CN114179865A - Turnout motion monitoring method, device and system based on optical flow method - Google Patents
Turnout motion monitoring method, device and system based on optical flow method Download PDFInfo
- Publication number
- CN114179865A CN114179865A CN202111346627.9A CN202111346627A CN114179865A CN 114179865 A CN114179865 A CN 114179865A CN 202111346627 A CN202111346627 A CN 202111346627A CN 114179865 A CN114179865 A CN 114179865A
- Authority
- CN
- China
- Prior art keywords
- turnout
- target
- image sequence
- optical flow
- target image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 145
- 230000033001 locomotion Effects 0.000 title claims abstract description 102
- 230000003287 optical effect Effects 0.000 title claims abstract description 71
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 230000008569 process Effects 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012806 monitoring device Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
- B61L23/04—Control, warning or like safety means along the route or between vehicles or trains for monitoring the mechanical state of the route
- B61L23/042—Track changes detection
- B61L23/047—Track or rail movements
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a turnout motion monitoring method, device and system based on an optical flow method, wherein the method comprises the following steps: acquiring a target image sequence of a turnout rotation process; carrying out target detection on the target image sequence, and determining a target pixel area corresponding to a turnout notch in each frame image of the target image sequence; determining a plurality of target key points at the turnout notch based on the target pixel area; and obtaining the target rotating speed of the turnout based on the position information of the target key points in the target image sequence. The method detects the accurate position of the turnout notch through target detection, analyzes the motion characteristics of a target key point in a target pixel area by using an optical flow method, and further obtains the target rotation speed of the turnout, belongs to a non-contact monitoring method, does not influence the original turnout motion, and has high turnout motion judgment accuracy.
Description
Technical Field
The invention relates to the technical field of rail transit, in particular to a turnout motion monitoring method, device and system based on an optical flow method.
Background
The turnout is equipment for determining a train running route in rail transit, and the movement of the turnout is directly related to the train running safety.
The traditional turnout motion monitoring means mostly judges whether turnout motion is normal or not by acquiring sensor data such as current, voltage or moment and the like in the turnout based on an internal sensor and comparing the sensor data with a standard change trend.
The method for indirectly judging whether the turnout movement is abnormal or not by collecting data related to the turnout movement is a method for indirectly judging whether the turnout movement is abnormal or not, the change condition of related parameters sometimes cannot reflect real turnout movement, multiple parameters are often combined for simultaneous judgment, the judgment process is complex, the method has great subjectivity, and because the change of the parameters is not completely consistent during the turnout movement every time, the judgment whether the turnout movement is abnormal or not is often judged according to experience, and the judgment accuracy is low.
Disclosure of Invention
The invention provides a turnout motion monitoring method, device and system based on an optical flow method, which are used for solving the problem of low turnout motion monitoring accuracy in the prior art.
The invention provides a turnout motion monitoring method based on an optical flow method, which comprises the following steps:
acquiring a target image sequence of a turnout rotation process;
carrying out target detection on the target image sequence, and determining a target pixel area corresponding to a turnout notch in each frame image of the target image sequence;
determining a plurality of target key points at the turnout notch based on the target pixel area;
and obtaining the target rotating speed of the turnout based on the position information of the target key points in the target image sequence.
According to the turnout motion monitoring method based on the optical flow method, the method for obtaining the target rotating speed of the turnout based on the position information of the plurality of target key points in the target image sequence comprises the following steps:
obtaining the rotating speeds of a plurality of target key points based on the position information of each target key point in the target image sequence;
determining the target rotation speed based on an average of the rotation speeds of the plurality of target key points.
According to the turnout motion monitoring method based on the optical flow method provided by the invention, after the target rotating speed of the turnout is obtained based on the position information of the plurality of target key points in the target image sequence, the method further comprises the following steps:
obtaining a speed time curve of the turnout rotation based on the target rotation speed of the turnout;
and carrying out integral processing on the speed-time curve to obtain the size information of the turnout notch.
According to the turnout motion monitoring method based on the optical flow method provided by the invention, after the target image sequence in the turnout rotation process is obtained, before the target detection is carried out on the target image sequence and the target pixel area corresponding to the turnout notch in each frame image of the target image sequence is determined, the method further comprises the following steps:
and carrying out noise reduction processing on each frame of image in the target image sequence through Gaussian filtering.
According to the turnout motion monitoring method based on the optical flow method, the target key point comprises at least one of a boundary point and a boundary intersection point of the turnout.
The invention also provides a turnout motion monitoring device based on the optical flow method, which comprises the following steps:
the acquisition module is used for acquiring a target image sequence of the turnout rotation process;
the first processing module is used for carrying out target detection on the target image sequence and determining a target pixel area corresponding to a turnout notch in each frame image of the target image sequence;
the second processing module is used for determining a plurality of target key points at the turnout gap based on the target pixel region;
and the third processing module is used for obtaining the target rotating speed of the turnout based on the position information of the target key points in the target image sequence.
The invention also provides a turnout motion monitoring system based on the optical flow method, which comprises the following steps:
a switch motion monitoring device based on the optical flow method as described above;
the camera is installed on the turnout and used for acquiring a target image sequence of the turnout rotation process.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the turnout motion monitoring method based on the optical flow method.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the optical flow method-based switch motion monitoring method as described in any of the above.
The present invention also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the optical flow based switch motion monitoring method as described in any one of the above.
According to the turnout movement monitoring method, device and system based on the optical flow method, the accurate position of the turnout notch is detected through target detection, the movement characteristics of the target key points in the target pixel area are analyzed through the optical flow method, and then the target rotation speed of the turnout is obtained.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a turnout motion monitoring method based on an optical flow method provided by the invention;
FIG. 2 is a schematic structural diagram of a turnout motion monitoring device based on an optical flow method provided by the invention;
fig. 3 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the embodiments of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience in describing the embodiments of the present invention and simplifying the description, but do not indicate or imply that the referred devices or elements must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the embodiments of the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the embodiments of the present invention, it should be noted that, unless explicitly stated or limited otherwise, the terms "connected" and "connected" are to be interpreted broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; may be directly connected or indirectly connected through an intermediate. Specific meanings of the above terms in the embodiments of the present invention can be understood in specific cases by those of ordinary skill in the art.
In embodiments of the invention, unless expressly stated or limited otherwise, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through intervening media. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of an embodiment of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
The turnout is equipment for determining a train running route in rail transit, and the movement of the turnout is directly related to the train running safety.
The following describes the turnout motion monitoring method based on the optical flow method with reference to fig. 1, where an execution subject of the turnout motion monitoring method may be a controller on a device side, or a cloud side, or an edge server.
The turnout is equipment for determining a train running route in rail transit, and the movement of the turnout is directly related to the train running safety.
The optical flow method is a method for calculating motion information of an object between adjacent frames by using the change of pixels in an image sequence in a time domain and the correlation between adjacent frames to find the corresponding relationship between a previous frame and a current frame.
As shown in fig. 1, the switch motion monitoring method based on the optical flow method of the present invention includes steps 110 to 140.
And step 110, acquiring a target image sequence of the turnout rotation process.
The method comprises the steps of installing image acquisition equipment such as a camera on a train running route to obtain related images of the turnout.
The turnout rotation means that the movable end of the turnout moves relative to the fixed end of the turnout, and the turnout rotation can realize the conversion of the train operation line.
The camera continuously acquires a series of multiple turnout images according to a time sequence in sequence to obtain a corresponding target image sequence.
And 120, performing target detection on the target image sequence, and determining a target pixel area corresponding to a turnout notch in each frame image of the target image sequence.
It can be understood that when the movable end of the turnout moves relative to the fixed end of the turnout, a turnout notch is formed at the turnout, and in the rotating process of the turnout, the size of the turnout notch changes along with the rotation of the turnout.
And performing target detection on the target image sequence in the turnout rotation process, and determining a target pixel area corresponding to the turnout notch in each frame of image of the target image sequence.
In the turning process of the turnout, the size of the turnout gap changes along with the turning of the turnout, and the target pixel areas corresponding to the turnout gap in each frame image of the target image sequence are also different.
In this embodiment, the target image sequence is subjected to target detection, objects belonging to the switch and the switch gap in the target image sequence need to be identified, and the position parameters corresponding to the switch gap, that is, the target pixel region, are output.
In actual implementation, the target detection methods used for target detection of the target image sequence include, but are not limited to, Fast R-CNN, FPN, YOLO, SSD, and RetinaNet.
And step 130, determining a plurality of target key points at the turnout gap based on the target pixel area.
And determining a plurality of target key points at the turnout gap according to the target pixel area corresponding to the turnout gap determined in the step 120.
The key points of the target can represent the moving characteristics of the turnout and are important points for analyzing the movement of the turnout and determining the size of a turnout gap.
The moving of the turnout is that the movable end of the turnout moves relative to the fixed end of the turnout, and the plurality of target key points at the turnout notch in the target image sequence comprise points describing the movable end of the turnout.
In this embodiment, a plurality of target key points at the turnout notch may be determined from a target pixel region of the target image sequence by using Harris corner detection.
Harris angular point detection uses a fixed penetration expansion to slide on an image in any direction, the gray level change degrees of pixels in a window before sliding and after sliding are compared, if the sliding in any direction has larger gray level change, the angular point in the window is determined.
The invention detects the accurate position of the turnout gap through target detection, namely a target pixel area, and ensures that key points used by turnout monitoring movement cannot be influenced by other key points of a target image sequence.
And 140, obtaining the target rotating speed of the turnout based on the position information of the plurality of target key points in the target image sequence.
In the step, the position information of the target key points on each frame of image in the target image sequence is analyzed, and the target rotation speed of the turnout rotation process can be obtained by combining the change of each frame of image in the time domain.
The method comprises the steps of acquiring a target rotation speed based on position information of a plurality of target key points in a target image sequence, and calculating motion information of a turnout by utilizing a change relation of the positions of the plurality of target key points of a target pixel area in the target image sequence in a time domain through an optical flow method.
In this embodiment, the optical flow method can directly detect the motion of the switch, and track the motion direction of the key point of the target and the corresponding motion speed.
The optical flow method comprises a sparse optical flow method and a dense optical flow method, the sparse optical flow method calculates motion information by tracking a few key points, and the dense optical flow method calculates global pixels to obtain the motion information.
In the embodiment, a sparse optical flow method can be used for analyzing a plurality of target key points to obtain the target movement speed of the turnout, so that the calculation overhead is effectively reduced.
In the embodiment, the target rotating speed of the turnout movement is calculated by the optical flow method, the target rotating speed can be used for observing the change condition of the gap when a train passes through the turnout, the anti-vibration performance and the integral tightness degree of the turnout can be analyzed by the left-right shaking amplitude of the turnout gap, and a scientific basis is provided for the maintenance and the conservation of the turnout.
The method detects the accurate position of the turnout gap through target detection, analyzes the motion characteristics of the target key point in the target pixel area by using an optical flow method, further obtains the target rotation speed of the turnout, belongs to non-contact detection, does not influence the original turnout motion, directly detects the turnout motion speed, does not use the relevant motion parameters to indirectly judge, and has high turnout motion judgment accuracy.
In the related art, some technologies for judging whether turnout movement is in place or not by detecting turnout movement end points through auxiliary lines by using images during turnout movement appear, the technologies are greatly influenced by illumination, a camera for acquiring images needs to be accurately calibrated, and the movement of the turnout can influence the accuracy of image acquisition and movement judgment.
The invention utilizes the difference between the optical flow method and the auxiliary line measuring method, the optical flow method does not need to determine the background information in the turnout scene in advance, the requirement on the calibration precision of the camera is not high, the movement of the movable end in the turnout can be sensitively monitored in the scene of turnout movement, and the accurate target rotating speed of the turnout movement is further obtained.
According to the turnout movement monitoring method based on the optical flow method, the accurate position of a turnout notch is detected through target detection, the movement characteristics of target key points in a target pixel area are analyzed by using the optical flow method, and then the target rotation speed of the turnout is obtained.
In some embodiments, step 140 comprises: obtaining the rotating speeds of a plurality of target key points based on the position information of each target key point in the target image sequence;
the target rotational speed is determined based on an average of the rotational speeds of the plurality of target key points.
A plurality of target key points are determined in a target pixel area of a target image sequence, and corresponding rotation speed can be acquired for each target key point through an optical flow method.
In this embodiment, after the rotational speeds corresponding to the plurality of target key points are obtained, an average value is obtained for the plurality of rotational speeds, and the average value is the target rotational speed of the turnout rotation.
The average value of the rotating speeds corresponding to the target key points is obtained, the centralized trend of the turnout rotating speed can be effectively reflected, and the obtained target rotating speed can directly and simply reflect the rotating speed characteristic of the turnout.
In actual implementation, when the number of target key points in a target image sequence is large, or speed analysis is performed on a plurality of turnouts on a train running line, turnout rotation analysis can be performed by a method of calculating a speed average value or a standard deviation.
In some embodiments, after step 140, the switch motion monitoring method based on optical flow method of the present invention further comprises: obtaining a speed time curve of turnout rotation based on the target rotation speed of turnout; and integrating the speed-time curve to obtain the size information of the turnout gap.
It will be appreciated that the sequence of target images includes switch images of switch turns taken at different times.
When the target image sequence is analyzed, the target rotating speed of the turnout rotation at different time can be obtained, further, a speed-time curve of the turnout rotation is obtained, integration processing is carried out on the speed-time curve of the turnout rotation, and size information of a turnout notch is obtained.
The size of the turnout gap is changed in the turnout movement process, and the speed-time curve is subjected to integral processing by the time from the turnout starting movement to the turnout completing line conversion and ending movement, so that the size of the turnout gap after the turnout completing line conversion can be obtained.
Through the size analysis of the switch breach to the switch after accomplishing the circuit conversion, can confirm the degree of excursion of switch breach, and then the shockproof performance and the whole close elasticity degree of pasting of analysis switch provide the scientific foundation for the whole switch of industry and power federation.
A specific embodiment is described below.
Before the turnout is put into use, manual marking is carried out on the turnout movement process, and a standard movement curve, the starting position and the ending position of a turnout notch during turnout movement are collected.
The starting position of the turnout notch refers to the starting position of the movable end of the turnout, and the ending position refers to the ending position of the movable end of the turnout after the turnout completes the line conversion.
And in the stage of installing and trying out the turnout, tracking a target key point by using sparse optical flow, acquiring the target rotating speed of the turnout, and acquiring a corresponding speed-time curve. And comparing the speed curve with the marked standard motion curve, acquiring the size information of the turnout gap by integrating the speed time curve, and judging whether the turnout motion is normal or not.
In some embodiments, between step 110 and step 120, further comprising: and carrying out noise reduction processing on each frame image in the target image sequence through Gaussian filtering.
Gaussian filtering is essentially a filter for smoothing a signal, and can effectively remove noise of each frame of image in a target image sequence.
In some embodiments, a plurality of target keypoints are determined at a target pixel region of each frame image of the target image sequence, the target keypoints including at least one of boundary points and boundary intersections of switches.
The boundary point of the turnout can be a point on the boundary where the movable end of the turnout is located, and the boundary intersection point refers to an intersection point of the boundary and the boundary.
In the embodiment, in the turnout rotation process, the boundary point and the boundary intersection point are points with obvious pixel change in the target image sequence, and the accuracy of the target rotation speed can be improved and the turnout motion can be effectively monitored by determining the boundary point and the boundary intersection point as target key points and then carrying out speed analysis by using an optical flow method.
The following describes the switch motion monitoring device based on the optical flow method, and the switch motion monitoring device based on the optical flow method described below and the switch motion monitoring method based on the optical flow method described above may be referred to correspondingly.
As shown in fig. 2, the switch motion monitoring device based on the optical flow method provided by the invention comprises:
the obtaining module 210 is configured to obtain a target image sequence of a turnout rotation process;
the first processing module 220 is configured to perform target detection on the target image sequence, and determine a target pixel region corresponding to a turnout notch in each frame image of the target image sequence;
the second processing module 230 is configured to determine a plurality of target key points at the turnout gap based on the target pixel region;
and the third processing module 240 is configured to obtain a target rotation speed of the turnout based on the position information of the plurality of target key points in the target image sequence.
According to the turnout movement monitoring device based on the optical flow method, the accurate position of a turnout notch is detected through target detection, the movement characteristics of target key points in a target pixel area are analyzed through the optical flow method, and then the target rotation speed of the turnout is obtained.
In some embodiments, the third processing module 240 is configured to obtain rotation speeds of a plurality of target key points based on the position information of each target key point in the target image sequence;
the target rotational speed is determined based on an average of the rotational speeds of the plurality of target key points.
In some embodiments, the third processing module 240 is further configured to obtain a speed-time curve of the turnout based on the target turning speed of the turnout; and integrating the speed-time curve to obtain the size information of the turnout gap.
In some embodiments, the first processing module 220 is further configured to perform noise reduction on each frame image in the target image sequence through gaussian filtering.
In some embodiments, the target keypoints comprise at least one of boundary points and boundary intersections of switches.
The invention also provides a turnout motion monitoring system based on the optical flow method.
The turnout motion monitoring system based on the optical flow method comprises a camera and the turnout motion monitoring device based on the optical flow method.
The camera is installed in the switch, and the camera obtains a series of many switch images according to time sequence in proper order in succession, obtains the target image sequence of switch rotation process.
In actual execution, the camera can be installed beside the turnout and is positioned outside the limit invasion range of the train, so that the camera cannot move greatly due to the running of the train, and the quality of the obtained target image sequence of the turnout in the rotating process is ensured.
The turnout motion monitoring device based on the optical flow method can be located in a train operation monitoring room, can detect whether turnout motion is normal or not through the turnout motion monitoring device based on the optical flow method, can also acquire a target image sequence in real time, and can monitor turnout in real time.
According to the turnout movement monitoring system based on the optical flow method, the accurate position of a turnout notch is detected through target detection, the movement characteristics of target key points in a target pixel area are analyzed by using the optical flow method, and then the target rotation speed of the turnout is obtained.
Fig. 3 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 3: a processor (processor)310, a communication Interface (communication Interface)320, a memory (memory)330 and a communication bus 340, wherein the processor 310, the communication Interface 320 and the memory 330 communicate with each other via the communication bus 340. The processor 310 may invoke logic instructions in the memory 330 to perform a method of switch motion monitoring based on optical flow, the method comprising: acquiring a target image sequence of a turnout rotation process; carrying out target detection on the target image sequence, and determining a target pixel area corresponding to a turnout notch in each frame image of the target image sequence; determining a plurality of target key points at the turnout gap based on the target pixel region; and obtaining the target rotating speed of the turnout based on the position information of the target key points in the target image sequence.
In addition, the logic instructions in the memory 330 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, when the computer program is executed by a processor, a computer can execute the switch motion monitoring method based on the optical flow method provided by the above methods, the method includes: acquiring a target image sequence of a turnout rotation process; carrying out target detection on the target image sequence, and determining a target pixel area corresponding to a turnout notch in each frame image of the target image sequence; determining a plurality of target key points at the turnout gap based on the target pixel region; and obtaining the target rotating speed of the turnout based on the position information of the target key points in the target image sequence.
In yet another aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to execute the optical flow method-based switch motion monitoring method provided by the above methods, the method including: acquiring a target image sequence of a turnout rotation process; carrying out target detection on the target image sequence, and determining a target pixel area corresponding to a turnout notch in each frame image of the target image sequence; determining a plurality of target key points at the turnout gap based on the target pixel region; and obtaining the target rotating speed of the turnout based on the position information of the target key points in the target image sequence.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A turnout motion monitoring method based on an optical flow method is characterized by comprising the following steps:
acquiring a target image sequence of a turnout rotation process;
carrying out target detection on the target image sequence, and determining a target pixel area corresponding to a turnout notch in each frame image of the target image sequence;
determining a plurality of target key points at the turnout notch based on the target pixel area;
and obtaining the target rotating speed of the turnout based on the position information of the target key points in the target image sequence.
2. The method for monitoring the switch motion based on the optical flow method as claimed in claim 1, wherein the obtaining the target rotation speed of the switch based on the position information of the plurality of target key points in the target image sequence comprises:
obtaining the rotating speeds of a plurality of target key points based on the position information of each target key point in the target image sequence;
determining the target rotation speed based on an average of the rotation speeds of the plurality of target key points.
3. The method for monitoring the motion of the turnout based on the optical flow method according to claim 1, wherein after obtaining the target rotation speed of the turnout based on the position information of the plurality of target key points in the target image sequence, the method further comprises:
obtaining a speed time curve of the turnout rotation based on the target rotation speed of the turnout;
and carrying out integral processing on the speed-time curve to obtain the size information of the turnout notch.
4. The method for monitoring the turnout motion based on the optical flow method according to any one of claims 1-3, wherein after the target image sequence of the turnout rotation process is obtained, before the target detection is performed on the target image sequence and the target pixel area corresponding to the turnout notch in each frame image of the target image sequence is determined, the method further comprises:
and carrying out noise reduction processing on each frame of image in the target image sequence through Gaussian filtering.
5. The optical flow method-based switch motion monitoring method as claimed in any one of claims 1-3, wherein said target key point comprises at least one of a boundary point and a boundary intersection point of said switch.
6. A turnout motion monitoring device based on an optical flow method is characterized by comprising:
the acquisition module is used for acquiring a target image sequence of the turnout rotation process;
the first processing module is used for carrying out target detection on the target image sequence and determining a target pixel area corresponding to a turnout notch in each frame image of the target image sequence;
the second processing module is used for determining a plurality of target key points at the turnout gap based on the target pixel region;
and the third processing module is used for obtaining the target rotating speed of the turnout based on the position information of the target key points in the target image sequence.
7. A switch motion monitoring system based on an optical flow method is characterized by comprising the following components:
the switch motion monitoring device based on optical flow method as claimed in claim 6;
the camera is installed on the turnout and used for acquiring a target image sequence of the turnout rotation process.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the optical flow based switch motion monitoring method as claimed in any one of claims 1 to 5.
9. A non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements the steps of the switch motion monitoring method based on optical flow method according to any one of claims 1 to 5.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, carries out the steps of the switch motion monitoring method based on optical flow method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111346627.9A CN114179865A (en) | 2021-11-15 | 2021-11-15 | Turnout motion monitoring method, device and system based on optical flow method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111346627.9A CN114179865A (en) | 2021-11-15 | 2021-11-15 | Turnout motion monitoring method, device and system based on optical flow method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114179865A true CN114179865A (en) | 2022-03-15 |
Family
ID=80602165
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111346627.9A Pending CN114179865A (en) | 2021-11-15 | 2021-11-15 | Turnout motion monitoring method, device and system based on optical flow method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114179865A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446630A (en) * | 2018-03-20 | 2018-08-24 | 平安科技（深圳）有限公司 | Airfield runway intelligent control method, application server and computer storage media |
| CN110293993A (en) * | 2019-08-09 | 2019-10-01 | 大连维德集成电路有限公司 | A kind of track switch detection device and system |
| CN111860137A (en) * | 2020-06-09 | 2020-10-30 | 北京航空航天大学 | Track turnout identification method based on vision |
| CN112307864A (en) * | 2019-07-31 | 2021-02-02 | 百度（美国）有限责任公司 | Method and device for determining target object and man-machine interaction system |
| CN113753094A (en) * | 2021-09-24 | 2021-12-07 | 北京杰迈科技股份有限公司 | Switch detection system and method |
-
2021
- 2021-11-15 CN CN202111346627.9A patent/CN114179865A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446630A (en) * | 2018-03-20 | 2018-08-24 | 平安科技（深圳）有限公司 | Airfield runway intelligent control method, application server and computer storage media |
| CN112307864A (en) * | 2019-07-31 | 2021-02-02 | 百度（美国）有限责任公司 | Method and device for determining target object and man-machine interaction system |
| US20210034868A1 (en) * | 2019-07-31 | 2021-02-04 | Baidu Usa Llc | Method and apparatus for determining a target object, and human-computer interaction system |
| CN110293993A (en) * | 2019-08-09 | 2019-10-01 | 大连维德集成电路有限公司 | A kind of track switch detection device and system |
| CN111860137A (en) * | 2020-06-09 | 2020-10-30 | 北京航空航天大学 | Track turnout identification method based on vision |
| CN113753094A (en) * | 2021-09-24 | 2021-12-07 | 北京杰迈科技股份有限公司 | Switch detection system and method |
Non-Patent Citations (1)
| Title |
|---|
| 严强等: "光流法在机车安全行驶中的应用", 《计算机应用研究》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10480939B2 (en) | High speed stereoscopic pavement surface scanning system and method | |
| US10061993B2 (en) | Warning method of obstacles and device of obstacles | |
| EP2697738B1 (en) | Method and system of rail component detection using vision technology | |
| CN112418103B (en) | Bridge crane hoisting safety anti-collision system and method based on dynamic binocular vision | |
| CN106226157B (en) | Concrete structure member crevices automatic detection device and method | |
| CN103077526B (en) | There is train method for detecting abnormality and the system of depth detection function | |
| JP6524529B2 (en) | Building limit judging device | |
| CN201233223Y (en) | Lumber automatic monitor system | |
| CN104535356A (en) | Method and system for monitoring rope arrangement faults of drum steel wire rope on basis of machine vision | |
| JP6737638B2 (en) | Appearance inspection device for railway vehicles | |
| CN109489724A (en) | A kind of tunnel safe train operation environment comprehensive detection device and detection method | |
| CN109766746A (en) | A kind of track foreign matter detecting method of unmanned plane video | |
| CN107578021A (en) | Pedestrian detection method, apparatus and system based on deep learning network | |
| KR20150012384A (en) | Pothole Recognition System and Its Implementation Method | |
| CN111754460A (en) | Method, system and storage medium for automatically detecting gap of point switch | |
| CN102556119A (en) | Method for directly collecting gap data measured by indication lever gap image of railway point switch | |
| US20170228602A1 (en) | Method for detecting height | |
| EP3069955A1 (en) | Train self-position estimation device | |
| KR20160044757A (en) | Method and Apparatus for Analyzing Traffic Situation | |
| CN108957024A (en) | A kind of method, apparatus and electronic equipment of tachometric survey | |
| JP6699323B2 (en) | Three-dimensional measuring device and three-dimensional measuring method for train equipment | |
| CN114179865A (en) | Turnout motion monitoring method, device and system based on optical flow method | |
| RU2446471C1 (en) | Method for detecting moving objects and determining parameters thereof | |
| CN113866184A (en) | Non-contact hard spot detection method and non-contact hard spot detection system | |
| CN109753858A (en) | A kind of road barricade object detecting method and device based on binocular 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 |