CN116884235A - Video vehicle speed detection method, device and equipment based on wire collision and storage medium - Google Patents
Video vehicle speed detection method, device and equipment based on wire collision and storage medium Download PDFInfo
- Publication number
- CN116884235A CN116884235A CN202311003690.1A CN202311003690A CN116884235A CN 116884235 A CN116884235 A CN 116884235A CN 202311003690 A CN202311003690 A CN 202311003690A CN 116884235 A CN116884235 A CN 116884235A
- Authority
- CN
- China
- Prior art keywords
- collision
- vehicle
- target vehicle
- line
- video
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 45
- 238000005259 measurement Methods 0.000 claims abstract description 152
- 238000006073 displacement reaction Methods 0.000 claims abstract description 68
- 239000013598 vector Substances 0.000 claims abstract description 59
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims description 30
- 238000000034 method Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000005516 engineering process Methods 0.000 abstract description 12
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 description 9
- 238000009434 installation Methods 0.000 description 7
- 238000011160 research Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000006698 induction Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The application provides a video vehicle speed detection method, a device, equipment and a storage medium based on wire collision, which mainly relate to the technical field of video monitoring technology and intelligent traffic calculation, and comprise the steps of obtaining a video to be detected, drawing a speed measurement reference wire collision, obtaining information of a vehicle to be detected according to the video to be detected, and extracting target vehicle information from the information of the vehicle to be detected; acquiring a pixel value of a target vehicle on a speed measurement reference collision line and calculating a unit distance pixel value; constructing areas with the same distance on two sides of a speed measurement reference collision line as a collision line threshold area; reading the frame rate of the video to be detected and acquiring continuous video frames of the target vehicle in the wire collision threshold area; analyzing the continuous video frames and calculating a displacement vector of the target vehicle; calculating the real driving distance of the target vehicle according to the number of pixels in the unit distance and the displacement vector; and calculating the running speed of the target vehicle at the speed measurement reference collision line according to the real running distance and the frame rate. The application is suitable for different driving situations of vehicles and has the effects of high efficiency and high accuracy.
Description
Technical Field
The invention relates to the technical fields of video monitoring technology, image processing technology and intelligent traffic calculation, in particular to a video vehicle speed detection method, device and equipment based on wire collision and a storage medium.
Background
With the acceleration of economic development, the number of motor vehicles has increased dramatically, bringing about a number of traffic problems, such as: traffic jams, traffic management lag, etc. By studying the speed of the road section vehicles, the distribution condition of traffic flow and the degree of traffic jam can be known. Such information is critical to the formulation of traffic management strategies, improving road networks, traffic planning research and planning new traffic facilities. The traditional vehicle speed detection adopts the technologies of infrared rays, annular coils, radars and the like as a detection method. Drawbacks of these methods: the hardware system is complex, the system environment adaptability is poor, the installation flexibility is low, and the maintenance cost is high. With the development of video monitoring technology, video cameras have been widely used in the field of intelligent transportation technology. Therefore, the vehicle speed detection by video has the possibility of wide application and relatively low maintenance cost.
The video image processing technology is different from the algorithm, and the classical method of the video speed measuring technology is based on a coil speed measuring method. The coil speed measuring method needs to know the distance between the two coils in reality and the distance between the second coil and the stop line, and needs to embed the induction coil on the ground, once the road surface is changed, the coils need to be buried again, the construction amount is large, and in addition, the coil maintenance work on the road surface in high-latitude open freezing period and low-latitude summer and the place where the road surface quality is poor has certain complexity and difficulty.
Disclosure of Invention
In order to enable video speed measurement to be applied to various road conditions and to be more efficient and accurate, the application provides a video vehicle speed detection method, device and equipment based on wire collision and a storage medium.
The first object of the present application is achieved by the following technical solutions:
the video vehicle speed detection method based on the collision line for traffic planning research comprises the following steps: acquiring a video to be detected, drawing a speed measurement reference collision line in the video to be detected, acquiring information of a vehicle to be detected according to the video to be detected, and extracting target vehicle information from the information of the vehicle to be detected;
acquiring a vehicle pixel value of the target vehicle on the speed measurement reference collision line, and calculating a unit distance pixel value of the target vehicle according to the vehicle pixel value;
constructing areas with the same distance on two sides of the speed measurement reference collision line as a collision line threshold area;
reading the frame rate of the video to be detected, and acquiring a threshold continuous video frame of the target vehicle in the wire collision threshold area;
performing displacement analysis on the threshold continuous video frames, and calculating a displacement vector of the target vehicle in the line collision threshold area according to a displacement analysis result;
Calculating the actual driving distance of the target vehicle according to the unit distance pixel number and the displacement vector corresponding to the target vehicle;
and calculating the driving speed of the target vehicle at the collision line according to the real driving distance and the frame rate.
By adopting the technical scheme, the video to be detected is obtained, the speed measurement reference collision line is drawn in the video to be detected, all the information of the vehicles to be detected is identified, the target vehicles are sequentially extracted from the vehicles to be detected for speed measurement analysis, and the corresponding speed measurement reference collision line is analyzed and drawn for different videos to be detected, so that the method can be applied to a plurality of traffic road scenes, and can be correspondingly and dynamically adjusted according to different road conditions, thereby meeting the general applicability of traffic planning research; after the speed measurement reference collision line is drawn, measuring a vehicle pixel value of a target vehicle at the speed measurement reference collision line position, calculating a unit distance pixel value of the target vehicle, confirming an image distance threshold before and after the speed measurement reference collision line position, and constructing areas with the same distance on two sides of the speed measurement reference collision line as a collision line threshold area; the method comprises the steps of utilizing a video image processing technology to read the frame rate of video, detecting and tracking continuous video frames of a target vehicle in a line collision threshold area, ensuring that the target vehicle can be correctly matched between adjacent frames, comparing the positions of the target vehicle in the adjacent frames and calculating the displacement vector of the target vehicle in the line collision threshold area; according to the method, an induction coil is not required to be arranged under a road surface, and the speed measurement reference collision line and the construction of a collision line threshold area are dynamically drawn for different target vehicles in a video, and the motion vector, the unit distance pixel value and the frame rate of the target vehicles in the collision line threshold area are acquired to detect the speed of the vehicle, so that the vehicle is not limited by road conditions and the road surface is not required to be damaged during installation and maintenance, and the installation and maintenance difficulty is reduced.
The present application may be further configured in a preferred example to: the obtaining the vehicle pixel value of the target vehicle on the speed measurement reference collision line, and calculating the unit distance pixel value of the target vehicle according to the vehicle pixel value specifically includes: calling a real pixel value of a corresponding vehicle type according to the vehicle pixel value, and obtaining a pixel comparison result by comparing the vehicle pixel value with the real pixel value of the corresponding vehicle type;
and calculating the unit distance pixel value of the target vehicle according to the pixel comparison result.
By adopting the technical scheme, the unit distance pixel value is calculated by calling the real data corresponding to the vehicle type of the target vehicle to carry out comparison and reference, so that the calculated target vehicle related data and the calculated unit distance pixel value are closer to reality, the error is smaller, and the accuracy of speed measurement is further improved.
The present application may be further configured in a preferred example to: the method for constructing the area with the same distance at the two sides of the speed measurement reference collision line as a collision line threshold area specifically comprises the following steps:
the video to be tested draws at least two speed measurement reference collision lines, wherein the speed measurement reference collision lines are parallel to each other and have equal interval distance;
Acquiring a line collision continuous video frame when the target vehicle passes through the speed measurement reference line collision;
comparing the distances between the target vehicle and the speed measurement reference collision lines when the target vehicle sequentially appears at two sides of the speed measurement reference collision lines according to the collision line continuous video frames;
confirming a distance threshold before and after the speed measurement reference line collision according to the distance comparison result;
according to the distance threshold, constructing the areas with the same distance on the two sides of the speed measurement reference collision line as a collision line threshold area;
the line collision threshold areas are parallel to each other and have equal interval distances.
By adopting the technical scheme, the dynamic corresponding collision threshold area is constructed for different target vehicles according to actual conditions, a reference area is provided for testing the speed of the target vehicles, the construction of the collision threshold area is further limited, the target vehicles are ensured to appear at least once before and after the collision of the speed measurement reference, the effective running data of the target vehicles in the collision threshold area are ensured to be obtained, the calculated basic data of the speed detection of the target vehicles are obtained, the data effectiveness is improved, the speed measurement efficiency is higher, the collision threshold area is adaptive according to different dynamic changes of the target vehicles, and the corresponding dynamic adjustment can be carried out under multiple vehicle types and multiple traffic road scenes according to different vehicle conditions, so that the speed measurement method has higher applicability.
The present application may be further configured in a preferred example to: and performing displacement analysis on the continuous video frames, and calculating a displacement vector of the target vehicle in the collision threshold area according to a displacement analysis result, wherein the displacement vector specifically comprises the following steps:
acquiring vehicle characteristic information of the target vehicle from the target vehicle information, and detecting and tracking the target vehicle in the continuous video frames according to the vehicle characteristic information;
analyzing the position information of the target vehicle in each frame of the continuous video frames according to the vehicle characteristic information of the target vehicle, and marking the position and the size of the target vehicle through a boundary box;
and calculating a motion vector on the pixel unit of the target vehicle according to the coordinate point of the boundary box of the target vehicle.
By adopting the technical scheme, the vehicle characteristic information of the target vehicle is acquired from the target vehicle information, the position distance of the target vehicle, the overlapping degree of the characteristic images and the vehicle type are matched in the continuous frames according to the acquired position, the characteristic images and the vehicle type of the target vehicle, whether the target vehicle is the same target vehicle or not is determined, the target vehicle can be effectively and accurately detected and tracked in the continuous video frames through the vehicle characteristic marking, the position and the size information of the target vehicle in the continuous video frames can be marked through the boundary frame, the position change of the target vehicle can be more intuitively analyzed in the adjacent video frames, and the motion vector on the pixel unit of the target vehicle can be calculated.
The present application may be further configured in a preferred example to: the calculating the motion vector on the pixel unit of the target vehicle according to the coordinate point of the boundary box of the target vehicle specifically comprises the following steps:
after the target vehicle enters the line collision threshold area, acquiring a boundary frame of the target vehicle in adjacent frames according to the continuous video frames;
and acquiring coordinate points of the target vehicle according to the boundary frame of the target vehicle, acquiring coordinate differences according to the coordinate points of the target vehicle in the adjacent frames, and calculating the displacement vector according to the coordinate differences.
By adopting the technical scheme, the continuous video frames of the target vehicle entering the wire collision threshold area are analyzed, the analysis range is further limited, the analysis and calculation of unnecessary video frames are reduced, and the speed measurement efficiency is further improved.
The second object of the present application is achieved by the following technical solutions:
a video vehicle speed detection device based on a wire collision, the video vehicle speed detection device based on the wire collision comprising:
the device comprises a speed measurement reference collision line drawing module, a speed measurement reference collision line drawing module and a speed measurement control module, wherein the speed measurement reference collision line drawing module is used for obtaining a video to be measured, drawing a speed measurement reference collision line in the video to be measured, obtaining information of a vehicle to be measured according to the video to be measured, and extracting target vehicle information from the information of the vehicle to be measured;
The unit distance pixel value calculation module is used for obtaining the vehicle pixel value of the target vehicle on the speed measurement reference collision line and calculating the unit distance pixel value of the target vehicle according to the vehicle pixel value;
the line collision threshold region construction module is used for constructing regions with the same distance on two sides of the speed measurement reference line collision as a line collision threshold region; the video frame rate reading module is used for reading the frame rate of the video to be detected and acquiring a threshold continuous video frame of the target vehicle in the wire collision threshold area;
the displacement vector calculation module is used for carrying out displacement analysis on the threshold continuous video frames and calculating the displacement vector of the target vehicle in the line collision threshold area according to the displacement analysis result;
the real driving distance calculation module is used for calculating the real driving distance of the target vehicle according to the unit distance pixel number corresponding to the target vehicle and the displacement vector;
and the running speed calculation module is used for calculating the running speed of the target vehicle at the speed measurement reference collision line according to the real running distance and the frame rate.
By adopting the technical scheme, the video to be detected is obtained, the speed measurement reference collision line is drawn in the video to be detected, all the information of the vehicles to be detected is identified, the target vehicles are sequentially extracted from the vehicles to be detected for speed measurement analysis, and the corresponding speed measurement reference collision line is analyzed and drawn for different videos to be detected, so that the method can be applied to a plurality of traffic road scenes, and can be correspondingly and dynamically adjusted according to different road conditions, thereby meeting the general applicability of traffic planning research; after the speed measurement reference collision line is drawn, measuring a vehicle pixel value of a target vehicle at the speed measurement reference collision line position, calculating a unit distance pixel value of the target vehicle, confirming an image distance threshold before and after the speed measurement reference collision line position, and constructing areas with the same distance on two sides of the speed measurement reference collision line as a collision line threshold area; the method comprises the steps of utilizing a video image processing technology to read the frame rate of video, detecting and tracking continuous video frames of a target vehicle in a line collision threshold area, ensuring that the target vehicle can be correctly matched between adjacent frames, comparing the positions of the target vehicle in the adjacent frames and calculating the displacement vector of the target vehicle in the line collision threshold area; according to the method, an induction coil is not required to be arranged under a road surface, and the speed measurement reference collision line and the construction of a collision line threshold area are dynamically drawn for different target vehicles in a video, and the motion vector, the unit distance pixel value and the frame rate of the target vehicles in the collision line threshold area are acquired to detect the speed of the vehicle, so that the vehicle is not limited by road conditions and the road surface is not required to be damaged during installation and maintenance, and the installation and maintenance difficulty is reduced.
The third object of the present application is achieved by the following technical solutions:
a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the wire-strike based video vehicle speed detection method described above when the computer program is executed.
The fourth object of the present application is achieved by the following technical solutions:
a computer readable storage medium storing a computer program which when executed by a processor performs the steps of the above-described video vehicle speed detection method based on wire collision.
In summary, the present application includes at least one of the following beneficial technical effects:
1. acquiring a video to be tested, drawing a speed measurement reference collision line in the video to be tested, identifying all vehicle information to be tested, sequentially extracting target vehicles from the vehicles to be tested for speed measurement analysis, and analyzing and drawing corresponding speed measurement reference collision lines for different videos to be tested, so that the method can be applied to a plurality of traffic road scenes, and can be used for carrying out corresponding dynamic adjustment according to different road conditions, thereby meeting the general applicability of traffic planning research;
2. The method comprises the steps of utilizing a video image processing technology to read the frame rate of a video, detecting and tracking continuous video frames of a target vehicle in a collision threshold area, ensuring that the target vehicle can be correctly matched between adjacent frames, comparing the positions of the target vehicle in the adjacent frames, calculating the displacement vector of the target vehicle in the collision threshold area, calculating the real driving distance of the target vehicle according to the unit distance pixel number and the displacement vector of the target vehicle, calculating the driving speed of the target vehicle at a speed measurement reference collision line according to the real driving distance and the frame rate, so as to achieve the purpose of detecting the video vehicle speed, and unlike a coil speed measuring method, the method does not need to set an induction coil under a road surface, and dynamically drawing the speed measurement reference collision line and constructing the collision threshold area for different target vehicles in the video, and acquiring the motion vector, the unit distance pixel value and the frame rate of the target vehicle in the collision threshold area to detect the vehicle speed, so that the road surface is not limited by road conditions and the road surface is not required to be damaged during installation and maintenance, thereby reducing the installation and maintenance difficulty;
3. the real data corresponding to the vehicle type of the target vehicle is called for comparison and reference, and a unit distance pixel value is obtained through calculation, so that the calculated target vehicle related data and the unit distance pixel value are closer to reality, the error is smaller, the accuracy of speed measurement is further improved, continuous video frames of the target vehicle entering a wire collision threshold area are analyzed, the analysis range is further limited, the analysis and calculation of unnecessary video frames are reduced, and the speed measurement efficiency is further improved;
4. The method comprises the steps of constructing dynamic corresponding collision threshold areas for different target vehicles according to actual conditions, providing a reference area for testing the speed of the target vehicles, further limiting the construction of the collision threshold areas so as to ensure that the target vehicles can respectively appear at least once before and after the speed measurement reference collision, ensure that the effective running data of the target vehicles in the collision threshold areas can be obtained so as to obtain the calculation basic data of the speed detection of the target vehicles, improve the data validity, enable the speed measurement efficiency of the method to be higher, adapt to different dynamic changes of the target vehicles, and be correspondingly and dynamically adjusted under the conditions of multiple vehicle types and multiple traffic roads according to different vehicle conditions, and have higher applicability.
Drawings
FIG. 1 is a flow chart of a video vehicle speed detection method based on wire collision in an embodiment of the application;
FIG. 2 is a schematic view of a crash of a video vehicle speed detection method based on a crash in an embodiment of the application;
FIG. 3 is another flow chart of a video vehicle speed detection method based on wire collision in an embodiment of the application;
FIG. 4 is a flowchart showing a video vehicle speed detection method based on wire collision in an embodiment of the present application, step S20;
FIG. 5 is a flowchart showing a video vehicle speed detection method based on wire collision in step S30 according to an embodiment of the present application;
FIG. 6 is a flowchart showing a video vehicle speed detection method based on wire collision in step S50 according to an embodiment of the present application;
FIG. 7 is a flowchart showing a video vehicle speed detection method based on wire collision in step S53 according to an embodiment of the present application;
FIG. 8 is a schematic block diagram of a video vehicle speed detection device based on wire collision in an embodiment of the application;
fig. 9 is a schematic diagram of an apparatus in an embodiment of the application.
Detailed Description
The present application will be described in further detail with reference to the accompanying drawings.
In an embodiment, as shown in fig. 1 and 3, the application discloses a video vehicle speed detection method based on wire collision, which specifically comprises the following steps:
s10: the method comprises the steps of obtaining a video to be tested, drawing a speed measurement reference collision line in the video to be tested, obtaining information of a vehicle to be tested according to the video to be tested, and extracting target vehicle information from the information of the vehicle to be tested.
In this embodiment, the video to be tested refers to a driving situation video recorded with one or more vehicles to be tested on the road section. The speed measurement reference collision line refers to an auxiliary line for carrying out video speed measurement on the vehicle. The vehicle to be tested is a vehicle which needs to be tested. The information of the vehicle to be tested refers to all vehicle information identified from the video to be tested. The target vehicle information is to extract one of the vehicle information of the video to be tested according to the information of the vehicle to be tested, and extract the next vehicle information after the vehicle speed measurement is completed until the vehicle speed measurement in the video to be tested is completed.
Specifically, taking fig. 2 as an example, in order to measure the speed of the vehicle in the video to be measured, a corresponding speed measurement reference collision line is drawn in a picture of the video to be measured, the vehicle running on the road is shot through a camera or other camera equipment on the road to obtain the video to be measured carrying the vehicle to be measured, the video to be measured is loaded for visualization, the speed measurement reference collision line is drawn, information of all the vehicles to be measured in the video to be measured is identified, vehicle information which has too short time to generate effective running data at the beginning or ending in the video is filtered, one of the vehicles to be measured is extracted from the vehicle information which has effective running data as a target vehicle, and in one embodiment, the vehicle information to be measured is detected and obtained through a YOLOv3 target detection algorithm.
S20: and acquiring a vehicle pixel value of the target vehicle on the speed measurement reference collision line, and calculating a unit distance pixel value of the target vehicle according to the vehicle pixel value.
In this embodiment, the vehicle pixel value refers to the number of pixels in the video when the vehicle passes through the speed measurement reference collision line. The unit distance pixel value refers to the number of pixels corresponding to the actual unit distance in the video to be detected.
Specifically, after the target vehicle is identified from the video to be tested and the speed measurement reference collision line is drawn, the number of pixels of the target vehicle when the target vehicle passes through the speed measurement reference collision line is obtained from the video to be tested, and the number of pixels of the target vehicle in the video corresponding to a unit distance is calculated by referring to real size data of the vehicle, for example, the number of pixels of each meter in different lanes of different actual speed measurement reference collision lines in the video to be tested can be calculated.
S30: and constructing the areas with the same distance on both sides of the speed measurement reference collision line as a collision line threshold area.
In the present embodiment, the crash threshold region is a base reference region for testing the vehicle speed of the target vehicle.
Specifically, when the target vehicle passes through the speed measurement reference collision line for multiple times, the distance between the target vehicle and the speed measurement reference collision line is acquired, a collision line distance data set is obtained, the image distance threshold before and after the speed measurement reference collision line position is confirmed by carrying out data processing on the collision line distance data set, and the areas with the same distance on the two sides of the speed measurement reference collision line are constructed as a collision line threshold area as shown in fig. 2.
S40: and reading the frame rate of the video to be detected, and acquiring the threshold continuous video frames of the target vehicle in the line collision threshold area.
In the present embodiment, the frame rate refers to the frequency at which the video to be measured continuously appears on the display in bitmap images in frames called units. The threshold successive video frames refer to successive frames in which the target vehicle appears in the crashed threshold zone.
Specifically, the frame rate of the video to be detected is read by utilizing a video image processing technology, continuous video frames of the target vehicle in the collision threshold area are extracted, if the occurrence time of the target vehicle in the collision threshold area in the video to be detected is too short, the running process of the target vehicle in the collision threshold area can only acquire one frame or can not form continuous frames, the effective running data of the target vehicle can not be formed, namely the speed of the target vehicle can not be detected in the video to be detected, and another vehicle to be detected in the video to be detected is replaced to be the target vehicle.
S50: and carrying out displacement analysis on the threshold continuous video frames, and calculating a displacement vector of the target vehicle in the line collision threshold area according to the displacement analysis result.
In the present embodiment, the displacement analysis result refers to a result of detecting and tracking consecutive video frames of the target vehicle in the collision threshold region. The displacement vector refers to a displacement vector of the target vehicle in the collision threshold region.
Specifically, continuous video frames of the target vehicle in the collision threshold area are detected and tracked, namely, the position information of the target vehicle is identified and acquired according to the information of the target vehicle in each frame, so that the target vehicle can be matched correctly between adjacent frames, the positions of the target vehicle in the adjacent frames are compared to calculate the displacement vector of the target vehicle in the collision threshold area, for example, as shown in fig. 2, after the vehicle enters the collision threshold area, the boundary frames (x 1 ,y 1 ,w 1 ,h 1 ) And (x) 2 ,y 2 ,w 2 ,h 2 ) Using the Euclidean distance formula: l= v (x 2 -x 1 ) 2 +(y 2 -y 1 ) 2 The displacement vector L is calculated.
S60: and calculating the actual driving distance of the target vehicle according to the number of the unit distance pixels and the displacement vector corresponding to the target vehicle.
In the present embodiment, the true travel distance refers to the true travel distance of the target vehicle in the collision threshold region in reality.
Specifically, the actual travel distance of the target vehicle in the collision threshold region is calculated according to the number of pixels per unit distance of the target vehicle and the displacement vector in the collision threshold region, for example, the number of pixels per pixel of the target vehicle is calculated to be ppm, the displacement vector is calculated to be L, and the relation between the number of pixels per pixel (ppm) and the displacement vector L is calculated: s=l/ppm, the true travel distance S of the target vehicle is calculated.
S70: and calculating the running speed of the target vehicle at the speed measurement reference collision line according to the real running distance and the frame rate.
In the present embodiment, the running speed refers to the running speed of the target vehicle at the speed measurement reference collision line.
Specifically, the running speed of the target vehicle at the speed measurement reference collision line is calculated according to the actual running distance and the frame rate of the target vehicle in the collision line threshold area, for example, the actual running distance of the target vehicle is calculated to be S, the video frame rate is calculated to be fps, a unit conversion coefficient is obtained, in this embodiment, the conversion coefficient is 3.6, and the running speed V of the target vehicle at the speed measurement reference collision line is calculated according to the relation v=s×fps×3.6.
In one embodiment, as shown in fig. 4, in step S20, a vehicle pixel value of the target vehicle on the speed measurement reference collision line is obtained, and a unit distance pixel value of the target vehicle is calculated according to the vehicle pixel value, which specifically includes:
s21: and calling the real pixel value of the corresponding vehicle type according to the vehicle pixel value, and obtaining a pixel comparison result by comparing the vehicle pixel value with the real pixel value of the corresponding vehicle type.
In this embodiment, the real pixel value refers to real vehicle type parameter data of the target vehicle in reality. The pixel comparison result refers to the difference multiple relation between the pixel value of the target vehicle in the video and the real vehicle type parameter.
Specifically, a corresponding brand type of the target vehicle is obtained in the video frame, real parameter data of the corresponding brand type is obtained, and then the real parameter data of the brand type of the target vehicle is compared with the vehicle pixel value of the target vehicle in the video frame, so that the difference multiple relation between the pixel value of the target vehicle in the video frame and the real vehicle type parameter data is obtained.
S22: and calculating a unit distance pixel value of the target vehicle according to the pixel comparison result.
Specifically, according to the difference multiple relation between the pixel value of the target vehicle in the video and the real vehicle model parameter, the pixel size of the target vehicle in the video is corresponding to one unit distance. For example, a vehicle length pixel value of a target vehicle at a speed measurement reference collision line position is measured, and the number of pixels per pixel (ppm) is calculated by referring to the actual vehicle length of the corresponding vehicle type.
In one embodiment, as shown in fig. 5, in step S30, a region with the same distance between two sides of the speed measurement reference collision line is constructed as a collision threshold region, which specifically includes:
s31: at least two speed measurement reference collision lines are drawn in the video to be measured, and the speed measurement reference collision lines are parallel to each other and have equal interval distances.
Specifically, at least two speed measurement reference collision lines are drawn according to the road condition shot by the video to be measured, namely, for different videos to be measured, different speed measurement reference collision lines are drawn according to respective driving paths, and the speed measurement reference collision lines are parallel to each other and have equal interval distances.
S32: and acquiring a line collision continuous video frame when the target vehicle passes through the speed measurement reference line collision.
In the present embodiment, the line collision continuous video frame refers to a continuous frame when the target vehicle passes through the speed measurement reference line collision.
Specifically, when the front wheel or the rear wheel of the target vehicle is identified from the video to be detected and pressed to the position of the speed measurement reference collision line, the video frame of the frame before or after the current video frame is obtained, and continuous frames are formed when the target vehicle passes through the speed measurement reference collision line.
S33: and comparing the distances between the target vehicle and the speed measurement reference collision lines when the target vehicle sequentially appears at the two sides of the speed measurement reference collision lines according to the collision line continuous video frames.
Specifically, in the continuous frames when the target vehicle passes through the speed measurement reference line collision, the distance between each frame of target vehicle and the speed measurement reference line collision is obtained, a line collision distance data set is obtained, and data analysis processing is carried out on the line collision distance data set, for example, the average value of the line collision distance data set is obtained.
S34: and confirming a distance threshold before and after the speed measurement reference line collision according to the distance comparison result.
In this embodiment, the distance comparison result refers to a comparison result of the distance between the target vehicle and the speed measurement reference line when the target vehicle sequentially passes before and after the speed measurement reference line.
Specifically, a distance threshold before and after the line collision of the speed measurement reference is confirmed according to the result of the data analysis processing of the line collision distance data set, for example, an average value of the line collision distance data set is taken as the distance threshold before and after the line collision of the speed measurement reference.
S35: and constructing the areas with the same distance on both sides of the speed measurement reference line collision as a line collision threshold area according to the distance threshold.
Specifically, according to the distance threshold, the areas with the same distance on both sides of the speed measurement reference collision line are constructed as a collision line threshold area, so that the target vehicle is ensured to appear at least once before and after the speed measurement reference collision line.
S36: the line collision threshold regions are parallel to each other and are spaced apart by equal distances.
Specifically, the collision line threshold regions are parallel to each other and have equal interval distances, so that the traveling data of the target vehicle in the collision line threshold region is ensured to have referential property and effectiveness, and can be used as the basic data of speed measurement calculation.
In one embodiment, as shown in fig. 6, in step S50, displacement analysis is performed on the continuous video frames, and a displacement vector of the target vehicle in the collision threshold area is calculated according to the result of the displacement analysis, which specifically includes:
s51: vehicle characteristic information of the target vehicle is acquired from the target vehicle information, and the target vehicle is detected and tracked in successive video frames according to the vehicle characteristic information.
In the present embodiment, the vehicle characteristic information refers to the vehicle position, the characteristic image, and the vehicle type of the target vehicle.
Specifically, vehicle characteristic information of the target vehicle is obtained from the target vehicle information, and according to the obtained target vehicle position, characteristic image and vehicle type, the position distance of the target vehicle, the overlapping degree of the characteristic image and the vehicle type are matched in continuous frames, and whether the target vehicle is the same or not is determined so as to achieve the tracking purpose, and in one embodiment, the vehicle characteristic information is obtained through a YOLOv3 target detection algorithm.
S52: according to the vehicle characteristic information of the target vehicle, the position information of the target vehicle is analyzed in each frame of continuous video frames, and the position and the size of the target vehicle are marked by the boundary frame.
In the present embodiment, the bounding box refers to a rectangular box, which is a rectangular box with vehicle features generated centering on the target vehicle.
Specifically, according to the vehicle feature information of the target vehicle, the vehicle information tracked in each frame of continuous video frames extracts the position information of the target vehicle, and a boundary box with the vehicle feature is generated centering on the target vehicle, the position and the size of the target vehicle are marked by the boundary box, in one embodiment, the vehicle position information is detected by using a YOLOv3 target detection algorithm, a vehicle feature map is obtained, and the vehicle position information is marked by using the boundary box. .
S53: and calculating a motion vector on the pixel unit of the target vehicle according to the coordinate point of the boundary box of the target vehicle.
Specifically, the motion vector of the target vehicle on the pixel unit is calculated by taking the coordinate points of the boundary box through the boundary box of the target vehicle in the acquired continuous frames.
In one embodiment, as shown in fig. 7, in step S53, that is, calculating a motion vector on a pixel unit of the target vehicle according to a coordinate point of a boundary box of the target vehicle, specifically includes:
s531: and after the target vehicle enters the line collision threshold area, acquiring a boundary frame of the target vehicle in the adjacent frames according to the continuous video frames.
Specifically, after the target vehicle travels into the collision threshold area, the target vehicle bounding boxes in adjacent frames are acquired according to the continuous video frames of the vehicle in the collision threshold area.
S532: and acquiring coordinate points of the target vehicle according to the boundary frame of the target vehicle, acquiring coordinate differences according to the coordinate points of the target vehicle in the adjacent frames, and calculating displacement vectors according to the coordinate differences.
In the present embodiment, the coordinate difference refers to a difference between coordinates of the target vehicle in adjacent frames.
Specifically, coordinate points of a boundary frame of the target vehicle in the adjacent frame are taken, a difference value between coordinates of the target vehicle in the adjacent frame is calculated according to the coordinate points, and a displacement vector is calculated according to the coordinate difference.
For example, as shown in fig. 2, when the target vehicle enters the threshold region of the wire 2, the position (x 1 ,y 1 ,w 1 ,h 1 ) And then extracting the position (x) 2 ,y 2 ,w 2 ,h 2 ) Wherein x, y are coordinates of the central position of the feature map of the target vehicle, w, h are the width and height of the feature map of the target vehicle, and a Euclidean distance formula is utilized: l= v (x 2 -x 1 ) 2 +(y 2 -y 1 ) 2 The displacement vector L is calculated.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.
In one embodiment, a video vehicle speed detection device based on wire collision is provided, and the video vehicle speed detection device based on wire collision corresponds to the video vehicle speed detection method based on wire collision in the embodiment one by one. As shown in fig. 9, the video vehicle speed detection device based on the collision line comprises a speed measurement reference collision line drawing module, a unit distance pixel value calculation module, a collision line threshold value region construction module, a video frame rate reading module, a displacement vector calculation module, a real driving distance calculation module and a driving speed calculation module. The functional modules are described in detail as follows:
the speed measurement reference collision line drawing module is used for obtaining a video to be measured, drawing a speed measurement reference collision line in the video to be measured, obtaining information of a vehicle to be measured according to the video to be measured, and extracting target vehicle information from the information of the vehicle to be measured;
the unit distance pixel value calculation module is used for obtaining the vehicle pixel value of the target vehicle on the speed measurement reference collision line and calculating the unit distance pixel value of the target vehicle according to the vehicle pixel value;
the line collision threshold region construction module is used for constructing regions with the same distance on two sides of a speed measurement reference line collision as a line collision threshold region;
the video frame rate reading module is used for reading the frame rate of the video to be detected and acquiring a threshold continuous video frame of the target vehicle in the line collision threshold area;
The displacement vector calculation module is used for carrying out displacement analysis on the threshold continuous video frames and calculating the displacement vector of the target vehicle in the collision threshold area according to the displacement analysis result;
the real driving distance calculation module is used for calculating the real driving distance of the target vehicle according to the number of unit distance pixels and the displacement vector corresponding to the target vehicle;
and the running speed calculation module is used for calculating the running speed of the target vehicle at the speed measurement reference collision line according to the real running distance and the frame rate.
Optionally, the unit distance pixel value calculating module includes:
the pixel comparison module is used for calling the real pixel value of the corresponding vehicle type according to the vehicle pixel value, and obtaining a pixel comparison result by comparing the vehicle pixel value with the real pixel value of the corresponding vehicle type;
and the pixel comparison result processing module is used for calculating the unit distance pixel value of the target vehicle according to the pixel comparison result.
Optionally, the wire-strike threshold region building module includes:
the speed measurement reference collision line definition module is used for defining a video to be measured, drawing at least two speed measurement reference collision lines, wherein the speed measurement reference collision lines are parallel to each other and have equal interval distance;
the line collision continuous video frame acquisition module is used for acquiring line collision continuous video frames when the target vehicle passes through the speed measurement reference line collision;
The distance comparison module is used for comparing the distance between the target vehicle and the speed measurement reference collision line when the target vehicle sequentially appears at two sides of the speed measurement reference collision line according to the collision line continuous video frames;
the distance threshold confirming module is used for confirming a distance threshold before and after the speed measurement reference line collision according to the distance comparison result;
the line collision threshold region construction module is used for constructing regions with the same distance on two sides of the speed measurement reference line collision as a line collision threshold region according to the distance threshold;
the wire-collision threshold area definition module is parallel to each other and is equal in interval distance.
Optionally, the displacement vector calculation module includes:
the vehicle characteristic acquisition module is used for acquiring vehicle characteristic information of the target vehicle from the target vehicle information, and detecting and tracking the target vehicle in continuous video frames according to the vehicle characteristic information;
the vehicle information marking module is used for analyzing the position information of the target vehicle in each frame of continuous video frames according to the vehicle characteristic information of the target vehicle and marking the position and the size of the target vehicle through the boundary frame;
and the motion vector calculation module is used for calculating the motion vector on the pixel unit of the target vehicle according to the coordinate point of the boundary box of the target vehicle.
Optionally, the motion vector calculation module includes:
the vehicle boundary frame acquisition module is used for acquiring boundary frames of the target vehicles in adjacent frames according to continuous video frames after the target vehicles enter the wire collision threshold area;
the displacement vector calculation module acquires coordinate points of the target vehicle according to the boundary frame of the target vehicle, acquires coordinate differences according to the coordinate points of the target vehicle in adjacent frames, and calculates a displacement vector according to the coordinate differences.
The specific limitation of the video vehicle speed detection device based on the crash line can be referred to as the limitation of the video vehicle speed detection method based on the crash line, and is not described herein. The above-mentioned video vehicle speed detection device based on wire collision can be implemented by all or part of software, hardware and their combination. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 9. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing vehicle type data, vehicle information to be tested and speed measurement results. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a video vehicle speed detection method based on wire collision.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program:
acquiring a video to be detected, drawing a speed measurement reference collision line in the video to be detected, acquiring information of a vehicle to be detected according to the video to be detected, and extracting target vehicle information from the information of the vehicle to be detected;
acquiring a vehicle pixel value of a target vehicle on a speed measurement reference collision line, and calculating a unit distance pixel value of the target vehicle according to the vehicle pixel value;
constructing areas with the same distance on two sides of a speed measurement reference collision line as a collision line threshold area;
reading the frame rate of the video to be detected, and acquiring a threshold continuous video frame of the target vehicle in the line collision threshold area;
performing displacement analysis on the threshold continuous video frames, and calculating a displacement vector of the target vehicle in the line collision threshold area according to a displacement analysis result; calculating the real driving distance of the target vehicle according to the number of unit distance pixels and the displacement vector corresponding to the target vehicle;
and calculating the running speed of the target vehicle at the speed measurement reference collision line according to the real running distance and the frame rate. In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
Acquiring a video to be detected, drawing a speed measurement reference collision line in the video to be detected, acquiring information of a vehicle to be detected according to the video to be detected, and extracting target vehicle information from the information of the vehicle to be detected;
acquiring a vehicle pixel value of a target vehicle on a speed measurement reference collision line, and calculating a unit distance pixel value of the target vehicle according to the vehicle pixel value;
constructing areas with the same distance on two sides of a speed measurement reference collision line as a collision line threshold area;
reading the frame rate of the video to be detected, and acquiring a threshold continuous video frame of the target vehicle in the line collision threshold area;
performing displacement analysis on the threshold continuous video frames, and calculating a displacement vector of the target vehicle in the line collision threshold area according to a displacement analysis result; calculating the real driving distance of the target vehicle according to the number of unit distance pixels and the displacement vector corresponding to the target vehicle;
and calculating the running speed of the target vehicle at the speed measurement reference collision line according to the real running distance and the frame rate.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in 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.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
1. The video vehicle speed detection method based on the collision line is characterized by comprising the following steps of:
Acquiring a video to be detected, drawing a speed measurement reference collision line in the video to be detected, acquiring information of a vehicle to be detected according to the video to be detected, and extracting target vehicle information from the information of the vehicle to be detected;
acquiring a vehicle pixel value of the target vehicle on the speed measurement reference collision line, and calculating a unit distance pixel value of the target vehicle according to the vehicle pixel value;
constructing areas with the same distance on two sides of the speed measurement reference collision line as a collision line threshold area;
reading the frame rate of the video to be detected, and acquiring a threshold continuous video frame of the target vehicle in the wire collision threshold area;
performing displacement analysis on the threshold continuous video frames, and calculating a displacement vector of the target vehicle in the line collision threshold area according to a displacement analysis result;
calculating the actual driving distance of the target vehicle according to the unit distance pixel number and the displacement vector corresponding to the target vehicle;
and calculating the running speed of the target vehicle at the speed measurement reference collision line according to the real running distance and the frame rate.
2. The method for detecting a video vehicle speed based on a collision line according to claim 1, wherein the step of obtaining a vehicle pixel value of the target vehicle on the speed measurement reference collision line, and calculating a unit distance pixel value of the target vehicle according to the vehicle pixel value, specifically comprises:
Calling a real pixel value of a corresponding vehicle type according to the vehicle pixel value, and obtaining a pixel comparison result by comparing the vehicle pixel value with the real pixel value of the corresponding vehicle type;
and calculating the unit distance pixel value of the target vehicle according to the pixel comparison result.
3. The video vehicle speed detection method based on wire collision according to claim 1, wherein the constructing the area with the same distance at two sides of the speed measurement reference wire collision as a wire collision threshold area specifically comprises:
the video to be tested draws at least two speed measurement reference collision lines, wherein the speed measurement reference collision lines are parallel to each other and have equal interval distance;
acquiring a line collision continuous video frame when the target vehicle passes through the speed measurement reference line collision;
comparing the distances between the target vehicle and the speed measurement reference collision lines when the target vehicle sequentially appears at two sides of the speed measurement reference collision lines according to the collision line continuous video frames;
confirming a distance threshold before and after the speed measurement reference line collision according to the distance comparison result;
according to the distance threshold, constructing the areas with the same distance on the two sides of the speed measurement reference collision line as a collision line threshold area;
the line collision threshold areas are parallel to each other and have equal interval distances.
4. The crash-based video vehicle speed detection method according to claim 1, wherein the performing displacement analysis on the continuous video frames, and calculating a displacement vector of the target vehicle in the crash threshold region according to a displacement analysis result, specifically comprises:
acquiring vehicle characteristic information of the target vehicle from the target vehicle information, and detecting and tracking the target vehicle in the continuous video frames according to the vehicle characteristic information;
analyzing the position information of the target vehicle in each frame of the continuous video frames according to the vehicle characteristic information of the target vehicle, and marking the position and the size of the target vehicle through a boundary box;
and calculating a motion vector on the pixel unit of the target vehicle according to the coordinate point of the boundary box of the target vehicle.
5. The wire-crash-based video vehicle speed detection method according to claim 4, wherein the calculating a motion vector on the target vehicle pixel unit from the coordinate point of the target vehicle bounding box specifically comprises:
after the target vehicle enters the line collision threshold area, acquiring a boundary frame of the target vehicle in adjacent frames according to the continuous video frames;
And acquiring coordinate points of the target vehicle according to the boundary frame of the target vehicle, acquiring coordinate differences according to the coordinate points of the target vehicle in the adjacent frames, and calculating the displacement vector according to the coordinate differences.
6. A video vehicle speed detection device based on wire collision, characterized in that the video vehicle speed detection device based on wire collision comprises:
the device comprises a speed measurement reference collision line drawing module, a speed measurement reference collision line drawing module and a speed measurement control module, wherein the speed measurement reference collision line drawing module is used for obtaining a video to be measured, drawing a speed measurement reference collision line in the video to be measured, obtaining information of a vehicle to be measured according to the video to be measured, and extracting target vehicle information from the information of the vehicle to be measured;
the unit distance pixel value calculation module is used for obtaining the vehicle pixel value of the target vehicle on the speed measurement reference collision line and calculating the unit distance pixel value of the target vehicle according to the vehicle pixel value;
the line collision threshold region construction module is used for constructing regions with the same distance on two sides of the speed measurement reference line collision as a line collision threshold region;
the video frame rate reading module is used for reading the frame rate of the video to be detected and acquiring a threshold continuous video frame of the target vehicle in the wire collision threshold area;
the displacement vector calculation module is used for carrying out displacement analysis on the threshold continuous video frames and calculating the displacement vector of the target vehicle in the line collision threshold area according to the displacement analysis result;
The real driving distance calculation module is used for calculating the real driving distance of the target vehicle according to the unit distance pixel number corresponding to the target vehicle and the displacement vector;
and the running speed calculation module is used for calculating the running speed of the target vehicle at the speed measurement reference collision line according to the real running distance and the frame rate.
7. The wire-strike based video vehicle speed detection apparatus according to claim 6, wherein the unit distance pixel value calculation module includes:
the pixel comparison module is used for calling the real pixel value of the corresponding vehicle type according to the vehicle pixel value, and obtaining a pixel comparison result by comparing the vehicle pixel value with the real pixel value of the corresponding vehicle type;
and the pixel comparison result processing module is used for calculating the unit distance pixel value of the target vehicle according to the pixel comparison result.
8. The wire-strike based video vehicle speed detection device according to claim 6, wherein the wire-strike threshold zone construction module includes:
the speed measurement reference collision line definition module is used for defining the video to be measured and drawing at least two speed measurement reference collision lines, and the speed measurement reference collision lines are parallel to each other and have equal interval distance;
The line collision continuous video frame acquisition module is used for acquiring line collision continuous video frames when the target vehicle passes through the speed measurement reference line collision;
the distance comparison module is used for comparing the distance between the target vehicle and the speed measurement reference collision line when the target vehicle sequentially appears at two sides of the speed measurement reference collision line according to the collision line continuous video frames;
the distance threshold confirming module is used for confirming the distance threshold before and after the speed measurement reference collision line according to the distance comparison result;
the line collision threshold region construction module is used for constructing regions with the same distance on two sides of the speed measurement reference line collision as the line collision threshold region according to the distance threshold;
the wire-collision threshold regions define modules, and the wire-collision threshold regions are parallel to each other and are equally spaced.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the crash-based video vehicle speed detection method according to any one of claims 1 to 5 when the computer program is executed.
10. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the crash-based video vehicle speed detection method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311003690.1A CN116884235B (en) | 2023-08-09 | 2023-08-09 | Video vehicle speed detection method, device and equipment based on wire collision and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311003690.1A CN116884235B (en) | 2023-08-09 | 2023-08-09 | Video vehicle speed detection method, device and equipment based on wire collision and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116884235A true CN116884235A (en) | 2023-10-13 |
| CN116884235B CN116884235B (en) | 2024-01-30 |
Family
ID=88270013
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311003690.1A Active CN116884235B (en) | 2023-08-09 | 2023-08-09 | Video vehicle speed detection method, device and equipment based on wire collision and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116884235B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101615342A (en) * | 2008-06-27 | 2009-12-30 | 青岛海信电子产业控股股份有限公司 | A kind of vehicle checking method |
| CN102592456A (en) * | 2012-03-09 | 2012-07-18 | 泉州市视通光电网络有限公司 | Video-based vehicle speed measuring method |
| CN104021676A (en) * | 2014-06-25 | 2014-09-03 | 上海交通大学 | Vehicle positioning and speed measuring method based on dynamic video feature of vehicle |
| CN107895492A (en) * | 2017-10-24 | 2018-04-10 | 河海大学 | A kind of express highway intelligent analysis method based on conventional video |
| CN109686088A (en) * | 2018-12-29 | 2019-04-26 | 重庆同济同枥信息技术有限公司 | A kind of traffic video alarm method, equipment and system |
| CN111462503A (en) * | 2019-01-22 | 2020-07-28 | 杭州海康威视数字技术股份有限公司 | Vehicle speed measuring method and device and computer readable storage medium |
| CN112798811A (en) * | 2020-12-30 | 2021-05-14 | 杭州海康威视数字技术股份有限公司 | Speed measurement method, device and equipment |
| CN113470374A (en) * | 2021-06-30 | 2021-10-01 | 平安科技（深圳）有限公司 | Vehicle overspeed monitoring method and device, computer equipment and storage medium |
| CN114332153A (en) * | 2021-12-28 | 2022-04-12 | 京东方科技集团股份有限公司 | Vehicle speed detection and collision early warning method and electronic equipment |
| CN114419485A (en) * | 2021-12-17 | 2022-04-29 | 奇酷软件（深圳）有限公司 | Camera-based intelligent vehicle speed measuring method and system, storage medium and computer equipment |
| CN116503818A (en) * | 2023-04-27 | 2023-07-28 | 内蒙古工业大学 | Multi-lane vehicle speed detection method and system |
-
2023
- 2023-08-09 CN CN202311003690.1A patent/CN116884235B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101615342A (en) * | 2008-06-27 | 2009-12-30 | 青岛海信电子产业控股股份有限公司 | A kind of vehicle checking method |
| CN102592456A (en) * | 2012-03-09 | 2012-07-18 | 泉州市视通光电网络有限公司 | Video-based vehicle speed measuring method |
| CN104021676A (en) * | 2014-06-25 | 2014-09-03 | 上海交通大学 | Vehicle positioning and speed measuring method based on dynamic video feature of vehicle |
| CN107895492A (en) * | 2017-10-24 | 2018-04-10 | 河海大学 | A kind of express highway intelligent analysis method based on conventional video |
| CN109686088A (en) * | 2018-12-29 | 2019-04-26 | 重庆同济同枥信息技术有限公司 | A kind of traffic video alarm method, equipment and system |
| CN111462503A (en) * | 2019-01-22 | 2020-07-28 | 杭州海康威视数字技术股份有限公司 | Vehicle speed measuring method and device and computer readable storage medium |
| CN112798811A (en) * | 2020-12-30 | 2021-05-14 | 杭州海康威视数字技术股份有限公司 | Speed measurement method, device and equipment |
| CN113470374A (en) * | 2021-06-30 | 2021-10-01 | 平安科技（深圳）有限公司 | Vehicle overspeed monitoring method and device, computer equipment and storage medium |
| CN114419485A (en) * | 2021-12-17 | 2022-04-29 | 奇酷软件（深圳）有限公司 | Camera-based intelligent vehicle speed measuring method and system, storage medium and computer equipment |
| CN114332153A (en) * | 2021-12-28 | 2022-04-12 | 京东方科技集团股份有限公司 | Vehicle speed detection and collision early warning method and electronic equipment |
| WO2023124383A1 (en) * | 2021-12-28 | 2023-07-06 | 京东方科技集团股份有限公司 | Vehicle speed measurement method, collision early-warning method, and electronic device |
| CN116503818A (en) * | 2023-04-27 | 2023-07-28 | 内蒙古工业大学 | Multi-lane vehicle speed detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116884235B (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111652097B (en) | Image millimeter wave radar fusion target detection method | |
| US11035958B2 (en) | Systems and methods for correcting a high-definition map based on detection of obstructing objects | |
| CN112433203B (en) | Lane linearity detection method based on millimeter wave radar data | |
| US9185402B2 (en) | Traffic camera calibration update utilizing scene analysis | |
| CN109035299A (en) | Method for tracking target, device, computer equipment and storage medium | |
| CN112509364B (en) | Method and device for determining parking state of vehicle, computer equipment and storage medium | |
| CN100454355C (en) | Video method for collecting information of vehicle flowrate on road in real time | |
| CN110197173B (en) | Road edge detection method based on binocular vision | |
| CN113781537B (en) | Rail elastic strip fastener defect identification method and device and computer equipment | |
| CN116242316B (en) | Method and device for detecting positioning points of rigid contact net in real time | |
| CN111626275A (en) | Abnormal parking detection method based on intelligent video analysis | |
| Arjapure et al. | Deep learning model for pothole detection and area computation | |
| CN104754327A (en) | Method for detecting and eliminating defective pixels of high spectral image | |
| CN106611147A (en) | Vehicle tracking method and device | |
| CN111488762A (en) | Lane-level positioning method and device and positioning equipment | |
| CN116884235B (en) | Video vehicle speed detection method, device and equipment based on wire collision and storage medium | |
| EP4250245A1 (en) | System and method for determining a viewpoint of a traffic camera | |
| CN110322508B (en) | Auxiliary positioning method based on computer vision | |
| Temiz et al. | Real time speed estimation from monocular video | |
| CN113824880B (en) | Vehicle tracking method based on target detection and UWB positioning | |
| CN115439792A (en) | Monitoring method and system based on artificial intelligence | |
| JPH10187974A (en) | Physical distribution measuring instrument | |
| Yao | An effective vehicle counting approach based on CNN | |
| CN114004876A (en) | Dimension calibration method, dimension calibration device and computer readable storage medium | |
| CN113191239A (en) | Vehicle overall dimension dynamic detection system based on computer vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |