Anomaly detection method, device, equipment and medium

By obtaining the position information and area of ​​the target item in the conveyor belt image, using preset thresholds to determine whether there are missing packets and stacked packets during the transmission process, the detection inaccurate problem caused by failures of multi-moving components and multi-sensor components is solved, and the accuracy of item management is improved.

CN114359215BActive Publication Date: 2025-08-22ZHEJIANG DAHUA TECH CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202111665438.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-31
Publication Date
2025-08-22
Estimated Expiration
2041-12-31

AI Technical Summary

Technical Problem

In the prior art, any parts in multiple movable elements and multi-sensors fail, resulting in inaccurate detection of abnormalities during the transmission of items, affecting item management.

Method used

By obtaining the target item position information in the conveyor belt image, using preset thresholds to determine whether there are leaky packets and overlapping packets during the item transmission process, combining visual analysis algorithms to identify the item position and area, and update the threshold to improve detection accuracy.

Benefits of technology

It effectively avoids the impact of component failures, improves the accuracy of abnormal detection during item transmission, and ensures the accuracy of item management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114359215B_ABST
    Figure CN114359215B_ABST
Patent Text Reader

Abstract

The present invention discloses an anomaly detection method, apparatus, equipment and medium. In an embodiment of the present invention, whether there is an anomaly in the transmission of an item can be determined based on the first position information of the first target item and the second position information of the second target item obtained in an image containing a conveyor belt. This can effectively avoid the problem that the failure of any component in multiple active elements and multiple sensors cannot accurately determine whether the item is abnormal during transmission, thereby improving the accuracy of item management.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an anomaly detection method, device, equipment and medium. Background Art

[0002] With the rapid development of mechanization, conveyor belt-based item transmission can facilitate subsequent item statistics and item management. Among them, determining whether there are any abnormalities in the item transmission process is an important part of item management. For example, determining whether there are problems such as overlapping or missing items.

[0003] In the prior art, determining whether an item is abnormal during transport is typically done using a combination of multiple active components and sensors. These components include fixed brackets and movable arms, while the sensors include detectors and sensors. If any of these components or sensors malfunctions, accurate determination of whether an item is abnormal during transport cannot be made, impacting item management. Summary of the Invention

[0004] Embodiments of the present invention provide an anomaly detection method, apparatus, device, and medium to address the problem in the prior art that if a component failure occurs in multiple active elements and multiple sensors, the accuracy of determining whether an item is abnormal during transmission is reduced.

[0005] In a first aspect, the present invention provides an anomaly detection method, the method comprising:

[0006] Obtaining a currently detected image containing a conveyor belt, wherein the image contains an item transported on the conveyor belt;

[0007] If a first target object at a preset position on the conveyor belt exists in the image, obtaining first position information of the first target object;

[0008] Obtaining second position information of a second target object that is closest to the first target object and is located on the conveyor belt;

[0009] Based on the first location information, the second location information, and a preset threshold, it is determined whether there is a packet missing during the item transmission process.

[0010] Furthermore, the determining whether there is a packet missing during the item transmission process based on the first location information, the second location information, and a preset threshold includes:

[0011] Determining whether a difference between the first location information and the second location information is greater than a preset length threshold;

[0012] If so, it is determined that a packet is missed between the first target item and the second target item during the item transmission process;

[0013] If not, it is determined that no package is missed between the first target item and the second target item during the item transmission process.

[0014] Furthermore, the method further comprises:

[0015] It is determined whether there is overlapped packaging during the object transmission process according to the determined target area of ​​the first target object and a preset area threshold.

[0016] Furthermore, determining whether there is overlapped packages during the item transfer process based on the target area and a preset area threshold includes:

[0017] Determining whether the target area is greater than a preset area threshold;

[0018] If yes, it is determined that an item is overlapped with the first target item during the item transfer process;

[0019] If not, it is determined that no item overlaps with the first target item during the item transfer process.

[0020] Furthermore, after determining that a package is missing between the first target item and the second target item during the item transfer process, and before determining whether there is package overlap during the item transfer process based on the determined target area of ​​the first target item and a preset area threshold, the method further includes:

[0021] The preset area threshold is reduced, and the preset area threshold is updated using the reduced area threshold.

[0022] Furthermore, the method further comprises:

[0023] Identify the objects contained in the image, determine whether there is a third target object detected within a preset time length before the current detection time among the objects, and if so, determine that the third target object is blocking the packet during transmission.

[0024] Furthermore, the method further comprises:

[0025] For the currently detected image, overlapping or missing packets are detected, and the number of detected overlapping or missing packets is updated.

[0026] In a second aspect, the present invention further provides an anomaly detection device, comprising:

[0027] an acquisition module configured to obtain a currently detected image containing a conveyor belt, wherein the image contains items transported on the conveyor belt; if a first target item is located at a preset position on the conveyor belt in the image, obtain first position information of the first target item; and obtain second position information of a second target item that is closest to the first target item and is located on the conveyor belt;

[0028] The determination module is configured to determine whether there is a packet missing during the item transmission process based on the first location information, the second location information, and a preset threshold.

[0029] Furthermore, the determination module is specifically used to determine whether the difference between the first position information and the second position information is greater than a preset length threshold; if so, it is determined that a package is missed between the first target item and the second target item during the item transmission process; if not, it is determined that no package is missed between the first target item and the second target item during the item transmission process.

[0030] Furthermore, the determination module is further configured to determine whether there is overlapped packaging during the item transmission process based on the determined target area of ​​the first target item and a preset area threshold.

[0031] Furthermore, the determination module is specifically used to determine whether the target area is greater than a preset area threshold; if so, it is determined that there is an item overlapping with the first target item during the item transmission process; if not, it is determined that there is no item overlapping with the first target item during the item transmission process.

[0032] Furthermore, the device further comprises:

[0033] An updating module is configured to reduce the preset area threshold and update the preset area threshold using the reduced area threshold.

[0034] Furthermore, the determination module is also used to identify the objects contained in the image, and determine whether there is a third target object among the objects that can be detected within a preset time length before the current detection time. If so, it is determined that the third target object is blocked during the transmission process.

[0035] Furthermore, the updating module is further configured to detect overlapping or missing packets in the currently detected image and update the number of detected overlapping or missing packets.

[0036] In a third aspect, the present invention further provides an electronic device, which includes at least a processor and a memory, and the processor is used to implement the steps of any of the above-mentioned anomaly detection methods when executing a computer program stored in the memory.

[0037] In a fourth aspect, the present invention further provides a computer-readable storage medium storing a computer program, which implements the steps of any of the above-mentioned anomaly detection methods when executed by a processor.

[0038] In an embodiment of the present invention, a currently detected image including a conveyor belt is obtained, wherein the image includes items being transported on the conveyor belt; if a first target item located at a preset position on the conveyor belt is present in the image, first position information of the first target item is obtained; second position information of a second target item located closest to the first target item and located on the conveyor belt is obtained; and based on the first position information, the second position information, and a pre-set threshold, a determination is made as to whether a package has been missed during the item transmission process. In an embodiment of the present invention, the determination as to whether an anomaly exists in the item transmission process can be made based on the first position information of the first target item and the second position information of the second target item obtained in the image including the conveyor belt. This effectively avoids the problem of failure of any one component of multiple active elements or multiple sensors, which may result in an inability to accurately determine whether an item has an anomaly during transmission, thereby improving the accuracy of item management. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0040] Figure 1 A schematic diagram of a process of an anomaly detection method provided by an embodiment of the present invention;

[0041] Figure 2a A schematic diagram of an image including a conveyor belt obtained according to an embodiment of the present invention;

[0042] Figure 2b A schematic diagram of determining the distance between a first target object and a second target object in an image provided by an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of a target area of ​​a first target object in an image determined according to an embodiment of the present invention;

[0044] Figure 4a A schematic diagram showing two mud bags stacked in parallel provided by an embodiment of the present invention;

[0045] Figure 4b A schematic diagram showing two mud bags stacked non-parallel to each other provided by an embodiment of the present invention;

[0046] Figure 4c A schematic diagram showing the conversion of two mud bags stacked in a non-parallel manner to a parallel manner provided by an embodiment of the present invention;

[0047] Figure 5 A schematic diagram of a process for determining whether a courier is abnormal during transmission provided by an embodiment of the present invention;

[0048] Figure 6 A schematic structural diagram of an anomaly detection device provided by an embodiment of the present invention;

[0049] Figure 7 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] To make the objectives, technical solutions, and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings. It is apparent that the embodiments described are only some, not all, of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are intended to fall within the scope of protection of the present invention.

[0051] In an embodiment of the present invention, a currently detected image including a conveyor belt is obtained, wherein the image includes items transported on the conveyor belt; if a first target item located at a preset position on the conveyor belt exists in the image, first position information of the first target item is obtained; second position information of a second target item that is closest to the first target item and located on the conveyor belt is obtained; and based on the first position information, the second position information, and a pre-set threshold, it is determined whether there is a package missing during the item transmission process.

[0052] In order to accurately determine whether an item is abnormal during transportation and improve the accuracy of item management, embodiments of the present invention provide an abnormality detection method, apparatus, device, and medium.

[0053] Example 1:

[0054] Figure 1 A schematic diagram of a process of an anomaly detection method provided by an embodiment of the present invention includes the following steps:

[0055] S101: Obtaining a currently detected image containing a conveyor belt, wherein the image contains items transported on the conveyor belt.

[0056] The anomaly detection method provided in an embodiment of the present invention is applied to electronic devices such as image acquisition devices, terminals, PCs or servers, and the anomaly detection method is mainly applied to anomaly detection of items placed on a conveyor belt for transmission at set time intervals, and the specifications of each transmitted item are the same.

[0057] To determine whether an abnormality exists during the transport of an item currently under inspection, an embodiment of the present invention obtains an image of the conveyor belt being inspected. The image includes items being transported on the conveyor belt, such as mud bags, parcels, and food. The image may be obtained by the electronic device itself. If the electronic device is not an image capture device, the image may be captured by the image capture device and then sent to the electronic device.

[0058] S102: If a first target object located at a preset position on the conveyor belt exists in the image, first position information of the first target object is obtained.

[0059] In an embodiment of the present invention, since it takes a certain amount of time for an item to be transported along a conveyor belt of a certain length, that is, an item may appear simultaneously in multiple images containing the conveyor belt to be detected. Therefore, to avoid duplicate detection, a target image of the object located at a predetermined position on the conveyor belt can be selected from the multiple images to be detected. Based on this target image, it can be determined whether there are any abnormalities in the object's transport process. Specifically, it can be determined whether there are other items overlapping with the item during transport, or whether there are any missing packages between the item and its adjacent items.

[0060] Similarly, since the items on the conveyor belt are transported in real time, for any item being transported on the conveyor belt, the number of times the item appears at the preset position of the conveyor belt is only once. Therefore, it is also possible to first determine the items at the preset position of the conveyor belt in each image to be detected that includes the conveyor belt, and then determine whether there are any abnormalities in the transmission process of the item at the preset position of the conveyor belt or other items adjacent to it on the conveyor belt, which can also avoid the problem of repeated detection. The preset position can be the middle position of the conveyor belt contained in the image to be detected, or it can be the edge position of the outgoing item of the conveyor belt contained in the image to be detected. In an embodiment of the present invention, the preset position is the edge position of the outgoing item of the conveyor belt.

[0061] When determining whether an abnormality exists in the item transmission process, if a first target item is located at a preset position on the conveyor belt in the currently detected image of the conveyor belt, first position information of the first target item is obtained. The first position information may be coordinate information corresponding to an arbitrary set position of the item in the image, for example, the coordinate information corresponding to the center of the item in the image. Specifically, the coordinate information corresponding to an arbitrary set position of the item in the image may be determined based on a general target detection algorithm used in visual analysis. The process of determining the coordinate information corresponding to the set position of the item in the image based on the general target detection algorithm used in visual analysis is conventional technology and is not further described here.

[0062] S103: Obtain second position information of a second target object that is closest to the first target object and is located on the conveyor belt.

[0063] In order to determine whether there is a missing package between the items adjacent to the first target item, in an embodiment of the present invention, the second position information of the second target item that is closest to the first target item and located on the conveyor belt is obtained, wherein, if the first position information is the coordinate information corresponding to the center of the first target item in the image, then the second position information may also be the coordinate information corresponding to the center of the second target item in the image.

[0064] S104: Determine whether there is any packet missing during the item transmission process based on the first location information, the second location information, and a preset threshold.

[0065] After determining the first and second location information, it is possible to determine whether any packages were missed during the transport process based on the first and second location information and a pre-set threshold. For example, if a coordinate system is established using a conveyor belt transport method with the x-axis as the positive direction, the ratio of the first and second location information can be compared with a pre-set ratio threshold. If the ratio is greater than the pre-set ratio threshold, it is determined that any packages were missed between the first and second target items.

[0066] In the embodiment of the present invention, it is possible to determine whether there is an abnormality in the transmission of the item based on the first position information of the first target item and the second position information of the second target item in the image containing the conveyor belt. This can effectively avoid the problem of failure of any component in multiple active elements and multiple sensors, which may lead to the inability to accurately determine whether there is an abnormality in the transmission of the item, thereby improving the accuracy of item management.

[0067] Example 2:

[0068] To determine whether packets are missed during item transmission, based on the above embodiment, in an embodiment of the present invention, determining whether packets are missed during item transmission based on the first location information, the second location information, and a preset threshold includes:

[0069] Determining whether a difference between the first location information and the second location information is greater than a preset length threshold;

[0070] If so, it is determined that a packet is missed between the first target item and the second target item during the item transmission process;

[0071] If not, it is determined that no package is missed between the first target item and the second target item during the item transmission process.

[0072] In order to determine whether there is any packet leakage during the transmission of an item, in an embodiment of the present invention, the difference between the first position information of the first target item and the second position information of the second target item is first determined, and the distance between the first target item and the second target item is determined based on the difference, wherein the larger the difference, the larger the distance between the first target item and the second target item.

[0073] In an embodiment of the present invention, since the items are placed on the conveyor belt for transmission at set time intervals, and the specifications of each item are the same, the length interval between each two adjacent items transmitted on the conveyor belt is also the same. In order to determine whether there is a case of missing packages during the transmission of items, the difference can be compared with a pre-set length threshold to determine whether the difference is greater than the pre-set length threshold. If so, it means that the distance between the first target item and the second target item is too large, and therefore, there is a package missing between the first target item and the second target item. If the difference is not greater than the pre-set length threshold, it means that the distance between the first target item and the second target item is normal, and therefore, there is no package missing between the first target item and the second target item. Among them, the pre-set length threshold can be the length interval between each two adjacent items. Specifically, the pre-set length threshold can be set according to demand.

[0074] In the embodiment of the present invention, according to Determine the preset length threshold, wherein the is the length of the item, α is a preset distance coefficient, and the range of the distance coefficient is [1.2, 1.5]. The range of the distance coefficient takes into account the possibility that some items may be placed at an angle, v is the speed of the conveyor belt, and t is the interval time between items being placed on the conveyor belt.

[0075] Figure 2a A schematic diagram of an image including a conveyor belt obtained according to an embodiment of the present invention is provided. Figure 2b A schematic diagram of determining the distance between a first target object and a second target object in an image provided by an embodiment of the present invention is now directed to Figure 2a and Figure 2b To explain:

[0076] If the object being transported on the conveyor belt is a mud bag, Figure 2a In the embodiment, the mud bag D is located at a preset position on the conveyor belt. The first target object is the mud bag D, and the second target object that is closest to the first target object and located on the conveyor belt is the mud bag B.

[0077] The position information of mud bag D and mud bag B on the image is as follows Figure 2b As shown, the position information of the upper left vertex of the mud bag D is (DX1, DY1), the position information of the lower right vertex is (DX2, DY2), the position information of the upper left vertex of the mud bag B is (BX1, BY1), and the position information of the lower right vertex is (BX2, BY2). Therefore, the distance L between the mud bags D and B is BD= DX1-BX2.

[0078] In addition, the position information of the mud bag at any position on the conveyor belt of the image can also be obtained. For example, the position information of the upper left vertex of mud bag A is (AX1, AY1), and the position information of the lower right vertex is (AX2, AY2). And based on the position information of each mud bag, the distance between any two mud bags can also be determined. For example, the distance L between mud bag A and mud bag B is AB =BX1-AX2.

[0079] Example 3:

[0080] In order to determine whether there is overlapped packaging during the transport process, based on the above embodiments, in an embodiment of the present invention, the method further includes:

[0081] It is determined whether there is overlapped packaging during the object transmission process according to the determined target area of ​​the first target object and a preset area threshold.

[0082] In addition to package loss, other anomalies that may occur during the transport of items include package overlap. To determine whether there is package overlap during transport, in this embodiment of the present invention, the target area of ​​the first target item can also be obtained. The target area of ​​the first target item can be determined based on the corresponding coordinate information of each point on the edge of the first target item in the image.

[0083] Since the specifications of each object are the same and known, the larger the difference between the target area of ​​a certain object and the preset area threshold, the greater the possibility that the object is overlapped.

[0084] In order to determine whether there is overlapped packaging during the transport of items, based on the above embodiments, in an embodiment of the present invention, determining whether there is overlapped packaging during the transport of items based on the target area and a preset area threshold includes:

[0085] Determining whether the target area is greater than a preset area threshold;

[0086] If yes, it is determined that an item is overlapped with the first target item during the item transfer process;

[0087] If not, it is determined that no item overlaps with the first target item during the item transfer process.

[0088] Since the items transported on the conveyor belt are of the same specification, the area corresponding to each item in the image should also be the same and fixed. To determine whether any items are overlapped during transport, in an embodiment of the present invention, the target area of ​​the first target item is compared with a pre-set area threshold for the items to determine whether the target area is greater than the pre-set area threshold. The pre-set area threshold can be the area of ​​a standard item. Specifically, the pre-set area threshold is set as required. If the target area is greater than the pre-set area threshold, it indicates that at least two items are stacked together, that is, at least one item is overlapped with the first target item during transport. If the target area is not greater than the pre-set area threshold, it indicates that no items are overlapped, that is, no items are overlapped with the first target item during transport.

