CN114494845A - Artificial intelligence hidden danger troubleshooting system and method for construction project site - Google Patents
Artificial intelligence hidden danger troubleshooting system and method for construction project site Download PDFInfo
- Publication number
- CN114494845A CN114494845A CN202111535313.3A CN202111535313A CN114494845A CN 114494845 A CN114494845 A CN 114494845A CN 202111535313 A CN202111535313 A CN 202111535313A CN 114494845 A CN114494845 A CN 114494845A
- Authority
- CN
- China
- Prior art keywords
- image
- aerial vehicle
- unmanned aerial
- cloud computing
- computing platform
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
Abstract
The invention discloses a system and a method for checking artificial intelligence hidden dangers on construction project sites, and belongs to the technical field of highway engineering management. The unmanned aerial vehicle aerial photographing device can move back and forth on a highway engineering construction site and is used for acquiring pictures of the highway engineering construction site; the cloud computing platform is used for receiving image information transmitted by the unmanned aerial vehicle aerial photography device, and the CNN model is used for comparing and analyzing the image information and classifying diseases in the image; an image automatic fitting and positioning system is loaded in the cloud computing platform, and the image automatic fitting and positioning system is used for positioning and displaying the identified disease picture at the corresponding position of the three-dimensional model; the control center is used for receiving state information of the unmanned aerial vehicle aerial photographing device, judging whether the operation state of the unmanned aerial vehicle aerial photographing device is normal or not, performing data interaction with the cloud computing platform through the wireless network, and sending alarm information to an attendant. The invention can automatically identify and position the diseases in the highway engineering.
Description
Technical Field
The invention belongs to the technical field of highway engineering, and particularly relates to a system and a method for checking artificial intelligence hidden dangers on construction project sites.
Background
The construction of wisdom building site is mostly through video monitoring, the sensor, techniques such as face identification, manage the building site, to such long linear project of highway engineering, all install supervisory equipment and sensor everywhere and will throw a large amount of equipment undoubtedly, the wasting of resources has also been caused, and supervisory equipment and sensor are limited to the problem discernment that exists in the engineering, mainly patrol every day through the special messenger at present, the record of shooing, inform the mode of rectification and reform to carry out the security quality inspection to the scene, this requires that this personnel need possess basic technical knowledge and long-time work warp, need arrange the special technical messenger every day and inspect whole project, and the manual inspection can not reach all the way, the scope of inspection and result are good and are influenced by artificial subjectively great, efficiency is also not high.
Disclosure of Invention
The invention aims to provide a site artificial intelligence hidden danger troubleshooting system and a site artificial intelligence hidden danger troubleshooting method for a construction project, which can be used for efficiently identifying diseases on highway engineering.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a system for checking artificial intelligence hidden danger on construction project site comprises
The unmanned aerial vehicle aerial photographing device can move back and forth on a highway engineering construction site and is used for acquiring pictures of the highway engineering construction site;
the cloud computing platform is used for receiving image information transmitted by the unmanned aerial vehicle aerial photographing device, a set of image processing system is integrated in the cloud computing platform, and the image processing system processes the photo of the unmanned aerial vehicle and establishes a three-dimensional model; a CNN model is loaded in the cloud computing platform, and the CNN model performs comparative analysis on the image information and classifies diseases existing in the image; an image automatic fitting and positioning system is loaded in the cloud computing platform, and the image automatic fitting and positioning system is used for positioning and displaying the identified disease picture at a position corresponding to the three-dimensional model;
and the control center is used for receiving the state information of the unmanned aerial vehicle aerial photographing device and judging whether the running state of the unmanned aerial vehicle aerial photographing device is normal or not, and the control center performs data interaction with the cloud computing platform through a wireless network and sends alarm information to an attendant.
Furthermore, the photo shot by the unmanned aerial vehicle is provided with a geographical position coordinate, and the position of the problem on the engineering site can be displayed by combining the three-dimensional model.
Further, the diseases comprise site surface water accumulation, pot holes and side slope landslides.
Further, the method is characterized by comprising the following steps:
s1, setting a line setting area and parameters according to the construction route map, acquiring images by the unmanned aerial vehicle along the construction route map and uploading the images to a cloud computing platform, and processing the images of the unmanned aerial vehicle by the image processing system;
s2, establishing a three-dimensional map model, wherein the three-dimensional map model displays geographic position coordinates and mileage stake marks;
s3, establishing a parallel number CNN model;
s4, analyzing the photos by the CNN models with good numbers, screening and outputting hidden danger photos, classifying diseases in the photos, and positioning and displaying the recognized pictures of the diseases at the corresponding positions of the three-dimensional models.
