CN115860642A - Access management method and system based on visual identification - Google Patents
Access management method and system based on visual identification Download PDFInfo
- Publication number
- CN115860642A CN115860642A CN202310051384.9A CN202310051384A CN115860642A CN 115860642 A CN115860642 A CN 115860642A CN 202310051384 A CN202310051384 A CN 202310051384A CN 115860642 A CN115860642 A CN 115860642A
- Authority
- CN
- China
- Prior art keywords
- state
- library
- area
- value
- image frame
- 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
Images
Abstract
The invention provides an in-out library management method and system based on visual identification, wherein the method comprises the following steps: marking a buffer area at the position of an entrance and an exit of a warehouse in the image frame, marking each warehouse position in the warehouse, numbering and acquiring position data, and acquiring the position data in the image frame where each buffer area is located; giving an initial first state value to each storage position according to the storage position occupation condition; recording goods entering the entry cache area and acquiring position data in the image frame where the goods are located
(ii) a Counting the first state value of each storage position, screening out a storage position set E capable of receiving goods to calculate
And calculating the KIou value K1 of each library position in the E, calculating the KIou value K2 of each library position and the position data of the exit cache region in the E, and then calculating the KIou value K2 of each library position and the position data of the exit cache region in the EAnd allocating the stock position corresponding to the number of the minimum value in the K1 and K2 sets to the goods, and updating the first state value of the stock position. Therefore, automatic management of warehousing and ex-warehousing under a warehousing scene is realized on the basis of a computer vision technology.
Description
Technical Field
The invention relates to application of a computer vision technology in the field of automatic warehousing, in particular to an in-out library management method and system based on visual identification.
Background
With the development of internet economy, the rapid increase of freight express delivery causes the automatic reform of storage, but the automatic management of complex and various storage environments needs to be realized, and a certain technical threshold still exists at present. Particularly in a transfer area in a warehouse, goods are frequently accessed, the state of the warehouse is frequently changed, non-single access positions and high efficiency requirements are met, and great challenges are brought to automatic management. The storage position, the position of the storage position, the warehouse-out or warehouse-in are very basic and important information for automatic management, and the method plays a vital guiding role in subsequent path planning of the AGV.
At present, in the prior art, a photoelectric sensor is usually adopted to reflect whether goods exist in a warehouse location, but the method is used in a storage scene with busy freight, has large loss to the photoelectric sensor and needs frequent replacement, and therefore is not beneficial to efficient operation management of the warehouse, and on the other hand, the arrangement of the photoelectric sensor also needs a large amount of maintenance cost of power lines.
In another prior art, management is performed by adopting a mode of adding a new two-dimensional code, for example, the information of a current library position is obtained by scanning the two-dimensional code, but the method firstly needs manual operation, and is very easy to wear if being installed on the ground, and in addition, if things needing to be placed in the library position are changed, the new two-dimensional code needs to be frequently pasted, so that the labor cost is high.
Therefore, in the prior art, the in-out state of the goods cannot be efficiently and accurately acquired so as to perform automatic warehousing management. Therefore, the inventor tries to solve the difficult problem of warehouse entry and exit management in the warehouse automation field through a computer vision target detection technology and an image processing technology.
Disclosure of Invention
The invention mainly aims to provide an in-out warehouse management method and system based on visual identification, so as to realize automatic management of in-out warehouse under a warehousing scene based on a computer vision technology.
In order to achieve the above object, according to a first aspect of the present invention, there is provided a visual recognition-based access management method, comprising the steps of:
step S100, marking a buffer area at the warehouse exit and entrance positions in the image frame, and marking each warehouse position in the warehouse; numbering each library position, acquiring position data in an image frame where each library position is located, and acquiring position data in an image frame where each cache region is located;
step S200, giving an initial first state value to each storage position according to the storage position occupation condition;
step S300, recording goods entering an entrance cache region, and acquiring position data in an image frame where the goods enter
；
Step S400, counting the first state value of each storage position, screening out a storage position set E capable of receiving goods to calculate
And the KIou value K1 of each library position in the E, calculating the KIou value K2 of each library position and the position data of the exit cache region in the E, and then compiling the minimum value in the K1 and K2 setsThe stock position corresponding to the number is assigned to the goods and the first state value of the stock position is updated.
In a possible preferred embodiment, the calculating step of the value K1 of KIou comprises:
step S410, setting the area represented by the position data of the goods as A, and setting the area represented by the position data of each storage position capable of receiving the goods as B;
step S420 calculation
，
Wherein the coordinates of the upper left corner of the notation A are
And the coordinate of the lower right corner is->
(ii) a Let B coordinate in the upper left corner be
And the coordinate of the lower right corner is->
；
Parameter(s)
;
Parameter(s)
;
Parameter(s)
。
In a possible preferred embodiment, the step of calculating the value K2 of KIou comprises:
step S430 sets the area represented by the position data of each storage position capable of receiving goods as A; setting the area represented by the exit cache area position data as B;
step S440 calculation
，
Wherein the coordinates of the upper left corner of the notation A are
And the coordinate of the lower right corner is->
(ii) a Let B coordinate in the upper left corner be
And the coordinate of the lower right corner is->
；
Parameter(s)
;
Parameter(s)
;
Parameter(s)
。
In order to further reasonably schedule the warehousing location based on the example of the first aspect of the present invention, the second aspect of the present invention also provides a method for managing the warehousing based on visual identification, which comprises the following steps:
step S100, marking a buffer area at the warehouse exit and entrance positions in the image frame, and marking each warehouse position in the warehouse; numbering each library position, and acquiring position data in an image frame where each library position is located; an auxiliary area is arranged around each storage position, and position data in an image frame where each auxiliary area is located is obtained; acquiring position data in the image frame where each cache region is located;
step S200, giving an initial first state value to each storage position according to the storage position occupation condition; assigning a second state value to the affiliated area of each library bit;
step S300, recording goods entering an entrance cache region, and acquiring position data in an image frame where the goods enter
；
Step S400, counting the first state value of each storage position, screening out a storage position set E capable of receiving goods to calculate
Calculating a KIou value K2 of position data of each library position and an exit buffer area in the E with the KIou value K1 of each library position in the E, then distributing the library position corresponding to the number of the minimum value in the K1 and K2 sets to the goods, and updating the first state value of the library position; />
Step S500 selects a corresponding affiliated area to enter the depot for unloading according to the first rule according to the second state value of the affiliated area of the allocated depot.
In a possible preferred embodiment, the calculating step of the value K1 of KIou comprises:
step S410, setting the area represented by the position data of the goods as A, and setting the area represented by the position data of each storage position capable of receiving the goods as B;
step S420 calculation
，
Wherein the coordinates of the upper left corner of the notation A are
And the coordinate of the lower right corner is->
(ii) a Let B coordinate in the upper left corner be
And the coordinate of the lower right corner is->
；
Parameter(s)
;
Parameter(s)
;
Parameter(s)
。
In a possible preferred embodiment, the step of calculating the value K2 of KIou comprises:
step S430 sets an area indicated by the position data of each storage location capable of receiving goods as a; setting the area represented by the exit cache area position data as B;
step S440 calculation
，
Wherein the coordinates of the upper left corner of the notation A are
And the coordinate of the lower right corner is->
(ii) a Let B coordinate in the upper left corner be
And the coordinate of the lower right corner is->
；
Parameter(s)
;
Parameter(s)
;
Parameter(s)
。
In a possible preferred embodiment, the first rule comprises:
4 attached regions are arranged on the upper, lower, left and right sides of the storage position, and the second state value comprises: an on state, an allowed on state, and an off state;
s1, if one of 4 auxiliary areas of the library position is in an open state, the rest 3 areas are in an open allowing state;
s2, if an auxiliary area corresponding to a certain auxiliary area is in an on state, the auxiliary area per se needs to be in an off state;
s3, only distributing warehousing tasks to the auxiliary areas which are allowed to be in the on state, changing the allowed on state into the on state after distribution, and changing the allowed on state into the allowed on state after warehousing is finished;
and S4, if the state of an auxiliary area in the same direction in the same row/column is in an on state, not allowing the same auxiliary area in the same row/column to be in an on state, and not allowing the opposite auxiliary area in the opposite row/column to be in an on state.
In a third aspect, the present invention provides a system for managing an entrance and exit library based on visual recognition, including:
the storage unit is used for storing a program comprising any one of the visual identification-based warehousing and warehousing management method steps so as to be timely called and executed by the camera, the visual identification unit, the processing unit and the scheduling unit;
the camera is used for acquiring the warehouse area image frame to send to the visual identification unit;
the visual identification unit is used for marking a buffer area at the warehouse exit and entrance positions in the image frame and marking each warehouse position in the warehouse; numbering each library position, acquiring position data in an image frame where each library position is located, and acquiring position data in the image frame where each cache region is located;
the visual identification unit is further used for giving an initial first state value to each storage position according to the storage position occupation condition; recording goods entering the entry cache area and acquiring position data in the image frame where the goods are located
；
A processing unit for counting the first state value of each storage position, screening out a storage position set E capable of receiving goods to calculate
And calculating the KIou value K1 of each library position in the E, calculating the KIou value K2 of each library position and the position data of the exit cache region in the E, and then calculating the KIou value K2 of each library position and the position data of the exit cache region in the ECalculating a library position corresponding to the number of the minimum value in the K1 and K2 sets so as to send the library position to a scheduling unit;
and the scheduling unit is used for distributing the storage position calculated by the processing unit to the goods and updating the first state value of the storage position.
In a fourth aspect of the present invention, which corresponds to the above method, there is provided a system for managing an access library based on visual recognition, comprising:
the storage unit is used for storing a program comprising the steps of the access management method based on visual identification, so that the camera, the visual identification unit, the processing unit and the scheduling unit can be timely called and executed;
the camera is used for acquiring the warehouse area image frame to send to the visual identification unit;
the visual identification unit is used for marking a buffer area at the warehouse exit and entrance positions in the image frame and marking each warehouse position in the warehouse; numbering each library position, and acquiring position data in an image frame where each library position is located; an auxiliary area is arranged around each library position, and position data in an image frame where each auxiliary area is located is obtained; acquiring position data in the image frame where each cache region is located;
the visual identification unit is further used for endowing each library position with an initial first state value according to the occupation condition of the library position; assigning a second state value to the affiliated area of each library bit; recording goods entering the entry cache region and acquiring position data in the image frame where the goods are located
；
A processing unit for counting the first state value of each storage position, screening out a storage position set E capable of receiving goods to calculate
And the KIou value K1 of each library position in the E, calculating the KIou value K2 of each library position in the E and the position data of the exit buffer area, and then calculating the library position corresponding to the number of the minimum value in the K1 and K2 sets so as to send the library position to a scheduling unit;
and the dispatching unit is used for allocating the storage position calculated by the processing unit to the goods, updating the first state value of the storage position, and simultaneously indicating the corresponding auxiliary area to enter the storage position for unloading according to the first rule and the second state value of the auxiliary area of the allocated storage position.
In a possible preferred embodiment, the visual recognition unit sets 4 attached regions above, below, to the left, and to the right of the library space, and sets the second state value includes: an on state, an allowed on state, and an off state;
the first rule according to which the scheduling unit is based includes: s1, if one of 4 auxiliary areas of the library position is in an open state, the rest 3 areas are in an open allowing state; s2, if an auxiliary area corresponding to a certain auxiliary area is in an on state, the auxiliary area is in an off state; s3, only distributing warehousing tasks to the auxiliary areas which are allowed to be in an on state, changing the allowed on state into the on state after distribution, and changing the allowed on state into the allowed on state after warehousing is completed; and S4, if the state of an auxiliary area in the same direction in the same row/column is in an on state, not allowing the same auxiliary area in the same row/column to be in an on state, and not allowing the opposite auxiliary area in the opposite row/column to be in an on state.
In a fifth aspect, the present invention provides a computer device of an access management system based on visual identification, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.
In a sixth aspect, the present invention also provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the method described above.
By the visual identification-based warehousing and ex-warehouse management method and system, the warehousing and ex-warehouse states of goods in a warehouse can be accurately and efficiently acquired in real time based on the visual identification technology, the warehousing of the goods is convenient to manage, the planning of a goods area and the planning and allocation of loading and unloading are facilitated, the dynamic use conditions of the warehouse location, such as the states of the occupied warehouse location, the unoccupied warehouse location, the planned occupied warehouse location and the like, can be more clearly known, and the computer vision technology is used for providing finer-grained information for the automatic warehousing management.
On the other hand, in some embodiments, the scheme also designs a state management scheme of an auxiliary area for the storage space, provides more information and more scheduling rationality for the freight path planning of the freight robot, and improves the efficiency of cargo circulation and the reliability of the overall freight scheduling management.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic diagram illustrating a layout of a warehouse, a warehouse entrance/exit buffer area and a warehouse location in a first embodiment and a second embodiment of the method for managing an entrance/exit database based on visual recognition according to the present invention;
FIG. 2 is a conceptual diagram of KIou measurement in the first and second embodiments of the method for managing an entrance and exit database based on visual recognition according to the present invention;
FIG. 3 is a method step diagram of a first embodiment of the method for managing an access management based on visual recognition according to the present invention;
FIG. 4 is a schematic diagram illustrating how KIou and other Iou are compared in the first and second embodiments of the method for managing access management based on visual recognition according to the present invention;
FIG. 5 is a comparison of the effects of KIou and other Iou in the first and second embodiments of the method for managing entrance and exit library based on visual recognition, wherein the results of other four Iou are shown in enlarged view;
FIG. 6 is a schematic diagram of a visual identification-based access management system according to the present invention;
FIG. 7 is a method step diagram of a second embodiment of the method for managing an access management based on visual recognition according to the present invention;
fig. 8 is a schematic diagram of the attached areas of the storage locations in the second embodiment of the method for managing an access management based on visual identification according to the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the following will clearly and completely describe the specific technical solution of the present invention with reference to the embodiments to help those skilled in the art to further understand the present invention. It should be apparent that the embodiments described herein are only a few embodiments of the present invention, and not all embodiments. It should be noted that the embodiments and features of the embodiments in the present application can be combined with each other without departing from the inventive concept and without conflicting therewith by those skilled in the art. All other embodiments based on the embodiments of the present invention, which can be obtained by a person of ordinary skill in the art without any creative effort, shall fall within the disclosure and the protection scope of the present invention.
Furthermore, the terms "first," "second," "S1," "S2," and the like in the description and in the claims of the invention and in the drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the invention described herein may be practiced in sequences other than those described. Also, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. Unless expressly stated or limited otherwise, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in this case can be understood by those skilled in the art in combination with the prior art according to the specific situation.
Referring to fig. 1 to 5, the method for managing an access library based on visual recognition according to the present invention includes the steps of:
step S100: marking a buffer area at the warehouse exit and entrance positions in the image frame, and marking each warehouse position in the warehouse; numbering each library position, acquiring position data in an image frame where each library position is located, and acquiring position data in the image frame where each cache region is located;
specifically, assuming that the warehouse is a rectangular area, a camera with a downward lens is installed at a certain height above the warehouse, so that the camera can completely and clearly shoot the whole warehouse, and therefore a continuously output video stream can be obtained, wherein the video stream is essentially one frame image, for example, the video stream of the camera with the frame rate of 25 is essentially 25 frames of images output within one second, because the camera is fixed and the size of the field of the warehouse is also fixed, one image frame with the fixed size and the field can be obtained, and the subsequent operation is based on the image frame.
As shown in fig. 1, assuming that west and South of the warehouse are entrances and East and North are exits in the example, the present scheme will set a region called Buffer area (Buffer) at the exits and entrances, and the combined orientations are defined as North Buffer, south Buffer, westBuffer, and East Buffer. As can be seen from the above, the inlet corresponds to the North Buffer and the South Buffer, and the outlet corresponds to the West Buffer and the East Buffer.
Then, planning m rows and n columns of rectangular library positions for the area according to the size of the warehouse, wherein each library position is given a number
I is more than or equal to 1 and less than or equal to m, and j is more than or equal to 1 and less than or equal to n.
Then, drawing a rectangular library position in the warehouse area on the image, and using the above steps
Indicates that each £ er corresponding to a bin bit in the true bin can then be retrieved>
Is used in the image>
（（/>
，/>
），（/>
，/>
) In this way, the positions of the corresponding four Buffer regions can be expressed as: north Buffer with->
（（/>
，/>
），（/>
，/>
) Expressed by &. In South Buffer &>
（（/>
，/>
），（/>
，/>
) Is indicated by) West Buffer is->
（（/>
，
），（/>
，/>
) Represents,. East Buffer is &>
（（/>
，/>
），（/>
，/>
) Is) is shown.
Step S200: and giving an initial first state value to each library position according to the occupation condition of the library positions.
For example, to show
For subsequent scheduling assignment, a state value, i.e. a first state value, needs to be set, which indicates whether the current pool bit is occupied, for example: the initial state value is 0, indicating unoccupied, 1 indicating occupied, and 1/2 indicating currently unoccupied but planned to be occupied (i.e., to be binned). In addition, based on the present example, those skilled in the art can understand that the states may be adjusted or changed according to the actual freight requirement, and the present disclosure is not limited thereto.
Step S300: recording goods entering the entry cache area and acquiring position data in the image frame where the goods are located
。
Specifically, this case illustrates using Q = ∑ tone
Represents the goods in all warehouses by ∑ on @>
Indicating a certain cargo therein; if an AGV enters the warehouse from the entrance with a load, the AGV first appears in the buffer area, and can give out the load to the receiver>
An initial state, such as an initial value of 0, indicates that the item is not in the storage location and is not allocated a storage location, 1/2 indicates that the item has been allocated a storage location but has not entered a storage location, and 1 indicates that the item is in the storage location. Let West Buffer and South Buffer be the entrance of the staging area and East Buffer and North Buffer be the exit of the warehouse.
At the moment, the camera above the warehouse transmits the image to the visual recognition unit, and the visual recognition unit can detect the position of the goods in the image for use
（（/>
，/>
），（/>
，/>
) ) are shown.
Step S400: counting the first state value of each storage position, screening out a storage position set E capable of receiving goods to calculate
And the KIou value of each bin bit in E is recorded as>
And calculating KIou value of each library bit and exit buffer position data in E and recording as->
，/>
Will then->
+/>
Set and->
+/>
The bin corresponding to the number of the smallest value in the collection of the set is assigned to the good and the first state value of the bin is updated.
Specifically, as shown in fig. 2, it is assumed that the largest rectangular region is E, the rectangular region a intersects with the rectangular region B, the intersection is a rectangular region C, and the remaining regions are denoted as D;
therefore, the following steps are carried out: e = A + B-C + D,
，
the traditional Iou judgment method has the following defects that if A and B are not intersected, the A and B are not intersected
Is always 0, in the present invention, assuming the frame identifying the cargo is A and the bin is B, if A is close to B, then the value is greater than or equal to B as long as the two do not intersect>
The position relation between the two can not be reacted if the value is always 0; in order to make up for the defect, the scheme provides a KIou judgment method.
Statistics ofEach one of which is
Put the state that is unoccupied into the set, marked E, E = ^ if E>
Calculating
And the value of KIou for each bin bit in E is recorded as +>
Examples of the calculation steps include:
step S410, setting the area represented by the position data of the goods as A, and setting the area represented by the position data of each storage position capable of receiving the goods as B;
step S420 calculation
，
Wherein the coordinates of the upper left corner of the notation A are
And the coordinate of the lower right corner is->
(ii) a Let B coordinate in the upper left corner be
And the coordinate of the lower right corner is->
；
Parameter(s)
;
Parameter(s)
；
Parameter(s)
。
Then, calculating the value of KIou of each bin position and two outlet Buffer areas East Buffer and North Buffer in the E, and recording the value as the value
，/>
The calculation steps include:
step S430 sets the area represented by the position data of each storage position capable of receiving goods as A; setting the area represented by the two exit cache area position data as B;
step S440 is calculated as step S420
Thereby respectively acquiring->
，/>
。
Finally, calculate
+/>
Set and->
+/>
The smallest value in the collection of sets, the ij corresponding to the smallest value is the bin bit ^ greater than or equal to the bin bit assigned to the cargo>
While at the same time taking the->
The state value of (1) is updated to be currently unoccupied but planned to be occupied, thus completing the allocation of the warehouse space for warehousing goods.
Compared with other existing Iou judgment methods, only KIou meets the requirements of the scheme and the scene, KIou has the advantages of other Iou, and can reflect the relation between the goods and the storage position at all times, and other Iou is invalid when the goods and the storage position are not overlapped.
As shown in fig. 4, in which four Iou schemes other than KIou are visually overlapped, the above situation occurs because the coordinate system shows the performance of each Iou at a pixel value of 2000 × 2000 on one figure, but the four Iou values in the region fall between (-1 to 0); as shown in fig. 5, the amplified performance of the four ious is shown, and thus, the KIou scheme provided by the present application better meets the scene requirements of the present application, and can better reflect the position relationship between the two.
In response to the above method, as shown in fig. 6, the system for managing an entrance and exit library based on visual recognition according to the present invention includes:
the storage unit is used for storing a program comprising the steps of the method for managing the access and warehouse based on the visual identification, so that the camera, the visual identification unit, the processing unit and the scheduling unit can be timely called and executed.
And the camera is used for acquiring the warehouse area image frame to send the image frame to the visual recognition unit.
The visual identification unit is used for marking a buffer area at the warehouse exit and entrance positions in the image frame and marking each warehouse position in the warehouse; numbering each library position, acquiring position data in an image frame where each library position is located, and acquiring position data in the image frame where each cache region is located.
The visual identification unit is further used for giving an initial first state value to each storage position according to the storage position occupation condition; recording goods entering the entry cache area and acquiring position data in the image frame where the goods are located
。
A processing unit for counting the first state value of each storage position, screening out a storage position set E capable of receiving goods to calculate
And the KIou value of each bin bit in E is recorded as>
And calculating KIou value of each library bit and exit buffer position data in E and recording as->
，/>
Then calculates out->
+/>
Set and->
+/>
And the library bit corresponding to the number of the minimum value in the collection of the set is sent to the scheduling unit.
And the scheduling unit is used for distributing the storage position calculated by the processing unit to the goods and updating the first state value of the storage position.
As shown in fig. 1, 2, 4, 5, 7 to 8, in order to further reasonably schedule the warehousing location based on the first embodiment of the present invention, a second embodiment of the present invention further provides an warehousing management method based on visual identification, which includes the steps of:
step S100, marking a buffer area at the warehouse exit and entrance positions in the image frame, and marking each warehouse position in the warehouse; numbering each library position, and acquiring position data in an image frame where each library position is located; an auxiliary area is arranged around each storage position, and position data in an image frame where each auxiliary area is located is obtained; and acquiring position data in the image frame where each buffer area is located.
Step S200, giving an initial first state value to each storage position according to the storage position occupation condition; assigning a second state value to the affiliated area of each library bit;
step S300, recording goods entering an entrance cache region, and acquiring position data in an image frame where the goods enter
；
Step S400, counting the first state value of each storage position, screening out a storage position set E capable of receiving goods to calculate
Calculating a KIou value K2 of position data of each library position and an exit buffer area in the E with the KIou value K1 of each library position in the E, then distributing the library position corresponding to the number of the minimum value in the K1 and K2 sets to the goods, and updating the first state value of the library position;
step S500 selects a corresponding affiliated area to enter the depot for unloading according to the first rule according to the second state value of the affiliated area of the allocated depot.
Specifically, based on the method of the first embodiment, in step S100, an auxiliary area is further set around each library bit, and position data in an image frame where each auxiliary area is located is acquired. Therefore, a judgment basis is provided for judging which direction of the warehouse location the warehoused goods are warehoused from is more appropriate for subsequent scheduling, and the reliability of warehousing and the scheduling rationality are improved.
For example, the library sites have a width w and a height h. The upper and lower sides of the warehouse are vertically translated outwards by a distance of 1/5h, and the left and right sides are horizontally translated outwards by a distance of 1/5w, wherein it should be noted that the distance can be set according to practical situations, and the above is only an exemplary possibility and is not limited.
After obtaining four additional rectangular areas, defined as Northzone, southZone, westzone and Eastzone, respectively, abbreviated as NZ, SZ, WZ and EZ, respectively, according to the direction, so the bin is located
These four regions of (a) may be referred to as: />
. As shown in fig. 8. />
Further, in the above-mentioned case,
four auxiliary areas>
Each of the second state values is a state value indicating whether the region is in an on state, an allowed on state, or an off state, and the initial value is 0 indicating the off state, and if the state value is 1/2, the region is in the allowed on state, and if the state value is 1, the region is in the on state.
Calculating goods while receiving
Slave->
When the position of the slave is matched with the database, the slave is judged>
Four satellite zones of
Which accessory zone enters->
Because the distance between the cargos cannot accommodate two AGV dollies to move side by side or in opposite directions in many times, and the safe working range of the mechanical arm of the steering operation or the composite robot and the like are added, the two AGV dollies on one path are avoided as much as possible.
For this purpose, a first rule is set, such as:
1. if it is
One of the 4 subsidiary zones is in an on state, and the remaining 3 zones are in an allowed on state.
2. If an auxiliary area is on, the area itself must be off.
3. And only distributing the warehousing task to the auxiliary area in the on-allowed state, changing the on-allowed state into the on-allowed state after distribution, and changing the on-allowed state into the on-allowed state after warehousing is finished.
4. If the state of a certain auxiliary area in the same direction in the same row/column is on, the same auxiliary area in the same row/column is not allowed to be in the on-allowed state, and the opposite auxiliary area in the opposite row/column is not allowed to be in the on-allowed state.
According to the rule program, the states of all the library bits in a complete warehouse and the states of four attached areas of each library bit are obtained. Goods distributed to the cache area according to the state can be warehoused according to the designated auxiliary area of the warehouse location, so that a complete cycle is completed, and the reasonability and the reliability of scheduling can be ensured.
In response to the above method, as shown in fig. 6, the system for managing an entrance and exit library based on visual recognition provided by the present invention includes:
the storage unit is used for storing a program comprising the steps of the method for managing the access and warehouse based on the visual identification, so that the camera, the visual identification unit, the processing unit and the scheduling unit can be timely called and executed.
And the camera is used for acquiring the warehouse area image frame to send the image frame to the visual recognition unit.
The visual identification unit is used for marking a buffer area at the warehouse exit and entrance positions in the image frame and marking each warehouse position in the warehouse; numbering each library position, and acquiring position data in an image frame where each library position is located; an auxiliary area is arranged around each storage position, and position data in an image frame where each auxiliary area is located is obtained; and acquiring position data in the image frame where each buffer area is located.
The visual identification unit is further used for giving an initial first state value to each storage position according to the storage position occupation condition; assigning a second state value to the affiliated area of each library bit; recording goods entering the entry cache area and acquiring position data in the image frame where the goods are located
。/>
A processing unit for counting the first state value of each storage position, screening out a storage position set E capable of receiving goods to calculate
And the KIou value of each bin bit in E is recorded as>
And calculating KIou value of each library bit and exit buffer position data in E and recording as->
，/>
Then calculates out->
+/>
Set and->
+/>
And the library bit corresponding to the number of the minimum value in the collection of the set is used for transmitting to the scheduling unit.
And the dispatching unit is used for allocating the storage position calculated by the processing unit to the goods, updating the first state value of the storage position, and simultaneously indicating the corresponding auxiliary area to enter the storage position for unloading according to the first rule and the second state value of the auxiliary area of the allocated storage position.
Corresponding to the methods of the first and second embodiments, the present invention further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.
Corresponding to the methods of the first and second embodiments, the invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described above.
In summary, the warehouse entry and exit management method and system based on visual identification provided by the invention can accurately and efficiently acquire the warehouse entry and exit states of goods in a warehouse in real time based on the visual identification technology, are convenient for managing the goods warehouse entry, and planning the goods area and the loading and unloading planning and allocating, can more clearly understand the dynamic use conditions of the warehouse location, such as the states of the occupied warehouse location, the unoccupied warehouse location, the occupied warehouse location plan and the like, and can realize the purpose of providing more fine-grained information for the warehouse automatic management by using the computer vision technology.
On the other hand, the scheme also designs a state management scheme of an auxiliary area for the storage position, provides more information for the freight path planning of the freight robot, has more scheduling rationality, and improves the efficiency of cargo circulation and the reliability of the overall freight scheduling management.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof, and any modification, equivalent replacement, or improvement made within the spirit and principle of the invention should be included in the protection scope of the invention.
It will be appreciated by those skilled in the art that, in addition to implementing the system, apparatus and individual modules thereof provided by the present invention in purely computer readable program code means, the system, apparatus and individual modules thereof provided by the present invention can be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like, all by logically programming the method steps. Therefore, the system, the device and the modules thereof provided by the present invention can be considered as a hardware component, and the modules included in the system, the device and the modules thereof for implementing various programs can also be considered as structures in the hardware component; modules for performing various functions may also be considered to be both software programs for performing the methods and structures within hardware components.
In addition, all or part of the steps of the method according to the above embodiments may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a single chip, a chip, or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In addition, any combination of various different implementation manners of the embodiments of the present invention is also possible, and the embodiments of the present invention should be considered as disclosed in the embodiments of the present invention as long as the combination does not depart from the spirit of the embodiments of the present invention.
Claims (10)
1. A method for managing an access library based on visual recognition is characterized by comprising the following steps:
step S100, marking a buffer area at the warehouse exit and entrance positions in the image frame, and marking each warehouse position in the warehouse; numbering each library position, acquiring position data in an image frame where each library position is located, and acquiring position data in the image frame where each cache region is located;
step S200, giving an initial first state value to each storage position according to the storage position occupation condition;
step S300, recording goods entering an entry cache area, and acquiring position data in an image frame where the goods are located
；
Step S400, the first state value of each storage position is counted, and a storage position set E capable of receiving goods is screened out to calculate
And calculating a KIou value K2 of each library position and the position data of the exit buffer area in the E, then allocating the library position corresponding to the number of the minimum value in the K1 and K2 sets to the goods, and updating the first state value of the library position.
2. A visual recognition-based method for managing an entrance/exit library, comprising the steps of:
step S100, marking a buffer area at the warehouse exit and entrance positions in the image frame, and marking each warehouse position in the warehouse; numbering each library position, and acquiring position data in an image frame where each library position is located; an auxiliary area is arranged around each storage position, and position data in an image frame where each auxiliary area is located is obtained; acquiring position data in the image frame where each cache region is located;
step S200, giving an initial first state value to each storage position according to the storage position occupation condition; assigning a second state value to the affiliated area of each library bit;
step S300, recording goods entering an entrance cache region, and acquiring position data in an image frame where the goods enter
；
Step S400, counting the first state value of each storage position, screening out a storage position set E capable of receiving goods to calculate
Calculating a KIou value K2 of position data of each library position and an exit buffer area in the E with the KIou value K1 of each library position in the E, then distributing the library position corresponding to the number of the minimum value in the K1 and K2 sets to the goods, and updating the first state value of the library position;
step S500 selects a corresponding affiliated area to enter the depot for unloading according to the first rule according to the second state value of the affiliated area of the allocated depot.
3. The visual recognition-based entry and exit library management method of claim 2, wherein the calculating of the value K1 of KIou comprises:
step S410, setting the area represented by the position data of the goods as A, and setting the area represented by the position data of each storage position capable of receiving the goods as B;
step S420 calculation
，
Wherein the coordinates of the upper left corner of the notation A are
And the coordinate of the lower right corner is->
(ii) a Marking the coordinate of the upper left corner of the B as->
And the coordinate of the lower right corner is->
；
Parameter(s)
;
Parameter(s)
;
Parameter(s)
。/>
4. The visual recognition-based in-and-out library management method of claim 2, wherein the calculating of the KIou value K2 comprises:
step S430 sets the area represented by the position data of each storage position capable of receiving goods as A; setting the area represented by the exit cache area position data as B;
step S440 calculation
，
Wherein the coordinates of the upper left corner of the notation A are
And the coordinate of the lower right corner is->
(ii) a Marking the coordinate of the upper left corner of the B as->
And the coordinate of the lower right corner is->
；
Parameter(s)
;
Parameter(s)
;
Parameter(s)
。
5. The visual recognition-based access management method of claim 2, wherein the first rule comprises:
4 affiliated areas are arranged on the upper, lower, left and right sides of the warehouse location, and the second state value comprises: an on state, an allowed on state, and an off state;
s1, if one of 4 auxiliary areas of the library position is in an open state, the rest 3 areas are in an open allowing state;
s2, if an auxiliary area corresponding to a certain auxiliary area is in an on state, the auxiliary area per se needs to be in an off state;
s3, only distributing warehousing tasks to the auxiliary areas which are allowed to be in the on state, changing the allowed on state into the on state after distribution, and changing the allowed on state into the allowed on state after warehousing is finished;
and S4, if the state of an auxiliary area in the same direction in the same row/column is in an on state, not allowing the same auxiliary area in the same row/column to be in an on state, and not allowing the opposite auxiliary area in the opposite row/column to be in an on state.
6. A visual recognition-based access management system, comprising:
a storage unit for storing a program comprising the steps of the visual identification-based warehousing and warehousing management method according to claim 1, wherein the video camera, the visual identification unit, the processing unit and the scheduling unit are used for timely invoking and executing;
the camera is used for acquiring the warehouse area image frame to send to the visual identification unit;
the visual identification unit is used for marking a buffer area at the warehouse exit and entrance positions in the image frame and marking each warehouse position in the warehouse; numbering each library position, acquiring position data in an image frame where each library position is located, and acquiring position data in the image frame where each cache region is located;
the visual identification unit is further used for giving an initial first state value to each storage position according to the storage position occupation condition; recording goods entering the entry cache area and acquiring position data in the image frame where the goods are located
；
A processing unit for counting the first state value of each storage position, screening out a storage position set E capable of receiving goods to calculate
And the KIou value K1 of each library position in the E, calculating the KIou value K2 of each library position in the E and the position data of the exit buffer area, and then calculating the library position corresponding to the number of the minimum value in the K1 and K2 sets so as to send the library position to a scheduling unit;
and the scheduling unit is used for distributing the storage position calculated by the processing unit to the goods and updating the first state value of the storage position.
7. A visual recognition-based in-and-out library management system, comprising:
a storage unit for storing a program comprising the steps of the visual identification-based warehousing and warehousing management method according to any one of claims 2 to 5, wherein the video camera, the visual identification unit, the processing unit and the scheduling unit are used for timely invoking and executing;
the camera is used for acquiring the warehouse area image frame to send to the visual identification unit;
the visual identification unit is used for marking a buffer area at the warehouse exit and entrance positions in the image frame and marking each warehouse position in the warehouse; numbering each library position, and acquiring position data in an image frame where each library position is located; an auxiliary area is arranged around each library position, and position data in an image frame where each auxiliary area is located is obtained; acquiring position data in the image frame where each cache region is located;
the visual identification unit is further used for giving an initial first state value to each storage position according to the storage position occupation condition; assigning a second state value to the affiliated area of each library bit; recording goods entering the entry cache region and acquiring position data in the image frame where the goods are located
；
A processing unit for counting the first state value of each storage position, screening out a storage position set E capable of receiving goods to calculate
And the KIou value K1 of each library position in the E, calculating the KIou value K2 of each library position in the E and the position data of the exit buffer area, and then calculating the library position corresponding to the number of the minimum value in the K1 and K2 sets so as to send the library position to a scheduling unit;
and the dispatching unit is used for allocating the storage position calculated by the processing unit to the goods, updating the first state value of the storage position, and simultaneously indicating the corresponding auxiliary area to enter the storage position for unloading according to the first rule and the second state value of the auxiliary area of the allocated storage position.
8. The system of claim 7, wherein the visual recognition unit is configured to set the library level with 4 attached areas, up, down, left, right, and second status values, and wherein the visual recognition unit is configured to set the second status values to include: an on state, an allowed on state, and an off state;
the first rule according to which the scheduling unit is based includes: s1, if one of 4 auxiliary areas of the library position is in an open state, the rest 3 areas are in an open allowing state; s2, if an auxiliary area corresponding to a certain auxiliary area is in an on state, the auxiliary area per se needs to be in an off state; s3, only distributing warehousing tasks to the auxiliary areas which are allowed to be in the on state, changing the allowed on state into the on state after distribution, and changing the allowed on state into the allowed on state after warehousing is finished; and S4, if the state of an auxiliary area in the same direction in the same row/column is in an on state, not allowing the same auxiliary area in the same row/column to be in an on state, and not allowing the opposite auxiliary area in the opposite row/column to be in an on state.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program performs the steps of the method according to any of claims 1 to 5.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310051384.9A CN115860642B (en) | 2023-02-02 | 2023-02-02 | Visual identification-based warehouse-in and warehouse-out management method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310051384.9A CN115860642B (en) | 2023-02-02 | 2023-02-02 | Visual identification-based warehouse-in and warehouse-out management method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115860642A true CN115860642A (en) | 2023-03-28 |
| CN115860642B CN115860642B (en) | 2023-05-05 |
Family
ID=85657460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310051384.9A Active CN115860642B (en) | 2023-02-02 | 2023-02-02 | Visual identification-based warehouse-in and warehouse-out management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115860642B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116880477A (en) * | 2023-07-07 | 2023-10-13 | 盐城工业职业技术学院 | AGV intelligent guiding system and method applied to warehouse logistics |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140277691A1 (en) * | 2013-03-15 | 2014-09-18 | Cybernet Systems Corporation | Automated warehousing using robotic forklifts |
| US20180029797A1 (en) * | 2016-07-28 | 2018-02-01 | X Development Llc | Inventory Management |
| WO2018189820A1 (en) * | 2017-04-12 | 2018-10-18 | 株式会社日立物流 | Article management assistance device, article management assistance system, and article management assistance method |
| CN108876241A (en) * | 2018-06-08 | 2018-11-23 | 四川木牛流马智能科技有限公司 | A kind of storage space identification and management system of view-based access control model |
| CN112149555A (en) * | 2020-08-26 | 2020-12-29 | 华南理工大学 | Multi-storage AGV tracking method based on global vision |
| CN112242940A (en) * | 2020-07-31 | 2021-01-19 | 广州微林软件有限公司 | Intelligent cabinet food management system and management method |
| WO2022014133A1 (en) * | 2020-07-16 | 2022-01-20 | 東京ロボティクス株式会社 | Mobile manipulator, method for controlling same, program |
| JP7036329B1 (en) * | 2021-05-17 | 2022-03-15 | 株式会社アラヤ | Worksite management system, worksite management method, and worksite management program |
| CN114367457A (en) * | 2022-01-15 | 2022-04-19 | 郭平芳 | E-commerce storage automatic sorting device based on visual identification technology |
| CN115601271A (en) * | 2022-11-29 | 2023-01-13 | 上海仙工智能科技有限公司（Cn） | Visual information anti-shaking method, warehouse location state management method and system |
-
2023
- 2023-02-02 CN CN202310051384.9A patent/CN115860642B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140277691A1 (en) * | 2013-03-15 | 2014-09-18 | Cybernet Systems Corporation | Automated warehousing using robotic forklifts |
| US20180029797A1 (en) * | 2016-07-28 | 2018-02-01 | X Development Llc | Inventory Management |
| WO2018189820A1 (en) * | 2017-04-12 | 2018-10-18 | 株式会社日立物流 | Article management assistance device, article management assistance system, and article management assistance method |
| CN108876241A (en) * | 2018-06-08 | 2018-11-23 | 四川木牛流马智能科技有限公司 | A kind of storage space identification and management system of view-based access control model |
| WO2022014133A1 (en) * | 2020-07-16 | 2022-01-20 | 東京ロボティクス株式会社 | Mobile manipulator, method for controlling same, program |
| CN112242940A (en) * | 2020-07-31 | 2021-01-19 | 广州微林软件有限公司 | Intelligent cabinet food management system and management method |
| CN112149555A (en) * | 2020-08-26 | 2020-12-29 | 华南理工大学 | Multi-storage AGV tracking method based on global vision |
| JP7036329B1 (en) * | 2021-05-17 | 2022-03-15 | 株式会社アラヤ | Worksite management system, worksite management method, and worksite management program |
| CN114367457A (en) * | 2022-01-15 | 2022-04-19 | 郭平芳 | E-commerce storage automatic sorting device based on visual identification technology |
| CN115601271A (en) * | 2022-11-29 | 2023-01-13 | 上海仙工智能科技有限公司（Cn） | Visual information anti-shaking method, warehouse location state management method and system |
Non-Patent Citations (5)
| Title |
|---|
| ?骥;韩巍;: "智能仓储物流机器人产业技术应用研究" * |
| ?骥;韩巍;: "智能仓储物流机器人产业技术应用研究", 现代信息科技 * |
| 苗中华;陈苏跃;何创新;金称雄;马世伟;徐双喜;: "基于3D视觉的青饲机拖车车斗自动识别与定位方法" * |
| 苗中华;陈苏跃;何创新;金称雄;马世伟;徐双喜;: "基于3D视觉的青饲机拖车车斗自动识别与定位方法", 农业机械学报 * |
| 黄海婷: "基于机器视觉的智能仓储系统" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116880477A (en) * | 2023-07-07 | 2023-10-13 | 盐城工业职业技术学院 | AGV intelligent guiding system and method applied to warehouse logistics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115860642B (en) | 2023-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101681450B (en) | Calculation processing apparatus and control method thereof | |
| US11052539B2 (en) | Method, server and storage medium for robot routing | |
| JP2022037223A (en) | Method for controlling route of robot, server and memory medium | |
| CN111103887B (en) | Multi-sensor-based multi-mobile-robot scheduling system design method | |
| Zhang et al. | Lift planning and optimization in construction: A thirty-year review | |
| CN115860642A (en) | Access management method and system based on visual identification | |
| EP2688021A2 (en) | Method for identifying the maximal packing density of shifting-tiles automated warehouses | |
| CN110232368B (en) | Lane line detection method, lane line detection device, electronic device, and storage medium | |
| Igwe et al. | Construction workspace management: Critical review and roadmap | |
| CN113219992A (en) | Path planning method and cleaning robot | |
| CN113848888B (en) | AGV forklift path planning method, device, equipment and storage medium | |
| CN115014328A (en) | Dynamic loading method, device, equipment and medium for grid map | |
| CN114611896A (en) | Robot task scheduling method, computer device and storage medium | |
| CN113592390A (en) | Warehousing digital twin method and system based on multi-sensor fusion | |
| CN113879751B (en) | Goods checking method and device for mobile operation machine and goods checking system | |
| Yu et al. | Virtual reality platform-based conceptual design and simulation of a hot cell facility | |
| JP2003141548A (en) | Three-dimensional labeling device and method | |
| CN115546237A (en) | Point cloud density adjusting method, electronic device and storage medium | |
| CN114442608B (en) | Office building logistics robot and control method thereof | |
| CN109670469A (en) | A kind of axis net generation method, electronic equipment and storage medium | |
| CN114169565A (en) | Asset goods allocation optimization method, device, equipment and storage medium | |
| KR20230067180A (en) | Method for arrangement and management blocks of the storage facility in the shipyard | |
| CN113205294A (en) | Cargo checking method and system | |
| Liang et al. | Progress-oriented waypoint sampling for unmanned ground vehicle mission planning | |
| CN115187176B (en) | Cargo transfer method and device for optimizing cargo storage space |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Visual Recognition Based Method and System for Inventory Management Effective date of registration: 20230828 Granted publication date: 20230505 Pledgee: Bank of Communications Ltd. Shanghai New District Branch Pledgor: Shanghai Xiangong Intelligent Technology Co.,Ltd. Registration number: Y2023310000491 |