[0089] Figure 3 A schematic diagram of a target area of ​​a first target object in an image determined according to an embodiment of the present invention is now provided. Figure 3 To explain:

[0090] Take the mud bag as an example, the area of ​​the mud bag A is S A , the area of ​​the mud bag B is S B The area of ​​the overlapping mud bags C and D is S CD .

[0091] Figure 4a A schematic diagram showing two mud bags stacked in parallel provided by an embodiment of the present invention. Figure 4b A schematic diagram showing two mud bags stacked non-parallel to each other is provided in an embodiment of the present invention. Figure 4c A schematic diagram showing the transformation of two mud bags stacked non-parallel to parallel is provided in an embodiment of the present invention. Figure 4a 、 Figure 4b as well as Figure 4c Provide explanation.

[0092] Take two mud bags stacked together as an example. When mud bag A and mud bag B are stacked in parallel, Figure 4a As shown, the target area is the total area of ​​the two mud bags minus the overlapping area C, wherein the overlapping area C is the overlapping area of ​​the mud bag A and the mud bag B, and the overlapping area C is a rectangle.

[0093] Specifically, when determining the overlapping area C, if the coordinate information of the lower left corner of mud bag A is (x1, y1) and the coordinate information of the upper right corner is (x2, y2), and the coordinate information of the lower left corner of mud bag B is (x3, y3) and the coordinate information of the upper right corner is (x4, y4), based on the coordinate information of the lower left corner and upper right corner of mud bag A and the coordinate information of the lower left corner and upper right corner of mud bag B, it can be determined that the coordinate information of the lower left corner of the overlapping area C is (x2, y2) and the coordinate information of the upper right corner is (x3, y3). The area of ​​overlapping area C is S C =|(x3-x2)|×|(y3-y2)|.

[0094] Since the area of ​​each mud bag is known, if the area of ​​each mud bag is The target area is

[0095] When mud bag A and mud bag B are not stacked in parallel, Figure 4b As shown, in order to determine the target area, mud bag B can be rotated so that mud bag A and mud bag B are stacked in parallel, as shown in FIG. Figure 4c As shown, the overlapping area after rotation is approximated to the corresponding overlapping area when not rotated, wherein the overlapping area corresponding to the rotation is the real overlapping area of ​​mud bag A and mud bag B, wherein the process of determining the overlapping area after rotation is the same as Figure 4a The process of determining the overlapping area is the same as in , so it will not be described here.

[0096] Example 3:

[0097] In order to accurately determine whether there is overlap during the transport of items, based on the above embodiments, in an embodiment of the present invention, after determining that a package is missing between the first target item and the second target item during the transport of the items, and before determining whether there is overlap during the transport of the items based on the determined target area of ​​the first target item and a preset area threshold, the method further includes:

[0098] The preset area threshold is reduced, and the preset area threshold is updated using the reduced area threshold.

[0099] In an embodiment of the present invention, if a package is missing between the first target object and the second target object, it is very likely that the missing object between the first target object and the second target object will overlap with the first target object. Therefore, in order to more accurately determine whether an item overlaps with the first target item during the item transmission process, after determining that a package is missing between the first target item and the second target item during the item transmission process, and before determining whether an item overlaps with the first target item during the item transmission process, the preset area threshold is first reduced, and the preset area threshold is updated using the reduced area threshold. Subsequently, based on a comparison of the updated area threshold and the target area of ​​the first target object, it is determined whether an item overlaps with the first target item during the item transmission process.

[0100] Since the object missed between the first target object and the second target object may also overlap with the second target object, in an embodiment of the present invention, in order to improve the subsequent determination of whether there is overlap with the second target object during the item transmission process, when the second target object is subsequently located at a preset position of the conveyor belt, the area of ​​the second target object and the preset area threshold are used to determine whether there is overlap with the first target object during the item transmission process. The preset area threshold may also be the updated area threshold corresponding to the determination of whether there is overlap with the first target object.

[0101] Example 4:

[0102] In order to determine whether there is a packet blockage during the transmission of an item, based on the above embodiments, in an embodiment of the present invention, the method further includes:

[0103] Identify the objects contained in the image, determine whether there is a third target object detected within a preset time length before the current detection time among the objects, and if so, determine that the third target object is blocking the packet during transmission.

[0104] In this embodiment of the present invention, to determine whether there is a packet jam during transmission, all objects included in the currently detected image are identified, and a determination is made as to whether any of the objects contains a third target object detected within a preset time period before the current detection time. If so, this indicates that the third target object has been continuously transported on the conveyor belt from the preset time period before the current detection time to the current detection time, i.e., the third target object has been blocked during transmission. The preset time period can be, for example, one minute, and is specifically set as required.

[0105] In addition, to facilitate the management of abnormal items, each item is assigned corresponding identification information. The identification information can be a QR code or an identification value. The identification value is used to indicate the number of items placed on the conveyor belt. The identification value can be a number or a letter. For example, if an item is the first item placed on the conveyor belt, the identification value corresponding to the item can be 1 or A. In order to facilitate the subsequent identification of each item based on the obtained image containing each item, the corresponding QR code or identification value is affixed to the surface of each item.

[0106] Therefore, when abnormal items are identified, including blocked, missing or overlapped packages, identification information of the abnormal items can be reported to facilitate subsequent management of the abnormal items.

[0107] Furthermore, images corresponding to abnormalities encountered during the transport process can also be reported, such as images of blocked, missing, or overlapping packages. Since, in this embodiment of the present invention, the detection of abnormalities during transport is based on images of items located at the edge of the conveyor belt, images of items located in the middle of the conveyor belt can also be reported to facilitate determining when an abnormality occurred during transport.

[0108] For example, if the current detection image is image A, and it is determined that there is a missing package between item B located at the edge of the conveyor belt in image A and item C, which is closest to item B and located on the conveyor belt, then image B in which item B is located in the middle of the conveyor belt and image A will be reported at the same time.

[0109] In order to solve the problem of the third target item being blocked and avoid the subsequent transmission of items being affected by the third target item being blocked, an early warning can be issued after determining that the third target item is blocked. Specifically, the early warning can be based on voice information or text information.

[0110] If the identification information of an item is 3, and the item with identification information 3 is blocking the bag, then when issuing an early warning based on voice information, the voice message "The item with identification information 3 is blocking the bag, please deal with it in time" can be directly output; when issuing an early warning based on text information, the text "The item with identification information 3 is blocking the bag, please deal with it in time" can also be displayed on the display screen.

[0111] Example 5:

[0112] In order to count the number of overlapped packets or missed packets, based on the above embodiments, in an embodiment of the present invention, the method further includes:

[0113] For the currently detected image, overlapping or missing packets are detected, and the number of detected overlapping or missing packets is updated.

[0114] In an embodiment of the present invention, in order to facilitate subsequent management, statistics can be collected based on the overlapping and missing packages of all items transmitted within a set time length. Specifically, the overlapping and missing packages in all images that have been detected can be recorded in real time. Specifically, the number of overlapping packages or missing packages detected in the currently detected image can be updated.

[0115] The anomaly detection method provided by the embodiment of the present invention can be applied to multiple application fields such as express delivery, catering, building construction, transportation inventory, production lines, etc. The objects for anomaly detection can also be items purchased by users, food ingredients, cement, casting tools, etc.

[0116] Figure 5 A schematic diagram of a process for determining whether a courier is abnormal during transmission is provided in an embodiment of the present invention. Figure 5 Provide explanation.

[0117] Taking the express delivery as an example, first obtain a video stream of the express delivery on the conveyor belt. The video stream contains many images of the conveyor belt to be detected, and the images contain the items transported on the conveyor belt. For each image in the video stream, determine in turn whether there is an express delivery appearing at the edge of the conveyor belt's outgoing items. If there is an express delivery appearing at the edge of the conveyor belt's outgoing items, then based on the image, determine whether there are any missing or overlapping packages in the transmission process. If there is no express delivery appearing at the edge of the conveyor belt's outgoing items, then determine whether there is any express delivery that has not disappeared. In other words, identify the items contained in the image and determine whether there are any items that can be detected within a preset time length before the current detection time. If so, it is determined that the express delivery is blocked and an early warning is issued.

[0118] Based on the overlapped or missed packages detected in each image, the number of overlapped or missed packages detected is updated, and finally the normal express delivery situation and the abnormal express delivery situation are reported.

[0119] Example 6:

[0120] Figure 6 A schematic diagram of the structure of an anomaly detection device provided in an embodiment of the present invention, the device comprising:

[0121] An acquisition module 601 is configured to obtain a currently detected image containing a conveyor belt, wherein the image contains objects transported on the conveyor belt; if a first target object is located at a predetermined position on the conveyor belt in the image, obtain first position information of the first target object; and obtain second position information of a second target object located closest to the first target object and on the conveyor belt.

[0122] The determination module 602 is configured to determine whether there is a packet missing during the item transmission process based on the first location information, the second location information, and a preset threshold.

[0123] In one possible implementation, the determination module 602 is specifically configured to determine whether a difference between the first location information and the second location information is greater than a preset length threshold; if so, determining that a packet is missed between the first target item and the second target item during item transmission; if not, determining that no packet is missed between the first target item and the second target item during item transmission.

[0124] In a possible implementation, the determining module 602 is further configured to determine whether there is overlapped packaging during the object transmission process according to the determined target area of ​​the first target object and a preset area threshold.

[0125] In one possible implementation, the determination module 602 is specifically configured to determine whether the target area is greater than a preset area threshold; if so, determining that an item overlaps with the first target item during item transfer; if not, determining that an item does not overlap with the first target item during item transfer.

[0126] In a possible implementation, the device further includes:

[0127] The updating module 603 is configured to reduce the preset area threshold and update the preset area threshold using the reduced area threshold.

[0128] In a possible embodiment, the determination module 602 is further used to identify objects contained in the image, determine whether there is a third target object among the objects that was detected within a preset time length before the current detection time, and if so, determine that the third target object is blocked during the transmission process.

[0129] In a possible implementation, the updating module 603 is further configured to update the number of detected overlapping packets or missing packets if overlapping packets or missing packets are detected in the currently detected image.

[0130] Example 7:

[0131] On the basis of the above embodiments, an embodiment of the present invention further provides an electronic device, such as Figure 7 As shown, it includes: a processor 701 , a communication interface 702 , a memory 703 and a communication bus 704 , wherein the processor 701 , the communication interface 702 and the memory 703 communicate with each other via the communication bus 704 .

[0132] The memory 703 stores a computer program. When the program is executed by the processor 701, the processor 701 performs the following steps:

[0133] Obtaining a currently detected image containing a conveyor belt, wherein the image contains an item transported on the conveyor belt;

[0134] If a first target object at a preset position on the conveyor belt exists in the image, obtaining first position information of the first target object;

[0135] Obtaining second position information of a second target object that is closest to the first target object and is located on the conveyor belt;

[0136] Based on the first location information, the second location information, and a preset threshold, it is determined whether there is a packet missing during the item transmission process.

[0137] Furthermore, the processor 701 is also used to determine whether the difference between the first position information and the second position information is greater than a preset length threshold; if so, it is determined that a packet is missed between the first target item and the second target item during the item transmission process; if not, it is determined that no packet is missed between the first target item and the second target item during the item transmission process.

[0138] Furthermore, the processor 701 is further configured to determine whether there is overlapped packaging during the item transmission process according to the determined target area of ​​the first target item and a preset area threshold.

[0139] Furthermore, the processor 701 is also used to determine whether the target area is greater than a preset area threshold; if so, it is determined that there is an item overlapping with the first target item during the item transmission process; if not, it is determined that there is no item overlapping with the first target item during the item transmission process.

[0140] Furthermore, the processor 701 is further configured to reduce the preset area threshold, and use the reduced area threshold to update the preset area threshold.

[0141] Furthermore, the processor 701 is also used to identify the objects contained in the image, determine whether there is a third target object among the objects that can be detected within a preset time length before the current detection time, and if so, determine that the third target object is blocked during the transmission process.

[0142] Furthermore, the processor 701 is further configured to detect overlapping or missing packets in the currently detected image, and update the number of detected overlapping or missing packets.

[0143] The communication bus mentioned in the server above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0144] The communication interface 702 is used for communication between the electronic device and other devices.

[0145] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk memory. Alternatively, the memory may be at least one storage device located away from the processor.

[0146] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (NP), etc.; it can also be a digital signal processing processor (DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0147] Example 8:

[0148] Based on the above embodiments, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program executable by an electronic device. When the program is executed on the electronic device, the electronic device implements the following steps:

[0149] The memory stores a computer program, which, when executed by the processor, causes the processor to perform the following steps:

[0150] Obtaining a currently detected image containing a conveyor belt, wherein the image contains an item transported on the conveyor belt;

[0151] If a first target object at a preset position on the conveyor belt exists in the image, obtaining first position information of the first target object;

[0152] Obtaining second position information of a second target object that is closest to the first target object and is located on the conveyor belt;

[0153] Based on the first location information, the second location information, and a preset threshold, it is determined whether there is a packet missing during the item transmission process.

[0154] Furthermore, the determining whether there is a packet missing during the item transmission process based on the first location information, the second location information, and a preset threshold includes:

[0155] Determining whether a difference between the first location information and the second location information is greater than a preset length threshold;

[0156] If so, it is determined that a packet is missed between the first target item and the second target item during the item transmission process;

[0157] If not, it is determined that no package is missed between the first target item and the second target item during the item transmission process.

[0158] Furthermore, the method further comprises:

[0159] It is determined whether there is overlapped packaging during the object transmission process according to the determined target area of ​​the first target object and a preset area threshold.

[0160] Furthermore, determining whether there is overlapped packages during the item transfer process based on the target area and a preset area threshold includes:

[0161] Determining whether the target area is greater than a preset area threshold;

[0162] If yes, it is determined that an item is overlapped with the first target item during the item transfer process;

[0163] If not, it is determined that no item overlaps with the first target item during the item transfer process.

[0164] Furthermore, after determining that a package is missing between the first target item and the second target item during the item transfer process, and before determining whether there is package overlap during the item transfer process based on the determined target area of ​​the first target item and a preset area threshold, the method further includes:

[0165] The preset area threshold is reduced, and the preset area threshold is updated using the reduced area threshold.

[0166] Furthermore, the method further comprises:

[0167] Identify the objects contained in the image, determine whether there is a third target object detected within a preset time length before the current detection time among the objects, and if so, determine that the third target object is blocking the packet during transmission.

[0168] Furthermore, the method further comprises:

[0169] For the currently detected image, overlapping or missing packets are detected, and the number of detected overlapping or missing packets is updated.

[0170] In the embodiment of the present invention, it is possible to determine whether there is an abnormality in the transmission of the item based on the first position information of the first target item and the second position information of the second target item in the image containing the conveyor belt. This can effectively avoid the problem of failure of any component in multiple active elements and multiple sensors, which may lead to the inability to accurately determine whether there is an abnormality in the transmission of the item, thereby improving the accuracy of item management.

[0171] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0172] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0173] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0174] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more blocks. Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include such modifications and variations.

Claims

1. A method for detecting anomalies, characterized in that: The method comprises: Obtaining a currently detected image containing a conveyor belt, wherein the image contains an item transported on the conveyor belt; If a first target object at a preset position on the conveyor belt exists in the image, obtaining first position information of the first target object; Obtaining second position information of a second target object that is closest to the first target object and is located on the conveyor belt; Determining whether there is a packet missing during the item transmission process based on the first location information, the second location information, and a preset threshold; The method further comprises: determining whether there is overlapped packaging during the transportation of the items based on the determined target area of ​​the first target item and a preset area threshold; After determining that a package is missing between the first target item and the second target item during the item transfer process, and before determining whether there is a package overlap during the item transfer process based on the determined target area of ​​the first target item and a preset area threshold, the method further includes: The preset area threshold is reduced, and the preset area threshold is updated using the reduced area threshold.

2. The method according to claim 1, characterized in that The determining whether there is a packet missing during the item transmission process based on the first location information, the second location information, and a preset threshold includes: Determining whether a difference between the first location information and the second location information is greater than a preset length threshold; If so, it is determined that a packet is missed between the first target item and the second target item during the item transmission process; If not, it is determined that no package is missed between the first target item and the second target item during the item transmission process.

3. The method according to claim 1, characterized in that The determining, based on the target area and a preset area threshold, whether there is overlap during the item transfer process includes: Determining whether the target area is greater than a preset area threshold; If yes, it is determined that an item is overlapped with the first target item during the item transfer process; If not, it is determined that no item overlaps with the first target item during the item transfer process.

4. The method according to claim 1, wherein The method further comprises: Identify the objects contained in the image, determine whether there is a third target object detected within a preset time length before the current detection time among the objects, and if so, determine that the third target object is blocking the packet during transmission.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: For the currently detected image, overlapping or missing packets are detected, and the number of detected overlapping or missing packets is updated.

6. An abnormality detection device, characterized in that: The device comprises: an acquisition module configured to obtain a currently detected image containing a conveyor belt, wherein the image contains items transported on the conveyor belt; if a first target item is located at a preset position on the conveyor belt in the image, obtain first position information of the first target item; and obtain second position information of a second target item located closest to the first target item and on the conveyor belt; a determination module, configured to determine whether there is a packet missing during the item transmission process based on the first location information, the second location information, and a preset threshold; The determining module is further configured to determine whether there is any overlap during the transport of items based on the determined target area of ​​the first target item and a preset area threshold; An updating module is configured to reduce the preset area threshold and update the preset area threshold using the reduced area threshold.

7. An electronic device, characterized in that: The electronic device comprises a processor, and the processor is configured to implement the steps of the method according to any one of claims 1 to 5 when executing a computer program stored in a memory.

8. A computer-readable storage medium, characterized in that The device stores a computer program, which implements the steps of the method according to any one of claims 1 to 5 when executed by a processor.

Citation Information

Patent Citations

  • Working condition detecting method, device and system

    CN101738224A

  • Conveying line bag blockage detecting method and device

    CN106429305A

  • Method of identifying key time point in video, computer equipment and storage medium

    CN108810620A

  • Material conveying control method

    CN112691949A