CN107986127A - The stranded detection method of passenger in a kind of elevator - Google Patents
The stranded detection method of passenger in a kind of elevator Download PDFInfo
- Publication number
- CN107986127A CN107986127A CN201711156972.XA CN201711156972A CN107986127A CN 107986127 A CN107986127 A CN 107986127A CN 201711156972 A CN201711156972 A CN 201711156972A CN 107986127 A CN107986127 A CN 107986127A
- Authority
- CN
- China
- Prior art keywords
- image
- lift car
- pixel
- detecting
- passenger
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0018—Devices monitoring the operating condition of the elevator system
- B66B5/0031—Devices monitoring the operating condition of the elevator system for safety reasons
Landscapes
- Indicating And Signalling Devices For Elevators (AREA)
Abstract
The invention discloses a kind of stranded detection method of passenger in elevator, belong to image processing field.This method includes obtaining image sequence；For each image in image sequence, Canny edge detections are carried out to the image in image sequence, obtain the first image；Whether opened according to the first image detection elevator cab door；If detecting, elevator cab door is not switched on, and whether detection timer reaches the scheduled time；If detecting, timer reaches the scheduled time, whether there is passenger in detection lift car；If detecting the presence of passenger, alarm signal is sent；Solves the problem of equipment installation is complicated, and situation about being able to detect that is limited in correlation technique；The location of extra hardware device need not be increased by having reached, it is not required that when consideration lift car stops, it becomes possible to detecting whether that passenger is stranded in real time, improved the real-time of detection and the effect of efficiency.
Description
Technical field
The present embodiments relate to image processing field, the stranded detection method of passenger in more particularly to a kind of elevator.
Background technology
Most common phenomenon when elevator malfunction is Lift out of order, when elevator is abnormal, elevator would generally be immediately
It is out of service, the personal safety of passenger is protected to a certain extent.If but failure occur after rescue not in time or passenger has not
Work as behavior, still result in dangerous generation.
In correlation technique, using the hardware device set in elevator come detect in elevator operating condition and elevator whether
There is passenger, if detecting when elevator stops in non-flat layer state, and have passenger in lift car, then it represents that passenger is stranded.
But the installation of hardware device is complex in practical applications, and it is only able to detect elevator and stops at non-flat bed
When the stranded situation of passenger, the stranded situation of passenger when elevator stops at flat bed can not be detected.
The content of the invention
In order to solve problem of the prior art, an embodiment of the present invention provides a kind of stranded detection side of passenger in elevator
Method.The technical solution is as follows：
First aspect, there is provided the stranded detection method of passenger, this method include in a kind of elevator
Image sequence is obtained, the image in image sequence includes lift car and elevator cab door；
For each image in image sequence, Canny edge detections are carried out to the image in image sequence, obtain first
Image；
Whether opened according to the first image detection elevator cab door；
If detecting, elevator cab door is not switched on, and whether detection timer reaches the scheduled time；
If detecting, timer reaches the scheduled time, whether there is passenger in detection lift car；
If detecting the presence of passenger, alarm signal is sent.
Optionally, whether opened according to the first image detection elevator cab door, including：
According to the first image, detect lift car left side presumptive area and lift car right side presumptive area it is whether same
When there is crack between a door and its frame edge line, crack between a door and its frame edge line is used for the edge for representing elevator cab door；
If detecting, there is crack between a door and its frame side at the same time in the left side presumptive area of lift car and the right side presumptive area of lift car
Edge straight line, it is determined that elevator cab door is opened.
Optionally, detect lift car left side presumptive area and lift car right side presumptive area whether and meanwhile occur
Crack between a door and its frame edge line, including：
Obtain the Hough straight line in the first image；
Whether detection Hough straight line meets predetermined constraints condition, and predetermined constraints condition is：
rlmin<r<rlmax, θlmin<θ<θlmax, rrmin<r<rrmax, θrmin<θ<θrmax,
Wherein, (r, θ) be Hough straight line polar form, (rlmin,θlmin) and (rlmax,θlmax) be used to limit elevator
The left side presumptive area of carriage, (rrmin,θrmin) and (rrmax,θrmax) be used to limit the right side presumptive area of lift car；
If detecting, a Hough straight line meets r at the same timelmin<r<rlmaxAnd θlmin<θ<θlmax, another Hough straight line
Meet r at the same timermin<r<rrmaxAnd θrmin<θ<θrmax, it is determined that the left side presumptive area of lift car and the right side of lift car
There is crack between a door and its frame edge line at the same time in side presumptive area.
Optionally, detect in lift car and whether there is passenger, including：
The image of scheduled time next frame is obtained, and is denoted as the second image；
According to the second image and background image, detect in the second image and whether there is foreground blocks；
If detecting, there are foreground blocks in second graph, it is determined that there are passenger in lift car.
Optionally, according to the second image and background image, detect in the second image and whether there is foreground blocks, including：
Detect whether the pixel in the second image meets predetermined segmentation condition, predetermined segmentation condition is：|rb-ri|>
thbgs, or, | gb-gi|>thbgs, or, | bb-bi|>thbgs,
Wherein, thbgsFor predetermined segmentation threshold, (rb,gb,bb) be background image in a pixel, (ri,gi,bi) be
In second image with pixel (rb,gb,bb) an identical pixel of position；
If detecting, the pixel in the second image meets | rb-ri|>thbgs, or, the pixel satisfaction in the second image |
gb-gi|>thbgs, or, the pixel satisfaction in the second image | bb-bi|>thbgs, it is determined that the pixel in the second image is to treat
Determine foreground pixel point；
Foreground pixel figure undetermined is generated according to foreground pixel point undetermined；
Corrosion dilation operation is carried out to foreground pixel figure undetermined, obtains foreground picture；
Search area is less than the connected domain of predetermined area threshold value in foreground picture；
Whether the quantity of detection connected domain is equal to predetermined quantity；
If detect the in varying numbers in predetermined quantity of connected domain, it is determined that there are foreground blocks in the second image.
Optionally, this method further includes：
Dilation operation is carried out to foreground picture, be expanded denoising foreground picture；
Background image is updated by preset formula, preset formula is：
B (x, y)=I (x, y) ifF1(x, y)=1ifF3(x, y)=0,
Wherein, B (x, y) represents background image, F1(x, y) represents foreground pixel figure undetermined, F3(x, y) represents foreground picture, I
(x, y) represents next two field picture；
Whether the pixel quantity updated in detection background image exceedes the predetermined ratio of total pixel quantity of background image
Example；
If detect predetermined ratio of the pixel quantity not less than total pixel quantity of renewal, it is determined that current background is not
Change, obtain the quantity of connected domain, and re-execute the step of being updated by preset formula to background image；
Detection meet current background do not change and the quantity of connected domain be equal to predetermined quantity image continuous frame number
Whether it is predetermined frame number；
If it is predetermined frame number to detect continuous frame number, present image is determined as the background image after renewal.
Optionally, this method further includes：
If detecting, elevator cab door is opened, and resets timer.
Optionally, this method further includes：
When alarm signal releases, timer is reset.
The beneficial effect that technical solution provided in an embodiment of the present invention is brought is：
By obtaining image sequence, for each image in image sequence, each image in image sequence is carried out
Whether Canny edge detections obtain the first image, opened according to the first image detection elevator cab door, detecting lift car
When door is not switched on, whether detection timer reaches the scheduled time, if detecting, timer reaches the scheduled time, detects elevator car
It whether there is passenger in railway carriage or compartment, if sending alarm signal there are passenger in lift car；Solve equipment in correlation technique to install
The problem of complexity, situation about being able to detect that is limited；Extra hardware device need not be increased by having reached, it is not required that consider electricity
The location of when terraced carriage stops, it becomes possible to detecting whether that passenger is stranded in real time, improved the real-time and efficiency of detection
Effect.
Brief description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for
For those of ordinary skill in the art, without creative efforts, other can also be obtained according to these attached drawings
Attached drawing.
Fig. 1 is the flow chart of the detection method that passenger is stranded in a kind of elevator according to an exemplary embodiment；
Fig. 2 is the flow chart of the detection method that passenger is stranded in a kind of elevator shown according to another exemplary embodiment；
Fig. 3 is the principle schematic of the detection that passenger is stranded in a kind of elevator according to an exemplary embodiment；
Fig. 4 is the principle schematic of the detection that passenger is stranded in a kind of elevator according to an exemplary embodiment.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
Please refer to Fig.1, it illustrates the stream of the stranded detection method of passenger in elevator provided by one embodiment of the present invention
Cheng Tu.The stranded detection method of passenger is suitable for the server at elevator monitoring center in the elevator.As shown in Figure 1, the elevator
The stranded detection method of interior passenger may comprise steps of：
Step 101, image sequence is obtained.
Image in image sequence includes lift car and elevator cab door.
Image sequence is provided in the camera collection in lift car.
Step 102, for each image in image sequence, Canny edge detections are carried out to the image in image sequence,
Obtain the first image.
Step 103, whether opened according to the first image detection elevator cab door.
Since the first image includes lift car and elevator cab door, elevator car can be determined by detecting the first image
Whether railway carriage or compartment door is opened.
If detecting, elevator cab door is not switched on, and performs step 104.If detecting, elevator cab door is opened, and is reset
Timer.
Step 104, if detecting, elevator cab door is not switched on, and whether detection timer reaches the scheduled time.
Optionally, the scheduled time can determine according to being actually needed.
Step 105, if detecting, timer reaches the scheduled time, whether there is passenger in detection lift car.
If detecting in lift car there are passenger, step 106 is performed；If detecting, there is no multiply in lift car
Visitor, then reset timer.
According to whether there is passenger in the image detection lift car of scheduled time next frame.
Step 106, if detecting the presence of passenger, alarm signal is sent.
In conclusion the stranded detection method of passenger in elevator provided in an embodiment of the present invention, by obtaining image sequence, pin
To each image in image sequence, Canny edge detections are carried out to each image in image sequence and obtain the first image, root
Whether opened according to the first image detection elevator cab door, when detecting that elevator cab door is not switched on, whether detection timer reaches
To the scheduled time, if detecting, timer reaches the scheduled time, whether there is passenger in detection lift car, if lift car
Inside there are passenger, then alarm signal is sent；It is limited to solve equipment installation complexity, situation about being able to detect that in correlation technique
Problem；The location of extra hardware device need not be increased by having reached, it is not required that when consideration lift car stops, with regard to energy
It is enough to have detected whether that passenger is stranded in real time, improve the real-time of detection and the effect of efficiency.
Please refer to Fig.2, the stranded detection method of passenger in the elevator provided it illustrates another embodiment of the present invention
Flow chart.The stranded detection method of passenger is suitable for the server at elevator monitoring center in the elevator.As shown in Fig. 2, the electricity
The stranded detection method of passenger may comprise steps of in ladder：
Step 201, image sequence is obtained.
Image in image sequence includes lift car and elevator cab door.
As the image in sequence includes lift car and elevator cab door.
Image sequence is provided in the camera collection in lift car.
Step 202, for each image in image sequence, Canny edge detections are carried out to the image in image sequence,
Obtain the first image.
Step 203, according to the first image, the left side presumptive area of lift car and the right side fate of lift car are detected
Whether domain there is crack between a door and its frame edge line at the same time.
Crack between a door and its frame edge line is used for the edge for representing elevator cab door.
Optionally, elevator cab door is two-door that, when elevator cab door is in opening procedure, left-hand door and right door move opposite to each other
It is dynamic, when elevator cab door is in closing process, left-hand door and the relative movement of right door.
The step can be realized by the following steps：
Step 2031, the Hough straight line in the first image is obtained.
The expression formula of Hough straight line is：Xcos (θ)+ysin (θ)=r, wherein, r is Hough straight line to the distance of origin, θ
The angle between straight line and X-axis for origin excessively and perpendicular to Hough straight line.
Hough parameter space is quantified as to limited section, which becomes summing elements；It is right in the conversion of Hough straight line
Each point in input picture calculates possible straight line parameter, and increases its summing elements variable, when summing elements add up quantity
During more than threshold value, it is believed that the summing elements represent straight line exist with image.
The quantity of Hough straight line in first image is not unique.
Step 2032, whether detection Hough straight line meets predetermined constraints condition.
Predetermined constraints condition is：
rlmin<r<rlmax, θlmin<θ<θlmax, rrmin<r<rrmax, θrmin<θ<θrmax,
Wherein, (r, θ) be Hough straight line polar form, (rlmin,θlmin) and (rlmax,θlmax) be used to limit elevator
The left side presumptive area of carriage, (rrmin,θrmin) and (rrmax,θrmax) be used to limit the right side presumptive area of lift car.
As shown in figure 3, the left side of elevator push button plate 38 is elevator cab door, straight line 30 is closed for elevator cab door
The intersection of Shi Zuomen 32 and right door 31；The polar form of dotted line 33 is (rlmin,θlmin), the polar form of dotted line 34 is
(rlmax,θlmax), the region between dotted line 33 and dotted line 34 is left side presumptive area；The polar form of dotted line 35 is (rrmin,
θrmin), the polar form of dotted line 36 is (rrmax,θrmax), the region between dotted line 35 and dotted line 36 is right side presumptive area.
If detecting, a Hough straight line meets r at the same timelmin<r<rlmaxAnd θlmin<θ<θlmax, another Hough straight line
Meet r at the same timermin<r<rrmaxAnd θrmin<θ<θrmax, it is determined that the left side presumptive area of lift car and the right side of lift car
There is crack between a door and its frame edge line at the same time in side presumptive area.It will meet r at the same timelmin<r<rlmaxAnd θlmin<θ<θlmaxA Hough
Straight line regards the crack between a door and its frame edge line of left-hand door as, will meet r at the same timermin<r<rrmaxAnd θrmin<θ<θrmaxAnother Hough it is straight
Line regards the crack between a door and its frame edge line of right door as.
As shown in figure 4, a Hough straight line 42 occurs in the presumptive area of left side, Hough straight line 42 meets r at the same timelmin<r
<rlmaxAnd θlmin<θ<θlmax, and another Hough straight line 41 occurs in the presumptive area of right side, Hough straight line 41 meets at the same time
rrmin<r<rrmaxAnd θrmin<θ<θrmax, at this time elevator cab door open.
If detecting, the left side presumptive area of lift car does not occur crack between a door and its frame edge line, and/or, the right side of lift car
Presumptive area does not occur crack between a door and its frame edge line, it is determined that elevator cab door is not switched on, and performs step 205.
Step 204, if detecting, the left side presumptive area of lift car and the right side presumptive area of lift car go out at the same time
Existing crack between a door and its frame edge line, it is determined that elevator cab door is opened.
When detecting that elevator cab door is opened, timer is reset, and hold again for next two field picture of current time
Row step 203.
When detecting that elevator cab door is opened, illustrate that elevator cab door is in opening procedure, closed alternatively, being in
Journey.
Step 205, when detecting that elevator cab door is not switched on, whether detection timer reaches the scheduled time.
If detecting, timer does not reach the scheduled time, continues to detect whether elevator cab door is beaten for follow-up image
Open, namely next two field picture for current time, step 203 is re-executed to 205.
If detecting, timer reaches the scheduled time, performs step 206.
When detecting that timer reaches the scheduled time, there are two kinds of situations：First, without passenger in elevator, elevator is in etc.
Treat operating status；2nd, there is passenger in elevator, elevator cab door can not be opened；Therefore, it is necessary to when timer reaches the scheduled time
It whether there is passenger in detection lift car.
Step 206, when detecting that timer reaches the scheduled time, it whether there is passenger in detection lift car.
If detecting in lift car there are passenger, step 207 is performed.
If detecting in lift car and passenger being not present, timer is reset, and for next two field picture of current time
Step 203 is performed to 206.
For the image of scheduled time next frame, it whether there is passenger in detection lift car, if according under the scheduled time
The image detection of one frame is to there are passenger, then illustrating that the stranded situation of passenger occurs for elevator in lift car.
Wherein, detecting in lift car can be realized with the presence or absence of passenger by the following steps：
Step 2061, the image of scheduled time next frame is obtained, and is denoted as the second image.
Optionally, the second image is without Canny edge detections.
Step 2062, according to the second image and background image, detect in the second image and whether there is foreground blocks.
Optionally, background image obtains in advance.
Step 2063, whether the pixel detected in the second image meets predetermined segmentation condition.
Predetermined segmentation condition is：|rb-ri|>thbgsOr | gb-gi|>thbgsOr | bb-bi|>thbgs,
Wherein, thbgsFor predetermined segmentation threshold, (rb,gb,bb) be background image in a pixel, (ri,gi,bi) be
In second image with pixel (rb,gb,bb) an identical pixel of position.
For each pixel in the second image, whether detection pixel meets predetermined segmentation condition.
If detecting, the pixel in the second image meets | rb-ri|>thbgs, or, the pixel satisfaction in the second image |
gb-gi|>thbgs, or, the pixel satisfaction in the second image | bb-bi|>thbgs, it is determined that the pixel in the second image is to treat
Determine foreground pixel point.
Optionally, thbgsIt is pre-set.Such as thbgsTake 20.Step 2063, generated according to foreground pixel point undetermined
Foreground pixel figure undetermined.
Whole foreground pixel points undetermined can represent that foreground pixel figure undetermined is a two-value with foreground pixel figure undetermined
Figure, is denoted as F1(x,y)。
Step 2064, corrosion dilation operation is carried out to foreground pixel figure undetermined, obtains foreground picture.
In general, obtained foreground pixel figure F undetermined1(x, y) has more noise, to foreground pixel figure F undetermined1(x, y) is done
With predefined size (such as：Size is 5 × 5) rectangle be structural element corrosion dilation operation, obtain the prospect after preliminary denoising
Scheme F2(x,y)。
Note etching operation is erode (), and expansive working is dilate (), then F2(x, y)=erode (dilate (erode
(F1)))。
Step 2065, connected domain of the search area less than predetermined area threshold value in foreground picture.
Optionally, predetermined area threshold value is determined according to actual image size.
Count the quantity that the area searched is less than the connected domain of predetermined area threshold value.
Step 2066, whether the quantity for detecting connected domain is equal to predetermined quantity.
Optionally, predetermined quantity 1.
If detect the in varying numbers in predetermined quantity of connected domain, it is determined that there are foreground blocks in the second image.If detection
Into second graph, there are foreground blocks, it is determined that there are passenger in lift car.
Step 207, when detecting the presence of passenger, alarm signal is sent.
Step 208, when alarm signal releases, timer is reset.
After alarm signal releasing, reset timer and re-execute step 201 to step 207.
In conclusion the stranded detection method of passenger in elevator provided in an embodiment of the present invention, by obtaining image sequence, pin
To each image in image sequence, Canny edge detections are carried out to each image in image sequence and obtain the first image, root
Whether opened according to the first image detection elevator cab door, when detecting that elevator cab door is not switched on, whether detection timer reaches
To the scheduled time, if detecting, timer reaches the scheduled time, whether there is passenger in detection lift car, if lift car
Inside there are passenger, then alarm signal is sent；It is limited to solve equipment installation complexity, situation about being able to detect that in correlation technique
Problem；The location of extra hardware device need not be increased by having reached, it is not required that when consideration lift car stops, with regard to energy
It is enough to have detected whether that passenger is stranded in real time, improve the real-time of detection and the effect of efficiency.
It should be noted that since the scene of elevator operation may change, in order to judge the second image exactly
In whether there is foreground blocks, background image can also be updated, this method further include to background image renewal method, step
It is rapid as follows：
Step 2067, dilation operation is carried out to foreground picture, be expanded denoising foreground picture.
Note extension denoising foreground picture is F3(x, y), F3(x, y)=dilate (F2)。
By expansive working, the background and current prospect for making renewal have certain distance.
Step 2068, background image is updated by preset formula.
Preset formula is：B (x, y)=I (x, y) ifF1(x, y)=1andF3(x, y)=0,
Wherein, B (x, y) represents background image, F1(x, y) represents foreground pixel figure undetermined, F3(x, y) represents foreground picture, I
(x, y) represents next two field picture.
When initial, I (x, y) is next two field picture of the image of scheduled time next frame.
Step 2069, the total the pixel quantity whether pixel quantity updated in background image exceedes background image is detected
Predetermined ratio.
Optionally, predetermined ratio 0.2%.
If detecting, the pixel quantity of renewal exceedes the predetermined ratio of total pixel quantity, illustrates current background
Change, remember fludFor 1.
If detect predetermined ratio of the pixel quantity not less than total pixel quantity of renewal, it is determined that current background is not
Change, obtain the quantity of connected domain, and re-execute the step of being updated by preset formula to background image.
When detect the pixel quantity of renewal not less than total pixel quantity predetermined ratio when, remember fludFor 0, and obtain
Area in the foreground picture counted in step 2065 is taken to be less than the quantity of the connected domain of predetermined area threshold value, the quantity of connected domain is denoted as
unmfgblock。
Step 2068 is repeated to 2069.
Step 2070, detection meets that current background does not change and the quantity of connected domain is equal to the image of predetermined quantity
Whether continuous frame number is predetermined frame number.
After step 2068 has often performed once to 2069, a step 2070 is performed, namely detection meets flud=0 and
numfgbiockWhether the continuous frame number of=0 image is predetermined frame number.
If continuous frame number is predetermined frame number, it is believed that it is at this time sky in lift car, performs background and update operation completely, namely
Perform step 2071.
Step 2071, when it is predetermined frame number to detect continuous frame number, present image is determined as the Background after renewal
Picture.
More new formula is：B (x, y)=I (x, y).
It should be noted that step 2066 can perform at the same time with step 2067 to 2071.
It should be noted that：The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
One of ordinary skill in the art will appreciate that hardware can be passed through by realizing all or part of step of above-described embodiment
To complete, relevant hardware can also be instructed to complete by program, the program can be stored in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only storage, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent replacement, improvement and so on, should all be included in the protection scope of the present invention.
Claims (8)
- A kind of 1. stranded detection method of passenger in elevator, it is characterised in that the described method includesImage sequence is obtained, the image in described image sequence includes lift car and elevator cab door；For each image in described image sequence, Canny edge detections are carried out to the image in described image sequence, are obtained First image；Detect whether the elevator cab door is opened according to described first image；If detecting, the elevator cab door is not switched on, and whether detection timer reaches the scheduled time；If detecting, the timer reaches the scheduled time, detects in the lift car and whether there is passenger；If detecting the presence of the passenger, alarm signal is sent.
- 2. according to the method described in claim 1, it is characterized in that, described detect the lift car according to described first image Whether door is opened, including：According to described first image, the left side presumptive area of the lift car and the right side fate of the lift car are detected Whether domain there is crack between a door and its frame edge line at the same time, and the crack between a door and its frame edge line is used for the edge for representing elevator cab door；If detecting, there is institute at the same time in the left side presumptive area of the lift car and the right side presumptive area of the lift car State crack between a door and its frame edge line, it is determined that the elevator cab door is opened.
- 3. according to the method described in claim 2, it is characterized in that, the left side presumptive area of the detection lift car and Whether the right side presumptive area of the lift car there is crack between a door and its frame edge line at the same time, including：Obtain the Hough straight line in described first image；Detect whether the Hough straight line meets predetermined constraints condition, the predetermined constraints condition is：rlmin<r<rlmax, θlmin<θ<θlmax, rrmin<r<rrmax, θrmin<θ<θrmax,Wherein, (r, θ) be the Hough straight line polar form, (rlmin,θlmin) and (rlmax,θlmax) be used to limit the electricity The left side presumptive area of terraced carriage, (rrmin,θrmin) and (rrmax,θrmax) be used to limit the right side fate of the lift car Domain；If detecting, a Hough straight line meets r at the same timelmin<r<rlmaxAnd θlmin<θ<θlmax, another Hough straight line be full at the same time Sufficient rrmin<r<rrmaxAnd θrmin<θ<θrmax, it is determined that the left side presumptive area of the lift car and the lift car There is crack between a door and its frame edge line at the same time in right side presumptive area.
- 4. according to the method described in claim 1, it is characterized in that, whether there is passenger in the detection lift car, Including：The image of the scheduled time next frame is obtained, and is denoted as the second image；According to second image and background image, detect in second image and whether there is foreground blocks；If detecting, there are the foreground blocks in the second graph, it is determined that there are the passenger in the lift car.
- It is 5. according to the method described in claim 4, it is characterized in that, described according to second image and background image, detection It whether there is foreground blocks in second image, including：Detect whether the pixel in second image meets predetermined segmentation condition, the predetermined segmentation condition is：|rb-ri|> thbgs, or, | gb-gi|>thbgs, or, | bb-bi|>thbgs,Wherein, thbgsFor predetermined segmentation threshold, (rb,gb,bb) be the background image in a pixel, (ri,gi,bi) be In second image with the pixel (rb,gb,bb) an identical pixel of position；If detecting, the pixel in second image meets | rb-ri|>thbgs, or, pixel in second image expires Foot | gb-gi|>thbgs, or, the pixel satisfaction in second image | bb-bi|>thbgs, it is determined that in second image Pixel be foreground pixel point undetermined；The foreground pixel figure undetermined is generated according to the foreground pixel point undetermined；Corrosion dilation operation is carried out to the foreground pixel figure undetermined, obtains foreground picture；Search area is less than the connected domain of predetermined area threshold value in the foreground picture；Whether the quantity for detecting the connected domain is equal to predetermined quantity；If detect the in varying numbers in the predetermined quantity of the connected domain, it is determined that there are before described in second image Scape block.
- 6. according to the method described in claim 5, it is characterized in that, the method further includes：Dilation operation is carried out to the foreground picture, be expanded denoising foreground picture；The background image is updated by preset formula, the preset formula is：B (x, y)=I (x, y) ifF1(x, y)=1ifF3(x, y)=0,Wherein, B (x, y) represents background image, F1(x, y) represents foreground pixel figure undetermined, F3(x, y) represents foreground picture, I (x, y) Represent next two field picture；Detect the pixel quantity that is updated in the background image whether exceed the background image total pixel quantity it is pre- Certainty ratio；If detect predetermined ratio of the pixel quantity not less than total pixel quantity of the renewal, it is determined that current background is not Change, obtain the quantity of the connected domain, and re-execute and described the background image is updated by preset formula The step of；Detection meets that current background does not change and the quantity of the connected domain is continuous equal to the image of the predetermined quantity Whether frame number is predetermined frame number；If detecting, the continuous frame number is predetermined frame number, and present image is determined as the background image after renewal.
- 7. method according to any one of claims 1 to 5, it is characterised in that the method further includes：If detecting, the elevator cab door is opened, and resets the timer.
- 8. method according to any one of claims 1 to 5, its spy is being that the method further includes：When the alarm signal releases, the timer is reset.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711156972.XA CN107986127A (en) | 2017-11-20 | 2017-11-20 | The stranded detection method of passenger in a kind of elevator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711156972.XA CN107986127A (en) | 2017-11-20 | 2017-11-20 | The stranded detection method of passenger in a kind of elevator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107986127A true CN107986127A (en) | 2018-05-04 |
Family
ID=62031042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711156972.XA Pending CN107986127A (en) | 2017-11-20 | 2017-11-20 | The stranded detection method of passenger in a kind of elevator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107986127A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110697529A (en) * | 2019-09-20 | 2020-01-17 | 日立楼宇技术（广州）有限公司 | Method and device for detecting trapping of elevator and computer equipment |
| CN113233273A (en) * | 2020-05-21 | 2021-08-10 | 山东中兴合智通信新技术有限公司 | Elevator fault monitoring method and device, storage medium, electronic equipment and elevator |
| US11535491B2 (en) | 2019-03-28 | 2022-12-27 | Otis Elevator Company | Verification of trapped passenger alarm |
| CN115724312A (en) * | 2022-05-31 | 2023-03-03 | 海纳云物联科技有限公司 | Method and device for detecting people trapping of elevator car |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09278328A (en) * | 1996-04-08 | 1997-10-28 | Hitachi Building Syst Co Ltd | Elevator door monitor |
| JP2001122542A (en) * | 1999-10-25 | 2001-05-08 | Tietech Co Ltd | Image pick-up method in elevator car |
| CN1759613A (en) * | 2003-03-20 | 2006-04-12 | 因温特奥股份公司 | Monitoring a lift area by means of a 3d sensor |
| CN1919711A (en) * | 2006-09-20 | 2007-02-28 | 浙江工业大学 | Elevator inner violence-proof apparatus based on image and speech recognition technique |
| DE202011051664U1 (en) * | 2011-10-18 | 2012-01-13 | Slc Sautter Lift Components Gmbh & Co. Kg | Braking device for an elevator |
| CN102737370A (en) * | 2011-04-02 | 2012-10-17 | 株式会社理光 | Method and device for detecting image foreground |
| CN102902971A (en) * | 2012-08-31 | 2013-01-30 | 电子科技大学 | Method and system for conducting statistics on elevator visitor flow based on intelligent visual perception |
| CN103130063A (en) * | 2011-11-29 | 2013-06-05 | 深圳市一兆科技发展有限公司 | Method and system for emergency security and protection monitoring |
| CN103771207A (en) * | 2014-01-09 | 2014-05-07 | 深圳市汇川技术股份有限公司 | Elevator car passenger detection system and method |
| CN103986906A (en) * | 2014-05-08 | 2014-08-13 | 杭州同尊信息技术有限公司 | Door opening and closing detection method based on monitoring videos |
| CN103996203A (en) * | 2014-06-13 | 2014-08-20 | 北京锐安科技有限公司 | Method and device for detecting whether face in image is sheltered |
| CN104499864A (en) * | 2014-12-11 | 2015-04-08 | 南华大学 | Anti-collision anti-jamming bus safety door system |
| CN104573697A (en) * | 2014-12-31 | 2015-04-29 | 西安丰树电子科技发展有限公司 | Construction hoist lift car people counting method based on multi-information fusion |
| CN106144861A (en) * | 2015-04-03 | 2016-11-23 | 奥的斯电梯公司 | Passenger based on the depth transducer sensing controlled for passenger traffic |
| CN106204537A (en) * | 2016-06-24 | 2016-12-07 | 浙江大学 | Live pig image partition method under a kind of complex environment |
| CN106986248A (en) * | 2017-05-23 | 2017-07-28 | 四川长虹电器股份有限公司 | Elevator switch door detection method based on photographed images |
-
2017
- 2017-11-20 CN CN201711156972.XA patent/CN107986127A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09278328A (en) * | 1996-04-08 | 1997-10-28 | Hitachi Building Syst Co Ltd | Elevator door monitor |
| JP2001122542A (en) * | 1999-10-25 | 2001-05-08 | Tietech Co Ltd | Image pick-up method in elevator car |
| CN1759613A (en) * | 2003-03-20 | 2006-04-12 | 因温特奥股份公司 | Monitoring a lift area by means of a 3d sensor |
| CN1919711A (en) * | 2006-09-20 | 2007-02-28 | 浙江工业大学 | Elevator inner violence-proof apparatus based on image and speech recognition technique |
| CN102737370A (en) * | 2011-04-02 | 2012-10-17 | 株式会社理光 | Method and device for detecting image foreground |
| DE202011051664U1 (en) * | 2011-10-18 | 2012-01-13 | Slc Sautter Lift Components Gmbh & Co. Kg | Braking device for an elevator |
| CN103130063A (en) * | 2011-11-29 | 2013-06-05 | 深圳市一兆科技发展有限公司 | Method and system for emergency security and protection monitoring |
| CN102902971A (en) * | 2012-08-31 | 2013-01-30 | 电子科技大学 | Method and system for conducting statistics on elevator visitor flow based on intelligent visual perception |
| CN103771207A (en) * | 2014-01-09 | 2014-05-07 | 深圳市汇川技术股份有限公司 | Elevator car passenger detection system and method |
| CN103986906A (en) * | 2014-05-08 | 2014-08-13 | 杭州同尊信息技术有限公司 | Door opening and closing detection method based on monitoring videos |
| CN103996203A (en) * | 2014-06-13 | 2014-08-20 | 北京锐安科技有限公司 | Method and device for detecting whether face in image is sheltered |
| CN104499864A (en) * | 2014-12-11 | 2015-04-08 | 南华大学 | Anti-collision anti-jamming bus safety door system |
| CN104573697A (en) * | 2014-12-31 | 2015-04-29 | 西安丰树电子科技发展有限公司 | Construction hoist lift car people counting method based on multi-information fusion |
| CN106144861A (en) * | 2015-04-03 | 2016-11-23 | 奥的斯电梯公司 | Passenger based on the depth transducer sensing controlled for passenger traffic |
| CN106204537A (en) * | 2016-06-24 | 2016-12-07 | 浙江大学 | Live pig image partition method under a kind of complex environment |
| CN106986248A (en) * | 2017-05-23 | 2017-07-28 | 四川长虹电器股份有限公司 | Elevator switch door detection method based on photographed images |
Non-Patent Citations (3)
| Title |
|---|
| 徐贵力: "《光电检测技术与系统设计》", 31 August 2013, 北京：国防工业出版社 * |
| 赵坚勇: "《应用电视技术》", 31 December 2013, 西安：西安电子科技大学出版社 * |
| 雷帮军: "《视频目标跟踪系统分步详解》", 31 December 2015, 北京：国防工业出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11535491B2 (en) | 2019-03-28 | 2022-12-27 | Otis Elevator Company | Verification of trapped passenger alarm |
| CN110697529A (en) * | 2019-09-20 | 2020-01-17 | 日立楼宇技术（广州）有限公司 | Method and device for detecting trapping of elevator and computer equipment |
| CN113233273A (en) * | 2020-05-21 | 2021-08-10 | 山东中兴合智通信新技术有限公司 | Elevator fault monitoring method and device, storage medium, electronic equipment and elevator |
| CN115724312A (en) * | 2022-05-31 | 2023-03-03 | 海纳云物联科技有限公司 | Method and device for detecting people trapping of elevator car |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107986127A (en) | The stranded detection method of passenger in a kind of elevator | |
| WO2021036636A1 (en) | Vibration detection method and apparatus for lifting device, server and storage medium | |
| CN107298354B (en) | Elevator door-motor monitoring method, device, system and computer-readable medium, equipment | |
| CN103747213B (en) | A kind of real-time defogging method of the Traffic Surveillance Video based on moving target | |
| WO2017210894A1 (en) | Fault monitoring method for electric arc furnace based on operating video information | |
| CN105678295A (en) | Method for real-time monitoring gas heating furnace flame on the basis of ROI average image analysis | |
| WO2020206407A3 (en) | Segmentation and prediction of low-level temporal plume patterns | |
| Peng et al. | Detection and analysis of large‐scale WT blade surface cracks based on UAV‐taken images | |
| KR20170075267A (en) | System for prognosticating failure of elevator | |
| CN105809133A (en) | Fingerprint feature information updating method and device | |
| CN110887173A (en) | Method and device for remotely controlling central air-conditioning system | |
| CN103870824A (en) | Method and device for capturing face in face detecting and tracking process | |
| KR20200017594A (en) | Method for Recognizing and Tracking Large-scale Object using Deep learning and Multi-Agent | |
| CN114037087B (en) | Model training method and device, depth prediction method and device, equipment and medium | |
| Misbha | Detection of attacks using attention-based conv-lstm and bi-lstm in industrial internet of things | |
| Rao et al. | Dynamic traffic system based on real time detection of traffic congestion | |
| CN107729811B (en) | Night flame detection method based on scene modeling | |
| CN105279821B (en) | A kind of pedestrian counting method based on angle half-tone information | |
| CN115880629A (en) | Loading and unloading vehicle crane pipe state identification method and system | |
| Kim et al. | An intelligent collaboration framework between edge camera and video analysis system | |
| CN111438460B (en) | Vision-based thick plate T-shaped joint welding seam forming characteristic online measurement method | |
| KR20230030258A (en) | Semi-supervised learning-based defect detection method using small amount of label data | |
| CN113673335A (en) | Dangerous boundary-crossing behavior recognition algorithm in electric power field operation | |
| TWI526988B (en) | Motion variation based adaptive local area iterative updating method for background modeling | |
| TWI790957B (en) | A high-speed data association method for multi-object tracking |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180504 |
|
| RJ01 | Rejection of invention patent application after publication |