CN106022309B - A kind of monitoring method and system of the automatic detection LVDT pull rod state based on video - Google Patents
A kind of monitoring method and system of the automatic detection LVDT pull rod state based on video Download PDFInfo
- Publication number
- CN106022309B CN106022309B CN201610420248.2A CN201610420248A CN106022309B CN 106022309 B CN106022309 B CN 106022309B CN 201610420248 A CN201610420248 A CN 201610420248A CN 106022309 B CN106022309 B CN 106022309B
- Authority
- CN
- China
- Prior art keywords
- pull rod
- lvdt
- video
- characteristic point
- drawhead
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The monitoring method and system for the automatic detection LVDT pull rod state based on video that the invention discloses a kind of, this method comprises: obtaining the video image monitored in real time to LVDT;The characteristic point in area to be tested is preset by the video images detection;The motion change of the characteristic point is tracked;By the relative displacement between drawhead detection zone and pull rod fixing piece region, the moving distance of LVDT pull rod is determined.The monitoring method and system of automatic detection LVDT pull rod state provided by the present invention based on video, pass through video monitoring LVDT pull rod, can directly the working condition of LVDT be tracked and be analyzed, further when found the abnormal situation can automatic alarm, to reduce the investment of loss and manpower in monitor video caused by unit exception.
Description
Technical field
The present invention relates to the target following technical fields in digital picture, more particularly to a kind of automatic inspection based on video
Survey the monitoring method and system of LVDT pull rod state.
Background technique
With the development of multimedia information technology, various high-tech products are had more visitors or business than one can attend to.Wherein in information-intensive society, monitoring view
Frequency technology is rapidly developed, monitoring device spread life in major place, such as: bank, school, shop, cell,
Workshop, school etc..The utilization of monitoring brings great side to the prevention and case proof of our life public security, dangerous situation
It helps.Wherein, the video monitoring in workshop is particularly important, understands the equipment work feelings in workshop in time by video monitoring
Condition can notify people promptly to safeguard once noting abnormalities, and loss is reduced to minimum.
The intervention of traditional workshop video monitoring system mainly manually.Firstly, camera is acquired by monitoring system
The video come is transmitted to monitoring center;Then staff watches the video in video wall attentively in real time, rule of thumb judges whether to deposit
In anomalous event.But conventional monitoring systems it is impossible to meet real time monitoring place requirement, specific deficiency be embodied in
Under several aspects: one, people can not monitor a large amount of video in real time in 24 hours, can not real-time watch device state;Two,
Due to the physiology weakness of people itself, visual fatigue can be caused by watching monitor video attentively for a long time, to can not discover security threat;
Three, after abnormal conditions occur, if can not know time of origin in time, it will cause largely to lose.It can be seen that inquiry and it is clear
Monitor video of looking at is time- and labor-consuming, and efficiency is very low.In consideration of it, being directed to the LVDT pull rod exception problem, how to use
Video Analysis Technology is directly tracked and is analyzed to LVDT working condition, notes abnormalities and automatic alarm is those skilled in the art
Member's technical problem urgently to be resolved.
Summary of the invention
The monitoring method and system for the automatic detection LVDT pull rod state based on video that the object of the present invention is to provide a kind of,
Purpose is by being automatically performed the monitoring to LVDT working condition using image analysis technology, to reduce caused by unit exception
The investment of loss and manpower in monitor video.
In order to solve the above technical problems, the present invention provides a kind of monitoring of automatic detection LVDT pull rod state based on video
Method, comprising:
Obtain the video image monitored in real time to LVDT;
The characteristic point in area to be tested is preset by the video images detection;
The motion change of the characteristic point is tracked;
By the relative displacement between drawhead detection zone and pull rod fixing piece region, the movement of LVDT pull rod is determined
Distance.
Optionally, further includes:
By the video image, the straight line between LVDT drawhead and pull rod fixing piece is detected, determines the current of pull rod
Direction;
It is compared described when front direction with preset direction, judges whether pull rod falls off.
Optionally, described to be compared described when front direction with preset direction, judging whether pull rod falls off includes:
By the left half height and right half height of current frame image drawhead, drawhead in current frame image is determined
The absolute value of left and right two parts displacement;
The absolute value is compared with preset threshold;When the absolute value is greater than the preset threshold, determine to draw
Bar has fallen off.
Optionally, after the video image for obtaining and being monitored in real time to LVDT further include:
Equal proportion scaling is carried out to the video image got, zoom factor is long image or width and display area corresponding sides
Ratio;
Gray processing processing is carried out to the image after scaling, and enhancing processing is carried out using color histogram to image.
Optionally, the characteristic point is angle point.
Optionally, the motion change to the characteristic point, which track, includes:
Calculate the position of the characteristic point in previous frame image in drawhead detection zone;
In current frame image using optical flow algorithm around the characteristic point position of the previous frame image in predeterminable area
It scans for;
After the current frame image searches corresponding characteristic point, drawhead detection zone is updated to present frame
Characteristic point region.
The monitoring system for the automatic detection LVDT pull rod state based on video that the present invention also provides a kind of, comprising:
Video image obtains module, for obtaining the video image monitored in real time to LVDT;
Characteristic point detection module, for presetting the characteristic point in area to be tested by the video images detection;
Tracking module is tracked for the motion change to the characteristic point;
Determining module, for being determined by the relative displacement between drawhead detection zone and pull rod fixing piece region
The moving distance of LVDT pull rod.
Optionally, further includes:
Fall off detection module, for detecting straight between LVDT drawhead and pull rod fixing piece by the video image
Line, determine pull rod works as front direction;It is compared described when front direction with preset direction, judges whether pull rod falls off.
Optionally, the detection module that falls off is specifically used for:
By the left half height and right half height of current frame image drawhead, drawhead in current frame image is determined
The absolute value of left and right two parts displacement;The absolute value is compared with preset threshold;When the absolute value is greater than described pre-
If when threshold value, determining that pull rod has fallen off.
Optionally, the tracking module includes:
Computing unit, for calculating the position of the characteristic point in previous frame image in drawhead detection zone;
Search unit, for utilizing optical flow algorithm in the characteristic point position week of the previous frame image in current frame image
It encloses in predeterminable area and scans for;
Updating unit, for after the current frame image searches corresponding characteristic point, by drawhead detection zone
It is updated to the characteristic point region of present frame.
The monitoring method and system of automatic detection LVDT pull rod state provided by the present invention based on video, pass through acquisition
The video image that LVDT is monitored in real time;The characteristic point in area to be tested is preset by video images detection;To feature
The motion change of point is tracked;It is determined by the relative displacement between drawhead detection zone and pull rod fixing piece region
The moving distance of LVDT pull rod.As it can be seen that the monitoring side of the automatic detection LVDT pull rod state provided by the present invention based on video
Method and system directly can be tracked and be analyzed to the working condition of LVDT, further be existed by video monitoring LVDT pull rod
When found the abnormal situation can automatic alarm, to reduce loss and manpower caused by unit exception in monitor video
Investment.
Detailed description of the invention
It, below will be to embodiment or existing for the clearer technical solution for illustrating the embodiment of the present invention or the prior art
Attached drawing needed in technical description is briefly described, it should be apparent that, the accompanying drawings in the following description is only this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is that one kind of the monitoring method of the automatic detection LVDT pull rod state provided by the present invention based on video is specific
The flow chart of embodiment;
Fig. 2 is another tool of the monitoring method of the automatic detection LVDT pull rod state provided by the present invention based on video
The flow chart of body embodiment;
Fig. 3 is another tool of the monitoring method of the automatic detection LVDT pull rod state provided by the present invention based on video
The flow chart of body embodiment;
Fig. 4 is that LVDT detection system sets schematic diagram;
Fig. 5 is target area characteristic point detection effect figure in LVDT detection;
Fig. 6 is pull rod testing result schematic diagram one in LVDT detection;
Fig. 7 is pull rod testing result schematic diagram two in LVDT detection;
Fig. 8 is the structure of the monitoring system of the automatic detection LVDT pull rod state provided in an embodiment of the present invention based on video
Block diagram.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.Obviously, described embodiments are only a part of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
A kind of specific implementation of the monitoring method of automatic detection LVDT pull rod state provided by the present invention based on video
The flow chart of mode as shown in Figure 1, this method comprises:
Step S101: the video image monitored in real time to LVDT is obtained;
The video image got can be the video that various video capture devices monitor LVDT according to fixed frequency, example
Such as: the video obtained by monitoring camera, the video etc. obtained by cell phone.
Step S102: the characteristic point in area to be tested is preset by the video images detection;
Step S103: the motion change of the characteristic point is tracked;
Step S104: by described in the relative displacement determination between drawhead detection zone and pull rod fixing piece region
The moving distance of LVDT pull rod.
Wherein, drawhead detection zone is the predeterminable area comprising drawhead, and pull rod fixing piece is to include pull rod fixing piece
Predeterminable area, above-mentioned two region can shift to an earlier date to be set by user, or by image detection determine, this is not influenced
Realization of the invention.
The relative displacement between drawhead detection zone and pull rod fixing piece region is being determined by feature point tracking,
Behind the position of i.e. current drawhead and the position of pull rod firmware, the position of pull rod can be calculated by simple Euclidean distance
It moves.Although camera has shake, the shake of camera all influences the position of drawhead and pull rod firmware.So passing through two
The distance of person position still can accurately obtain the measured value of pull rod.The measured value, which carries out grade ratio conversion with actual value, to be obtained
To the value of LVDT.
The monitoring method of automatic detection LVDT pull rod state provided by the present invention based on video, by obtaining to LVDT
The video image monitored in real time;The characteristic point in area to be tested is preset by video images detection;To the fortune of characteristic point
Dynamic variation is tracked;LVDT pull rod is determined by the relative displacement between drawhead detection zone and pull rod fixing piece region
Moving distance.As it can be seen that the monitoring method of the automatic detection LVDT pull rod state provided by the present invention based on video, passes through view
Frequency monitoring LVDT pull rod, directly can be tracked and be analyzed to the working condition of LVDT, further when found the abnormal situation
Can automatic alarm, to reduce the investment of loss and manpower in monitor video caused by unit exception.
On the basis of the above embodiments, the prison of the automatic detection LVDT pull rod state provided by the present invention based on video
Vision method can further include: detect to pull rod direction, to judge its process whether to fall off.Detailed process are as follows:
By the direction of setting pull rod starting, then determine whether pull rod falls off by the way that whether the comparison direction changes.In reality
Now, by the straight line between detection drawhead and pull rod fixing piece in region, the current direction of pull rod is obtained, and passes through the party
Determine whether to fall off to the difference between direction initialization.Automatic inspection provided by the present invention based on video referring to figure 2.
The flow chart of another specific embodiment of the monitoring method of LVDT pull rod state is surveyed, which includes:
Step S201: the video image monitored in real time to LVDT is obtained;
Step S202: the characteristic point in area to be tested is preset by the video images detection;
Step S203: the motion change of the characteristic point is tracked;
Step S204: by described in the relative displacement determination between drawhead detection zone and pull rod fixing piece region
The moving distance of LVDT pull rod;
Step S205: by the video image, the straight line between LVDT drawhead and pull rod fixing piece is detected, determines and draws
Bar works as front direction;
Step S206: it is compared described when front direction with preset direction, judges whether pull rod falls off.
The process of above-mentioned judgement can be with specifically:
By the left half height and right half height of current frame image drawhead, drawhead in current frame image is determined
The absolute value of left and right two parts displacement;The absolute value is compared with preset threshold;When the absolute value is greater than described pre-
If when threshold value, determining that pull rod has fallen off.
The present embodiment is recognized if being twisted over certain threshold value T by calculating whether drawhead left-right parts twist
For the possibility being broken.
Based on any of the above embodiments, the present embodiment obtain video image that LVDT is monitored in real time it
After can also include: that pretreated process is carried out to video image.The process can specifically include:
Equal proportion scaling is carried out to the video image got, zoom factor is long image or width and display area corresponding sides
Ratio.
The image of each frame is read, and equal proportion scaling is carried out to it, can be carried out in system display area normal
It has been shown that, zoom factor are image length or the wide ratio with display area corresponding sides.If the ratio of long side is greater than the ratio of broadside,
Then take the zoom factor of long side;Conversely, taking the zoom factor of broadside.
After determining zoom factor, gray processing processing is carried out to the image after scaling, and color histogram is utilized to image
Figure carries out enhancing processing.
As a kind of specific embodiment, characteristic point can be specially angle point in the present embodiment.In this way, it is only necessary to selection
Detection target area carry out Corner Detection, do not need to detect entire video frame, greatly reduce answering for detection
Miscellaneous degree, improves detection efficiency.
By taking angle point as an example, referring to figure 3., the automatic detection LVDT pull rod shape to provided by the present invention based on video below
The course of work of another specific embodiment of the monitoring method of state is explained in further detail.
Step S301: the setting of system is carried out.
Since LVDT is flexible for installation, position is changeable.For better deployment system, the angles and positions of camera can basis
Actual scene is changed.Specifically, system can be targetedly set according to the angles and positions of camera, improve system
Flexibility.This system some predominantly detect region and improves the practicability of system by being arranged.
Area to be tested, drawhead detection zone, three, pull rod fixing piece region region are mainly set in the present embodiment,
The setting in the direction of pull rod can also be further set.Area to be tested is area-of-interest, for determining the model of method detection
It encloses, improves the robustness to various noises, reduce extraneous interference, and reduce computation complexity.Drawhead detection zone and
Pull rod fixing piece region starts the target of detection for setting method.According to the target area of the setting, method can track the area
The movement in domain, so that implementation method detects the function of pull rod displacement automatically.
As shown in Fig. 4 LVDT detection system setting schematic diagram, system setting is carried out in order to facilitate staff, this implementation can
Directly by being operated on graphic interface.Its operating process are as follows: first obtain video, then click pause, and according to video
In object's position and direction area to be tested, drawhead detection zone, pull rod fixing piece region and pull rod is set separately
Preset direction is finally clicked and restores to realize real-time detection.These settings can be saved by system, to carry out the tracking of target, position
The detection that the detection of shifting, pull rod fall off.
Step S302: target detection and tracking;
There is the characteristic of more apparent characteristic point, the method that the present embodiment mainly uses feature point tracking based on LVDT
It realizes the tracking of drawhead and pull rod fixing piece, and determines the displacement of pull rod according to its relative distance.Feature point tracking is calculated
Method mainly includes two basic steps: the detection of step S3021 characteristic point and the neighbor search of step S3022 characteristic point.
Step S3021: the detection of characteristic point;
The present embodiment uses characteristic point of the angle point as target area, and the algorithm that angle point grid uses can be used specifically
The Corner Detection function cvGoodFeaturesToTrack provided in OpenCV, function library version are 2.3.1.Function are as follows:
Void cvGoodFeaturesToTrack (const CvArr*image, CvArr*eig_image, CvArr*
Temp_image, CvPoint2D32f*corners, int*corner_count, double quality_level, double
Min_distance, const CvArr*mask=NULL, int blockSize);
Wherein, image is 8- or floating-point 32- bit single image of input;Eig_image temporary floating point 32- bitmap
Picture, size are consistent with input picture;Temp_image is another intermediate images, and format is consistent with size with eig_image;
Corners is output parameter, is the angle point detected;Corner_count output parameter is the angle point number detected;
Quality_level is the multiplication factor of size characteristic value, quality_level=0.1 in the embodiment of the present invention;min_
The restriction factor of the small distance for the angle point that distance is, min_distance=5 of the present invention;Mask, the present invention are implemented
Example mask=NULL, represents whole region;BlockSize is the size for searching for block, blockSize=3 of the present invention.
Step S3022: the neighbor search of characteristic point;
This method uses the method for feature point tracking mainly to realize the tracking of drawhead and pull rod fixing piece, and according to it
Mobile relative distance determines the displacement of pull rod.The tracking of drawhead mainly tracks the displacement of drawhead, pull rod fixing piece
Tracking mainly prevent the shake of camera from causing error and the measure taken, target tracking algorism is the same.
Current main algorithm of target detection has optical flow method, frame difference method and background subtraction.Optical flow method is by will be in image
Each pixel is got up with velocity correlation, utilizes the priori knowledge in video, to estimate the direction of motion of target, the algorithm comparison meter
It is high to calculate complexity, to noise-sensitive caused by multiple light courcess.Frame difference method is subtracted each other by detecting two frames, then carries out two-value to difference result
Change, if variation is little, then it is assumed that background, it is on the contrary then be target, it is disadvantageous in that algorithm is more sensitive to background.Background phase
Subtraction, background subtraction, by present frame and background subtracting, obtain difference image by establishing background model, then, it is big to calculate difference
It is small, the image of movement is considered if diversity ratio is larger, but the algorithm requires a more accurately real-time background modeling
Algorithm.
The embodiment of the present invention is tracked using optical flow method, and specific track algorithm is as follows:
Calculate the position of the characteristic point in previous frame image in drawhead detection zone;
In current frame image using optical flow algorithm around the characteristic point position of the previous frame image in predeterminable area
It scans for;
After the current frame image searches corresponding characteristic point, drawhead detection zone is updated to present frame
Characteristic point region.
The position of the characteristic point in the target area of former frame is calculated, then utilizes optical flow algorithm in the current frame, for
It is scanned near former frame characteristic point position, after present frame searches former frame corresponding characteristic point, by target
The characteristic point region of area update present frame.Used algorithm can be specially the optical flow tracking function provided in OpenCV
CvCalcOpticalFlowPyrLK, function library version are 2.3.1.Function are as follows:
Void cvCalcOpticalFlowPyrLK (const CvArr*prev, const CvArr*curr, CvArr*
Prev_pyr, CvArr*curr_pyr, const CvPoint2D32f*prev_features, CvPoint2D32f*curr_
Features, int count, CvSize win_size, int level, char*status, float*track_error,
CvTerm Criteriacriteria, int flags);
Wherein, prev is the first frame in time t;Curr is the second frame in time t+dt;Prev_pyr is first frame
Pyramid caching;Curr_pyr and prev_pyr are similarly used for the second frame;Prev_features is the point for needing to find light stream
Collection;Curr_feature is the point set of the position comprising newly calculating;Features is count characteristic point in the second width image
Number;Win_size is the search window size of each pyramidal layer, and the embodiment of the present invention takes 10*10;The maximum gold of level
The word tower number of plies, level=10 of the embodiment of the present invention;Status is array.If the light stream of character pair is found, in array
Each element both is set to 1, is otherwise provided as 0;Error is double-precision array, includes original image fragment and transfer point
Between difference.For optional parameters, NULL can be;Criteria is criterion, is specified in each pyramidal layer, finds light for certain point
The termination condition of the iterative process of stream, criteria=new MCvTermCriteria (20,0.3) of the present invention;Flags is it
Its option:
CV_LKFLOW_PYR_A_READY first calculates the pyramid of first frame before calling
CV_LKFLOW_PYR_B_READY first calculates the pyramid of the second frame before calling
CV_LKFLOW_INITIAL_GUESSES, before calling, array B includes the initial coordinate of feature.
Flags=CV_LKFLOW_INITIAL_GUESSES of the present invention.
Step S303: pull rod displacement measurement.It is determined by calculating the relative distance between drawhead and pull rod firmware in real time
The displacement measurement of pull rod.
Pull rod displacement measurement is mainly the relative displacement by the tracking of the tracking and pull rod fixed area of above-mentioned drawhead
To calculate the displacement scale of pull rod.In drawhead detection zone, by calculating characteristic point being averaged in the opposite former frame of present frame
Shift position, update drawhead detection zone are present bit position;Similarly, the tracking of pull rod fixed area is also to be worked as by calculating
The average moving distance of characteristic point and former frame characteristic point obtains present frame pull rod fixed test region, characteristic point inspection in previous frame
It is as shown in Figure 5 to survey result schematic diagram.Then Euclidean distance is utilized, drawhead detection zone and pull rod fixed test region are calculated
Relative displacement can be obtained by the value of LVDT, the inspection of test video finally by measured value and the conversion of actual value memory equal proportion
It is as shown in Figure 6, Figure 7 to survey result, wherein it is the normal situation of pull rod that Fig. 6, which corresponds to testing result, and Fig. 7 corresponds to testing result to draw
The case where bar is broken.
In present frame, the center constraint condition of mark post head detection zone is calculated, the characteristic point recalculated should
In detection target area.
curPoints[i].X>objectRect.Left and curPoints[i].X<objectRect.Right
curPoints[i].Y>objectRect.Top and curPoints[i].Y<objectRect.Bottom
Wherein curPoints is the characteristic point in present frame detection target area, and ObjectRect is that previous frame is determined
Detection target position.
Wherein, a (x1,y1), b (x2,y2) be respectively drawhead detection zone and pull rod fixed area center.d12
It is the relative displacement of two, pull rod detections.
Step S304: pull rod falls off detection.By the direction of setting pull rod starting, then by comparing whether the direction is sent out
Changing determines whether pull rod falls off.When realizing, by detecting the straight line between drawhead and pull rod fixing piece in region,
The current direction of pull rod is obtained, and determines whether to fall off by the difference between the direction and direction initialization.
Drawhead is due to being connected to there are two pull rod, if being broken or falling off occur in pull rod, the left and right of drawhead
Part will disequilibrium twist, therefore can be according to this characteristic, by the way that drawhead is divided into symmetrical two parts, respectively
Tracing detection is carried out, two-part relative displacement is then calculated.Think to occur if when two parts are greater than a certain threshold value T
The possibility of fracture.
dlr=| Object_left-Object_right |
Wherein, dlrThe absolute value of the two-part displacement in left and right of present frame drawhead is represented, Object_left indicates current
The height of the left half of frame drawhead, Object_right indicate the height of the right half part of the drawhead of present frame.
Wherein, State indicates the state whether pull rod falls off, and normal indicates that pull rod is in normal condition, broked table
Show that pull rod has fallen off.
It further, can also include: transmission warning message, to relevant staff after detecting pull rod failure
It is prompted.
The monitoring system of the automatic detection LVDT pull rod state to provided in an embodiment of the present invention based on video carries out below
It introduces, the monitoring system of the automatic detection LVDT pull rod state described below based on video and above-described based on video
The monitoring method of automatic detection LVDT pull rod state can correspond to each other reference.
Fig. 8 is the structure of the monitoring system of the automatic detection LVDT pull rod state provided in an embodiment of the present invention based on video
The monitoring system of block diagram, the automatic detection LVDT pull rod state referring to Fig. 8 based on video may include:
Video image obtains module 100, for obtaining the video image monitored in real time to LVDT;
Characteristic point detection module 200, for presetting the characteristic point in area to be tested by the video images detection;
Tracking module 300 is tracked for the motion change to the characteristic point;
Determining module 400, for true by the relative displacement between drawhead detection zone and pull rod fixing piece region
Determine the moving distance of LVDT pull rod.
As a kind of specific embodiment, the prison of the automatic detection LVDT pull rod state provided by the present invention based on video
Viewing system can further include:
Fall off detection module, for detecting straight between LVDT drawhead and pull rod fixing piece by the video image
Line, determine pull rod works as front direction;It is compared described when front direction with preset direction, judges whether pull rod falls off.
Wherein, the above-mentioned detection module that falls off is specifically used for:
By the left half height and right half height of current frame image drawhead, drawhead in current frame image is determined
The absolute value of left and right two parts displacement;
The absolute value is compared with preset threshold;When the absolute value is greater than the preset threshold, determine to draw
Bar has fallen off.
Based on any of the above embodiments, above-mentioned tracking module can specifically include:
Computing unit, for calculating the position of the characteristic point in previous frame image in drawhead detection zone;
Search unit, for utilizing optical flow algorithm in the characteristic point position week of the previous frame image in current frame image
It encloses in predeterminable area and scans for;
Updating unit, for after the current frame image searches corresponding characteristic point, by drawhead detection zone
It is updated to the characteristic point region of present frame.
To sum up, the monitoring method and system of the automatic detection LVDT pull rod state provided by the present invention based on video are led to
The video image that camera obtains LVDT is crossed, a series of pretreatment is carried out to video image.Then in selecting video image
Detection zone is wanted, and detects the characteristic point in the region.Later, the varying motion direction of the characteristic point on LVDT is detected, thus
Realize the tracking of LVDT pull rod.Subsequently, the position of pull rod is determined by the change in displacement of the reference zone of setting and target area
Shifting amount.The detection finally, pull rod falls off, is completed according to the characteristic point acute variation of the part of target area.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with it is other
The difference of embodiment, same or similar part may refer to each other between each embodiment.For being filled disclosed in embodiment
For setting, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part
Explanation.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Above the monitoring method and system of the automatic detection LVDT pull rod state to provided by the present invention based on video into
It has gone and has been discussed in detail.Used herein a specific example illustrates the principle and implementation of the invention, the above implementation
The explanation of example is merely used to help understand method and its core concept of the invention.It should be pointed out that for the general of the art
, without departing from the principle of the present invention, can be with several improvements and modifications are made to the present invention for logical technical staff, this
A little improvement and modification are also fallen within the protection scope of the claims of the present invention.
Claims (6)
1. a kind of monitoring method of the automatic detection LVDT pull rod state based on video characterized by comprising
Obtain the video image monitored in real time to LVDT;
The characteristic point in area to be tested is preset by the video images detection;
The motion change of the characteristic point is tracked;
By the relative displacement between drawhead detection zone and pull rod fixing piece region, determine the movement of LVDT pull rod away from
From;
Further include:
By the video image, the straight line between LVDT drawhead and pull rod fixing piece is detected, determine pull rod works as front direction;
It is compared described when front direction with preset direction, judges whether pull rod falls off;
Described to be compared described when front direction with preset direction, judging whether pull rod falls off includes:
By the left half height and right half height of current frame image drawhead, the left and right of drawhead in current frame image is determined
The absolute value of two parts displacement;
The absolute value is compared with preset threshold;When the absolute value is greater than the preset threshold, pull rod has been determined
It falls off.
2. the monitoring method of the automatic detection LVDT pull rod state based on video as described in claim 1, which is characterized in that
After the video image that the acquisition monitors LVDT in real time further include:
Equal proportion scaling is carried out to the video image got, zoom factor is image length or wide and display area corresponding sides ratios
Value;
Gray processing processing is carried out to the image after scaling, and enhancing processing is carried out using color histogram to image.
3. the monitoring method of the automatic detection LVDT pull rod state based on video as claimed in claim 2, which is characterized in that institute
Stating characteristic point is angle point.
4. the monitoring method of the automatic detection LVDT pull rod state based on video as claimed in claim 3, which is characterized in that institute
It states that the motion change of the characteristic point track and includes:
Calculate the position of the characteristic point in previous frame image in drawhead detection zone;
It is carried out in predeterminable area around the characteristic point position of the previous frame image in current frame image using optical flow algorithm
Search;
After the current frame image searches corresponding characteristic point, drawhead detection zone is updated to the feature of present frame
Point region.
5. a kind of monitoring system of the automatic detection LVDT pull rod state based on video characterized by comprising
Video image obtains module, for obtaining the video image monitored in real time to LVDT;
Characteristic point detection module, for presetting the characteristic point in area to be tested by the video images detection;
Tracking module is tracked for the motion change to the characteristic point;
Determining module, for determining that LVDT is drawn by the relative displacement between drawhead detection zone and pull rod fixing piece region
The moving distance of bar;Further include:
Fall off detection module, for detecting the straight line between LVDT drawhead and pull rod fixing piece, really by the video image
That determines pull rod works as front direction;It is compared described when front direction with preset direction, judges whether pull rod falls off;
The detection module that falls off is specifically used for:
By the left half height and right half height of current frame image drawhead, the left and right of drawhead in current frame image is determined
The absolute value of two parts displacement;The absolute value is compared with preset threshold;When the absolute value is greater than the default threshold
When value, determine that pull rod has fallen off.
6. the monitoring system of the automatic detection LVDT pull rod state based on video as claimed in claim 5, which is characterized in that institute
Stating tracking module includes:
Computing unit, for calculating the position of the characteristic point in previous frame image in drawhead detection zone;
Search unit, for utilizing optical flow algorithm pre- around the characteristic point position of the previous frame image in current frame image
If being scanned in region;
Updating unit, for after the current frame image searches corresponding characteristic point, drawhead detection zone to be updated
For the characteristic point region of present frame.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610420248.2A CN106022309B (en) | 2016-06-13 | 2016-06-13 | A kind of monitoring method and system of the automatic detection LVDT pull rod state based on video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610420248.2A CN106022309B (en) | 2016-06-13 | 2016-06-13 | A kind of monitoring method and system of the automatic detection LVDT pull rod state based on video |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106022309A CN106022309A (en) | 2016-10-12 |
CN106022309B true CN106022309B (en) | 2019-07-26 |
Family
ID=57087902
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610420248.2A Active CN106022309B (en) | 2016-06-13 | 2016-06-13 | A kind of monitoring method and system of the automatic detection LVDT pull rod state based on video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106022309B (en) |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102316307B (en) * | 2011-08-22 | 2013-09-25 | 安科智慧城市技术(中国)有限公司 | Road traffic video detection method and apparatus thereof |
CN109711304B (en) * | 2013-05-21 | 2022-06-14 | 深圳市腾讯计算机***有限公司 | Face feature point positioning method and device |
-
2016
- 2016-06-13 CN CN201610420248.2A patent/CN106022309B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN106022309A (en) | 2016-10-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101978351B1 (en) | System and Method for Measuring Real Time Water Discharge based on CCTV Image | |
CN105915846B (en) | A kind of the invader monitoring method and system of the multiplexing of list binocular | |
CN106851049B (en) | A kind of scene alteration detection method and device based on video analysis | |
CN105651377B (en) | A kind of non-contact object vibration frequency measurement method based on video data digging | |
EA018349B1 (en) | Method for video analysis | |
Liu et al. | On directional k-coverage analysis of randomly deployed camera sensor networks | |
CN110636281B (en) | Real-time monitoring camera shielding detection method based on background model | |
Kang et al. | The change detection of building models using epochs of terrestrial point clouds | |
CN112233179A (en) | Visual odometer measuring method | |
CN109905670A (en) | A kind of multi-stage platform monitoring system | |
KR20110023468A (en) | Apparatus and method for detecting and tracking object based on adaptive background | |
CN106611165B (en) | A kind of automotive window detection method and device based on correlation filtering and color-match | |
CN104392203A (en) | Video-analysis-based point-like stripe noise detection method | |
CN111767826A (en) | Timing fixed-point scene abnormity detection method | |
KR101813244B1 (en) | Realtime Surface Image Velocimeter using Thermal Images and Orientation Sensors | |
CN112687211B (en) | Method and device for measuring smear of display panel and storage medium | |
CN106022309B (en) | A kind of monitoring method and system of the automatic detection LVDT pull rod state based on video | |
JP4108593B2 (en) | Inundation monitoring device | |
CN112233139A (en) | System and method for detecting motion during 3D data reconstruction | |
CN107341818A (en) | Image analysis algorithm for the test of touch-screen response performance | |
CN114143440A (en) | Flow velocity detection device and method and computer readable storage medium | |
CN101888536A (en) | Anti-rain-interference image acquisition system | |
Yuan et al. | River video flow measurement algorithm with space-time image fusion of object tracking and statistical characteristics | |
CN106652860A (en) | Display screen gray scale detection method and device | |
JP2021047156A (en) | Surveillance system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |