CN111914669A - Method and device for detecting violation of tide lane, electronic equipment and storage medium - Google Patents
Method and device for detecting violation of tide lane, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111914669A CN111914669A CN202010650534.4A CN202010650534A CN111914669A CN 111914669 A CN111914669 A CN 111914669A CN 202010650534 A CN202010650534 A CN 202010650534A CN 111914669 A CN111914669 A CN 111914669A
- Authority
- CN
- China
- Prior art keywords
- lane
- vehicle
- image
- tidal
- tide
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000001514 detection method Methods 0.000 claims abstract description 101
- 239000003550 marker Substances 0.000 claims description 48
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010586 diagram Methods 0.000 description 21
- 230000006399 behavior Effects 0.000 description 11
- 230000011218 segmentation Effects 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 101710179734 6,7-dimethyl-8-ribityllumazine synthase 2 Proteins 0.000 description 3
- 101710186609 Lipoyl synthase 2 Proteins 0.000 description 3
- 101710122908 Lipoyl synthase 2, chloroplastic Proteins 0.000 description 3
- 101710101072 Lipoyl synthase 2, mitochondrial Proteins 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 101710179738 6,7-dimethyl-8-ribityllumazine synthase 1 Proteins 0.000 description 1
- 101710186608 Lipoyl synthase 1 Proteins 0.000 description 1
- 101710137584 Lipoyl synthase 1, chloroplastic Proteins 0.000 description 1
- 101710090391 Lipoyl synthase 1, mitochondrial Proteins 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000028838 turning behavior Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- 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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for detecting violation of regulations on a tidal lane, electronic equipment and a storage medium, which are used for improving the detection efficiency of violation of regulations on the tidal lane. The method comprises the steps of acquiring a first video which is acquired by first image acquisition equipment and contains a tide lane mark area, and acquiring a second video which is acquired by second image acquisition equipment and contains a tide lane area; detecting a tide lane where each vehicle is located and a driving direction in a second image of the second video, and detecting a tide lane mark indicating direction in a first image which is acquired simultaneously with the second image in the first video; and if the driving direction of the vehicle in the tide lane is different from the indication direction of the tide lane mark corresponding to the tide lane, determining that the vehicle runs against the regulations. According to the embodiment of the invention, whether the running direction of the vehicle on the tide lane is the same as the specified running direction or not is judged by detecting whether the running direction of the vehicle on the tide lane is the same as the specified running direction or not in the first image and the second image which are acquired simultaneously, the violation detection of the tide lane is automatically carried out, and the detection efficiency is higher.
Description
Technical Field
The present disclosure relates to the field of multimedia technologies, and in particular, to a method and an apparatus for detecting violation of tide lane, an electronic device, and a storage medium.
Background
The tidal traffic phenomenon refers to a phenomenon that traffic congestion may be caused by a large amount of vehicles moving in a certain direction within a certain period of time, for example, the traffic flow in the coming-in direction is large in the morning, and the traffic flow in the coming-out direction is large in the evening. For this phenomenon, traffic organization is performed in a manner of using a tide lane in traffic diversion, that is, a tide lane indicator light or a traffic lane indicator board indicates the change of the driving direction of a certain lane in different periods of time, for example, more vehicles enter the city in early peak, the number of lanes in the direction of entering the city is increased, more vehicles go out of the city in late peak, and the number of lanes in the direction of going out of the city is increased.
With the development of economy, the vehicle holding amount is increased, various traffic violation behaviors are increased, and hidden dangers are buried for urban traffic safety. At present, when the tidal lane violation detection is carried out, a road vehicle is usually captured through an intelligent traffic violation monitoring and shooting management system, then the captured image is subjected to secondary verification through manpower, whether the vehicle in the captured image runs in a violation mode or not is judged, and the existing manual violation behavior detection efficiency is low.
Disclosure of Invention
The invention aims to provide a method and a device for detecting violation of tide lane, electronic equipment and a storage medium, which are used for improving the efficiency of detecting violation of tide lane.
In a first aspect, an embodiment of the present disclosure provides a method for detecting a violation of a tidal lane, including:
acquiring a first video which is acquired by a first image acquisition device and contains a tide lane mark area for indicating a driving direction, and acquiring a second video which is acquired by a second image acquisition device and contains the tide lane area; wherein the tidal lane area corresponds to the tidal lane marker;
detecting a tidal lane and a driving direction of each vehicle in a second image of the vehicle in any frame of the second video, and detecting a tidal lane marker indication direction in a first image acquired simultaneously with the second image in the first video;
and for any vehicle, if the driving direction of the vehicle in the tide lane is different from the indication direction of the tide lane mark corresponding to the tide lane, determining that the vehicle runs against the regulations.
In an alternative embodiment, the tidal lane zones correspond one-to-one to the tidal lane markers;
determining a tidal lane marker corresponding to the tidal lane by:
determining a tidal lane contained in the second image and a tidal lane marker contained in the first image;
and for any tidal lane, determining the arrangement position of the tidal lane in all tidal lanes, and taking the tidal lane mark corresponding to the arrangement position in all tidal lane marks as the tidal lane mark corresponding to the tidal lane.
An optional embodiment is that the determining the tidal lane contained in the second image comprises:
detecting a plurality of lane lines included in the second image;
and determining the lane surrounded by the N +1 th lane line as the Nth tidal lane.
An optional implementation is that, detecting the tidal lane in which each vehicle is located in the second image, includes:
taking a lane surrounded by two adjacent lane lines with the first position parameter values with opposite positive and negative values as a tide lane where the vehicle is located;
wherein, the positive and negative of the first position parameter value of the lane line represent the relative position of the vehicle and the lane line; the first position parameter value of the lane line is determined based on the coordinates of the center point of the detection frame of the vehicle and the coordinates of the end point of the lane line.
An optional implementation is that, detecting the driving direction of each vehicle in the second image includes:
if the target vehicle running to the target area is detected in the second image, detecting the coordinates of the center point of a detection frame of the target vehicle in continuous M frames of second images acquired after the second image based on a target tracking model;
determining the driving angle of the target vehicle according to the initial coordinate of the central point of the detection frame of the target vehicle in the first frame image of the continuous M frames and the final coordinate of the central point of the detection frame of the target vehicle in the last frame image of the continuous M frames;
and determining the running direction corresponding to the running angle, the starting coordinate and the ending coordinate of the target vehicle according to the corresponding relation of the preset running angle, the starting coordinate, the ending coordinate and the running direction.
In an optional embodiment, the detecting that there is a target vehicle traveling to a target area in the second image includes:
detecting end point coordinates respectively corresponding to two stop lines contained in the second image;
for any vehicle, determining a second position parameter value of the vehicle for each stop line according to the coordinates of the center point of a detection frame of the vehicle and the coordinates of the end points corresponding to the two stop lines respectively, wherein the positive and negative of the second position parameter value represent the relative position of the vehicle and the stop line;
and if the positive and negative of the second position parameter values of the vehicle aiming at the two stop lines are opposite, determining that the vehicle is the target vehicle.
An optional embodiment is that, determining the tide lane marking indication direction corresponding to the tide lane comprises:
identifying a tidal lane marker indication direction contained in the first image based on a detection model;
and determining the tide lane mark indication direction corresponding to the tide lane in which the vehicle is positioned from the determined tide lane mark indication directions contained in the first image.
In a second aspect, the disclosed embodiments also provide a tidal lane violation detection device, including:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a first video which is acquired by a first image acquisition device and contains a tide lane mark area for indicating a driving direction and acquiring a second video which is acquired by a second image acquisition device and contains the tide lane area; wherein the tidal lane area corresponds to the tidal lane marker;
the detection module is used for detecting a tide lane and a driving direction of each vehicle in a second image of the vehicle in any frame of the second video and detecting a tide lane mark indicating direction in a first image which is acquired simultaneously with the second image in the first video;
and the judging module is used for determining that the vehicle runs against the rules if the running direction of the vehicle in the tide lane is different from the indication direction of the tide lane mark corresponding to the tide lane.
In an alternative embodiment, the tidal lane zones correspond one-to-one to the tidal lane markers;
the judgment module is specifically used for determining the tide lane mark corresponding to the tide lane in the following ways:
determining a tidal lane contained in the second image and a tidal lane marker contained in the first image;
and for any tidal lane, determining the arrangement position of the tidal lane in all tidal lanes, and taking the tidal lane mark corresponding to the arrangement position in all tidal lane marks as the tidal lane mark corresponding to the tidal lane.
An optional implementation manner is that the determining module is specifically configured to:
detecting a plurality of lane lines included in the second image;
and determining the lane surrounded by the N +1 th lane line as the Nth tidal lane.
An optional implementation manner is that the detection module is specifically configured to:
taking a lane surrounded by two adjacent lane lines with the first position parameter values with opposite positive and negative values as a tide lane where the vehicle is located;
wherein, the positive and negative of the first position parameter value of the lane line represent the relative position of the vehicle and the lane line; the first position parameter value of the lane line is determined based on the coordinates of the center point of the detection frame of the vehicle and the coordinates of the end point of the lane line.
An optional implementation manner is that the detection module is specifically configured to:
if the target vehicle running to the target area is detected in the second image, detecting the coordinates of the center point of a detection frame of the target vehicle in continuous M frames of second images acquired after the second image based on a target tracking model;
determining the driving angle of the target vehicle according to the initial coordinate of the central point of the detection frame of the target vehicle in the first frame image of the continuous M frames and the final coordinate of the central point of the detection frame of the target vehicle in the last frame image of the continuous M frames;
and determining the running direction corresponding to the running angle, the starting coordinate and the ending coordinate of the target vehicle according to the corresponding relation of the preset running angle, the starting coordinate, the ending coordinate and the running direction.
An optional implementation manner is that the detection module is specifically configured to:
detecting end point coordinates respectively corresponding to two stop lines contained in the second image;
for any vehicle, determining a second position parameter value of the vehicle for each stop line according to the coordinates of the center point of a detection frame of the vehicle and the coordinates of the end points corresponding to the two stop lines respectively, wherein the positive and negative of the second position parameter value represent the relative position of the vehicle and the stop line;
and if the positive and negative of the second position parameter values of the vehicle aiming at the two stop lines are opposite, determining that the vehicle is the target vehicle.
An optional implementation manner is that the detection module is specifically configured to:
identifying a tidal lane marker indication direction contained in the first image based on a detection model;
the judgment module is specifically configured to:
and determining the tide lane mark indication direction corresponding to the tide lane in which the vehicle is positioned from the determined tide lane mark indication directions contained in the first image.
In a third aspect, another embodiment of the present disclosure also provides an electronic device, including at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform any of the tidal lane violation detection methods provided by the embodiments of the present disclosure.
In a fourth aspect, another embodiment of the present disclosure also provides a computer storage medium having computer-executable instructions stored thereon for causing a computer to perform any of the tidal lane violation detection methods of the embodiments of the present disclosure.
In the method for detecting the violation of the tide lane, the video is acquired through the first image acquisition device and the second image acquisition device, the first image acquisition device acquires a first video containing a tide lane mark area, and the second image acquisition device acquires a second video containing the tide lane area; detecting the indication direction of the tide lane mark in the first image, and the tide lane and the driving direction of each vehicle in the second image through any frame of the first image and the second image which are simultaneously acquired in the first video and the second video; and then judging whether the running direction of the vehicle in the tide lane is the same as the indication direction of the tide lane mark corresponding to the tide lane or not for any vehicle, and if so, determining that the vehicle runs against the rules. In the embodiment of the invention, video acquisition is carried out on the tide lane mark area and the lane area, whether the driving direction of the tide lane where the vehicle is located in the first image and the second image which are acquired simultaneously is the same as the specified driving direction of the tide lane is detected, if the driving direction is different from the specified driving direction, the vehicle is judged to drive against the regulations, the automatic detection of the violation of the tide lane is realized, and the detection efficiency is higher; in addition, the first image acquisition equipment and the second image acquisition equipment can be integrated in one electronic eye in the embodiment of the invention, and devices such as an inductance coil and the like do not need to be additionally laid, so that the cost is saved; in addition, the violation detection method provided by the embodiment of the invention can be used for detecting various violation behaviors, the detection of the vehicle running direction can be carried out in multiple directions, the violation behaviors such as vehicle turning violations and the like can be detected, and the application range is wide.
Additional features and advantages of the disclosure will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the disclosure. The objectives and other advantages of the disclosure may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the embodiments of the present disclosure will be briefly described below, and it is apparent that the drawings described below are only some embodiments of the present disclosure, and it is obvious for those skilled in the art that other drawings can be obtained based on the drawings without inventive labor.
FIG. 1 is a schematic view of a tidal lane provided by an embodiment of the present invention;
FIG. 2 is a schematic diagram of a tidal lane change provided by an embodiment of the present invention;
FIG. 3 is a flow chart of a method of detecting a tidal lane violation according to an embodiment of the present invention;
FIG. 4 is a schematic view of a tidal lane marker provided in an embodiment of the present invention;
fig. 5 is an installation schematic diagram of a first image capturing device and a second image capturing device according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a second image including a plurality of lane lines according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a first image containing a plurality of tidal lane markers according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a target area provided in accordance with an embodiment of the present invention;
FIG. 9 is a block diagram of a method of detecting a tidal lane violation according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of a tidal lane violation detection device according to an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present application will be described in detail and removed with reference to the accompanying drawings. In the description of the embodiments herein, "/" means "or" unless otherwise specified, for example, a/B may mean a or B; "and/or" in the text is only an association relationship describing an associated object, and means that three relationships may exist, for example, a and/or B may mean: three cases of a alone, a and B both, and B alone exist, and in addition, "a plurality" means two or more than two in the description of the embodiments of the present application.
In the following, the terms "first", "second" are used for descriptive purposes only and are not to be understood as implying or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of embodiments of the application, unless stated otherwise, "plurality" means two or more.
The term "and/or" in the embodiments of the present invention describes an association relationship of associated objects, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
The tidal lane is a variable lane, one or more tidal lanes are arranged according to different conditions of traffic flow in the morning and at night, and the tidal lane is a lane in which the specified driving direction changes along with the change of time intervals. For example, the lane number in a certain direction is adjusted by indicating a change in direction with a lane lamp and controlling a predetermined traveling direction.
As shown in fig. 1, a tidal lane schematic diagram is provided according to an embodiment of the present invention, in which the specified driving direction of the tidal lane is indicated by lane lights, for example, the specified driving direction of the left two tidal lanes is backward and the specified driving direction of the right three tidal lanes is forward at the present time.
Assuming that the time period changes, the backward driving traffic flow increases, and the number of tide lanes in the backward direction needs to increase to relieve traffic pressure, and assuming that the lane lights after adjustment are as shown in fig. 2, the specified driving directions of the tide lanes after adjustment are respectively: the four tidal lanes on the left provide the rearward direction of travel and the one tidal lane on the right provide the forward direction of travel.
It should be noted that the descriptions of "forward" and "backward" in the driving direction are only examples, and reference may be made to the direction indicated by the indicator light in the figure.
There may also be a violation of the vehicle travelling on a tidal lane, for example in the tidal lane shown in figure 2, where a vehicle travelling backwards is on the rightmost tidal lane and there is a back-running violation of the vehicle. In order to detect the violation behaviors of tidal lanes, an optional implementation mode is that vehicles on the road surface are captured through an electronic eye (an intelligent traffic violation monitoring and shooting management system), then the captured images are subjected to secondary verification manually, whether the vehicles in the captured images run in violation or not is judged, the detection efficiency of the violation behaviors is low through manual detection, and auditors check a large number of violation images every day, so that the workload is large, the spirit is easy to be exhausted, law enforcement is not strict or misjudgment is caused, and road traffic safety accidents are caused. Another optional implementation is that an inductance coil is laid on a tide lane, and by analyzing signals of a lane lamp and the inductance coil, when a retrograde vehicle is detected, a snapshot device is controlled to take a snapshot.
The embodiment of the invention provides a method for detecting violation behaviors of a tidal lane, which can automatically detect the violation behaviors of vehicles on the tidal lane without manual examination and verification, has higher detection efficiency, does not need to lay an inductance coil, saves the cost and can detect various violation behaviors.
As shown in fig. 3, a flow chart of a method for detecting a violation of a tidal lane according to an embodiment of the present invention includes:
acquiring a first video including a tidal lane marker region indicating a driving direction acquired by a first image acquisition device and acquiring a second video including a tidal lane region acquired by a second image acquisition device in step S301;
wherein the tidal lane area corresponds to a tidal lane marker;
in step S302, detecting that any frame of the second video includes a tidal lane and a driving direction of each vehicle in the second image of the vehicle, and detecting a tidal lane marker indication direction in the first image captured simultaneously with the second image in the first video;
in step S303, if the traveling direction of the vehicle in the tidal lane is different from the indication direction of the tidal lane marker corresponding to the tidal lane, it is determined that the vehicle is traveling against the regulation.
In the embodiment of the invention, video acquisition is carried out through a first image acquisition device and a second image acquisition device, the first image acquisition device acquires a first video containing a tide lane mark area, and the second image acquisition device acquires a second video containing the tide lane area; detecting the indication direction of the tide lane mark in the first image, and the tide lane and the driving direction of each vehicle in the second image through any frame of the first image and the second image which are simultaneously acquired in the first video and the second video; and then judging whether the running direction of the vehicle in the tide lane is the same as the indication direction of the tide lane mark corresponding to the tide lane or not for any vehicle, and if so, determining that the vehicle runs against the rules. In the embodiment of the invention, video acquisition is carried out on the tide lane mark area and the lane area, whether the driving direction of the tide lane where the vehicle is located in the first image and the second image which are acquired simultaneously is the same as the specified driving direction of the tide lane is detected, if the driving direction is different from the specified driving direction, the vehicle is judged to drive against the regulations, the automatic detection of the violation of the tide lane is realized, and the detection efficiency is higher; in addition, the first image acquisition equipment and the second image acquisition equipment can be integrated in one electronic eye in the embodiment of the invention, and devices such as an inductance coil and the like do not need to be additionally laid, so that the cost is saved; in addition, the violation detection method provided by the embodiment of the invention can be used for detecting various violation behaviors, the detection of the vehicle running direction can be carried out in multiple directions, the violation behaviors such as vehicle turning violations and the like can be detected, and the application range is wide.
It should be noted that the tidal lane marker in the embodiment of the present invention may be a lane lamp or a sign, the sign is shown in fig. 4, if the tidal lane marker is the sign, the lane violation detection method provided in the embodiment of the present invention may determine whether the vehicle runs in violation of regulations according to the tidal lane and the running direction in which each vehicle is located in the second image, and the specified running direction of the tidal lane at the time of collecting the second image; wherein the prescribed direction of travel of the tidal lane at the time the second image is acquired may be determined by the sign included in the first image. In the embodiment of the present invention, the tidal lane marker is taken as a lane lamp for illustration.
Fig. 5 is a schematic installation diagram of a first image capturing device and a second image capturing device according to an embodiment of the present invention; an alternative embodiment is that the first image capturing device and the second image capturing device are integrated into a whole to form a two-way monitoring camera installed on the tidal lane section in fig. 5, so as to capture the first video and the second video.
In an optional implementation mode, the two-way monitoring camera consists of a long-focus camera and a short-focus camera, wherein the long-focus camera is first image acquisition equipment and is used for acquiring a first far video containing a tidal lane marking area; the short-focus camera is a second image acquisition device and is used for acquiring a second video containing a tide lane area, and the two image acquisition devices form a double-path monitoring camera which can be optionally arranged at a position opposite to the tide lane marking area.
After the first image acquisition device and the second image acquisition device are installed, a first video containing a tide lane mark area is acquired through the first image acquisition device, and a second video containing the tide lane area is acquired through the second image acquisition device.
In the embodiment of the invention, the tide lane marks and the tide lane areas have corresponding relations, and one optional implementation mode is that a plurality of tide lane areas correspond to one tide lane mark, namely, the indication of the specified driving direction of a plurality of tide lanes is realized through one tide lane mark; or, the tidal lane areas correspond to the tidal lane marks one by one, that is, each tidal lane mark indicates a specified driving direction of a tidal lane.
It should be noted that the method for detecting violation of a tidal lane provided by the embodiment of the present invention is also applicable to the case where a plurality of tidal lane areas correspond to one tidal lane marker, and the embodiment of the present invention is not described in detail.
An alternative embodiment is to determine the tidal lane marker for the tidal lane by:
determining a tidal lane contained in the second image and a tidal lane marker contained in the first image; and determining the arrangement positions of the tidal lanes in all the tidal lanes aiming at any tidal lane, and taking the tidal lane mark corresponding to the arrangement position in all the tidal lane marks as the tidal lane mark corresponding to the tidal lane.
Specifically, the tidal lane marks included in the second image and the tidal lane marks included in the first image are detected, and since the tidal lane areas correspond to the tidal lane marks one by one in the embodiment of the present invention, the number of the tidal lanes is the same as the number of the tidal lane marks, and the tidal lane marks at the same arrangement position correspond to the tidal lanes.
In implementation, the tide lane marks contained in the second image are detected, the tide lane marks contained in the first image are detected, and then the tide lane marks are in one-to-one correspondence with the tide lanes.
In an optional embodiment, a plurality of lane lines included in the second image are detected; and determining the lane surrounded by the N +1 th lane line as the Nth tidal lane.
Specifically, a plurality of lane lines included in the second image may be obtained through post-processing based on the deep learning segmentation model, and a lane enclosed by the nth lane line and the (N + 1) th lane line is an nth tidal lane according to the detected arrangement positions of the plurality of lane lines.
In implementation, any frame of second image is acquired from a second video acquired by second image acquisition equipment, the second image is input into a trained segmentation model, an example segmentation and semantic segmentation result corresponding to the second image is obtained, and endpoint coordinates of a plurality of lane lines are obtained.
It should be noted that, in the embodiment of the present invention, the establishing manner of the coordinate system is not specifically limited, and the endpoint coordinates of the lane line are determined according to the established coordinate system.
As shown in fig. 6, for a second image schematic diagram including a plurality of lane lines provided in the embodiment of the present invention, it is assumed that 5 lane lines are detected, and the corresponding end point coordinates are:
L1：{(x1s,y1s),(x1e,y1e) Represents a lane line L1; l2: { (x)2s,y2s),(x2e,y2e) Represents a lane line L2; l3: { (x)3s,y3s),(x3e,y3e) Represents a lane line L3; l4: { (x)4s,y4s),(x4e,y4e) Represents a lane line L4; l5: { (x)5s,y5s),(x5e,y5e) Represents a lane line L5.
Wherein x is in the coordinate system as shown in FIG. 61s、x2s、……、x5sGradually increases, and the lane line L1 and the lane line L2 enclose a first tidal lane; the lane line L2 and the lane line L3 enclose a second tidal lane; the lane line L3 and the lane line L4 enclose a third tidal lane; lane line L4 and lane line L5 enclose a fourth tidal lane.
An alternative embodiment is that, based on the detection model for deep learning, tidal lane markers contained in the first image are identified, and the tidal lane markers contained in the first image indicate a direction;
in implementation, any frame of first image is acquired from a first video acquired by the first image acquisition device, the first image is input into the trained detection model, and the position coordinates of a plurality of tidal lane markers in the first image and the indication direction of each tidal lane marker are obtained. Wherein the indicated direction of the tidal lane is used for application in determining whether the vehicle is driving in violation, as explained below.
Assuming that there are 4 tidal lanes in the detection result of the second image, the number of the detected tidal lane markers is also 4, as shown in fig. 7, which is a schematic diagram of a first image containing a plurality of tidal lane markers provided by the embodiment of the present invention, assuming that there are 4 tidal lane markers detected, the position coordinates are:
Pt1＝{(txtl1，tytl1),(txbr1，tybr1) Indicates the direction recognition result as R1Denotes a first tidal lane marker Pt1The coordinates of two end points of the diagonal of the detection frame are respectively (tx)tl1，tytl1) And (tx)br1，tybr1) Wherein the pointing direction recognition result may be forward;
Pt2＝{(txtl2，tytl2),(txbr2，tybr2) Indicates the direction recognition result as R2Indicating a second tidal lane marker Pt2The coordinates of two end points of the diagonal of the detection frame are respectively (tx)tl2，tytl2) And (tx)br2，tybr2) Wherein the pointing direction recognition result may be forward;
Pt3＝{(txtl3，tytl3),(txbr3，tybr3) Indicates the direction recognition result as R3Represents a third tidal lane marker Pt3The coordinates of two end points of the diagonal of the detection frame are respectively (tx)tl3，tytl3) And (tx)br3，tybr3) Wherein the pointing direction recognition result may be forward;
Pt4＝{(txtl4，tytl4),(txbr4，tybr4) Indicates thatThe direction recognition result is R4Denotes a fourth tidal lane marker Pt4The coordinates of two end points of the diagonal of the detection frame are respectively (tx)tl4，tytl4) And (tx)br4，tybr4) Wherein the indication direction recognition result may be backward.
Wherein tx is the coordinate system as shown in FIG. 7tl1、txtl2、……、txtl4Gradually increases in value.
Assuming that the detected arrangement positions of the tidal lanes are as shown in fig. 6, and are a first tidal lane, a second tidal lane, a third tidal lane and a fourth tidal lane in sequence; the positions of the tide lane markers are shown in FIG. 7 and are in turn Pt1、Pt2、Pt3、Pt4Then P ist1A tidal lane marker corresponding to the first tidal lane; pt2A tidal lane marker corresponding to the second tidal lane; pt3A tidal lane marker corresponding to the third tidal lane; pt4Is the tide lane marker corresponding to the fourth tide lane.
In the embodiment of the invention, the tidal lane where the vehicle is located and the driving direction of the vehicle need to be judged.
An optional implementation manner is that the detection model based on deep learning detects each frame of second images in the second video, and if no vehicle is detected in any frame of second images, the detection of the next frame is continued until a second image containing a vehicle is detected.
It should be noted that in the embodiment of the present invention, the detection of the tidal lane marker in the first image may be that after the second image containing the vehicle is detected, the acquisition time of the second image containing the vehicle is determined, and the tidal lane marker detection is performed on the first image acquired at the acquisition time.
In the embodiment of the invention, the detection result of detecting the vehicle in the second image based on the detection model of deep learning comprises a detection frame corresponding to the vehicle and the license plate number of the vehicle, wherein the detection frame is used for representing the vehicle and can be represented by coordinates of two end points of a diagonal line of the detection frame of the vehicle, and the license plate number is used for recording when the vehicle is determined to run illegally.
For example, the vehicle detection result of any vehicle is { (x)tl,ytl),(xbr,ybr) And then, the coordinates of the center point of the detection frame can be expressed as:
can detect the frame center point (x) through the vehiclec,yc) Indicating the position of the vehicle.
It should be noted that violation detection is performed on each vehicle detected in the second image, and whether each vehicle runs in violation is determined by determining the tidal lane in which each vehicle is located and the running direction of each vehicle, and determining the indication direction of the tidal lane mark corresponding to the tidal lane in which the vehicle is located. The following describes a method for determining the tidal lane in which the vehicle is located and a method for determining the driving direction of the vehicle according to the embodiments of the present invention.
An alternative embodiment is to determine the tidal lane in which the vehicle is located according to the following:
a lane surrounded by two adjacent lane lines with the first position parameter values with opposite positive and negative values is used as a tide lane where the vehicle is located; wherein, the positive and negative of the first position parameter value of the lane line represent the relative position of the vehicle and the lane line; the first position parameter value of the lane line is determined based on the coordinates of the center point of the detection frame of the vehicle and the coordinates of the end point of the lane line.
Specifically, a first position parameter representing the relative position of the vehicle and the lane line is determined through the coordinate of the center point of a detection frame of the vehicle and the coordinate of the end point of the lane line, and the tide lane where the vehicle is located is determined according to the first position parameter of each lane line.
For example, the coordinates of the end points of the lane lines are { (x), respectively1s,y1s),(x1e,y1e)}、{(x2s,y2s),(x2e,y2e)}、{(x3s,y3s),(x3e,y3e)}、{(x4s,y4s),(x4e,y4e)}、{(x5s,y5s),(x5e,y5e)}。
The equation corresponding to each lane line is:
L1:(x1e-x1s)y-(y1e-y1s)x+(y1e-y1s)x1s-y1s(x1e-x1s)＝0
L2:(x2e-x2s)y-(y2e-y2s)x+(y2e-y2s)x2s-y2s(x2e-x2s)＝0
L3:(x3e-x3s)y-(y3e-y3s)x+(y3e-y3s)x3s-y3s(x3e-x3s)＝0
L4:(x4e-x4s)y-(y4e-y4s)x+(y4e-y4s)x4s-y4s(x4e-x4s)＝0
L3:(x5e-x5s)y-(y5e-y5s)x+(y5e-y5s)x5s-y5s(x5e-x5s)＝0
coordinates of the central point of the detection frame are (x)c,yc) The first position parameter of each lane line is as follows:
Z1＝(x1e-x1s)yc-(y1e-y1s)xc+(y1e-y1s)x1s-y1s(x1e-x1s)
Z2＝(x2e-x2s)yc-(y2e-y2s)xc+(y2e-y2s)x2s-y2s(x2e-x2s)
Z3＝(x3e-x3s)yc-(y3e-y3s)xc+(y3e-y3s)x3s-y3s(x3e-x3s)
Z4＝(x4e-x4s)yc-(y4e-y4s)xc+(y4e-y4s)x4s-y4s(x4e-x4s)
Z5＝(x5e-x5s)yc-(y5e-y5s)xc+(y5e-y5s)x5s-y5s(x5e-x5s)
wherein Z1, Z2, Z3, Z4 and Z5 respectively represent vehicles (x)c,yc) First position parameters for lane lines L1, L2, L3, L4, L5.
Assuming that Z1 is positive, Z2 is positive, Z3 is negative, Z4 is negative, and Z5 is negative in the first position parameters determined by the method, it means that the vehicle is on the same side of lane lines Z1 and Z2, on the same side of lane lines Z3, Z4 and Z5, and is equivalent to that Z1, Z2 and Z3, Z4 and Z5 are on different sides, and it can be determined that the tidal lane in which the vehicle is located is a lane surrounded by lane lines Z2 and Z3, that is, the lane in which the vehicle is located is the second tidal lane.
In an alternative embodiment, the vehicle travel direction is determined in accordance with the following:
if the target vehicle running to the target area is detected in the second image, detecting the coordinates of the center point of a detection frame of the target vehicle in the continuous M frames of second images acquired after the second image based on the target tracking model; determining the driving angle of the target vehicle according to the initial coordinate of the central point of the detection frame of the target vehicle in the first frame image of the continuous M frames and the final coordinate of the central point of the detection frame of the target vehicle in the last frame image of the continuous M frames; and determining the running angle, the starting coordinate and the running direction corresponding to the ending coordinate of the target vehicle according to the preset corresponding relation between the running angle, the starting coordinate, the ending coordinate and the running direction.
Specifically, a vehicle entering a target area is used as a target vehicle, the target vehicle is subjected to target tracking, a running track of the target vehicle is determined by continuously detecting multi-frame images, and then the running direction of the target vehicle is determined.
The target area may be an area beyond a stop line at an intersection, as shown in fig. 8, LS1 and LS2 in the figure are stop lines, and a hatched area is the target area.
An alternative embodiment is that a target vehicle traveling to the target area is determined in the second image according to the following:
detecting end point coordinates respectively corresponding to two stop lines contained in the second image; for any vehicle, determining a second position parameter value of the vehicle for each stop line according to the coordinates of the center point of a detection frame of the vehicle and the coordinates of end points corresponding to the two stop lines respectively, wherein the positive and negative of the second position parameter value represent the relative position of the vehicle and the stop line; and if the positive and negative of the second position parameter values of the vehicle aiming at the two stop lines are opposite, determining that the vehicle is the target vehicle.
Specifically, two stop lines included in the second image may be obtained through post-processing based on a segmentation model of deep learning.
In implementation, any frame of second image is acquired from a second video acquired by second image acquisition equipment, the second image is input into a trained segmentation model, an example segmentation result and a semantic segmentation result corresponding to the second image are obtained, and endpoint coordinates of two stop lines are obtained.
It should be noted that, in the embodiment of the present invention, the establishing manner of the coordinate system is not specifically limited, and the endpoint coordinate of the stop line is determined according to the established coordinate system.
Suppose that the coordinates of the end points corresponding to the two stop lines are detected as follows:
LS1：{(xs1s,ys1s),(xs1e,ys1e) Denotes a stop line LS 1;
LS2：{(xs2s,ys2s),(xs2e,ys2e) Denotes a stop line LS 2.
The stop line SL1 encloses a target area with the stop line LS 2.
Specifically, a second position parameter indicating the relative position of the vehicle and the stop line is determined through the coordinate of the center point of the detection frame of the vehicle and the coordinate of the end point of the stop line, and whether the vehicle is in the target area is determined according to the second position parameter of each stop line.
For example, the coordinates of the end points of the lane lines are { (x), respectivelys1s,ys1s),(xs1e,ys1e)}、{(xs2s,ys2s),(xs2e,ys2e)}。
The equation corresponding to each stop line is:
LS1:(xS1e-xS1s)y-(yS1e-yS1s)x+(yS1e-yS1s)xS1s-yS1s(xS1e-xS1s)＝0
LS2:(xS2e-xS2s)y-(yS2e-yS2s)x+(yS2e-yS2s)xS2s-yS2s(xS2e-xS2s)＝0
coordinates of the central point of the detection frame are (x)c,yc) The second position parameter of each stop line is:
ZS1＝(xS1e-xS1s)yc-(yS1e-yS1s)xc+(yS1e-yS1s)xS1s-yS1s(xS1e-xS1s)
ZS2＝(xS2e-xS2s)yc-(yS2e-yS2s)xc+(yS2e-yS2s)xS2s-yS2s(xS2e-xS2s)
wherein ZS1 and ZS2 respectively represent vehicles (x)c,yc) Second position parameters for the stop lines LS1, LS 2.
It is assumed that, of the second position parameters determined by the above method, ZS1 and ZS2 are opposite in sign, indicating that the vehicle is on different sides of the stop lines ZS1, ZS2, that is, the vehicle is in the target zone between two stop lines, and the vehicle is the target vehicle.
And if the target vehicle is detected, tracking the target vehicle based on the target tracking model, and detecting the coordinates of the center point of the detection frame of the target vehicle in the continuous multi-frame second images collected after the second image of the target vehicle is determined.
Suppose that the coordinates of the center point of the vehicle detection frame in the second images of the continuous M frames are { (x)c1,yc1),(xc2,yc2),(xc3,yc3),…,(xcN,ycN) Wherein (x)c1,yc1) Starting coordinates of the center point of the detection frame of the target vehicle in the first frame image of the continuous M frames, (x)cN,ycN) Determining the driving angle of the target vehicle according to the starting coordinate and the ending coordinate, wherein the starting coordinate is the center point ending coordinate of the detection frame of the target vehicle in the last frame image of the continuous M frames:
in practice, the travel angle of the target vehicle may be determined according to the following formula:
where θ represents the travel angle of the target vehicle.
The corresponding relation among the preset driving angle, the initial coordinate, the final coordinate and the driving direction is as follows:
assume that the traveling angle of the target vehicle is 20 °, and yNcGreater than y1cThen the target vehicle is determined to be in forward progress.
The preset corresponding relationship between the driving angle, the start coordinate, the end coordinate and the driving direction may be preset by those skilled in the art according to actual conditions, and will not be described in detail herein.
And after any vehicle in the second image enters the target area, tracking the target vehicle, continuously detecting the multi-frame images collected after the second image, and determining the running direction of the target vehicle.
The method provided by the embodiment of the invention determines the tide lane where any vehicle is located and the driving direction on the tide lane, and determines whether the vehicle runs against the regulations according to the direction indicated by the tide lane mark corresponding to the tide lane.
Wherein the tidal lane marker indication direction corresponding to the tidal lane may be determined at the time of tidal lane marker detection, as shown in fig. 7.
Assuming that the vehicle A is detected to be traveling on the first tidal lane with the traveling direction being forward, the tidal lane marker P corresponding to the first tidal lanet1If the indication direction is forward, the vehicle A does not run against the regulations;
assuming that the vehicle B is detected to be traveling on the third tidal lane with the traveling direction being backward, the tidal lane marker P corresponding to the third tidal lanet3The direction indicated is forward, and the vehicle B is running in violation.
The violation detection method provided by the embodiment of the invention can also detect whether the turning behavior is violated, and if the violation detection method detects that the vehicle C runs on the second tide lane and the running direction is right turn, the tide lane mark P corresponding to the second tide lanet2The direction of indication is forward, then the vehicle C is running in violation.
And recording the license plate numbers of the vehicle B and the vehicle C, and carrying out follow-up illegal driving treatment.
As shown in fig. 9, for a frame schematic diagram of a method for detecting a violation of a tide lane provided in an embodiment of the present invention, a first image is acquired by a first image acquisition device, a second image is acquired by a second image acquisition device, lane detection, vehicle and license plate detection, and driving direction detection are performed on the second image by performing tide lane mark detection and direction indication detection on the first image, and the lane and the tide lane mark are associated to determine whether the driving direction of the vehicle on the lane corresponds to the tide lane mark indication direction corresponding to the lane, and determine whether the vehicle runs in violation of the tide.
Based on the same inventive concept, the embodiment of the invention also provides electronic equipment, and as the problem solving principle of the electronic equipment and the method for detecting the violation of the tide lane in the embodiment of the invention, the implementation of the electronic equipment can refer to the implementation of the method, and repeated parts are not described again.
Referring to fig. 10, an electronic device 1000 according to an embodiment of the present invention includes:
at least one processor 1001, and
a memory 1002 communicatively coupled to the at least one processor;
the memory 1002 stores instructions executable by the at least one processor 1001, and the at least one processor 1001 implements the tidal lane violation detection method according to the embodiment of the present application by executing the instructions stored in the memory.
Based on the same inventive concept, as shown in fig. 11, an embodiment of the present invention provides a tidal lane violation detecting device, including:
an obtaining module 1101, configured to obtain a first video collected by a first image collecting device and including a tidal lane marker region for indicating a driving direction, and obtain a second video collected by a second image collecting device and including the tidal lane marker region; wherein the tidal lane area corresponds to the tidal lane marker;
a detection module 1102, configured to detect that any frame of the second video includes a tidal lane and a driving direction of each vehicle in the second image of the vehicle, and detect a tidal lane marker indication direction in the first image acquired simultaneously with the second image in the first video;
the determining module 1103 is configured to, for any vehicle, determine that the vehicle runs against regulations if the running direction of the vehicle in the tidal lane is different from the indication direction of the tidal lane mark corresponding to the tidal lane.
In an alternative embodiment, the tidal lane zones correspond one-to-one to the tidal lane markers;
the determining module 1103 is specifically configured to determine the tidal lane marker corresponding to the tidal lane by:
determining a tidal lane contained in the second image and a tidal lane marker contained in the first image;
and for any tidal lane, determining the arrangement position of the tidal lane in all tidal lanes, and taking the tidal lane mark corresponding to the arrangement position in all tidal lane marks as the tidal lane mark corresponding to the tidal lane.
An optional implementation manner is that the determining module 1103 is specifically configured to:
detecting a plurality of lane lines included in the second image;
and determining the lane surrounded by the N +1 th lane line as the Nth tidal lane.
An optional implementation manner is that the detection module 1102 is specifically configured to:
taking a lane surrounded by two adjacent lane lines with the first position parameter values with opposite positive and negative values as a tide lane where the vehicle is located;
wherein, the positive and negative of the first position parameter value of the lane line represent the relative position of the vehicle and the lane line; the first position parameter value of the lane line is determined based on the coordinates of the center point of the detection frame of the vehicle and the coordinates of the end point of the lane line.
An optional implementation manner is that the detection module 1102 is specifically configured to:
if the target vehicle running to the target area is detected in the second image, detecting the coordinates of the center point of a detection frame of the target vehicle in continuous M frames of second images acquired after the second image based on a target tracking model;
determining the driving angle of the target vehicle according to the initial coordinate of the central point of the detection frame of the target vehicle in the first frame image of the continuous M frames and the final coordinate of the central point of the detection frame of the target vehicle in the last frame image of the continuous M frames;
and determining the running direction corresponding to the running angle, the starting coordinate and the ending coordinate of the target vehicle according to the corresponding relation of the preset running angle, the starting coordinate, the ending coordinate and the running direction.
An optional implementation manner is that the detection module 1102 is specifically configured to:
detecting end point coordinates respectively corresponding to two stop lines contained in the second image;
for any vehicle, determining a second position parameter value of the vehicle for each stop line according to the coordinates of the center point of a detection frame of the vehicle and the coordinates of the end points corresponding to the two stop lines respectively, wherein the positive and negative of the second position parameter value represent the relative position of the vehicle and the stop line;
and if the positive and negative of the second position parameter values of the vehicle aiming at the two stop lines are opposite, determining that the vehicle is the target vehicle.
An optional implementation manner is that the detection module 1102 is specifically configured to:
identifying a tidal lane marker indication direction contained in the first image based on a detection model;
the determining module 1103 is specifically configured to:
and determining the tide lane mark indication direction corresponding to the tide lane in which the vehicle is positioned from the determined tide lane mark indication directions contained in the first image.
Embodiments of the present application provide a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described tidal lane violation detection method.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (10)
1. A method of tidal lane violation detection, the method comprising:
acquiring a first video which is acquired by a first image acquisition device and contains a tide lane mark area for indicating a driving direction, and acquiring a second video which is acquired by a second image acquisition device and contains the tide lane area; wherein the tidal lane area corresponds to the tidal lane marker;
detecting a tidal lane and a driving direction of each vehicle in a second image of the vehicle in any frame of the second video, and detecting a tidal lane marker indication direction in a first image acquired simultaneously with the second image in the first video;
and for any vehicle, if the driving direction of the vehicle in the tide lane is different from the indication direction of the tide lane mark corresponding to the tide lane, determining that the vehicle runs against the regulations.
2. The method of claim 1, wherein the tidal lane area is in one-to-one correspondence with the tidal lane markers;
determining a tidal lane marker corresponding to the tidal lane by:
determining a tidal lane contained in the second image and a tidal lane marker contained in the first image;
and for any tidal lane, determining the arrangement position of the tidal lane in all tidal lanes, and taking the tidal lane mark corresponding to the arrangement position in all tidal lane marks as the tidal lane mark corresponding to the tidal lane.
3. The method of claim 2, wherein said determining the tidal lane contained in the second image comprises:
detecting a plurality of lane lines included in the second image;
and determining the lane surrounded by the N +1 th lane line as the Nth tidal lane.
4. The method of claim 1, wherein detecting the tidal lane in which each vehicle is located in the second image comprises:
taking a lane surrounded by two adjacent lane lines with the first position parameter values with opposite positive and negative values as a tide lane where the vehicle is located;
wherein, the positive and negative of the first position parameter value of the lane line represent the relative position of the vehicle and the lane line; the first position parameter value of the lane line is determined based on the coordinates of the center point of the detection frame of the vehicle and the coordinates of the end point of the lane line.
5. The method of claim 1, wherein detecting the direction of travel of each vehicle in the second image comprises:
if the target vehicle running to the target area is detected in the second image, detecting the coordinates of the center point of a detection frame of the target vehicle in continuous M frames of second images acquired after the second image based on a target tracking model;
determining the driving angle of the target vehicle according to the initial coordinate of the central point of the detection frame of the target vehicle in the first frame image of the continuous M frames and the final coordinate of the central point of the detection frame of the target vehicle in the last frame image of the continuous M frames;
and determining the running direction corresponding to the running angle, the starting coordinate and the ending coordinate of the target vehicle according to the corresponding relation of the preset running angle, the starting coordinate, the ending coordinate and the running direction.
6. The method of claim 5, wherein the detecting of the target vehicle traveling to the target area in the second image comprises:
detecting end point coordinates respectively corresponding to two stop lines contained in the second image;
for any vehicle, determining a second position parameter value of the vehicle for each stop line according to the coordinates of the center point of a detection frame of the vehicle and the coordinates of the end points corresponding to the two stop lines respectively, wherein the positive and negative of the second position parameter value represent the relative position of the vehicle and the stop line;
and if the positive and negative of the second position parameter values of the vehicle aiming at the two stop lines are opposite, determining that the vehicle is the target vehicle.
7. The method of claim 2 or 5, wherein determining a tidal lane marker indication direction corresponding to the tidal lane comprises:
identifying a tidal lane marker indication direction contained in the first image based on a detection model;
and determining the tide lane mark indication direction corresponding to the tide lane in which the vehicle is positioned from the determined tide lane mark indication directions contained in the first image.
8. A tidal lane violation detection device, comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a first video which is acquired by a first image acquisition device and contains a tide lane mark area for indicating a driving direction and acquiring a second video which is acquired by a second image acquisition device and contains the tide lane area; wherein the tidal lane area corresponds to the tidal lane marker;
the detection module is used for detecting a tide lane and a driving direction of each vehicle in a second image of the vehicle in any frame of the second video and detecting a tide lane mark indicating direction in a first image which is acquired simultaneously with the second image in the first video;
and the judging module is used for determining that the vehicle runs against the rules if the running direction of the vehicle in the tide lane is different from the indication direction of the tide lane mark corresponding to the tide lane.
9. An electronic device, comprising:
at least one processor, and
a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor, the at least one processor implementing the method of tidal lane violation detection as claimed in any one of claims 1-7 by executing the instructions stored by the memory.
10. A computer storage medium storing a computer program, the computer program when executed by a computer being adapted to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010650534.4A CN111914669A (en) | 2020-07-08 | 2020-07-08 | Method and device for detecting violation of tide lane, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010650534.4A CN111914669A (en) | 2020-07-08 | 2020-07-08 | Method and device for detecting violation of tide lane, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111914669A true CN111914669A (en) | 2020-11-10 |
Family
ID=73226525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010650534.4A Pending CN111914669A (en) | 2020-07-08 | 2020-07-08 | Method and device for detecting violation of tide lane, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111914669A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116564133A (en) * | 2023-07-05 | 2023-08-08 | 蘑菇车联信息科技有限公司 | Vehicle early warning method and device for tidal lane and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204143636U (en) * | 2014-11-10 | 2015-02-04 | 东软集团股份有限公司 | A kind of changeable driveway is broken rules and regulations proof system |
| CN108109390A (en) * | 2018-02-02 | 2018-06-01 | 沈阳市公安局交通警察支队 | A kind of road traffic changeable driveway regulator control system and regulation and control method |
| KR101889085B1 (en) * | 2017-12-07 | 2018-08-16 | 렉스젠(주) | Apparatus for generating traffic information using vehicle trajectory and method thereof |
| CN110533925A (en) * | 2019-09-04 | 2019-12-03 | 上海眼控科技股份有限公司 | Processing method, device, computer equipment and the storage medium of vehicle illegal video |
| CN111382704A (en) * | 2020-03-10 | 2020-07-07 | 北京以萨技术股份有限公司 | Vehicle line-pressing violation judgment method and device based on deep learning and storage medium |
-
2020
- 2020-07-08 CN CN202010650534.4A patent/CN111914669A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204143636U (en) * | 2014-11-10 | 2015-02-04 | 东软集团股份有限公司 | A kind of changeable driveway is broken rules and regulations proof system |
| KR101889085B1 (en) * | 2017-12-07 | 2018-08-16 | 렉스젠(주) | Apparatus for generating traffic information using vehicle trajectory and method thereof |
| CN108109390A (en) * | 2018-02-02 | 2018-06-01 | 沈阳市公安局交通警察支队 | A kind of road traffic changeable driveway regulator control system and regulation and control method |
| CN110533925A (en) * | 2019-09-04 | 2019-12-03 | 上海眼控科技股份有限公司 | Processing method, device, computer equipment and the storage medium of vehicle illegal video |
| CN111382704A (en) * | 2020-03-10 | 2020-07-07 | 北京以萨技术股份有限公司 | Vehicle line-pressing violation judgment method and device based on deep learning and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116564133A (en) * | 2023-07-05 | 2023-08-08 | 蘑菇车联信息科技有限公司 | Vehicle early warning method and device for tidal lane and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102368356B (en) | Monitoring system and method used for freeway ramp mouth | |
| WO2022116361A1 (en) | Traffic light control method and system based on urban trunk line vehicle queuing length | |
| CN112069643B (en) | Automatic driving simulation scene generation method and device | |
| CN101313345B (en) | System and method for detecting driving against road traffic regulation | |
| CN110532916B (en) | Motion trail determination method and device | |
| CN111145555B (en) | Method and device for detecting vehicle violation | |
| CN103778786A (en) | Traffic violation detection method based on significant vehicle part model | |
| CN110544382B (en) | Lane management method, device and system | |
| CN104575043A (en) | Automatic prompt system and method during passing of motor vehicle through pedestrian crosswalk | |
| CN105809964A (en) | Traffic warning method and device | |
| CN109427191A (en) | A kind of traveling detection method and device | |
| DE102014226957A1 (en) | price estimator | |
| CN111209880A (en) | Vehicle behavior identification method and device | |
| CN104574979A (en) | Photographing system and method for behaviors of motor vehicle passing through crosswalk not stopping to give way according to law | |
| CN111627217A (en) | Method, device and equipment for judging vehicle illegal turning around and storage medium | |
| CN115311888B (en) | Route guiding method, medium and system for avoiding congestion in parking lot | |
| CN107705577A (en) | A kind of real-time detection method and system based on lane line demarcation vehicle peccancy lane change | |
| CN111914669A (en) | Method and device for detecting violation of tide lane, electronic equipment and storage medium | |
| CN112329553A (en) | Lane line marking method and device | |
| CN111475591B (en) | Road association method and equipment for interest point acquisition | |
| CN112906428B (en) | Image detection region acquisition method and space use condition judgment method | |
| GB2342800A (en) | Measuring vehicle speed | |
| CN112270258A (en) | Violation information acquisition method and device for non-motor vehicle | |
| CN111583659A (en) | Vehicle violation determination method, device, equipment and medium | |
| CN114078318B (en) | Vehicle violation detection system |
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 |