Further, the CNN model includes:
the convolution unit is used for performing convolution summation on the characteristic mapping graph of the input number by adopting a convolution kernel, and consists of 10 convolution layers, wherein the 10 convolution layers have different weights and thresholds;
the pooling unit is used for downsampling the feature mapping image after convolution, reducing the resolution of the feature mapping image and selecting excellent features;
and the classification unit classifies the output number of the feature mapping graph output by the convolution unit to a softmax loss function through a full connection layer and provides a classification result.
Further, in step S3, the method for counting the CNN models includes:
s2.1, establishing a deep learning model;
s2.2, collecting a large number of road disease pictures, performing data set amplification on the collected pictures, and dividing the amplified road disease data into a plurality of samples and target samples;
s2.3, giving a number sample, and giving an initial weight and a threshold value of the target sample;
s2.4, outputting the type of the disease;
s2.5, outputting an error: the difference between the target disease type and the output disease type;
s2.6, error evaluation is carried out, and if the error is smaller than a preset value, counting is finished; if the error deviation is larger than the preset value, the error deviation is calculated, the weight value and the threshold value are adjusted, and then the step S2.4 is carried out.
Further, in the step S4,
s4.1, comparing the pictures acquired by the unmanned aerial vehicle with the pictures in the data set one by one;
s4.2, carrying out graying processing on the two image images to be compared to obtain a grayscale image of the image; creating a one-dimensional gray histogram, and enabling the statistical image to be distributed in [0, 255] pixels; calculating a one-dimensional histogram of the gray level image; normalizing the calculated one-dimensional histogram; creating a graph for displaying a histogram of each pixel, wherein the abscissa is a gray level and the ordinate is the number of pixels; drawing each histogram into the created graph; measuring the Babbitt distance of the histograms of the two images to calculate the similarity of the images, namely calculating the similarity of the images based on the gray-scale color histogram;
s4.3, extracting image texture features by adopting a gray level co-occurrence matrix, and then calculating the similarity of the images;
s4.4, calculating the final image similarity by adopting weighted average according to the image similarity calculated in the previous two steps;
s4.5, when the final image similarity is larger than a preset value, determining that the picture acquired by the unmanned aerial vehicle corresponds to the disease type of the picture in the data set;
and S4.6, the image automatic fitting and positioning system positions and displays the recognized disease picture at the corresponding position of the three-dimensional model.
Due to the adoption of the technical scheme, the invention has the following beneficial effects:
1. according to the invention, the unmanned aerial vehicle is adopted for routing inspection, the unmanned aerial vehicle aerial photography improves the efficiency of the inspection of the safety quality of highway engineering management compared with manual inspection, the unmanned aerial vehicle aerial photography can perform overall evaluation on projects, the overall progress is identified, the unmanned aerial vehicle aerial photography range is wider, the problem of engineering safety quality which is difficult to find manually can be found, and the efficiency and the accuracy of CNN model identification are high.
2. According to the invention, an engineering disease treatment database is formed by aerial photos of the unmanned aerial vehicle, and quality problem parts are generated by big data analysis, so that the quality problem parts are avoided in the project construction process.
3. The method disclosed by the invention keeps the characteristics of rapidness and high efficiency of the gray-scale color histogram algorithm as much as possible, and simultaneously further improves the accuracy of the algorithm through the texture characteristics of the image, thereby improving the accuracy of the algorithm to the maximum extent.
4. The automatic image fitting and positioning system comprises an automatic image fitting and positioning system, and can position and display the disease picture at the corresponding position of the three-dimensional model, so that workers can conveniently confirm the disease position and take corresponding measures.
Drawings
FIG. 1 is a schematic structural view of the present invention;
fig. 2 is a schematic structural diagram of the CNN model of the present invention.
Detailed Description
The following detailed description of the present invention is provided in conjunction with the accompanying drawings, but it should be understood that the scope of the present invention is not limited to the specific embodiments.
Throughout the specification and claims, unless explicitly stated otherwise, the word "comprise", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated element or component but not the exclusion of any other element or component.
