CN114613132B - Illegal parking detection system based on visual identification - Google Patents
Illegal parking detection system based on visual identification Download PDFInfo
- Publication number
- CN114613132B CN114613132B CN202210208559.8A CN202210208559A CN114613132B CN 114613132 B CN114613132 B CN 114613132B CN 202210208559 A CN202210208559 A CN 202210208559A CN 114613132 B CN114613132 B CN 114613132B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- license plate
- traffic flow
- parking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of intelligent traffic, in particular to a system for detecting illegal parking based on visual identification, which comprises the following steps: s100: acquiring acquisition information uploaded by a vehicle-mounted terminal, wherein the acquisition information comprises image information and position information; s200: identifying road identification, vehicle position, vehicle information and parking state in the image information; s300: judging whether illegal parking behaviors exist or not according to the vehicle position, the parking state and the road identification; s400: and when the illegal parking behavior is judged to exist, sending the image information, the position information, the vehicle information and the judgment result to the supervision platform. The system for detecting illegal parking based on visual identification can realize detection of illegal parking in the whole road section and improve the processing efficiency of illegal parking behaviors.
Description
Technical Field
The invention relates to the technical field of intelligent traffic, in particular to a system for detecting illegal parking based on visual identification.
Background
The quantity of automobile reserves in cities is increased sharply, the corresponding parking spaces are relatively deficient in growth, the daily parking requirements cannot be met, particularly in busy areas and road sections, land resources are short, few and few parking spaces exist, the density of vehicles is high, under the condition, a plurality of vehicle owners stop the automobiles on two sides of a road, the road is narrow, the driving of the vehicles is influenced, particularly in peak periods, the traffic is seriously congested, and even vehicle scratching and collision accidents can be caused.
The traditional law enforcement scheme for illegal parking detection mainly comprises manual law enforcement and snapshot law enforcement, wherein the manual law enforcement needs traffic law enforcement personnel to go to a field for patrol treatment, and the problems of low efficiency, high cost, poor real-time performance and the like exist. The candid photograph law enforcement mainly utilizes the camera that crossing or forbidden district set up to detect the discernment to the action of stopping violating, has solved artifical law enforcement inefficiency problem to a certain extent, but some vehicles can stop in the unable position of shooing of control, and this scheme has the coverage rate low, can't realize the problem that the whole road section detected, also can have simultaneously because shoot unclear, and the license plate that leads to discerns mistake, wrong report scheduling problem.
Disclosure of Invention
The invention aims to provide a system for detecting illegal parking based on visual identification, which can realize detection of illegal parking in all road sections and improve the processing efficiency of illegal parking behaviors.
The application provides the following technical scheme:
the system for detecting illegal parking based on visual identification comprises the following steps:
s100: acquiring acquisition information uploaded by a vehicle-mounted terminal, wherein the acquisition information comprises image information and position information;
s200: identifying road identification, vehicle position, vehicle information and parking state in the image information;
s300: judging whether illegal parking behaviors exist or not according to the vehicle position, the parking state and the road identification;
s400: and when the illegal parking behavior is judged to exist, sending the image information, the position information, the vehicle information and the judgment result to the supervision platform.
The technical scheme of the invention has the beneficial effects that: according to the technical scheme, the vehicle-mounted terminals carried on the vehicles can be used for fully and timely collecting the image information of each road, judging whether the illegal parking behaviors and the illegal parking vehicles exist or not through identifying the image information, further realizing illegal parking detection on the whole road section of the road, and after the illegal parking behaviors are identified, the image information can be timely sent to the supervision platform, so that the illegal parking behaviors can be processed as soon as possible. Meanwhile, the corresponding image information can be used as law enforcement evidence; compared with the prior art, the technical scheme of the application can realize illegal parking monitoring of the whole road section, improve detection accuracy, and ensure that illegal parking behaviors are processed as soon as possible and relevant information is recorded.
Further, the S400 further includes:
s401: and recording the times of recognizing the existence of the illegal parking behaviors of the vehicles corresponding to the license plates by the acquired information corresponding to the vehicle-mounted terminals, and if the times are greater than a preset value, judging that the illegal parking behaviors exist in the vehicles corresponding to the license plates.
The illegal action is judged by overlapping times, so that the identification accuracy can be improved, and single false alarm is avoided.
Further, the vehicle information includes a license plate number, and the S200 further includes:
s201: identifying a license plate number of the vehicle;
s202: calling a corresponding road section intersection monitoring video according to the position information, identifying license plate numbers of vehicles in the monitoring video, judging whether vehicles with the license plate numbers enter or exit the intersection in S201, and judging that the license plate identification is correct if the vehicles with the license plate numbers enter or exit the intersection;
if not, calculating the similarity between the license plate number of the vehicle in the intersection monitoring video and the license plate number identified in S201, selecting the license plate number larger than the preset value as a candidate according to the similarity, acquiring the vehicle characteristic of the vehicle corresponding to the candidate license plate number, judging whether the vehicle characteristic is matched with the vehicle characteristic of the vehicle, and if so, taking the candidate license plate number as the license plate number of the vehicle.
The accuracy of license plate number identification can be ensured through comparison and judgment between the license plate numbers shot by intersection monitoring and the license plate numbers in the image information.
Further, the S202 further includes:
s2021: if the license plate number with the similarity larger than the preset value or the vehicle characteristics are not matched, keeping the license plate number identified in the S201, and marking the vehicle as a vehicle to be confirmed;
s2022: recording the times of identifying the license plate number corresponding to the vehicle to be confirmed by the acquisition information corresponding to each vehicle-mounted terminal, if the times is greater than a preset value, judging that the license plate number is the license plate number of the vehicle, and marking the vehicle as the confirmed vehicle.
And marking the vehicles which are not accurately identified to avoid false alarm.
Further, the S300 further includes:
if the vehicle corresponding to the license plate number is not the vehicle to be confirmed, judging whether the license plate number is judged to have illegal parking behaviors within a preset time range, and if so, skipping the detection of the vehicle. And repeated detection is avoided, and the processing efficiency is improved.
Further, the S400 further includes:
s402: acquiring traffic flow information of an inlet and an outlet of a road where the vehicle-mounted terminal is located according to the acquisition information uploaded by the vehicle-mounted terminal;
s403: matching the traffic flow information of the road exit of the data that the vehicle-mounted terminal is located on the road without the illegal vehicle and the entrance traffic flow information is similar to the traffic flow information in S402 from the historical data;
s404: judging the influence degree of the illegal parking behavior according to the traffic flow information of the exit under the condition that the vehicle does not break and the traffic flow information of the exit under the condition that the vehicle breaks;
s405: the importance of the information sent to the supervisory platform is marked according to the degree of influence. By collecting information, the traffic flow information is detected and analyzed, the influence condition of the illegal parking vehicle on the traffic flow can be accurately judged by analyzing the change condition of the traffic flow information, so that law enforcement personnel can preferentially handle urgent illegal parking behaviors, and the scientificity of law enforcement arrangement is improved.
Further, the method also comprises S500: and acquiring the contact way corresponding to the license plate number according to the feedback of the supervision platform, and sending notification information to the corresponding contact way.
Further, the step S200 further includes identifying a parking lot identifier in the image information and an empty parking space in the roadside parking lot; the notification information includes empty space information and surrounding parking lot information. By means of reminding the car owner of the empty parking spaces around the car owner and the parking lot information, the probability of illegal parking behavior is reduced.
Further, the method also comprises the step S600: and recording the number of illegal parking times of each license plate number, and sending empty parking space information and surrounding parking lot information to the vehicle owner when the number of illegal parking times is greater than a preset value and the intersection monitors and monitors the corresponding license plate number. The vehicle owner is prevented from violating the parking on the corresponding road again, and the probability of occurrence of the violating parking behaviors is reduced.
Further, the S400 further includes:
s407: intercepting image segments corresponding to the illegal operation from image information uploaded by each vehicle-mounted terminal to obtain an evidence image list;
s408: according to the evidence image list, identifying and classifying the shooting angles of the image segments;
s409: and calculating the distance between the position of the corresponding vehicle-mounted terminal in the evidence image list and the illegal vehicle, analyzing the definition of the content of the image fragment, weighting the distance and the definition to be used as the validity score of the image fragment, and sequencing the image fragments classified at each shooting angle according to the validity score.
S703: and pushing the classified and sequenced evidence image list to a supervision platform.
The image information uploaded by the vehicle-mounted terminal is used as evidence for traffic administration and law enforcement, and meanwhile, classification according to all angles and sorting according to effectiveness grading are beneficial to law enforcement personnel to quickly judge illegal behaviors.
Drawings
Fig. 1 is a flow chart of the system for detecting illegal parking based on visual identification.
Detailed Description
The technical scheme of the application is further explained in detail through the following specific implementation modes:
example one
As shown in fig. 1, the system for detecting illegal parking based on visual identification in the embodiment includes the following steps:
s100: the acquisition information uploaded by the vehicle-mounted terminal is acquired, when the technical scheme is implemented, the intelligent vehicle-mounted terminal needs to be installed on each vehicle, and the existing new energy automobile generally integrates an intelligent vehicle-mounted system and a camera and can be realized by installing corresponding vehicle-mounted terminal software. The server receives the acquired information uploaded by each vehicle-mounted terminal in real time, and the acquired information in real time comprises image information, position information and the like.
S200: identifying road identification, vehicle position, vehicle information and parking state in the image information; in this embodiment, an existing image recognition algorithm is adopted to recognize road signs related to the image information, such as a parking space line frame range, a parking prohibition sign, and the like, vehicle positions, vehicle information, such as vehicle colors, license plate numbers, vehicle brand models, and the like, and parking states, that is, whether the vehicle is in a parking state.
In this embodiment, the specific process of identifying the license plate number in S200 includes:
s201: identifying a license plate number of the vehicle;
s202: calling a corresponding road section intersection monitoring video according to the position information, identifying license plate numbers of vehicles in the monitoring video, judging whether vehicles with the license plate numbers enter or exit the intersection in S201, and judging that the license plate identification is correct if the vehicles with the license plate numbers enter or exit the intersection;
if not, calculating the similarity between the license plate number of the vehicle in the intersection monitoring video and the license plate number identified in S201, selecting the license plate number larger than a preset value as a candidate according to the similarity, acquiring the vehicle characteristics of the vehicle corresponding to the candidate license plate number, such as vehicle color, vehicle brand model and the like, judging whether the vehicle characteristics are matched with the vehicle characteristics of the vehicle, and if so, taking the candidate license plate number as the license plate number of the vehicle.
S2021: if the license plate number with the similarity larger than the preset value or the vehicle characteristics are not matched, keeping the license plate number identified in the S201, and marking the vehicle as a vehicle to be confirmed;
s2022: and recording the times of identifying the license plate number corresponding to the vehicle to be confirmed by the acquisition information corresponding to each vehicle-mounted terminal, if the times are greater than a preset value, judging that the license plate number is the license plate number of the vehicle, and marking the vehicle as the confirmed vehicle.
S300: judging whether illegal parking behaviors exist or not according to the vehicle position, the parking state and the road identification; in this embodiment, it is first determined whether there is a vehicle in a parking state, and then it is determined whether there is an illegal parking behavior for each vehicle in the image according to whether there is a parking space or an illegal parking mark on the roadside and whether the vehicle is parked within a parking space wire frame range. In the step S300, if the vehicle corresponding to the license plate number is not the vehicle to be confirmed, it is determined whether the license plate number has been determined to have a parking violation within a preset time range, and if so, the detection of the vehicle is skipped.
S400: and when the illegal parking behavior is judged to exist, sending the image information, the position information, the vehicle information and the judgment result to the supervision platform.
S400 includes:
s401: and recording the times of recognizing the existence of the illegal parking behaviors of the vehicles corresponding to the license plates by the acquired information corresponding to the vehicle-mounted terminals, and if the times are greater than a preset value, judging that the illegal parking behaviors exist in the vehicles corresponding to the license plates.
S402: acquiring traffic flow information of an inlet and an outlet of a road where the vehicle-mounted terminal is located according to the acquisition information uploaded by the vehicle-mounted terminal; and loading the traffic flow information and the information of the illegal parking vehicles to a traffic flow prediction model to obtain traffic flow prediction results of the entrance and the exit of the road.
S403: matching the traffic flow information of the road exit of the data that the vehicle-mounted terminal is located on the road without the illegal vehicle and the entrance traffic flow information is similar to the traffic flow information in S402 from the historical data;
s404: judging the influence degree of the illegal parking behavior according to the traffic flow information of the exit under the condition that the vehicle does not illegally park, the traffic flow information of the exit under the condition that the vehicle illegally parks and the traffic flow prediction result; in this embodiment, the current influence factor is obtained by calculating a difference between traffic flow information of an exit without an illegal parking vehicle and traffic flow information of an exit with an illegal parking vehicle, the future influence factor is obtained by calculating a difference between traffic flow information of an exit without an illegal parking vehicle and a traffic flow prediction result, and the influence degree is obtained by performing weighted summation on the current influence factor and the future influence factor. In this embodiment, S404 includes: constructing a traffic flow prediction initial model; acquiring historical emergency data and historical regional traffic flow data, and constructing a training set and a test set; training the traffic flow prediction initial model by using a training set, and calculating cost functions of two groups of data according to the output result after training and the data of the test set; and adjusting the weight and the bias of each layer according to the calculation result until the cost function is converged to obtain a traffic flow prediction model. And loading the current traffic flow information and the illegal parking vehicle information including the illegal parking position, the size of the vehicle and the like of each illegal parking vehicle as input parameters to a traffic flow prediction model to obtain a regional traffic flow prediction result. The construction of the traffic flow prediction initial model specifically comprises the following steps: constructing an input layer, an output layer, a forgetting layer and a hiding layer based on an LSTM algorithm; the input layer controls output through a sigmoid function, the hidden layer controls output through a tanh function, and the forgetting layer controls output through the sigmoid function; optimizing the number of hidden layer nodes by an ant-lion optimization algorithm; the method comprises the following steps: initializing the positions of ants and ant lions as the number of nodes of a hidden layer, and setting an expression of a fitness function;
calculating the fitness of all initialized ants and ant lions, and finding the ant lions with the highest fitness as initial elite ant lions; randomly walking the ants and updating the positions of the ants; selecting the positions of ants as the positions of ant lions according to a roulette strategy;
screening the elite ant lions according to the fitness, updating the positions of the elite ant lions, judging whether an iterative convergence condition is met, and if the iterative convergence condition is met, taking the positions of the elite ant lions as the number of nodes of a hidden layer; if the iteration convergence condition is not met, recording the iteration times, if the iteration times are larger than a preset value, selecting the ant lion through a roulette strategy, and randomly walking the ant lion position.
S405: the importance of the information sent to the supervisory platform is marked according to the degree of influence.
S407: capturing image segments corresponding to the illegal parking behaviors from image information uploaded by each vehicle-mounted terminal to obtain an evidence image list;
s408: according to the evidence image list, identifying and classifying the shooting angles of the image segments;
s409: and calculating the distance between the position of the corresponding vehicle-mounted terminal in the evidence image list and the illegal vehicle, analyzing the definition of the content of the image fragment, weighting the distance and the definition to be used as the validity score of the image fragment, and sequencing the image fragments classified at each shooting angle according to the validity score.
S500: and acquiring the contact way corresponding to the license plate number according to the feedback of the supervision platform, and sending notification information to the corresponding contact way. In this implementation, S200 further includes identifying the parking lot identifier in the image information and the empty parking space of the roadside parking lot; the notification information includes empty space information and surrounding parking lot information.
S600: and recording the number of times of illegal parking of each license plate number, and sending empty parking space information and surrounding parking lot information to the vehicle owner when the number of times of illegal parking is greater than a preset value and the intersection monitors and monitors the corresponding license plate number.
The above are only examples of the present invention, and the present invention is not limited to the field related to the embodiments, the general knowledge of the specific structures and characteristics of the embodiments is not described herein, and those skilled in the art can know all the common technical knowledge in the technical field before the application date or the priority date, can know all the prior art in the field, and have the capability of applying the conventional experimental means before the application date, and those skilled in the art can combine the capabilities of themselves to complete and implement the present invention, and some typical known structures or known methods should not become obstacles for those skilled in the art to implement the present application. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (5)
1. The system for detecting illegal parking based on visual identification is characterized in that: the method comprises the following steps:
s100: acquiring acquisition information uploaded by a vehicle-mounted terminal, wherein the acquisition information comprises image information and position information;
s200: identifying road identification, vehicle position, vehicle information and parking state in the image information;
s300: judging whether illegal parking behaviors exist or not according to the vehicle position, the parking state and the road identification;
s400: when the parking violation is judged to exist, sending the image information, the position information, the vehicle information and the judgment result to a supervision platform;
the S200 further comprises the steps of identifying parking lot identification in the image information and empty parking spaces of roadside parking lots;
the S400 further includes:
s401: recording the times of the vehicles corresponding to the license plates and the times of the illegal parking behaviors identified by the acquired information corresponding to the vehicle-mounted terminals, and if the times are greater than a preset value, judging that the vehicles corresponding to the license plates have the illegal parking behaviors;
s402: acquiring traffic flow information of an inlet and an outlet of a road where the vehicle-mounted terminal is located according to the acquisition information uploaded by the vehicle-mounted terminal;
s403: matching the traffic flow information of the road exit of the data that the vehicle-mounted terminal is located on the road without the illegal vehicle and the entrance traffic flow information is similar to the traffic flow information in S402 from the historical data;
s404: judging the influence degree of the illegal parking behavior according to the traffic flow information of the exit under the condition that the vehicle does not break and the traffic flow information of the exit under the condition that the vehicle breaks;
obtaining a current influence factor by calculating a difference value between traffic flow information of an exit under the condition that vehicles are not illegally parked and traffic flow information of an exit under the condition that vehicles are illegally parked, obtaining a future influence factor by calculating a difference value between the traffic flow information of the exit under the condition that vehicles are not illegally parked and a traffic flow prediction result, and obtaining the influence degree by weighting and summing the current influence factor and the future influence factor; in order to obtain a traffic flow prediction result, constructing a traffic flow prediction initial model; acquiring historical emergency data and historical regional traffic flow data, and constructing a training set and a test set; training the traffic flow prediction initial model by using a training set, and calculating cost functions of two groups of data according to the output result after training and the data of the test set; adjusting the weight and the bias of each layer according to the calculation result until the cost function is converged to obtain a traffic flow prediction model; loading the current traffic flow information and the illegal parking vehicle information including illegal parking positions and vehicle sizes of various illegal parking vehicles as input parameters into a traffic flow prediction model to obtain a regional traffic flow prediction result; the construction of the traffic flow prediction initial model specifically comprises the following steps: constructing an input layer, an output layer, a forgetting layer and a hiding layer based on an LSTM algorithm; the input layer controls output through a sigmoid function, the hidden layer controls output through a tanh function, and the forgetting layer controls output through the sigmoid function; optimizing the number of hidden layer nodes by an ant-lion optimization algorithm; the method comprises the following steps: initializing the positions of ants and ant lions as the number of nodes of a hidden layer, and setting an expression of a fitness function;
calculating the fitness of all initialized ants and ant lions, and finding the ant lions with the highest fitness as initial elite ant lions; the ants are randomly wandered and the positions of the ants are updated; selecting the positions of ants as the positions of ant lions according to a roulette strategy;
screening the elite ant lions according to the fitness, updating the positions of the elite ant lions, judging whether an iterative convergence condition is met, and if the iterative convergence condition is met, taking the positions of the elite ant lions as the number of nodes of a hidden layer; if the iteration convergence condition is not met, recording the iteration times, if the iteration times are larger than a preset value, selecting the ant lion through a roulette strategy, and randomly walking the ant lion position;
s405: marking the importance degree of the information sent to the supervision platform according to the influence degree;
further comprising S500: acquiring a contact way corresponding to the license plate number according to the feedback of the supervision platform, and sending notification information to the corresponding contact way; the notification information comprises empty parking space information and surrounding parking lot information;
further comprising S600: and recording the number of illegal parking times of each license plate number, and sending empty parking space information and surrounding parking lot information to the vehicle owner when the number of illegal parking times is greater than a preset value and the intersection monitors and monitors the corresponding license plate number.
2. The system of claim 1 for detecting illegal parking based on visual identification, characterized in that: the vehicle information includes a license plate number, and the S200 further includes:
s201: identifying a license plate number of the vehicle;
s202: calling a corresponding road section intersection monitoring video according to the position information, identifying license plate numbers of vehicles in the monitoring video, judging whether vehicles with the license plate numbers enter or exit the intersection in S201, and judging that the license plate identification is correct if the vehicles with the license plate numbers enter or exit the intersection;
if not, calculating the similarity between the license plate number of the vehicle in the intersection monitoring video and the license plate number identified in S201, selecting the license plate number larger than the preset value as a candidate according to the similarity, acquiring the vehicle characteristic of the vehicle corresponding to the candidate license plate number, judging whether the vehicle characteristic is matched with the vehicle characteristic of the vehicle, and if so, taking the candidate license plate number as the license plate number of the vehicle.
3. The system of claim 2 for detecting illegal parking based on visual identification, characterized in that: the S202 further includes:
s2021: if the license plate number with the similarity larger than the preset value or the vehicle characteristics are not matched, keeping the license plate number identified in the S201, and marking the vehicle as a vehicle to be confirmed;
s2022: recording the times of identifying the license plate number corresponding to the vehicle to be confirmed by the acquisition information corresponding to each vehicle-mounted terminal, if the times is greater than a preset value, judging that the license plate number is the license plate number of the vehicle, and marking the vehicle as the confirmed vehicle.
4. The system of claim 3 for detecting illegal parking based on visual identification, characterized in that: the S300 further includes:
and if the vehicle corresponding to the license plate number is not the vehicle to be confirmed, judging whether the license plate number is judged to have illegal parking behaviors in a preset time range, and if so, skipping the detection of the vehicle.
5. The system of claim 4 for detecting illegal parking based on visual identification, characterized in that: the S400 further includes:
s407: capturing image segments corresponding to the illegal parking behaviors from image information uploaded by each vehicle-mounted terminal to obtain an evidence image list;
s408: according to the evidence image list, identifying and classifying the shooting angles of the image segments;
s409: and calculating the distance between the position of the corresponding vehicle-mounted terminal in the evidence image list and the illegal vehicle, analyzing the definition of the content of the image fragment, weighting the distance and the definition to be used as the validity score of the image fragment, and sequencing the image fragments classified at each shooting angle according to the validity score.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210208559.8A CN114613132B (en) | 2022-03-04 | 2022-03-04 | Illegal parking detection system based on visual identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210208559.8A CN114613132B (en) | 2022-03-04 | 2022-03-04 | Illegal parking detection system based on visual identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114613132A CN114613132A (en) | 2022-06-10 |
| CN114613132B true CN114613132B (en) | 2023-02-03 |
Family
ID=81861899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210208559.8A Active CN114613132B (en) | 2022-03-04 | 2022-03-04 | Illegal parking detection system based on visual identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114613132B (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105575130B (en) * | 2016-02-25 | 2018-06-05 | 浙江宇视科技有限公司 | A kind of unattended parking implementation method and device |
| CN111750879A (en) * | 2019-03-29 | 2020-10-09 | 上海擎感智能科技有限公司 | Auxiliary parking method and device |
| CN111750880A (en) * | 2019-03-29 | 2020-10-09 | 上海擎感智能科技有限公司 | Auxiliary parking method and device |
| KR102516890B1 (en) * | 2020-11-24 | 2023-03-30 | 전주비전대학교산학협력단 | Identification system and method of illegal parking and stopping vehicle numbers using drone images and artificial intelligence technology |
-
2022
- 2022-03-04 CN CN202210208559.8A patent/CN114613132B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114613132A (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111325978B (en) | Whole-process monitoring and warning system and method for abnormal behaviors of vehicles on expressway | |
| CN109326124A (en) | A kind of urban environment based on machine vision parks cars Activity recognition system | |
| CN110895662A (en) | Vehicle overload alarm method and device, electronic equipment and storage medium | |
| KR102122850B1 (en) | Solution for analysis road and recognition vehicle license plate employing deep-learning | |
| CN109670431A (en) | A kind of behavioral value method and device | |
| CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
| CN116580547B (en) | Intelligent control method and system for buried traffic signal lamp | |
| CN112749630A (en) | Intelligent video monitoring method and system for road conditions | |
| CN117037084A (en) | Method and device for identifying abnormal behavior of toll station vehicle based on track reconstruction | |
| CN115662113A (en) | Signalized intersection people-vehicle game conflict risk assessment and early warning method | |
| CN116206285A (en) | Traffic weakness group collision risk assessment method and system applied to automatic driving | |
| CN110880243B (en) | Road illegal parking management method based on high-order video roadside parking charging equipment | |
| CN111127882A (en) | Tourist attraction parking lot coming vehicle number prediction method based on big data | |
| CN114613132B (en) | Illegal parking detection system based on visual identification | |
| CN114220040A (en) | Parking method, terminal and computer readable storage medium | |
| CN113112813B (en) | Illegal parking detection method and device | |
| CN113989715A (en) | Vehicle parking violation detection method and device, electronic equipment and storage medium | |
| CN113870551A (en) | Roadside monitoring system capable of identifying dangerous and non-dangerous driving behaviors | |
| CN114613134B (en) | Regional traffic flow condition prediction method based on visual identification | |
| CN117058634A (en) | Expressway scene self-adaptive traffic offence behavior identification method | |
| CN113593256B (en) | Unmanned aerial vehicle intelligent driving-away control method and system based on city management and cloud platform | |
| CN112633163B (en) | Detection method for realizing illegal operation vehicle detection based on machine learning algorithm | |
| CN115407704A (en) | Intelligent traffic marking control method, system and equipment | |
| CN114038209A (en) | Bus lane occupation processing method, device and equipment | |
| CN113177443A (en) | Method for intelligently identifying road traffic violation based on image vision |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |