CN110619747A - Intelligent monitoring method and system for highway road - Google Patents
Intelligent monitoring method and system for highway road Download PDFInfo
- Publication number
- CN110619747A CN110619747A CN201910929511.4A CN201910929511A CN110619747A CN 110619747 A CN110619747 A CN 110619747A CN 201910929511 A CN201910929511 A CN 201910929511A CN 110619747 A CN110619747 A CN 110619747A
- Authority
- CN
- China
- Prior art keywords
- video data
- data
- road
- vehicle
- detection result
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/955—Hardware or software architectures specially adapted for image or video understanding using specific electronic processors
-
- 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
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/048—Detecting movement of traffic to be counted or controlled with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/097—Supervising of traffic control systems, e.g. by giving an alarm if two crossing streets have green light simultaneously
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/161—Decentralised systems, e.g. inter-vehicle communication
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Abstract
The invention discloses an intelligent monitoring method and system for highway roads, wherein the system comprises the following steps: the system comprises an acquisition end, a server end and a client end which are connected in sequence; the acquisition end receives high-definition video data or infrared video data in two directions of a road at the same time, performs data preprocessing on the high-definition video data or the infrared video data, and extracts video frames to obtain picture data; inputting the picture data into a trained deep convolution neural network for detection to obtain a vehicle detection result, a lane line detection result and an environmental visibility detection result; analyzing abnormal traffic conditions according to the vehicle detection results and the lane line detection results to obtain and display graded early warning results or warning results, and actively early warning or warning the vehicle in real time; the abnormal traffic conditions include vehicle violations, faults, and accidents; and obtaining and displaying a grading guide result according to the environment visibility detection result, and actively guiding the vehicle in real time.
Description
Technical Field
The invention belongs to the technical field of intelligent traffic facilities, and particularly relates to an intelligent monitoring method and system for an expressway road.
Background
The highway is a totally-enclosed and full-interchange road, and vehicles running on the highway have high running speed and high traffic flow. Its ideal characteristics are "safe, quick, high-effective, comfortable and convenient". However, with the increasing demand for traffic and the occurrence of congestion, accidents and pollution, highway monitoring systems are becoming a focus of attention for the construction and management of traffic facilities.
The monitoring system for the expressway is established to solve two main problems of congestion and safety in the operation of the expressway, and aims to ensure the driving safety and the smooth road. The highway monitoring system should have the following three functions: information collection, namely collecting the changing road traffic state including traffic information, meteorological information, traffic abnormal event information and the like in real time; analyzing and processing information, including judging whether the traffic running state is normal or not, confirming the severity of the traffic abnormal event, predicting the traffic abnormal state, determining the handling scheme of the occurred or possibly occurred abnormal event and the like; and information providing functions including providing road traffic condition information to drivers who are driving on the highway, giving restriction, persuasion, and advisory instructions to driving vehicles, providing treatment instructions to departments handling traffic accidents and other abnormal events, and providing highway traffic information for more widespread use to information media or society.
However, the inventors have found in the course of research that the following problems exist in the existing highway monitoring system.
First, there is a problem of separation of information collection and analysis processing of information. The existing acquisition end only acquires highway monitoring information, transmits the acquired monitoring information to the server end, and analyzes and processes the monitoring information by the server end in an algorithm mode and the like, however, with the popularization of technologies such as high-definition video monitoring and the like, the transmission speed is slow due to overlarge acquired video images, the video images received by the server end and the acquisition end are delayed, the server end receives the video images, processes the video images and then transmits the processed video images to the client end, certain delay exists, real-time processing cannot be achieved, and an information providing function cannot be performed in real time. Traffic accidents often occur in a very short moment, and the delay of information can cause serious traffic dangerous events, property loss and even casualties.
Second, there is a problem of lack of timely warning and guidance of offending vehicles. For the behaviors that a driver drives a vehicle to break rules and regulations on an expressway, the driver is punished afterwards only in an administrative punishing mode, and the existing expressway monitoring system cannot prevent the violation behaviors in time, cannot correct the violation behaviors in time and cannot effectively prevent traffic accidents because the existing expressway monitoring system has no on-site warning device or mobile client to remind the driver to forbid the violation behaviors on the expressway when the vehicle breaks rules and regulations.
Third, there is a problem of lack of active prevention of vehicle violations and traffic accidents. Most of the existing highway monitoring systems are used for post-event punishment of vehicle violation behaviors or for judging accidents and making emergency plans after accidents occur, the prevention of the vehicle violation behaviors and the traffic accidents only needs passive preventive measures such as setting fixed warning slogans, and intelligent monitoring methods and systems for actively preventing the vehicle violation behaviors and the traffic accidents through highway monitoring facilities are lacked.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides an intelligent monitoring method and system for an expressway road, wherein collected expressway monitoring information is processed in real time by an intelligent chip through a deep learning algorithm at a collecting end, so that early warning information or warning information is displayed on an on-site warning device in real time, the monitoring information under the early warning or warning condition is transmitted to a server end for further analysis and processing, and the expressway road is intelligently monitored in all directions in real time.
According to one aspect of one or more embodiments of the present disclosure, there is provided an intelligent monitoring method for an expressway road.
An intelligent monitoring method for an expressway road, comprising the following steps:
simultaneously receiving high-definition video data or infrared video data in two directions of a road, performing data preprocessing on the high-definition video data or the infrared video data, and extracting video frames to obtain picture data;
inputting the picture data into a trained deep convolution neural network for detection to obtain a vehicle detection result, a lane line detection result and an environmental visibility detection result;
analyzing abnormal traffic conditions according to the vehicle detection results and the lane line detection results to obtain and display graded early warning results or warning results, and actively early warning or warning the vehicle in real time; the abnormal traffic conditions include vehicle violations, faults, and accidents;
and obtaining and displaying a grading guide result according to the environment visibility detection result, and actively guiding the vehicle in real time.
Further, in the method, the receiving high definition video data or infrared video data of two directions of a road simultaneously includes: simultaneously receives high-definition video data or infrared video data in two directions of the road collected by a collecting end arranged on a common expressway,
or simultaneously receiving high-definition video data or infrared video data in two directions of the tunnel road collected by a collecting end arranged in the high-speed tunnel.
Further, in the method, the specific steps of simultaneously receiving high definition video data or infrared video data in two directions of a road collected by a collection end arranged on a common expressway, performing data preprocessing on the high definition video data or the infrared video data, and extracting a video frame to obtain picture data include:
receiving illumination data collected by an illumination sensor, and judging the size of the illumination data and a preset illumination threshold value;
when the illumination data is larger than a preset illumination threshold value, only sending a high-definition camera starting command to start a high-definition camera to collect high-definition video data in two directions of a road, receiving the high-definition video data in the two directions of the road, performing data preprocessing, and extracting video frames to obtain picture data;
when the illumination data is less than or equal to a preset illumination threshold value, sending an infrared camera starting command to start an infrared camera to collect infrared video data in two directions of a road, receiving the infrared video data in the two directions of the road, performing data preprocessing, and extracting a video frame to obtain picture data; and when the abnormal traffic condition is analyzed, sending a high-definition camera starting command and a supplementary lighting lamp starting command, starting the high-definition camera to collect high-definition video data in two directions of the road under the supplementary lighting of the supplementary lighting lamp, and recording the video.
Further, in the method, the specific steps of simultaneously receiving high-definition video data or infrared video data in two directions of a road collected by a collection end arranged in the high-speed tunnel, performing data preprocessing on the high-definition video data or the infrared video data, and extracting a video frame to obtain picture data include:
simultaneously receiving infrared video data collected by infrared cameras in two directions of a road, performing data preprocessing on the infrared video data, and extracting video frames to obtain picture data; and when the analysis result is an abnormal traffic condition, sending a starting command of the two-direction high-definition camera on the road and a starting command of the light supplement lamp, starting the two-direction high-definition camera on the road to acquire high-definition video data under the light supplement of the light supplement lamp, and recording the video.
Further, in the method, the deep convolutional neural network adopts an improved SSD network, and the specific step of obtaining the trained improved SSD network includes:
receiving high-definition video data and infrared video data in two directions of a road, performing data preprocessing, and extracting video frames to obtain picture data;
receiving a labeling instruction to label the picture data to form a training set, a verification set and a test set;
inputting the training set and the verification set into an improved SSD network for training and cross-verifying; the improved SSD network adopts a residual error network to extract features, the rear end of the residual error network is connected with the SSD network through a residual error module, and the rear end of the SSD network is connected with a deconvolution module;
and optimizing the improved SSD network through the test set to obtain the trained improved SSD network.
Further, in the method, when abnormal traffic conditions do not exist, the video frames are extracted by adopting a frame extraction algorithm, and when the analysis result is the abnormal traffic conditions, the video frames are extracted frame by frame.
Further, the method further comprises: and sending the vehicle detection result, the lane line detection result and the environmental visibility detection result to a server side.
According to an aspect of one or more embodiments of the present disclosure, there is provided a computer-readable storage medium.
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to execute a method for intelligent monitoring of highway roads.
According to an aspect of one or more embodiments of the present disclosure, there is provided a terminal device.
A terminal device comprising a processor and a computer-readable storage medium, the processor being configured to implement instructions; the computer readable storage medium is used for storing a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the intelligent monitoring method for the highway roads.
According to one aspect of one or more embodiments of the present disclosure, there is provided an intelligent monitoring apparatus for an expressway road.
An intelligent monitoring device for an expressway road is based on the intelligent monitoring method for the expressway road, and comprises the following steps:
the data acquisition module is configured to receive high-definition video data or infrared video data in two directions of a road at the same time, perform data preprocessing on the high-definition video data or the infrared video data, and extract video frames to obtain picture data;
the data detection module is configured to input the picture data into a trained deep convolutional neural network for detection to obtain a vehicle detection result, a lane line detection result and an environment visibility detection result;
the first data analysis module is configured to analyze abnormal traffic conditions according to the vehicle detection result and the lane line detection result, obtain and display graded early warning results or warning results, and actively early warn or warn the vehicle in real time; the abnormal traffic conditions include vehicle violations, faults, and accidents;
and the second data analysis module is configured to obtain and display a grading guide result according to the environment visibility detection result and actively guide the vehicle in real time.
According to one aspect of one or more embodiments of the present disclosure, there is provided an intelligent monitoring system for an expressway road.
An intelligent monitoring system for highway roads, the system comprising: the system comprises an acquisition end, a server end and a client end which are connected in sequence;
the collection end realizes the intelligent monitoring method for the highway; the method comprises the steps that vehicle detection results, lane line detection results and environment visibility detection results are sent to a server side, or high-definition video data collected by a high-definition camera are sent to the server side while infrared video data are collected by an infrared camera;
the acquisition end comprises an acquisition end arranged on a common expressway and an acquisition end arranged in the expressway, wherein the acquisition end arranged on the common expressway is provided with a high-definition camera and an infrared camera at the front end in the vehicle running direction, and the high-definition camera is arranged at the rear end; the high-definition cameras and the infrared cameras are arranged at the front end and the rear end of the acquisition end arranged in the high-speed tunnel in the vehicle running direction.
The above one or more technical solutions have the following beneficial effects:
1. according to the intelligent monitoring method and system for the expressway road, the information acquisition and the information analysis and processing are unified by the acquisition end, the acquired video data are processed in real time through the AI chip, the processing result is directly displayed through the display device, a driver of a vehicle on the expressway is reminded in real time, and traffic hazard events caused by information lag are effectively avoided.
2. The invention discloses an intelligent monitoring method and system for an expressway road, which are characterized in that a vehicle detection result and a lane line detection result are obtained through deep learning of collected video data, abnormal traffic condition analysis is carried out according to the vehicle detection result and the lane line detection result, a graded early warning result or warning result is obtained and displayed, and real-time active early warning or warning is carried out on a vehicle; the display of the early warning result effectively realizes the active prevention of the vehicle violation behaviors and the traffic accidents before the occurrence; the display of the warning result can correct the violation behaviors in time, effectively prevent traffic accidents and play a good role in prompting the rear vehicles with the traffic accidents.
3. According to the intelligent monitoring method and system for the highway, the environmental visibility detection result is obtained through deep learning of collected video data, the grading guide result is obtained and displayed according to the environmental visibility detection result, the vehicle is actively guided in real time, the detection of the existing visibility detector on the environmental visibility can be cancelled at the collection end, and the cost is effectively saved.
4. According to the characteristics of an ordinary road and a tunnel of the highway, a collection end is respectively arranged on the ordinary highway to collect high-definition video data or infrared video data in two directions of the road, and a collection end is arranged in the highway to collect the high-definition video data or infrared video data in two directions of the tunnel road; the high-definition camera and the infrared camera are arranged at the front end and the rear end of the driving direction of the vehicle on the common road, the high-definition camera is adopted to collect high-definition video data in two directions of the road in the daytime, the infrared camera is adopted to collect infrared video data in two directions of the road at night, the infrared camera is adopted to collect the infrared video data in two directions of the road all day in the tunnel, the infrared video data can effectively sense objects in the video data at night and prevent the noise generated by the automobile light in the video data from influencing the vehicle detection of the convolutional neural network, when the analysis result is an abnormal traffic condition, a high-definition camera starting command and a light supplementing lamp starting command are sent, the high-definition camera is started to collect the high-definition video data under the light supplementing lamp, video recording is carried out, and the detail data missing of the infrared video data.
