CN210836135U - Traffic sign detecting and identifying system - Google Patents
Traffic sign detecting and identifying system Download PDFInfo
- Publication number
- CN210836135U CN210836135U CN201922342658.1U CN201922342658U CN210836135U CN 210836135 U CN210836135 U CN 210836135U CN 201922342658 U CN201922342658 U CN 201922342658U CN 210836135 U CN210836135 U CN 210836135U
- Authority
- CN
- China
- Prior art keywords
- traffic sign
- module
- traffic
- motor vehicle
- frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 claims abstract description 50
- 238000013145 classification model Methods 0.000 claims abstract description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
An embodiment of the utility model provides a traffic sign detects identification system, the system includes: the video acquisition module is used for acquiring video images of the surrounding environment of the motor vehicle and extracting image frames from the video images frame by frame; the detection module is connected with the video acquisition module and is used for detecting the image frames according to a pre-established traffic sign detection model, determining and acquiring the area where the traffic sign is located and correspondingly generating a traffic sign pattern to be identified; and the classification module is connected with the detection module and used for analyzing and judging the traffic sign pattern to be recognized according to the traffic sign classification model established in advance, determining the category information of the traffic sign contained in the traffic sign pattern to be recognized and outputting the category information as a recognition result. The embodiment determines the class information of the traffic signs contained in the traffic sign pattern through the detection module and the classification module, can accurately detect the traffic signs for the reference of a driver, and improves the driving safety of the motor vehicle.
Description
Technical Field
The embodiment of the utility model provides a motor vehicle driver assistance technical field especially relates to a traffic sign detects identification system.
Background
Generally, in a real road scene, traffic signs are often in a relatively complex environment, such as being blocked, being blurred due to aging, being reflected by strong light, and the like, and these factors may cause difficulty in detecting and identifying the traffic signs. At present, many detection systems exist in the industry, but many of the detection systems have no poor universality, and in addition, the detection and identification effects on the traffic signs of small targets are poor, and the traffic signs are easy to ignore or misjudge, so that the traffic sign detection and identification systems cannot accurately detect the traffic signs, and bring much inconvenience to motor vehicle drivers.
SUMMERY OF THE UTILITY MODEL
The embodiment of the utility model provides a technical problem who solves lies in, the embodiment of the utility model provides a traffic sign detects identification system to the accurate traffic sign that detects out supplies the driver to refer to.
In order to solve the technical problem, an embodiment of the utility model provides a following technical scheme: a traffic sign detection and identification system, the system comprising:
the video acquisition module is used for acquiring video images of the surrounding environment of the motor vehicle and extracting image frames from the video images frame by frame;
the detection module is connected with the video acquisition module and is used for detecting the image frames according to a pre-established traffic sign detection model, determining and acquiring the area where the traffic sign is located and correspondingly generating a traffic sign pattern to be identified;
and the classification module is connected with the detection module and used for analyzing and judging the traffic sign pattern to be recognized according to a traffic sign classification model established in advance, determining the category information of the traffic sign contained in the traffic sign pattern to be recognized and outputting the category information as a recognition result.
Further, the video capture module specifically includes:
the vehicle speed unit is used for acquiring the current vehicle speed of the motor vehicle;
the acquisition unit is used for comparing the current speed of the motor vehicle with a preset speed threshold, acquiring video images of the surrounding environment of the motor vehicle when the current speed of the motor vehicle is greater than the speed threshold, and extracting image frames from the video images frame by frame.
Further, the detection module specifically includes:
the storage unit is used for storing a pre-trained traffic sign detection model;
the image processing unit is used for calling the traffic sign detection model to detect the image frame and determining the area where the traffic sign is located in the image frame;
and the target positioning unit is used for acquiring the area where the traffic sign is located and correspondingly generating a traffic sign pattern to be identified.
Further, the traffic sign detection model and the traffic sign classification model are convolutional neural network models based on deep learning.
Further, the traffic sign detecting and identifying system further comprises:
and the output module is connected with the classification module and used for displaying the identification result.
After the technical scheme is adopted, the embodiment of the utility model provides an at least, following beneficial effect has: the embodiment of the utility model provides a video image through video acquisition module collection motor vehicle all ring edge borders, and follow draw frame by frame in the video image and obtain the image frame, then it is right to adopt the traffic sign detection model of establishing in advance through detection module respectively the image frame detects, confirms and acquires the traffic sign place region and correspond the formation from the image frame and wait to discern the traffic sign pattern, and it is right to adopt traffic sign classification model through classification module at last wait to discern the traffic sign pattern with carry out the analysis and judge, confirm the traffic sign's that contains classification information and export as the recognition result in waiting to discern the traffic sign pattern to can accurately detect out the traffic sign, supply the driver to refer to, improve motor vehicle driving's security.
Drawings
Fig. 1 is a schematic block diagram of an alternative embodiment of the traffic sign detection and identification system of the present invention.
Fig. 2 is a schematic block diagram of a video capture module according to an alternative embodiment of the traffic sign detection and identification system of the present invention.
Fig. 3 is a schematic block diagram of a detection module according to an alternative embodiment of the traffic sign detection and identification system of the present invention.
Fig. 4 is a schematic block diagram of yet another alternative embodiment of the traffic sign detection and identification system of the present invention.
Fig. 5 is a flow chart showing the steps of the traffic sign detecting and identifying system of the present invention.
Fig. 6 is a specific flowchart of step S1 for detecting and recognizing the traffic sign detecting and recognizing system according to the present invention.
Fig. 7 is a specific flowchart of step S2 for detecting and recognizing the traffic sign detecting and recognizing system according to the present invention.
Fig. 8 is a flowchart of another step of detecting and recognizing by using the traffic sign detecting and recognizing system of the present invention.
Detailed Description
The present application will now be described in further detail with reference to the accompanying drawings and specific examples. It is to be understood that the following illustrative embodiments and description are only intended to illustrate the present invention, and are not intended to limit the present invention, and features in the embodiments and examples may be combined with each other in the present application without conflict.
As shown in fig. 1, the utility model discloses in the implementation provide a traffic sign detects identification system, the system includes:
the system comprises a video acquisition module 1, a video processing module and a video processing module, wherein the video acquisition module is used for acquiring video images of the surrounding environment of the motor vehicle and extracting image frames from the video images frame by frame;
the detection module 3 is connected with the video acquisition module 1 and is used for detecting the image frames according to a pre-established traffic sign detection model, determining and acquiring the area where the traffic sign is located and correspondingly generating a traffic sign pattern to be identified;
and the classification module 5 is connected with the detection module 3 and is used for analyzing and judging the traffic sign pattern to be recognized according to a traffic sign classification model established in advance, determining the category information of the traffic sign contained in the traffic sign pattern to be recognized and outputting the category information as a recognition result.
The embodiment of the utility model provides a gather the video image of motor vehicle all ring edge borders through video acquisition module 1, and follow draw frame by frame in the video image and obtain the image frame, then it is right to adopt the traffic sign detection model of establishing in advance through detection module 3 respectively the image frame detects, confirms and acquires the traffic sign place region and correspond the formation from the image frame and wait to discern the traffic sign pattern, and it is right to adopt traffic sign classification model through classification module 5 at last wait to discern the traffic sign pattern with carry out the analysis and judgment, confirm the traffic sign's that contains in waiting to discern the traffic sign pattern classification information and export as the recognition result to can accurately detect out the traffic sign, supply the driver to refer to, improve motor vehicle driving's security. In a specific implementation, the video capture module 1 may be a vehicle-mounted camera of a motor vehicle.
In an optional embodiment of the present invention, as shown in fig. 2, the video capture module 1 specifically includes:
the vehicle speed unit 10 is used for acquiring the current vehicle speed of the motor vehicle;
the acquisition unit 12 is configured to compare the current vehicle speed of the motor vehicle with a preset vehicle speed threshold, acquire a video image of the surrounding environment of the motor vehicle when the current vehicle speed is greater than the vehicle speed threshold, and extract image frames from the video image frame by frame.
In the embodiment, after the current speed of the motor vehicle is compared with the preset speed threshold value by the acquisition unit 12, the video image of the surrounding environment of the motor vehicle is correspondingly acquired when the current speed of the motor vehicle is greater than the speed threshold value, so that the acquisition is performed when the motor vehicle is in a preset speed; the detection and identification system can be effectively activated according to the current vehicle speed, the video image acquisition of the surrounding environment of the motor vehicle can be carried out, manual operation is not needed, and great convenience is realized.
In an optional embodiment of the present invention, as shown in fig. 3, the detecting module 3 specifically includes:
a storage unit 30, configured to store a traffic sign detection model trained in advance;
the image processing unit 32 is configured to invoke the traffic sign detection model to detect the image frame, and determine an area where a traffic sign is located in the image frame;
and the target positioning unit 34 is used for acquiring the area where the traffic sign is located and correspondingly generating a traffic sign pattern to be identified.
In the embodiment, the storage unit 30 stores the traffic sign detection model in advance, and the image processing unit 32 can be directly called when the image frame needs to be detected, so that the detection efficiency is improved; and then the target location unit 34 correspondingly generates the traffic sign pattern to be identified in the area where the traffic sign is located, so that the classification processing is convenient.
In an optional embodiment of the present invention, the traffic sign detection model and the traffic sign classification model are both convolutional neural network models based on deep learning. In the embodiment, the traffic sign detection model and the traffic sign classification model both adopt the convolutional neural network model based on deep learning, and a great amount of characteristics of the traffic sign such as shape, color and the like are deeply learned in advance through the convolutional neural network, so that the convolutional neural network model is generated, and the traffic sign can be efficiently detected and identified.
In an optional embodiment of the present invention, as shown in fig. 4, the traffic sign detecting and identifying system further includes:
and the output module 7 is connected with the classification module 5 and used for displaying the identification result.
This embodiment is through setting up output module 7, demonstrates the recognition result that classification module 5 determined, makes things convenient for the driver to know and need not the driver and look up by oneself, has improved the security of driving. In specific implementation, the output module 7 may be an audio device that outputs in an audio broadcasting manner, a display device that outputs in a video display manner, or a multimedia device that outputs audio and video.
As shown in FIG. 5, the traffic sign detection and identification system according to the embodiment of the present invention has the following steps:
s1: collecting video images of the surrounding environment of the motor vehicle, and extracting image frames from the video images frame by frame to obtain image frames;
s2: detecting the image frames according to a pre-established traffic sign detection model, determining and acquiring the area where the traffic sign is located and correspondingly generating a traffic sign pattern to be identified;
s3: and analyzing and judging the traffic sign pattern to be recognized according to a pre-established traffic sign classification model, determining the category information of the traffic sign contained in the traffic sign pattern to be recognized and outputting the category information as a recognition result.
As shown in fig. 6, the step S1 specifically includes:
s11: acquiring the current speed of the motor vehicle;
s12: comparing the current speed of the motor vehicle with a preset speed threshold, acquiring video images of the surrounding environment of the motor vehicle when the current speed of the motor vehicle is greater than the speed threshold, and extracting image frames from the video images frame by frame.
As shown in fig. 7, the step S2 specifically includes:
s21: storing a pre-trained traffic sign detection model;
s22: calling the traffic sign detection model to detect the image frame and determining the area of the traffic sign in the image frame;
s23: and acquiring the area where the traffic sign is located and correspondingly generating a traffic sign pattern to be identified.
The traffic sign detection model and the traffic sign classification model are convolutional neural network models based on deep learning.
As shown in fig. 8, adopt the embodiment of the utility model provides a traffic sign detects identification system and still includes to traffic sign detection discernment:
s4: and displaying the identification result.
The embodiments of the present invention have been described with reference to the accompanying drawings, but the present invention is not limited to the above-mentioned embodiments, which are only illustrative and not restrictive, and those skilled in the art can make many forms without departing from the spirit and scope of the present invention, and these forms are within the scope of the present invention.
Claims (5)
1. A traffic sign detection and identification system, said system comprising:
the video acquisition module is used for acquiring video images of the surrounding environment of the motor vehicle and extracting image frames from the video images frame by frame;
the detection module is connected with the video acquisition module and is used for detecting the image frames according to a pre-established traffic sign detection model, determining and acquiring the area where the traffic sign is located and correspondingly generating a traffic sign pattern to be identified;
and the classification module is connected with the detection module and used for analyzing and judging the traffic sign pattern to be recognized according to a traffic sign classification model established in advance, determining the category information of the traffic sign contained in the traffic sign pattern to be recognized and outputting the category information as a recognition result.
2. The system for detecting and identifying traffic signs according to claim 1, wherein the video capture module specifically comprises:
the vehicle speed unit is used for acquiring the current vehicle speed of the motor vehicle;
the acquisition unit is used for comparing the current speed of the motor vehicle with a preset speed threshold, acquiring video images of the surrounding environment of the motor vehicle when the current speed of the motor vehicle is greater than the speed threshold, and extracting image frames from the video images frame by frame.
3. The system for detecting and identifying traffic signs according to claim 1, wherein the detection module specifically comprises:
the storage unit is used for storing a pre-trained traffic sign detection model;
the image processing unit is used for calling the traffic sign detection model to detect the image frame and determining the area where the traffic sign is located in the image frame;
and the target positioning unit is used for acquiring the area where the traffic sign is located and correspondingly generating a traffic sign pattern to be identified.
4. The system of claim 1, wherein the traffic sign detection model and the traffic sign classification model are deep learning based convolutional neural network models.
5. The traffic-sign detection and identification system according to claim 1, further comprising:
and the output module is connected with the classification module and used for displaying the identification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201922342658.1U CN210836135U (en) | 2019-12-23 | 2019-12-23 | Traffic sign detecting and identifying system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201922342658.1U CN210836135U (en) | 2019-12-23 | 2019-12-23 | Traffic sign detecting and identifying system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN210836135U true CN210836135U (en) | 2020-06-23 |
Family
ID=71281558
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201922342658.1U Active CN210836135U (en) | 2019-12-23 | 2019-12-23 | Traffic sign detecting and identifying system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN210836135U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826544A (en) * | 2019-12-23 | 2020-02-21 | 深圳市豪恩汽车电子装备股份有限公司 | Traffic sign detection and identification system and method |
-
2019
- 2019-12-23 CN CN201922342658.1U patent/CN210836135U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826544A (en) * | 2019-12-23 | 2020-02-21 | 深圳市豪恩汽车电子装备股份有限公司 | Traffic sign detection and identification system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110532976B (en) | Fatigue driving detection method and system based on machine learning and multi-feature fusion | |
| US11003931B2 (en) | Vehicle monitoring method and apparatus, processor, and image acquisition device | |
| CN107392103B (en) | Method and device for detecting road lane line and electronic equipment | |
| WO2018201835A1 (en) | Signal light state recognition method, device and vehicle-mounted control terminal and motor vehicle | |
| CN107891808B (en) | Driving reminding method and device and vehicle | |
| US20120128210A1 (en) | Method for Traffic Sign Recognition | |
| JP2013529348A (en) | Lighting invariant and robust apparatus and method for detecting and recognizing various traffic signs | |
| CN104657735A (en) | Lane line detection method and system, as well as lane departure early warning method and system | |
| JP2011216051A (en) | Program and device for discriminating traffic light | |
| WO2019126908A1 (en) | Image data processing method, device and equipment | |
| CN107886034B (en) | Driving reminding method and device and vehicle | |
| CN105023452B (en) | A kind of method and device of multichannel traffic lights signal acquisition | |
| US11482012B2 (en) | Method for driving assistance and mobile device using the method | |
| CN110826544A (en) | Traffic sign detection and identification system and method | |
| US11250279B2 (en) | Generative adversarial network models for small roadway object detection | |
| US9569676B2 (en) | Computer implemented system and method for extracting and recognizing alphanumeric characters from traffic signs | |
| CN113044023B (en) | Parking space ponding identification method and device | |
| CN114639078A (en) | Vehicle type recognition method, device and system | |
| CN111046741A (en) | Method and device for identifying lane line | |
| CN210836135U (en) | Traffic sign detecting and identifying system | |
| US20120189161A1 (en) | Visual attention apparatus and control method based on mind awareness and display apparatus using the visual attention apparatus | |
| KR101620425B1 (en) | System for lane recognition using environmental information and method thereof | |
| CN112669615A (en) | Parking space detection method and system based on camera | |
| CN113053152A (en) | Vehicle-mounted traffic sign real-time display method and system | |
| CN102722724B (en) | Vehicle-mounted night view system having target identification function and target identification method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |