A method and apparatus for air jet singulation of objects changing lanes

Abstract

The application aims to provide a method and device for jet sorting of lane changing objects. The application obtains time axis data by calculating time axis coordinates of objects in the last round of shooting. The information of objects in the last round is added to the time axis data, and the new time axis data is cached to obtain cached data. The objects in the current round of shooting are matched in the cached data. According to the matching result, the information of objects changing lanes in the cached data is counted to obtain a counting result. The original sorting time period corresponding to the time axis of the objects changing lanes is updated based on the counting result to obtain a new sorting time period. The objects changing lanes are sorted according to the new sorting time period. Thus, after the objects change lanes, the objects can be quickly and accurately positioned and effectively jet sorted.

Description

Technical Field

[0001] This application relates to the field of computers, and more particularly to a method and apparatus for jet sorting of objects for changing lanes. Background Technology

[0002] In production, traditional bottle sorting requires sorting and collection. However, after sorting, traditional bottle sorting units mostly store bottles temporarily in collection boxes. Once full, the collection is manually transported to the packaging unit. This process requires manual intervention, resulting in low material transfer efficiency and easy waste of manpower.

[0003] In addition, the bottles may change lanes on the conveyor belt, affecting the positioning of the bottles. The original air-jet sorting time is not accurate and cannot achieve effective air-jet sorting. Summary of the Invention

[0004] One objective of this application is to provide a method and apparatus for jet sorting of objects after they change lanes, thereby solving the problem in the prior art that jet sorting cannot be performed effectively and accurately after objects change lanes.

[0005] According to one aspect of this application, a method for jet sorting of objects for lane changing is provided, the method comprising:

[0006] Calculate the time axis coordinates of the objects from the previous round of photography to obtain time axis data;

[0007] The information of the objects from the previous round is added to the timeline data, and the new timeline data is cached to obtain cached data;

[0008] The objects captured in the current round are matched against the cached data. Based on the matching results, the information of objects that have changed lanes in the cached data is statistically analyzed to obtain the statistical results.

[0009] The sorting time period corresponding to the original time axis of the object that changed lanes is updated based on the statistical results to obtain the new sorting time period.

[0010] The objects that have changed lanes are sorted according to the new sorting time period.

[0011] Optionally, the information of the object in the previous round includes: the object's identification information and tag information.

[0012] Optionally, the objects captured in the current round are matched against the cached data, including:

[0013] Step 1: Find the object with the nearest center point to each object captured in the current round of photography in the cached data;

[0014] Step 2: Determine the distance between the object closest to the center point, and determine whether the object in the current scroll is a new object based on the preset scrolling threshold and the distance.

[0015] Repeat steps 1 and 2 until none of the remaining objects in the current wheel have found a cached object whose distance is less than a preset scrolling threshold.

[0016] Optionally, the method includes:

[0017] If no object in the current round of the photo is found in the cached data, then the object in the current round is determined to be a new object.

[0018] Information on objects that change lanes is collected based on the scrolling threshold.

[0019] Optionally, the sorting time period corresponding to the original timeline of the object that changed lanes is updated based on the statistical results, including:

[0020] Remove the sorting time segment corresponding to the original timeline based on the object information that has changed lanes;

[0021] Recalculate the time period corresponding to the time axis of the object that changed lanes, and merge the calculated time period into the sorting time period after removal.

[0022] Optionally, the sorting time segment corresponding to the original timeline can be removed based on the object information where the lane change occurred, including:

[0023] Based on the information of the object that changed lanes, search the cache data for the original timeline corresponding to the object from the previous round.

[0024] Remove the sorting time period corresponding to the previous round of objects on the original timeline.

[0025] Optionally, the method includes:

[0026] After the previous round of object sorting is completed, the time period of the expired timeline is counted;

[0027] Based on the additional object information, the types of sorted and unsorted objects are statistically analyzed.

[0028] Optionally, based on additional object information, the types of sorted and unsorted objects can be identified, including:

[0029] The number of object types is counted based on the object identification information in the attached object information.

[0030] Based on the object label information in the additional object information, we can count the sorted and unsorted object types in all quantities.

[0031] According to another aspect of this application, an air-jet sorting device for object rerouting is also provided, the device comprising:

[0032] One or more processors; and

[0033] A memory storing computer-readable instructions, which, when executed, cause the processor to perform operations as described above.

[0034] According to another aspect of this application, a computer-readable medium is also provided, having stored thereon computer-readable instructions that can be executed by a processor to implement the method as described above.

[0035] Compared with existing technologies, this application calculates the time axis coordinates of the objects captured in the previous round of photography to obtain time axis data; adds the information of the objects from the previous round to the time axis data and caches the new time axis data to obtain cached data; matches the objects captured in the current round of photography with the cached data, and statistically analyzes the information of objects that have changed lanes in the cached data based on the matching results to obtain statistical results; updates the sorting time period corresponding to the original time axis of the objects that have changed lanes based on the statistical results to obtain new sorting time periods; and sorts the objects that have changed lanes according to the new sorting time periods. Therefore, after an object changes lanes, it can be quickly and accurately repositioned and effectively sorted using air jets. Attached Figure Description

[0036] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0037] Figure 1 This diagram illustrates a flow chart of a jet sorting method for object rerouting according to one aspect of this application.

[0038] The same or similar reference numerals in the accompanying drawings represent the same or similar parts. Detailed Implementation

[0039] The present application will now be described in further detail with reference to the accompanying drawings.

[0040] In a typical configuration of this application, the terminal, the device of the service network, and the trusted party all include one or more processors (e.g., a central processing unit (CPU)), input / output interfaces, network interfaces, and memory.

[0041] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0042] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined in this article, computer-readable media do not include non-transitory computer-readable media, such as modulated data signals and carrier waves.

[0043] Figure 1 This diagram illustrates a flow chart of a jet sorting method for object rerouting according to one aspect of this application. The method includes steps S11 to S15, wherein...

[0044] Step S11: Calculate the time axis coordinates of the objects captured in the previous round of photography to obtain time axis data. Here, a rectangular photography area is set in the middle of the conveyor belt for transporting and sorting objects. A camera at the top continuously takes pictures of the conveyor belt at a certain frequency. The previous round of photography captures photos of the objects on the conveyor belt, and the next round of photography captures photos of the objects in the next round. Since the objects may change lanes, such as rolling, between the previous and next round of photography, the time axis coordinates of the objects captured in the previous round are calculated first to facilitate subsequent determination of whether a lane change has occurred. Calculating the time axis coordinates requires obtaining the pixel coordinates of the objects in the photos taken by the camera; then converting the pixel coordinates to physical coordinates. Because the objects are continuously photographed as they move on the conveyor belt, using standard physical coordinates would result in different or significantly different coordinate values ​​for the same object in multiple photographs. Therefore, this application uses a method of converting physical coordinates to custom coordinates to ensure that the coordinate values ​​of the same object are as consistent as possible in multiple photographs. The custom coordinates are time coordinates. The physical coordinate system is processed using timestamps and converted into a time coordinate system. Finally, the timeline data of the object after each round of shooting is obtained. The timeline data includes the object's timeline coordinates and the jet range. The jet range is the timeline time corresponding to the start of jetting and the timeline time corresponding to the end of jetting.

[0045] Specifically, the physical coordinates are processed to obtain the true physical coordinates of all points on the object's outline. A checkerboard calibration board is used to convert the pixel coordinates in the captured image into physical coordinates. A transformation matrix is ​​then used to adjust the physical coordinate system to match the object's direction of travel, ultimately obtaining the true physical coordinates of all points on the object's outline. The horizontal axis (x-axis) in the true physical coordinate system is changed to a timestamp in milliseconds. The 0th point of this timestamp is the standard timestamp (January 1, 1970, 00:00:00:00 milliseconds). The value x1 of this timestamp indicates that the point will pass the position of the jet valve at the end of the conveyor belt at time x1. The y-axis is changed to a scalar in terms of jet nozzle numbers. By calculating the number and interval of the jet nozzles on the object's original physical y-axis, the current coordinate corresponds to which jet nozzle; the jet nozzle number is the y-axis coordinate. Therefore, after capturing the previous object image, the timeline data of the previous object is calculated.

[0046] Next, in step S12, the information of the object from the previous round is added to the timeline data, and the new timeline data is cached to obtain cached data. Here, the information of the object from the previous round includes the object's identification information and tag information. Adding the object's information to the timeline data obtained in the previous step labels and identifies the timeline data, facilitating subsequent comparison to determine whether the object has changed lanes during the next round of photography. After the object's information is added to the timeline data and cached, the cache time is obtained, and subsequent comparisons can be performed by matching from the cached data.

[0047] Step S13: Match the objects captured by the current wheel in the cache data. Based on the matching results, statistically analyze the information of objects that have changed lanes in the cache data to obtain statistical results. Here, the objects on the conveyor belt are captured by the current wheel. Whether the objects in the current wheel have changed lanes needs to be compared with the information obtained by the previous wheel. That is, the time axis coordinates of the objects in the current wheel are also calculated. The time axis data is used to match the objects in the cache data. When matching, additional object information, namely label and identification information, is used to compare the objects that have changed lanes and then perform statistics to obtain statistical results of objects that have changed lanes and those that have not.

[0048] Step S14: Update the sorting time period corresponding to the original time axis of the object that changed lanes based on the statistical results to obtain the new sorting time period. Here, according to the statistical information of the object that changed lanes and the object that did not change lanes, update the original sorting time period corresponding to the object that changed lanes. That is, the sorting time period corresponding to the original time axis is the sorting time period on the time axis calculated by taking pictures in the previous round of the current round. The object should have been sorted, but it was not sorted because it changed lanes. Therefore, a new sorting time period needs to be recalculated in the current round.

[0049] Subsequently, in step S15, the objects that have changed lanes are sorted according to the new sorting time period. Here, after the pixel coordinates obtained from each round of photography are converted into custom time axis coordinates, the range covered on the time axis corresponding to each object to be sorted is calculated based on the actual physical coordinates of all points on the outline of the object to be sorted, the speed of the conveyor belt, and the position from the photography position to the jet valve. The jet time and jet position are calculated based on the range covered on the corresponding time axis, and the jet position and jet time are merged to obtain sorting time data. The jet valve is controlled by the sorting time data to perform jet sorting. When an object changes lanes, the sorting data needs to be updated. In the current round, the newly calculated sorting time is used to perform jet sorting on objects that have changed lanes compared to the previous round, and the sorting time data calculated in the original method is no longer used for sorting. For example, if object A changes lanes or rolls during the two rounds of photo taking, causing the sorting time data calculated after the previous round of photo taking to fail to be used for jet sorting of object A, and object A remains on the conveyor belt, then the sorting time period for object A is updated during the current round of photo taking, and the updated time period is used to perform jet sorting of object A.

[0050] In one embodiment of this application, the timeline data includes the start and end times of when the object should be blown. When additional data is added, such as object information, it is associated with the timeline data. For example, the original timeline data has a start and end time of (100, 200). Adding additional data such as the label "a certain trademark" and a unique ID is associated with the start and end time data (100, 200) of the timeline.

[0051] In one embodiment of this application, in step S13, a greedy algorithm and historical data matching are used each time newly identified information is acquired. The specific steps include: Step 1, searching for the object with the nearest center point in the cached data for each object captured in the current round of photography; Step 2, determining the distance between the object and the object with the nearest center point, and judging whether the object in the current round is a new object based on a preset scrolling threshold and the distance; repeating steps 1 and 2 until no cached object with a distance lower than the preset scrolling threshold is found for the remaining objects in the current round. Here, object positioning and identification are performed once for each photograph. In this embodiment, a frequency of 50-100 milliseconds can be used for continuous photography. Because the conveyor belt is moving, the same object may be in different positions in two photographs. Step 1, after calculating the timeline data of each object in a new round of photos, sets a static or dynamic scrolling threshold. For each object in the new round, searching for the object with the nearest center point in the cached data one by one. If the distance between the center points of the current object and the object matched in the cached data is less than the threshold, they are considered to be the same object. The center point is determined by a polygon formed by time segments within the object's timeline. An object occupies multiple time segments within the timeline, and these time segments can form a polygon. The center point of this polygon is used for matching. When targeting bottles, since they are mostly convex polygons, the center point can be calculated directly using the object's outer rectangular outline. When irregularly shaped objects appear, the aforementioned polygon center point is used for calculation. In a specific embodiment of this application, the scrolling threshold can be set to 30 millimeters. That is, if the center point distance of the same object exceeds 30 millimeters between two photos, it is considered a new object; otherwise, it is the same object. Step 2: Repeat the above steps until no cached object with a distance lower than the threshold is found for the remaining objects. These objects are then considered new objects. When a non-new object is found, its identification information (such as a unique ID) is modified to the unique ID of the old object for subsequent statistics.

[0052] In one embodiment of this application, the method includes: if no object is matched in the cached data within the current wheel's shooting range, the current wheel object is determined to be a new object; and information on objects that have changed lanes is statistically analyzed based on a scrolling threshold. Here, because the camera position is fixed and can only capture photos within a certain area, it is necessary to statistically analyze the data within the current wheel's shooting range. This involves checking whether the current wheel object within the current wheel's shooting range can be matched in the cached data. If no match is found, the current wheel object is considered a new object. A set scrolling threshold is used to statistically analyze which objects have changed lanes. For example, if objects A, B, and C are more than the scrolling threshold away from the center point, they are considered to have changed lanes. The method also includes statistically analyzing the labels, identifiers, and timeline data of objects A, B, and C.

[0053] In one embodiment of this application, the sorting time period corresponding to the original timeline is removed based on the information of the object that changed lanes; the time period corresponding to the timeline of the object that changed lanes is recalculated, and the calculated time period is merged into the sorting time period after removal. Specifically, based on the information of the object that changed lanes, the original timeline corresponding to the previous round of objects is searched in the cache data; the sorting time period corresponding to the previous round of objects on the original timeline is removed. Here, the sorting time period corresponding to the original timeline of the object that changed lanes is removed from the original timeline calculated in the previous round by using additional object information. Data in the statistically obtained cache data that does not match the current round of objects and is within the current round's shooting range is merged into the sorting time period corresponding to the original timeline, thus completing the timeline update. If the object has moved, the time period data in the timeline calculated in the previous shooting will be invalid, that is, when using the time period calculated in the previous round for jetting, the object cannot be sprayed. It is necessary to remove these invalid time period data in the timeline to ensure effective jetting and sorting of objects.

[0054] In one embodiment of this application, the original timeline corresponding to the previous round of objects is searched in the cache data based on the information of the object that changed lanes; the sorting time period corresponding to the previous round of objects on the original timeline is removed. Here, when an object changes lanes, the object information of the object is determined, that is, the object label and identification information, so as to find the sorting time period of the previous round of objects corresponding to the same object label and identification information in the cache data, and remove the sorting time period. For example, for a mineral water bottle with a certain trademark A placed diagonally, in step S1, the data calculated when taking the first picture may be: [{timeline 1 (first air nozzle), air time from 100ms to 150ms}, {timeline 2, air time from 100ms to 150ms}, {timeline 3, air time from 120ms to 170ms}, {timeline 4, air time from 120ms to 170ms}, {timeline 5, paint spraying time from 120ms to 170ms}]. In step S2, if the jetting occurred before the second photo capture, rolling two jet nozzle distances in the positive Y-axis direction of the custom timeline, then after the second photo capture and data calculation, it's necessary to first locate the data calculated in step S1 during the previous photo capture using the additional information within the timeline. Then, this data is removed through the timeline manager, and the currently calculated data is merged into the timeline manager, which internally handles the merging with other timeline information. Specifically, the jetting position and jetting time calculated after each round of photo capture are pushed into the timeline manager. This manager uses a linked list data structure to merge timeline data valve by valve, managing the timeline data for jetting sorting.

[0055] In one embodiment of this application, the method includes: calculating the time period of the expired timeline after the previous round of object sorting is completed; and calculating the sorted and unsorted object types based on additional object information. Specifically, the calculation of object types and lane-changing situations involves calculating the expired timeline after jet sorting using the jetting time calculated from the current round's photography. For example, if the timeline information is 100ms-200ms, and jet sorting should begin at 100ms and end at 200ms, but the current absolute time is already 300ms, then this time period is the expired time period. The additional object information is then used to calculate the sorted and unsorted object types. During the calculation, the number of object types is counted based on the object identification information in the additional object information; and the sorted and unsorted object types are counted based on the object label information in the additional object information. Here, based on the object identifiers (unique IDs) stored in the cached data, the number of unique objects can be counted, the quantity of each object type can be determined, and by using its tags such as "trademark" and the user-selected sorting strategy such as "select transparent plastic bottles," it can be determined whether the object has been sorted, thus obtaining the sorted and unsorted object types. For example, if the object types are determined to be two categories, with 10 trademarks A and 5 trademarks B, then by using the tags and sorting strategy, it can be determined that all trademarks A have been sorted, while trademarks B have not. When counting rolling events, a rolling threshold needs to be added, for example, a value of 250 mm. This means that if the center point distance of the same object differs by less than 250 mm between two photos, it is considered to have rolled, and the number and type of rolling objects can be counted.

[0056] Furthermore, embodiments of this application also provide a computer-readable medium storing computer-readable instructions that can be executed by a processor to implement the aforementioned jet sorting method for object rerouting.

[0057] In one embodiment of this application, an air jet sorting device for object rerouting is also provided, the device comprising:

[0058] One or more processors; and

[0059] A memory storing computer-readable instructions, which, when executed, cause the processor to perform operations as described above.

[0060] For example, computer-readable instructions, when executed, cause the one or more processors to:

[0061] Calculate the time axis coordinates of the objects from the previous round of photography to obtain time axis data;

[0062] The information of the objects from the previous round is added to the timeline data, and the new timeline data is cached to obtain cached data;

[0063] The objects captured in the current round are matched against the cached data. Based on the matching results, the information of objects that have changed lanes in the cached data is statistically analyzed to obtain the statistical results.

[0064] The sorting time period corresponding to the original time axis of the object that changed lanes is updated based on the statistical results to obtain the new sorting time period.

[0065] The objects that have changed lanes are sorted according to the new sorting time period.

[0066] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

[0067] It should be noted that this application can be implemented in software and / or a combination of software and hardware, for example, using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In one embodiment, the software program of this application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium, such as RAM memory, magnetic or optical drives, floppy disks, and similar devices. Furthermore, some steps or functions of this application can be implemented in hardware, for example, as circuitry that cooperates with a processor to perform the various steps or functions.

[0068] Furthermore, a portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. The program instructions invoking the methods of this application may be stored in a fixed or removable recording medium, and / or transmitted via data streams in broadcast or other signal carrying media, and / or stored in the working memory of a computer device operating according to the program instructions. Here, one embodiment of this application includes an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the apparatus is triggered to operate the methods and / or technical solutions based on the foregoing embodiments of this application.

[0069] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that it can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. Terms such as "first," "second," etc., are used to denote names and do not indicate any particular order.

Claims

1. A method for jet sorting of objects for channel changing, characterized in that, The method includes: Calculate the time axis coordinates of the objects from the previous round of photography to obtain time axis data; The information of the objects from the previous round is added to the timeline data, and the new timeline data is cached to obtain cached data; The process of matching the objects captured by the current wheel in the cached data includes: Step 1, searching for the object closest to the center point of each object captured by the current wheel in the cached data; Step 2, determining the distance between the object and the object closest to the center point, and judging whether the current wheel object is a new object based on a preset scrolling threshold and the distance. If no object is found in the cached data for the current wheel object within the current wheel's capture range, the current wheel object is determined to be a new object; Steps 1 and 2 are repeated until no cached object with a distance lower than the preset scrolling threshold is found for the remaining current wheel objects; and the information of objects that have changed lanes in the cached data is statistically analyzed based on the matching results to obtain statistical results. The sorting time period corresponding to the original time axis of the object that changed lanes is updated based on the statistical results to obtain the new sorting time period. The objects that have changed lanes are sorted according to the new sorting time period.

2. The method according to claim 1, characterized in that, The information of the object in the previous round includes: the object's identification information and label information.

3. The method according to claim 1, characterized in that, The sorting time periods corresponding to the original timelines of objects that have changed lanes are updated based on statistical results, including: Remove the sorting time segment corresponding to the original timeline based on the object information that has changed lanes; Recalculate the time period corresponding to the time axis of the object that changed lanes, and merge the calculated time period into the sorting time period after removal.

4. The method according to claim 3, characterized in that, Remove the sorting time segment corresponding to the original timeline based on the object information where the lane change occurred, including: Based on the information of the object that changed lanes, search the cache data for the original timeline corresponding to the object from the previous round. Remove the sorting time period corresponding to the previous round of objects on the original timeline.

5. The method according to claim 2, characterized in that, The method includes: After the previous round of object sorting is completed, the time period of the expired timeline is counted; Based on the additional object information, the types of sorted and unsorted objects are statistically analyzed.

6. The method according to claim 5, characterized in that, Based on the additional object information, the types of sorted and unsorted objects are identified, including: The number of object types is counted based on the object identification information in the attached object information. Based on the object label information in the additional object information, we can count the sorted and unsorted object types in all quantities.

7. A jet-air sorting device for object rerouting, characterized in that, The device includes: One or more processors; and A memory storing computer-readable instructions, which, when executed, cause the processor to perform the operations of the method as described in any one of claims 1 to 6.

8. A computer-readable medium having stored thereon computer-readable instructions that can be executed by a processor to implement the method as described in any one of claims 1 to 6.

Images