An object culling method, system, apparatus, control device and storage medium

Abstract

Embodiments of the present application provide an object rejection method, system, device, control equipment and storage medium, and relate to the technical field of production automation. The method comprises: in the process of transmitting the object in a preset transmission direction through a transmission line, acquiring an image of the object located in a specified shooting area on the current transmission line to obtain a current to-be-detected image; detecting the current to-be-detected image for a defective object to obtain a pixel coordinate of the defective object in the transmission direction as a to-be-detected pixel coordinate; determining a preset pixel coordinate interval to which the to-be-detected pixel coordinate belongs among a plurality of preset pixel coordinate intervals in the transmission direction as a first pixel coordinate interval; and controlling a rejection mechanism to reject the object in a specified rejection area after a transmission time corresponding to the first pixel coordinate interval, thereby improving the efficiency of object rejection, saving the computing resources of the control equipment, and avoiding execution errors of the rejection mechanism.

Description

Technical Field

[0001] This application relates to the field of production automation technology, and in particular to an object elimination method, system, apparatus, control device, and storage medium. Background Technology

[0002] In the field of production automation, conveyor lines can be used to transport objects, such as raw materials used in production or finished products manufactured by machines. As the conveyor line moves, it passes through a detection area; that is, the objects transported on the conveyor line pass through this detection area. When an object passes through the detection area, it can be checked to determine if it is defective. For example, the object could be a dumpling; defective dumplings could be dumplings with exposed filling or dumplings containing foreign objects such as hair.

[0003] In related technologies, multiple technicians can be present in the inspection area to manually inspect objects passing through the area, identifying and removing defective objects. However, manually identifying defective objects is inefficient, leading to inefficient object removal. Summary of the Invention

[0004] The purpose of this application is to provide an object eviction method, system, apparatus, control device, and storage medium to improve the efficiency of object eviction, save the computing resources of the control device, and avoid errors in the execution of the eviction mechanism. The specific technical solution is as follows:

[0005] In a first aspect of the embodiments of this application, an object culling method is provided, the method comprising:

[0006] During the process of transmitting an object through a transmission line in a preset transmission direction, an image located within a specified shooting area of ​​the image acquisition device on the current transmission line is acquired to obtain the current image to be detected;

[0007] Defect objects are detected in the current image to be detected, and the pixel coordinates of the defect objects in the current image to be detected in the transmission direction are obtained as the pixel coordinates to be detected.

[0008] In the multiple preset pixel coordinate intervals in the transmission direction, the preset pixel coordinate interval to which the pixel coordinate to be detected belongs is determined as the first pixel coordinate interval; wherein, the multiple preset pixel coordinate intervals represent: multiple adjacent and non-overlapping intervals obtained by dividing the second pixel coordinate interval corresponding to the specified shooting area in the transmission direction, and the physical length represented by each preset pixel coordinate interval is not greater than the physical length of the specified rejection area of ​​the rejection mechanism in the transmission direction.

[0009] After the transmission time corresponding to the first pixel coordinate interval, the rejection mechanism is controlled to reject objects within the specified rejection area; wherein, the transmission time corresponding to the first pixel coordinate interval represents the time required for the transmission line to transmit an object from the physical location corresponding to the first pixel coordinate interval to the specified rejection area.

[0010] Optionally, before determining the preset pixel coordinate interval to which the coordinates of the pixel to be detected belong as the first pixel coordinate interval among multiple preset pixel coordinate intervals in the transmission direction, the method further includes:

[0011] The second pixel coordinate interval is divided according to the reference pixel length to obtain multiple adjacent and non-overlapping pixel coordinate intervals, which are referred to as the multiple preset pixel coordinate intervals; wherein, the physical length represented by the reference pixel length is not greater than the physical length of the specified rejection region in the transmission direction.

[0012] Optionally, the transmission duration corresponding to a preset pixel coordinate interval represents the ratio of the transmission physical distance corresponding to the preset pixel coordinate interval to the transmission speed of the transmission line; the transmission physical distance corresponding to the preset pixel coordinate interval represents the physical distance between the physical location corresponding to the center point of the preset pixel coordinate interval and the center point of the specified rejection area in the transmission direction.

[0013] Optionally, the transmission physical distance corresponding to a preset pixel coordinate range is obtained based on the following method:

[0014] Calculate the pixel distance between the center point of the preset pixel coordinate interval and the specified pixel coordinate in the transmission direction; wherein, in the second pixel coordinate interval, the physical location corresponding to the specified pixel coordinate is closest to the physical distance between the specified rejection area and the specified rejection area in the transmission direction;

[0015] Based on the mapping relationship between pixel length and physical length when the image acquisition device acquires the image, the pixel distance is converted to obtain the first physical distance;

[0016] The sum of the first physical distance and the second physical distance is calculated to obtain the transmission physical distance corresponding to the preset pixel coordinate interval; wherein, the second physical distance represents the physical distance between the physical position corresponding to the specified pixel coordinate and the center point of the specified rejection area in the transmission direction.

[0017] Optionally, among multiple preset pixel coordinate intervals in the transmission direction, the preset pixel coordinate interval to which the coordinates of the pixel to be detected belong is determined as the first pixel coordinate interval, including:

[0018] For each defective object in the current image to be detected, if the defective object does not exist in the historically acquired images to be detected, the preset pixel coordinate interval to which the defective object belongs is determined from multiple preset pixel coordinate intervals in the transmission direction, and is used as the first pixel coordinate interval.

[0019] In a second aspect of this application, an object culling system is provided, the object culling system including an image acquisition device, a control device, a culling mechanism, and a transmission line, wherein:

[0020] The transmission line is used to transmit objects in a preset transmission direction;

[0021] The image acquisition device is used to acquire images located within a designated shooting area on the transmission line to obtain the image to be detected;

[0022] The control device is used to execute the object removal method described in any of the first aspects above.

[0023] The rejection mechanism is used to reject objects within a designated rejection area under the control of the control device.

[0024] Optionally, the control device is specifically used to send rejection instructions to the rejection mechanism;

[0025] The removal mechanism is specifically used to remove objects within a specified removal area when the removal instruction is received.

[0026] In a third aspect of this application, an object culling apparatus is provided, the apparatus comprising:

[0027] The image acquisition module is used to acquire an image located within a specified shooting area of ​​the image acquisition device on the current transmission line during the transmission of an object in a preset transmission direction, thereby obtaining the current image to be detected.

[0028] The detection module is used to detect defect objects in the current image to be detected and obtain the pixel coordinates of the defect objects in the current image to be detected in the transmission direction, which are used as the pixel coordinates to be detected.

[0029] The interval determination module is used to determine, among multiple preset pixel coordinate intervals in the transmission direction, the preset pixel coordinate interval to which the coordinates of the pixel to be detected belong, as the first pixel coordinate interval; wherein, the multiple preset pixel coordinate intervals represent: multiple adjacent and non-overlapping intervals obtained by dividing the second pixel coordinate interval corresponding to the specified shooting area in the transmission direction, and the physical length represented by each preset pixel coordinate interval is not greater than the physical length of the specified rejection area of ​​the rejection mechanism in the transmission direction.

[0030] The control module is used to control the rejection mechanism to reject objects within the specified rejection area after the transmission time corresponding to the first pixel coordinate interval has elapsed; wherein, the transmission time corresponding to the first pixel coordinate interval represents the time required for the transmission line to transmit an object from the physical location corresponding to the first pixel coordinate interval to the specified rejection area.

[0031] Optionally, the device further includes:

[0032] The segmentation module is used to determine, before the interval determination module performs the operation of multiple preset pixel coordinate intervals in the transmission direction, the preset pixel coordinate interval to which the coordinates of the pixel to be detected belong, as the first pixel coordinate interval, and then divides the second pixel coordinate interval according to the reference pixel length to obtain multiple adjacent and non-overlapping pixel coordinate intervals, which are used as the multiple preset pixel coordinate intervals; wherein, the physical length represented by the reference pixel length is not greater than the physical length of the specified rejection region in the transmission direction.

[0033] Optionally, the transmission duration corresponding to a preset pixel coordinate interval represents the ratio of the transmission physical distance corresponding to the preset pixel coordinate interval to the transmission speed of the transmission line; the transmission physical distance corresponding to the preset pixel coordinate interval represents the physical distance between the physical location corresponding to the center point of the preset pixel coordinate interval and the center point of the specified rejection area in the transmission direction.

[0034] Optionally, the transmission physical distance corresponding to a preset pixel coordinate range is obtained based on the following method:

[0035] Calculate the pixel distance between the center point of the preset pixel coordinate interval and the specified pixel coordinate in the transmission direction; wherein, in the second pixel coordinate interval, the physical location corresponding to the specified pixel coordinate is closest to the physical distance between the specified rejection area and the specified rejection area in the transmission direction;

[0036] Based on the mapping relationship between pixel length and physical length when the image acquisition device acquires the image, the pixel distance is converted to obtain the first physical distance;

[0037] The sum of the first physical distance and the second physical distance is calculated to obtain the transmission physical distance corresponding to the preset pixel coordinate interval; wherein, the second physical distance represents the physical distance between the physical position corresponding to the specified pixel coordinate and the center point of the specified rejection area in the transmission direction.

[0038] Optionally, the interval determination module is specifically used for:

[0039] For each defective object in the current image to be detected, if the defective object does not exist in the historically acquired images to be detected, the preset pixel coordinate interval to which the defective object belongs is determined from multiple preset pixel coordinate intervals in the transmission direction, and is used as the first pixel coordinate interval.

[0040] In a fourth aspect of this application, a control device is provided, comprising:

[0041] Memory, used to store computer programs;

[0042] When a processor executes a program stored in memory, it implements the object eviction method described in any of the first aspects above.

[0043] In a fifth aspect of the embodiments of this application, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when the computer program is executed by a processor, it implements the object culling method described in any of the first aspects above.

[0044] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the object culling methods described above.

[0045] This application provides an object rejection method. During the transmission of an object via a transmission line in a preset transmission direction, a control device acquires an image located within a designated shooting area of ​​an image acquisition device on the current transmission line, obtaining the current image to be detected. The method then detects defective objects in the current image to be detected, obtaining the pixel coordinates of the defective objects in the transmission direction, which are used as the pixel coordinates to be detected. Among multiple preset pixel coordinate intervals in the transmission direction, the preset pixel coordinate interval to which the pixel coordinates to be detected belong is determined, serving as the first pixel coordinate interval. The multiple preset pixel coordinate intervals represent multiple adjacent and non-overlapping intervals obtained by dividing the second pixel coordinate interval corresponding to the designated shooting area in the transmission direction, and the physical length represented by each preset pixel coordinate interval is not greater than the physical length of the designated rejection area of ​​the rejection mechanism in the transmission direction. After the transmission time corresponding to the first pixel coordinate interval, the rejection mechanism is controlled to reject objects within the designated rejection area. The transmission time corresponding to the first pixel coordinate interval represents the time required for the transmission line to transmit an object from the physical position corresponding to the first pixel coordinate interval to the designated rejection area.

[0046] Based on the above processing, the control device can identify defective objects in the current image to be inspected, and after the transmission time corresponding to the first pixel coordinate interval to which the defective object belongs, control the removal mechanism to remove it, thus eliminating defective objects on the transmission line. This eliminates the need for manual inspection by technicians, improving the efficiency of object removal. Furthermore, since the control device controls the removal mechanism based on the transmission time corresponding to the first pixel coordinate interval, when multiple defective objects belong to the same first pixel coordinate interval, the control device only needs to control the removal mechanism to perform one removal operation based on the transmission time corresponding to that first pixel coordinate interval. This eliminates the need for multiple unnecessary removal operations, saving the control device's computational resources. Additionally, since each removal operation takes time, performing only one removal operation for multiple defective objects avoids multiple removal operations within a short period, preventing errors in the removal mechanism's execution.

[0047] Of course, implementing any product or method of this application does not necessarily require achieving all of the advantages described above at the same time. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other embodiments can be obtained based on these drawings.

[0049] Figure 1 This is a first schematic diagram of the object removal method provided in the embodiments of this application;

[0050] Figure 2 This is a first flowchart of an object removal method provided in an embodiment of this application;

[0051] Figure 3 A second schematic diagram of the object elimination method provided in the embodiments of this application;

[0052] Figure 4 A second flowchart of the object removal method provided in the embodiments of this application;

[0053] Figure 5 A structural diagram of the object rejection device provided in the embodiments of this application;

[0054] Figure 6 This is a structural diagram of a control device provided in an embodiment of this application. Detailed Implementation

[0055] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art based on this application are within the scope of protection of this application.

[0056] In related technologies, conveyor lines can be used to transport objects in the field of production automation. When objects transported on the conveyor line pass through an inspection area, multiple technicians in the inspection area can manually inspect the objects to identify and remove defective objects. However, manually identifying defective objects is inefficient, resulting in low object removal efficiency.

[0057] To address the aforementioned problems, embodiments of this application provide an object culling method. The following, in conjunction with... Figure 1 This application will be described in detail. Figure 1 This is a first schematic diagram of the object removal method provided in this application embodiment. The object removal method provided in this application embodiment is applied to a control device 105, which can be a server communicating with the image acquisition device 103 and the removal mechanism 106.

[0058] Figure 1 In the transmission line 101, the transmission direction is horizontal to the right, and multiple objects 102 are placed on the transmission line 101.

[0059] In a practical scenario, the image acquisition device 103 can be located directly above the transmission line 101, with the shooting direction pointing vertically downwards towards the transmission line 101. The defect detection area 104 is the designated shooting area of ​​the image acquisition device 103. Based on the object removal method provided in this application, defect objects are detected for each object within the designated shooting area. The image acquisition device 103 can be a camera.

[0060] According to the transmission direction of transmission line 101, the rejection mechanism 106 is located downstream of image acquisition device 103. The defect rejection area 107 is the designated rejection area of ​​rejection mechanism 106, and defective objects within the designated rejection area are rejected based on the object rejection method provided in this application.

[0061] During the transmission of object 102 along transmission line 101 in a preset transmission direction, image acquisition device 103 acquires images located within defect detection area 104 on transmission line 101, obtains the current image to be detected, and sends the current image to be detected to control device 105. Control device 105 detects defective objects in the current image to be detected according to the object removal method provided in this embodiment, and controls removal mechanism 106 to remove objects 102 within defect removal area 107 based on the detection results. This eliminates the need for manual inspection by technicians to remove defective objects, improving object removal efficiency, saving computing resources of control equipment, and preventing errors in the removal mechanism.

[0062] See Figure 2 , Figure 2 A first flowchart of the object removal method provided in this application embodiment, the method includes the following steps:

[0063] S201: During the process of transmitting the object through the transmission line in a preset transmission direction, the image located in the specified shooting area of ​​the image acquisition device on the current transmission line is acquired to obtain the current image to be detected.

[0064] S202: Detect defect objects in the current image to be detected, and obtain the pixel coordinates of the defect objects in the current image to be detected in the transmission direction, which are used as the pixel coordinates to be detected.

[0065] S203: Among multiple preset pixel coordinate intervals in the transmission direction, determine the preset pixel coordinate interval to which the coordinates of the pixel to be detected belong, and use it as the first pixel coordinate interval.

[0066] Among them, multiple preset pixel coordinate intervals refer to multiple adjacent and non-overlapping intervals obtained by dividing the second pixel coordinate interval corresponding to the specified shooting area in the transmission direction, and the physical length represented by each preset pixel coordinate interval is not greater than the physical length of the specified rejection area of ​​the rejection mechanism in the transmission direction.

[0067] S204: After the transmission time corresponding to the first pixel coordinate interval, control the elimination mechanism to eliminate objects within the specified elimination area.

[0068] The transmission time corresponding to the first pixel coordinate interval represents the time required for the transmission line to transmit an object from the physical location corresponding to the first pixel coordinate interval to the specified culling area.

[0069] Based on the object removal method provided in this application embodiment, a control device can identify defective objects in the current image to be detected. After the transmission time corresponding to the first pixel coordinate interval to which the defective object belongs, the removal mechanism is controlled to remove the defective objects on the transmission line. This eliminates the need for manual inspection by technicians, improving the efficiency of object removal. Furthermore, since the control device controls the removal mechanism based on the transmission time corresponding to the first pixel coordinate interval, when the pixel coordinates of multiple defective objects belong to the same first pixel coordinate interval, the control device only needs to control the removal mechanism to perform one removal operation based on one transmission time corresponding to the first pixel coordinate interval. This eliminates the need for multiple unnecessary removal operations, saving the control device's computational resources. Additionally, since each removal operation takes time, performing only one removal operation for multiple defective objects avoids multiple removal operations within a short period, preventing errors in the removal mechanism's execution.

[0070] For step S201, the transmission line can be a conveyor belt driven by a power source. Objects to be transmitted can be placed on the conveyor belt; the power output from the power source can drive the conveyor belt to move, thereby moving the objects placed on the conveyor belt and realizing the transmission of objects via the transmission line. The direction perpendicular to the transmission direction of the transmission line in the horizontal plane can be called the vertical direction; the physical length of the transmission line along the vertical direction can be called the transmission line width.

[0071] The objects to be transmitted are related to the business requirements of the application scenario. For example, if the business requirement indicates that the transmission line is a dumpling production line, the objects to be transmitted are dumplings; if the business requirement indicates that the transmission line is a metal parts handling line, the objects transmitted on the transmission line are metal parts, such as nuts.

[0072] The area within the field of view of the image acquisition device is the designated shooting area, which can be a rectangular area. The transmission line passes through the designated shooting area during object transmission. The transmission direction is perpendicular to one boundary of the designated shooting area; this perpendicular boundary can be called the first area boundary, and the corresponding boundary parallel to the transmission direction can be called the second area boundary. The physical width of the first area boundary is not less than the width of the transmission line. In this way, along the vertical direction, the image acquired by the image acquisition device includes the entire transmission line, preventing objects on the transmission line from being missed, thus avoiding missed detection of defective objects and improving the accuracy of object rejection.

[0073] In some embodiments, when the image acquisition device is located to the side of the transmission line, the objects in the acquired image may be distorted, resulting in low effectiveness of subsequent object removal based on the acquired image. However, when the image acquisition device is located directly above the transmission line, with the shooting direction vertically downwards towards the transmission line, the distortion of objects in the acquired image is smaller, and the effectiveness of subsequent object removal based on the acquired image is higher. Therefore, to improve the effectiveness of object removal, the image acquisition device can be positioned directly above the transmission line.

[0074] After the image acquisition equipment is installed, its shooting direction and focal length can be adjusted to change the field of view, i.e., to adjust the designated shooting area. For example, the shooting direction can be adjusted to point vertically downwards towards the transmission line; the physical width of the first boundary of the designated shooting area can be set to be no less than the width of the transmission line, etc.

[0075] During the transmission of objects along the transmission line in a preset direction, the image acquisition device can periodically acquire images located within a designated shooting area on the transmission line to obtain the image to be inspected. The image to be inspected may include objects, which can be categorized as normal objects or defective objects. The distinction between normal and defective objects can be determined based on actual business requirements. For example, a defective object can be an object that does not meet preset product standards. For instance, when the object is a dumpling, defective objects could be: dumplings with exposed filling, dumplings with missing dough, dumplings containing foreign objects such as hair, etc.; when the object is a nut, defective objects could be: nuts with missing corners, nuts with peeling paint, cracked nuts, etc.

[0076] The acquisition cycle of the image acquisition device can be set according to actual business needs. For example, the ratio of the physical length of the second region boundary to the transmission speed (which can be called the first ratio) can be calculated and used as the acquisition cycle. Alternatively, to avoid missed detections and improve the accuracy of object removal, the frequency of acquiring the images to be detected can be increased so that there are overlapping image areas between two adjacent images to be detected. For example, the product of the first ratio and a first preset coefficient can be calculated and used as the acquisition cycle. The first preset coefficient can be a positive number less than 1.

[0077] In step S202, after acquiring the current image to be detected, the control device can use a target detection algorithm to detect defective objects in the current image to obtain the pixel coordinates of the defective object in the transmission direction. For example, the control device can use a pre-trained defective object detection model to process the current image to be detected, obtaining the position of the minimum bounding rectangle of the defective object in the current image. Then, based on the position of the minimum bounding rectangle in the current image, the pixel coordinates of the defective object in the transmission direction are determined.

[0078] For example, a defect detection model can be trained based on sample images containing defective objects.

[0079] The position of a minimum bounding rectangle in the image to be detected can be represented by the pixel coordinates of the center point of the minimum bounding rectangle in the image to be detected; or, it can be represented by the pixel coordinates of the four vertices of the minimum bounding rectangle in the image to be detected.

[0080] The boundary of the first region of the specified shooting area is perpendicular to the transmission direction, and the edge of the image to be detected corresponding to the boundary of the first region can be called the first image edge; the boundary of the second region of the specified shooting area is parallel to the transmission direction, and the edge of the image to be detected corresponding to the boundary of the second region can be called the second image edge.

[0081] Since the boundary of the second region is parallel to the transmission direction, the edge of the second image is also parallel to the transmission direction of the transmission lines in the image to be detected. Accordingly, the pixel coordinates to be detected for each pixel in the image to be detected are: the pixel coordinates of that pixel on the pixel coordinate axis corresponding to the edge of the second image. For example, if a pixel coordinate system is constructed in the image to be detected with the edge of the second image as the x-axis and the edge of the first image as the y-axis, then the x-value of the pixel coordinates of each pixel in the image to be detected is the pixel coordinates to be detected for that pixel.

[0082] In step S203, after obtaining the pixel coordinates to be detected of the defective object, the control device determines the preset pixel coordinate interval to which the pixel coordinates to be detected belong from multiple preset pixel coordinate intervals, and uses it as the first pixel coordinate interval.

[0083] In some embodiments, before step S203, the method further includes the following steps: dividing the second pixel coordinate interval according to the reference pixel length to obtain multiple adjacent and non-overlapping pixel coordinate intervals, which serve as multiple preset pixel coordinate intervals.

[0084] The physical length represented by the reference pixel length is no greater than the physical length of the specified culling region in the transmission direction.

[0085] Once the installation location, shooting direction, and focal length of the image acquisition device are fixed, the designated shooting area of ​​the image acquisition device and the size of the acquired image are also fixed. Therefore, the control device can pre-calculate the mapping relationship between the pixel length and physical length of the image acquired by the image acquisition device, based on the pixel length of the second image edge of the image acquired by the image acquisition device and the physical length of the second region boundary of the designated shooting area. This mapping relationship can be a function relationship between the pixel length and the physical length when acquiring the image. Subsequently, the control device can convert the physical length of the designated rejection area in the transmission direction (which can be called the rejection physical length) according to this mapping relationship, that is, substitute the rejection length into the function relationship to calculate the pixel length corresponding to the rejection length (which can be called the rejection pixel length).

[0086] Since the control device will only perform one object rejection operation on a given first pixel coordinate interval after the transmission time corresponding to that interval, a preset pixel coordinate interval will only correspond to a maximum of one object rejection operation by the rejection mechanism. The area on the transmission line corresponding to a preset pixel coordinate interval can be called the first rejection area. If the physical length of the first rejection area in the transmission direction is greater than the rejection physical length, after the transmission time corresponding to the preset pixel coordinate interval, the rejection mechanism can only reject objects belonging to the designated rejection area within the first rejection area. This results in objects in other areas of the first rejection area not being rejected, potentially leading to defective objects located in those other areas not being rejected.

[0087] Therefore, to avoid the above situation, the physical length represented by any preset pixel coordinate interval can be set to be no greater than the physical length of the specified rejection region in the transmission direction. For example, a reference pixel length no greater than the rejection pixel length can be determined, and the second pixel coordinate interval can be divided according to the reference pixel length to obtain multiple adjacent and non-overlapping preset pixel coordinate intervals. The union of multiple preset pixel coordinate intervals is the second pixel coordinate interval. For example, the product of the rejection pixel length and a second preset coefficient can be used as the reference pixel length. The second preset coefficient can be any value in the interval [1 / 2, 1]. For example, the second preset coefficient can be 2 / 3.

[0088] When dividing the second pixel coordinate interval according to the reference pixel length, the division can be carried out along the transmission direction or in the opposite direction of transmission; this application does not limit this.

[0089] Specifically, dividing along the transmission direction means that when multiple preset pixel coordinate intervals are sequentially divided within the second pixel coordinate interval, the direction of each preset pixel coordinate interval is determined to be consistent with the transmission direction. Conversely, dividing in the opposite direction of the transmission direction is called dividing in the reverse transmission direction.

[0090] It is understandable that, since the quotient of the pixel length of the second pixel coordinate interval and the reference pixel length may not be an integer, when dividing the second pixel coordinate interval according to the reference pixel length, the pixel length of the last preset pixel coordinate interval may be less than the reference pixel length.

[0091] For example, such as Figure 3 As shown, Figure 3 This is a second schematic diagram of the object removal method provided in the embodiments of this application. Figure 3 In the middle, the transmission direction is from left to right, and the width of the specified rejection area is the physical length corresponding to the pixel length n of the rejection block 304. When dividing the captured image 303 along the transmission direction into the second pixel coordinate interval corresponding to the transmission direction using (2 / 3)n, starting from the left side of the second pixel coordinate interval, a pixel coordinate interval with a reference pixel length is determined to the right, serving as the first preset pixel coordinate interval. Figure 3 The first preset pixel coordinate interval is represented by the number "1". Then, the right endpoint of the first preset pixel coordinate interval is used as the left endpoint of the second preset pixel coordinate interval. This process continues to the right, defining a pixel coordinate interval with a reference pixel length, as the second preset pixel coordinate interval. Figure 3 The small area is represented by the number "2"; and so on. Figure 3 The small area represented by the number "3" corresponds to the third preset pixel coordinate interval; the small area represented by the number "4", within which a portion of the captured image corresponds to the fourth preset pixel coordinate interval, has a pixel length less than the reference pixel length. That is, along the transmission direction, the second pixel coordinate interval is divided into multiple preset pixel coordinate intervals based on the reference pixel length.

[0092] Based on the above processing, the control device can predetermine multiple preset pixel coordinate intervals. Subsequently, it can directly determine the first pixel coordinate interval according to these predetermined intervals, eliminating the need to divide the second pixel coordinate interval after acquiring the current image to be detected. This improves the efficiency of determining the first pixel coordinate interval and reduces the time required. Consequently, the accuracy of object removal after the transmission time corresponding to the first pixel coordinate interval is also higher.

[0093] In some embodiments, step S203 may include the following steps: for each defective object in the current image to be detected, if the defective object does not exist in the historically acquired images to be detected, determine the preset pixel coordinate interval to which the defective object's pixel coordinates belong in a plurality of preset pixel coordinate intervals in the transmission direction, and use it as the first pixel coordinate interval.

[0094] To avoid missed detections, overlapping image regions can exist between adjacent images to be inspected. That is, for each defective object in the current image to be inspected, the control device, when processing previously acquired images, may have already determined the corresponding first pixel coordinate range and the corresponding transmission time based on the defective object's pixel coordinates. Then, after that transmission time, the control rejection mechanism can remove the defective object. In this case, the control device does not need to determine the corresponding transmission time again based on the defective object's pixel coordinates.

[0095] For each defective object in the image to be inspected acquired by the image acquisition device, the control device can record the image features of that defective object. Then, for each defective object in the current image to be inspected, the image features of that defective object are matched with the image features in the historical records to determine whether the defective object has been detected before.

[0096] For example, in real-world business scenarios, the image acquisition cycle of an image acquisition device is fixed, and within this cycle, there will be at most overlapping image regions between two adjacent images to be detected. In other words, for each defective object in the current image to be detected, it is only necessary to match the image features of the defective object with the image features of the defective object in the previous image to determine whether the defective object has been detected previously.

[0097] Accordingly, for each image to be detected, after detecting the defective object in the image, the image features of the detected defective object can be cached for the duration of one acquisition cycle, so as to match the defective object in the next image to be detected.

[0098] For each defective object in the current image to be inspected, if the defective object has not been detected previously (i.e., the control device has not previously determined the corresponding transmission duration based on the defective object's pixel coordinates), the control device can determine a preset pixel coordinate interval to which the defective object's pixel coordinates belong, as the first pixel coordinate interval. The control device can also record the pixel coordinates of the center point of this first pixel coordinate interval. If the defective object has already been detected previously (i.e., the control device has previously determined the corresponding transmission duration based on the defective object's pixel coordinates), the control device does not need to determine the corresponding transmission duration again based on the defective object's pixel coordinates this time.

[0099] Based on the above processing, by increasing the frequency of acquiring images to be detected, overlapping image regions can be found between two adjacent images to be detected, thus avoiding missed detections. By matching the image features of each defective object with the image features of historical records, it can be determined whether the control device has previously detected the defective object, thus avoiding repeatedly determining the corresponding transmission time based on the same defective object and improving the accuracy of object removal.

[0100] In some embodiments, since the current image to be detected may include multiple defective objects, the pixel coordinates of multiple defective objects may belong to the same preset pixel coordinate interval. However, for these multiple defective objects, the control device only needs to determine the first pixel coordinate interval once, without repeating the determination. Therefore, to avoid repeated determination, for each defective object's pixel coordinate interval, the control device can first determine whether the preset pixel coordinate interval has already been determined as the first pixel coordinate interval. If the preset pixel coordinate interval has been determined as the first pixel coordinate interval, the control device does not repeat the determination; if the preset pixel coordinate interval has not been determined as the first pixel coordinate interval, the control device then determines the preset pixel coordinate interval as the first pixel coordinate interval.

[0101] Regarding step S204, since the current image to be detected may include multiple defective objects, and the distance between these defective objects may be large, meaning the pixel coordinates to be detected for these multiple defective objects may belong to different preset pixel coordinate intervals. Therefore, there may be multiple first pixel coordinate intervals determined based on the pixel coordinates to be detected for these multiple defective objects. After determining multiple first pixel coordinate intervals, the control device can obtain the transmission time corresponding to each first pixel coordinate interval. The transmission time corresponding to the first pixel coordinate interval can represent the time required for the transmission line to transmit an object from the physical location corresponding to the first pixel coordinate interval to the specified rejection area.

[0102] Accordingly, after the transmission time corresponding to the first pixel coordinate interval, the defective object whose pixel coordinates belong to the first pixel coordinate interval is transmitted to the designated rejection area by the transmission line. At this time, the control device controls the rejection mechanism to reject the object in the designated rejection area, thus removing the defective object.

[0103] In some embodiments, the control device can start timing after acquiring the current image to be detected. After the timing duration reaches the transmission duration corresponding to the first pixel coordinate interval, the control device can control the rejection mechanism to perform rejection. Alternatively, the control device can take the moment when the current image to be detected is acquired as the current moment, and after acquiring the transmission duration corresponding to the first pixel coordinate interval, calculate the sum of the transmission duration corresponding to the first pixel coordinate interval and the current moment to obtain the rejection moment, and then control the rejection mechanism to perform rejection when the rejection moment is reached.

[0104] When the control device determines multiple first pixel coordinate intervals based on the multiple defective objects included in the current image to be inspected, the control device can obtain the transmission duration corresponding to each first pixel coordinate interval. For each first pixel coordinate interval, the control device can calculate the sum of the transmission duration corresponding to that first pixel coordinate interval and the current time to obtain the removal time corresponding to that first pixel coordinate interval. That is, for the current image to be inspected, the control device may determine multiple removal times. Subsequently, when each removal time is reached, the control device can control the removal device to perform the removal.

[0105] In some embodiments, the transmission duration corresponding to a preset pixel coordinate interval represents the ratio of the transmission physical distance corresponding to the preset pixel coordinate interval to the transmission speed of the transmission line.

[0106] For example, the physical distance in the transmission direction between the physical location corresponding to any pixel coordinate in the preset pixel coordinate interval and any point in the specified rejection area can be calculated as the transmission physical distance corresponding to the preset pixel coordinate interval. Alternatively, to improve the accuracy of object rejection, the physical distance in the transmission direction between the physical location corresponding to the center point of the preset pixel coordinate interval and the center point of the specified rejection area can be calculated as the transmission physical distance corresponding to the preset pixel coordinate interval.

[0107] In one implementation, after determining the first pixel coordinate interval, the control device can calculate the ratio of the physical distance in the transmission direction between the physical location corresponding to the center point of the first pixel coordinate interval and the center point of the specified rejection area to the transmission speed of the transmission line, and obtain the transmission duration corresponding to the first pixel coordinate interval.

[0108] In another implementation, the physical location corresponding to the center point of a preset pixel coordinate interval can be called the first center position; the center point of the specified rejection area can be called the second center position. After determining multiple preset pixel coordinate intervals, the control device pre-calculates the ratio of the physical distance in the transmission direction between the first and second center positions of the preset pixel coordinate interval to the transmission speed of the transmission line, thus obtaining the transmission duration corresponding to the preset pixel coordinate interval. Subsequently, the control device can directly query the transmission duration corresponding to the first pixel coordinate interval from the pre-acquired transmission durations, improving the efficiency of determining the transmission duration corresponding to the first pixel coordinate interval. Therefore, the accuracy of object rejection after passing through the transmission duration corresponding to the first pixel coordinate interval is also higher.

[0109] In some embodiments, the transmission physical distance corresponding to a preset pixel coordinate range is obtained based on the following method:

[0110] Step 1: Calculate the pixel distance between the center point of the preset pixel coordinate interval and the specified pixel coordinate in the transmission direction.

[0111] In the second pixel coordinate range, the physical location corresponding to the specified pixel coordinate is closest to the specified rejection area in the transmission direction.

[0112] Step 2: Based on the mapping relationship between pixel length and physical length when the image is acquired by the image acquisition device, convert the pixel distance to obtain the first physical distance.

[0113] Step 3: Calculate the sum of the first physical distance and the second physical distance to obtain the transmission physical distance corresponding to the preset pixel coordinate interval.

[0114] The second physical distance refers to the physical distance in the transmission direction between the physical location corresponding to the specified pixel coordinates and the center point of the specified culling area.

[0115] After determining the specified pixel coordinates and the center point of the preset image area, the control device can calculate the difference between the specified pixel coordinates and the pixel coordinates of the center point of the preset image area in the transmission direction, and use the calculation result as the pixel distance between the center point of the preset pixel coordinate interval and the specified pixel coordinates in the transmission direction.

[0116] Then, according to the pre-obtained mapping relationship between pixel length and physical length when the image is captured by the image acquisition device, the calculated pixel distance is converted to obtain the first physical distance.

[0117] Furthermore, on a transmission line, once the image acquisition device is installed, the position of its designated shooting area is fixed; similarly, once the rejection mechanism is installed, the position of its designated rejection area is also fixed. Therefore, the control device pre-calculates the physical distance in the transmission direction between the physical position corresponding to the designated pixel coordinates and the second center position, thus obtaining the second physical distance.

[0118] The sum of the first physical distance and the second physical distance is the physical distance between the first center position and the second center position of the preset pixel coordinate interval in the transmission direction, which is the transmission physical distance corresponding to the preset pixel coordinate interval.

[0119] Based on the above processing, the control device can pre-calculate the transmission physical distance corresponding to each preset pixel coordinate interval, and then pre-calculate the transmission duration corresponding to each preset pixel coordinate interval. Subsequently, it can directly query the transmission duration corresponding to the first pixel coordinate interval from multiple transmission durations, which can reduce the time spent determining the transmission duration corresponding to the first pixel coordinate interval. Therefore, the accuracy of object removal after passing the transmission duration corresponding to the first pixel coordinate interval is also higher.

[0120] In some embodiments, the control device may also calculate the physical distance in the transmission direction between the first center position of the preset pixel coordinate interval and the physical position corresponding to the specified pixel coordinate, and the sum of the physical distance in the transmission direction between the physical position corresponding to the specified pixel coordinate and the second center position, to obtain the transmission physical distance corresponding to the preset pixel coordinate interval.

[0121] For example, Figure 3 In the schematic diagram shown, the conveyor belt on transmission line 301 is a belt that moves from left to right at a speed v; the object placed on the belt is a dumpling, and the object filled in black represents a defective dumpling 302. Figure 3 The captured image 303 is the current image to be detected in the aforementioned embodiment; the rejection block 304 is the rejection mechanism in the aforementioned embodiment. Figure 3 The width of the specified rejection region in the schematic diagram is the physical length corresponding to the length n of rejection block 304.

[0122] Along the transmission direction, the second pixel coordinate interval is divided into four preset pixel coordinate intervals by (2 / 3)n. These four preset pixel coordinate intervals are respectively... Figure 3 The small regions represented by the numbers "1", "2", "3", and "4" correspond to each other. The length of the preset pixel coordinate interval corresponding to the small region represented by the number "4" is less than (2 / 3)n. Figure 3The removal center point includes the center point of the preset pixel coordinate interval in the aforementioned embodiment. The removal center point coordinates (c, d) of the small region represented by the number "1" are such that the length of the preset pixel coordinate interval corresponding to the small region represented by the number "1" is (2 / 3)n. Therefore, the preset pixel coordinate interval 305 is [cn / 3, c+n / 3).

[0123] Figure 3 In the schematic diagram shown, the control device detects defects in the image to be inspected, obtaining the coordinates (a, b) of the defective dumpling 302. Then, it determines the preset pixel coordinate interval to which the pixel coordinate a to be detected within the defective dumpling 302 coordinates (a, b) belongs. Since the pixel coordinate a to be detected belongs to the preset pixel coordinate interval 305 [cn / 3, c+n / 3), the preset pixel coordinate interval 305 is the first pixel coordinate interval, and the control device can record the pixel coordinates (c, d) of the center point of the preset pixel coordinate interval 305.

[0124] Figure 3 The image edge in the above embodiment refers to the position of the specified pixel coordinates in the current image to be detected. The distance k from the removal center point to the image edge is: the physical distance in the transmission direction between the physical position corresponding to the center point of the first pixel coordinate interval and the physical position corresponding to the specified pixel coordinates, i.e., the first physical distance. The distance m from the image edge to the removal block is the second physical distance. The sum of the first physical distance k and the second physical distance m is (k+m), which is the transmission physical distance corresponding to the preset pixel coordinate interval.

[0125] Then, the control device can calculate the ratio of the transmission physical distance (k+m) to the speed v, i.e., calculate (k+m) / v, to obtain the delay time (i.e., the transmission duration in the aforementioned embodiment). Furthermore, taking the time when the image acquisition device acquires the captured image as the initial time (i.e., the current time in the aforementioned embodiment), the sum of the initial time and the delay time is calculated to obtain the actual time for rejection, i.e., the rejection time. Subsequently, when the actual rejection time is reached, the control device can control the rejection block 304 to reject objects within the specified rejection area, i.e., control the rejection mechanism to reject objects within the specified rejection area.

[0126] The specific method by which the rejection mechanism performs rejection is related to the actual application scenario. For example, the rejection mechanism may include a rejection plate, and the length of the area where the rejection plate contacts the transmission line is the physical rejection length. The control device can send a rejection command to the rejection mechanism when the rejection time is reached. After receiving the rejection command, the rejection mechanism controls a cylinder to move once via a PLC (Programmable Logic Controller). This single movement of the cylinder controls the rejection plate to move vertically once. As the rejection plate moves, it pushes objects located within the designated rejection area on the transmission line until the objects are pushed off the transmission line, thus removing them from the transmission line. Subsequently, when the rejection mechanism receives another rejection command, it controls the cylinder to move again via the PLC, controlling the rejection plate to continue moving vertically in the opposite direction to the previous movement, thus pushing objects within the designated rejection area off the transmission line again. In other words, the rejection mechanism can control the rejection plate to repeatedly reject objects within the designated rejection area. In practical applications, containers can be placed on both sides of the transmission line to hold objects that have been removed from the transmission line.

[0127] In some embodiments, see Figure 4 , Figure 4 This is a second flowchart of the object removal method provided in an embodiment of this application. The object transmitted on the transmission line is a dumpling, and the defective object is a defective dumpling.

[0128] S401: Acquire image information captured by the camera.

[0129] In this step, the camera refers to the image acquisition device described in the previous embodiment. The camera captures image information, meaning the image acquisition device in the previous embodiment captures images located within a designated shooting area on the transmission line, obtaining the image to be detected. After capturing the image information, the camera can send the image information to the control device.

[0130] S402: Algorithm analysis to obtain the location information of defective dumplings.

[0131] In this step, the defective dumpling location information is the same as the pixel coordinates of the defective object to be detected in the aforementioned embodiment; the algorithm analysis is the detection of the defective object in the current image to be detected in the aforementioned embodiment.

[0132] After acquiring the current image to be detected, the control device detects the defective object in the current image and obtains the pixel coordinates of the defective object in the transmission direction.

[0133] S403: Remove 2 / 3 of the block length and convert it to pixel length.

[0134] In this step, the rejection block is the rejection mechanism in the aforementioned embodiments, and the rejection block length is the physical length of the designated rejection area of ​​the rejection mechanism in the aforementioned embodiments in the transmission direction, i.e., the rejection physical length.

[0135] The control device converts the physical length to be removed according to the mapping relationship between the pixel length and the physical length when the image is acquired by the image acquisition device, so as to obtain the removed pixel length; then, it calculates the product of the removed pixel length and 2 / 3, and uses the calculation result as the reference pixel length.

[0136] S404: Calculation of image pixel length and culling block pixel length.

[0137] In this step, the image pixel length is the same as the pixel length of the image to be detected in the aforementioned embodiments; the pixel length of the image to be detected is consistent with the pixel length of the second pixel coordinate interval. The pixel length of the discarded block is the same as the reference pixel length in the aforementioned embodiments.

[0138] In other words, the control device divides the second pixel coordinate interval according to the reference pixel length to obtain multiple adjacent and non-overlapping pixel coordinate intervals, which are used as multiple preset pixel coordinate intervals.

[0139] S405: Obtain the coordinates of the center point to be removed in each theoretical step and the size of the removal area in this step.

[0140] In this step, the coordinates of the center point that is theoretically removed each time are the pixel coordinates of the center point of each preset pixel coordinate interval in the aforementioned embodiment; the size of the area to be removed this time is the pixel length of a preset pixel coordinate interval.

[0141] After determining multiple preset pixel coordinate intervals, the control device can determine the pixel coordinates of the center point of each preset pixel coordinate interval and the pixel length of the preset pixel coordinate interval.

[0142] S406: Find out which rejection area the defective dumpling belongs to.

[0143] In this step, the rejection area where the defective dumpling is located is located, which is the first pixel coordinate interval to which the coordinates of the pixel to be detected belonged in the previous embodiment. After the control device determines the first pixel coordinate interval, it can record the pixel coordinates of the center point of the first pixel coordinate interval.

[0144] S407: Determine whether the center point to be removed has been recorded.

[0145] In this step, the control device determines whether the removal center point has been recorded, that is, whether the preset pixel coordinate interval has been determined as the first pixel coordinate interval.

[0146] If the removal center point is not recorded, that is, the preset pixel coordinate interval has not been determined as the first pixel coordinate interval, execute step S408: record, that is, determine the preset pixel coordinate interval as the first pixel coordinate interval, and then record the pixel coordinates of the center point of the first pixel coordinate interval.

[0147] If the removal center point has already been recorded, that is, the preset pixel coordinate interval has been previously determined as the first pixel coordinate interval, execute step S409: skip, that is, do not repeatedly determine the preset pixel coordinate interval as the first pixel coordinate interval.

[0148] S410: Calculate the distance from each removal center point to the image edge.

[0149] In this step, the distance from a removal center point to the image edge is the first physical distance in the aforementioned embodiment.

[0150] Specifically, for each preset pixel coordinate interval, the control device can calculate the pixel distance in the transmission direction between the center point of the preset pixel coordinate interval and the specified pixel coordinates. Then, according to the mapping relationship between pixel length and physical length when the image acquisition device acquires the image, the pixel distance is converted to obtain the first physical distance. Alternatively, the control device can calculate the physical distance in the transmission direction between the first center position of the preset pixel coordinate interval and the physical position corresponding to the specified pixel coordinates to obtain the first physical distance.

[0151] S411: Calculate the distance from the image edge to the culling block.

[0152] In this step, the distance from the image edge to the culling block is the second physical distance in the aforementioned embodiment. The control device can pre-calculate the physical distance in the transmission direction between the physical location corresponding to the specified pixel coordinates and the second center location to obtain the second physical distance.

[0153] S412: Calculate the delay time based on the belt speed.

[0154] In this step, the belt speed is the same as the transmission speed of the transmission line in the aforementioned embodiment; the delay time is the same as the rejection time in the aforementioned embodiment. For each rejection area, the control device calculates the sum of the distance from the rejection center point of the rejection area to the image edge and the distance from the image edge to the rejection block, and then calculates the ratio of this sum to the belt speed to obtain the transmission time corresponding to the rejection area. Then, the sum of the transmission time and the current time is calculated to obtain the delay time corresponding to the rejection area, that is, the delay time from the rejection center point of the rejection area to the rejection block.

[0155] S413: Sort the delay time from each removal center point to the removal block in ascending order, and notify the removal block of the sorted delay time in sequence.

[0156] In this step, when multiple first pixel coordinate intervals exist in the image to be detected, the control device determines multiple rejection times. When a rejection time is reached, the control device sends a rejection command to the rejection mechanism. Upon receiving the rejection command, the rejection mechanism performs object rejection.

[0157] Based on the above processing, the control device can identify defective objects in the current image to be inspected, and after the transmission time corresponding to the first pixel coordinate interval to which the defective object belongs, control the removal mechanism to remove it, thus eliminating defective objects on the transmission line. This eliminates the need for manual inspection by technicians, improving the efficiency of object removal. Furthermore, since the control device controls the removal mechanism based on the transmission time corresponding to the first pixel coordinate interval, when multiple defective objects belong to the same first pixel coordinate interval, the control device only needs to control the removal mechanism to perform one removal operation based on the transmission time corresponding to that first pixel coordinate interval. This eliminates the need for multiple unnecessary removal operations, saving the control device's computational resources. Additionally, since each removal operation takes time, performing only one removal operation for multiple defective objects avoids multiple removal operations within a short period, preventing errors in the removal mechanism's execution.

[0158] Furthermore, the control equipment automatically identifies and removes defective objects, which can avoid the removal effect being affected by the fatigue of technicians, making the process of removing defective objects more stable.

[0159] In addition, when the transmission speed of the transmission line changes, the control device can still calculate the removal time after the transmission speed change based on the object removal method provided in this application, without having to modify the method itself. That is, it has good compatibility with speed changes and a wider range of applications.

[0160] This application embodiment also provides an object culling system, which includes an image acquisition device, a control device, a culling mechanism, and a transmission line, wherein:

[0161] A transmission line is used to transmit objects in a preset transmission direction.

[0162] An image acquisition device is used to acquire images located within a specified shooting area on a transmission line to obtain the image to be detected.

[0163] A control device for performing any of the object culling methods described in the foregoing embodiments.

[0164] The rejection mechanism is used to reject objects within a designated rejection area under the control of the control equipment.

[0165] Based on the above processing, the control device can identify defective objects in the current image to be inspected, and after the transmission time corresponding to the first pixel coordinate interval to which the defective object belongs, control the removal mechanism to remove it, thus eliminating defective objects on the transmission line. This eliminates the need for manual inspection by technicians, improving the efficiency of object removal. Furthermore, since the control device controls the removal mechanism based on the transmission time corresponding to the first pixel coordinate interval, when multiple defective objects belong to the same first pixel coordinate interval, the control device only needs to control the removal mechanism to perform one removal operation based on the transmission time corresponding to that first pixel coordinate interval. This eliminates the need for multiple unnecessary removal operations, saving the control device's computational resources. Additionally, since each removal operation takes time, performing only one removal operation for multiple defective objects avoids multiple removal operations within a short period, preventing errors in the removal mechanism's execution.

[0166] In some embodiments, the control device is specifically used to send a rejection instruction to the rejection mechanism. The rejection mechanism, upon receiving the rejection instruction, is specifically used to reject objects within a specified rejection area.

[0167] Based on the same inventive concept as the object elimination method described above, embodiments of this application also provide an object elimination apparatus. See also... Figure 5 , Figure 5 A structural diagram of an object rejection device provided in an embodiment of this application is shown. The device includes:

[0168] The image acquisition module 501 is used to acquire an image located within a specified shooting area of ​​the image acquisition device on the current transmission line during the transmission of an object in a preset transmission direction via a transmission line, thereby obtaining the current image to be detected.

[0169] Detection module 502 is used to detect defect objects in the current image to be detected and obtain the pixel coordinates of the defect objects in the current image to be detected in the transmission direction, which are used as the pixel coordinates to be detected.

[0170] The interval determination module 503 is used to determine, among multiple preset pixel coordinate intervals in the transmission direction, the preset pixel coordinate interval to which the coordinates of the pixel to be detected belong, as the first pixel coordinate interval; wherein, the multiple preset pixel coordinate intervals represent: multiple adjacent and non-overlapping intervals obtained by dividing the second pixel coordinate interval corresponding to the specified shooting area in the transmission direction, and the physical length represented by each preset pixel coordinate interval is not greater than the physical length of the specified rejection area of ​​the rejection mechanism in the transmission direction.

[0171] The control module 504 is used to control the rejection mechanism to reject objects within the specified rejection area after the transmission time corresponding to the first pixel coordinate interval has elapsed; wherein, the transmission time corresponding to the first pixel coordinate interval represents the time required for the transmission line to transmit an object from the physical location corresponding to the first pixel coordinate interval to the specified rejection area.

[0172] Optionally, the device further includes:

[0173] The segmentation module is used by the interval determination module 503 to determine, within a plurality of preset pixel coordinate intervals in the transmission direction, the preset pixel coordinate interval to which the coordinates of the pixel to be detected belong, as the first pixel coordinate interval, before performing the segmentation of the second pixel coordinate interval according to the reference pixel length, to obtain a plurality of adjacent and non-overlapping pixel coordinate intervals, which are used as the plurality of preset pixel coordinate intervals; wherein, the physical length represented by the reference pixel length is not greater than the physical length of the specified rejection region in the transmission direction.

[0174] Optionally, the transmission duration corresponding to a preset pixel coordinate interval represents the ratio of the transmission physical distance corresponding to the preset pixel coordinate interval to the transmission speed of the transmission line; the transmission physical distance corresponding to the preset pixel coordinate interval represents the physical distance between the physical location corresponding to the center point of the preset pixel coordinate interval and the center point of the specified rejection area in the transmission direction.

[0175] Optionally, the transmission physical distance corresponding to a preset pixel coordinate range is obtained based on the following method:

[0176] Calculate the pixel distance between the center point of the preset pixel coordinate interval and the specified pixel coordinate in the transmission direction; wherein, in the second pixel coordinate interval, the physical location corresponding to the specified pixel coordinate is closest to the physical distance between the specified rejection area and the specified rejection area in the transmission direction;

[0177] Based on the mapping relationship between pixel length and physical length when the image acquisition device acquires the image, the pixel distance is converted to obtain the first physical distance;

[0178] The sum of the first physical distance and the second physical distance is calculated to obtain the transmission physical distance corresponding to the preset pixel coordinate interval; wherein, the second physical distance represents the physical distance between the physical position corresponding to the specified pixel coordinate and the center point of the specified rejection area in the transmission direction.

[0179] Optionally, the interval determination module 503 is specifically used for:

[0180] For each defective object in the current image to be detected, if the defective object does not exist in the historically acquired images to be detected, the preset pixel coordinate interval to which the defective object belongs is determined from multiple preset pixel coordinate intervals in the transmission direction, and is used as the first pixel coordinate interval.

[0181] Based on the object removal device provided in this application embodiment, a control device can identify defective objects in the current image to be detected. After the transmission time corresponding to the first pixel coordinate interval to which the defective object belongs, the device controls the removal mechanism to remove the defective objects on the transmission line. This eliminates the need for manual inspection by technicians, improving the efficiency of object removal. Furthermore, since the control device controls the removal mechanism based on the transmission time corresponding to the first pixel coordinate interval, when the pixel coordinates of multiple defective objects belong to the same first pixel coordinate interval, the control device only needs to control the removal mechanism to perform one removal operation based on one transmission time corresponding to the first pixel coordinate interval. This eliminates the need for multiple unnecessary removal operations, saving the control device's computational resources. Additionally, since each removal operation takes time, performing only one removal operation for multiple defective objects avoids multiple removal operations within a short period, preventing errors in the removal mechanism's execution.

[0182] This application also provides a control device, such as... Figure 6 As shown, it includes:

[0183] Memory 601 is used to store computer programs;

[0184] When the processor 602 executes the program stored in the memory 601, it implements the steps of any of the object removal methods in the above embodiments.

[0185] Furthermore, the aforementioned control device may also include a communication bus and / or a communication interface, with the processor 602, communication interface, and memory 601 communicating with each other via the communication bus.

[0186] The communication bus mentioned in the control device above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not indicate that there is only one bus or one type of bus.

[0187] The communication interface is used for communication between the aforementioned control device and other devices.

[0188] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0189] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0190] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the steps of any of the above-described object removal methods.

[0191] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to perform any of the object removal methods described above.

[0192] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a solid-state drive (SSD), etc.

[0193] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0194] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system, apparatus, control device, computer-readable storage medium, and computer program product embodiments are basically similar to the method embodiments, and therefore the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0195] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application are included within the scope of protection of this application.

Claims

1. An object culling method, characterized in that, The method includes: During the process of transmitting an object through a transmission line in a preset transmission direction, an image located within a specified shooting area of ​​the image acquisition device on the current transmission line is acquired to obtain the current image to be detected; Defect objects are detected in the current image to be detected, and the pixel coordinates of the defect objects in the current image to be detected in the transmission direction are obtained as the pixel coordinates to be detected. In the multiple preset pixel coordinate intervals in the transmission direction, the preset pixel coordinate interval to which the pixel coordinate to be detected belongs is determined as the first pixel coordinate interval; wherein, the multiple preset pixel coordinate intervals represent: multiple adjacent and non-overlapping intervals obtained by dividing the second pixel coordinate interval corresponding to the specified shooting area in the transmission direction, and the physical length represented by each preset pixel coordinate interval is not greater than the physical length of the specified rejection area of ​​the rejection mechanism in the transmission direction. After the transmission time corresponding to the first pixel coordinate interval has elapsed, the rejection mechanism is controlled to reject objects within the specified rejection area; wherein, the transmission time corresponding to a preset pixel coordinate interval represents the ratio of the transmission physical distance corresponding to the preset pixel coordinate interval to the transmission speed of the transmission line; The transmission physical distance corresponding to a preset pixel coordinate range is obtained based on the following method: Calculate the pixel distance between the center point of the preset pixel coordinate interval and the specified pixel coordinate in the transmission direction; wherein, in the second pixel coordinate interval, the physical location corresponding to the specified pixel coordinate is closest to the physical distance between the specified rejection area and the specified rejection area in the transmission direction; Based on the mapping relationship between pixel length and physical length when the image acquisition device acquires the image, the pixel distance is converted to obtain the first physical distance; The sum of the first physical distance and the second physical distance is calculated to obtain the transmission physical distance corresponding to the preset pixel coordinate interval; wherein, the second physical distance represents the physical distance between the physical position corresponding to the specified pixel coordinate and the center point of the specified rejection area in the transmission direction.

2. The method according to claim 1, characterized in that, Before determining the preset pixel coordinate interval to which the coordinates of the pixel to be detected belong, among multiple preset pixel coordinate intervals in the transmission direction, as the first pixel coordinate interval, the method further includes: The second pixel coordinate interval is divided according to the reference pixel length to obtain multiple adjacent and non-overlapping pixel coordinate intervals, which are referred to as the multiple preset pixel coordinate intervals; wherein, the physical length represented by the reference pixel length is not greater than the physical length of the specified rejection region in the transmission direction.

3. The method according to claim 1, characterized in that, Among multiple preset pixel coordinate intervals in the transmission direction, determining the preset pixel coordinate interval to which the coordinates of the pixel to be detected belong, as the first pixel coordinate interval, includes: For each defective object in the current image to be detected, if the defective object does not exist in the historically acquired images to be detected, the preset pixel coordinate interval to which the defective object belongs is determined from multiple preset pixel coordinate intervals in the transmission direction, and is used as the first pixel coordinate interval.

4. An object culling system, characterized in that, The object removal system includes an image acquisition device, a control device, a removal mechanism, and a transmission line, wherein: The transmission line is used to transmit objects in a preset transmission direction; The image acquisition device is used to acquire images located within a designated shooting area on the transmission line to obtain the image to be detected; The control device is used to perform the method according to any one of claims 1-3; The rejection mechanism is used to reject objects within a designated rejection area under the control of the control device.

5. The system according to claim 4, characterized in that, The control device is specifically used to send rejection instructions to the rejection mechanism; The removal mechanism is specifically used to remove objects within a specified removal area when the removal instruction is received.

6. An object rejection device, characterized in that, The device includes: The image acquisition module is used to acquire an image located within a specified shooting area of ​​the image acquisition device on the current transmission line during the transmission of an object in a preset transmission direction, thereby obtaining the current image to be detected. The detection module is used to detect defect objects in the current image to be detected and obtain the pixel coordinates of the defect objects in the current image to be detected in the transmission direction, which are used as the pixel coordinates to be detected. The interval determination module is used to determine, among multiple preset pixel coordinate intervals in the transmission direction, the preset pixel coordinate interval to which the coordinates of the pixel to be detected belong, as the first pixel coordinate interval; wherein, the multiple preset pixel coordinate intervals represent: multiple adjacent and non-overlapping intervals obtained by dividing the second pixel coordinate interval corresponding to the specified shooting area in the transmission direction, and the physical length represented by each preset pixel coordinate interval is not greater than the physical length of the specified rejection area of ​​the rejection mechanism in the transmission direction. The control module is used to control the rejection mechanism to reject objects within the specified rejection area after the transmission time corresponding to the first pixel coordinate interval; wherein, the transmission time corresponding to the first pixel coordinate interval represents the time required for the transmission line to transmit an object from the physical location corresponding to the first pixel coordinate interval to the specified rejection area; the transmission time corresponding to a preset pixel coordinate interval represents the ratio of the transmission physical distance corresponding to the preset pixel coordinate interval to the transmission speed of the transmission line; The transmission physical distance corresponding to a preset pixel coordinate range is obtained based on the following method: Calculate the pixel distance between the center point of the preset pixel coordinate interval and the specified pixel coordinate in the transmission direction; wherein, in the second pixel coordinate interval, the physical location corresponding to the specified pixel coordinate is closest to the physical distance between the specified rejection area and the specified rejection area in the transmission direction; Based on the mapping relationship between pixel length and physical length when the image acquisition device acquires the image, the pixel distance is converted to obtain the first physical distance; The sum of the first physical distance and the second physical distance is calculated to obtain the transmission physical distance corresponding to the preset pixel coordinate interval; wherein, the second physical distance represents the physical distance between the physical position corresponding to the specified pixel coordinate and the center point of the specified rejection area in the transmission direction.

7. The apparatus according to claim 6, characterized in that, The device further includes: The segmentation module is used to determine, before the interval determination module performs the operation of multiple preset pixel coordinate intervals in the transmission direction, the preset pixel coordinate interval to which the coordinates of the pixel to be detected belong, as the first pixel coordinate interval, and then divides the second pixel coordinate interval according to the reference pixel length to obtain multiple adjacent and non-overlapping pixel coordinate intervals, which are used as the multiple preset pixel coordinate intervals; wherein, the physical length represented by the reference pixel length is not greater than the physical length of the specified rejection region in the transmission direction; The interval determination module is specifically used for: For each defective object in the current image to be detected, if the defective object does not exist in the historically acquired images to be detected, the preset pixel coordinate interval to which the defective object belongs is determined from multiple preset pixel coordinate intervals in the transmission direction, and is used as the first pixel coordinate interval.

8. A control device, characterized in that, include: Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 1-3.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-3.

10. A computer program product, characterized in that, When the computer program product is run on a computer, it causes the computer to perform the method according to any one of claims 1-3.

Images