CN111985418A - Vehicle-mounted intelligent identification device and method for risk source of road traffic safety facility - Google Patents
Vehicle-mounted intelligent identification device and method for risk source of road traffic safety facility Download PDFInfo
- Publication number
- CN111985418A CN111985418A CN202010859695.4A CN202010859695A CN111985418A CN 111985418 A CN111985418 A CN 111985418A CN 202010859695 A CN202010859695 A CN 202010859695A CN 111985418 A CN111985418 A CN 111985418A
- Authority
- CN
- China
- Prior art keywords
- image
- vehicle
- risk source
- traffic safety
- acquisition module
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 33
- 238000004364 calculation method Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 25
- 230000003993 interaction Effects 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000003384 imaging method Methods 0.000 claims description 7
- 230000003287 optical effect Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a vehicle-mounted intelligent identification device for risk sources of road traffic safety facilities, which belongs to the technical field of intelligent detection and identification and comprises a full-view image acquisition module, a positioning driving auxiliary information acquisition module and an image storage and online calculation unit, wherein the full-view image acquisition module, the positioning driving auxiliary information acquisition module and the image storage and online calculation unit are arranged on a vehicle; the full-view image acquisition module is used for acquiring a road image and sending the road image to the image storage and online calculation unit; the positioning driving auxiliary information acquisition module is used for acquiring position information and driving mileage information of a vehicle; and the image storage and online calculation unit is used for storing the acquired images, scanning the images, and extracting and outputting the risk source types and the position information in the images. A corresponding identification method is also included. The method does not depend on the prior knowledge of people in the risk source identification process, and does not need to carry out traffic control. The device is simple to operate, can accurately, intelligently and quickly output the highway risk source, and meets the requirement of ensuring the safe operation of the highway.
Description
Technical Field
The invention belongs to the technical field of intelligent detection and identification, and relates to a vehicle-mounted intelligent identification device and method for a risk source of a road traffic safety facility.
Background
The mountain highway has the characteristics of severe geological conditions, variable environmental climate, numerous bridges and tunnels, complex construction structure and distance from cities, so that the technical difficulty of operation management is higher. With the increasing number of the construction projects in China, the scale of the road network put into operation management is gradually enlarged, and a serious challenge is brought to the operation management work of the expressway.
Currently, a Chinese patent is found: the utility model provides a robot is patrolled and examined in emergent lane of highway, this patent has set up a guide rail on emergent lane, patrols and examines to the highway with machine vision's mode to do not explain the purpose of specifically patrolling and examining, also do not adopt artificial intelligence technique to discern the highway risk source, and the technical route is unclear, practical value is not high.
Disclosure of Invention
In view of the above, the present invention provides a vehicle-mounted device and method for intelligently and quickly identifying a risk source of a highway traffic safety facility, aiming at the traffic safety risk of the highway traffic safety facility, so as to solve the problems of high labor intensity, limitation of experience level, misjudgment of the risk source, high omission probability, and the like in the current manual patrol.
In order to achieve the purpose, the invention provides the following technical scheme:
on one hand, the vehicle-mounted intelligent identification device for the risk source of the road traffic safety facility comprises a full-view image acquisition module, a positioning driving auxiliary information acquisition module and an image storage and online calculation unit which are arranged on a vehicle;
the full-view image acquisition module is used for acquiring a road image and sending the road image to the image storage and online calculation unit;
the positioning driving auxiliary information acquisition module is used for acquiring position information and driving mileage information of a vehicle;
and the image storage and online calculation unit is used for storing the acquired images, scanning the images, and extracting and outputting the risk source types and the position information in the images.
Further, the full-view image acquisition module comprises an industrial camera array and an acquisition base which are arranged in front of and on the side of the top of the vehicle, the industrial camera array comprises a lens, a lens module, an optical filter, a CMOS or CCD integrated circuit, an image processor ISP and a data transmission interface which are arranged on the acquisition base, the CMOS or CCD integrated circuit is used for converting optical signals into electric signals, and the image processor ISP is used for converting the electric signals into digital image signals in a standard format and transmitting the digital image signals to the image storage and on-line calculation unit through the data transmission interface.
Furthermore, the positioning driving auxiliary information acquisition module adopts a satellite positioning or vehicle-mounted encoder, receives all visible Beidou satellites and RTK signals through an antenna, and interprets and calculates to obtain the self spatial position; and the non-signal area is positioned by fusing the geographical position of the road line, the information of the vehicle-mounted encoder and the satellite positioning information.
Further, the image storage and online computing unit integrates data collected by each sensor, and the system further comprises a continuous image frame collecting and processing module, which is used for processing the following steps:
a. when the processing of the continuous image frames starts to be executed, controlling a full-view image acquisition module to acquire images and playing back the acquired images to prompt a scanning range;
b. when a traffic safety facility region to be detected appears in a scene, detecting a possibility region from the image, and acquiring the approximate position of a risk source through a detection algorithm; if the imaging effect is not obvious due to the fact that the position is far, the imaging of the identified target is gradually amplified and clear in the process of waiting for the vehicle to move;
c. combining the detection result of each frame of image with the image frame number, and recording the detection result into a detection identification log;
d. and after the image processing is successful, prompting a user to detect the identification result through the detection log, and outputting an image sequence with a possible risk source.
Further, the image storage and online computing unit comprises an industrial personal computer and an embedded visual computing unit.
Furthermore, the system also comprises a human-computer interaction unit which is used for displaying and controlling the data of each unit.
On the other hand, the invention provides a vehicle-mounted intelligent identification method for risk sources of road traffic safety facilities, which comprises the following steps:
s1: the industrial computer sends an instruction through the interface to drive the industrial camera to acquire a color image;
s2: preprocessing the color image, including denoising and smoothing filtering;
s3: converting the processed color image into a gray image;
s4: detecting the image, and extracting an interested area containing a traffic sign, a traffic marking or a guardrail; if there is no detection result, go to step S1;
s5: calculating a local self-adaptive binary image in the region of interest;
s6: converting the binary image into a curve line segment by using a thinning algorithm, and extracting an end point;
s7: traversing all curve segment end points, introducing prior knowledge required by the existing specification, performing classification and identification by using multi-scale processing in combination with a gradient histogram and a support vector machine, and if the classification result of the local image of the end point under a certain scale or several scales is a traffic sign, a traffic marking and a guardrail risk source, determining the corresponding class of the end point as the traffic sign, the traffic marking and the guardrail risk source; otherwise, setting the risk source as a non-traffic safety facility risk source; recording all traffic safety facility risk sources and storing the traffic safety facility risk sources into a database;
s8: waiting for a user instruction, and returning to the step S1 if an exit instruction is not received within a certain time period; otherwise, go to step S9;
s9: and outputting a detection and identification result to form a traffic safety facility risk source identification report.
The invention has the beneficial effects that: the method can automatically identify the marks, the marked lines and the guardrails of the road traffic safety facilities in the visual field range image and then convert the marks, the marked lines and the guardrails into the local targeted processing of the region of interest. In the specific area, the detail information is strengthened by using a local binarization method so as to ensure high accuracy of detection. The risk source identification is modeled by adopting artificial intelligent algorithms such as a gradient histogram, a support vector machine and deep learning of the support vector machine, so that the implementation process is higher in speed and stability compared with the traditional method, and the method has higher noise and inclination resistance.
The method does not depend on the prior knowledge of people in the risk source identification process, and does not need to carry out traffic control. The device is simple to operate, can accurately, intelligently and quickly output the highway risk source, and meets the requirement of ensuring the safe operation of the highway.
Through the intensive research of the system, the invention solves the key technical problems of intelligent and efficient routing inspection of the highway safety facilities, breaks through the image detection and identification technology of the traffic safety risk source, and forms a targeted vehicle-mounted comprehensive monitoring device and a new generation traffic safety risk source sensing system under the complex environment. Therefore, the safety and the high efficiency of the operation management of the highway are improved, and the intelligent and information construction, upgrading and transformation of the highway network are served.
1. The invention has richer fusion information amount, more accurate classification and lower false alarm rate;
2. the invention is not limited by the field, and can be suitable for the detection and identification of the traffic safety risk source in a wider range and open-air environment;
3. the invention can combine the mileage identification technology to accurately position the spatial position of the risk source on the highway section;
4. the invention effectively utilizes the vehicle-mounted risk source acquisition and identification device and system, and utilizes the algorithm module to expand the existing functions;
5. the collected array image is used as a processing object, the image accords with human perception habits, and the image can be transmitted to each administrator for manual review;
6. the invention has higher automation processing level, can greatly reduce the workload of operators, improve the inspection efficiency and discover the highway risk source endangering the driving safety on the line as soon as possible.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Drawings
For the purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings in which:
fig. 1 is a schematic structural diagram of the vehicle-mounted intelligent risk source identification device for the road traffic safety facility.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention in a schematic way, and the features in the following embodiments and examples may be combined with each other without conflict.
Wherein the showings are for the purpose of illustrating the invention only and not for the purpose of limiting the same, and in which there is shown by way of illustration only and not in the drawings in which there is no intention to limit the invention thereto; to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by terms such as "upper", "lower", "left", "right", "front", "rear", etc., based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not an indication or suggestion that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes, and are not to be construed as limiting the present invention, and the specific meaning of the terms may be understood by those skilled in the art according to specific situations.
The invention discloses an intelligent rapid detection and identification method and device based on spatial prior information of a risk source of a highway traffic safety facility. Sources of traffic safety facility risk include, but are not limited to, sources of risk such as sign blocking or dropping, sign contamination or dropping, and non-compliant setting of guardrails. The invention can relate to the characteristic learning and characterization, the type identification and judgment and the area positioning of a risk source in an expressway scene in a complex scene, and can expand the characteristics of the existing functions by utilizing an algorithm module. The invention collects the risk source of the traffic safety facility through the front and side digital cameras arranged on the roof, stores the collected data in the industrial notebook, then adopts algorithms such as artificial intelligence and the like to intelligently identify the risk source, finally outputs the type and position information of the risk source of the highway on a certain road section, and forms a unified document to be provided for a maintenance management unit.
As shown in fig. 1, the present invention is specifically implemented as follows: the utility model provides a vehicular highway traffic safety facility risk source intelligent recognition device, mainly comprises following four parts: the system comprises a multi-camera full-view high-definition image real-time acquisition module, a vehicle position positioning and other auxiliary monitoring information acquisition module, an image data storage and online calculation unit system and a user interaction interface. (as shown in figure 1), the system is provided with an anti-interference image acquisition part, a high-precision vehicle positioning acquisition part, a high-reliability image data storage part, a risk source image processing detection and recognition core algorithm part and an interface part responsible for interaction with a user. The image acquisition part starts an industrial camera according to a user instruction and acquires a color video image according to a fixed frame rate; the traffic safety risk source detection and identification part scans images acquired by the camera, extracts and outputs risk source types and position information in the images; the man-machine interaction part receives a user work instruction, dynamically displays the processing process through a display during processing, and prompts completion and early warning information by a computer buzzer after the processing is completed. The four parts respectively comprise hardware connection and integration, a core processing algorithm and human-computer interaction interface software.
1) Multi-camera full-view high-definition image real-time acquisition module
The full-view visual information acquisition module consists of an industrial camera array for forward observation and lateral observation and an acquisition base thereof. The industrial camera array is mainly used for detecting traffic marked lines, traffic signs and guardrails, and can be influenced by rain and snow weather and illumination. The device comprises a lens, a lens module, a filter, a CMOS/CCD, an image processor ISP and a data transmission part. The light is focused on the sensor after passing through the optical lens and the optical filter, the light signal is converted into an electric signal through the CMOS or CCD integrated circuit, and then is converted into a digital image signal in a standard format of RAW, RGB or YUV and the like through the image processor (ISP), and the digital image signal is transmitted to the computer end through the data transmission interface.
The relationship between the resolution of visual imaging and object detection is calculated by an arctan function, and a minimum target is required to cover a pixel with sufficient resolution in image observation, so that missing detection caused by overlapping is avoided.
The information acquisition base is the basis that sensors such as camera modules are fixed in the top of the vehicle, forms a vehicle-mounted sensor arrangement platform and a data transmission channel, and simultaneously gives consideration to safety and legal compliance.
2) Auxiliary monitoring information acquisition module for vehicle position positioning and the like
In order to obtain the position information and the mileage information of the current vehicle, a vehicle position information recording module of a satellite positioning or encoder is adopted, and all visible Beidou satellites and RTK signals are received by a board card through an antenna and are interpreted and calculated to obtain the self space position. When a vehicle passes through the tunnel, the signal blind area is blocked and the risk that the signal cannot be accurately positioned exists, and the geographical position of a road line, the information of the vehicle-mounted encoder and the information of satellite positioning are fused.
3) Image data storage and online computing unit
Aiming at the requirement of image storage under complex operating conditions, an IPC (Industrial Personal Computer) is adopted as a recording terminal for man-machine interaction management control and video compression storage. The IPC serves as a reinforced personal computer, strengthens the capabilities of resisting electromagnetic interference, impact and vibration, and is used as a monitoring device controller and multisource sensor information recording equipment in a vehicle-mounted environment.
Aiming at the visual online computing performance requirement of high-performance parallelization, an embedded Nvidia Jetson TX2 is adopted as a vehicle-mounted visual computing unit to uniformly integrate data acquired by various sensors, the real-time requirement of video data preprocessing is guaranteed, the maximum delay of software response is enabled to be within an acceptable range, and data preprocessing and online analysis of partial simple tasks are realized.
And a continuous image frame acquisition processing module is also installed in the industrial computer. The process of processing successive frames is equivalent to processing a single image cyclically, as follows:
a. when the continuous image processing is started, the computer controls the industrial camera to start the image, and plays back the acquired image through the display screen to prompt the scanning range;
b. when a traffic safety facility region to be detected appears in a scene, the computer detects a possibility region from a picture transmitted by the digital camera, and obtains the approximate position of a risk source by using the detection algorithm; if the imaging effect is not obvious due to the fact that the position is far away, the imaging of the recognition target is gradually enlarged and clear in the process of the vehicle waiting to travel. In this case, the recognition target may be detected by the methods described herein;
c. combining the detection result of each frame of image with the image frame number, and recording the detection result into a detection identification log;
d. after the image processing is successful, the user is prompted to detect the identification result through the detection log, and an image frame sequence with a possible risk source is output to assist the operation of personnel.
4) User interaction interface
Aiming at the actual application needs, the invention designs a software interface special for human-computer interaction so as to comprehensively control the running condition of the device.
By taking multi-source heterogeneous expressway vehicle-mounted sensor detection data as a center, integrating expressway scene semantic analysis, key traffic identification and other equipment facility positioning identification, driving risk source visual identification and other core technical methods in a high-performance parallel computing server, and forming daily inspection and data management of expressway driving safety risk sources. The main verification contents comprise pollution, shielding, missing, falling off, insufficient photometric performance, out-of-specification setting and the like of highway traffic safety facilities (comprising signs, marked lines, guardrails and the like). The system constructs a core technology system of intelligent operation management of the highway and supports safe and stable operation of the highway.
The specific implementation mode and the steps of the invention are as follows:
1) giving an instruction for computing and executing processing by a user;
2) sending an instruction through an interface by an industrial computer to drive an industrial camera to read a color image;
3) preprocessing the color image, including denoising and smoothing filtering;
4) converting the processed color image into a gray image;
5) and detecting and extracting the region of interest by using the traffic sign, the traffic marking and the guardrail detection module. If no detection result exists, turning to the step 2);
6) calculating a local self-adaptive binary image in the region of interest (the image contains marks, marked lines and guardrails);
7) converting the binary image into a curve line segment by using a thinning algorithm, and extracting an end point;
8) traversing all curve segment endpoints, introducing expert prior knowledge (the requirement of the existing specification), performing classification and identification by combining multi-scale processing with a gradient histogram and a support vector machine, and if the classification result of the local image of the endpoint under one or more scales is a mark, a marking and a guardrail risk source, determining the corresponding category of the endpoint to be the mark, the marking and the guardrail risk source; otherwise, setting the risk source as a non-traffic safety facility risk source; and recording all traffic safety facility risk sources and storing the traffic safety facility risk sources into a database.
9) Waiting for a user instruction, and returning to the step 2) if the quit instruction is not received within a certain time period; otherwise, entering step 10);
10) and outputting a detection identification result to form a traffic safety facility risk source identification report.
11) And exiting.
Finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered by the claims of the present invention.
Claims (7)
1. The utility model provides a vehicular highway traffic safety facility risk source intelligent recognition device which characterized in that: the system comprises a full-view image acquisition module, a positioning driving auxiliary information acquisition module and an image storage and online calculation unit which are arranged on a vehicle;
the full-view image acquisition module is used for acquiring a road image and sending the road image to the image storage and online calculation unit;
the positioning driving auxiliary information acquisition module is used for acquiring position information and driving mileage information of a vehicle;
and the image storage and online calculation unit is used for storing the acquired images, scanning the images, and extracting and outputting the risk source types and the position information in the images.
2. The vehicle-mounted intelligent risk source identification device for the road traffic safety facility according to claim 1, characterized in that: the full-view image acquisition module comprises an industrial camera array and an acquisition base, wherein the industrial camera array and the acquisition base are arranged in front of and at the side of the top of the vehicle, the industrial camera array comprises a lens, a lens module, an optical filter, a CMOS or CCD integrated circuit, an image processor ISP and a data transmission interface, the CMOS or CCD integrated circuit is used for converting optical signals into electric signals, the image processor ISP is used for converting the electric signals into digital image signals in a standard format, and the digital image signals are transmitted to the image storage and on-line calculation unit through the data transmission interface.
3. The vehicle-mounted intelligent risk source identification device for the road traffic safety facility according to claim 1, characterized in that: the positioning driving auxiliary information acquisition module adopts a satellite positioning or vehicle-mounted encoder, receives all visible Beidou satellite and RTK signals through an antenna, and interprets and calculates to obtain the self spatial position; and the non-signal area is positioned by fusing the geographical position of the road line, the information of the vehicle-mounted encoder and the satellite positioning information.
4. The vehicle-mounted intelligent risk source identification device for the road traffic safety facility according to claim 1, characterized in that: the image storage and on-line computing unit integrates data collected by each sensor, and the device also comprises a continuous image frame collecting and processing module which is used for processing the following steps:
a. when the processing of the continuous image frames starts to be executed, controlling a full-view image acquisition module to acquire images and playing back the acquired images to prompt a scanning range;
b. when a traffic safety facility region to be detected appears in a scene, detecting a possibility region from the image, and acquiring the approximate position of a risk source through a detection algorithm; if the imaging effect is not obvious due to the fact that the position is far, the imaging of the identified target is gradually amplified and clear in the process of waiting for the vehicle to move;
c. combining the detection result of each frame of image with the image frame number, and recording the detection result into a detection identification log;
d. and after the image processing is successful, prompting a user to detect the identification result through the detection log, and outputting an image sequence with a possible risk source.
5. The vehicle-mounted intelligent risk source identification device for the road traffic safety facility according to claim 1, characterized in that: the image storage and online computing unit comprises an industrial personal computer and an embedded visual computing unit.
6. The vehicle-mounted intelligent risk source identification device for the road traffic safety facility according to claim 1, characterized in that: the system also comprises a man-machine interaction unit which is used for displaying and controlling the data of each unit.
7. A vehicle-mounted intelligent identification method for risk sources of road traffic safety facilities is characterized by comprising the following steps: the method comprises the following steps:
s1: the industrial computer sends an instruction through the interface to drive the industrial camera to acquire a color image;
s2: preprocessing the color image, including denoising and smoothing filtering;
s3: converting the processed color image into a gray image;
s4: detecting the image, and extracting an interested area containing a traffic sign, a traffic marking or a guardrail; if there is no detection result, go to step S1;
s5: calculating a local self-adaptive binary image in the region of interest;
s6: converting the binary image into a curve line segment by using a thinning algorithm, and extracting an end point;
s7: traversing all curve segment end points, introducing prior knowledge required by the existing specification, performing classification and identification by using multi-scale processing in combination with a gradient histogram and a support vector machine, and if the classification result of the local image of the end point under a certain scale or several scales is a traffic sign, a traffic marking and a guardrail risk source, determining the corresponding class of the end point as the traffic sign, the traffic marking and the guardrail risk source; otherwise, setting the risk source as a non-traffic safety facility risk source; recording all traffic safety facility risk sources and storing the traffic safety facility risk sources into a database;
s8: waiting for a user instruction, and returning to the step S1 if an exit instruction is not received within a certain time period; otherwise, go to step S9;
s9: and outputting a detection and identification result to form a traffic safety facility risk source identification report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010859695.4A CN111985418B (en) | 2020-08-24 | 2020-08-24 | Vehicle-mounted highway traffic safety facility risk source intelligent identification device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010859695.4A CN111985418B (en) | 2020-08-24 | 2020-08-24 | Vehicle-mounted highway traffic safety facility risk source intelligent identification device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111985418A true CN111985418A (en) | 2020-11-24 |
| CN111985418B CN111985418B (en) | 2024-02-27 |
Family
ID=73443087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010859695.4A Active CN111985418B (en) | 2020-08-24 | 2020-08-24 | Vehicle-mounted highway traffic safety facility risk source intelligent identification device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111985418B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112735139A (en) * | 2021-01-07 | 2021-04-30 | 中国安全生产科学研究院 | Device and method for checking potential safety hazards of common roads |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201269758Y (en) * | 2008-09-22 | 2009-07-08 | 交通部公路科学研究所 | Vehicle mounted full automatic detection recording system for traffic signs |
| US20120087636A1 (en) * | 2010-10-07 | 2012-04-12 | Canon Kabushiki Kaisha | Moving image playback apparatus, moving image management apparatus, method, and storage medium for controlling the same |
| CN104184997A (en) * | 2014-09-16 | 2014-12-03 | 哈尔滨恒誉名翔科技有限公司 | Quick surveillance video playback technique |
| CN104392224A (en) * | 2014-12-04 | 2015-03-04 | 西南交通大学 | Crack detection method for road surface |
| CN105678652A (en) * | 2015-11-05 | 2016-06-15 | 交通运输部公路科学研究所 | Slope construction safety risk assessment system based on GIS and index system method |
| JP2017033047A (en) * | 2015-07-28 | 2017-02-09 | 株式会社コンピュータシステム研究所 | Safety management support device, safety management support program, and storage medium |
| CN107680012A (en) * | 2016-08-01 | 2018-02-09 | 奥迪股份公司 | Vehicle DAS (Driver Assistant System) and method |
| CN110647863A (en) * | 2019-09-30 | 2020-01-03 | 重庆元韩汽车技术设计研究院有限公司 | Visual signal acquisition and analysis system for intelligent driving |
| 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 |
-
2020
- 2020-08-24 CN CN202010859695.4A patent/CN111985418B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201269758Y (en) * | 2008-09-22 | 2009-07-08 | 交通部公路科学研究所 | Vehicle mounted full automatic detection recording system for traffic signs |
| US20120087636A1 (en) * | 2010-10-07 | 2012-04-12 | Canon Kabushiki Kaisha | Moving image playback apparatus, moving image management apparatus, method, and storage medium for controlling the same |
| CN104184997A (en) * | 2014-09-16 | 2014-12-03 | 哈尔滨恒誉名翔科技有限公司 | Quick surveillance video playback technique |
| CN104392224A (en) * | 2014-12-04 | 2015-03-04 | 西南交通大学 | Crack detection method for road surface |
| JP2017033047A (en) * | 2015-07-28 | 2017-02-09 | 株式会社コンピュータシステム研究所 | Safety management support device, safety management support program, and storage medium |
| CN105678652A (en) * | 2015-11-05 | 2016-06-15 | 交通运输部公路科学研究所 | Slope construction safety risk assessment system based on GIS and index system method |
| CN107680012A (en) * | 2016-08-01 | 2018-02-09 | 奥迪股份公司 | Vehicle DAS (Driver Assistant System) and method |
| CN110647863A (en) * | 2019-09-30 | 2020-01-03 | 重庆元韩汽车技术设计研究院有限公司 | Visual signal acquisition and analysis system for intelligent driving |
| 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 |
Non-Patent Citations (4)
| Title |
|---|
| LI MENG 等: "Traffic Conflict Identification Technology of Vehicle Intersection Based on Vehicle Video Trajectory Extraction", 《PROCEDIA COMPUTER SCIENCE》, vol. 109, 31 December 2017 (2017-12-31), pages 963 - 968, XP085065618, DOI: 10.1016/j.procs.2017.05.454 * |
| 张金辉 等: "无线视频监控技术在公路隧道施工中的应用", 《河南科技》, no. 495, pages 58 * |
| 杨思源: "基于OPENCV的车辆牌照识别系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 15 December 2013 (2013-12-15), pages 138 - 1167 * |
| 陈松: "道路交通环境感知及行车风险评价方法研究", 《中国博士学位论文全文数据库工程科技Ⅰ辑》, pages 026 - 1 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112735139A (en) * | 2021-01-07 | 2021-04-30 | 中国安全生产科学研究院 | Device and method for checking potential safety hazards of common roads |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111985418B (en) | 2024-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
| CN102765365B (en) | Pedestrian detection method based on machine vision and pedestrian anti-collision warning system based on machine vision | |
| KR102167291B1 (en) | System and method for providing road status information | |
| JP2917661B2 (en) | Traffic flow measurement processing method and device | |
| CN102509089B (en) | Method for recognizing zebra crossing and measuring zebra crossing distance based on line-by-line scanning | |
| CN105575121B (en) | A kind of source science and technology overload remediation data collecting system and method based on intelligent transportation | |
| CN102915638A (en) | Surveillance video-based intelligent parking lot management system | |
| US11371851B2 (en) | Method and system for determining landmarks in an environment of a vehicle | |
| CN104392224A (en) | Crack detection method for road surface | |
| CN103065519A (en) | Detecting system of ramp fixed point stopping and starting and detecting method of ramp fixed point stopping and starting | |
| CN101510356A (en) | Video detection system and data processing device thereof, video detection method | |
| CN103472824A (en) | Camera-based navigation system and method for automatic navigation vehicle | |
| KR102167292B1 (en) | Apparatus and method for providing road status information | |
| CN111967396A (en) | Processing method, device and equipment for obstacle detection and storage medium | |
| CN112305573A (en) | Unmanned vehicle route selection system based on big dipper | |
| CN112769877A (en) | Group fog early warning method, cloud server, vehicle and medium | |
| CN111985418B (en) | Vehicle-mounted highway traffic safety facility risk source intelligent identification device and method | |
| CN201345166Y (en) | Video-based passage vehicle detector | |
| CN106960193A (en) | A kind of lane detection apparatus and method | |
| JP2002344952A (en) | License plate recognition device and method | |
| CN115965926B (en) | Vehicle-mounted road sign marking inspection system | |
| CN105575129B (en) | The method that vehicle is recognized by video source analysis | |
| CN107505946B (en) | Intelligent trolley path identification method based on black and white camera | |
| CN115953429A (en) | Mining area rockfall monitoring device and method | |
| CN114299715A (en) | Expressway information detection system based on videos, laser radar and DSRC |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220216 Address after: 400000 No.33 Xuefu Avenue, Nan'an District, Chongqing Applicant after: CHINA MERCHANTS CHONGQING HIGHWAY ENGINEERING TESTING CENTER Co.,Ltd. Address before: 400060 No. 79 Ertang street, Nan'an District, Chongqing Applicant before: Pang Rong |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |