beam and vehicle | |
| CN116958639A (en) | A method for detecting and enhancing wrong behavior of traffic light recognition models | |
| CN103247069B (en) | Ultraviolet scene simulation method and system based on emittance characteristic and spectral characteristic | |
| CN116245717B (en) | Method for generating simulated SAR radar image by aerial image | |
| CN112233071A (en) | Multi-granularity hidden danger detection method and system based on power transmission network picture in complex environment | |
| CN109978982B (en) | Point cloud rapid coloring method based on oblique image | |
| Lelowicz et al. | Discussion of novel filters and models for color space conversion | |
| JPH1151611A (en) | Apparatus and method for recognizing position and orientation of object to be recognized | |
| KR102023470B1 (en) | Solar module monitoring system using flight path generation algorithm and monitoring method of solar module using it | |
| da Cunha et al. | A study on the impact of domain randomization for monocular deep 6DoF pose estimation | |
| CN110008918B (en) | Method for identifying posture of motorcycle simulator driver | |
| CN106504200A (en) | The image irradiation compensation method mapped based on hue shift estimation and pointwise tone and system | |
| CN114387348A (en) | Calibration method of large view field camera with ground-based sky background | |
| CN118411683B (en) | Ship detection method and system for simulating different angle transformation | |
| CN118799435B (en) | Method for generating simulated hyperspectral image based on aerial image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |