CN115909758B - Laser radar-based vehicle detection method, device, equipment and storage medium - Google Patents
Laser radar-based vehicle detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115909758B CN115909758B CN202310028826.8A CN202310028826A CN115909758B CN 115909758 B CN115909758 B CN 115909758B CN 202310028826 A CN202310028826 A CN 202310028826A CN 115909758 B CN115909758 B CN 115909758B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target
- detection area
- target object
- parameters
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The embodiment of the invention discloses a laser radar-based vehicle detection method, a device, equipment and a storage medium, wherein the laser radar-based vehicle detection method is applied to a vehicle detection device arranged in a detection area, the vehicle detection device comprises a laser radar, the laser radar scanning area is the detection area, and the method specifically comprises the following steps: scanning targets to be detected in a detection area by using a laser radar to obtain a first target object set in the detection area, and screening the first target object set by using attribute parameters and motion parameters of a preset standard vehicle to obtain a target vehicle set; according to the motion parameters of each target vehicle in the target vehicle set, judging whether the vehicle violates, and if the vehicle violations are confirmed, triggering an alarm mode.
Description
Technical Field
The invention relates to the technical field of traffic intelligent vehicle monitoring, in particular to a laser radar-based vehicle detection method, a laser radar-based vehicle detection device, laser radar-based vehicle detection equipment and a laser radar-based storage medium.
Background
The illegal and illegal behavior of vehicles in the passing process is one of the important reasons for causing traffic accidents, so that traffic intelligentization is utilized to monitor the driving of vehicles, and the method is widely applied.
At present, most of the image recognition technologies are used for recognizing and detecting targets in detection areas, but: the image recognition technology has high requirements on weather and light rays, depends on sunlight, has weak capability of judging the spatial position of a moving target, and cannot be recognized normally under the condition of lacking a requisite, so that the problem that the detection accuracy of vehicles on a traffic road is not high and the illegal vehicles cannot be recognized and alarmed exists in the prior art when the illegal behaviors of the vehicles are detected.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a laser radar-based vehicle detection method, device, apparatus and storage medium for solving the problem that the accuracy of determining the spatial position of a vehicle is not high and that illegal vehicles cannot be identified and distinguished.
To achieve the above object, a first aspect of the present application provides a vehicle detection method based on a laser radar, the method being applied to a vehicle detection device disposed in a detection area, the vehicle detection device including the laser radar, an area scanned by the laser radar being the detection area, the method including:
scanning targets to be detected in the detection area by using the laser radar to obtain a first target object set in the detection area, wherein the first target object set comprises first target objects suspected to be vehicles and personnel in the detection area;
screening the first target object set by utilizing the attribute parameters and the motion parameters of the preset standard vehicle to obtain a target vehicle set;
judging whether a vehicle violation exists or not according to the motion parameters of each target vehicle in the target vehicle set;
and if the vehicle violation is confirmed, triggering an alarm mode.
Further, the scanning, by using the lidar, the target to be detected in the detection area to obtain a first target object set in the detection area specifically includes:
scanning the detection area once by using the laser radar to obtain point cloud data of one frame in the detection area, and deleting background points in the point cloud data to obtain foreground points in the detection area;
and clustering the foreground points by using a clustering algorithm to obtain a first target object set.
Further, the screening the first target object set by using the attribute parameter and the motion parameter of the preset standard vehicle to obtain a target vehicle set specifically includes:
performing attribute analysis on each first target object to obtain attribute parameters of each first target object;
screening the first object set according to preset attribute parameters of the standard vehicle and attribute parameters of the first objects to obtain a second object set, wherein the second object set comprises second objects suspected to be vehicles;
performing target tracking on each second target object to obtain motion parameters of each second target object;
and screening the second target object set according to the preset motion parameters of the standard vehicle and the motion parameters of the second target objects to obtain a target vehicle set.
Further, the attribute parameters of the first object at least comprise length, width and coordinate information of the first object;
the attribute parameters of the standard vehicle at least comprise length, width and coordinate information of the standard vehicle;
the step of screening the first target object set according to the preset attribute parameters of the standard vehicle and the attribute parameters of the first target objects to obtain a second target object set, specifically includes:
and carrying out matching screening on each first object in sequence by utilizing the length, width and coordinate information of the standard vehicle and the length, width and coordinate information of each first object to obtain a second object set.
Further, the performing object tracking on each second object to obtain a motion parameter of each second object specifically includes:
performing target tracking on each second target object by using a target tracking algorithm to obtain the position information of each second target object at different moments;
and analyzing and calculating according to the position information of each second target object at different moments to obtain the motion parameters of each second target object.
Further, the motion parameters of the second object at least comprise a motion direction and a motion speed of the second object;
the motion parameters of the standard vehicle at least comprise the motion direction and the motion speed of the standard vehicle;
the second target object set is screened according to the preset motion parameters of the standard vehicle and the motion parameters of the second target objects, so as to obtain a target vehicle set, which specifically comprises:
and sequentially carrying out matching screening on each second object by utilizing the movement direction and the movement speed of the standard vehicle and the movement direction and the movement speed of each second object to obtain a target vehicle set.
Further, the vehicle violation at least includes vehicle reverse, vehicle overspeed, vehicle low speed, and vehicle stay;
judging whether the vehicle violates the rule according to the motion parameters of each target vehicle in the target vehicle set, and specifically comprising the following steps:
judging whether vehicles are in reverse running in the detection area according to the movement directions of the target vehicles;
if a target vehicle with the motion direction inconsistent with the preset motion direction exists, determining that the vehicle is in reverse running;
and/or;
judging whether the vehicle runs at a low speed or overspeed in the detection area according to the movement speed of each target vehicle;
if a target vehicle with the movement speed not within the preset movement speed range exists, determining that the vehicle runs at a low speed or overspeed;
or;
judging whether a vehicle stays in the detection area according to the movement direction or the movement speed of each target vehicle;
if there is a target vehicle without a moving direction or a target vehicle with a moving speed of zero, it is determined that there is a vehicle stop.
To achieve the above object, a second aspect of the present application provides a laser radar-based vehicle detection apparatus, the apparatus comprising: the system comprises a laser radar unit, a vehicle screening unit and a violation warning unit;
the laser radar unit is used for scanning a target to be detected in the detection area by using the laser radar to obtain a first target object set in the detection area, wherein the first target object set comprises a first target object suspected to be a vehicle or a person in the detection area;
the vehicle screening unit is used for screening the first target object set by utilizing the attribute parameters and the motion parameters of the preset standard vehicle to obtain a target vehicle set;
the violation warning unit is used for judging whether the vehicle is in violation or not according to the motion parameters of each target vehicle in the target vehicle set;
and if the vehicle violation is confirmed, triggering an alarm mode.
To achieve the above object, a third aspect of the present application provides a computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor, causes the processor to perform the steps of the method according to the first aspect.
To achieve the above object, a fourth aspect of the present application provides a computer device comprising a memory and a processor, characterized in that the memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the method according to the first aspect.
The embodiment of the invention has the following beneficial effects:
the vehicle detection method based on the laser radar is applied to a vehicle detection device arranged in a detection area, the vehicle detection device comprises the laser radar, the area scanned by the laser radar is the detection area, and the method specifically comprises the following steps: scanning targets to be detected in a detection area by using a laser radar to obtain a first target object set in the detection area, and screening the first target object set by using attribute parameters and motion parameters of a preset standard vehicle to obtain a target vehicle set; according to the motion parameters of each target vehicle in the target vehicle set, judging whether the vehicle violates, if the vehicle violations are confirmed, triggering an alarm mode, detecting a detection area by using a laser radar, obtaining space positioning information with higher accuracy, screening suspected vehicles twice to obtain more accurate vehicle information, judging the violations according to the motion information of the vehicles, and further alarming the violating vehicles.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Wherein:
FIG. 1 is a schematic diagram of a flow of a lidar-based vehicle detection method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a refinement flow of step 200 of FIG. 1 in an embodiment of the present application;
FIG. 3a is a schematic illustration of an embodiment of the present application in a situation where no offending vehicle is present;
FIG. 3b is a schematic diagram of an embodiment of the present application in the context of an offending vehicle;
FIG. 4 is a block diagram of a lidar-based vehicle detection device in an embodiment of the present application;
fig. 5 is an internal structural diagram of a computer device in an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In an embodiment of the present application, referring to fig. 1, fig. 1 is a schematic diagram of a flow of a laser radar-based vehicle detection method according to an embodiment of the present invention, where the method is applied to a vehicle detection device disposed in a detection area, the vehicle detection device includes a laser radar, and an area scanned by the laser radar is a detection area, and the method includes:
step 100, scanning an object to be detected in a detection area by using a laser radar to obtain a first object set in the detection area, wherein the first object set at least comprises first object suspected to be a vehicle and a person in the detection area.
And 200, screening the first target object set by utilizing the attribute parameters and the motion parameters of the preset standard vehicle to obtain a target vehicle set.
And 300, judging whether the vehicle violates the rule according to the motion parameters of each target vehicle in the target vehicle set.
Step 400, if the vehicle violation is confirmed, triggering an alarm mode.
In a feasible embodiment of the present application, the laser radar may be erected beside the road of the detected area, and the passing vehicles in the detected area are scanned so as to obtain information of all suspected vehicles and people in the detected area, and in the embodiment of the present application, the laser radar with performance parameters of 20HZ/S and a scanning angle of 270 ° may be adopted, so that the laser radar is utilized to scan the detected area, and a first target set of all suspected vehicles and people in the detected area may be obtained so as to achieve the purpose of filtering the background of the detected area.
After targets of suspected vehicles and people are acquired, the attribute parameters and the motion parameters of all the first targets in the first target object set are compared and screened one by utilizing the acquired attribute parameters and the motion parameters of the preset standard vehicles, so that target vehicles meeting the attribute parameters and the motion parameters of the standard vehicles are obtained, a target vehicle set is obtained according to all the target vehicles meeting the standard, more accurate target vehicle information can be obtained through screening all the first targets twice by utilizing the attribute parameters and the motion parameters, the attribute parameters can comprise the length, the width and the coordinate information of the targets, and the motion parameters can comprise the motion direction and the motion speed of the targets.
When the first target object is screened, the motion parameters of the target vehicle can be obtained, so that the target vehicle can be subjected to violation detection by utilizing the motion parameters of the target vehicle, and whether the target vehicle is violated or not is judged, so that the aim of monitoring the target vehicle in the detection area is fulfilled.
If the target vehicle is confirmed to be illegal, an alarm mode is triggered, and an alarm is sent to the illegal vehicle so as to reduce the illegal behavior of the target vehicle.
According to the vehicle detection method, the laser radar can be used for detecting the detection area, the suspected vehicles are screened twice, vehicle information with higher accuracy can be obtained, the vehicles are subjected to illegal action judgment by using the vehicle information, and further the illegal vehicles are warned, so that the problems that the vehicle detection accuracy is not high on a passing road, and the illegal vehicles cannot be identified and warned are solved.
Further, step 100, scanning the target to be detected in the detection area by using a laser radar to obtain a first target object set in the detection area, specifically including:
step 110, scanning the detection area by using a laser radar to obtain point cloud data of one frame in the detection area, and deleting background points in the point cloud data to obtain foreground points in the detection area.
And 120, clustering foreground points by using a clustering algorithm to obtain a first target object set.
In a feasible embodiment of the application, the laser radar is utilized to scan the detection area for one circle, all point cloud data in the detection area can be obtained, points which are not interested are deleted according to the obtained point cloud data, and points which are not interested are reserved, wherein the points which are not interested can be points comprising buildings and trees, and the points which are interested can be points comprising people and vehicles; and taking all points which are not interested as background points and all points which are interested as foreground points, so that background filtering is carried out on a detection area, and interference of the background on a detection result is eliminated.
After background filtering is carried out on point cloud data in a detection area, clustering analysis is carried out on foreground points obtained through background filtering by using a DBSCAN clustering algorithm, so that first target objects of all suspected vehicles and people in the detection area are obtained, and a set of all first target objects is used as a first target object set.
All foreground points in the detection area are obtained through a laser radar, and the foreground points are clustered by using a clustering algorithm to obtain a first target object, so that the purposes of carrying out background filtering on the detection area and obtaining the first target object are achieved.
Further, referring to fig. 2, fig. 2 is a schematic diagram of a refinement process of step 200 of fig. 1 in the embodiment of the present application, which specifically includes:
and 210, performing attribute analysis on each first target object to obtain attribute parameters of each first target object.
Step 220, screening the first object set according to the attribute parameters of the preset standard vehicle and the attribute parameters of each first object to obtain a second object set, wherein the second object set comprises second objects suspected to be vehicles.
And 230, performing target tracking on each second target object to obtain the motion parameters of each second target object.
Step 240, screening the second object set according to the preset motion parameters of the standard vehicle and the motion parameters of the second objects to obtain a target vehicle set.
In a possible embodiment of the present application, attribute analysis is performed by using point cloud data of each first object in the first object set, so that attribute parameters of each first object can be obtained, where the attribute parameters of the first object at least include length, width and coordinate information of the first object.
Further, the attribute parameters of the standard vehicle include at least the length, width, and coordinate information of the standard vehicle.
After the attribute parameters of the first objects and the standard vehicle are obtained, the length, width and coordinate information of the standard vehicle can be used to match and screen the first objects in sequence to obtain a second object set.
Specifically, the attribute parameters of the standard vehicle are preset, and the attribute parameters of the standard vehicle and the attribute parameters of the first objects are used for sequentially comparing, and the second object suspected to be the vehicle is screened out, so that the shape, the size and the coordinate position of the central point can be obtained through one-time screening of the attribute parameters to meet the object of the suspected vehicle.
It can be understood that the laser radar is a radar system for detecting the characteristic quantities of the position, the speed and the like of the target by emitting a laser beam, specifically, the laser radar is used for emitting a detection signal to the target, then comparing the received signal reflected from the target with the emission signal, and obtaining relevant information of the target, such as parameters of the distance, the azimuth, the height, the speed, the gesture, the even shape and the like of the target after proper processing, so as to detect, track and identify the target, thus the second target object of the suspected vehicle can be tracked by using the laser radar, and the motion parameters of each second target object can be obtained.
Therefore, step 230 may utilize the laser radar to track the second target object, which is specifically implemented as follows:
performing target tracking on each second target object by using a target tracking algorithm to obtain the position information of each second target object at different moments; analyzing and calculating according to the position information of each second object at different moments to obtain the motion parameters of each second object; and calculating and analyzing the position information of each second object in the target track set at different moments to obtain the motion parameters of each second object.
Specifically, the laser radar is utilized to scan the detection area for one circle to obtain the original data information of each target object, so that after a second target object set is obtained through one scan in this embodiment, the original data information of each second target object can be obtained, and if n current second target objects exist, the original data information D of the first frame can be obtained 1 =（d 1,1 ,d 1，2 ，d 1,3 ,…，d 1，n ) Wherein d is the distance value from the laser radar emission point to the second target object.
After the original data information D is obtained 1 =（d 1,1 ,d 1，2 ，d 1,3 ,…，d 1，n ) Then, calculating according to the distance value and the offset included angle of the laser radar when the second target object is scanned to obtain the coordinate of each second target object with the laser radar as the origin, for example, the distance value between the laser radar and the nth second target object is d n And the offset included angle of the laser radar is alpha, the coordinate of the second target object can be represented as p 1，n （x，y）=（d 1，n *cosα，d 1，n * sin alpha), therefore, the original data information is subjected to data classification, the position information of each second object can be obtained, and the object coordinate set K is obtained according to the position information of each second object 1 ={k 1，1 ，k 1，2 ，…，k 1，n }, where k 1，n =p 1，n （x，y）=（d 1，n *cosα，d 1，n *sinα）。
Because the target coordinate set of one frame can be obtained by scanning once, the second target object is tracked by utilizing the laser radar, namely the second target object is scanned for a plurality of times, the coordinate set of a plurality of frames relative to each second target object can be obtained, and then the target track set T= { T can be obtained according to the multi-frame target coordinate set containing the position information of the second target object at different time points 1 ，t 2 ，…，t n And t n ={p 1，n ，p 2，n ，…，p m，n Wherein m is the number of scans and the target track set comprises the second targets in a certain period of timeAnd calculating and analyzing the motion trail of each second target object to obtain the motion parameters of each second target object.
Specifically, the motion parameters of the second object at least include a motion direction and a motion speed of the second object; the motion parameters of the standard vehicle include at least a motion direction and a motion speed of the standard vehicle.
Then, the specific implementation of step 240 may be: and sequentially carrying out matching screening on each second object by utilizing the movement direction and movement speed of the standard vehicle and the movement direction and movement speed of each second object to obtain a target vehicle set.
It can be understood that the motion parameters of the standard vehicle are preset, and then the motion parameters of the standard vehicle and the motion parameters of the second objects are compared, the object vehicle is screened from the second objects suspected to be vehicles, and the second object set is screened, so that the object with the motion direction and the motion speed conforming to the standard vehicle can be obtained.
The attribute parameters of the first object are screened for the first time to obtain a second object set, and the motion parameters of the second object set are screened for the second time to obtain a target vehicle set, so that more accurate target vehicle data can be obtained.
Further, in a viable embodiment of the present application, the vehicle violation includes at least vehicle reverse, vehicle overspeed, and vehicle deceleration.
Then, step 300, determining whether there is a vehicle violation according to the motion parameters of each target vehicle in the target vehicle set, specifically includes:
judging whether the vehicles are in reverse running in the detection area according to the movement directions of the target vehicles; if a target vehicle with the movement direction inconsistent with the preset movement direction exists, determining that the vehicle is in reverse running.
And/or judging whether the vehicle runs slowly or overspeed in the detection area according to the movement speed of each target vehicle; if a target vehicle with the movement speed not within the preset movement speed range exists, determining that the vehicle runs slowly or overspeed; or judging whether the vehicle stays in the detection area according to the movement direction or the movement speed of each target vehicle, and if the target vehicle without the movement direction exists or the target vehicle with the movement speed of zero exists, determining that the vehicle stays.
Specifically, when at least one of the violations of reverse, overspeed, low speed, stop and the like occurs to the target vehicle, the target vehicle violation is confirmed. For example, if a vehicle traveling direction preset in one lane in the detection area is western traveling and it is detected that the target vehicle is eastward traveling, the target vehicle is retrograde; for another example, the preset movement speed in one lane in the detection area is 80km/h-120km/h, and the detected speed of the target vehicle is 60km/h, so that the target vehicle is in low-speed driving, or in the same scene, the speed of the target vehicle is 150km/h, so that the target vehicle is in overspeed driving; for another example, if no moving direction of the target vehicle is detected in the detection area or the detected moving speed of the target vehicle is zero, the target vehicle is in a stop state.
The target vehicles all belong to the rule violation, and when one or more of the conditions of the target vehicles occur, the vehicle rule violation is confirmed.
And monitoring the illegal behaviors of the vehicles in the detection area by acquiring the acquired motion parameters of the target vehicles, and finding out the illegal vehicles in time.
When the target vehicle breaks rules, an alarm mode is triggered.
For ease of understanding, referring to fig. 3a and 3b, fig. 3a is a schematic diagram of an embodiment of the present application in which no offending vehicle is present, and fig. 3b is a schematic diagram of an embodiment of the present application in which an offending vehicle is present.
As shown in fig. 3a and 3b, in a bifurcation road with a western straight line and a right turn, a laser radar is installed between the straight road and the right turn road, on the road, the speed of the allowed traffic is assumed to be 80km/h-120km/h, the detection area is scanned by taking the laser radar as the center of a circle, and the scanning angle of the laser radar can be 270 degrees.
In fig. 3a, A, B and C are target vehicles, and it can be seen that both target vehicles A, B and C are detected to be passing normally, without violations, and therefore, the alert mode is not triggered.
In fig. 3b, target vehicles D, E, F and G are detected, and it can be seen from the figure that there is a reverse going violation of target vehicle D, a low-speed violation of target vehicle E, a high-speed violation of target vehicle F, and a stay violation of target vehicle G, so that if there is a violation of target vehicle in the detection area, an alarm mode is triggered; for example, when the target vehicle E is traveling at a low speed, the alarm mode may be triggered by the illumination of the alarm lamp and the voice alarm "please increase the traffic speed", so as to achieve the purpose of warning the offending vehicle and reducing the offending behavior.
According to the vehicle detection method, the laser radar is used for detecting the detection area, vehicle space positioning information with higher accuracy can be obtained, suspected vehicles are screened twice, more accurate vehicle information is obtained, illegal behavior judgment is carried out according to the motion information of the vehicles, and further, illegal vehicles are warned, so that the problems that the vehicle detection accuracy is low on a passing road, and the illegal vehicles cannot be identified and warned are solved.
In an embodiment of the present application, a vehicle detection device based on a laser radar is provided, referring to fig. 4, fig. 4 is a structural diagram of the vehicle detection device based on the laser radar in the embodiment of the present application, and the device includes: a lidar unit 401, a vehicle screening unit 402, and a violation alert unit 403.
The laser radar unit 401 is configured to scan a target to be detected in the detection area by using a laser radar, so as to obtain a first target object set in the detection area, where the first target object set includes a first target object suspected to be a vehicle or a person in the detection area.
The vehicle screening unit 402 is configured to screen the first target object set by using attribute parameters and motion parameters of a preset standard vehicle, so as to obtain a target vehicle set.
And the violation alert unit 403 is configured to determine whether there is a vehicle violation according to the motion parameters of each target vehicle in the target vehicle set.
And if the vehicle violation is confirmed, triggering an alarm mode.
The device is used for scanning the target to be detected in the detection area by using the laser radar to obtain a first target object set in the detection area, and screening the first target object set by using the attribute parameters and the motion parameters of the preset standard vehicle to obtain a target vehicle set; according to the motion parameters of each target vehicle in the target vehicle set, judging whether the vehicle violates, if the vehicle violations are confirmed, triggering an alarm mode, detecting a detection area by using a laser radar, obtaining space positioning information with higher accuracy, screening suspected vehicles twice to obtain more accurate vehicle information, judging the violations according to the motion information of the vehicles, and then alarming the violating vehicles.
FIG. 5 shows an internal block diagram of a computer device in one embodiment of the invention. The computer device may specifically be a terminal or a system. As shown in fig. 5, the computer device includes a processor, a memory, and a network interface connected by a system bus. The memory includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and may also store a computer program which, when executed by a processor, causes the processor to implement the steps of the method embodiments described above. The internal memory may also have stored therein a computer program which, when executed by a processor, causes the processor to perform the steps of the method embodiments described above. It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided that includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method embodiments described above.
In one embodiment, a computer-readable storage medium is provided, in which a computer program is stored which, when executed by a processor, causes the processor to perform the steps of the method embodiments described above.
Those skilled in the art will appreciate that the processes implementing all or part of the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, and the program may be stored in a non-volatile computer readable storage medium, and the program may include the processes of the embodiments of the methods as above when executed. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples represent only a few embodiments of the present application, which are described in more detail and are not thereby to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (7)
1. A laser radar-based vehicle detection method, wherein the method is applied to a vehicle detection device arranged in a detection area, the vehicle detection device comprises a laser radar, and an area scanned by the laser radar is the detection area, and the method comprises:
scanning targets to be detected in the detection area by using the laser radar to obtain a first target object set in the detection area, wherein the first target object set comprises first target objects suspected to be vehicles and personnel in the detection area;
screening the first target object set by utilizing the attribute parameters and the motion parameters of the preset standard vehicle to obtain a target vehicle set;
judging whether a vehicle violation exists or not according to the motion parameters of each target vehicle in the target vehicle set;
if the vehicle violation is confirmed, triggering an alarm mode;
the step of scanning the target to be detected in the detection area by using the laser radar to obtain a first target object set in the detection area, specifically includes:
scanning the detection area once by using the laser radar to obtain point cloud data of one frame in the detection area, and deleting background points in the point cloud data to obtain foreground points in the detection area;
clustering the foreground points by using a clustering algorithm to obtain a first target object set;
the screening the first target object set by using the attribute parameters and the motion parameters of the preset standard vehicle to obtain a target vehicle set specifically includes:
performing attribute analysis on each first target object to obtain attribute parameters of each first target object;
screening the first object set according to preset attribute parameters of the standard vehicle and attribute parameters of the first objects to obtain a second object set, wherein the second object set comprises second objects suspected to be vehicles;
performing target tracking on each second target object to obtain motion parameters of each second target object;
screening the second target object set according to the preset motion parameters of the standard vehicle and the motion parameters of the second target objects to obtain a target vehicle set;
the attribute parameters of the first object at least comprise the length, the width and the coordinate information of the first object;
the attribute parameters of the standard vehicle at least comprise length, width and coordinate information of the standard vehicle;
the step of screening the first target object set according to the preset attribute parameters of the standard vehicle and the attribute parameters of the first target objects to obtain a second target object set, specifically includes:
and carrying out matching screening on each first object in sequence by utilizing the length, width and coordinate information of the standard vehicle and the length, width and coordinate information of each first object to obtain a second object set.
2. The method according to claim 1, wherein the performing object tracking on each second object to obtain the motion parameters of each second object specifically includes:
performing target tracking on each second target object by using a target tracking algorithm to obtain the position information of each second target object at different moments;
and analyzing and calculating according to the position information of each second target object at different moments to obtain the motion parameters of each second target object.
3. The method of claim 1, wherein the motion parameters of the second object include at least a direction of motion and a speed of motion of the second object;
the motion parameters of the standard vehicle at least comprise the motion direction and the motion speed of the standard vehicle;
the second target object set is screened according to the preset motion parameters of the standard vehicle and the motion parameters of the second target objects, so as to obtain a target vehicle set, which specifically comprises:
and sequentially carrying out matching screening on each second target object by utilizing the movement direction and the movement speed of the standard vehicle and the movement direction and the movement speed of each second target object to obtain a target vehicle set.
4. A method according to claim 3, wherein the vehicle violations include at least vehicle reverse, vehicle overspeed, vehicle low speed, and vehicle stay;
judging whether the vehicle violates the rule according to the motion parameters of each target vehicle in the target vehicle set, and specifically comprising the following steps:
judging whether vehicles are in reverse running in the detection area according to the movement directions of the target vehicles;
if a target vehicle with the motion direction inconsistent with the preset motion direction exists, determining that the vehicle is in reverse running;
and/or;
judging whether the vehicle runs at a low speed or overspeed in the detection area according to the movement speed of each target vehicle;
if a target vehicle with the movement speed not within the preset movement speed range exists, determining that the vehicle runs at a low speed or overspeed;
or;
judging whether a vehicle stays in the detection area according to the movement direction or the movement speed of each target vehicle;
if there is a target vehicle without a moving direction or a target vehicle with a moving speed of zero, it is determined that there is a vehicle stop.
5. A lidar-based vehicle detection device, the device comprising: the system comprises a laser radar unit, a vehicle screening unit and a violation warning unit;
the laser radar unit is used for scanning a target to be detected in a detection area by using the laser radar to obtain a first target object set in the detection area, wherein the first target object set comprises a first target object suspected to be a vehicle or a person in the detection area;
the vehicle screening unit is used for screening the first target object set by utilizing the attribute parameters and the motion parameters of the preset standard vehicle to obtain a target vehicle set;
the violation warning unit is used for judging whether the vehicle is in violation or not according to the motion parameters of each target vehicle in the target vehicle set;
if the vehicle violation is confirmed, triggering an alarm mode;
the step of scanning the target to be detected in the detection area by using the laser radar to obtain a first target object set in the detection area, specifically includes:
scanning the detection area once by using the laser radar to obtain point cloud data of one frame in the detection area, and deleting background points in the point cloud data to obtain foreground points in the detection area;
clustering the foreground points by using a clustering algorithm to obtain a first target object set;
the screening the first target object set by using the attribute parameters and the motion parameters of the preset standard vehicle to obtain a target vehicle set specifically includes:
performing attribute analysis on each first target object to obtain attribute parameters of each first target object;
screening the first object set according to preset attribute parameters of the standard vehicle and attribute parameters of the first objects to obtain a second object set, wherein the second object set comprises second objects suspected to be vehicles;
performing target tracking on each second target object to obtain motion parameters of each second target object;
screening the second target object set according to the preset motion parameters of the standard vehicle and the motion parameters of the second target objects to obtain a target vehicle set;
the attribute parameters of the first object at least comprise the length, the width and the coordinate information of the first object;
the attribute parameters of the standard vehicle at least comprise length, width and coordinate information of the standard vehicle;
the step of screening the first target object set according to the preset attribute parameters of the standard vehicle and the attribute parameters of the first target objects to obtain a second target object set, specifically includes:
and carrying out matching screening on each first object in sequence by utilizing the length, width and coordinate information of the standard vehicle and the length, width and coordinate information of each first object to obtain a second object set.
6. A computer readable storage medium storing a computer program, which when executed by a processor causes the processor to perform the steps of the method according to any one of claims 1 to 4.
7. A computer device comprising a memory and a processor, wherein the memory stores a computer program which, when executed by the processor, causes the processor to perform the steps of the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310028826.8A CN115909758B (en) | 2023-01-09 | 2023-01-09 | Laser radar-based vehicle detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310028826.8A CN115909758B (en) | 2023-01-09 | 2023-01-09 | Laser radar-based vehicle detection method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115909758A CN115909758A (en) | 2023-04-04 |
| CN115909758B true CN115909758B (en) | 2023-07-21 |
Family
ID=86486031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310028826.8A Active CN115909758B (en) | 2023-01-09 | 2023-01-09 | Laser radar-based vehicle detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115909758B (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7024610B2 (en) * | 2018-05-30 | 2022-02-24 | 株式会社Ihi | Detection device and detection system |
| CN112099040A (en) * | 2020-09-15 | 2020-12-18 | 浙江省机电设计研究院有限公司 | Whole-course continuous track vehicle tracking system and method based on laser radar network |
| WO2022247932A1 (en) * | 2021-05-27 | 2022-12-01 | 北京万集科技股份有限公司 | Method and system for recognizing traffic violation participant, and computer-readable storage medium |
| CN115482672B (en) * | 2022-08-11 | 2023-12-19 | 西安天和防务技术股份有限公司 | Method, device, terminal equipment and storage medium for detecting vehicle reverse running |
-
2023
- 2023-01-09 CN CN202310028826.8A patent/CN115909758B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115909758A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11380105B2 (en) | Identification and classification of traffic conflicts | |
| CN110738857B (en) | Vehicle violation evidence obtaining method, device and equipment | |
| CN113424121A (en) | Vehicle speed control method and device based on automatic driving and computer equipment | |
| CN113470374B (en) | Vehicle overspeed monitoring method and device, computer equipment and storage medium | |
| US20220373353A1 (en) | Map Updating Method and Apparatus, and Device | |
| CN111383294B (en) | Drawing method and device for defense area in safety and lightning protection system | |
| CN111582130B (en) | Traffic behavior perception fusion system and method based on multi-source heterogeneous information | |
| CN112949566B (en) | Monitoring method, device and system and computer storage medium | |
| EP3349038A1 (en) | Method to classify objects in a vehicle environment based on radar detections | |
| CN113269811A (en) | Data fusion method and device and electronic equipment | |
| CN113850995B (en) | Event detection method, device and system based on tunnel radar vision data fusion | |
| CN115331413A (en) | Barrier gate rod early warning method and device, electronic equipment and storage medium | |
| CN115909758B (en) | Laser radar-based vehicle detection method, device, equipment and storage medium | |
| US11176379B2 (en) | Method of acquiring detection zone in image and method of determining zone usage | |
| CN115966084B (en) | Holographic intersection millimeter wave radar data processing method and device and computer equipment | |
| US20210107486A1 (en) | Apparatus for determining lane change strategy of autonomous vehicle and method thereof | |
| CN111680633A (en) | Vehicle violation identification method and device, computer equipment and storage medium | |
| CN115547066B (en) | Laser radar-based street crossing warning method, device, equipment and storage medium | |
| CN113299024A (en) | Road operation safety protection system and method based on automatic perception | |
| CN113223049A (en) | Track data processing method and device | |
| Mostafi et al. | Real-Time Jaywalking Detection and Notification System using Deep Learning and Multi-Object Tracking | |
| Moayed et al. | Surveillance-based Collision-time Analysis of Road-crossing Pedestrians | |
| KR102616571B1 (en) | System and method for providing road traffic information based on image analysis using artificial intelligence | |
| CN113687348B (en) | Pedestrian recognition method and device based on tracking micro Doppler graph | |
| CN117111019B (en) | Target tracking and monitoring method and system based on radar detection |
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 |