5. According to the intelligent monitoring method and system for the highway road, disclosed by the invention, the acquisition end acquires high-definition video data or infrared video data in two directions of the road, and the unidirectional visual blind area is avoided by detecting the two video data in the vehicle driving direction and the vehicle driving reverse direction at the same time, so that the highway road is monitored in an all-around manner.
6. The invention discloses an intelligent monitoring method and system for an expressway road, which adopt an improved SSD network to simultaneously detect the visibility of vehicles, lane lines and the environment in video data, and the improved SSD network is additionally provided with a deconvolution module at the rear end of the original SSD network, thereby effectively expanding the situation information of low latitude, effectively improving the detection of a small-scale target of an expressway road video image perspective, adopting a residual error network and adding a residual error module before the classification regression of the SSD network, extracting the characteristics of higher semantic information by using a deeper network, and effectively improving the detection precision.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a schematic flow chart of an intelligent monitoring method for an expressway road according to one or more embodiments of the present invention;
fig. 2 is a schematic flow chart of an intelligent monitoring method for an expressway during the daytime, which is executed by a collection-end controller installed on an ordinary expressway road according to one or more embodiments of the present invention;
fig. 3 is a schematic flow chart of an intelligent monitoring method for an expressway road, which is performed at night in a controller at a collection end installed on an ordinary expressway road according to one or more embodiments of the present invention;
fig. 4 is a flowchart illustrating an intelligent monitoring method for an expressway road, which is implemented in a collection-side controller disposed in an expressway tunnel according to one or more embodiments of the present invention.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
It is noted that the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems according to various embodiments of the present disclosure. It should be noted that each block in the flowchart or block diagrams may represent a module, a segment, or a portion of code, which may comprise one or more executable instructions for implementing the logical function specified in the respective embodiment. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example one
According to one aspect of one or more embodiments of the present disclosure, an intelligent monitoring method for an expressway is provided, in which collected expressway monitoring information is processed in real time by an intelligent chip at a collection end by using a deep learning algorithm, so that early warning information or warning information is displayed on an on-site warning device in real time, and the monitoring information under the early warning or warning condition is transmitted to a server end for further analysis and processing, thereby realizing omnibearing real-time intelligent monitoring for the expressway.
As shown in fig. 1, an intelligent monitoring method for an expressway road includes:
step S1: simultaneously receiving high-definition video data or infrared video data in two directions of a road, performing data preprocessing on the high-definition video data or the infrared video data, and extracting video frames to obtain picture data;
step S2: inputting the picture data into a trained deep convolution neural network for detection to obtain a vehicle detection result, a lane line detection result and an environmental visibility detection result;
step S3: analyzing abnormal traffic conditions according to the vehicle detection results and the lane line detection results to obtain and display graded early warning results or warning results, and actively early warning or warning the vehicle in real time; the abnormal traffic conditions include vehicle violations, faults, and accidents;
step S4: and obtaining and displaying a grading guide result according to the environment visibility detection result, and actively guiding the vehicle in real time.
In this embodiment, the receiving high definition video data or infrared video data of two directions of road simultaneously includes: simultaneously receives high-definition video data or infrared video data in two directions of the road collected by a collecting end arranged on a common expressway,
or simultaneously receiving high-definition video data or infrared video data in two directions of the tunnel road collected by a collecting end arranged in the high-speed tunnel.
The intelligent monitoring method for the highway road in the embodiment is realized in a controller of an acquisition end. According to the characteristics of the highway, the intelligent monitoring method for the highway road is slightly different between the controller arranged at the acquisition end of the highway tunnel and the controller arranged at the acquisition end of the highway ordinary road.
On an ordinary highway road, a collection end is arranged at a certain distance, and a high-definition camera and an infrared camera are arranged at the front end and the rear end of the collection end of the ordinary highway in the driving direction of road vehicles. The high-definition camera and the infrared camera which are arranged at the front end and the rear end of the running direction of a road vehicle at the collecting end of the common highway are connected with the controller of the collecting end, and the controller arranged at the collecting end of the common highway is also connected with the light supplement lamp, the illumination sensor and the wireless transmission module which are arranged beside the high-definition camera. The high-definition cameras and the infrared cameras are arranged at the front end and the rear end of the running direction of the vehicle on the common road, the high-definition cameras are used for collecting high-definition video data in two directions of the road in the daytime, and the infrared cameras are used for collecting infrared video data in two directions of the road at night. In this embodiment, an acquisition end is arranged every 1km on an ordinary highway.
As shown in fig. 2, an intelligent monitoring method for an expressway road is implemented in a controller disposed at an acquisition end of an ordinary expressway road, and includes:
step S1: receiving illumination data collected by an illumination sensor, and judging the size of the illumination data and a preset illumination threshold value; when the illumination data is larger than a preset illumination threshold value, only sending a high-definition camera starting command to start a high-definition camera to collect high-definition video data in two directions of a road, receiving the high-definition video data in the two directions of the road, performing data preprocessing, and extracting video frames to obtain picture data;
step S2: inputting the picture data into a trained deep convolutional neural network for detection to obtain a vehicle detection result, a lane line detection result and an environment visibility detection result, and sending the vehicle detection result, the lane line detection result and the environment visibility detection result to a server side through a wireless transmission module;
step S3: analyzing abnormal traffic conditions according to the vehicle detection results and the lane line detection results to obtain and display graded early warning results or warning results, and actively early warning or warning the vehicle in real time; and sending the data to a server end through a wireless transmission module; the abnormal traffic conditions include vehicle violations, faults, and accidents;
step S4: and according to the detection result of the environmental visibility, obtaining and displaying a grading guide result, actively guiding the vehicle in real time, and sending the grading guide result to a server side through a wireless transmission module.
As shown in fig. 3, an intelligent monitoring method for an expressway road is implemented in a controller disposed at an acquisition end of an ordinary expressway road, and includes:
step S1: receiving illumination data collected by an illumination sensor, and judging the size of the illumination data and a preset illumination threshold value; when the illumination data is less than or equal to a preset illumination threshold value, sending an infrared camera starting command to start an infrared camera to collect infrared video data in two directions of a road, receiving the infrared video data in the two directions of the road, performing data preprocessing, and extracting a video frame to obtain picture data;
step S2: inputting the picture data into a trained deep convolutional neural network for detection to obtain a vehicle detection result, a lane line detection result and an environment visibility detection result, and sending the vehicle detection result, the lane line detection result and the environment visibility detection result to a server side through a wireless transmission module;
step S3: analyzing abnormal traffic conditions according to the vehicle detection results and the lane line detection results to obtain and display graded early warning results or warning results, and actively early warning or warning the vehicle in real time; and sending the data to a server end through a wireless transmission module; the abnormal traffic conditions include vehicle violations, faults, and accidents;
when the abnormal traffic condition is analyzed, sending a high-definition camera starting command and a supplementary lighting lamp starting command, starting the high-definition camera to collect high-definition video data in two directions of a road under the supplementary lighting of the supplementary lighting lamp, and recording videos; and sending the data to a server end through a wireless transmission module;
step S4: according to the detection result of the environmental visibility, obtaining and displaying a grading guide result, actively guiding the vehicle in real time, and sending the grading guide result to a server end through a wireless transmission module;
when the abnormal traffic condition is analyzed, sending a high-definition camera starting command and a supplementary lighting lamp starting command, starting the high-definition camera to collect high-definition video data in two directions of a road under the supplementary lighting of the supplementary lighting lamp, and recording videos; and sends it to the server side through the wireless transmission module.
In this embodiment, in dark weather such as night or dense fog, that is, when illumination data is less than or equal to a preset illumination threshold, infrared cameras arranged at the front end and the rear end of the traveling direction of the vehicle at the end are collected to shoot video images of the vehicle, and because the vehicle turns on a dipped headlight or a high beam and a tail light (a rear fog light or a brake light, a turn light) at night, the fog light can also be turned on in heavy fog weather, so that light in a high-definition video image shot by a high-definition camera at night has a great influence on the recognition and detection of the vehicle or lane lines; the infrared video data can effectively sense objects in the video data at night and prevent noise generated by automobile light in the video data from influencing vehicle detection on the convolutional neural network, when an analysis result is an abnormal traffic condition, a high-definition camera starting command and a light supplement lamp starting command are sent, the high-definition camera is started to collect high-definition video data under the light supplement of the light supplement lamp, video recording is carried out, and the detail data missing in the infrared video data are compensated.
The method comprises the steps that a collection end is arranged in the expressway tunnel at certain intervals, and a high-definition camera and an infrared camera are arranged at the front end and the rear end of the collection end in the expressway tunnel in the driving direction of road vehicles. The high-definition camera and the infrared camera which are arranged at the front end and the rear end of the running direction of a road vehicle at the collection end of the common highway are connected with the controller of the collection end, and the controller of the collection end is also connected with the light supplement lamp and the wireless transmission module which are arranged beside the high-definition camera.
As shown in fig. 4, an intelligent monitoring method for an expressway road is implemented in a controller of an acquisition end disposed in an expressway tunnel, and includes:
step S1: receiving infrared video data of two directions of a road collected by an infrared camera, preprocessing the data, and extracting video frames to obtain picture data;
step S2: inputting the picture data into a trained deep convolutional neural network for detection to obtain a vehicle detection result, a lane line detection result and an environment visibility detection result, and sending the vehicle detection result, the lane line detection result and the environment visibility detection result to a server side through a wireless transmission module;
step S3: analyzing abnormal traffic conditions according to the vehicle detection results and the lane line detection results to obtain and display graded early warning results or warning results, and actively early warning or warning the vehicle in real time; and sending the data to a server end through a wireless transmission module; the abnormal traffic conditions include vehicle violations, faults, and accidents;
when the abnormal traffic condition is analyzed, sending a high-definition camera starting command and a supplementary lighting lamp starting command, starting the high-definition camera to collect high-definition video data in two directions of a road under the supplementary lighting of the supplementary lighting lamp, and recording videos; and sending the data to a server end through a wireless transmission module;
step S4: according to the detection result of the environmental visibility, obtaining and displaying a grading guide result, actively guiding the vehicle in real time, and sending the grading guide result to a server end through a wireless transmission module;
when the abnormal traffic condition is analyzed, sending a high-definition camera starting command and a supplementary lighting lamp starting command, starting the high-definition camera to collect high-definition video data in two directions of a road under the supplementary lighting of the supplementary lighting lamp, and recording videos; and sends it to the server side through the wireless transmission module.
High definition digtal camera and the infrared camera that sets up to the vehicle direction of travel front and back end in the tunnel, adopt infrared camera to gather the infrared video data of road two directions throughout the day, object in the infrared video data can effectively be perceived to the infrared video data and prevent that the noise that car light produced carries out vehicle detection to the convolutional neural network in the video data, when analysis result is unusual traffic conditions, send high definition digtal camera start-up command and light filling lamp start-up command, start high definition digtal camera and gather high definition digtal video data under the light filling lamp light filling, carry out video recording, compensate the detailed data of infrared video data disappearance.
In this embodiment, one collection end is arranged every 1km in the highway tunnel. The wireless transmission module of the acquisition end arranged in the ordinary tunnel of the highway adopts a tunnel wireless communication technology, and the wireless communication in the tunnel is a conventional technical means of a person skilled in the art, and is not described in detail in this embodiment.
In this embodiment, the controllers of the acquisition end arranged on the ordinary road of the expressway and the acquisition end arranged in the tunnel of the expressway all adopt haisi intelligent AI chips, and specifically adopt Hi3519AVl 00.
In step S2 according to one or more embodiments of the present disclosure, the deep convolutional neural network uses an improved SSD network, and the specific step of obtaining the trained improved SSD network includes:
s2-1: receiving high-definition video data and infrared video data in two directions of a road, performing data preprocessing, and extracting video frames to obtain picture data; it should be noted that, in the early stage of training the improved SSD network, a large amount of high definition video data and infrared video data on the ordinary highway and in the tunnel are collected, and include high definition video data and infrared video data in the day, at night and under various weather conditions. In this embodiment, 30000 pieces of picture data are obtained by extracting video frames after data preprocessing.
In this embodiment, the high-definition video data and the infrared video data with different acquired sizes and frame rates are unified in size and frame rate.
S2-2: receiving a labeling instruction to label the picture data to form a training set, a verification set and a test set;
in this embodiment, labelImg is used to label picture data obtained after extracting a video frame, and the vehicles, lane lines and visibility true values in the picture are respectively labeled to form a data set, and 99.5% of the data in the data set is used as a training set, 0.4% of the data is used as a verification set, and 0.1% of the data is used as a test set.
S2-3: inputting the training set and the verification set into an improved SSD network for training and cross-verifying; the improved SSD network adopts a residual error network to extract features, the rear end of the residual error network is connected with the SSD network through a residual error module, and the rear end of the SSD network is connected with a deconvolution module;
in this embodiment, a residual network of Resnet-101 is selected to replace a VGG network in an original SSD network as a feature extraction network for feature extraction, a sixth convolutional layer, a seventh convolutional layer, an eighth convolutional layer, and a ninth convolutional layer are sequentially added after a fifth convolutional layer of the residual network of Resnet-101, where the sixth convolutional layer includes 104 convolutional kernels 10 × 10, the seventh convolutional layer includes 107 convolutional kernels 5 × 5, the eighth convolutional layer includes 110 convolutional kernels 3 × 3, the ninth convolutional layer includes 113 convolutional kernels 1 × 1, and a maximum posterior probability point estimation MAP in a gradient descent method is calculated, where MAP is an approximate bayesian estimation method for point estimation. MAP selects the point that maximizes the posterior probability as the optimal estimate, defined as follows:
the log (x | θ) term to the right of the above equation is just the log maximum likelihood part, while logp (θ) term is the prior probability part. The use of the prior probability component can serve to reduce the generalization error.
And (3) expanding the feature information on a small scale by adopting 512 2 x 2 deconvolution kernels in a deconvolution module, and performing element multiplication on the feature information and the convolution layer with the same feature map size of the previous convolution layer to further expand the size of the feature map.
S2-4: and optimizing the improved SSD network through the test set to obtain the trained improved SSD network. The method for training the improved SSD network is the same as the existing method for training the SSD network, and the method is not repeated in the invention.
In this embodiment, when there is no abnormal traffic condition, a frame extraction algorithm is used to extract video frames, and when the analysis result is an abnormal traffic condition, the video frames are extracted frame by frame. For example, every 10 frames are extracted for analysis, and the recognition result is obtained quickly.
And (4) inputting the picture data extracted in the step (S1) into a trained deep convolutional neural network for detection, obtaining a vehicle detection result, a lane line detection result and an environmental visibility detection result, and sending the vehicle detection result, the lane line detection result and the environmental visibility detection result to a server through a wireless transmission module for further post-processing by the server.
In step S3 of this embodiment, abnormal traffic condition analysis is performed according to the vehicle detection result and the lane line detection result, and a graded early warning result or warning result is obtained and displayed, so as to actively early warn or warn the vehicle in real time; and sending the data to a server end through a wireless transmission module; the abnormal traffic conditions include vehicle violations, faults, and accidents; in this embodiment, the license plate numbers in the picture are also detected, and correspond to the vehicle detection results one to one, and the license plate number detection is a mature technical scheme in the field, which is not described in detail in the present invention.
For example, when the distance between two or more vehicle detection frame lines is smaller than the preset distance, an early warning result is generated to prompt a vehicle driver to please drive carefully when the distance is too short; when the coincidence or the overlapping time of two or more than two vehicle detection frame lines is detected to be greater than the preset time, an accident warning result is generated, the accident warning result is directly displayed to prompt a driver of a rear vehicle to have the accident at the position, the warning result is sent to a server side, the server side is sent to a client side of the rear vehicle, and the accident careful driving in front of the rear vehicle is prompted.
The lane line detection frame and the vehicle detection frame sideline are combined to analyze vehicle violation, such as abnormal traffic conditions of illegal overtaking in a tunnel, and obtain and display a graded early warning result or warning result.
In step S4 of this embodiment, a hierarchical guidance result is obtained and displayed according to the environmental visibility detection result, and the vehicle is actively guided in real time and sent to the server via the wireless transmission module; and calculating a grading guide result suitable for the running speed according to the environment visibility detection result, displaying the grading guide result to actively guide the vehicle in real time, sending the grading guide result to a server side, sending the grading guide result to a client side of the rear vehicle, and prompting that the front of the rear vehicle is driven carefully in fog, even guiding the rear vehicle to run away from a high speed.
Example two
According to an aspect of one or more embodiments of the present disclosure, there is provided a computer-readable storage medium.
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to execute a method for intelligent monitoring of highway roads.
EXAMPLE III
According to an aspect of one or more embodiments of the present disclosure, there is provided a terminal device.
A terminal device comprising a processor and a computer-readable storage medium, the processor being configured to implement instructions; the computer readable storage medium is used for storing a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the intelligent monitoring method for the highway roads.
These computer-executable instructions, when executed in a device, cause the device to perform methods or processes described in accordance with various embodiments of the present disclosure.
In the present embodiments, a computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for performing various aspects of the present disclosure. The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described in this disclosure may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present disclosure may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry can execute computer-readable program instructions to implement aspects of the present disclosure by utilizing state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).
Example four
According to one aspect of one or more embodiments of the present disclosure, there is provided an intelligent monitoring apparatus for an expressway road.
An intelligent monitoring device for an expressway road is based on the intelligent monitoring method for the expressway road, and comprises the following steps:
the data acquisition module is configured to receive high-definition video data or infrared video data in two directions of a road at the same time, perform data preprocessing on the high-definition video data or the infrared video data, and extract video frames to obtain picture data;
the data detection module is configured to input the picture data into a trained deep convolutional neural network for detection to obtain a vehicle detection result, a lane line detection result and an environment visibility detection result;
the first data analysis module is configured to analyze abnormal traffic conditions according to the vehicle detection result and the lane line detection result, obtain and display graded early warning results or warning results, and actively early warn or warn the vehicle in real time; the abnormal traffic conditions include vehicle violations, faults, and accidents;
and the second data analysis module is configured to obtain and display a grading guide result according to the environment visibility detection result and actively guide the vehicle in real time.
The steps involved in the second, third and fourth embodiments correspond to the first embodiment of the method, and the detailed description thereof can be found in the relevant description of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media containing one or more sets of instructions; it should also be understood to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any of the methods of the present invention.
EXAMPLE five
According to one aspect of one or more embodiments of the present disclosure, there is provided an intelligent monitoring system for an expressway road.
An intelligent monitoring system for highway roads, the system comprising: the system comprises an acquisition end, a server end and a client end which are connected in sequence;
the acquisition end comprises an acquisition end arranged on a common expressway and an acquisition end arranged in a high-speed tunnel; the collection end realizes the intelligent monitoring method for the highway.
Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code that is executable by computing means, such that they are stored in memory means for execution by the computing means, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps of them are fabricated into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
The above one or more technical solutions have the following beneficial effects:
1. according to the intelligent monitoring method and system for the expressway road, the information acquisition and the information analysis and processing are unified by the acquisition end, the acquired video data are processed in real time through the AI chip, the processing result is directly displayed through the display device, a driver of a vehicle on the expressway is reminded in real time, and traffic hazard events caused by information lag are effectively avoided.
2. The invention discloses an intelligent monitoring method and system for an expressway road, which are characterized in that a vehicle detection result and a lane line detection result are obtained through deep learning of collected video data, abnormal traffic condition analysis is carried out according to the vehicle detection result and the lane line detection result, a graded early warning result or warning result is obtained and displayed, and real-time active early warning or warning is carried out on a vehicle; the display of the early warning result effectively realizes the active prevention of the vehicle violation behaviors and the traffic accidents before the occurrence; the display of the warning result can correct the violation behaviors in time, effectively prevent traffic accidents and play a good role in prompting the rear vehicles with the traffic accidents.
3. According to the intelligent monitoring method and system for the highway, the environmental visibility detection result is obtained through deep learning of collected video data, the grading guide result is obtained and displayed according to the environmental visibility detection result, the vehicle is actively guided in real time, the detection of the existing visibility detector on the environmental visibility can be cancelled at the collection end, and the cost is effectively saved.
4. According to the characteristics of an ordinary road and a tunnel of the highway, a collection end is respectively arranged on the ordinary highway to collect high-definition video data or infrared video data in two directions of the road, and a collection end is arranged in the highway to collect the high-definition video data or infrared video data in two directions of the tunnel road; adopt high definition digtal camera to gather high definition video data daytime to ordinary road, adopt infrared camera to gather infrared video data night, then adopt infrared camera to gather infrared video data throughout the day in the tunnel, infrared video data can effectively the perception object in the video data at night and prevent that the noise that car light produced carries out vehicle detection's influence to convolutional neural network in the video data, when analysis result is unusual traffic conditions, send high definition digtal camera start command and light filling lamp start command, start high definition digtal camera and gather high definition video data under the light filling lamp light filling, carry out video recording, compensate the detailed data of infrared video data disappearance.
5. According to the intelligent monitoring method and system for the highway road, disclosed by the invention, the acquisition end acquires high-definition video data or infrared video data in two directions of the road, and the unidirectional visual blind area is avoided by detecting the two video data in the vehicle driving direction and the vehicle driving reverse direction at the same time, so that the highway road is monitored in an all-around manner.
6. The invention discloses an intelligent monitoring method and system for an expressway road, which adopt an improved SSD network to simultaneously detect the visibility of vehicles, lane lines and the environment in video data, and the improved SSD network is additionally provided with a deconvolution module at the rear end of the original SSD network, thereby effectively expanding the situation information of low latitude, effectively improving the detection of a small-scale target of an expressway road video image perspective, adopting a residual error network and adding a residual error module before the classification regression of the SSD network, and using a deeper network to mention the characteristics of higher semantic information, thereby effectively improving the detection precision.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. An intelligent monitoring method for an expressway road is characterized by comprising the following steps:
simultaneously receiving high-definition video data or infrared video data in two directions of a road, performing data preprocessing on the high-definition video data or the infrared video data, and extracting video frames to obtain picture data;
inputting the picture data into a trained deep convolution neural network for detection to obtain a vehicle detection result, a lane line detection result and an environmental visibility detection result;
analyzing abnormal traffic conditions according to the vehicle detection results and the lane line detection results to obtain and display graded early warning results or warning results, and actively early warning or warning the vehicle in real time; the abnormal traffic conditions include vehicle violations, faults, and accidents;
and obtaining and displaying a grading guide result according to the environment visibility detection result, and actively guiding the vehicle in real time.
2. The intelligent monitoring method for the highway road as claimed in claim 1, wherein the method for simultaneously receiving the high definition video data or the infrared video data in two directions of the road comprises: simultaneously receives high-definition video data or infrared video data in two directions of the road collected by a collecting end arranged on a common expressway,
or simultaneously receiving high-definition video data or infrared video data in two directions of the tunnel road collected by a collecting end arranged in the high-speed tunnel.
3. The intelligent monitoring method for the highway road as claimed in claim 2, wherein in the method, the specific steps of simultaneously receiving high definition video data or infrared video data in two directions of the road collected by a collecting end arranged on a common highway, performing data preprocessing on the high definition video data or the infrared video data, and extracting video frames to obtain picture data comprise:
receiving illumination data collected by an illumination sensor, and judging the size of the illumination data and a preset illumination threshold value;
when the illumination data is larger than a preset illumination threshold value, only sending a high-definition camera starting command to start a high-definition camera to collect high-definition video data in two directions of a road, receiving the high-definition video data in the two directions of the road, performing data preprocessing, and extracting video frames to obtain picture data;
when the illumination data is less than or equal to a preset illumination threshold value, sending an infrared camera starting command to start an infrared camera to collect infrared video data in two directions of a road, receiving the infrared video data in the two directions of the road, performing data preprocessing, and extracting a video frame to obtain picture data; and when the abnormal traffic condition is analyzed, sending a high-definition camera starting command and a supplementary lighting lamp starting command, starting the high-definition camera to collect high-definition video data in two directions of the road under the supplementary lighting of the supplementary lighting lamp, and recording the video.
4. The intelligent monitoring method for the highway road as claimed in claim 1, wherein in the method, the specific steps of simultaneously receiving high definition video data or infrared video data in two directions of the road collected by a collecting end arranged in the highway tunnel, performing data preprocessing on the high definition video data or the infrared video data, and extracting video frames to obtain picture data comprise:
simultaneously receiving infrared video data collected by infrared cameras in two directions of a road, performing data preprocessing on the infrared video data, and extracting video frames to obtain picture data; and when the analysis result is an abnormal traffic condition, sending a starting command of the two-direction high-definition camera on the road and a starting command of the light supplement lamp, starting the two-direction high-definition camera on the road to acquire high-definition video data under the light supplement of the light supplement lamp, and recording the video.
5. The intelligent monitoring method for the highway road according to claim 1, wherein in the method, the deep convolutional neural network adopts an improved SSD network, and the specific step of obtaining the trained improved SSD network comprises:
receiving high-definition video data and infrared video data in two directions of a road, performing data preprocessing, and extracting video frames to obtain picture data;
receiving a labeling instruction to label the picture data to form a training set, a verification set and a test set;
inputting the training set and the verification set into an improved SSD network for training and cross-verifying; the improved SSD network adopts a residual error network to extract features, the rear end of the residual error network is connected with the SSD network through a residual error module, and the rear end of the SSD network is connected with a deconvolution module;
and optimizing the improved SSD network through the test set to obtain the trained improved SSD network.
6. The intelligent monitoring method for expressway roads as recited in claim 1, wherein in the method, when there is no abnormal traffic condition, a frame extraction algorithm is used to extract video frames, and when the analysis result is an abnormal traffic condition, the video frames are extracted frame by frame.
7. A computer-readable storage medium having stored thereon a plurality of instructions, wherein the instructions are adapted to be loaded by a processor of a terminal device and to perform a method for intelligent monitoring of highway roads according to any one of claims 1-6.
8. A terminal device comprising a processor and a computer-readable storage medium, the processor being configured to implement instructions; a computer-readable storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform a method for intelligent monitoring of highway roads according to any one of claims 1-6.
9. An intelligent monitoring device for highway roads, based on the intelligent monitoring method for highway roads as claimed in any one of claims 1-6, comprising:
the data acquisition module is configured to receive high-definition video data or infrared video data in two directions of a road at the same time, perform data preprocessing on the high-definition video data or the infrared video data, and extract video frames to obtain picture data;
the data detection module is configured to input the picture data into a trained deep convolutional neural network for detection to obtain a vehicle detection result, a lane line detection result and an environment visibility detection result;
the first data analysis module is configured to analyze abnormal traffic conditions according to the vehicle detection result and the lane line detection result, obtain and display graded early warning results or warning results, and actively early warn or warn the vehicle in real time; the abnormal traffic conditions include vehicle violations, faults, and accidents;
and the second data analysis module is configured to obtain and display a grading guide result according to the environment visibility detection result and actively guide the vehicle in real time.
10. An intelligent monitoring system for highway roads, comprising: the system comprises an acquisition end, a server end and a client end which are connected in sequence;
the acquisition end comprises an acquisition end arranged on a common expressway and an acquisition end arranged in a high-speed tunnel; the collection end realizes the intelligent expressway road monitoring method as claimed in any one of claims 1 to 6, and sends the vehicle detection result, the lane line detection result and the environmental visibility detection result to the server end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910929511.4A CN110619747A (en) | 2019-09-27 | 2019-09-27 | Intelligent monitoring method and system for highway road |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910929511.4A CN110619747A (en) | 2019-09-27 | 2019-09-27 | Intelligent monitoring method and system for highway road |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110619747A true CN110619747A (en) | 2019-12-27 |
Family
ID=68924732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910929511.4A Pending CN110619747A (en) | 2019-09-27 | 2019-09-27 | Intelligent monitoring method and system for highway road |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110619747A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111428752A (en) * | 2020-02-25 | 2020-07-17 | 南通大学 | Visibility detection method based on infrared image |
| CN111968378A (en) * | 2020-07-07 | 2020-11-20 | 浙江大华技术股份有限公司 | Motor vehicle red light running snapshot method and device, computer equipment and storage medium |
| CN112383605A (en) * | 2020-11-09 | 2021-02-19 | 广西信路威科技发展有限公司 | Remote maintenance system and maintenance method for expressway monitoring equipment |
| CN112712124A (en) * | 2020-12-31 | 2021-04-27 | 山东奥邦交通设施工程有限公司 | Multi-module cooperative object recognition system and method based on deep learning |
| CN112802338A (en) * | 2020-12-31 | 2021-05-14 | 山东奥邦交通设施工程有限公司 | Expressway real-time early warning method and system based on deep learning |
| CN112863100A (en) * | 2020-12-31 | 2021-05-28 | 山东奥邦交通设施工程有限公司 | Intelligent construction safety monitoring system and method |
| CN112906664A (en) * | 2021-04-06 | 2021-06-04 | 昭通亮风台信息科技有限公司 | Neural network-based method and system for detecting abnormal events in tunnel |
| CN113076566A (en) * | 2021-04-26 | 2021-07-06 | 深圳市三旺通信股份有限公司 | Display content detection method, device, computer program product and storage medium |
| CN113128382A (en) * | 2021-04-06 | 2021-07-16 | 青岛以萨数据技术有限公司 | Method and system for detecting lane line at traffic intersection |
| CN114202914A (en) * | 2021-11-24 | 2022-03-18 | 黑龙江工程学院 | Close-range image traffic violation and road condition photogrammetry system based on Wifi signal |
| CN114495493A (en) * | 2022-01-05 | 2022-05-13 | 贵州银智科技发展有限公司 | Highway tunnel vehicle abnormal driving warning and lighting control system |
| CN114743380A (en) * | 2022-03-04 | 2022-07-12 | 中铁发展投资有限公司 | Method for detecting traffic flow data quality of highway |
| CN116597404A (en) * | 2023-05-06 | 2023-08-15 | 浙江大学 | Sustainable road abnormality detection method and system based on multi-source sensor fusion |
| WO2023241536A1 (en) * | 2022-06-13 | 2023-12-21 | Anlyvis Limited | A system and method for detecting traffic events |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101105892A (en) * | 2007-07-30 | 2008-01-16 | 深圳市融合视讯科技有限公司 | Vehicle traffic accident automatic detection method |
| CN102231231A (en) * | 2011-06-16 | 2011-11-02 | 同济大学 | Area road network traffic safety situation early warning system and method thereof |
| CN106611162A (en) * | 2016-12-20 | 2017-05-03 | 西安电子科技大学 | Method for real-time detection of road vehicle based on deep learning SSD frame |
| CN106935035A (en) * | 2017-04-07 | 2017-07-07 | 西安电子科技大学 | Parking offense vehicle real-time detection method based on SSD neutral nets |
| CN108492584A (en) * | 2018-03-19 | 2018-09-04 | 中国电子科技集团公司第三十八研究所 | A kind of traffic accident alarm method and device based on wisdom lamp stand |
| CN109756706A (en) * | 2018-12-17 | 2019-05-14 | 珠海市国宏网络科技有限公司 | A kind of distributed video monitoring analysis system and data transmission method |
| CN110033650A (en) * | 2019-05-23 | 2019-07-19 | 范学超 | A kind of highway light warning system |
| CN209134509U (en) * | 2018-08-28 | 2019-07-19 | 深圳市必特佳科技有限公司 | A kind of infrared peccancy detection integrated camera |
| WO2019145018A1 (en) * | 2018-01-23 | 2019-08-01 | Siemens Aktiengesellschaft | System, device and method for detecting abnormal traffic events in a geographical location |
-
2019
- 2019-09-27 CN CN201910929511.4A patent/CN110619747A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101105892A (en) * | 2007-07-30 | 2008-01-16 | 深圳市融合视讯科技有限公司 | Vehicle traffic accident automatic detection method |
| CN102231231A (en) * | 2011-06-16 | 2011-11-02 | 同济大学 | Area road network traffic safety situation early warning system and method thereof |
| CN106611162A (en) * | 2016-12-20 | 2017-05-03 | 西安电子科技大学 | Method for real-time detection of road vehicle based on deep learning SSD frame |
| CN106935035A (en) * | 2017-04-07 | 2017-07-07 | 西安电子科技大学 | Parking offense vehicle real-time detection method based on SSD neutral nets |
| WO2019145018A1 (en) * | 2018-01-23 | 2019-08-01 | Siemens Aktiengesellschaft | System, device and method for detecting abnormal traffic events in a geographical location |
| CN108492584A (en) * | 2018-03-19 | 2018-09-04 | 中国电子科技集团公司第三十八研究所 | A kind of traffic accident alarm method and device based on wisdom lamp stand |
| CN209134509U (en) * | 2018-08-28 | 2019-07-19 | 深圳市必特佳科技有限公司 | A kind of infrared peccancy detection integrated camera |
| CN109756706A (en) * | 2018-12-17 | 2019-05-14 | 珠海市国宏网络科技有限公司 | A kind of distributed video monitoring analysis system and data transmission method |
| CN110033650A (en) * | 2019-05-23 | 2019-07-19 | 范学超 | A kind of highway light warning system |
Non-Patent Citations (1)
| Title |
|---|
| 李珊珊: ""基于深度学习的交通场景多目标检测"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111428752A (en) * | 2020-02-25 | 2020-07-17 | 南通大学 | Visibility detection method based on infrared image |
| CN111428752B (en) * | 2020-02-25 | 2023-10-31 | 南通大学 | Visibility detection method based on infrared image |
| CN111968378A (en) * | 2020-07-07 | 2020-11-20 | 浙江大华技术股份有限公司 | Motor vehicle red light running snapshot method and device, computer equipment and storage medium |
| CN112383605A (en) * | 2020-11-09 | 2021-02-19 | 广西信路威科技发展有限公司 | Remote maintenance system and maintenance method for expressway monitoring equipment |
| CN112863100B (en) * | 2020-12-31 | 2022-09-06 | 山东奥邦交通设施工程有限公司 | Intelligent construction safety monitoring system and method |
| CN112712124A (en) * | 2020-12-31 | 2021-04-27 | 山东奥邦交通设施工程有限公司 | Multi-module cooperative object recognition system and method based on deep learning |
| CN112863100A (en) * | 2020-12-31 | 2021-05-28 | 山东奥邦交通设施工程有限公司 | Intelligent construction safety monitoring system and method |
| CN112802338A (en) * | 2020-12-31 | 2021-05-14 | 山东奥邦交通设施工程有限公司 | Expressway real-time early warning method and system based on deep learning |
| CN112906664A (en) * | 2021-04-06 | 2021-06-04 | 昭通亮风台信息科技有限公司 | Neural network-based method and system for detecting abnormal events in tunnel |
| CN113128382A (en) * | 2021-04-06 | 2021-07-16 | 青岛以萨数据技术有限公司 | Method and system for detecting lane line at traffic intersection |
| CN112906664B (en) * | 2021-04-06 | 2023-02-24 | 昭通亮风台信息科技有限公司 | Neural network-based method and system for detecting abnormal events in tunnel |
| CN113076566A (en) * | 2021-04-26 | 2021-07-06 | 深圳市三旺通信股份有限公司 | Display content detection method, device, computer program product and storage medium |
| CN113076566B (en) * | 2021-04-26 | 2024-02-27 | 深圳市三旺通信股份有限公司 | Display content detection method, apparatus, computer program product, and storage medium |
| CN114202914A (en) * | 2021-11-24 | 2022-03-18 | 黑龙江工程学院 | Close-range image traffic violation and road condition photogrammetry system based on Wifi signal |
| CN114495493A (en) * | 2022-01-05 | 2022-05-13 | 贵州银智科技发展有限公司 | Highway tunnel vehicle abnormal driving warning and lighting control system |
| CN114743380A (en) * | 2022-03-04 | 2022-07-12 | 中铁发展投资有限公司 | Method for detecting traffic flow data quality of highway |
| WO2023241536A1 (en) * | 2022-06-13 | 2023-12-21 | Anlyvis Limited | A system and method for detecting traffic events |
| CN116597404A (en) * | 2023-05-06 | 2023-08-15 | 浙江大学 | Sustainable road abnormality detection method and system based on multi-source sensor fusion |
| CN116597404B (en) * | 2023-05-06 | 2024-04-09 | 浙江大学 | Sustainable road abnormality detection method and system based on multi-source sensor fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110619747A (en) | Intelligent monitoring method and system for highway road | |
| US10977567B2 (en) | Automated vehicular accident detection | |
| US20130093895A1 (en) | System for collision prediction and traffic violation detection | |
| US11836985B2 (en) | Identifying suspicious entities using autonomous vehicles | |
| US11380105B2 (en) | Identification and classification of traffic conflicts | |
| CN109345829B (en) | Unmanned vehicle monitoring method, device, equipment and storage medium | |
| CN110738842A (en) | Accident responsibility division and behavior analysis method, device, equipment and storage medium | |
| US20200074326A1 (en) | Systems and methods for classifying driver behavior | |
| KR20100119476A (en) | An outomatic sensing system for traffic accident and method thereof | |
| CN105355039A (en) | Road condition information processing method and equipment | |
| US20220139090A1 (en) | Systems and methods for object monitoring | |
| CN104282154A (en) | Vehicle overload monitoring system and method | |
| CN113012436B (en) | Road monitoring method and device and electronic equipment | |
| CA3056611A1 (en) | Automatic warning generation system intended for the users of a road | |
| CN114387785A (en) | Safety management and control method and system based on intelligent highway and storable medium | |
| CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
| CN113936465A (en) | Traffic incident detection method and device | |
| KR102039723B1 (en) | Vehicle's behavior analyzing system using aerial photo and analyzing method using the same | |
| Detzer et al. | Analysis of traffic safety for cyclists: The automatic detection of critical traffic situations for cyclists | |
| CN113408319A (en) | Urban road abnormity perception processing method, device, system and storage medium | |
| CN109895694B (en) | Lane departure early warning method and device and vehicle | |
| Panda et al. | Application of Image Processing In Road Traffic Control | |
| KR102618451B1 (en) | Traffic system capable of verifying display of enforcement standard information and method for providing verification information | |
| CN113920722B (en) | Intersection passing state obtaining method and device, electronic equipment and storage medium | |
| Gupta et al. | Traffic Management system using Deep Learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191227 |