CN114170591A - Intelligent parking solution method and system based on Saas mode - Google Patents
Intelligent parking solution method and system based on Saas mode Download PDFInfo
- Publication number
- CN114170591A CN114170591A CN202111365554.8A CN202111365554A CN114170591A CN 114170591 A CN114170591 A CN 114170591A CN 202111365554 A CN202111365554 A CN 202111365554A CN 114170591 A CN114170591 A CN 114170591A
- Authority
- CN
- China
- Prior art keywords
- image
- vehicle
- information
- license plate
- neural network
- 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
- 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
Abstract
The invention discloses an intelligent parking solution method and system based on a Saas mode, wherein the method comprises the following steps: acquiring an image of a front body of the vehicle through a camera for primary processing; inputting the image after primary processing into a multi-information detection BP neural network model, and outputting detection information; inputting the image into a preset convolutional neural network to perform vehicle precursor target identification, and identifying the color of a preset position in the regional image according to the regional image of the target identification frame; preprocessing the area image, and extracting a maximum outline image of the vehicle front body target image; and respectively comparing the detected vehicle license plate information and the vehicle sign image, the identified color and the extracted maximum outline image with the pre-stored corresponding information, and controlling the rod lifting and releasing of the barrier machine when the detected vehicle license plate information and the vehicle sign image are completely consistent. The method provides a complete set of software and hardware services for users based on the Saas mode, and the method can be used without the participation of users in software and hardware maintenance and installation; the manual management cost is reduced, and the vehicle identity is accurately identified.
Description
Technical Field
The invention relates to the technical field of intelligent parking, in particular to an intelligent parking solution method and system based on a Saas mode.
Background
Along with the rapid increase of the quantity of retained automobiles of residents, the intelligent parking is born, which means that the wireless communication technology, the mobile terminal technology, the GPS positioning technology, the GIS technology and the like are comprehensively applied to the acquisition, management, inquiry, reservation and navigation services of urban parking spaces, the integration of real-time updating, inquiry, reservation and navigation services of parking space resources is realized, and the maximization of the utilization rate of the parking space resources, the maximization of the profit of a parking lot and the optimization of the parking service of car owners are realized.
The intelligent parking usually depends on a software technology, at present, the garage enters and exits basically depending on license plate recognition, the rod can be lifted for releasing as long as the license plate is correct, and even whether the garage enters or exits repeatedly is not detected; causing many drivers to drill empty, such as fake plate in and out; or the license plate is manually lifted, and the lifting rod can be released, so that a unlicensed vehicle or other unknown vehicles can drive in. Therefore, a great challenge is brought to property management work, other traffic safety hidden dangers are easily caused, and authority cannot be divided.
In the related art, SaaS is Software-as-a-service (Software as a service). The SaaS provider builds all network infrastructures, software and hardware operation platforms required by informatization for enterprises and is responsible for a series of services such as implementation in the early stage, maintenance in the later stage and the like, and the enterprises can use the information system through the Internet without purchasing software and hardware, building a machine room and recruiting IT personnel. Just like opening a tap water to use water, enterprises rent software services to SaaS providers according to actual needs.
Therefore, how to solve the problem of the bugs existing in the license plate recognition based on the SaaS mode becomes a problem to be solved urgently by practitioners of the same department.
Disclosure of Invention
In view of the above, the present invention provides an intelligent parking solution method and system based on Saas mode, which can solve the management problem occurring in the current parking management when entering and exiting; software service can be provided based on the Saas mode, and the software and hardware can be purchased and used without the participation of a user in maintenance and protection of the software and the hardware; the manual management cost is reduced, the vehicle identity is accurately identified based on the multi-source information, and management disputes caused by illegal vehicles passing are avoided.
In a first aspect, an embodiment of the present invention provides an intelligent parking solution based on Saas mode, including:
s10, acquiring an image of the front body of the vehicle through a camera;
s20, processing the image for one time;
s30, inputting the once processed image into a multi-information detection BP neural network model, and outputting detection information; the multi-information detection BP neural network model is used for detecting and identifying: license plate information of the vehicle and a logo image of the vehicle;
s40, inputting the image into a preset convolutional neural network for vehicle precursor target recognition, and recognizing the color of a preset position in the area image according to the area image of the target recognition frame;
s50, preprocessing the area image of the step S40, and extracting a maximum outline drawing of the vehicle forebody target image;
and S60, respectively comparing the license plate information and the sign image of the vehicle detected in the step S30, the color identified in the step S40 and the maximum outline image extracted in the step S50 with the pre-stored corresponding information, and controlling the rod raising of the railing machine to be released when the comparison results are completely consistent.
