CN112309134A - Vehicle speed detection method and device - Google Patents

Vehicle speed detection method and device Download PDF

Info

Publication number
CN112309134A
CN112309134A CN201910688572.6A CN201910688572A CN112309134A CN 112309134 A CN112309134 A CN 112309134A CN 201910688572 A CN201910688572 A CN 201910688572A CN 112309134 A CN112309134 A CN 112309134A
Authority
CN
China
Prior art keywords
block
vehicle
frame
cache
matching
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
Application number
CN201910688572.6A
Other languages
Chinese (zh)
Other versions
CN112309134B (en
Inventor
张楠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujitsu Ltd
Original Assignee
Fujitsu Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Fujitsu Ltd filed Critical Fujitsu Ltd
Priority to CN201910688572.6A priority Critical patent/CN112309134B/en
Priority to JP2020092429A priority patent/JP7435258B2/en
Publication of CN112309134A publication Critical patent/CN112309134A/en
Application granted granted Critical
Publication of CN112309134B publication Critical patent/CN112309134B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
    • G08G1/054—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed photographing overspeeding vehicles

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The embodiment of the application provides a vehicle speed detection method and device, wherein the method comprises the following steps: detecting a current vehicle block in a foreground block of a current frame of an input image sequence; adjusting the size of the current vehicle block according to the relation between the first lane width of the lane where the buffer vehicle block in the first frame or the previous matching frame of each buffer block in the buffer and the second lane width of the lane where the current vehicle block is located in the current frame; matching the current vehicle block after being adjusted in size with the cache vehicle block to determine whether the current vehicle block and the cache vehicle block are the same vehicle; when the current vehicle block and the cache vehicle block are determined to be the same vehicle, calculating the travel distance of the vehicle in a first time, wherein the first time is equal to the difference between the current frame and the first frame or a previous matching frame; the vehicle speed is calculated based on the first time and the travel distance.

Description

Vehicle speed detection method and device
Technical Field
The embodiment of the application relates to the technical field of image processing.
Background
Since most traffic accidents are caused by overspeed, overspeed event detection is a very important function in traffic monitoring systems.
Current speed detection methods are based on hardware sensors, such as radar velocimeters, laser velocimeters, infrared speed detectors, toroidal coil speed detectors, etc. These methods are very expensive and not suitable for large-scale traffic monitoring.
In recent years, surveillance cameras are widely used for road surveillance. Monitoring camera-based traffic event detection is a popular area of research, particularly for vehicle speed detection. The current vehicle speed detection methods can be divided into two categories: one is a detection method based on background modeling, and the speed value is detected by tracking a foreground block, which is low in cost but cannot solve the problem of vehicle occlusion; the second method is a feature-based detection method that takes a part of a vehicle as a feature (e.g., a license plate), then tracks a feature region, and detects a speed, which requires a high-quality image and cannot be applied to various environments. Further, both of the above methods rely on the tracking effect, but when the velocity value is very high, the distance and the ratio are greatly changed, and thus the tracking accuracy is lowered.
It should be noted that the above background description is provided only for the sake of clarity and complete description of the technical solutions of the embodiments of the present application, and for the sake of understanding by those skilled in the art. These solutions are not considered to be known to a person skilled in the art merely because they have been set forth in the background section of the embodiments of the present application.
Disclosure of Invention
The inventor finds that the detection method based on background modeling cannot solve the problem of vehicle occlusion; feature-based detection methods require high quality images and cannot be applied to different environments. Both methods rely on the tracking effect, but when the speed value is very high, the distance and the proportion change greatly, so the tracking precision is reduced, and the accuracy of the vehicle speed detection result is affected.
The embodiment of the application provides a vehicle speed detection method and device, which do not need to depend on a tracking method, are not influenced by frame skipping, can be suitable for detection of high vehicle speed, and have less calculation amount.
According to a first aspect of embodiments of the present application, there is provided a vehicle speed detection apparatus, wherein the apparatus includes:
a detection unit for detecting a current vehicle block in a foreground block of a current frame of an input image sequence;
a first adjusting unit, configured to adjust a size of a current vehicle block according to a relationship between a first lane width of a lane (lane) in which a buffered vehicle block is located in a first frame or a previous matching frame of each buffered block in a buffer and a second lane width of the lane in which the current vehicle block is located in the current frame;
the matching unit is used for matching the current vehicle block adjusted by the first adjusting unit with the cache vehicle block and determining whether the current vehicle block and the cache vehicle block are the same vehicle;
a calculating unit, configured to calculate a travel distance of the vehicle within a first time when it is determined that the current vehicle block and the cached vehicle block are the same vehicle, where the first time is equal to a difference between the current frame and the first frame or a previous matching frame, and calculate the vehicle speed according to the first time and the travel distance.
According to a second aspect of the embodiments of the present application, there is provided a vehicle speed detection method, wherein the method includes:
detecting a current vehicle block in a foreground block of a current frame of an input image sequence;
adjusting the size of the current vehicle block according to the relation between the first lane width of the lane where the buffer vehicle block in the first frame or the previous matching frame of each buffer block in the buffer and the second lane width of the lane where the current vehicle block is located in the current frame;
matching the current vehicle block after being adjusted in size with the cache vehicle block to determine whether the current vehicle block and the cache vehicle block are the same vehicle;
when the current vehicle block and the cache vehicle block are determined to be the same vehicle, calculating the travel distance of the vehicle in a first time, wherein the first time is equal to the difference between the current frame and the first frame or a previous matching frame;
calculating the vehicle speed from the first time and the travel distance.
One of the benefits of the embodiment of the application is that the size of the detected current vehicle block is adjusted according to the lane width, the current vehicle block is matched with the cache block in the cache, and when the matching is successful, the vehicle speed is determined according to the travel distance and time of the current vehicle block, so that the method does not need to depend on a tracking method, is not influenced by frame skipping, can be suitable for detecting higher vehicle speed, and has less calculation amount.
Specific embodiments of the present application are disclosed in detail with reference to the following description and drawings, indicating the manner in which the principles of the application may be employed. It should be understood that the embodiments of the present application are not so limited in scope. The embodiments of the present application include many variations, modifications and equivalents within the spirit and scope of the appended claims.
Features that are described and/or illustrated with respect to one embodiment may be used in the same way or in a similar way in one or more other embodiments, in combination with or instead of the features of the other embodiments.
It should be emphasized that the term "comprises/comprising" when used herein, is taken to specify the presence of stated features, integers, operations or components but does not preclude the presence or addition of one or more other features, integers, operations or components.
Drawings
Many aspects of embodiments of the present application can be better understood with reference to the following drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating the principles of embodiments of the application. For convenience in illustrating and describing some parts of the embodiments of the present application, corresponding parts may be enlarged or reduced in the drawings. Elements and features described in one drawing or one embodiment of the application may be combined with elements and features shown in one or more other drawings or embodiments. Moreover, in the drawings, like reference numerals designate corresponding parts throughout the several views, and may be used to designate corresponding parts for use in more than one embodiment.
In the drawings:
fig. 1 is a schematic view of a vehicle speed detection device according to embodiment 1 of the present application;
fig. 2 is a schematic diagram of one frame of image in the image sequence acquired in embodiment 1 of the present application;
3A-3C are schematic diagrams of current vehicle block detection in embodiment 1 of the present application;
4A-4C are schematic diagrams of the matching of the current vehicle block in the embodiment 1 of the application;
fig. 5 is a schematic diagram of the configuration of the matching unit 103 in embodiment 1 of the present application;
FIG. 6 is a diagram showing a hardware configuration of an image processing apparatus in embodiment 2 of the present application;
fig. 7 is a flowchart of a vehicle speed detection method in embodiment 3 of the present application.
Detailed Description
The foregoing and other features of embodiments of the present application will become apparent from the following description, taken in conjunction with the accompanying drawings. These embodiments are merely exemplary and are not intended to limit the present application. Embodiments of the present application will be described below with reference to the drawings.
In the embodiments of the present application, the terms "first", "second", and the like are used for distinguishing different elements by reference, but do not denote a spatial arrangement, a temporal order, or the like of the elements, and the elements should not be limited by the terms. The term "and/or" includes any and all combinations of one or more of the associated listed terms. The terms "comprising," "including," "having," and the like, refer to the presence of stated features, elements, components, and do not preclude the presence or addition of one or more other features, elements, components, and elements.
Embodiments of the first aspect
Embodiments of a first aspect of the present application provide a vehicle speed detection apparatus; fig. 1 is a schematic view of the configuration of the vehicle speed detection device, and as shown in fig. 1, the vehicle speed detection device 100 includes:
a detection unit 101 for detecting a current vehicle block in a foreground block of a current frame of an input image sequence;
a first adjusting unit 102, configured to adjust a size of a current vehicle block according to a relationship between a first lane width of a lane in which a cached vehicle block in a first frame or a previous matching frame of each cached vehicle block in a cache and a second lane width of the lane in which the current vehicle block is located in the current frame;
a matching unit 103, configured to match the current vehicle block adjusted by the first adjusting unit 102 with the cached vehicle block, and determine whether the current vehicle block is the same vehicle;
a calculating unit 104, configured to, when it is determined that the current vehicle block and the cached vehicle block are the same vehicle, calculate a travel distance of the vehicle within a first time, where the first time is equal to a difference between the current frame and the first frame or a previous matching frame, and calculate the vehicle speed according to the first time and the travel distance.
Therefore, the size of the detected current vehicle block is adjusted according to the lane width, the current vehicle block is matched with the cache block in the cache, and the vehicle speed is determined according to the traveling distance and time of the current vehicle block when the matching is successful.
In the embodiment of the present application, since the vehicle speed in the real world needs to be obtained according to the processing result of the acquired image sequence, before actual detection, a conversion matrix of an image coordinate system and a world coordinate system needs to be acquired in advance, fig. 2 is a schematic diagram of a frame of image in the acquired image sequence, as shown in fig. 2, 4 reference points a, a ', B' can be determined in one frame of image to establish a mapping relationship between a, a ', B' in the image and a, a ', B' in the real world, for example, the distances AA ', BB', AB, a 'B' in the following two reference points in the image and AA ', BB', AB, a 'B' in the real world are measured and substituted into the following formula (1) to obtain a conversion matrix H, where (X, Y) represents coordinates in the world coordinate system and (X, Y) represents coordinates in the input image coordinate system, further, the coordinates of the real world corresponding to any point in the input image can be calculated according to the following formula (2).
Figure BDA0002147146740000051
Figure BDA0002147146740000052
In this embodiment of the present application, the detecting unit 101 may obtain an input image sequence from a camera of a traffic monitoring system, and detect a foreground block from a current Frame of the input image sequence, where the foreground block may refer to the prior art, such as a Frame differencing method (Frame differentiating), a Gaussian Mixture Model (Mixture of Gaussian Model), a single Gaussian Model (single Gaussian Model), a Vibe algorithm, a color background Model, and the like.
In this embodiment of the application, after obtaining the bounding box of the one or more foreground blocks, the current vehicle block may be extracted using an algorithm such as machine learning, for example, a vehicle classifier is obtained in advance by using histogram of oriented gradients HOG (HOG) features and cascade classifier training, the one or more foreground blocks are input into the vehicle classifier, and the output result is the current vehicle block, where the current frame may include the one or more current vehicle blocks. Thus, by detecting the foreground block to detect the vehicle block, the processing time can be reduced.
In the embodiment of the present application, the appropriate size of the vehicle block may be estimated according to the lane width in the current frame, and therefore, the lane widths of different positions in the current frame may be predetermined, that is, the apparatus 100 further includes:
and a lane width calculation unit (optionally, not shown) for calculating a lane width of a lane where the vehicle travels corresponding to each position in the input image coordinate system, based on the conversion matrix of the world coordinate system and the input image coordinate system. For example, it can be known in advance that the lane width in the real world is usually 3.75m, as shown in fig. 2, a dotted line l is drawn in the input image, the ordinate y of each position on l is traversed, a target image point in the input image and the current position in the real world, which is 3.75m away, is found by using the transformation matrix H, the distance between the current position and the target image point in the input image coordinate system (i.e., the lane width) is calculated, and then the lane width in the input image coordinate system corresponding to the ordinate y of different positions in the input image is obtained.
In one or more embodiments, in order to make the size of the detected current vehicle block within a predetermined range, the apparatus 100 may further include: a second adjusting unit (optional, not shown) for adjusting the size of the foreground block according to the lane width in the current frame; then, the detection unit 101 detects a current vehicle block from the adjusted foreground block size. For example, for one or more foreground blocks detected, a reference point for the foreground block is determined, y being based on the reference pointcCoordinate, the lane width w [ y ] corresponding to the foreground block can be determinedc]For example, the width of the vehicle block may be set to w [ y ]c]X 2/3(2/3 is merely an example, and the embodiment of the present application is not limited thereto), and the adjustment factor scale of the foreground block is determined according to the following formula (3):
Figure BDA0002147146740000061
wherein C _ width represents a reference vehicle width of the vehicle classifier (which may be preset as required), the second adjusting unit may readjust the size of each foreground block according to the ratio of the adjustment factor scale (the original foreground block size is multiplied by the adjustment factor to perform adjustment), fig. 3A-3C are schematic diagrams of current vehicle block detection, as shown in fig. 3A-3B, a rectangular frame is a foreground block obtained by initial detection, and after the second adjusting unit readjusts the size of each rectangular frame according to the ratio of the adjustment factor, the detecting unit 101 inputs the same into the vehicle classifier, so as to obtain a vehicle block detection result as shown in fig. 3C.
In this embodiment of the present application, a template block to be matched may be preset for matching with a detected current vehicle block, for example, a buffer may be set, one or more buffer blocks are stored in the buffer, the buffer block is used as the template block, and the buffer stores therein relevant information of each buffer block, including first information of a buffered vehicle block in the first frame and the first frame of each buffer block and second information of a buffered vehicle block in the previous matching frame and the previous matching frame of each buffer block, where the first information includes: the frame number of the first frame in the input image sequence, the position of the buffer vehicle block in the first frame and the first frame image; the second information includes: the frame number of the previous matching frame in the input image sequence, the position of the buffered vehicle block in the previous matching frame and the previous matching frame image; optionally, the related information further includes: and matching times. The first frame of the buffer block may be determined according to an actual situation, and the previous matching frame of the buffer block is determined according to a subsequent matching result, that is, a vehicle block successfully matched last time is stored in the buffer as a buffer vehicle block in the previous matching frame for matching of a subsequent vehicle block, which will be described later.
Table 1 below is a cache block related information schematic table, as shown in table 1:
Figure BDA0002147146740000062
Figure BDA0002147146740000071
4A-4C are schematic diagrams of a block matching process, as shown in FIGS. 4A-4C, in this embodiment of the present application, since a vehicle is moving, a position of the vehicle in an input image sequence is changing continuously, which results in different sizes of vehicle blocks in different frame images from far to near, in order to perform vehicle block matching more accurately, the first adjusting unit 102 adjusts the size of the current vehicle block according to a relationship between a first lane width of a lane where the buffered vehicle block in a first frame or a previous matching frame of each buffered block in a buffer and a second lane width of the lane where the current vehicle block is located in the current frame; for example, as shown in FIGS. 4A-4B-4C, the ordinate position of the vehicle mass is represented by y1Becomes y2Becomes y3The corresponding lane width position is represented by w [ y ]1]Becomes w [ y2]Becomes w [ y3]Thus, adjustment of the vehicle massFactor equal to w [ y1]/w[y3]Or w [ y ]2]/w[y3]Assuming that the size of the current vehicle block is W × H, if its matching object is the first frame as shown in fig. 4A, its adjusted current vehicle block size is (W × W [ y ])1]/w[y3])×(H×w[y1]/w[y3]) If the matching object is the previous matching frame as shown in FIG. 4B, the adjusted current vehicle block size is (W x W y)2]/w[y3])×(H×w[y2]/w[y3]) Wherein y is3Corresponding to the ordinate position, y, of the current vehicle block1Corresponding to the ordinate position, y, of the block of cached vehicles in the first frame2Corresponding to the ordinate position of the cached vehicle block in the previous matching frame.
In the embodiment of the present application, in order to avoid a deviation caused by position detection of the vehicle classifier, the size of the current vehicle block may be appropriately enlarged, as shown in fig. 4C, the inner solid line rectangle is the size of the detected current vehicle block, and the outer dotted line rectangle is the size of the expanded current vehicle block, where the expanded adjustment factor may be determined as needed, for example, the expanded range may be about 0.2 times of the original area, which is not limited in the embodiment of the present application.
In this embodiment of the application, the matching unit 103 may match the resized current vehicle block with the cached vehicle block to determine whether the current vehicle block is the same vehicle; the specific matching algorithm may refer to the prior art, for example, using a template matching algorithm, sliding the cached vehicle block in the resized current vehicle block region, comparing the overlapped regions (converting into a grayscale image and then comparing), and storing the comparison result, and specifically may use the following formula (5) to calculate the matching degree between the current vehicle block and the cached vehicle block:
Figure BDA0002147146740000072
Figure BDA0002147146740000081
where I denotes the current vehicle block, T denotes the buffer vehicle block, R denotes the matching degree, w denotes the width of the current vehicle block, and h denotes the height of the current vehicle block, in order to avoid errors due to illumination variations, formula (4) may be used to normalize I and T before calculating the matching degree. The R values are in the range of-1 to 1, where 1 means identical, -1 means completely different, and 0 means that there is no linear relationship between the two.
The following describes the matching process of the matching unit 103 with reference to fig. 5, fig. 5 is a schematic diagram of the configuration of an embodiment of the matching unit 103, and as shown in fig. 5, the matching unit 103 includes:
a first calculating module 501, configured to match the resized current vehicle block with the cache vehicle block in the first frame of each cache block, and calculate a first matching degree of each cache block;
a first determining module 502, configured to determine that the current vehicle block and a cached vehicle block in a first frame of a cached block are the same vehicle when the first matching degree of the cached block is greater than or equal to a first threshold;
a second calculating module 503, configured to match the resized current vehicle block with a cached vehicle block in a previous matching frame of each cache block when the first matching degree of each cache block is smaller than a first threshold, and calculate a second matching degree;
a second determining module 504, configured to determine that the current vehicle block is the same vehicle as the cached vehicle block in the previous matching frame of the one cached block when the second matching degree of the one cached block is greater than or equal to the first threshold.
In this embodiment of the present application, the first calculating module 501 calculates a first matching degree of the resized current vehicle block and the first frame cache vehicle block in table 1 of each cache block by using the above formulas (4) - (5), and when the first matching degree of one cache block is greater than or equal to a first threshold, it indicates that the first frame cache vehicle block in the cache block corresponding to the first matching degree is successfully matched with the current vehicle block, that is, the first determining module 502 determines that the current vehicle block and the cache vehicle block in the first frame of the cache block are the same vehicle; when the first matching degree of each buffer block is smaller than the first threshold, it indicates that the current vehicle block does not match the first frame buffer vehicle block of each buffer block, the second calculating module 503 calculates the second matching degree of the resized current vehicle block and the buffer vehicle block in the previous matching frame of each buffer block using the above formulas (4) - (5), and when the second matching degree of one buffer block is greater than or equal to the first threshold, it indicates that the buffer vehicle block in the previous matching frame corresponding to the second matching degree matches the current vehicle block successfully, that is, the second determining module 504 determines that the current vehicle block and the buffer vehicle block in the previous matching frame of the one buffer block are the same vehicle. The first threshold may be determined as needed, for example, set to 0.7, but the embodiment of the present application is not limited thereto. It should be noted that the resized current vehicle block used by the first calculation module 501 is adjusted according to the relationship between the first lane width of the lane where the first frame buffer vehicle block is located and the second lane width, and the resized current vehicle block used by the second calculation module 503 is adjusted according to the relationship between the first lane width of the lane where the previous matching frame buffer vehicle block is located and the second lane width.
In this embodiment of the application, as shown in fig. 5, when the second matching degree of a cache block is greater than or equal to a first threshold, the matching unit 103 further includes:
an updating module 505 (optional) that replaces the current frame with a previous matching frame stored in the one buffer block in the buffer, and replaces the current vehicle block (the current vehicle block without resizing, i.e. the original current vehicle block) with a buffered vehicle block in the previous matching frame stored in the one buffer block in the buffer; namely, the updating module 505 updates columns 4-6 in table 1, that is, the frame number of the previous matching frame in the input image sequence is replaced by the sequence number of the current frame, the position of the buffered vehicle block in the previous matching frame is replaced by the position of the current vehicle block in the current frame, and the image of the previous matching frame is replaced by the image of the current frame.
And when the second matching degree of each buffer block is smaller than the first threshold, it indicates that the current vehicle block is a new vehicle, and the updating module 505 stores the current frame and the current vehicle block into the buffer as a first frame and a first frame buffer vehicle block of a new buffer block. That is, a new buffer block is created, and the updating module 505 updates columns 1-3 (columns 4-6 are empty) in table 1, that is, the frame number of the first frame in the input image sequence is set as the sequence number of the current frame, the position of the buffer vehicle block in the first frame is set as the position of the current vehicle block in the current frame, and the first frame image is set as the current frame image.
In the embodiment of the present application, when the first determination module 502 or the second determination module 504 determines that the vehicle is the same vehicle, indicating that the matching is successful, the matching unit 103 adds 1 to the number of matching times in table 1.
As shown in fig. 4A, the vehicle block is a new vehicle block detected for the first time, and is stored in the buffer as a first frame buffer vehicle block of the new buffer block, as shown in fig. 4B, the vehicle block is a vehicle block successfully matched for the previous time, and is stored in the buffer as a previous matched frame buffer vehicle block of the buffer block, as shown in fig. 4C, the vehicle block is a current vehicle block, the size of the current vehicle block is adjusted according to the lane width of the buffer vehicle block in fig. 4A, and then the current vehicle block is matched with the buffer vehicle block, as shown in fig. 4C, when the matching is not successful, the size of the current vehicle block is re-adjusted according to the lane width of the buffer vehicle block in fig. 4B, and then the current vehicle block is matched with the buffer vehicle block, as a new buffer block when the matching is not successful, and (3) replacing the previous matching frame and the previous matching frame in the buffer with the current frame and the current vehicle block, and buffering the vehicle block, wherein the matching times are added by 1.
In one or more embodiments, to save storage space, the apparatus further comprises:
a deleting unit (optionally, not shown) configured to delete a buffer block from the buffer when a difference between the current frame and a first frame of the buffer block exceeds a second threshold. For example, the second threshold is set to 2s, but the embodiment of the present application is not limited thereto.
In the embodiment of the present application, the calculating unit 104 calculates, according to the transformation matrix of the world coordinate system and the coordinate system of the input image, a first position of the vehicle in the world coordinate system corresponding to the current vehicle block position in the current frame, and a second position of the vehicle in the world coordinate system corresponding to the cached vehicle block position in the first frame or the previous matching frame (the first frame or the previous matching frame is a frame that is successfully matched); the distance between the first position and the second position is taken as the travel distance. Wherein, a reference pixel point in the current vehicle block can be selected as the position of the current vehicle block, as shown in fig. 4C, the position (C) is the position of the current vehicle block, and p is selected2As a reference pixel point, the position is the position of the first frame buffer vehicle block (the buffer vehicle block successfully matched), and p is selected1As a reference pixel point, p is calculated according to the formula (2)2Position P in the corresponding world coordinate system2And p is1Position P in the corresponding world coordinate system1Calculate P1And P2Distance | P between1-P2And calculating a first time which is equal to the difference between the current frame and the first frame or the previous matching frame (the first frame or the previous matching frame is a frame successfully matched), and dividing the travel distance by the first time to obtain the vehicle speed.
In this embodiment, optionally, when the number of matching times of one buffer block in the buffer is greater than or equal to a fourth threshold and the tracked duration (the current frame minus the first frame) is greater than or equal to a fifth threshold, the calculating unit 104 calculates the speed of the vehicle so as to improve the accuracy, where the fourth threshold and the fifth threshold may be determined as needed, for example, the fourth threshold is 0.5 times the frame rate, and the fifth threshold is 0.6 times the frame rate, but this embodiment of the present application is not limited thereto.
In the embodiment of the application, the vehicle is determined to overspeed when the calculated vehicle speed is greater than or equal to the third threshold value according to comparison between the calculated vehicle speed and the third threshold value, and the overspeed result can be notified to the server.
The above embodiments are merely illustrative of the embodiments of the present application, but the present application is not limited thereto, and appropriate modifications may be made on the basis of the above embodiments. For example, the above-described embodiments may be used alone, or one or more of the above-described embodiments may be combined.
Through the device of the embodiment of the application, the size of the detected current vehicle block is adjusted according to the lane width, the current vehicle block is matched with the cache block in the cache, and the vehicle speed is determined according to the travel distance and time of the current vehicle block when the matching is successful, so that the device is not dependent on a tracking method, is not influenced by frame skipping, can be suitable for detecting high vehicle speed, and has less calculation amount.
Embodiments of the second aspect
Embodiments of the second aspect of the present application also provide an image processing device, which may be, for example, a computer, a server, a workstation, a laptop, a smartphone, or the like; the embodiments of the present application are not limited thereto.
Fig. 6 is a schematic diagram of a hardware configuration of an image processing apparatus 600 according to an embodiment of the present application, and as shown in fig. 6, the image processing apparatus 600 may include: an interface (not shown), a Central Processing Unit (CPU)620, a memory 610; the memory 610 is coupled to the central processor 620. Wherein the memory 610 may store various data; further, a program 603 for vehicle speed detection is stored, and the program 603 is executed under the control of the central processor 620, and various preset values and predetermined conditions and the like are stored.
In the embodiment of the present application, the functions of the vehicle speed detection apparatus 100 may be integrated into the central processor 620. Wherein the central processor 620 may be configured to: detecting a current vehicle block in a foreground block of a current frame of an input image sequence; adjusting the size of the current vehicle block according to the relation between the first lane width of the lane where the buffer vehicle block in the first frame or the previous matching frame of each buffer block in the buffer and the second lane width of the lane where the current vehicle block is located in the current frame; matching the current vehicle block after being adjusted in size with the cache vehicle block to determine whether the current vehicle block and the cache vehicle block are the same vehicle; when the current vehicle block and the cache vehicle block are determined to be the same vehicle, calculating the travel distance of the vehicle in a first time, wherein the first time is equal to the difference between the current frame and the first frame or a previous matching frame; the vehicle speed is calculated based on the first time and the travel distance.
In this embodiment, the central processor 620 may be further configured to: adjusting the size of the foreground block according to the lane width in the current frame; and detecting the current vehicle block according to the adjusted foreground block size.
In this embodiment, the central processor 620 may be further configured to: matching the current vehicle block after being adjusted in size with the cache vehicle blocks in the first frame of each cache block, and calculating to obtain a first matching degree of each cache block; when the first matching degree of one cache block is larger than or equal to a first threshold value, determining that the current vehicle block and a cache vehicle block in a first frame of the cache block are the same vehicle; when the first matching degree of each cache block is smaller than a first threshold value, matching the current vehicle block after being adjusted in size with a cache vehicle block in a previous matching frame of each cache block, and calculating to obtain a second matching degree; and when the second matching degree of the one cache block is greater than or equal to a first threshold value, determining that the current vehicle block and a cache vehicle block in a previous matching frame of the one cache block are the same vehicle.
In this embodiment, the central processor 620 may be further configured to: when the second matching degree of one cache block is larger than or equal to a first threshold value, replacing a previous matching frame stored by the cache block in the cache with the current frame, and replacing a cached vehicle block in the previous matching frame stored by the cache block in the cache with the current vehicle block; and when the second matching degree of each cache block is smaller than a first threshold value, the current frame and the current vehicle block are stored into the cache as a first frame and a cache vehicle block of a new cache block.
In this embodiment, the central processor 620 may be further configured to: when the difference between the current frame and the first frame of a buffer block in the buffer exceeds a second threshold, the buffer block is deleted from the buffer.
In this embodiment, the central processor 620 may be further configured to: according to the conversion matrix of the world coordinate system and the input image coordinate system, calculating a first position of the vehicle in the world coordinate system corresponding to the current vehicle block position in the current frame, and a second position of the vehicle in the world coordinate system corresponding to the cached vehicle block position in the first frame or the previous matching frame; the distance between the first position and the second position is taken as the travel distance.
In this embodiment, the central processor 620 may be further configured to: and calculating the lane width of a lane where the vehicle corresponding to each position in the input image coordinate system travels according to the conversion matrix of the world coordinate system and the input image coordinate system.
The embodiment of the cpu 620 can refer to embodiment 1, and will not be repeated here.
In another embodiment, the vehicle speed detecting device may be disposed on a chip (not shown) connected to the central processing unit 620, and the function of the vehicle speed detecting device may be realized by the control of the central processing unit 620.
It is noted that the image processing device 600 may also comprise a display 605 and an I/O device 604, or may not necessarily comprise all the components shown in fig. 6, for example a camera (not shown) for acquiring the input image sequence; furthermore, the image processing apparatus 600 may also include components not shown in fig. 6, which may be referred to in the prior art.
Through the device of the embodiment of the application, the size of the detected current vehicle block is adjusted according to the lane width, the current vehicle block is matched with the cache block in the cache, and the vehicle speed is determined according to the travel distance and time of the current vehicle block when the matching is successful, so that the device does not need to depend on a tracking method, is not influenced by frame skipping, can be suitable for detecting higher vehicle speed, and has less calculation amount.
Examples of the third aspect
Embodiments of the third aspect of the present application provide a vehicle speed detection method, and since the principle of solving the problem of the method is similar to that of the apparatus of the first aspect, specific implementation thereof may refer to implementation of the apparatus of the first aspect, and description thereof is not repeated where the same matters.
Fig. 7 is a flowchart of an embodiment of a vehicle speed detection method according to an embodiment of the present application, and referring to fig. 7, the method includes:
operation 701, detecting a current vehicle block in a foreground block of a current frame of an input image sequence;
operation 702, adjusting the size of the current vehicle block according to a relationship between a first lane width of a lane where the buffered vehicle block in the first frame or the previous matching frame of each buffered block in the buffer is located and a second lane width of the lane where the current vehicle block is located in the current frame;
in operation 703, matching the resized current vehicle block with the cached vehicle block to determine whether the current vehicle block is the same vehicle;
at operation 704, upon determining that the current vehicle block and the cached vehicle block are the same vehicle, a distance traveled by the vehicle within a first time equal to a difference between the current frame and the first frame or a previous matching frame is calculated.
In the embodiment of the present application, the specific embodiment of the operations 701-704 may refer to the determining unit 101, the first adjusting unit 102, the matching unit 103, and the calculating unit 104 in embodiment 1, which are incorporated herein, and repeated descriptions thereof are omitted.
In an embodiment of the present application, the method may further include: (optionally, not shown) adjusting the size of the foreground block according to the lane width in the current frame; and, in operation 701, a current vehicle block is detected according to the adjusted foreground block size.
In this embodiment of the present application, in operation 703, a current vehicle block is matched with a cached vehicle block in a first frame of each cache block, a first matching degree of each cache block is obtained through calculation, and when the first matching degree of one cache block is greater than or equal to a first threshold, it is determined that the current vehicle block and a cached vehicle block in the first frame of the cache block are the same vehicle; when the first matching degree of each cache block is smaller than a first threshold value, matching the current vehicle block after being adjusted in size with a cache vehicle block in a previous matching frame of each cache block, calculating to obtain a second matching degree, and when the second matching degree of the cache block is larger than or equal to the first threshold value, determining that the current vehicle block and the cache vehicle block in the previous matching frame of the cache block are the same vehicle. For example, when the second matching degree of one cache block is greater than or equal to a first threshold, the current frame may replace a previous matching frame stored in the one cache block in the cache, and the current vehicle block may replace a cached vehicle block in the previous matching frame stored in the one cache block in the cache; and when the second matching degree of each buffer block is smaller than the first threshold, the current frame and the current vehicle block may be stored in the buffer as a first frame and a buffer vehicle block of a new buffer block.
In this embodiment of the present application, the buffer stores therein relevant information of each buffer block, including first information of a buffered vehicle block in the first frame and the first frame of each buffer block and second information of a buffered vehicle block in the previous matching frame and the previous matching frame of each buffer block, where the first information includes: the frame number of the first frame in the input image sequence, the position of the buffer vehicle block in the first frame and the first frame image; the second information includes: the frame number of the previous matching frame in the input image sequence, the position of the buffered vehicle block in the previous matching frame and the previous matching frame image; the related information further includes: and matching times, wherein when the matching is successful, the matching times are added by 1.
In an embodiment of the present application, the method may further include: (optionally, not shown) when the difference between the current frame and the first frame of a buffer block in the buffer exceeds a second threshold, the buffer block is deleted from the buffer.
In an embodiment of the present application, the method may further include: (optionally, not shown) calculating a first position of the vehicle in the world coordinate system corresponding to the current vehicle block position in the current frame and a second position of the vehicle in the world coordinate system corresponding to the buffered vehicle block position in the first frame or a previous matching frame according to the conversion matrix of the world coordinate system and the input image coordinate system; the distance between the first position and the second position is taken as the travel distance.
In an embodiment of the present application, the method may further include: (optionally, not shown) the lane width of the lane where the vehicle travels corresponding to each position in the input image coordinate system is calculated from the conversion matrix of the world coordinate system and the input image coordinate system.
It should be noted that fig. 7 above is only a schematic illustration of the embodiment of the present application, but the present application is not limited thereto. For example, the order of execution of various operations may be appropriately adjusted, and other operations may be added or some of the operations may be subtracted. Those skilled in the art can appropriately modify the above description without being limited to the description of fig. 7.
According to the method, the size of the detected current vehicle block is adjusted according to the lane width, the current vehicle block is matched with the cache block in the cache, and the vehicle speed is determined according to the travel distance and time of the current vehicle block when the matching is successful.
Embodiments of the present application also provide a computer-readable program, wherein when the program is executed in a vehicle speed detection apparatus, the program causes a computer to execute the vehicle speed detection method in the embodiment of the third aspect as above in the vehicle speed detection apparatus.
Embodiments of the present application also provide a storage medium storing a computer-readable program, where the computer-readable program causes a computer to execute the vehicle speed detection method in the embodiment of the third aspect above in a vehicle speed detection device.
The method for vehicle speed detection in a vehicle speed detection apparatus described in connection with the embodiments of the present application may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. For example, one or more of the functional block diagrams and/or one or more combinations of the functional block diagrams illustrated in the figures may correspond to individual software modules, or may correspond to individual hardware modules of a computer program flow. These software modules may correspond to respective operations shown in the figures. These hardware modules may be implemented, for example, by solidifying these software modules using a Field Programmable Gate Array (FPGA).
A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium; or the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The software module may be stored in the memory of the vehicle speed detection device, or may be stored in a memory card that is insertable into the vehicle speed detection device.
One or more of the functional block diagrams and/or one or more combinations of the functional block diagrams described in the figures can be implemented as a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any suitable combination thereof designed to perform the functions described in the embodiments of the present application. Combinations of computing devices may also be implemented with respect to one or more of the functional block diagrams and/or one or more combinations of the functional block diagrams depicted in the figures, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP communication, or any other such configuration.
The embodiments of the present application have been described in conjunction with specific embodiments, but it should be clear to those skilled in the art that these descriptions are intended to be illustrative and not to limit the scope of the present application. Various modifications and adaptations of the present application may occur to those skilled in the art based on the spirit and principles of the application and are within the scope of the application.
With regard to the above embodiments, the following remarks are also disclosed.
Supplementary note 1, a vehicle speed detecting apparatus, characterized in that the apparatus comprises:
a detection unit for detecting a current vehicle block in a foreground block of a current frame of an input image sequence;
a first adjusting unit, configured to adjust a size of a current vehicle block according to a relationship between a first lane width of a lane in which a cached vehicle block in a first frame or a previous matching frame of each cached block in a cache and a second lane width of the lane in which the current vehicle block is located in the current frame;
the matching unit is used for matching the current vehicle block adjusted by the first adjusting unit with the cache vehicle block and determining whether the current vehicle block and the cache vehicle block are the same vehicle;
a calculating unit, configured to calculate a travel distance of the vehicle within a first time when it is determined that the current vehicle block and the cached vehicle block are the same vehicle, where the first time is equal to a difference between the current frame and the first frame or a previous matching frame, and calculate the vehicle speed according to the first time and the travel distance.
2. The apparatus according to supplementary note 1, wherein the apparatus further comprises:
a second adjusting unit, configured to adjust the size of the foreground block according to a lane width in the current frame;
and the detection unit detects the current vehicle block according to the adjusted foreground block size.
3. The apparatus according to supplementary note 1, wherein the matching unit includes:
the first calculation module is used for matching the current vehicle block after being adjusted in size with the cache vehicle blocks in the first frame of each cache block, and calculating to obtain a first matching degree of each cache block;
a first determining module, configured to determine that the current vehicle block and a cached vehicle block in a first frame of a cached block are the same vehicle when the first matching degree of one cached block is greater than or equal to a first threshold;
the second calculation module is used for matching the current vehicle block after being adjusted in size with the cache vehicle block in the previous matching frame of each cache block when the first matching degree of each cache block is smaller than a first threshold value, and calculating to obtain a second matching degree;
a second determining module, configured to determine that the current vehicle block and a cached vehicle block in a previous matching frame of the one cached block are the same vehicle when the second matching degree of the one cached block is greater than or equal to a first threshold.
4. The apparatus according to supplementary note 3, wherein when the second matching degree of one cache block is greater than or equal to a first threshold, the matching unit further includes:
an updating module, configured to replace the current frame with a previous matching frame stored in the one cache block in the cache, and replace the current vehicle block with a cached vehicle block in the previous matching frame stored in the one cache block in the cache;
and when the second matching degree of each cache block is smaller than a first threshold, the updating module stores the current frame and the current vehicle block into the cache as a first frame and a cache vehicle block of a new cache block.
5. The apparatus according to supplementary note 1, wherein the buffer stores therein relevant information of each buffer block, including first information of a buffered vehicle block in the first frame and first frame of each buffer block and second information of a buffered vehicle block in the previous matching frame and previous matching frame of each buffer block, wherein the first information includes: a frame number of the first frame in a sequence of input images, a location of the cached vehicle block in the first frame, and the first frame image; the second information includes: a frame number of the previous matching frame in the sequence of input images, a position of the buffered vehicle block in the previous matching frame, and the previous matching frame image;
the related information further comprises: and matching times, wherein when the matching is successful, the matching unit adds 1 to the matching times.
6. The apparatus according to supplementary note 5, wherein the apparatus further comprises:
a deleting unit, configured to delete a buffer block from the buffer when a difference between a current frame and a first frame of the buffer block exceeds a second threshold.
7. The apparatus according to supplementary note 1, wherein the calculation unit calculates a first position of the vehicle in a world coordinate system corresponding to a current vehicle block position in a current frame and a second position of the vehicle in the world coordinate system corresponding to a cached vehicle block position in the first frame or a previous matching frame, based on a conversion matrix of the world coordinate system and an input image coordinate system; taking the distance of the first position and the second position as the travel distance.
8. The apparatus according to supplementary note 1, wherein the apparatus further comprises:
and a lane width calculation unit for calculating a lane width of a lane in which the vehicle travels corresponding to each position in the input image coordinate system, based on the conversion matrix of the world coordinate system and the input image coordinate system.
9. A vehicle speed detection method, characterized by comprising:
detecting a current vehicle block in a foreground block of a current frame of an input image sequence;
adjusting the size of the current vehicle block according to the relation between the first lane width of the lane where the buffer vehicle block in the first frame or the previous matching frame of each buffer block in the buffer and the second lane width of the lane where the current vehicle block is located in the current frame;
matching the current vehicle block after being adjusted in size with the cache vehicle block to determine whether the current vehicle block and the cache vehicle block are the same vehicle;
when the current vehicle block and the cache vehicle block are determined to be the same vehicle, calculating the travel distance of the vehicle in a first time, wherein the first time is equal to the difference between the current frame and the first frame or a previous matching frame;
calculating the vehicle speed from the first time and the travel distance.
10. The method of supplementary note 9, wherein matching the current vehicle block with the cached vehicle block comprises:
matching a current vehicle block with a cache vehicle block in a first frame of each cache block, calculating to obtain a first matching degree of each cache block, and when the first matching degree of one cache block is greater than or equal to a first threshold value, determining that the current vehicle block and the cache vehicle block in the first frame of the cache block are the same vehicle;
when the first matching degree of each cache block is smaller than a first threshold value, matching the current vehicle block after being adjusted in size with a cache vehicle block in a previous matching frame of each cache block, calculating to obtain a second matching degree, and when the second matching degree of one cache block is larger than or equal to the first threshold value, determining that the current vehicle block and the cache vehicle block in the previous matching frame of the cache block are the same vehicle.
11. The method according to supplementary note 9, wherein the method further comprises:
adjusting the size of the foreground block according to the lane width in the current frame;
and detecting the current vehicle block according to the adjusted foreground block size.
12. According to the method described in supplementary note 10, when the second matching degree of one cache block is greater than or equal to a first threshold, replacing the current frame with a previous matching frame stored in the one cache block in the cache, and replacing the current vehicle block with a cached vehicle block in the previous matching frame stored in the one cache block in the cache;
and when the second matching degree of each cache block is smaller than a first threshold value, storing the current frame and the current vehicle block into the cache as a first frame and a cache vehicle block of a new cache block.
13. The method according to supplementary note 9, wherein the buffer stores therein relevant information of each buffer block, including first information of a buffered vehicle block in the first frame and first frame of each buffer block and second information of a buffered vehicle block in the previous matching frame and previous matching frame of each buffer block, wherein the first information includes: a frame number of the first frame in a sequence of input images, a location of the cached vehicle block in the first frame, and the first frame image; the second information includes: a frame number of the previous matching frame in the sequence of input images, a position of the buffered vehicle block in the previous matching frame, and the previous matching frame image;
the related information further comprises: and matching times, wherein when the matching is successful, the matching times are added by 1.
14. The method according to supplementary note 13, wherein the method further comprises:
and when the difference between the current frame and the first frame of one cache block in the cache exceeds a second threshold value, deleting the cache block from the cache.
15. The method of supplementary note 9, wherein calculating the distance traveled by the vehicle within the first time comprises: according to a conversion matrix of a world coordinate system and an input image coordinate system, calculating a first position of the vehicle in the world coordinate system corresponding to the current vehicle block position in the current frame and a second position of the vehicle in the world coordinate system corresponding to the cached vehicle block position in the first frame or a previous matching frame; taking the distance of the first position and the second position as the travel distance.
16. The method according to supplementary note 9, wherein the method further comprises:
and calculating the lane width of a lane where the vehicle corresponding to each position in the input image coordinate system travels according to the conversion matrix of the world coordinate system and the input image coordinate system.

Claims (10)

1. A vehicle speed detection apparatus, characterized by comprising:
a detection unit for detecting a current vehicle block in a foreground block of a current frame of an input image sequence;
a first adjusting unit, configured to adjust a size of a current vehicle block according to a relationship between a first lane width of a lane in which a cached vehicle block in a first frame or a previous matching frame of each cached block in a cache and a second lane width of the lane in which the current vehicle block is located in the current frame;
the matching unit is used for matching the current vehicle block adjusted by the first adjusting unit with the cache vehicle block and determining whether the current vehicle block and the cache vehicle block are the same vehicle;
a calculating unit, configured to calculate a travel distance of the vehicle within a first time when it is determined that the current vehicle block and the cached vehicle block are the same vehicle, where the first time is equal to a difference between the current frame and the first frame or a previous matching frame, and calculate the vehicle speed according to the first time and the travel distance.
2. The apparatus of claim 1, wherein the apparatus further comprises:
a second adjusting unit, configured to adjust the size of the foreground block according to a lane width in the current frame;
and the detection unit detects the current vehicle block according to the adjusted foreground block size.
3. The apparatus of claim 1, wherein the matching unit comprises:
the first calculation module is used for matching the current vehicle block after being adjusted in size with the cache vehicle blocks in the first frame of each cache block, and calculating to obtain a first matching degree of each cache block;
a first determining module, configured to determine that the current vehicle block and a cached vehicle block in a first frame of a cached block are the same vehicle when the first matching degree of one cached block is greater than or equal to a first threshold;
the second calculation module is used for matching the current vehicle block after being adjusted in size with the cache vehicle block in the previous matching frame of each cache block when the first matching degree of each cache block is smaller than a first threshold value, and calculating to obtain a second matching degree;
a second determining module, configured to determine that the current vehicle block and a cached vehicle block in a previous matching frame of the one cached block are the same vehicle when the second matching degree of the one cached block is greater than or equal to a first threshold.
4. The apparatus of claim 3, when the second matching degree of one cache block is greater than or equal to a first threshold, the matching unit further comprising:
an updating module, configured to replace the current frame with a previous matching frame stored in the one cache block in the cache, and replace the current vehicle block with a cached vehicle block in the previous matching frame stored in the one cache block in the cache;
and when the second matching degree of each cache block is smaller than a first threshold, the updating module stores the current frame and the current vehicle block into the cache as a first frame and a cache vehicle block of a new cache block.
5. The apparatus of claim 1, wherein the buffer stores therein information about each buffer block, including first information about buffered vehicle blocks in the first frame and first frame of each buffer block and second information about buffered vehicle blocks in the previous matching frame and previous matching frame of each buffer block, wherein the first information includes: a frame number of the first frame in a sequence of input images, a location of the cached vehicle block in the first frame, and the first frame image; the second information includes: a frame number of the previous matching frame in the sequence of input images, a position of the buffered vehicle block in the previous matching frame, and the previous matching frame image;
the related information further comprises: and matching times, wherein when the matching is successful, the matching unit adds 1 to the matching times.
6. The apparatus of claim 5, wherein the apparatus further comprises:
a deleting unit, configured to delete a buffer block from the buffer when a difference between a current frame and a first frame of the buffer block exceeds a second threshold.
7. The apparatus according to claim 1, wherein the calculation unit calculates a first position of the vehicle in a world coordinate system corresponding to a current vehicle block position in a current frame and a second position of the vehicle in the world coordinate system corresponding to a cached vehicle block position in a first frame or a previous matching frame, based on a conversion matrix of the world coordinate system and an input image coordinate system; taking the distance of the first position and the second position as the travel distance.
8. The apparatus of claim 1, wherein the apparatus further comprises:
and a lane width calculation unit for calculating a lane width of a lane in which the vehicle travels corresponding to each position in the input image coordinate system, based on the conversion matrix of the world coordinate system and the input image coordinate system.
9. A vehicle speed detection method, characterized by comprising:
detecting a current vehicle block in a foreground block of a current frame of an input image sequence;
adjusting the size of the current vehicle block according to the relation between the first lane width of the lane where the buffer vehicle block in the first frame or the previous matching frame of each buffer block in the buffer and the second lane width of the lane where the current vehicle block is located in the current frame;
matching the current vehicle block after being adjusted in size with the cache vehicle block to determine whether the current vehicle block and the cache vehicle block are the same vehicle;
when the current vehicle block and the cache vehicle block are determined to be the same vehicle, calculating the travel distance of the vehicle in a first time, wherein the first time is equal to the difference between the current frame and the first frame or a previous matching frame;
calculating the vehicle speed from the first time and the travel distance.
10. The method of claim 9, wherein matching a current vehicle block with the cached vehicle block comprises:
matching a current vehicle block with a cache vehicle block in a first frame of each cache block, calculating to obtain a first matching degree of each cache block, and when the first matching degree of one cache block is greater than or equal to a first threshold value, determining that the current vehicle block and the cache vehicle block in the first frame of the cache block are the same vehicle;
when the first matching degree of each cache block is smaller than a first threshold value, matching the current vehicle block after being adjusted in size with a cache vehicle block in a previous matching frame of each cache block, calculating to obtain a second matching degree, and when the second matching degree of one cache block is larger than or equal to the first threshold value, determining that the current vehicle block and the cache vehicle block in the previous matching frame of the cache block are the same vehicle.
CN201910688572.6A 2019-07-29 2019-07-29 Vehicle speed detection method and device Active CN112309134B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201910688572.6A CN112309134B (en) 2019-07-29 2019-07-29 Vehicle speed detection method and device
JP2020092429A JP7435258B2 (en) 2019-07-29 2020-05-27 Vehicle speed detection method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910688572.6A CN112309134B (en) 2019-07-29 2019-07-29 Vehicle speed detection method and device

Publications (2)

Publication Number Publication Date
CN112309134A true CN112309134A (en) 2021-02-02
CN112309134B CN112309134B (en) 2022-12-16

Family

ID=74329240

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910688572.6A Active CN112309134B (en) 2019-07-29 2019-07-29 Vehicle speed detection method and device

Country Status (2)

Country Link
JP (1) JP7435258B2 (en)
CN (1) CN112309134B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101877174A (en) * 2009-09-29 2010-11-03 杭州海康威视软件有限公司 Vehicle speed measurement method, supervisory computer and vehicle speed measurement system
CN102810250A (en) * 2012-07-31 2012-12-05 长安大学 Video based multi-vehicle traffic information detection method
CN104575003A (en) * 2013-10-23 2015-04-29 北京交通大学 Method for detecting vehicle speed based on road monitoring videos
US20170098304A1 (en) * 2015-10-06 2017-04-06 Genetec Inc. Camera-based speed estimation and system calibration therefor
CN109147341A (en) * 2018-09-14 2019-01-04 杭州数梦工场科技有限公司 Violation vehicle detection method and device
CN109509345A (en) * 2017-09-15 2019-03-22 富士通株式会社 Vehicle detection apparatus and method
CN109979206A (en) * 2017-12-28 2019-07-05 杭州海康威视系统技术有限公司 Vehicle speed measuring method, device, system, electronic equipment and storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101877174A (en) * 2009-09-29 2010-11-03 杭州海康威视软件有限公司 Vehicle speed measurement method, supervisory computer and vehicle speed measurement system
CN102810250A (en) * 2012-07-31 2012-12-05 长安大学 Video based multi-vehicle traffic information detection method
CN104575003A (en) * 2013-10-23 2015-04-29 北京交通大学 Method for detecting vehicle speed based on road monitoring videos
US20170098304A1 (en) * 2015-10-06 2017-04-06 Genetec Inc. Camera-based speed estimation and system calibration therefor
CN109509345A (en) * 2017-09-15 2019-03-22 富士通株式会社 Vehicle detection apparatus and method
CN109979206A (en) * 2017-12-28 2019-07-05 杭州海康威视系统技术有限公司 Vehicle speed measuring method, device, system, electronic equipment and storage medium
CN109147341A (en) * 2018-09-14 2019-01-04 杭州数梦工场科技有限公司 Violation vehicle detection method and device

Also Published As

Publication number Publication date
CN112309134B (en) 2022-12-16
JP2021022366A (en) 2021-02-18
JP7435258B2 (en) 2024-02-21

Similar Documents

Publication Publication Date Title
US10261515B2 (en) System and method for controlling navigation of a vehicle
CN113168520A (en) Method of tracking objects in a scene
JP6439757B2 (en) Image processing apparatus and image processing method
CN115063454B (en) Multi-target tracking matching method, device, terminal and storage medium
Johnson et al. Real-time side-slip angle measurements using digital image correlation
CN104834886A (en) Method and device for detecting video image
CN112446353B (en) Video image trace line detection method based on depth convolution neural network
Ashraf et al. HVD-net: a hybrid vehicle detection network for vision-based vehicle tracking and speed estimation
CN113516853A (en) Multi-lane traffic flow detection method for complex monitoring scene
CN112309134B (en) Vehicle speed detection method and device
CN114037977B (en) Road vanishing point detection method, device, equipment and storage medium
CN115512542B (en) Track restoration method and system considering shielding based on roadside laser radar
JP4469980B2 (en) Image processing method for tracking moving objects
JP2007188269A (en) On-image mobile object tracking method and device
CN113269007A (en) Target tracking device and method for road monitoring video
CN111415369B (en) Target real-time speed measurement method based on road-side monocular camera
CN113902047A (en) Image element matching method, device, equipment and storage medium
KR20220043316A (en) License plate detection apparatus and method using image warping
JP2021051542A (en) Learning data collection device
JP4573590B2 (en) Moving object measuring method and apparatus by image processing
TWI823721B (en) Method for identifying lane line and related devices
CN114779271B (en) Target detection method and device, electronic equipment and storage medium
CN115222771B (en) Target tracking method and device
CN112926493B (en) License plate detection method, device, equipment and medium
CN113269004B (en) Traffic counting device and method and electronic equipment

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