CN116040432A - Elevator image processing method, system and storage medium - Google Patents
Elevator image processing method, system and storage medium Download PDFInfo
- Publication number
- CN116040432A CN116040432A CN202310210997.2A CN202310210997A CN116040432A CN 116040432 A CN116040432 A CN 116040432A CN 202310210997 A CN202310210997 A CN 202310210997A CN 116040432 A CN116040432 A CN 116040432A
- Authority
- CN
- China
- Prior art keywords
- image
- elevator door
- area
- difference
- obstacle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title abstract description 10
- 238000012544 monitoring process Methods 0.000 claims abstract description 85
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims description 17
- 238000003384 imaging method Methods 0.000 claims description 9
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 238000010191 image analysis Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
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
- B66B5/0012—Devices monitoring the users of the elevator system
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B1/00—Control systems of elevators in general
- B66B1/34—Details, e.g. call counting devices, data transmission from car to control system, devices giving information to the control system
- B66B1/3415—Control system configuration and the data transmission or communication within the control system
- B66B1/3423—Control system configuration, i.e. lay-out
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B13/00—Doors, gates, or other apparatus controlling access to, or exit from, cages or lift well landings
- B66B13/24—Safety devices in passenger lifts, not otherwise provided for, for preventing trapping of passengers
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B50/00—Energy efficient technologies in elevators, escalators and moving walkways, e.g. energy saving or recuperation technologies
Abstract
The invention belongs to the field of image data processing, and particularly relates to a processing method, a system and a storage medium of an elevator image. The method comprises the following steps: step S1: acquiring a maximum monitoring area of an elevator door, and establishing a coordinate system of the maximum monitoring area; step S2: correcting an image of the monitoring area based on the first coordinate, comparing the second image with the first image to obtain a first difference image, and obtaining the movement direction, the movement speed and the background image of the elevator door based on the first difference image; step S3: comparing the second image with the background image to obtain a second difference image, and judging whether an obstacle exists in a second target area corresponding to the second difference image; step S4: predicting a minimum distance from the elevator door during the obstacle leaving the second target area when it is determined that the obstacle is present; step S5: the motion of the elevator door is determined based on the distance of the elevator door from the obstacle. The invention improves the recognition precision of the tiny objects and the operation efficiency of the elevator.
Description
Technical Field
The invention belongs to the field of image data processing, and particularly relates to a processing method, a system and a storage medium of an elevator image.
Background
In our daily life, an elevator is an indispensable transportation means for going upstairs and downstairs, and in the process of closing an elevator door, the elevator mostly adopts infrared detection to detect whether foreign matters are clamped, but tiny objects are clamped and cannot be identified, for example: although there are people's hair or knapsack area etc. discerns the object through the mode of image analysis, because the elevator is the shake that probably causes the camera unit to move, makes the image that shoots correspond the coordinate shift, and the error is great when the image contrast, for example: JP4664394B2, which, when an image of an entrance is acquired using an imaging device such as a camera, can reliably grasp the operation of an elevator door by image processing, does not determine the closing elevator door as a foreign object; there is also japanese patent JP2023024069a, which extracts edge information from an image taken by a camera mounted on a car; and an edge extracted by the edge extraction unit, moving an object from the photographed image based on an edge variation obtained by comparing images continuously obtained as photographed images, both of which do not perform image coordinate calibration, and in the prior art, since a background near each floor elevator door is different or the same floor background replacement is not able to accurately obtain accurate obstacle detection information by comparison with the background image due to the inability to timely obtain the complete background image, and the shortest distance of a predicted obstacle from a monitoring area is not calculated according to the position and movement speed of the obstacle and the position and movement speed of the elevator door, but is directly opened, and once a malicious use of a person is occurred, a tiny object moves back and forth at the elevator door opening to cause the elevator door to be continuously opened, not only reducing the operation efficiency of the elevator but also reducing the service life of the elevator.
Disclosure of Invention
In order to better solve the problems, the invention provides a processing method of elevator images, which comprises the following steps:
step S1: in an initial state, continuously acquiring an image of an elevator door, acquiring a maximum monitoring area of the elevator door, establishing a coordinate system of the maximum monitoring area, and acquiring a first coordinate of an intersection point between the maximum monitoring area and a longitudinal bisector of the maximum monitoring area;
step S2: correcting the acquired image of the monitoring area based on the first coordinate, acquiring a first real-time position of the elevator door by calculating a column pixel value of the monitoring area, simultaneously comparing a second image acquired in real time with a first image acquired last time to acquire a first difference image, and acquiring a moving direction, a moving speed and a background image of the elevator door based on the first difference image;
step S3: comparing the second image acquired in real time with the background image to acquire a second difference image, acquiring a second target area by calculating a column pixel value of the second image, and judging whether an obstacle exists in the second target area based on the second difference image;
Step S4: calculating the running speed and the position of the obstacle in real time when the obstacle exists in the second target area corresponding to the second difference image, predicting the minimum distance from the elevator door in the process that the obstacle leaves the second target area according to the position and the moving speed of the obstacle and the first real-time position and the moving speed of the elevator door, and adjusting the image acquisition mode of the target area according to the distance between the obstacle and the elevator door;
step S5: and determining the action of the elevator door according to the distance between the elevator door and the obstacle.
In the step S1, a column pixel value of the image is calculated in real time according to an image of the continuously collected elevator door, in all the images, an image with the most columns having column pixel values larger than a first set value corresponds to a state after the elevator door is fully opened, an opening and closing area of the elevator door is a maximum monitoring area, a row pixel value and a column pixel value of the image are calculated, a row pixel direction of the lowermost end of the image, which satisfies the row pixel value larger than a second set value, is taken as an x-axis, a column pixel direction of the leftmost end of the image, which satisfies the column pixel value larger than the first set value, is taken as a y-axis, a crossing point of the x-axis and the y-axis is taken as a coordinate origin, coordinates of four endpoints of the maximum monitoring area are also obtained, a first coordinate of the crossing point of the maximum monitoring area on a longitudinal bisector of the maximum monitoring area is calculated based on the coordinates of the four endpoints, and a door seam of the elevator door corresponding to the longitudinal bisector of the maximum monitoring area is calculated.
As a more preferable technical solution, in step S2, a second coordinate of an intersection point of the longitudinal bisector of the monitoring area and the monitoring area is calculated based on the acquired image of the monitoring area, the second coordinate is compared with the first coordinate, a difference vector between the first coordinate and the second coordinate is obtained, when an absolute value of the difference vector is smaller than a first threshold value, the image of the monitoring area is corrected based on the difference vector, and when the absolute value of the difference vector is larger than the first threshold value, the image of the monitoring area is corrected by adjusting an imaging angle of an imaging unit.
As a more preferable technical solution, step S2 further includes the following steps:
step S21: calculating a column pixel value of the first image, wherein a region with the column pixel value larger than a first set value is a first target region, calculating a column pixel value of the second image, wherein a region with the column pixel value larger than the first set value in the second image is a second target region, and comparing the first target region with the second target region to obtain a first difference image;
step S22: the direction of a difference area, of which the column pixels are larger than the first set value, in the first difference image relative to the first target area is the movement direction of the elevator door, when the difference area is arranged on two sides of the first target area, the movement direction of the elevator door is open, and when the difference area is arranged in the middle of the first target area, the movement direction of the elevator door is closed;
Step S23: when the movement direction of the elevator door is open, the position of the difference area close to the two sides is a first real-time position of the elevator door, and when the movement direction of the elevator door is closed, the position of the difference area close to the inner side is a first real-time position of the elevator door;
step S24: when all the column pixel values are smaller than the first set value, the elevator door is in a closed state, when the first target area is larger than or equal to the maximum monitoring area, the elevator door is all opened, and in the process of the elevator door from closing to fully opening, the acquired difference area images in all the first difference images are spliced to acquire a background image, wherein the expression is as follows:
wherein ,
for background image +.>
And i is a positive integer from 1 to N for the difference area in the first difference image of the second image acquired for the ith time and the first image of the previous time, wherein N is the total amount of the second images acquired from the closing to the full opening of the elevator door.
As a more preferable technical solution, in the step S3, when the motion direction of the elevator door is closed, a second target area with a column pixel value greater than a first set value in the second image acquired in real time is calculated, the second target area is compared with the background image to obtain the second difference image, a pixel value of each pixel in the second difference image is calculated, and when the pixel values of n adjacent pixels are smaller than a third preset value, an obstacle exists in the second target area, otherwise, no obstacle exists, wherein n is greater than or equal to 10.
As a more preferable solution, when it is determined that the obstacle exists, the step S4 includes the steps of:
step S41: calculating pixel values of the second difference image corresponding to each pixel in a second target area, wherein an area formed by adjacent pixels with the pixel values smaller than a second preset value is an outline of an obstacle, and the position of the area is the coordinate position of the obstacle;
step S42: comparing the acquired second difference image with the acquired second difference image to acquire the movement displacement and movement direction of the obstacle, and calculating the movement speed of the obstacle according to the time difference between the acquired second difference image and the acquired second difference image;
step S43: and calculating a first difference of a real-time shortest distance between the obstacle and the elevator door based on the coordinate position of the obstacle and the first real-time position of the elevator door acquired in the step S2, and increasing the shooting focal length of the shooting unit and increasing the shooting frequency of the shooting unit when the first difference is smaller than the first distance.
As a more preferable technical solution, in step S5, when the first gap is smaller than the first distance, predicting a minimum distance from the elevator door during the process that the obstacle leaves the second target area according to the position and the movement speed of the obstacle and the first real-time position and the movement speed of the elevator door, when the minimum distance is larger than the second distance, reducing the operation speed of the elevator door when the minimum distance is smaller than the second distance, and when the first gap is smaller than the second distance, the elevator door pauses for a predetermined time, and when the elevator door pauses for a predetermined time, the obstacle still exists, opening the elevator door and giving an alarm; after the elevator door is paused for a predetermined time, the obstacle disappears, and the elevator door is closed, wherein the first distance is greater than the second distance.
The invention also provides a processing system of the elevator image, which is used for realizing the processing method of the elevator image, and comprises the following steps:
the camera shooting unit is used for continuously collecting images of the elevator door;
the image analysis unit is configured to: acquiring a maximum monitoring area of an elevator door, establishing a coordinate system of the maximum monitoring area, and acquiring a first coordinate of an intersection point between the maximum monitoring area and a longitudinal bisector of the maximum monitoring area; meanwhile, comparing a second image acquired in real time with a first image acquired last time to acquire a first difference image, and acquiring the movement direction, movement speed and background image of the elevator door based on the first difference image; comparing the second image acquired in real time with the background image to acquire a second difference image, acquiring a second target area by calculating column pixel values of the second image, and judging whether an obstacle exists in the second target area based on the second difference image; when determining that an obstacle exists, calculating the running state and the position of the obstacle in real time, and predicting the minimum distance from the elevator door in the process that the obstacle leaves the second target area according to the position and the movement speed of the obstacle and the first real-time position and the movement speed of the elevator door;
The image capturing unit is also used for adjusting the image acquisition mode of the target area according to the first distance.
The invention also provides a computer storage medium which stores program instructions, wherein the program instructions control equipment where the computer storage medium is located to execute the elevator image processing method when running.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, a coordinate system is established through the maximum monitoring area, the acquired images are corrected according to the first coordinate of the intersection point of the maximum monitoring area on the longitudinal bisector of the maximum monitoring area of the monitoring area, all images are ensured to be based on the same coordinate system in image analysis, and based on the second image and the first image, a complete background image is acquired through the first difference image, the background images of corresponding floors can be acquired in time when different floors correspond to different background images or the background images are replaced on the same floor, the accurate reference object is provided for judging the obstacle through the mutual matching of the image correction and the technical scheme of acquiring the complete background image, meanwhile, the real-time position and the movement direction of the elevator door are acquired according to the first difference image, the outline, the position and the running speed of the obstacle are accurately calculated according to each pixel value in the second image in the second target area, the running parameter of the elevator door and the elevator and the position are predicted based on the minimum distance between the running parameter of the elevator door and the position of the elevator and the running speed of the elevator, the real-time control distance between the elevator door and the elevator door is increased when the running parameter of the elevator is not more accurate than the first difference image, the real-time control accuracy of the elevator door is increased, and the running accuracy of the elevator can be more accurately is improved.
Drawings
Fig. 1 is a flow chart of a method of processing an elevator image according to the present invention;
fig. 2 is a block diagram of an elevator image processing system according to the present invention;
FIG. 3 is a schematic diagram of a coordinate system established according to a maximum monitored area;
fig. 4 is a schematic diagram when the acquired monitoring area image is offset.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The invention provides a processing method of an elevator image, as shown in fig. 1, comprising the following steps:
step S1: in an initial state, continuously acquiring an image of an elevator door, acquiring a maximum monitoring area of the elevator door, establishing a coordinate system of the maximum monitoring area, and acquiring a first coordinate of an intersection point between the maximum monitoring area and a longitudinal bisector of the maximum monitoring area; specifically, as shown in fig. 3, by collecting an image of an elevator door and calculating an area with a column pixel value larger than a set value, the image corresponding to the largest area in the collected image is an image when the elevator door is fully opened, the area is a maximum monitoring area, a coordinate system of the area is established, and a first coordinate of an intersection point between a longitudinal bisector of the maximum monitoring area and the maximum monitoring area is obtained, wherein the column pixel value is the sum of pixel values of all pixels in the column;
Step S2: correcting the acquired image of the monitoring area based on the first coordinate, acquiring a first real-time position of the elevator door by calculating a column pixel value of the monitoring area, simultaneously comparing a second image acquired in real time with a first image acquired last time to acquire a first difference image, and acquiring a moving direction, a moving speed and a background image of the elevator door based on the first difference image; specifically, as shown in fig. 4, by calculating the pixel value of each loudness of the collected image of the monitoring area, obtaining an area with the pixel value larger than a third set value as an elevator opening and closing area, obtaining coordinates of four endpoints of the elevator opening and closing area, calculating a second coordinate of an intersection point with the monitoring area on a longitudinal bisector of the elevator opening and closing area based on the coordinates of the four endpoints, correcting the image of the monitoring area according to the vector difference between the second coordinate and the first coordinate, providing a unified coordinate system for the comparison of the first image and the second image, ensuring the accuracy of the movement direction and the movement speed of the elevator door, ensuring the integrity of the obtained background image, avoiding shooting dead zones, and simultaneously, obtaining the corresponding background image in time when the elevator door is completely opened after the acquisition of the background image is completed and ensuring the accuracy of judging the obstacle when the elevator door is closed when the corresponding background image of each floor elevator door is different;
Step S3: comparing the second image acquired in real time with the background image to acquire a second difference image, acquiring a real-time target area by calculating a column pixel value of the second image, and judging whether an obstacle exists in the real-time target area based on the second difference image; specifically, a second difference image is obtained through differential calculation between a second image acquired in real time and the background image, pixel values of pixels in a portion, overlapped with a real-time target area, of the second difference image are calculated, and whether an obstacle exists in the real-time target area is judged based on the pixel values;
step S4: calculating the running speed and the position of the obstacle in real time when the obstacle exists in the second target area corresponding to the second difference image, predicting the minimum distance from the elevator door in the process that the obstacle leaves the second target area according to the position and the moving speed of the obstacle and the first real-time position and the moving speed of the elevator door, and adjusting the image acquisition mode of the target area according to the distance between the obstacle and the elevator door; when an obstacle exists in a monitoring area, the motion speed of the elevator door is adjusted by calculating the minimum distance, and when the minimum distance is smaller than a first distance, the closing speed of the elevator door is reduced, the imaging focal length of the imaging unit is increased, meanwhile, the imaging frequency of the imaging unit is increased, and clearer real-time image information is obtained, so that more accurate position information of the elevator door and the obstacle is obtained;
Step S5: and determining the action of the elevator door according to the distance between the elevator door and the obstacle. Specifically, when the first difference is smaller than the first distance, predicting the minimum distance from the elevator door in the process that the obstacle leaves the second target area according to the position and the movement speed of the obstacle and the first real-time position and the movement speed of the elevator door, when the minimum distance is larger than the second distance, the elevator door is normally closed, when the minimum distance is smaller than the second distance, the operation speed of the elevator door is reduced, and when the first difference is smaller than the second distance in the process that the elevator door is closed, the elevator door is paused for a preset time, and after the elevator door is paused for a preset time, the obstacle still exists, the elevator door is opened and an alarm is sent; after the elevator door is paused for a predetermined time, the obstacle disappears, and the elevator door is closed.
Further, in the step S1, a column pixel value of the image is calculated in real time according to the continuously collected image of the elevator door, in all the images, an image with the most columns having column pixel values larger than a first set value corresponds to a state after the elevator door is fully opened, an opening and closing area of the elevator door is a maximum monitoring area, a row pixel value and a column pixel value of the image are calculated, a row pixel direction meeting that the row pixel value is larger than a second set value at the lowest end in the image is taken as an x-axis, a column pixel direction meeting that the column pixel value is larger than the first set value at the leftmost end in the image is taken as a y-axis, a crossing point of the x-axis and the y-axis is taken as a coordinate origin, coordinates of four endpoints of the maximum monitoring area are also obtained, a first coordinate of the crossing point of the maximum monitoring area on a longitudinal bisector of the maximum monitoring area is calculated based on the coordinates of the four endpoints, and the longitudinal bisector of the maximum monitoring area corresponds to a door seam of the elevator door.
Specifically, after the elevator door is fully opened, the opening and closing area of the elevator door is maximum, and the brightness area is maximum, so that the corresponding row of pixel values are the maximum, the opening and closing area of the elevator door is the maximum monitoring area, the sitting angle of the maximum monitoring area is taken as the origin of coordinates to establish a coordinate system, the direction of the bottom row pixel of the maximum monitoring area is the x axis, the direction of the left column pixel of the maximum monitoring area is the y axis, and the first coordinates of two intersecting points between the longitudinal bisector of the maximum monitoring area and the maximum monitoring area are obtained through the coordinate system.
Further, in step S2, each pixel value in the image is calculated based on the acquired image of the monitored area, when the area with the pixel value larger than the third set value is the target monitored area, the pixel coordinates of four endpoints of the target monitored area are obtained, the second coordinates of the intersection point of the longitudinal bisector of the monitored area and the monitored area are determined based on the pixel coordinates of the four endpoints, the second coordinates are compared with the first coordinates, the difference vector between the first coordinates and the second coordinates is obtained, when the absolute value of the difference vector is smaller than the first threshold, the image of the monitored area is corrected based on the difference vector, and when the absolute value of the difference vector is larger than the first threshold, the image of the monitored area is corrected by adjusting the image capturing angle of the image capturing unit.
Specifically, the longitudinal bisector of the monitoring area and the intersection point of the monitoring area are divided into an upper end intersection point and a lower end intersection point, subtraction is carried out on second coordinates and first coordinates corresponding to the upper end intersection point and the lower end intersection point, a difference vector is obtained, when the absolute value of the difference vector is smaller than a first threshold value, the difference between the second coordinates and the first coordinates is smaller, possibly caused by jitter, the offset parameter can be calculated through the difference vector to correct an image, when the absolute value of the difference vector is larger than the first threshold value, the difference between the second coordinates and the first coordinates is larger, possibly, the shooting angle of the shooting unit is changed, the acquired image can be corrected through adjusting the shooting angle of the shooting unit, and all the acquired image images are in the same coordinate system through correction, so that the analysis processing of the image is facilitated.
Further, the step S2 further includes the following steps:
step S21: calculating a column pixel value of the first image, wherein a region with the column pixel value larger than a first set value is a first target region, calculating a column pixel value of the second image, wherein a region with the column pixel value larger than the first set value in the second image is a second target region, and comparing the first target region with the second target region to obtain a first difference image; specifically, the first target area is an opening and closing area of an elevator door in the first image, the second target area is an opening and closing area of the elevator door in the second image, the boundaries of two sides of the first target area are elevator door positions, the boundaries of two sides of the second target area are positions of the elevator door corresponding to the second image, the first difference image is obtained by comparing the first target area with the second target area, wherein the first difference image is an area difference between the first target area in the first image and the second target area in the second image, the running direction and the position of the elevator door are judged through the first difference image, the pixel value of the area where the second image coincides with the first image is the lowest, and the non-coinciding area highlights the pixel value to be larger;
Step S22: determining the movement direction of the elevator door according to the position of a difference area, of which the column pixels are larger than the first set value, in the first difference image relative to the first target area, wherein the movement direction of the elevator door is opened when the difference area appears on two sides of the first target area, and the movement direction of the elevator door is closed when the difference area appears on the boundary of the first target area; specifically, when the difference area appears on two sides of the first target area, the opening and closing area of the elevator door corresponding to the second image is larger than the opening and closing area of the elevator door corresponding to the first image, so that the movement direction of the elevator door can be judged to be open, and when the difference area appears on the boundary of the first target area, the opening and closing area of the elevator door corresponding to the second image is smaller than the opening and closing area of the elevator door corresponding to the first image, so that the movement direction of the elevator door can be judged to be closed;
step S23: when the movement direction of the elevator door is open, the position of the difference area close to the two sides is a first real-time position of the elevator door, and when the movement direction of the elevator door is closed, the position of the difference area close to the inner side is a first real-time position of the elevator door; specifically, when the elevator door is opened, a monitoring area of the second image acquired in real time is large relative to the first image acquired last time, a difference area is a moving distance of the elevator door, the inner side of the difference image is a position of the elevator door corresponding to the first image, the outer side of the difference area is a position of the elevator door at the moment, when the elevator door is closed, the monitoring area of the second image acquired in real time is small relative to the first image, the inner side of the difference area is a real-time position of the elevator door at the moment, and the outer side of the difference area is a position of the elevator door corresponding to the first image;
Step S24: when all column pixel values are smaller than the first set value, the elevator door is in a closed state, when the first target area is larger than or equal to the maximum monitoring area, the elevator door is all opened, and in the process of the elevator door from closing to fully opening, the difference area images in all the obtained first difference images are spliced to obtain a background image, wherein the expression is as follows:
wherein ,
for background image +.>
And i is a positive integer from 1 to N for the difference area in the first difference image of the second image acquired for the ith time and the first image of the previous time, wherein N is the total amount of the second images acquired from the closing to the full opening of the elevator door. Specifically, in the process of opening the elevator door, people can get in and out of the elevator, the real background image cannot be obtained, and the background images of each floor are possibly different, so that the instantaneous displacement area of the elevator door moving through the elevator cannot be occupied by people or objects in the moment, and in the process of opening the elevator door, the difference area image in the first difference image, namely the displacement of the elevator door in the second image relative to the elevator door in the first image, can be understood as the situation that the background images corresponding to the instantaneous displacement of the elevator are spliced together to obtain the complete background image, the complete background image can be obtained, the normal operation of the elevator is not influenced, and a complete and accurate reference object is provided for accurately capturing tiny obstacles.
Further, in the step S3, when the motion direction of the elevator door is on, a second target area, in which the column pixel value in the second image acquired in real time is greater than the first set value, is calculated, the second target area is compared with the background image to obtain the second difference image, the pixel value of each pixel in the second difference image is calculated, and when the pixel value of n adjacent pixels is less than the third preset value, an obstacle exists in the second target area, otherwise, no obstacle exists.
Specifically, the second target area in the second image is an opening and closing area of the elevator door and is also a real-time monitoring area, the second difference image is an image obtained by removing the background image from the second target area in the second image, each pixel value in the second difference image is calculated to judge whether an obstacle and the outline of the obstacle exist, wherein the area, which is the same as the background image, in the second target area of the second image is a highlight state, the pixel value of the pixel in the second difference image is larger, and when the obstacle exists, the light of the second target area is blocked by the obstacle, so that the pixel value of the pixel in the corresponding second difference image is smaller, whether the obstacle exists is judged by calculating the pixel value, the accuracy is higher, and the tiny obstacle can be identified.
Further, when it is determined that an obstacle exists, the step S4 includes the steps of:
step S41: calculating pixel values of the second difference image corresponding to each pixel in a second target area, wherein an area formed by adjacent pixels with the pixel values smaller than a second preset value is an outline of an obstacle, and the position of the area is the coordinate position of the obstacle; specifically, when an obstacle exists, the outline of the obstacle is obtained by calculating the pixel value, so that the shape and the appearance of the obstacle can be obtained accurately, and meanwhile, the coordinate position of the obstacle is obtained according to the position of the pixel contained in the outline of the obstacle, and the pixel is taken as the minimum unit, so that the coordinate position information of the obstacle is more accurate;
step S42: comparing the acquired second difference image with the acquired second difference image to acquire the movement displacement and movement direction of the obstacle, and calculating the movement speed of the obstacle according to the time difference between the acquired second difference image and the acquired second difference image; specifically, the movement speed and the movement direction of the obstacle can be obtained according to the second difference image position and the time difference of the obstacle obtained at the current time and the last time, and the movement track of the obstacle can be predicted through the parameters of the obstacle;
Step S43: and calculating a first difference of a real-time shortest distance between the obstacle and the elevator door based on the coordinate position of the obstacle and the first real-time position of the elevator door acquired in the step S2, and increasing the shooting focal length of the shooting unit and increasing the shooting frequency of the shooting unit when the first difference is smaller than the first distance. Specifically, when the shortest distance first gap of the barrier and the elevator door is smaller than the first distance, in order to obtain the position of the elevator door and the barrier more accurately, the shooting focal length of the unit is increased to obtain richer detail images so that the images are clearer, the shooting frequency of the shooting unit is increased to obtain the images with higher precision and continuity, and further the position and the distance of the barrier and the elevator door are more accurate, so that more timely tracking and control are facilitated, and the efficient operation of the elevator is ensured while the safety is ensured.
Further, when the first difference is smaller than the first distance, predicting the minimum distance from the elevator door in the process that the obstacle leaves the second target area according to the position and the movement speed of the obstacle and the first real-time position and the movement speed of the elevator door, when the minimum distance is larger than the second distance, the elevator door is normally closed, when the minimum distance is smaller than the second distance, the operation speed of the elevator door is reduced, and when the first difference is smaller than the second distance, the elevator door is paused for a preset time, and after the elevator door is paused for a preset time, the obstacle still exists, the elevator door is opened and an alarm is sent out; after the elevator door is paused for a predetermined time, the obstacle disappears, and the elevator door is closed, wherein the first distance is greater than the second distance. Specifically, the minimum distance is predicted, the minimum distance between the obstacle and the elevator door is judged, when the minimum distance is larger than the second distance, the elevator door and the obstacle are safe, the elevator door can normally execute closing operation, opening operation is carried out without detecting the obstacle, the operation efficiency of the elevator is improved, potential safety hazards exist between the elevator door and the obstacle when the minimum distance is smaller than the second distance, therefore, the operation speed of the elevator door is reduced, when the first difference is smaller than the second distance, the operation of the obstacle is suspended for a preset time, the operation of the obstacle is kept away from a second target area, if the obstacle is not kept away after the preset time, the elevator door is opened, an alarm prompt is given, the obstacle is urged to leave, and if the obstacle is kept away after the preset time, the elevator door is normally closed, through the scheme, the situation that the elevator door is frequently closed and opened due to detection sensitivity is reduced, the operation efficiency of the elevator is also improved while the safety is ensured, and the service life of the elevator is also prolonged.
The invention also provides a processing system of the elevator image, which is used for realizing the processing method of the elevator image, as shown in fig. 2, and comprises the following steps:
the camera shooting unit is used for continuously collecting images of the elevator door;
the image analysis unit is configured to: acquiring a maximum monitoring area of an elevator door, establishing a coordinate system of the maximum monitoring area, and acquiring a first coordinate of an intersection point between the maximum monitoring area and a longitudinal bisector of the maximum monitoring area; meanwhile, comparing a second image acquired in real time with a first image acquired last time to acquire a first difference image, and acquiring the movement direction, movement speed and background image of the elevator door based on the first difference image; comparing the second image acquired in real time with the background image to acquire a second difference image, acquiring a second target area by calculating column pixel values of the second image, and judging whether an obstacle exists in the second target area based on the second difference image; when determining that an obstacle exists, calculating the running state and the position of the obstacle in real time, and predicting the minimum distance from the elevator door in the process that the obstacle leaves the second target area according to the position and the movement speed of the obstacle and the first real-time position and the movement speed of the elevator door;
The image capturing unit is also used for adjusting the image acquisition mode of the target area according to the first distance.
The invention also provides a computer storage medium which stores program instructions, wherein the program instructions control equipment where the computer storage medium is located to execute the elevator image processing method when running.
In summary, the coordinate system is established through the maximum monitoring area, the collected images are corrected according to the first coordinate of the intersection point of the maximum monitoring area on the longitudinal bisector of the maximum monitoring area of the monitoring area, all images are ensured to be based on the same coordinate system in image analysis, the first difference image is obtained based on the second image and the first image, the complete background image is obtained through the first difference image, the background images of the corresponding floors can be timely obtained when different floors correspond to different background images or the background images are replaced on the same floor, an accurate reference object is provided for judging the obstacle, the real-time position and the moving direction of the elevator door are obtained according to the first difference image, meanwhile, the contour, the position and the moving speed of the obstacle are accurately calculated according to the second difference image obtained by the second image and the second difference image, meanwhile, the operation distance between the elevator door and the position are controlled based on the minimum distance between the elevator door and the position prediction and the actual distance between the elevator door and the elevator door, the accuracy of the elevator door is further improved when the elevator is smaller than the first difference image, the accuracy of the elevator is further improved, the elevator is further, the accuracy of the elevator can be further improved, and the elevator life is further improved.
The technical features of the above embodiments may be arbitrarily combined, and for brevity, all of the possible combinations of the technical features of the above embodiments are not described, however, they should be considered as the scope of the description of the present specification as long as there is no contradiction between the combinations of the technical features.
The foregoing examples have been presented to illustrate only a few embodiments of the invention and are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (9)
1. A method of processing an elevator image, the method comprising the steps of:
Step S1: in an initial state, continuously acquiring an image of an elevator door, acquiring a maximum monitoring area of the elevator door, establishing a coordinate system of the maximum monitoring area, and acquiring a first coordinate of an intersection point between the maximum monitoring area and a longitudinal bisector of the maximum monitoring area;
step S2: correcting the acquired image of the monitoring area based on the first coordinate, acquiring a first real-time position of the elevator door by calculating a column pixel value of the monitoring area, simultaneously comparing a second image acquired in real time with a first image acquired last time to acquire a first difference image, and acquiring a moving direction, a moving speed and a background image of the elevator door based on the first difference image;
step S3: comparing the second image acquired in real time with the background image to acquire a second difference image, acquiring a second target area by calculating a column pixel value of the second image, and judging whether an obstacle exists in a corresponding second target area in the second difference image;
step S4: calculating the running speed and the position of the obstacle in real time when the obstacle exists in the second target area corresponding to the second difference image, predicting the minimum distance from the elevator door in the process that the obstacle leaves the second target area according to the position and the moving speed of the obstacle and the first real-time position and the moving speed of the elevator door, and adjusting the image acquisition mode of the target area according to the distance between the obstacle and the elevator door;
Step S5: and determining the action of the elevator door according to the distance between the elevator door and the obstacle.
2. The method for processing an elevator image according to claim 1, wherein in the step S1, a column pixel value of the image is calculated in real time according to an image of an elevator door continuously collected, in all the images, an image with a column pixel value greater than a first set value and a column pixel value of the image with the largest column pixel value being greater than the first set value corresponds to a state after the elevator door is fully opened, an opening and closing area of the elevator door is a maximum monitoring area, a row pixel value and a column pixel value of an image corresponding to the maximum monitoring area are calculated, a row pixel direction of a lowermost end of the image corresponding to the maximum monitoring area, which satisfies the row pixel value greater than a second set value, is taken as an x-axis, a column pixel direction of a leftmost end of the image corresponding to the maximum monitoring area, which satisfies the column pixel value greater than the first set value, is taken as a y-axis, an intersection point of the x-axis and the y-axis is taken as a coordinate origin, coordinates of four end points of the maximum monitoring area are also acquired, and a longitudinal bisection line of the maximum elevator corresponding to the first intersection point of the maximum monitoring area is calculated based on the coordinates of the four end points.
3. The method according to claim 1, wherein in step S2, each pixel value in the image is calculated based on the acquired image of the monitored area, the pixel coordinates of four end points of the target monitored area are acquired when the area where the pixel value is larger than the third set value is the target monitored area, the second coordinates of the intersection point of the longitudinal bisector of the monitored area and the monitored area are determined based on the pixel coordinates of the four end points, the second coordinates are compared with the first coordinates, and a difference vector of the first coordinates and the second coordinates is acquired, the image of the monitored area is corrected based on the difference vector when the absolute value of the difference vector is smaller than the first threshold, and the image of the monitored area is corrected by adjusting the imaging angle of the imaging unit when the absolute value of the difference vector is larger than the first threshold.
4. The method according to claim 1, characterized in that in step S2 the steps of:
step S21: calculating a column pixel value of the first image, wherein a region with the column pixel value larger than a first set value is a first target region, calculating a corrected column pixel value of the second image, wherein a region with the column pixel value larger than the first set value in the second image is a second target region, and comparing the first target region with the second target region to obtain a first difference image;
Step S22: the direction of a difference area, of which the column pixels are larger than the first set value, in the first difference image relative to the first target area is the movement direction of the elevator door, when the difference area is arranged on two sides of the first target area, the movement direction of the elevator door is open, and when the difference area is arranged in the middle of the first target area, the movement direction of the elevator door is closed;
step S23: when the movement direction of the elevator door is open, the position of the difference area close to the two sides is a first real-time position of the elevator door, and when the movement direction of the elevator door is closed, the position of the difference area close to the inner side is a first real-time position of the elevator door;
step S24: when all the column pixel values are smaller than the first set value, the elevator door is in a closed state, when the first target area is larger than or equal to the maximum monitoring area, the elevator door is all opened, and in the process of the elevator door from closing to fully opening, the acquired difference area images in all the first difference images are spliced to acquire a background image, wherein the expression is as follows:
wherein ,
as a background image of the object, />
And i is a positive integer from 1 to N for the difference area in the first difference image of the second image acquired for the ith time and the first image of the previous time, wherein N is the total amount of the second images acquired from the closing to the full opening of the elevator door.
5. The method according to claim 4, wherein in the step S3, when the motion direction of the elevator door is closed, a second target area with a column pixel value greater than a first set value in the second image acquired in real time is calculated, the second target area is compared with the background image to obtain the second difference image, a pixel value of each pixel in the second difference image is calculated, and when the pixel value of n adjacent pixels is smaller than a third preset value, an obstacle exists in the second target area, otherwise, no obstacle exists, where n is greater than or equal to 10.
6. The method according to claim 5, characterized in that, when it is determined that an obstacle is present, the step S4 comprises the steps of:
step S41: calculating pixel values of the second difference image corresponding to each pixel in a second target area, wherein an area formed by adjacent pixels with the pixel values smaller than a second preset value is an outline of an obstacle, and the position of the area is the coordinate position of the obstacle;
Step S42: comparing the acquired second difference image with the acquired second difference image to acquire the movement displacement and movement direction of the obstacle, and calculating the movement speed of the obstacle according to the time difference between the acquired second difference image and the acquired second difference image;
step S43: and calculating a real-time shortest distance between the obstacle and the elevator door as a first difference based on the coordinate position of the obstacle and the first real-time position of the elevator door acquired in the step S2, and increasing the shooting focal length of the shooting unit and increasing the shooting frequency of the shooting unit when the first difference is smaller than the first distance.
7. The method according to claim 6, wherein in step S5, when the first difference is smaller than the first distance, a minimum distance from the elevator door during the process of moving the obstacle away from the second target area is predicted according to the position and the moving speed of the obstacle and the first real-time position and the moving speed of the elevator door, when the minimum distance is larger than the second distance, the elevator door is normally closed, when the minimum distance is smaller than the second distance, the moving speed of the elevator door is reduced, and when the first difference is smaller than the second distance, the elevator door is paused for a predetermined time during the closing of the elevator door, and after the elevator door is paused for a predetermined time, the obstacle is still present, the elevator door is opened and an alarm is issued; after the elevator door is paused for a predetermined time, the obstacle disappears, and the elevator door is closed, wherein the first distance is greater than the second distance.
8. A system for processing an elevator image, characterized in that the system is used for realizing a method for processing an elevator image according to claims 1-7, the system comprising:
the camera shooting unit is used for continuously collecting images of the elevator door;
the image analysis unit is configured to: acquiring a maximum monitoring area of an elevator door, establishing a coordinate system of the maximum monitoring area, and acquiring a first coordinate of an intersection point between the maximum monitoring area and a longitudinal bisector of the maximum monitoring area; meanwhile, comparing a second image acquired in real time with a first image acquired last time to acquire a first difference image, and acquiring the movement direction, movement speed and background image of the elevator door based on the first difference image; comparing the second image acquired in real time with the background image to acquire a second difference image, acquiring a second target area by calculating a column pixel value of the second image, and judging whether an obstacle exists in the second difference image corresponding to the second target area; when determining that an obstacle exists, calculating the running state and the position of the obstacle in real time, and predicting the minimum distance from the elevator door in the process that the obstacle leaves the second target area according to the position and the movement speed of the obstacle and the first real-time position and the movement speed of the elevator door;
The image capturing unit is also used for adjusting the image acquisition mode of the target area according to the first distance.
9. A computer storage medium, characterized in that the computer storage medium stores program instructions, wherein the program instructions, when run, control a device in which the computer storage medium is located to perform a method of processing an elevator image according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310210997.2A CN116040432B (en) | 2023-03-07 | 2023-03-07 | Elevator image processing method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310210997.2A CN116040432B (en) | 2023-03-07 | 2023-03-07 | Elevator image processing method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116040432A true CN116040432A (en) | 2023-05-02 |
| CN116040432B CN116040432B (en) | 2023-05-30 |
Family
ID=86125766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310210997.2A Active CN116040432B (en) | 2023-03-07 | 2023-03-07 | Elevator image processing method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116040432B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009035375A (en) * | 2007-08-01 | 2009-02-19 | Hitachi Building Systems Co Ltd | Abnormality monitoring device in elevator car |
| JP2009280362A (en) * | 2008-05-23 | 2009-12-03 | Hitachi Ltd | Safety device and safety control method for elevator door |
| CN102145839A (en) * | 2010-02-09 | 2011-08-10 | 东芝电梯株式会社 | Elevator remaining object detection device |
| JP2015231893A (en) * | 2014-06-09 | 2015-12-24 | 東芝エレベータ株式会社 | Elevator monitoring device |
| CN109573798A (en) * | 2017-09-29 | 2019-04-05 | 奥的斯电梯公司 | The elevator door control system clamped for detecting barrier |
| CN110127479A (en) * | 2019-04-17 | 2019-08-16 | 浙江工业大学 | A kind of elevator door switch method for detecting abnormality based on video analysis |
| CN110540121A (en) * | 2019-09-09 | 2019-12-06 | 广州广日电梯工业有限公司 | system and method for identifying foreign matters in sliding groove of elevator sill |
| CN111268539A (en) * | 2018-12-05 | 2020-06-12 | 东芝电梯株式会社 | Foreign matter detection system of elevator |
| CN112850396A (en) * | 2019-11-28 | 2021-05-28 | 宁波微科光电股份有限公司 | Elevator foreign matter detection method and system, computer storage medium and elevator |
| CN113086790A (en) * | 2021-03-03 | 2021-07-09 | 上海新时达电气股份有限公司 | Elevator foreign matter monitoring method and device, electronic equipment and storage medium |
| JP7187629B1 (en) * | 2021-08-06 | 2022-12-12 | 東芝エレベータ株式会社 | Elevator user detection system |
-
2023
- 2023-03-07 CN CN202310210997.2A patent/CN116040432B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009035375A (en) * | 2007-08-01 | 2009-02-19 | Hitachi Building Systems Co Ltd | Abnormality monitoring device in elevator car |
| JP2009280362A (en) * | 2008-05-23 | 2009-12-03 | Hitachi Ltd | Safety device and safety control method for elevator door |
| CN102145839A (en) * | 2010-02-09 | 2011-08-10 | 东芝电梯株式会社 | Elevator remaining object detection device |
| JP2015231893A (en) * | 2014-06-09 | 2015-12-24 | 東芝エレベータ株式会社 | Elevator monitoring device |
| CN109573798A (en) * | 2017-09-29 | 2019-04-05 | 奥的斯电梯公司 | The elevator door control system clamped for detecting barrier |
| CN111268539A (en) * | 2018-12-05 | 2020-06-12 | 东芝电梯株式会社 | Foreign matter detection system of elevator |
| CN110127479A (en) * | 2019-04-17 | 2019-08-16 | 浙江工业大学 | A kind of elevator door switch method for detecting abnormality based on video analysis |
| CN110540121A (en) * | 2019-09-09 | 2019-12-06 | 广州广日电梯工业有限公司 | system and method for identifying foreign matters in sliding groove of elevator sill |
| CN112850396A (en) * | 2019-11-28 | 2021-05-28 | 宁波微科光电股份有限公司 | Elevator foreign matter detection method and system, computer storage medium and elevator |
| CN113086790A (en) * | 2021-03-03 | 2021-07-09 | 上海新时达电气股份有限公司 | Elevator foreign matter monitoring method and device, electronic equipment and storage medium |
| JP7187629B1 (en) * | 2021-08-06 | 2022-12-12 | 東芝エレベータ株式会社 | Elevator user detection system |
Non-Patent Citations (1)
| Title |
|---|
| 张怡伟;陶银兵;茆海洋;: "试论电梯门柔性防夹安全技术", 科学技术创新, no. 23, pages 184 - 185 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116040432B (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107330920B (en) | Monitoring video multi-target tracking method based on deep learning | |
| US10941019B2 (en) | User detection system and image processing device | |
| KR100831122B1 (en) | Face authentication apparatus, face authentication method, and entrance and exit management apparatus | |
| TWI482123B (en) | Multi-state target tracking mehtod and system | |
| WO2014155979A1 (en) | Tracking processing device and tracking processing system provided with same, and tracking processing method | |
| JP7272024B2 (en) | Object tracking device, monitoring system and object tracking method | |
| KR101961571B1 (en) | Object recognition device using plurality of object detection means | |
| US20070229663A1 (en) | Image processing apparatus, monitoring camera, and image monitoring system | |
| CN109409315B (en) | Method and system for detecting remnants in panel area of ATM (automatic Teller machine) | |
| CN106559647B (en) | Door opening and closing detection device and method, people flow detection system and vehicle | |
| KR20190046351A (en) | Method and Apparatus for Detecting Intruder | |
| JP2008071172A (en) | Face authentication system, face authentication method, and access control device | |
| KR101712136B1 (en) | Method and apparatus for detecting a fainting situation of an object by using thermal image camera | |
| US20220366570A1 (en) | Object tracking device and object tracking method | |
| CN110674680A (en) | Living body identification method, living body identification device and storage medium | |
| KR102547768B1 (en) | Method and Apparatus for Detecting Real-time Anomaly in Video Surveillance System | |
| CN116040432B (en) | Elevator image processing method, system and storage medium | |
| KR101290517B1 (en) | Photographing apparatus for tracking object and method thereof | |
| JP5008118B2 (en) | Suspicious person discrimination system and profile distribution system | |
| CN110930432A (en) | Video analysis method, device and system | |
| JPH05300516A (en) | Animation processor | |
| CN103974028A (en) | Method for detecting fierce behavior of personnel | |
| KR20180111150A (en) | Apparatus for extracting foreground from video and method for the same | |
| JPH04111079A (en) | Traveling object identifying device | |
| KR100996482B1 (en) | System and Method for vehicle trajectory detection using long distance image 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |