CN112863189B - Behavior identification method and device for preventing overtaking and electronic equipment - Google Patents
Behavior identification method and device for preventing overtaking and electronic equipment Download PDFInfo
- Publication number
- CN112863189B CN112863189B CN201911191743.0A CN201911191743A CN112863189B CN 112863189 B CN112863189 B CN 112863189B CN 201911191743 A CN201911191743 A CN 201911191743A CN 112863189 B CN112863189 B CN 112863189B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- overtaking
- distance
- speed information
- hindering
- 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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a method and a device for identifying a behavior blocking overtaking and electronic equipment. The behavior identification method for preventing overtaking comprises the following steps: when the distance between a first vehicle and a second vehicle is judged to be abnormal according to the speed information fed back by the speed measuring equipment, a video stream of a speed measuring interval containing the speed measuring equipment in a video frame is obtained; tracking the first and second vehicles based on the video stream and calculating a centroid distance between the first and second vehicles; and judging whether the overtaking obstacle exists or not according to the change of the centroid distance. By utilizing the built basic detection equipment, the active identification of the maliciously-hindered overtaking behaviors is realized, the supervision of the maliciously-hindered overtaking behaviors is enhanced, and the vacancy in traffic supervision is made up.
Description
Technical Field
The invention relates to the technical field of traffic, in particular to a method and a device for recognizing a behavior of hindering overtaking and an electronic device.
Background
Civilized driving is not only the responsibility of each driver, but also an obligation. As driving travel becomes a common travel mode, civilized driving becomes more important. Although drivers all understand the importance of civilized driving, in the actual driving process, behaviors which obstruct normal driving of other people can be made due to personal emotion and the like. However, these obstructive behaviors often cause serious accidents. Thus, the driving behavior of the driver needs to be effectively supervised.
Maliciously impeding the passing of other vehicles during driving is a very dangerous act. However, in the prior art, no measures are provided for effectively detecting a behavior that maliciously hinders overtaking. The driver is difficult to worry about the difficulty in monitoring the malicious obstacle of overtaking due to the fact that the driver only depends on reporting and evidence-taking by other people.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for recognizing a behavior that hinders overtaking, and an electronic device.
In order to achieve the above purpose, the embodiment of the present invention adopts the following technical solutions:
in a first aspect, an embodiment provides a method for identifying a behavior that hinders passing, where the method for identifying the behavior that hinders passing includes:
when the distance between a first vehicle and a second vehicle is judged to be abnormal according to the speed information fed back by the speed measuring equipment, a video stream of a speed measuring interval containing the speed measuring equipment in a video frame is obtained;
tracking the first and second vehicles based on the video stream and calculating a centroid distance between the first and second vehicles;
and judging whether the overtaking obstacle exists or not according to the change of the centroid distance.
In a second aspect, an embodiment provides a passing prevention behavior recognition apparatus, including:
the acquisition module is used for acquiring a video stream containing a speed measurement interval of the speed measurement equipment in a video frame when the abnormal distance between the first vehicle and the second vehicle is judged according to the speed information fed back by the speed measurement equipment;
a tracking module to track the first and second vehicles based on the video stream and to calculate a centroid distance between the first and second vehicles;
and the judging module is used for judging whether the overtaking obstructing action exists according to the change of the centroid distance.
In a third aspect, embodiments provide an electronic device comprising a processor and a memory, the memory storing machine executable instructions capable of being executed by the processor, the processor being capable of executing the machine executable instructions to implement the method of any one of the preceding embodiments.
In a fourth aspect, embodiments provide a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method according to any of the preceding embodiments.
According to the method for recognizing the behavior of obstructing overtaking provided by the embodiment of the invention, when the abnormal distance between the first vehicle and the second vehicle is judged according to the speed information fed back by the speed measuring equipment, the corresponding video stream is obtained, and the video frame of the video stream comprises the speed measuring interval corresponding to the speed measuring equipment, so that the first vehicle and the second vehicle with the abnormal distance can be tracked according to the video stream. Then, a centroid distance between the first vehicle and the second vehicle is calculated based on the video stream. And judging whether the overtaking obstacle occurs between two cars or not by using the change rule of the centroid distance. By utilizing the built basic detection equipment, the active identification of the malicious overtaking obstacle is realized, and the supervision of the malicious overtaking obstacle is enhanced.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 shows one of the application scenarios provided by the embodiment of the present invention.
Fig. 2 shows a second application scenario provided by the embodiment of the present invention.
Fig. 3 shows a schematic diagram of an electronic device provided by an embodiment of the invention.
Fig. 4 is a flowchart illustrating one of the steps of the method for recognizing a passing obstacle behavior according to an embodiment of the present invention.
Fig. 5 is a diagram illustrating an example of a centroid distance between two vehicles in a video frame according to an embodiment of the present invention.
FIG. 6 shows a centroid distance variation trend graph for a plurality of overtaking conditions.
Fig. 7 shows a second step flowchart of the behavior recognition method for preventing overtaking provided by the embodiment of the invention.
Fig. 8 is a flowchart illustrating sub-steps of step S102 in fig. 7.
Fig. 9 shows an example diagram of a first mapped image region and a second mapped image region in a video frame.
Fig. 10 is a schematic diagram illustrating a behavior recognizing device for hindering overtaking provided by an embodiment of the present invention.
Icon: 10-a camera acquisition device; 20-a server; 30-a speed measuring device; 100-an electronic device; 110-a memory; 120-a processor; 130-a communication module; 200-a behavior recognition device hindering overtaking; 201-an acquisition module; 202-a tracking module; 203-judging module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It is noted that relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The phenomenon that the drivers on the outer road and the drivers on the inner road can not normally change the road due to personal emotion and other reasons, wherein the drivers on the outer road and the drivers on the inner road can continuously adjust the speed of the vehicles to drive at the same speed is frequently generated on the expressway or the intercity road. The above-mentioned behavior of outside lane drivers often results in the inside lane vehicles being in a rather dangerous state and may cause a significant traffic accident.
At present, no reliable active detection mode exists for the behavior of maliciously hindering overtaking. The final penalty is usually given by manually analyzing the surveillance video after an alarm or accident is caused by others. Such current situation has led to most outcoming drivers being lucky and unscrupulous.
In order to solve the problems, the application provides a method and a device for recognizing a behavior of hindering overtaking and an electronic device.
Please refer to fig. 1, which illustrates one of application scenarios of the behavior recognition method for preventing overtaking provided in the present application. As shown in fig. 1, the camera shooting device 10, the speed measuring device 30 and the server 20 are described above. The camera shooting collection device 10 is in communication connection with the server 20 through a network, so that data interaction is performed between the camera shooting collection device 10 and the server 20. The server 20 is further in communication connection with the speed measuring device 30 through a network, so that data interaction is performed between the speed measuring device 30 and the server 20.
The above-described camera shooting and capturing apparatus 10 may be a heavy-duty video apparatus erected aloft. The camera shooting and collecting device 10 is used for collecting video frames with a monitored area as a background to generate a video stream. The above-described camera capture apparatus 10 transmits the captured video stream to the server 20. It is understood that the above-mentioned camera shooting device 10 may comprise one or more, and each camera shooting device 10 is responsible for the video stream capturing of one monitored area.
The speed measuring device 30 may be a camera shooting speed measuring bayonet device erected near the road, or a radar speed measuring instrument installed on the ground. The speed measuring device 30 is configured to collect vehicle speed, vehicle information, and the like of the vehicle passing through the corresponding speed measuring interval, and feed back the collected data to the server 20, so as to facilitate the server 20 to determine whether a behavior hindering overtaking occurs based on the video stream and the vehicle speed information.
It can be understood that the speed measurement interval (i.e., the speed measurement section) of the speed measurement device 30 belongs to the monitored area of at least one camera shooting and collecting device 10. That is, a vehicle in which a speed measurement interval of the speed measurement device 30 occurs will also occur in the video stream captured by the camera capture device 10. Of course, the monitored area of the camera shooting and collecting device 10 may cover the speed measuring intervals of the plurality of speed measuring devices 30.
Please refer to fig. 2, which illustrates a second application scenario of the behavior recognition method for preventing overtaking provided in the present application. As shown in fig. 2, the above-mentioned camera shooting and collecting device 10 and the speed measuring device 30. The camera shooting and collecting device 10 is in communication connection with the corresponding speed measuring device 30 through a network, so that data interaction is performed between the camera shooting and collecting device 10 and the speed measuring device 30.
The above-described camera shooting and capturing apparatus 10 may be a heavy-duty video apparatus erected aloft. The camera shooting and collecting device 10 is used for collecting video frames with a monitored area as a background to generate a video stream.
The speed measuring device 30 is configured to collect vehicle speed, vehicle information, and the like of the vehicle passing through the corresponding speed measuring interval, and feed the collected data back to the camera capturing device 10, so as to facilitate the camera capturing device 10 to determine whether an overtaking obstacle occurs based on the video stream and the vehicle speed information.
Referring to fig. 3, fig. 3 illustrates an electronic device 100 implementing the inventive concepts of the present application. For example, the electronic device 100 may be the server 20 in the scenario shown in fig. 1, or may be the image capture device 10 in the scenario shown in fig. 2. Optionally, as shown in fig. 3, the electronic device 100 includes a memory 110, a processor 120, and a communication module 130. The memory 110, the processor 120 and the communication module 130 are electrically connected to each other directly or indirectly to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines.
The memory 110 is used to store programs or data. The Memory 110 may be, but is not limited to, a Random Access Memory 110 (RAM), a Read Only Memory 110 (ROM), a Programmable Read Only Memory 110 (PROM), an Erasable Read Only Memory 110 (EPROM), an electrically Erasable Read Only Memory 110 (EEPROM), and the like.
The processor 120 is used to read/write data or programs stored in the memory 110 and perform corresponding functions.
The communication module 130 is configured to establish a communication connection between the server 20 and another communication terminal through the network, and to transceive data through the network.
It should be understood that the configuration shown in fig. 3 is merely a schematic diagram of the configuration of the server 20, and that the server 20 may include more or fewer components than shown in fig. 3, or have a different configuration than shown in fig. 3. The components shown in fig. 3 may be implemented in hardware, software, or a combination thereof.
First embodiment
Referring to fig. 4, fig. 4 is a flowchart illustrating steps of a method for recognizing a behavior of hindering overtaking according to an embodiment of the present invention. Alternatively, the above-described behavior recognition method that hinders overtaking may be applied to the electronic apparatus 100. As shown in fig. 4, the method for recognizing the overtaking hindering behavior includes the following steps:
step S101, when it is determined that the distance between the first vehicle and the second vehicle is abnormal according to the vehicle speed information fed back by the speed measuring device 30, obtaining a video stream in a video frame, where the video stream includes a speed measuring interval of the speed measuring device 30.
The speed measuring device 30 is configured to measure the speed of the vehicle driving through the speed measuring road segment in real time, and feed the obtained speed information of the vehicle back to the electronic device 100. In some embodiments, the speed measuring device 30 can collect vehicle speed information of vehicles traveling on different lanes and feed the vehicle speed information back to the electronic device 100, so that the electronic device 100 can determine that the inter-vehicle distance between different vehicles is abnormal according to the vehicle speed information. It is to be understood that the first vehicle and the second vehicle are used to refer to two different vehicles and are not limited to a specific vehicle.
The above-mentioned inter-vehicle distance abnormality may be that a projected inter-vehicle distance between the first vehicle and the second vehicle is too short. It can be understood that, usually, the situation of overtaking between the first vehicle and the second vehicle can be judged when the projected vehicle distance is too short, and meanwhile, the overtaking blocking behavior usually occurs after that, so that a corresponding video stream is obtained so as to monitor whether the overtaking blocking behavior occurs.
Optionally, in an application scenario shown in fig. 1, each speed measuring device 30 corresponds to one image capturing device 10, and a correspondence between the image capturing devices 10 and the speed measuring devices 30 is stored in the server 20. In addition, the speed information carries an identifier of the corresponding speed measuring device 30. Thus, the step S101 may be: the electronic device 100 searches for the corresponding camera capturing device 10 according to the identifier of the speed measuring device 30 carried in the speed information corresponding to the first vehicle and the second vehicle, and obtains the video stream acquired by the corresponding camera capturing device 10.
Optionally, in the application scenario shown in fig. 2, each speed measuring device 30 corresponds to one image capturing device 10. Meanwhile, the speed measuring device 30 sends the collected vehicle speed information to the corresponding camera shooting and collecting device 10, so the step S101 may be: the camera capture device 10 may use the data it captures as a corresponding video stream.
Step S102, tracking the first vehicle and the second vehicle based on the video stream, and calculating the centroid distance between the first vehicle and the second vehicle.
In an embodiment of the present invention, the first vehicle and the second vehicle may be tracked according to the corresponding video streams, and the centroid distance between the first vehicle and the second vehicle may be calculated in real time during the tracking. Optionally, the centroid distance between the first vehicle and the second vehicle is calculated from the presence of video frames of the first vehicle and the second vehicle in the video stream. It will be appreciated that each frame of video where the first vehicle and the second vehicle are present is capable of calculating a centroid distance. For example, D in fig. 5 is the centroid distance between vehicle a and vehicle B.
And step S103, judging whether a behavior of preventing overtaking exists between the first vehicle and the second vehicle according to the change of the centroid distance.
The overtaking hindering behavior may be represented by a similar vehicle speed change of a vehicle driving on an outer lane (i.e., an ordinary lane adjacent to the overtaking lane) when the vehicle speed of the vehicle driving on the inner lane (i.e., the overtaking lane) changes. For example, the vehicles on the inner lane accelerate to overtake, and the vehicles on the outer lane accelerate correspondingly to prevent overtaking. The vehicles in the inner lane are forced to give up overtaking for deceleration, and at the same time, the vehicles in the outer lane are decelerated to prevent the vehicles from returning to the original lane. Thus, the centroid distance between the two vehicles will change during the overtaking hindering action. Therefore, in the embodiment of the present invention, the electronic device 100 obtains the change of the centroid distance according to all the obtained centroid distances. As shown in fig. 6, a curve 1 is a variation trend of the centroid distance between two vehicles during normal overtaking, a curve 2 is a variation trend of the centroid distance between two vehicles during abandoning overtaking, a curve 3 is a variation trend of the centroid distance between two vehicles during normal following, and a curve 4 is a variation trend of the centroid distance between two vehicles during occurrence of behavior hindering overtaking. Therefore, whether the overtaking obstacle exists between the two vehicles can be judged based on the change of the centroid distance.
In an embodiment of the present invention, the purpose of step S101 described above is to trigger the monitoring of the driving behaviour between the first vehicle and the second vehicle. After the driving behavior between the two vehicles is monitored, the behavior of hindering overtaking is identified through the cooperation of the step S102 and the step S103. Therefore, the existing foundation is utilized to perform the house, the active monitoring of the overtaking obstacle is realized, the vacancy in traffic management is made up, and the traffic safety is improved.
The following describes specific procedures and details for implementing the present solution.
In some embodiments, on the basis of fig. 4, as shown in fig. 7, the above behavior identification method for hindering overtaking may further include the steps of:
s201, judging whether a first vehicle and a second vehicle with abnormal vehicle distance appear according to the vehicle speed information fed back by the speed measuring equipment 30.
Optionally, the vehicle speed information further carries lane marks where the corresponding vehicle runs, and each piece of vehicle speed information corresponds to one collection time point.
In the embodiment of the present invention, the electronic device 100 stores the received vehicle speed information, and determines whether the distance between the first vehicle and the second vehicle from different lanes is abnormal based on the vehicle speed information collected by the same speed measurement device 30. For convenience of description, a vehicle passing through the speed measuring device 30 first serves as a first vehicle, and a vehicle passing through the speed measuring device 30 later serves as a second vehicle.
As an embodiment, first, according to a first vehicle speed information of a first vehicle, a first collecting time point corresponding to the first vehicle speed information, and a second collecting time point corresponding to a second vehicle speed information of a second vehicle, using a formula:
d=(t2-t1)v1,
a projected vehicle distance between the first vehicle and the second vehicle is calculated. D represents a projected vehicle distance between the first vehicle and the second vehicle, and t1Represents the first acquisition time point, t2Represents a second acquisition time point, v above1Representing first vehicle speed information.
And secondly, comparing the obtained projected vehicle distance with a preset distance value, and if the projected vehicle distance is smaller than the preset distance value, judging that the vehicle distance between the first vehicle and the second vehicle is abnormal.
As another embodiment, in order to avoid the misjudgment caused by traffic congestion, S201 may be: and when the vehicle speed information of the first vehicle and the second vehicle is greater than the preset vehicle speed, calculating the projection vehicle distance based on the vehicle speed information of the first vehicle and the second vehicle and the acquisition time point of the vehicle speed information. For example, when the vehicle speeds of the first vehicle and the second vehicle driving in different lanes both exceed 60km/h, the vehicle speed information of the first vehicle and the second vehicle and the acquisition time point of the vehicle speed information calculate the projected vehicle distance. And if the projected vehicle distance is smaller than the preset distance value, judging that the vehicle distance between the first vehicle and the second vehicle is abnormal.
As another embodiment, in order to avoid the erroneous determination caused by traffic congestion, S201 may be: the projection vehicle distance is calculated based on the vehicle speed information of the first vehicle and the second vehicle and the acquisition time point of the vehicle speed information. If the projected vehicle distance is abnormal, judging whether the vehicle speed information of the first vehicle and the second vehicle is greater than the preset vehicle speed. If the vehicle speed is greater than the preset vehicle speed, the process goes to step S101, otherwise, the process is ended.
As can be appreciated, the field of view of the camera capturing device 10 is large in order to enable continuous tracking of the vehicle. However, it is often difficult to perform license plate recognition on video frames captured under a large field of view. To accurately lock the first and second vehicles being tracked in the video stream. As shown in fig. 8, the step S102 may include the following steps:
in the substep S102-1, the first vehicle and the second vehicle are identified according to the corresponding first mapping image region and the second mapping image region in each frame of video frame of the speed measuring device 30.
The mapped image area may be an area in real space where a particular area is mapped to an image area in a video frame. The specific region may be set in advance. In other words, the image content presented by the above-described mapped image region is a specific region in the real space. Optionally, the specific areas corresponding to the first mapping image area and the second mapping image area are both related to the speed measuring device 30. For example, as shown in fig. 9, the first mapping image area and the second mapping image area are adjacent to the image area where the speed measuring device 30 is located in the video frame. Optionally, the specific area of the first mapping image area is a position range where the first vehicle is likely to appear after the distance between the first vehicle and the second vehicle is determined to be abnormal, and the specific area of the second mapping image area is a position range where the second vehicle is likely to appear after the distance between the first vehicle and the second vehicle is determined to be abnormal.
It is understood that the corresponding image coordinates of the first mapping image area and the second mapping image area in the video frame can be obtained through a previous test. The image coordinates corresponding to the first mapping image area and the second mapping image area in the video frame acquired by the same camera acquisition device 10 are the same.
In some embodiments, if the camera shooting device 10 corresponds to a plurality of speed measuring devices 30, the video frame has a plurality of sets of first mapping image areas and second mapping image areas. Each set of the first mapping image area and the second mapping image area corresponds to the speed measuring device 30.
In an embodiment of the present invention, comparing the first mapping image regions of at least two frames of video frames, the first vehicle will have a position change in the first mapping image region. Comparing the second mapping image areas of the at least two frames of video frames, the second vehicle will have a position change in the second mapping image areas.
Based on the above principle, the step S102-1 may include the following steps:
(1) and determining the vehicles which appear in the first mapping image area and have different positions in the first mapping image area of different video frames as the first vehicle.
(2) And determining the vehicles which appear in the second mapping image area and have different positions in the second mapping image area of different video frames as second vehicles.
The first vehicle and the second vehicle can be locked from the video frame on the premise of not depending on license plate recognition. In this manner, the first vehicle and the second vehicle may be tracked in the video stream. The defect that the license plate identification is difficult to carry out under a large visual field is overcome.
And a substep S102-2, calculating corresponding centroid distances according to the image areas occupied by the first vehicle and the second vehicle in each frame of video frame.
In the embodiment of the invention, after the first vehicle and the second vehicle are determined from the video frame, the first image area and the second image area occupied by the first vehicle and the second vehicle in the video frame are respectively obtained, and the image distance between the centroids of the first image area and the second image area is determined as the centroid distance.
It will be appreciated that the first vehicle and the second vehicle will appear in a plurality of consecutive video frames, so each video frame in which the first vehicle and the second vehicle appear corresponds to a centroid distance. The change of the centroid distance between the first vehicle and the second vehicle can be obtained by calculating the centroid distance based on the video frames of the first vehicle and the second vehicle appearing in each frame.
In some embodiments, the step S103 may include:
s103-1, comparing the centroid distance with a preset numerical value interval.
The preset value interval may be a value interval determined through a large number of tests, and the preset value interval includes an upper limit value and a lower limit value. The upper limit value is obtained according to statistics of a plurality of cases for successful overtaking, and the lower limit value is obtained according to statistics of cases for abandoning overtaking.
In the embodiment of the invention, the newly calculated centroid distance is compared with the upper limit value and the lower limit value of the preset numerical interval, and whether the centroid distance belongs to the preset numerical interval is judged.
S103-2, if the centroid distance does not belong to the preset numerical value interval, judging that no behavior of obstructing overtaking exists.
In the embodiment of the invention, when the newly obtained centroid distance does not belong to the preset numerical value interval any more, the driving behaviors of the two vehicles are judged to be normal, and the behavior of obstructing overtaking does not occur in the overtaking process. Otherwise, the overtaking prevention behavior may exist between the two vehicles.
Of course, in order to avoid misinterpreting the normal car following behavior as the behavior of hindering overtaking, the step S103 may further include:
s103-3, if the centroid distance belongs to a preset numerical value interval, calculating the mean square error based on the obtained centroid distance.
In the embodiment of the invention, the mean square error calculation can be carried out in real time by using the obtained centroid distance. For example, each time a new centroid distance is obtained, the corresponding mean square error is calculated based on the centroid distance and the other centroid distances that have been obtained.
S103-4, judging that the overtaking is blocked when the calculated mean square error is larger than a preset value.
It can be understood that under the condition of normal vehicle following, the centroid distance of the two vehicles is less changed, and therefore, the corresponding mean square error is less. On the contrary, when the overtaking behavior is obstructed, the variation fluctuation of the centroid distance of the two vehicles is large, and the corresponding mean square error is large. Therefore, the behavior of obstructing overtaking can be distinguished by comparing the mean square error with the preset value.
After the occurrence of the behavior of obstructing the overtaking is judged, the alarm can be actively sent to the traffic supervision department so as to be convenient for the traffic supervision department to carry out punishment.
In other embodiments, the display screen mounted on the roadway is also communicatively coupled to the electronic device 100. After the electronic device 100 determines that the overtaking obstructing action occurs, the display screen is controlled to display and warn the license plate of the vehicle obstructing the overtaking of other people. It can be understood that the license plate number displayed by the display screen is the license plate number carried in the collected speed information of the outside road vehicle.
Compared with the prior art, the method for identifying the overtaking hindering behavior comprises the following steps: the overtaking behavior is supervised by triggering the vehicle speed information acquired by the speed measuring device 30, and the first vehicle and the second vehicle are locked in the video stream by using the preset mapping image area and tracked. The problem that vehicle identification is difficult to perform on video streams collected under a large visual field is solved. And judging whether the overtaking blocking behavior occurs between the two vehicles in the overtaking process or not through the change of the centroid distance displayed by the first vehicle and the second vehicle in the video stream. The gap in traffic management is filled, and the driving safety is improved.
In order to execute the corresponding steps in the above-described embodiments and various possible manners, an implementation manner of the overtaking-hindering behavior recognizing apparatus 200 is given below, and optionally, the overtaking-hindering behavior recognizing apparatus 200 may adopt the device structure of the electronic device 100 shown in fig. 3. Further, referring to fig. 10, fig. 10 is a functional block diagram of a behavior recognition device 200 for preventing overtaking provided by an embodiment of the present invention. It should be noted that the basic principle and the technical effects of the overtaking-preventing behavior recognition device 200 provided in the present embodiment are the same as those of the above-mentioned embodiment, and for the sake of brief description, no part of the present embodiment is mentioned, and reference may be made to the corresponding contents in the above-mentioned embodiment. The overtaking obstacle behavior recognition device 200 includes: an acquisition module 201, a tracking module 202 and a judgment module 203.
The obtaining module 201 is configured to obtain a video stream, which includes a speed measurement interval of the speed measurement device 30, in a video frame when it is determined that a vehicle distance between the first vehicle and the second vehicle is abnormal according to the vehicle speed information fed back by the speed measurement device 30.
In an embodiment of the present invention, the step S101 may be executed by the obtaining module 201.
A tracking module 202 for tracking the first vehicle and the second vehicle based on the video stream and calculating a centroid distance between the first vehicle and the second vehicle.
In an embodiment of the present invention, the step S102 may be executed by the tracking module 202. Optionally, the tracking module 202 includes: an identification submodule and a calculation submodule.
And the identification submodule is configured to identify the first vehicle and the second vehicle according to a first mapping image area and a second mapping image area corresponding to each frame of the video frame of the speed measurement device 30.
In an embodiment of the present invention, the sub-step S102-1 may be performed by an identification sub-module. For example, the identification sub-module may be configured to identify a vehicle displaced within the first mapped image region as the first vehicle based on a plurality of frames of the video frame. And may be further configured to identify a vehicle displaced within the second mapped image region as the second vehicle based on a plurality of frames of the video frame.
And the calculating submodule is used for calculating the corresponding centroid distance according to the image positions of the first vehicle and the second vehicle in each frame of the video frame.
In an embodiment of the present invention, the sub-step S102-2 may be performed by a computation sub-module.
And the judging module 203 is used for judging whether the overtaking obstacle exists according to the change of the centroid distance.
In an embodiment of the present invention, the step S103 may be executed by the determining module 203. Optionally, the determining module 203 is further configured to compare the centroid distance with a preset value interval, and if the centroid distance does not belong to the preset value interval, determine that the overtaking obstacle does not exist.
Optionally, the determining module 203 is further configured to calculate a mean square error based on the obtained centroid distance if the centroid distance belongs to the preset numerical value interval; and when the calculated mean square error is larger than a preset value, judging that the overtaking hindering behavior occurs.
In some embodiments, the overtaking hindering behavior recognition device 200 further comprises an abnormality recognition module. The abnormality identification module is configured to determine whether the first vehicle and the second vehicle have an abnormal vehicle distance according to the vehicle speed information fed back by the speed measurement device 30.
Optionally, the abnormality identification module is specifically configured to calculate a projected vehicle distance based on the vehicle speed information of the first vehicle and the second vehicle and the collection time point of the vehicle speed information when the vehicle speed information of the first vehicle and the second vehicle is greater than a preset vehicle speed; and if the projected vehicle distance is smaller than a preset distance value, judging that the vehicle distance between the first vehicle and the second vehicle is abnormal.
Alternatively, the modules may be stored in the memory 110 shown in fig. 3 in the form of software or Firmware (Firmware) or be fixed in an Operating System (OS) of the electronic device 100, and may be executed by the processor 120 in fig. 3. Meanwhile, data, codes of programs, and the like required to execute the above-described modules may be stored in the memory 110.
In summary, the embodiments of the present invention provide a method and an apparatus for recognizing a behavior hindering overtaking, and an electronic device. The behavior identification method for preventing overtaking comprises the following steps: when the distance between a first vehicle and a second vehicle is judged to be abnormal according to the speed information fed back by the speed measuring equipment, a video stream of a speed measuring interval containing the speed measuring equipment in a video frame is obtained; tracking the first and second vehicles based on the video stream and calculating a centroid distance between the first and second vehicles; and judging whether the overtaking obstacle exists or not according to the change of the centroid distance. By utilizing the built basic detection equipment, the active identification of the malicious overtaking obstacle is realized, and the supervision of the malicious overtaking obstacle is enhanced.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A behavior recognition method for hindering overtaking, characterized in that the behavior recognition method for hindering overtaking comprises:
when the distance between a first vehicle and a second vehicle is judged to be abnormal according to the speed information fed back by the speed measuring equipment, a video stream of a speed measuring interval containing the speed measuring equipment in a video frame is obtained;
the abnormal vehicle distance represents that a projected vehicle distance between a first vehicle and a second vehicle is smaller than a preset distance value, wherein the projected vehicle distance is determined according to first vehicle speed information of the first vehicle, a first acquisition time point corresponding to the first vehicle speed information and a second acquisition time point corresponding to second vehicle speed information of the second vehicle;
tracking the first and second vehicles based on the video stream and calculating a centroid distance between the first and second vehicles;
and judging whether the overtaking obstacle exists or not according to the change of the centroid distance.
2. The method of claim 1, wherein the step of tracking the first and second vehicles based on the video stream comprises:
and identifying the first vehicle and the second vehicle according to a first mapping image area and a second mapping image area corresponding to the speed measuring equipment in each frame of the video frame.
3. The method for recognizing a behavior of hindering overtaking as claimed in claim 2, wherein the step of recognizing the first vehicle and the second vehicle according to the corresponding first mapping image area and the second mapping image area of the speed measuring device in each frame of the video frame comprises:
identifying a vehicle displaced within the first mapped image region as the first vehicle based on a plurality of frames of the video;
and identifying a vehicle displaced in the second mapping image area as the second vehicle based on the plurality of frames of the video.
4. The overtaking hindering behavior recognition method as claimed in claim 1, wherein the step of determining whether there is an overtaking hindering behavior according to the change of the centroid distance comprises:
comparing the centroid distance with a preset numerical value interval;
and if the centroid distance does not belong to the preset numerical value interval, judging that the overtaking hindering behavior does not exist.
5. The overtaking hindering behavior recognition method as recited in claim 4, wherein the step of determining whether there is an overtaking hindering behavior according to the change in the centroid distance further comprises:
if the centroid distance belongs to the preset numerical value interval, calculating a mean square error based on the obtained centroid distance;
and when the calculated mean square error is larger than a preset value, judging that the overtaking hindering behavior occurs.
6. The overtaking hindering behavior recognition method according to claim 1, wherein the overtaking hindering behavior recognition method further comprises: judging whether the first vehicle and the second vehicle with abnormal vehicle distance appear or not according to the vehicle speed information fed back by the speed measuring equipment; wherein the first vehicle and the second vehicle travel in different lanes;
the step of judging whether the first vehicle and the second vehicle with abnormal vehicle distance appear according to the vehicle speed information fed back by the speed measuring equipment comprises the following steps:
when the vehicle speed information of the first vehicle and the second vehicle is larger than a preset vehicle speed, calculating a projection vehicle distance based on the vehicle speed information of the first vehicle and the second vehicle and the acquisition time point of the vehicle speed information;
and if the projected vehicle distance is smaller than a preset distance value, judging that the vehicle distance between the first vehicle and the second vehicle is abnormal.
7. An overtaking hindering behavior recognition apparatus characterized by comprising:
the acquisition module is used for acquiring a video stream containing a speed measurement interval of the speed measurement equipment in a video frame when the abnormal distance between the first vehicle and the second vehicle is judged according to the speed information fed back by the speed measurement equipment;
the abnormal vehicle distance represents that a projected vehicle distance between a first vehicle and a second vehicle is smaller than a preset distance value, wherein the projected vehicle distance is determined according to first vehicle speed information of the first vehicle, a first acquisition time point corresponding to the first vehicle speed information and a second acquisition time point corresponding to second vehicle speed information of the second vehicle;
a tracking module to track the first and second vehicles based on the video stream and to calculate a centroid distance between the first and second vehicles;
and the judging module is used for judging whether the overtaking obstructing action exists according to the change of the centroid distance.
8. The overtaking impeding behavior recognition device of claim 7 wherein the tracking module comprises:
the identification submodule is used for identifying the first vehicle and the second vehicle according to a first mapping image area and a second mapping image area which correspond to the speed measuring equipment in each frame of the video frame;
and the calculating submodule is used for calculating the corresponding centroid distance according to the image positions of the first vehicle and the second vehicle in each frame of the video frame.
9. An electronic device comprising a processor and a memory, the memory storing machine executable instructions executable by the processor to perform the method of any one of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911191743.0A CN112863189B (en) | 2019-11-28 | 2019-11-28 | Behavior identification method and device for preventing overtaking and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911191743.0A CN112863189B (en) | 2019-11-28 | 2019-11-28 | Behavior identification method and device for preventing overtaking and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112863189A CN112863189A (en) | 2021-05-28 |
CN112863189B true CN112863189B (en) | 2022-04-12 |
Family
ID=75995595
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911191743.0A Active CN112863189B (en) | 2019-11-28 | 2019-11-28 | Behavior identification method and device for preventing overtaking and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112863189B (en) |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE10324725A1 (en) * | 2003-05-30 | 2004-12-16 | Wabco Gmbh & Co.Ohg | Procedure for regulating overtaking in a non-passing lane |
CN101645204A (en) * | 2009-07-30 | 2010-02-10 | 杨迎春 | Communication device for avoiding risks among vehicles and data processing method thereof |
CN201698589U (en) * | 2010-04-15 | 2011-01-05 | 国通道路交通管理工程技术研究中心有限公司 | Equipment for detecting low-speed vehicle driving on fast lane for long time |
EP2797027A1 (en) * | 2013-04-25 | 2014-10-29 | Volvo Car Corporation | A vehicle driver alert arrangement, a vehicle and a method for alerting a vehicle driver |
DE102013104292A1 (en) * | 2013-04-26 | 2014-10-30 | Hella Kgaa Hueck & Co. | Method and device for controlling high-beam headlamps in an overtaking process and means for detecting an overtaking process |
CN104269073B (en) * | 2014-09-11 | 2016-05-18 | 同济大学 | A kind of reverse track based on truck traffic method for early warning of overtaking other vehicles |
CN105047019B (en) * | 2015-07-07 | 2017-08-11 | 长安大学 | A kind of passenger stock prevent rear car overtake other vehicles after lane change determination methods and device suddenly |
CN106114520A (en) * | 2016-06-30 | 2016-11-16 | 上海卓易科技股份有限公司 | A kind of vehicle drive lane change alert system and method |
CN106585639A (en) * | 2016-10-24 | 2017-04-26 | 深圳市元征科技股份有限公司 | Driving method and system |
KR20180092204A (en) * | 2017-02-08 | 2018-08-17 | 주식회사 만도 | System for Lane Detection Warning Of Vehicle And Method Of Driving Thereof |
DE102017212277B3 (en) * | 2017-07-18 | 2018-09-06 | Robert Bosch Gmbh | Danger detection with intentional lane change |
JP7021983B2 (en) * | 2018-03-07 | 2022-02-17 | 本田技研工業株式会社 | Vehicle control devices, vehicle control methods, and programs |
CN108583426B (en) * | 2018-03-14 | 2022-05-03 | 斑马网络技术有限公司 | Overtaking indicating system and indicating method thereof |
CN110053621B (en) * | 2019-04-09 | 2020-12-29 | 上海丰豹商务咨询有限公司 | Overtaking method for automatically driving overtaking lane |
-
2019
- 2019-11-28 CN CN201911191743.0A patent/CN112863189B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN112863189A (en) | 2021-05-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11322018B2 (en) | Determining causation of traffic events and encouraging good driving behavior | |
CN110164130B (en) | Traffic incident detection method, device, equipment and storage medium | |
US9047773B2 (en) | Exceptional road-condition warning device, system and method for a vehicle | |
CN108346288B (en) | Road section operation state early warning method and device and electronic equipment | |
KR101921168B1 (en) | Traffic violation managing system | |
CA2925843C (en) | System for traffic behaviour surveillance | |
JP6690702B2 (en) | Abnormal traveling detection device, abnormal traveling detection method and program thereof | |
CN111028503B (en) | Vehicle lane change monitoring method and device | |
JP3758534B2 (en) | Traffic flow anomaly detection apparatus and method | |
KR20230091400A (en) | Intelligent traffic control system using risk calculation | |
CN114512002A (en) | Road surface abnormity detection method and device | |
CN112863189B (en) | Behavior identification method and device for preventing overtaking and electronic equipment | |
CN113989715A (en) | Vehicle parking violation detection method and device, electronic equipment and storage medium | |
US20220161798A1 (en) | Method and device for detecting a traffic law violation due to the allowable distance between a following vehicle and a guide vehicle being undershot | |
JP2019079150A (en) | Danger sign determination device, danger sign determination system, vehicle, and program | |
JP4311647B2 (en) | Management apparatus, management system, management method, and program | |
EP3269608B1 (en) | Detection of tailgating situations | |
CN111784973B (en) | MDVR equipment integration fatigue detection method of fleet management platform | |
CN111047878B (en) | Traffic violation determination method and device and traffic access | |
CN112447055A (en) | Monitoring and warning method for low-speed driving on expressway | |
CN113674311A (en) | Abnormal behavior detection method and device, electronic equipment and storage medium | |
CN112597945A (en) | Vehicle detection method and device | |
CN110969895A (en) | Vehicle distance detection method, device, system and server | |
US12027041B1 (en) | Systems and methods for detecting stop sign vehicle compliance | |
CN114529871B (en) | Drunk driving identification method and device, electronic equipment and storage medium |
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 |