CN117237932A - Intelligent identification system and method for urban illegal tags - Google Patents
Intelligent identification system and method for urban illegal tags Download PDFInfo
- Publication number
- CN117237932A CN117237932A CN202311208441.6A CN202311208441A CN117237932A CN 117237932 A CN117237932 A CN 117237932A CN 202311208441 A CN202311208441 A CN 202311208441A CN 117237932 A CN117237932 A CN 117237932A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- signs
- illegal
- wide
- sign
- 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
- 238000000034 method Methods 0.000 title claims description 19
- 238000001514 detection method Methods 0.000 claims description 20
- 238000012216 screening Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000012015 optical character recognition Methods 0.000 description 14
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000002411 adverse Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification 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
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of illegal label identification, and discloses an intelligent identification system for urban illegal advertising labels, which comprises the following steps: the vehicle-mounted video acquisition module is used for shooting wide-angle videos containing a red line range of a road and storing the wide-angle videos in the movable storage equipment; the coordinate acquisition equipment is used for acquiring real-time recorded coordinate data while shooting wide-angle videos containing the red line range of the road and storing the real-time recorded coordinate data in the movable storage equipment; the intelligent identification module is used for carrying out intelligent identification on the shot wide-angle video and classifying the shot wide-angle video, and the identification objects comprise traffic signs, government public welfare signs and advertising signs. The application adopts the vehicle-mounted video to collect data, and utilizes the intelligent machine vision technology and the OCR technology to extract the illegal advertising placard, thereby greatly improving the recognition efficiency and the accuracy.
Description
Technical Field
The application relates to the technical field of illegal label identification, in particular to an intelligent identification system and method for urban illegal labels.
Background
Advertising signs are important municipal facilities that provide the necessary information for proper operation of the city. However, when the advertisement sign is set by a plurality of merchants, the merchants have actions such as effective registration, private establishment and the like, which cause adverse effects on urban management. At present, detection of illegal advertising signs is mainly finished manually, and the detection efficiency is low and the detection omission rate is high.
With the continuous development of artificial intelligence technology, intelligent detection has been gradually applied to urban management, and significant benefits are obtained. The Chinese patent application CN202010950038.0 discloses a detection method, a system and electronic equipment for illegally posting advertisements by combining background shape feature recognition, and proposes a method for recognizing by adopting a convolutional neural network; chinese patent application CN202011243239.3 discloses an intelligent detection method for YOLOv3 illegal billboards based on attention mechanism, which identifies illegal billboards through image feature mapping of billboards. Therefore, although intelligent recognition technology for municipal illegal advertising signs has been developed, related schemes are few, and a complete acquisition and recognition system is not proposed.
Disclosure of Invention
The application aims to provide an intelligent recognition system and method for an urban illegal label, which are used for solving the problems in the background technology.
In order to achieve the above purpose, the present application provides the following technical solutions: an intelligent recognition system for an urban illegal advertising placard, comprising:
the vehicle-mounted video acquisition module is used for shooting wide-angle videos containing a red line range of a road and storing the wide-angle videos in the movable storage equipment;
the coordinate acquisition equipment is used for acquiring real-time recorded coordinate data while shooting wide-angle videos containing the red line range of the road and storing the real-time recorded coordinate data in the movable storage equipment;
the intelligent identification module is used for carrying out intelligent identification on the shot wide-angle video and classifying the shot wide-angle video, and the identification objects comprise traffic signs, government public welfare signs and advertising signs;
the sign OCR detection module is used for extracting sign text information from the classified advertising signs, screening illegal advertising signs after comparing the sign text information with registered legal advertising signs, and reporting the legal advertising signs to law enforcement departments after recording coordinate data.
As a preferred embodiment of the present application, the vehicle-mounted video acquisition module is a high-definition vehicle-mounted pan-tilt with a wide-angle lens, and the resolution of the captured video is not lower than 2.7K and not lower than 30 frames per second; the shooting angle is inclined to the road side so as to collect more paths of side billboard information, and the precision of simultaneously recording coordinate data in the shooting process is not lower than 0.1m.
As a preferred implementation mode of the application, the intelligent recognition module is a high-performance computing device with different types of label recognition models deployed in advance, and the GPU is not lower than GeForce RTX 3090-24G.
As a preferred embodiment of the application, the mode of screening illegal advertising placards by the placard OCR detection module is as follows: and comparing the extracted information of each advertisement label with the legal label database information, and judging the advertisement label with the text matching degree lower than 60% as an illegal advertisement label.
An intelligent recognition method for an urban illegal advertisement sign adopts an intelligent recognition system for the urban illegal advertisement sign, which comprises the following steps:
the vehicle-mounted video acquisition module is arranged at the top position of the acquisition vehicle, shooting directions are adjusted to ensure acquisition of sign facilities in a road range and two side ranges, and meanwhile, coordinate acquisition equipment is started to record coordinate data in real time;
the shooting high-definition video and the coordinate data are imported into an intelligent recognition module, and the intelligent recognition module outputs recognition results of traffic signs, government public welfare signs and advertisement signs respectively and stores the recognition results in a specified folder in a screenshot mode respectively;
identifying the stored advertisement signage screenshot through an OCR text detection algorithm, extracting advertisement signage text information, respectively comparing the extracted text information of a certain advertisement signage screenshot with the pre-established legal advertisement signage text information, judging the advertisement signage with the matching degree lower than a preset value as illegal advertisement signage, and recording the screenshot, the OCR recognition result and the coordinate information.
As a preferred embodiment of the present application, the speed of the collection vehicle is between 40 and 60 km/h.
Compared with the prior art, the application provides an intelligent identification system and method for urban illegal tags, which have the following beneficial effects:
compared with the traditional manual inspection mode, the intelligent identification system and method for the urban illegal tags adopt the vehicle-mounted video to collect data, and the intelligent machine vision technology and the OCR technology are utilized to extract the illegal tags, so that the identification efficiency and the accuracy rate are greatly improved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
FIG. 1 is a schematic block diagram of an intelligent identification system for urban illegal tags according to the present application;
FIG. 2 is a schematic flow chart of an intelligent identification method of an urban illegal tag of the application;
FIG. 3 is a schematic diagram showing the detection effect of a transverse sign applied to an intelligent identification method of an urban illegal sign according to the present application;
fig. 4 is a schematic diagram of an applied vertical signage detection effect of the intelligent identification method of the urban illegal signage.
In the figure: 1. the vehicle-mounted video acquisition module; 2. a coordinate acquisition device; 3. an intelligent identification module; 4. a signage OCR detection module; 5. removable storage devices.
Detailed Description
In order to better understand the purpose, structure and function of the present application, the present application provides an intelligent identification system and method for urban illegal tags, which are described in further detail below with reference to the accompanying drawings.
As shown in fig. 1 to 4, the present application provides a technical solution: an intelligent recognition system for an urban illegal advertising placard, comprising:
the vehicle-mounted video acquisition module 1 is used for shooting wide-angle videos containing a red line range of a road and storing the wide-angle videos in the movable storage equipment 5;
the coordinate acquisition device 2 is used for acquiring real-time recorded coordinate data while shooting a wide-angle video containing a red line range of a road and storing the real-time recorded coordinate data in the movable storage device 5;
the intelligent recognition module 3 is used for intelligently recognizing and classifying the shot wide-angle video, and recognition objects comprise traffic signs, government public welfare signs and advertising signs;
the sign OCR detection module 4 is used for extracting sign text information from the classified advertisement signs, screening illegal advertisement signs after comparing with registered legal advertisement sign contents, recording coordinate data and reporting to law enforcement departments.
In this embodiment, the vehicle-mounted video acquisition module 1 is a large-area pan-tilt camera, has a better anti-shake function, avoids video blurring caused by shake in the vehicle driving process, and the coordinate acquisition device 2 is a thousand-search RTK (real time kinematic) device so as to ensure that the precision is not lower than 0.1m, the two are time-aligned before use, the subsequent video identification and coordinate data matching are performed through a time stamp, the large-area pan-tilt camera is fixed on a vehicle roof through a sucker bracket, the adjustment direction faces the range of a road to be acquired, particularly, the advertisement sign in the right-side range of the road is ensured to be clearly visible, the parameters of the large-area pan-tilt camera are adjusted to have the resolution of 2.7K and 60FPS/s, and after the pan-tilt device and the RTK device are started, the vehicle is started to drive at the speed of 40-60 km/h.
In this embodiment, the intelligent recognition module 3 is a high-performance computing device with different types of sign recognition models deployed in advance, where the GPU of the high-performance computing device is not lower than the GeForce RTX 3090-24G to ensure that the recognition efficiency thereof reaches 20FPS/s, the different types of sign recognition models are YOLO-5V, the sign data are used in advance to train them, ensure that the recognition rate of the sign reaches more than 90%, the photographed high-definition video data are recognized, traffic signs, government public and benefit signs and advertisement signs are detected and classified, and the screenshots of the recognition results are saved, so that the sign OCR detection module 4 uses an OCR text detection algorithm to recognize the advertisement screenshots and determine text information in the advertisement signs.
In this embodiment, the method for screening the illegal advertisement signage by the signage OCR detection module 4 is as follows: comparing the extracted information of each advertisement label with the information of a legal label database, judging the advertisement label with the matching degree lower than 60% as an illegal advertisement label, and recording a screenshot, an OCR (optical character recognition) result and coordinate information, wherein the information of the legal label database is obtained by acquiring characters and position information of traffic labels, government public welfare labels and legal registered advertisement labels through departments such as local area civil administration, traffic, urban management and the like in advance.
An intelligent recognition method for an urban illegal advertisement sign adopts an intelligent recognition system for the urban illegal advertisement sign, which comprises the following steps:
s1, mounting a vehicle-mounted video acquisition module 1 at the top position of an acquisition vehicle, adjusting the shooting direction to ensure acquisition of sign facilities in a road range and two side ranges, and starting coordinate acquisition equipment 2 to record coordinate data in real time;
s2, importing the shot high-definition video and the coordinate data into an intelligent recognition module 3, and respectively outputting recognition results of traffic labels, government public welfare labels and advertisement labels by the intelligent recognition module 3 and respectively storing the recognition results in a specified folder in a screenshot mode;
s3, identifying the stored advertisement signage screenshot through an OCR text detection algorithm, extracting advertisement signage text information, respectively comparing the text information extracted by a certain advertisement signage screenshot with the pre-established legal advertisement signage text information, judging the advertisement signage with the matching degree lower than a preset value as illegal advertisement signage, and recording the screenshot, the OCR recognition result and the coordinate information.
It will be understood that the application has been described in terms of several embodiments, and that various changes and equivalents may be made to these features and embodiments by those skilled in the art without departing from the spirit and scope of the application. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the application without departing from the essential scope thereof. Therefore, it is intended that the application not be limited to the particular embodiment disclosed, but that the application will include all embodiments falling within the scope of the appended claims.
Claims (6)
1. An intelligent recognition system for an urban illegal advertising placard is characterized by comprising:
the vehicle-mounted video acquisition module (1) is used for shooting wide-angle videos containing a red line range of a road and storing the wide-angle videos in the movable storage equipment (5);
the coordinate acquisition device (2) is used for acquiring real-time recorded coordinate data while shooting wide-angle videos containing the red line range of the road and storing the real-time recorded coordinate data in the movable storage device (5);
the intelligent identification module (3) is used for carrying out intelligent identification on the shot wide-angle video and classifying the shot wide-angle video, and the identification objects comprise traffic signs, government public welfare signs and advertising signs;
and the sign OCR detection module (4) is used for extracting sign text information from the classified advertisement signs, screening illegal advertisement signs after comparing the sign text information with registered legal advertisement sign contents, recording coordinate data and reporting the recorded coordinate data to law enforcement departments.
2. The intelligent recognition system of the urban illegal advertising sign according to claim 1, wherein the vehicle-mounted video acquisition module (1) is a high-definition vehicle-mounted cloud platform with a wide-angle lens, and the resolution of the shot video is not lower than 2.7K and not lower than 30 frames per second; the shooting angle is inclined to the road side so as to collect more paths of side billboard information, and the precision of simultaneously recording coordinate data in the shooting process is not lower than 0.1m.
3. The intelligent recognition system for urban illegal advertising signage according to claim 1, wherein the intelligent recognition module (3) is a high-performance computing device with pre-deployed different types of signage recognition models, and the GPU is not lower than GeForce RTX 3090-24G.
4. The intelligent recognition system for urban illegal advertising signs according to claim 1, wherein the mode of screening out illegal advertising signs by the sign OCR detection module (4) is as follows: and comparing the extracted information of each advertisement label with the legal label database information, and judging the advertisement label with the text matching degree lower than 60% as an illegal advertisement label.
5. An intelligent recognition method for an urban illegal advertisement sign, which adopts the intelligent recognition system for the urban illegal advertisement sign according to any one of claims 1-4, and is characterized by comprising the following steps:
the vehicle-mounted video acquisition module (1) is arranged at the top position of an acquisition vehicle, shooting directions are adjusted to ensure acquisition of sign facilities in a road range and two side ranges, and meanwhile, the coordinate acquisition equipment (2) is started to record coordinate data in real time;
the shooting high-definition video and the coordinate data are imported into an intelligent recognition module (3), and the intelligent recognition module (3) respectively outputs recognition results of traffic signs, government public welfare signs and advertisement signs and respectively stores the recognition results in a specified folder in a screenshot mode;
identifying the stored advertisement signage screenshot through an OCR text detection algorithm, extracting advertisement signage text information, respectively comparing the extracted text information of a certain advertisement signage screenshot with the pre-established legal advertisement signage text information, judging the advertisement signage with the matching degree lower than a preset value as illegal advertisement signage, and recording the screenshot, the OCR recognition result and the coordinate information.
6. The intelligent recognition method for the urban illegal advertising placard according to claim 5, wherein the speed of the collected vehicles is between 40 km/h and 60 km/h.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311208441.6A CN117237932A (en) | 2023-09-19 | 2023-09-19 | Intelligent identification system and method for urban illegal tags |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311208441.6A CN117237932A (en) | 2023-09-19 | 2023-09-19 | Intelligent identification system and method for urban illegal tags |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117237932A true CN117237932A (en) | 2023-12-15 |
Family
ID=89085703
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311208441.6A Pending CN117237932A (en) | 2023-09-19 | 2023-09-19 | Intelligent identification system and method for urban illegal tags |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117237932A (en) |
-
2023
- 2023-09-19 CN CN202311208441.6A patent/CN117237932A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109637151B (en) | Method for identifying illegal driving of emergency lane on highway | |
| CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
| Patel et al. | License plate detection using Harris corner and character segmentation by integrated approach from an image | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| US7171046B2 (en) | Method and apparatus for portably recognizing text in an image sequence of scene imagery | |
| Saha et al. | License Plate localization from vehicle images: An edge based multi-stage approach | |
| US20180158327A1 (en) | Method for generating a digital record and roadside unit of a road toll system implementing the method | |
| CN106919939B (en) | A kind of traffic signboard tracks and identifies method and system | |
| CN113505638B (en) | Method and device for monitoring traffic flow and computer readable storage medium | |
| CN106934374A (en) | The recognition methods of traffic signboard and system in a kind of haze scene | |
| CN113903008A (en) | Ramp exit vehicle violation identification method based on deep learning and trajectory tracking | |
| WO2024046053A1 (en) | Vehicle violation detection method, apparatus and system, and storage medium | |
| Almutairy et al. | Arts: Automotive repository of traffic signs for the united states | |
| CN113949719B (en) | Vehicle-mounted inspection method and system based on 5G communication | |
| Balali et al. | Video-based detection and classification of US traffic signs and mile markers using color candidate extraction and feature-based recognition | |
| CN117237932A (en) | Intelligent identification system and method for urban illegal tags | |
| CN102722724B (en) | Vehicle-mounted night view system having target identification function and target identification method thereof | |
| CN110287897B (en) | Rail train visual positioning system based on deep learning | |
| Seifert et al. | Visual object detection for mobile road sign inventory | |
| Rahmani et al. | IR-LPR: A Large Scale Iranian License Plate Recognition Dataset | |
| CN111815960A (en) | Vehicle information display method based on big data | |
| Aiyelabegan et al. | Proposed automatic number plate recognition system using machine learning | |
| CN109145744A (en) | A kind of LSTM network pedestrian recognition methods again based on adaptive prediction mode | |
| CN107577995A (en) | The processing method and processing device of view data | |
| CN116824549B (en) | Target detection method and device based on multi-detection network fusion and vehicle |
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 |