As shown in FIGS. 1-2, a system for checking the hidden danger of the artificial intelligence on the construction project site comprises
The unmanned aerial vehicle aerial photographing device can move back and forth on a highway engineering construction site and is used for acquiring pictures of the highway engineering construction site;
the cloud computing platform is used for receiving image information transmitted by the unmanned aerial vehicle aerial photographing device, a set of image processing system is integrated in the cloud computing platform, and the image processing system processes the photo of the unmanned aerial vehicle and establishes a three-dimensional model; a CNN model is loaded in the cloud computing platform, and the CNN model performs comparative analysis on the image information and classifies diseases existing in the image; an image automatic fitting and positioning system is loaded in the cloud computing platform, and the image automatic fitting and positioning system is used for positioning and displaying the identified disease picture at a position corresponding to the three-dimensional model;
and the control center is used for receiving the state information of the unmanned aerial vehicle aerial photographing device and judging whether the running state of the unmanned aerial vehicle aerial photographing device is normal or not, and the control center performs data interaction with the cloud computing platform through a wireless network and sends alarm information to an attendant.
Furthermore, the photo shot by the unmanned aerial vehicle is provided with a geographical position coordinate, and the position of the problem on the engineering site can be displayed by combining the three-dimensional model.
Further, the diseases comprise site surface water accumulation, pot holes and side slope landslides.
Further, the method is characterized by comprising the following steps:
s1, setting a line setting area and parameters according to the construction route map, acquiring images by the unmanned aerial vehicle along the construction route map and uploading the images to a cloud computing platform, and processing the images of the unmanned aerial vehicle by the image processing system;
s2, establishing a three-dimensional map model, wherein the three-dimensional map model displays geographic position coordinates and mileage stake marks;
s3, establishing a parallel number CNN model;
s4, analyzing the photos by the CNN models with good numbers, screening and outputting hidden danger photos, classifying diseases in the photos, and positioning and displaying the recognized pictures of the diseases at the corresponding positions of the three-dimensional models.
Further, the CNN model includes:
the convolution unit is used for performing convolution summation on the characteristic mapping graph of the input number by adopting a convolution kernel, and consists of 10 convolution layers, wherein the 10 convolution layers have different weights and thresholds;
the pooling unit is used for downsampling the feature mapping image after convolution, reducing the resolution of the feature mapping image and selecting excellent features;
and the classification unit classifies the output number of the feature mapping graph output by the convolution unit to a softmax loss function through a full connection layer and provides a classification result.
Further, in step S3, the method for counting the CNN models includes:
s2.1, establishing a deep learning model;
s2.2, collecting a large number of road disease pictures, performing data set amplification on the collected pictures, and dividing the amplified road disease data into a plurality of samples and target samples;
s2.3, giving a number sample, and giving an initial weight and a threshold value of the target sample;
s2.4, outputting the type of the disease;
s2.5, outputting an error: the difference between the target disease type and the output disease type;
s2.6, error evaluation is carried out, and if the error is smaller than a preset value, counting is finished; if the error deviation is larger than the preset value, the error deviation is calculated, the weight value and the threshold value are adjusted, and then the step S2.4 is carried out.
In step S4, the specific implementation method is as follows:
s4.1, comparing the pictures acquired by the unmanned aerial vehicle with the pictures in the data set one by one;
s4.2, carrying out graying processing on the two image images to be compared to obtain a grayscale image of the image; creating a one-dimensional gray histogram, and enabling the statistical image to be distributed in [0, 255] pixels; calculating a one-dimensional histogram of the gray level image; normalizing the calculated one-dimensional histogram; creating a graph for displaying a histogram of each pixel, wherein the abscissa is a gray level and the ordinate is the number of pixels; drawing each histogram into the created graph; measuring the Babbitt distance of the histograms of the two images to calculate the similarity of the images, namely calculating the similarity of the images based on the gray-scale color histogram;
s4.3, extracting image texture features by adopting a gray level co-occurrence matrix, and then calculating the similarity of the images;
s4.4, calculating the final image similarity by adopting weighted average according to the image similarity calculated in the previous two steps;
s4.5, when the final image similarity is larger than a preset value, determining that the picture acquired by the unmanned aerial vehicle corresponds to the disease type of the picture in the data set;
and S4.6, the image automatic fitting and positioning system positions and displays the recognized disease picture at the corresponding position of the three-dimensional model.
According to the invention, the unmanned aerial vehicle is adopted for routing inspection, the unmanned aerial vehicle aerial photography improves the efficiency of highway engineering management safety quality inspection compared with manual inspection, the unmanned aerial vehicle aerial photography can realize overall evaluation of projects, identifies the overall progress, has a wider aerial photography range, and can find the engineering safety quality problem which is difficult to find manually.
The above description is directed to the preferred embodiments of the present invention, but the embodiments are not intended to limit the scope of the claims of the present invention, and all equivalent changes and modifications made within the technical spirit of the present invention should fall within the scope of the claims of the present invention.
Claims (7)
1. A system for checking artificial intelligence hidden dangers on construction project site is characterized by comprising
The unmanned aerial vehicle aerial photographing device can move back and forth on a highway engineering construction site and is used for acquiring pictures of the highway engineering construction site;
the cloud computing platform is used for receiving image information transmitted by the unmanned aerial vehicle aerial photographing device, a set of image processing system is integrated in the cloud computing platform, and the image processing system processes the photo of the unmanned aerial vehicle and establishes a three-dimensional model; a CNN model is loaded in the cloud computing platform, and the CNN model performs comparative analysis on the image information and classifies diseases existing in the image; an image automatic fitting and positioning system is loaded in the cloud computing platform, and the image automatic fitting and positioning system is used for positioning and displaying the identified disease picture at a position corresponding to the three-dimensional model;
and the control center is used for receiving the state information of the unmanned aerial vehicle aerial photographing device and judging whether the running state of the unmanned aerial vehicle aerial photographing device is normal or not, and the control center performs data interaction with the cloud computing platform through a wireless network and sends alarm information to an attendant.
2. The system for troubleshooting manual intelligence potential safety hazards in construction project sites of claim 1 wherein the photo taken by the drone is provided with geographical location coordinates and in combination with a three dimensional model can show where the problem occurred on the project site.
3. The system for troubleshooting construction project site artificial intelligence potential hazards of claim 1 wherein said diseases include site surface water, pot holes and side slope landslides.
4. The troubleshooting method for the construction project site artificial intelligence hidden danger troubleshooting system of claim 1, comprising the steps of:
s1, setting a line setting area and parameters according to the construction route map, acquiring images by the unmanned aerial vehicle along the construction route map and uploading the images to a cloud computing platform, and processing the images of the unmanned aerial vehicle by the image processing system;
s2, establishing a three-dimensional map model, wherein the three-dimensional map model displays geographic position coordinates and mileage stake marks;
s3, establishing a parallel number CNN model;
s4, analyzing the photos by the CNN models with good numbers, screening and outputting hidden danger photos, classifying diseases in the photos, and positioning and displaying the recognized pictures of the diseases at the corresponding positions of the three-dimensional models.
5. The troubleshooting method for the construction project site artificial intelligence hidden danger troubleshooting system of claim 4 wherein said CNN model comprises:
the convolution unit is used for performing convolution summation on the characteristic mapping graph of the input number by adopting a convolution kernel, and consists of 10 convolution layers, wherein the 10 convolution layers have different weights and thresholds;
the pooling unit is used for downsampling the convolved feature mapping image, reducing the resolution of the feature mapping image and selecting excellent features;
and the classification unit classifies the output number of the feature mapping graph output by the convolution unit to a softmax loss function through a full connection layer and provides a classification result.
6. The investigation method for the system for investigating artificial intelligence hidden dangers in a construction project site as claimed in claim 4, wherein in the step S3, the method for counting the number of CNN models comprises:
s2.1, establishing a deep learning model;
s2.2, collecting a large number of road disease pictures, performing data set amplification on the collected pictures, and dividing the amplified road disease data into a plurality of samples and target samples;
s2.3, giving a number sample, and giving an initial weight and a threshold value of the target sample;
s2.4, outputting the type of the disease;
s2.5, outputting an error: the difference between the target disease type and the output disease type;
s2.6, error evaluation is carried out, and if the error is smaller than a preset value, counting is finished; if the error deviation is larger than the preset value, the error deviation is calculated, the weight value and the threshold value are adjusted, and then the step S2.4 is carried out.
7. The troubleshooting method for the artificial intelligence hidden danger troubleshooting system on the construction project site recited in claim 4, wherein in said step S4,
s4.1, comparing the pictures acquired by the unmanned aerial vehicle with the pictures in the data set one by one;
s4.2, carrying out graying processing on the two image images to be compared to obtain a grayscale image of the image; creating a one-dimensional gray histogram, and enabling the statistical image to be distributed in [0, 255] pixels; calculating a one-dimensional histogram of the gray level image; normalizing the calculated one-dimensional histogram; creating a graph for displaying a histogram of each pixel, wherein the abscissa is a gray level and the ordinate is the number of pixels; drawing each histogram into the created graph; measuring the Babbitt distance of the histograms of the two images to calculate the similarity of the images, namely calculating the similarity of the images based on the gray-scale color histogram;
s4.3, extracting image texture features by adopting a gray level co-occurrence matrix, and then calculating the similarity of the images;
s4.4, calculating the final image similarity by adopting weighted average according to the image similarity calculated in the previous two steps;
s4.5, when the final image similarity is larger than a preset value, determining that the picture acquired by the unmanned aerial vehicle corresponds to the disease type of the picture in the data set;
and S4.6, the image automatic fitting and positioning system positions and displays the recognized disease picture at the corresponding position of the three-dimensional model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111535313.3A CN114494845A (en) | 2021-12-15 | 2021-12-15 | Artificial intelligence hidden danger troubleshooting system and method for construction project site |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111535313.3A CN114494845A (en) | 2021-12-15 | 2021-12-15 | Artificial intelligence hidden danger troubleshooting system and method for construction project site |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114494845A true CN114494845A (en) | 2022-05-13 |
Family
ID=81494060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111535313.3A Pending CN114494845A (en) | 2021-12-15 | 2021-12-15 | Artificial intelligence hidden danger troubleshooting system and method for construction project site |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114494845A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115375864A (en) * | 2022-08-26 | 2022-11-22 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | Unmanned aerial vehicle-based completion acceptance method for high-speed railway |
| CN117634987A (en) * | 2024-01-25 | 2024-03-01 | 中建安装集团有限公司 | Building high slope construction evaluation management system and method based on Internet of things |
-
2021
- 2021-12-15 CN CN202111535313.3A patent/CN114494845A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115375864A (en) * | 2022-08-26 | 2022-11-22 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | Unmanned aerial vehicle-based completion acceptance method for high-speed railway |
| CN115375864B (en) * | 2022-08-26 | 2023-03-10 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | Unmanned aerial vehicle-based high-speed railway completion acceptance method |
| CN117634987A (en) * | 2024-01-25 | 2024-03-01 | 中建安装集团有限公司 | Building high slope construction evaluation management system and method based on Internet of things |
| CN117634987B (en) * | 2024-01-25 | 2024-04-02 | 中建安装集团有限公司 | Building high slope construction evaluation management system and method based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Akagic et al. | Pothole detection: An efficient vision based method using rgb color space image segmentation | |
| CN109448326B (en) | Geological disaster intelligent group defense monitoring system based on rapid image recognition | |
| CN110147714B (en) | Unmanned aerial vehicle-based coal mine goaf crack identification method and detection system | |
| CN109935080B (en) | Monitoring system and method for real-time calculation of traffic flow on traffic line | |
| CN114494845A (en) | Artificial intelligence hidden danger troubleshooting system and method for construction project site | |
| CN110781853B (en) | Crowd abnormality detection method and related device | |
| CN112330593A (en) | Building surface crack detection method based on deep learning network | |
| CN107798293A (en) | A kind of crack on road detection means | |
| CN111896549A (en) | Building crack monitoring system and method based on machine learning | |
| CN113221682A (en) | Bridge vehicle load space-time distribution fine-grained identification method based on computer vision | |
| CN115993096A (en) | High-rise building deformation measuring method | |
| CN114972177A (en) | Road disease identification management method and device and intelligent terminal | |
| CN114662208B (en) | Construction visualization system and method based on Bim technology | |
| CN113313006A (en) | Urban illegal construction supervision method and system based on unmanned aerial vehicle and storage medium | |
| CN113781537A (en) | Track elastic strip fastener defect identification method and device and computer equipment | |
| CN116129135A (en) | Tower crane safety early warning method based on small target visual identification and virtual entity mapping | |
| CN115311623A (en) | Equipment oil leakage detection method and system based on infrared thermal imaging | |
| KR102185225B1 (en) | Method for detecting sinkhole using deep learning and data association and sinkhole detecting system using it | |
| Kong et al. | Detecting type and size of road crack with the smartphone | |
| CN110765900B (en) | Automatic detection illegal building method and system based on DSSD | |
| CN112017213A (en) | Target object position updating method and system | |
| Li et al. | Road Damage Evaluation via Stereo Camera and Deep Learning Neural Network | |
| CN113033443B (en) | Unmanned aerial vehicle-based automatic pedestrian crossing facility whole road network checking method | |
| CN114998251A (en) | Air multi-vision platform ground anomaly detection method based on federal learning | |
| CN113963230A (en) | Parking space detection method based on deep learning |
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 |