CN113963243A - Black smoke vehicle detection method based on artificial intelligence - Google Patents
Black smoke vehicle detection method based on artificial intelligence Download PDFInfo
- Publication number
- CN113963243A CN113963243A CN202010636859.7A CN202010636859A CN113963243A CN 113963243 A CN113963243 A CN 113963243A CN 202010636859 A CN202010636859 A CN 202010636859A CN 113963243 A CN113963243 A CN 113963243A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- black smoke
- smoke vehicle
- artificial intelligence
- method based
- 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.)
- Withdrawn
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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a black smoke vehicle detection method based on artificial intelligence, which comprises the steps of training a model through a big data deep learning framework, judging a black smoke value of a vehicle tail area by adopting a black smoke vehicle Ringelmann blackness model, and tracking a vehicle to perform secondary identification and confirmation; the invention has high detection efficiency and accurate detection, can complete all the work of the snapshot of the black cigarette vehicle, improves the identification accuracy of the black cigarette vehicle, has higher identification reliability, and further improves the accuracy of the judgment by a secondary judgment method.
Description
Technical Field
The invention relates to the technical field of transportation safety management, in particular to a black smoke vehicle detection method based on artificial intelligence.
Background
The black cigarette car is used as an important source for generating PM2.5 and one of main pioneers causing haze weather, the life of people is influenced, and at the present stage, the black cigarette car inspection is mainly performed in a manual inspection mode, so that labor consumption and efficiency are low; some economically developed areas adopt laser remote sensing monitoring on part of road sections, and the method has high cost investment and is not suitable for large-area popularization.
At present, detection and identification of exhaust smoke emission of black smoke vehicles are paid more attention in the fields of artificial intelligent traffic supervision and environment monitoring. Currently applicable to many scenarios such as: (1) a road intelligent environment monitoring system; (2) a motor vehicle exhaust over-standard emission monitoring system and the like; (3) automatic snapshot system of road. The current domestic supervision mode to the black cigarette car is mainly through way inspection and smoke sensing, the mode of the compound detector of sensitization, set up the checkpoint by the environmental protection department and carry out the tail gas inspection to some suspicious vehicles, under the current situation that motor vehicle reserves the volume and increases rapidly, the method is executed and is had the inefficiency too low, the detector detects the black cigarette that the motor vehicle discharged through black cigarette particle and concentration, can only play the detection effect in the place nearer from black cigarette car tail gas vent, to the regional great place in traffic road, the reliability of its detection is lower, can't carry out supervision and detection effect effectively. Therefore, an intelligent method for detecting black smoke cars is urgently needed to solve the problems.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides a black smoke vehicle detection method based on artificial intelligence.
A black smoke vehicle detection method based on artificial intelligence comprises the following steps:
s1: collecting a plurality of vehicle images, carrying out sample marking, and constructing a training sample;
s2: carrying out image processing on the training sample, and constructing a training model of a deep learning framework;
s3: detecting a black smoke vehicle, acquiring a target vehicle image, judging the Ringelmann blackness of a vehicle tail area by adopting a Ringelmann blackness model of the black smoke vehicle, if the Ringelmann blackness is smaller than a set threshold value, judging the vehicle to be a non-black smoke vehicle, otherwise, performing fine judgment, and tracking the vehicle after roughly judging that the vehicle is possibly a black smoke vehicle type;
s4: and analyzing the multi-frame vehicle image, performing secondary confirmation on the black smoke vehicle by adopting a black smoke vehicle Ringelmann blackness model, and judging whether the target vehicle is the black smoke vehicle or a non-black smoke vehicle.
Further, when S2 is carried out, firstly, the target sample is analyzed by adopting big data, the vehicle is detected, firstly, the vehicle type of the non-black smoke vehicle is eliminated, the possible vehicle type of the black smoke vehicle is analyzed, and the deep convolution neural network is adopted for training to obtain a training model.
Further, the position information of the camera is superposed and labeled on the vehicle image of the black smoke vehicle determined secondarily, and a license plate recognition model is called to recognize the license plate in the image.
Further, the system inquires the basic information of the vehicle in a vehicle information base according to the identification result, summarizes the basic information of the vehicle, the picture information of the passing vehicle and the brief video information, and sends the alarm information to the handheld terminal through the alarm server.
According to the black smoke vehicle detection method based on artificial intelligence, provided by the invention, a black smoke vehicle snapshot method which can adapt to various complex environment conditions is developed by fully utilizing and improving algorithms in the fields of existing target detection, target tracking and the like, the detection efficiency is high, the detection is accurate, and all work of black smoke vehicle snapshot can be completed; the method has the advantages that the model is trained through a deep learning framework, the black smoke value of the tail area of the vehicle is judged by adopting the black smoke vehicle Ringelmann blackness model, the vehicle is tracked to carry out secondary recognition and confirmation, the recognition accuracy of the black smoke vehicle can be improved, the recognition reliability is higher, and the accuracy of judgment is further improved through a secondary judgment method.
Detailed Description
The present invention will be further illustrated with reference to the following specific examples.
The invention provides a black smoke vehicle detection method based on artificial intelligence, which comprises the following steps:
a black smoke vehicle detection method based on artificial intelligence comprises the following steps:
s1: collecting a plurality of vehicle images, carrying out sample marking, and constructing a training sample;
s2: carrying out image processing on the training sample, and constructing a training model of a deep learning framework;
s3: detecting a black smoke vehicle, acquiring a target vehicle image, judging the Ringelmann blackness of a vehicle tail area by adopting a Ringelmann blackness model of the black smoke vehicle, if the Ringelmann blackness is smaller than a set threshold value, judging the vehicle to be a non-black smoke vehicle, otherwise, performing fine judgment, tracking the vehicle after the coarse judgment is possible to be a black smoke vehicle type, and if the Ringelmann blackness is smaller than the set threshold value, not transmitting a signal outwards;
s4: and analyzing the multi-frame vehicle image, performing secondary confirmation on the black smoke vehicle by adopting a black smoke vehicle Ringelmann blackness model, and judging whether the target vehicle is the black smoke vehicle or a non-black smoke vehicle.
Preferably, in S2, the target sample is analyzed by using the big data, the vehicle is detected, the vehicle model of the non-black smoke vehicle is excluded, the possible vehicle model of the black smoke vehicle is analyzed, and the deep convolutional neural network is used for training to obtain the training model.
Preferably, the position information of the camera is superposed and labeled on the vehicle image of the secondarily confirmed black smoke vehicle, and a license plate recognition model is called to recognize the license plate in the image.
Preferably, the system queries the basic information of the vehicle in the vehicle information base according to the recognition result, summarizes the basic information of the vehicle, the picture information of the passing vehicle and the brief video information, and sends the alarm information to the handheld terminal through the alarm server.
According to the black smoke vehicle detection method based on artificial intelligence, provided by the invention, a black smoke vehicle snapshot method which can adapt to various complex environment conditions is developed by fully utilizing and improving algorithms in the fields of existing target detection, target tracking and the like, the detection efficiency is high, the detection is accurate, and all work of black smoke vehicle snapshot can be completed; the method has the advantages that the model is trained through a deep learning framework, the black smoke value of the tail area of the vehicle is judged by adopting the black smoke vehicle Ringelmann blackness model, the vehicle is tracked to carry out secondary recognition and confirmation, the recognition accuracy of the black smoke vehicle can be improved, the recognition reliability is higher, and the accuracy of judgment is further improved through a secondary judgment method.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (4)
1. A black smoke vehicle detection method based on artificial intelligence is characterized by comprising the following steps:
s1: collecting a plurality of vehicle images, carrying out sample marking, and constructing a training sample;
s2: carrying out image processing on the training sample, and constructing a training model of a deep learning framework;
s3: detecting a black smoke vehicle, acquiring a target vehicle image, judging the Ringelmann blackness of a vehicle tail area by adopting a Ringelmann blackness model of the black smoke vehicle, if the Ringelmann blackness is smaller than a set threshold value, judging the vehicle to be a non-black smoke vehicle, otherwise, performing fine judgment, and tracking the vehicle after roughly judging that the vehicle is possibly a black smoke vehicle type;
s4: and analyzing the multi-frame vehicle image, performing secondary confirmation on the black smoke vehicle by adopting a black smoke vehicle Ringelmann blackness model, and judging whether the target vehicle is the black smoke vehicle or a non-black smoke vehicle.
2. The black smoke vehicle detection method based on artificial intelligence of claim 1, wherein in the step of S2, the target sample is first analyzed by using big data to detect the vehicle, the vehicle type of the non-black smoke vehicle is first excluded, the possible vehicle type of the black smoke vehicle is analyzed, and a deep convolutional neural network is used for training to obtain a training model.
3. The black smoke vehicle detection method based on artificial intelligence of claim 1, wherein for a vehicle image secondarily confirmed as a black smoke vehicle, camera position information is added and labeled to the image, and a license plate recognition model is called to recognize a license plate in the image.
4. The black smoke vehicle detection method based on artificial intelligence of claim 3, wherein the system queries basic information of the vehicle in a vehicle information base according to the recognition result, summarizes the basic information of the vehicle, picture information of the passing vehicle and brief video information, and sends alarm information to the handheld terminal through the alarm server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010636859.7A CN113963243A (en) | 2020-07-04 | 2020-07-04 | Black smoke vehicle detection method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010636859.7A CN113963243A (en) | 2020-07-04 | 2020-07-04 | Black smoke vehicle detection method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113963243A true CN113963243A (en) | 2022-01-21 |
Family
ID=79459204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010636859.7A Withdrawn CN113963243A (en) | 2020-07-04 | 2020-07-04 | Black smoke vehicle detection method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113963243A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114723693A (en) * | 2022-03-28 | 2022-07-08 | 浙江十翼科技有限公司 | Method for movably detecting tail gas of motor vehicle |
-
2020
- 2020-07-04 CN CN202010636859.7A patent/CN113963243A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114723693A (en) * | 2022-03-28 | 2022-07-08 | 浙江十翼科技有限公司 | Method for movably detecting tail gas of motor vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110261436B (en) | Rail fault detection method and system based on infrared thermal imaging and computer vision | |
| CN106652468B (en) | The detection and from vehicle violation early warning alarm set and method in violation of rules and regulations of road vehicle front truck | |
| CN109409337B (en) | Muck vehicle feature identification method based on convolutional neural network | |
| CN107478590A (en) | A kind of method of combination motor vehicle intelligent vision identification and remote exhaust emission detection | |
| CN105809679A (en) | Mountain railway side slope rockfall detection method based on visual analysis | |
| CN106331636A (en) | Intelligent video monitoring system and method of oil pipelines based on behavioral event triggering | |
| CN110738857A (en) | vehicle violation evidence obtaining method, device and equipment | |
| CN113657305B (en) | Video-based intelligent detection method for black smoke vehicle and ringeman blackness level | |
| CN111444843B (en) | Multimode driver and vehicle illegal behavior monitoring method and system | |
| CN113822285A (en) | Vehicle illegal parking identification method for complex application scene | |
| Hasegawa et al. | Type classification, color estimation, and specific target detection of moving targets on public streets | |
| CN111914773A (en) | Equipment and method for capturing illegal boarding and alighting of passengers | |
| CN113963243A (en) | Black smoke vehicle detection method based on artificial intelligence | |
| Zhang et al. | Recognition of Front-Vehicle Taillights Based on YOLOv5s | |
| CN111862621A (en) | Intelligent snapshot system of multi-type adaptive black cigarette vehicle | |
| CN114973156B (en) | Night muck car detection method based on knowledge distillation | |
| CN116665385A (en) | Microwave vibration intrusion detection method, device, equipment and medium based on machine vision | |
| CN116645831A (en) | Traffic blind area detection and early warning system | |
| CN105206060A (en) | Vehicle type recognition device and method based on SIFT characteristics | |
| CN112633163B (en) | Detection method for realizing illegal operation vehicle detection based on machine learning algorithm | |
| CN115423845A (en) | Target object detection and tracking method fusing millimeter wave radar and camera | |
| CN114973169A (en) | Vehicle classification counting method and system based on multi-target detection and tracking | |
| CN114693722A (en) | Vehicle driving behavior detection method, detection device and detection equipment | |
| CN113299024A (en) | Road operation safety protection system and method based on automatic perception | |
| CN109145732B (en) | Black smoke vehicle detection method based on Gabor projection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220121 |
|
| WW01 | Invention patent application withdrawn after publication |