In one embodiment, further comprising:
s70, when the comparison result is inconsistent, displaying the corresponding error information through a display screen or broadcasting the error information through an external loudspeaker.
In one embodiment, the step of S20 includes: and sequentially carrying out Gaussian smoothing, median filtering, graying and binarization processing on the image.
In one embodiment, the multi-information detection BP neural network model is obtained by training a BP neural network model through multiple sets of training data; each set of data of the plurality of sets of training data includes a plurality of license plate types and/or logo images of the vehicle with the label information.
In one embodiment, the step of S40 includes:
s401, inputting the image into a trained R-CNN, FAST-RCNN or FASTER-RCNN network to identify a vehicle precursor object;
s402, obtaining a height value and a width value of the vehicle front body target according to the identified vehicle front body target;
and S403, collecting pixel point color values in the area according to the height value and the width value of the vehicle front body target and the preset proportion of the front engine hood area as the vehicle color.
In one embodiment, the step of S50 includes:
and (5) carrying out binarization processing on the region image of S40, and obtaining the maximum outline image of the vehicle precursor target image by adopting Canny edge detection or Sobel operator edge detection.
In one embodiment, the step S60, comparing the maximum outline drawing with the corresponding information stored in advance, includes:
after the license plate information is compared correctly, a hu moment matching function provided by OPENCV is adopted, the input maximum outline graph is compared with the outline graph corresponding to the pre-stored license plate information, and the hu moment similarity between the two outline graphs is returned;
and when the similarity reaches a threshold value, the comparison of the contour maps is correct.
In a second aspect, an embodiment of the present invention further provides an intelligent parking solution system based on the Saas model, including:
the acquisition module is used for acquiring an image of the front body of the vehicle through the camera;
the processing module is used for processing the image for one time;
the detection module is used for inputting the once processed image into a multi-information detection BP neural network model and outputting detection information; the multi-information detection BP neural network model is used for detecting and identifying: license plate information of the vehicle and a logo image of the vehicle;
the identification module is used for inputting the image into a preset convolutional neural network to identify a vehicle precursor target, and identifying the color of a preset position in the area image according to the area image of the target identification frame;
the extraction module is used for preprocessing the area image and extracting a maximum outline image of the vehicle precursor target image;
and the comparison module is used for comparing the detected license plate information of the vehicle, the mark image of the vehicle, the color identified by the identification module and the maximum outline image extracted by the extraction module with the prestored corresponding information respectively, and controlling the rod lifting and releasing of the barrier machine when the comparison results are completely consistent.
Compared with the prior art, the intelligent parking solution based on the Saas mode provided by the embodiment of the invention has the advantages that the image of the front body of the vehicle is acquired through the camera; processing the image for one time; inputting the image after primary processing into a multi-information detection BP neural network model, and outputting detection information; the multi-information detection BP neural network model is used for detecting and identifying: license plate information of the vehicle and a logo image of the vehicle; inputting the image into a preset convolutional neural network to perform vehicle precursor target identification, and identifying the color of a preset position in the area image according to the area image of the target identification frame; preprocessing the area image, and extracting a maximum outline image of the vehicle precursor target image; and respectively comparing the detected license plate information of the vehicle, the mark image of the vehicle, the identified color and the extracted maximum outline image with the pre-stored corresponding information, and controlling the rod lifting of the barrier machine to be released when the comparison results are completely consistent. The method can provide a complete set of software and hardware services for a user based on the Saas mode, and can solve the management problem in the current parking process when entering and exiting are managed based on a cloud platform constructed by Internet big data; the software and hardware maintenance is not needed, and the software and hardware can be used after being purchased; the manual management cost is reduced, the vehicle identity is accurately identified based on the multi-source information, and management disputes caused by illegal vehicles passing are avoided.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart of an intelligent parking solution based on Saas mode according to an embodiment of the present invention;
fig. 2 is a structural diagram of an intelligent parking solution system based on the Saas model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a vehicle precursor object segmentation provided by an embodiment of the present invention;
fig. 4 is a matching graph of the license plate information corresponding to all pre-stored information provided by the embodiment of the present invention;
fig. 5 is a block diagram of an intelligent parking solution system based on the Saas model according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to fig. 1, an embodiment of the present invention provides an intelligent parking solution based on Saas mode,
s10, acquiring an image of a front body of the vehicle through a camera;
s20, processing the image for one time;
s30, inputting the once processed image into a multi-information detection BP neural network model, and outputting detection information; the multi-information detection BP neural network model is used for detecting and identifying: license plate information of the vehicle and a logo image of the vehicle;
s40, inputting the image into a preset convolutional neural network for vehicle precursor target recognition, and recognizing the color of a preset position in the area image according to the area image of the target recognition frame;
s50, preprocessing the area image of the step S40, and extracting a maximum outline drawing of the vehicle forebody target image;
and S60, respectively comparing the license plate information and the sign image of the vehicle detected in the step S30, the color identified in the step S40 and the maximum outline image extracted in the step S50 with the pre-stored corresponding information, and controlling the rod raising of the railing machine to be released when the comparison results are completely consistent.
In a particular arrangement, as shown with reference to fig. 2, comprising: parking area management equipment and cloud platform, parking area management equipment includes: hardware such as barrier machines, cameras, field computers, and the like; based on the Saas mode, the cloud platform can provide intelligent parking service for a plurality of parking lots at the same time.
In this embodiment, gather the image of vehicle predecessor through acquireing the camera, can realize the four kinds of information discernment to the vehicle based on this image, include: license plate information, logo images, body colors and a vehicle front body contour map. The same vehicle is characterized based on the four information, the four information of the vehicle is pre-recorded based on the management requirement before the method is used, wherein the mark images directly adopt more than 400 types existing on the market, and can be updated in time at a remote server end according to the new vehicle marketing and replacement of the vehicle. When the computer is recorded in the field, only corresponding selection is needed. The vehicle front body outline drawing can be shot by a vehicle owner, the outline drawing is extracted by the cloud server and then is downloaded to the on-site computer.
The license plate information and the vehicle mark image can be obtained through a BP neural network model, the vehicle body color is obtained based on a convolutional neural network, the maximum outline image is further extracted, then the maximum outline image is compared with the corresponding information stored by a field computer, and the vehicle can be released after the comparison is completely correct. The method provides a complete set of software and hardware services for users based on the Saas mode, and the method can be used without the participation of users in software and hardware maintenance and installation; the manual management cost is reduced, and the vehicle identity is accurately identified. Can accomplish unmanned on duty, realize wisdom parking.
In one embodiment, the method further comprises: s70, when any information of the comparison result is wrong, displaying wrong information through a field display screen, wherein the wrong information comprises the following information: when the color of the vehicle body is wrong, displaying that the color of the vehicle body is wrong in comparison, and having no right of pass; error messages can also be broadcast through an external loudspeaker. At this time, the owner of the vehicle can leave the system autonomously, or the manager is contacted to explain the reason, and the manual control of the rod lifting process is requested.
The comparison of the four kinds of information can completely prevent the entering of a fake mode, and provides safer guarantee for normal management.
The process identified in each of the above steps is described in detail below:
in one embodiment, the vehicle image is detected, and the license plate information and the mark image of the vehicle can be obtained by identifying based on a multi-information detection BP neural network model. Wherein, the vehicle forebody image that gathers to the camera before discernment carries out following processing in proper order:
gaussian smoothing, median filtering, graying and binarization processing. The noise of the target image is suppressed under the condition of keeping the detail characteristics of the image as much as possible, and the effectiveness and reliability of subsequent image processing and analysis are directly influenced by the quality of the processing effect of each step.
The multi-information detection BP neural network model is formed by adopting BP neural network multitask learning training, training data of the model comprise various license plate information with label information and/or mark images of vehicles, and the training process can be realized by adopting the prior art: the method comprises the following steps:
(1) acquiring a large number of training images; the training image comprises images of various license plate information and mark images of various vehicles, wherein each license plate is marked with license plate information, such as 'Jing A00000'; label image label information: the "popular", "BMW", "Jeep", etc.
(2) Extracting color features and texture features of the labeling frame;
(3) inputting the extracted color features and texture features into a BP neural network model, and training by using a Tensorflow2.3 deep learning framework;
(4) and judging whether the trained model meets preset conditions or not, and testing the verification set data, wherein the accuracy rate is more than 98%, and when the model tends to be convergent or over-fitting, the trained model is determined to be a multi-information detection BP neural network model.
In the embodiment, the license plate information of the vehicle and the mark image of the vehicle can be detected through the multi-information detection BP neural network model, at the moment, the license plate information and the mark image of the vehicle can be directly compared, and when the license plate information and the mark image are not consistent with the stored information, a warning is prompted to be sent; if the two items are correctly compared, the extraction and comparison of the vehicle color and the outline drawing can be carried out.
In one embodiment, inputting the image of step S10 into a trained convolutional neural network for vehicle precursor target recognition, and recognizing the color of a preset position in the area image according to the area image of the target recognition frame includes:
s401, inputting the image into a trained R-CNN, FAST-RCNN or FASTER-RCNN network to identify a vehicle precursor object;
s402, obtaining a height value and a width value of the vehicle front body target according to the identified vehicle front body target;
and S403, collecting pixel point color values in the area according to the height value and the width value of the vehicle front body target and the preset proportion of the front engine hood area as the vehicle color.
The target region may be determined using R-CNN, FAST-RCNN, or FASTER-RCNN for vehicle precursor target identification. The training process can be as follows.
Further, referring to fig. 3, after the vehicle front body target is obtained, the height value and the width value of the vehicle front body target are obtained, the area is divided, two fifths of the height value is selected as a first dividing point from bottom to top, two fifths of the height value is selected as a second dividing point from top to bottom, and the distance between the two dividing points is used as the height value of the front engine cover.
Then, according to the height value of the front engine cover and the width value of the vehicle body, an area image of the front engine cover can be obtained, and any collection point in the area can be used as the color of the vehicle body. In practical application, a common car body is only one color and can be treated according to the color. And when the color of the current engine hood is inconsistent with the color of the vehicle body, the color of the engine hood before recording is accurate when the system records.
The identification process comprises the following steps: the GRB of the area image of the front engine cover can be converted into YUV and HSV color spaces, and channel values of all pixel points of the area image corresponding to all channels in the color spaces are obtained, wherein a calculation formula for converting the RGB color space into the YUV color space is as follows:
Y＝0.299R+0.587G+0.114B
U＝-0.147R-0.289G+0.436B
V＝0.615R-0.515G-0.100B
the calculation formula for converting the RGB color space into the HSV color space is as follows:
let max be equal to the maximum of r, g, and b, and min be the minimum. The (h, s, v) value in the corresponding HSV space is:
v＝max。
fusing nine channels of RGB, YUV and HSV color spaces of the area image to form new area image data; as input for color feature calculation; and finally, identifying the vehicle color based on the trained R-CNN, FAST-RCNN or FASTER-RCNN network.
Further, in order to obtain the maximum outline drawing of the vehicle precursor target image, after the R-CNN, FAST-RCNN or FASTER-RCNN network obtains a target detection frame, binarization processing is carried out, and then Canny edge detection or Sobel operator edge detection is adopted to obtain the maximum outline drawing of the vehicle precursor target image.
In one embodiment, in step S60, the four data obtained in the above steps are respectively compared with the corresponding information in advance. In the comparison process: for example, the license plate information is used as a main identifier, and specifically includes:
firstly, comparing the recognized license plate information with the pre-stored license plate information, and acquiring corresponding associated information after the comparison is successful, as shown in fig. 4.
And then comparing the identified mark image with a pre-stored mark image, continuously comparing the color of the vehicle body with the contour map of the front body of the vehicle after the comparison is successful, and lifting the rod to release the vehicle after the four items of information are compared correctly in sequence. In the comparison sequence, when any comparison is incorrect, subsequent comparison is not needed, and a warning can be directly sent out.
For example, after the license plate information is compared correctly, a hu moment matching function provided by OPENCV is adopted, the maximum outline graph is input and compared with the outline graph corresponding to the pre-stored license plate information, and the hu moment similarity between the two outline graphs is returned; when the similarity reaches a threshold value, the contour map is considered to be correctly compared. The threshold may be adjusted according to actual conditions, for example, to 70%.
The intelligent parking solution is provided based on the SaaS mode, and is completely based on software and hardware provided by a SaaS provider, so that the intelligent parking solution can be used after being installed without a user participating in maintenance of the software and the hardware; the manual management cost is reduced, the vehicle identity is accurately identified based on the multi-source information, and management disputes caused by illegal vehicles passing are avoided.
Based on the same inventive concept, the embodiment of the invention also provides an intelligent parking solution system based on the Saas mode, and as the principle of the problem solved by the system is similar to that of the intelligent parking solution based on the Saas mode, the implementation of the system can refer to the implementation of the method, and repeated details are not repeated.
An embodiment of the present invention further provides an intelligent parking solution system based on the Saas mode, which is shown in fig. 5 and includes:
the acquisition module is used for acquiring an image of the front body of the vehicle through the camera;
the processing module is used for processing the image for one time;
the detection module is used for inputting the once processed image into a multi-information detection BP neural network model and outputting detection information; the multi-information detection BP neural network model is used for detecting and identifying: license plate information of the vehicle and a logo image of the vehicle;
the identification module is used for inputting the image into a preset convolutional neural network to identify a vehicle precursor target, and identifying the color of a preset position in the area image according to the area image of the target identification frame;
the extraction module is used for preprocessing the area image and extracting a maximum outline image of the vehicle precursor target image;
and the comparison module is used for comparing the detected license plate information of the vehicle, the mark image of the vehicle, the color identified by the identification module and the maximum outline image extracted by the extraction module with the prestored corresponding information respectively, and controlling the rod lifting and releasing of the barrier machine when the comparison results are completely consistent.
After the four kinds of information related to the appointed vehicle, such as license plate information, logo image, vehicle body color and vehicle front body outline are input into the system, the system can automatically recognize the four kinds of information passing through the vehicle and inquire an internal database. When the comparison is completely consistent, the electronic door or the barrier machine needs to be released, the on-site computer sends out an instruction to drive the electronic door or the barrier machine to pass through, and when the comparison is wrong, a warning is given out and is processed by an attendant.
The license plate recognition equipment is arranged at an entrance and an exit, records the license plate number and the entrance and exit time of the vehicle, and is combined with the control equipment of an automatic door and a barrier machine to realize the automatic management of the vehicle. The intelligent parking system is applied to a parking lot, can realize intelligent parking, such as automatic timing charging, can also automatically calculate the number of available parking spaces and give a prompt, and realizes automatic management of parking charging, thereby saving labor and improving efficiency. Even can also be applied to intelligent district and can judge automatically whether the vehicle that drives into belongs to this district, realize the automatic timing charge to non-interior vehicle.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and are not limited. Although the present invention has been described in detail with reference to the embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (8)
1. An intelligent parking solution based on Saas mode is characterized by comprising the following steps:
s10, acquiring an image of the front body of the vehicle through a camera;
s20, processing the image for one time;
s30, inputting the once processed image into a multi-information detection BP neural network model, and outputting detection information; the multi-information detection BP neural network model is used for detecting and identifying: license plate information of the vehicle and a logo image of the vehicle;
s40, inputting the image into a preset convolutional neural network for vehicle precursor target recognition, and recognizing the color of a preset position in the area image according to the area image of the target recognition frame;
s50, preprocessing the area image of the step S40, and extracting a maximum outline drawing of the vehicle forebody target image;
and S60, respectively comparing the license plate information and the sign image of the vehicle detected in the step S30, the color identified in the step S40 and the maximum outline image extracted in the step S50 with the pre-stored corresponding information, and controlling the rod raising of the railing machine to be released when the comparison results are completely consistent.
2. The method as claimed in claim 1, further comprising:
s70, when the comparison result is inconsistent, displaying the corresponding error information through a display screen or broadcasting the error information through an external loudspeaker.
3. The method as claimed in claim 2, wherein the S20 step includes: and sequentially carrying out Gaussian smoothing, median filtering, graying and binarization processing on the image.
4. The intelligent parking solution based on the Saas model according to claim 3, wherein the multi-information detection BP neural network model is obtained by training the BP neural network model through a plurality of sets of training data; each set of data of the plurality of sets of training data includes a plurality of license plate types and/or logo images of the vehicle with the label information.
5. The method as claimed in claim 4, wherein the step of S40 includes:
s401, inputting the image into a trained R-CNN, FAST-RCNN or FASTER-RCNN network to identify a vehicle precursor object;
s402, obtaining a height value and a width value of the vehicle front body target according to the identified vehicle front body target;
and S403, collecting pixel point color values in the area according to the height value and the width value of the vehicle front body target and the preset proportion of the front engine hood area as the vehicle color.
6. The method as claimed in claim 4, wherein the step S50 includes:
and (5) carrying out binarization processing on the region image of S40, and obtaining the maximum outline image of the vehicle precursor target image by adopting Canny edge detection or Sobel operator edge detection.
7. The method as claimed in claim 1, wherein the step S60 of comparing the maximum outline drawing with the corresponding information stored in advance comprises:
after the license plate information is compared correctly, a hu moment matching function provided by OPENCV is adopted, the input maximum outline graph is compared with the outline graph corresponding to the pre-stored license plate information, and the hu moment similarity between the two outline graphs is returned;
and when the similarity reaches a threshold value, the comparison of the contour maps is correct.
8. An intelligent parking solution system based on Saas mode, comprising:
the acquisition module is used for acquiring an image of the front body of the vehicle through the camera;
the processing module is used for processing the image for one time;
the detection module is used for inputting the once processed image into a multi-information detection BP neural network model and outputting detection information; the multi-information detection BP neural network model is used for detecting and identifying: license plate information of the vehicle and a logo image of the vehicle;
the identification module is used for inputting the image into a preset convolutional neural network to identify a vehicle precursor target, and identifying the color of a preset position in the area image according to the area image of the target identification frame;
the extraction module is used for preprocessing the area image and extracting a maximum outline image of the vehicle precursor target image;
and the comparison module is used for comparing the detected license plate information of the vehicle, the mark image of the vehicle, the color identified by the identification module and the maximum outline image extracted by the extraction module with the prestored corresponding information respectively, and controlling the rod lifting and releasing of the barrier machine when the comparison results are completely consistent.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111365554.8A CN114170591A (en) | 2021-11-17 | 2021-11-17 | Intelligent parking solution method and system based on Saas mode |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111365554.8A CN114170591A (en) | 2021-11-17 | 2021-11-17 | Intelligent parking solution method and system based on Saas mode |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114170591A true CN114170591A (en) | 2022-03-11 |
Family
ID=80479491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111365554.8A Pending CN114170591A (en) | 2021-11-17 | 2021-11-17 | Intelligent parking solution method and system based on Saas mode |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114170591A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117520979A (en) * | 2023-11-03 | 2024-02-06 | 长沙云软信息技术有限公司 | Wagon balance measuring equipment based on OCR (optical character recognition) and application method thereof |
-
2021
- 2021-11-17 CN CN202111365554.8A patent/CN114170591A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117520979A (en) * | 2023-11-03 | 2024-02-06 | 长沙云软信息技术有限公司 | Wagon balance measuring equipment based on OCR (optical character recognition) and application method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106373426B (en) | Parking stall based on computer vision and violation road occupation for parking monitoring method | |
| CN110009913B (en) | Intelligent checking method and system for off-site law enforcement picture of vehicle running red light | |
| EP3806064B1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| CN107909661B (en) | Parking lot control method, system and computer readable storage medium | |
| US9082038B2 (en) | Dram c adjustment of automatic license plate recognition processing based on vehicle class information | |
| CN109559395B (en) | Control method for identifying entrance charging of unlicensed vehicle and storage device | |
| CN110853391A (en) | Intelligent shared parking system | |
| CN112651293B (en) | Video detection method for road illegal spreading event | |
| CN112509325A (en) | Video deep learning-based off-site illegal automatic discrimination method | |
| CN110852236A (en) | Target event determination method and device, storage medium and electronic device | |
| CN113099181A (en) | Urban traffic parking safety intelligent analysis management method based on video monitoring | |
| CN110598550B (en) | Vehicle networking identification system based on multilayer information intelligent analysis | |
| CN114170591A (en) | Intelligent parking solution method and system based on Saas mode | |
| CN115063746A (en) | Vehicle warehousing management method and device, computer equipment and storage medium | |
| CN113486885A (en) | License plate recognition method and device, electronic equipment and storage medium | |
| CN111178359A (en) | License plate number recognition method, device and equipment and computer storage medium | |
| WO2023241595A1 (en) | Parking space range processing method and computing device | |
| CN109685920B (en) | Parking space charge management method, device, system and storage medium | |
| CN114743403B (en) | Intelligent parking system based on computer vision algorithm | |
| CN115512315A (en) | Non-motor vehicle child riding detection method, electronic device and storage medium | |
| CN204884183U (en) | Parking area bluetooth WIFI read head and cell -phone APP assist license plate recognition | |
| CN113569874A (en) | License plate number re-identification method and device, computer equipment and storage medium | |
| CN113095281A (en) | Fake-licensed vehicle identification method and device, electronic equipment and storage medium | |
| CN108520637B (en) | Intelligent parking system with parking guidance function | |
| CN112614237A (en) | Method and system for establishing association between license plate number and parking space number |
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 |