Excessive package detection system, method and device
By combining image acquisition devices and a rotating mechanism, along with weight acquisition, a three-dimensional model of the item to be tested is constructed, solving the problems of accuracy and efficiency in over-packaging detection and enabling reasonable management of product packaging.
Patent Information
- Application Number
- CN202411093738.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-11-15
AI Technical Summary
Existing technologies are insufficient to effectively detect and manage the problem of excessive packaging of goods, leading to resource waste and environmental pollution.
An over-packaging detection system is used to collect multiple two-dimensional images of the item under test through the cooperation of image acquisition devices and a rotating mechanism. The images are then reconstructed into three dimensions, and combined with data from a weight acquisition device, to determine whether the item is over-packaged.
This enables reasonable control and management of product packaging, improves the accuracy and efficiency of inspection, reduces manual intervention, and ensures the integrity of the 3D model and the accuracy of volume calculation.
Smart Images

Figure CN118953818A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of automated detection technology, and in particular to an over-packaging detection system, method and device. Background Art
[0002] With the rapid development of social economy and the continuous improvement of people's living standards, the packaging of goods has become more and more diverse and exquisite. However, the problem of excessive packaging has become increasingly serious. Excessive packaging not only increases the economic burden of consumers, but also leads to waste of resources and environmental pollution. Therefore, it is necessary to reasonably control and manage the packaging of goods.
[0003] Therefore, there is an urgent need for a detection method for determining whether a product is over-packaged. Summary of the invention
[0004] In view of this, the present disclosure proposes an over-packaging detection system, method and device to solve the problem of over-packaging of goods existing in the related art.
[0005] The first aspect of the present disclosure provides an over-packaging detection system, the system comprising: a control device and a data acquisition device;
[0006] The data acquisition device comprises a rectangular bracket, an image acquisition device arranged on the top of the rectangular bracket, a weight acquisition device and a workbench arranged at the bottom of the rectangular bracket, wherein the workbench is located above the upper end surface of the weight acquisition device; a rotating mechanism is arranged at the connection between the workbench and the weight acquisition device, and the rotating mechanism is fixedly connected to the lower end surface of the workbench;
[0007] The control device is used to send a driving instruction to the data acquisition device to control the field of view of the camera of the image acquisition device to cover the entire upper end surface of the workbench, and to control the workbench to rotate according to a preset angle in a direction parallel to the top of the rectangular support;
[0008] The control device is also used to receive multiple two-dimensional images of the object to be tested captured by the image acquisition device and the weight collected by the weight acquisition device when the object to be tested is placed on the end surface of the workbench, and determine whether the object to be tested is over-packaged based on the multiple two-dimensional images and the weight.
[0009] The disclosed embodiment can acquire multiple two-dimensional images of the object to be tested at all angles through the coordinated cooperation of the image acquisition device and the rotating mechanism, thereby performing three-dimensional reconstruction based on the multiple two-dimensional images to obtain a complete three-dimensional model of the object to be tested, so as to facilitate determining the volume of the object to be tested based on the three-dimensional model; and determining the weight of the object to be tested through the weighing device of the supporting workbench, and then detecting whether the object to be tested is over-packaged based on the volume and weight of the object to be tested, thereby effectively solving the problem of over-packaging of goods and achieving the purpose of reasonable control and management of the packaging of goods.
[0010] In the embodiment of the present disclosure, a first sliding mechanism, a first crossbar and a second crossbar parallel to each other, and a third crossbar slidably arranged on the first crossbar and the second crossbar are arranged on the top of the rectangular bracket; the image acquisition device is arranged on the third crossbar; the third crossbar is perpendicular to the first crossbar or the second crossbar; the first sliding mechanism is used to drive the third crossbar to move in a first preset direction; the preset direction is the setting direction of the first crossbar and / or the second crossbar;
[0011] The data acquisition device is used to send the shooting angle of the image acquisition device to the control device;
[0012] The data acquisition device is also used to receive left and right movement instructions from the control device, and drive the image acquisition device to move left and right by controlling the first sliding mechanism, so that the field of view of the image acquisition device covers the entire upper end surface of the workbench, or collects a two-dimensional image of the upper end surface of the recessed area of the object to be tested; the left and right movement instructions are determined by the control device according to the shooting angle.
[0013] The disclosed embodiment controls the first sliding mechanism to drive the image acquisition device to move in a first preset direction, so that the image acquisition device can reach a suitable angle and position to re-photograph the object to be measured, thereby completing the incomplete three-dimensional model and obtaining a complete three-dimensional model, thereby achieving the purpose of improving the efficiency of constructing the three-dimensional model; thereby solving the following problem: when the object to be measured placed on the workbench is an irregular object, or the object is too large, the cooperation between the image acquisition device and the rotating mechanism cannot capture two-dimensional images of all angles of the object to be measured, resulting in the problem of incomplete constructed three-dimensional model.
[0014] In the disclosed embodiment, a vertical rod is respectively provided at the four corners of the rectangular bracket; wherein the top ends of the first vertical rod and the second vertical rod are respectively connected to the two ends of the first cross rod; the top ends of the third vertical rod and the fourth vertical rod are respectively connected to the two ends of the second cross rod; the rectangular bracket is also provided with a second sliding mechanism for driving the first cross rod and the second cross rod to move in a second preset direction; the second preset direction is the setting direction of the first vertical rod, the second vertical rod, the third vertical rod and / or the fourth vertical rod;
[0015] The data acquisition device is also used to receive the up and down movement instructions of the control device, and drive the image acquisition device to move up and down by controlling the second sliding mechanism, so that the field of view of the image acquisition device covers the entire upper end surface of the workbench, or collects a two-dimensional image of the upper end surface of the recessed area of the object to be tested; the up and down movement instructions are determined by the control device according to the shooting angle.
[0016] The disclosed embodiment, through the second sliding mechanism and the four vertical rods arranged at the four corners of the rectangular bracket, can control the image acquisition device to move in the vertical direction, so that the image acquisition device can capture two-dimensional images of the object to be tested at more angles, thereby ensuring the integrity of the constructed three-dimensional model and greatly improving the construction efficiency of the three-dimensional model, thereby achieving improved detection accuracy of whether the object to be tested is over-packaged.
[0017] The second aspect of the present disclosure provides an over-packaging detection method, characterized in that the method is applied to the control device of the over-packaging detection system according to the first aspect of the present disclosure, and comprises:
[0018] Acquire a plurality of two-dimensional images of the object to be measured at different viewing angles and the weight of the object to be measured set on the data acquisition device; the plurality of two-dimensional images are acquired by the image acquisition device, and the weight is acquired by the weight acquisition device;
[0019] Performing three-dimensional reconstruction based on the multiple two-dimensional images to obtain a three-dimensional model of the object to be tested;
[0020] Determining whether the three-dimensional model is complete;
[0021] If the three-dimensional model is complete, determining the volume of the object to be tested according to the three-dimensional model;
[0022] Determine whether the object to be tested is over-packaged according to the volume and weight of the object to be tested.
[0023] The disclosed embodiment obtains multiple two-dimensional images of the object to be tested at different viewing angles and constructs a three-dimensional model based on the two-dimensional images. It determines whether the three-dimensional model is complete, thereby ensuring the accuracy and efficiency of building the three-dimensional model. It also ensures the accuracy of the volume of the object to be tested calculated based on the three-dimensional model. It determines whether the object to be tested is over-packaged through the volume and weight of the object to be tested, and can accurately detect whether the object is over-packaged, thereby achieving the purpose of reasonable management of the packaging of the object.
[0024] In the embodiment of the present disclosure, determining whether the three-dimensional model is complete includes:
[0025] If the three-dimensional model covers all observable areas of the object to be tested, it is determined that the three-dimensional model is complete;
[0026] If the three-dimensional model does not cover all observable areas of the object to be tested, it is determined that the three-dimensional model is incomplete.
[0027] The disclosed embodiment determines whether the three-dimensional model is complete by determining whether the three-dimensional model covers all observable areas of the object to be tested, which can greatly improve the accuracy of integrity detection of the three-dimensional model.
[0028] In an embodiment of the present disclosure, the method further includes:
[0029] If the three-dimensional model is incomplete, determining a target area of the object to be tested; the target area refers to an observable area of the object to be tested that is not covered by the three-dimensional model;
[0030] Adjusting the shooting position and shooting angle of the image acquisition device according to the target area, and / or adjusting the position of the workbench, so that the image acquisition device can capture a two-dimensional image of the target area;
[0031] Completing the three-dimensional model through the two-dimensional image of the target area to obtain a target three-dimensional model;
[0032] The volume of the object to be tested is determined according to the target three-dimensional model.
[0033] The disclosed embodiments ensure that the image acquisition device can acquire a two-dimensional image of the target area by determining the target area of the object to be tested when the three-dimensional model is determined to be incomplete, and adjusting the shooting position and shooting angle of the image acquisition device and / or adjusting the position of the workbench according to the target area; and can automatically identify the target area and adjust the shooting parameters (i.e., the shooting position of the image acquisition device or the position of the workbench), thereby reducing manual intervention and improving the efficiency and reliability of automatic detection and completion of the target area. Preferably, the three-dimensional model is completed through the two-dimensional image of the target area to obtain the target three-dimensional model, which can greatly improve the geometric accuracy of the model, especially in areas where the model is incomplete or blocked.
[0034] In an embodiment of the present disclosure, adjusting the shooting position and shooting angle of the image acquisition device according to the target area, or adjusting the position of the workbench, includes:
[0035] If the target area is a recessed area of the object to be tested, adjust the position of the image acquisition device and / or adjust the position of the workbench so that the image acquisition device and the target area are in the same vertical direction; and adjust the camera direction of the image acquisition device so that the camera direction is perpendicular to the upper end surface of the workbench.
[0036] The disclosed embodiment adjusts the position of the image acquisition device, the direction of the camera, and / or the position of the workbench so that the image acquisition device and the target area are in the same vertical direction, and the direction of the camera is perpendicular to the upper end surface of the workbench, thereby ensuring that the image acquisition device can capture the image of the recessed area, thereby achieving the effect of completing the three-dimensional model. By calculating the volume of the completed three-dimensional model, the volume prediction accuracy of the object to be tested is also improved to a certain extent.
[0037] In the embodiment of the present disclosure, the shooting position of the image acquisition device is adjusted in the following manner:
[0038] The first sliding mechanism is controlled to drive the third crossbar to move in the first preset direction, so that the image acquisition device moves in the first preset direction.
[0039] In an embodiment of the present disclosure, the method further includes:
[0040] The second sliding mechanism is controlled to drive the first crossbar and the second crossbar to move in the second preset direction, so that the image acquisition device moves in the second preset direction.
[0041] In the embodiment of the present disclosure, performing three-dimensional reconstruction based on the multiple two-dimensional images to obtain a three-dimensional model of the object to be tested includes:
[0042] extracting image features of each two-dimensional image;
[0043] Based on the image features of each two-dimensional image, a correspondence relationship between two-dimensional image pairs is established; the two-dimensional image pair refers to two two-dimensional images with overlapping areas among the multiple two-dimensional images; the correspondence relationship refers to a one-to-one correspondence between the imaging points of the same physical space point of the object to be tested in the two two-dimensional images;
[0044] Three-dimensional reconstruction is performed according to the corresponding relationship to obtain a three-dimensional model of the object to be tested.
[0045] The third aspect of the present disclosure provides an over-packaging detection device, the device comprising:
[0046] A data acquisition module, used to acquire a plurality of two-dimensional images of the object to be tested set at different viewing angles and the weight of the object to be tested, which are set on the data acquisition device; the plurality of two-dimensional images are acquired by the image acquisition device, and the weight is acquired by the weight acquisition device;
[0047] A three-dimensional reconstruction module, used for performing three-dimensional reconstruction based on the multiple two-dimensional images to obtain a three-dimensional model of the object to be tested;
[0048] A model judgment module, used to judge whether the three-dimensional model is complete;
[0049] A volume determination module, configured to determine the volume of the object to be tested according to the three-dimensional model if the three-dimensional model is complete;
[0050] The over-packaging determination module is used to determine whether the object to be tested is over-packed according to the volume and weight of the object to be tested.
[0051] An embodiment of the fourth aspect of the present disclosure provides an electronic device, which includes a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the excessive packaging detection method described in the first aspect by executing the computer instructions.
[0052] An embodiment of the fifth aspect of the present disclosure provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the excessive packaging detection method described in the first aspect above.
[0053] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will become apparent from the following description or be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] By reading the detailed description of the preferred embodiment below, various other advantages and benefits will become clear to those of ordinary skill in the art. The accompanying drawings are only used for the purpose of illustrating the preferred embodiment and are not considered to be limitations of the present disclosure. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings.
[0055] In the attached picture:
[0056] Figure 1 A schematic diagram of the structure of an over-packaging detection system provided by an embodiment of the present disclosure is shown;
[0057] Figure 2 A schematic diagram of the structure of another excessive packaging detection system provided by an embodiment of the present disclosure is shown;
[0058] Figure 3 A schematic diagram of the structure of another excessive packaging detection system provided by an embodiment of the present disclosure is shown;
[0059] Figure 4 A schematic diagram of the structure of another excessive packaging detection system provided by an embodiment of the present disclosure is shown;
[0060] Figure 5 A schematic diagram of the structure of another excessive packaging detection system provided by an embodiment of the present disclosure is shown;
[0061] Figure 6 A schematic diagram of the structure of another excessive packaging detection system provided by an embodiment of the present disclosure is shown;
[0062] Figure 7 A schematic diagram of a process of an over-packaging detection method provided by an embodiment of the present disclosure is shown;
[0063] Figure 8 A schematic diagram of the structure of an over-packaging detection device provided by an embodiment of the present disclosure is shown;
[0064] Fig. 9 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure is shown;
[0065] Fig.10 A schematic diagram of a storage medium provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION
[0066] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0067] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in the present disclosure should have the common meanings understood by those skilled in the art to which the present disclosure belongs.
[0068] According to an embodiment of the present disclosure, an over-packaging detection system is provided. Figure 1 is a structural diagram of an over-packaging detection device according to an embodiment of the present disclosure, such as Figure 1 As shown, the system includes:
[0069] Control device a1 and data acquisition device a2;
[0070] The data acquisition device a2 includes a rectangular bracket 101, an image acquisition device 102 arranged on the top of the rectangular bracket 101, a weight acquisition device 104 and a workbench 103 arranged at the bottom of the rectangular bracket 101, and the workbench 103 is located above the upper end surface of the weight acquisition device 104; a rotating mechanism 105 is provided at the connection between the workbench 103 and the weight acquisition device 104, and the rotating mechanism 105 is fixedly connected to the lower end surface of the workbench 103.
[0071] The control device a1 is used to send a driving instruction to the data acquisition device a2 to control the field of view of the camera of the image acquisition device 102 to cover the entire upper end surface of the workbench 103, and to control the workbench 103 to rotate according to a preset angle in a direction parallel to the top of the rectangular support 101;
[0072] The control device a1 is also used to receive multiple two-dimensional images of the object to be tested captured by the image acquisition device 102 and the weight collected by the weight acquisition device 104 when the object to be tested is placed on the end surface of the workbench 103, and determine whether the object to be tested is over-packaged based on the multiple two-dimensional images and the weight.
[0073] In some specific embodiments, the size of the rectangular bracket 101 can be set according to the size of each internal component and the size of the object to be tested, which is not specifically limited here. For example, the overall size of the rectangular bracket can be set to 1400mm*1300mm*1000mm.
[0074] In some specific embodiments, the image acquisition device 102 may be a binocular camera or two monocular cameras; when the image acquisition device 102 is two monocular cameras, the two monocular cameras are arranged horizontally, and there is a certain horizontal distance between them. The image acquisition device 102 is used to realize 3D scanning of the object to be measured, and adopts a high-resolution, high-frame-rate, and high-dynamic industrial camera to perform three-dimensional imaging of the object to be measured in a large range. Its parameters are shown in Table 1:
[0075] Table 1:
[0076]
[0077] In some specific embodiments, Figure 2 As shown, a driving motor 106 is also provided on the lower end surface of the workbench 103; the driving motor is connected to the rotating mechanism 105, and is used to drive the rotating mechanism 105 to rotate, so as to drive the workbench 103 to rotate at a preset angle in a direction parallel to the top of the rectangular bracket 101; wherein the preset angle can be 360 degrees in one direction, or 180 degrees in two opposite directions.
[0078] In some specific embodiments, the weight collection device 104 may use a high-precision weighing sensor to measure the weight value of the object to be measured in real time.
[0079] In some specific embodiments, Figure 3 As shown, the top of the rectangular bracket 101 is provided with a first sliding mechanism 301, a first crossbar 302 and a second crossbar 303 parallel to each other, and a third crossbar 304 slidably arranged on the first crossbar 302 and the second crossbar 303;
[0080] The image acquisition device 102 is arranged on the third crossbar 304; the third crossbar 304 is perpendicular to the first crossbar 302 or the second crossbar 303; the first sliding mechanism 301 is used to drive the third crossbar 304 to move in a first preset direction; the preset direction is the setting direction of the first crossbar 302 and / or the second crossbar 303, for example Figure 3 The “305” in the video.
[0081] The data acquisition device a2 is used to send the shooting angle of the image acquisition device 102 to the control device a1;
[0082] The data acquisition device a2 is also used to receive the left and right movement instructions of the control device a1, and drive the image acquisition device 102 to move left and right by controlling the first sliding mechanism 301, so that the field of view of the image acquisition device 102 covers the entire upper end surface of the workbench 103, or collects a two-dimensional image of the upper end surface of the recessed area of the object to be tested; the left and right movement instructions are determined by the control device a1 according to the shooting angle.
[0083] In the embodiment of the present disclosure, by arranging the first sliding mechanism 301, the first crossbar 302, the second crossbar 303, and the third crossbar 304 on the top of the rectangular bracket 101, and installing the image acquisition device 102 on the third crossbar 304, the following purposes can be achieved:
[0084] When the object to be tested placed on the workbench 103 is a regular object, the control device a1 will determine the left and right movement instruction 1 according to the position of the image acquisition device 102, and send it to the data acquisition device a2; after receiving the left and right movement instruction 1, the data acquisition device a2 will control the first sliding mechanism 301 to move the image acquisition device 102 to the target position corresponding to the left and right movement instruction 1; the field of view of the image acquisition device 102 at the target position can completely cover the upper end surface of the workbench, and then through the cooperation of the image acquisition device 102 and the rotating mechanism 105, the image acquisition device 102 can capture two-dimensional images of the object to be tested at various angles, and then construct a three-dimensional model based on multiple two-dimensional images, that is, a three-dimensional point cloud.
[0085] When the object to be tested placed on the workbench 103 is an irregular object, for example, there is a recessed area on the surface of the object, the image acquisition device 102 cannot capture the two-dimensional image of the recessed area at the target position, resulting in an incomplete constructed three-dimensional model; therefore, the control device a1 will re-determine the left and right movement instructions 2 according to the position of the recessed area, and send it to the data acquisition device a2, so that the data acquisition device a2 controls the first sliding mechanism 301 to move the image acquisition device 102 to the target position corresponding to the left and right movement instructions 2, thereby capturing the two-dimensional image of the recessed area, and then constructing a complete three-dimensional model.
[0086] In some specific embodiments, Figure 4 As shown, a vertical rod is respectively provided at the four corners of the rectangular support 101; wherein the top ends of the first vertical rod 401 and the second vertical rod 402 are respectively connected to the two ends of the first crossbar 302; the top ends of the third vertical rod 403 and the fourth vertical rod 404 are respectively connected to the two ends of the second crossbar 303;
[0087] The rectangular bracket 101 is further provided with a second sliding mechanism for driving the first crossbar 302 and the second crossbar 303 to move in a second preset direction; the second preset direction is the setting direction of the first vertical rod, the second vertical rod, the third vertical rod and / or the fourth vertical rod, for example Figure 4 The "405" in the message.
[0088] The data acquisition device a2 is also used to receive the up and down movement instructions of the control device a1, and drive the image acquisition device 102 to move up and down by controlling the second sliding mechanism, so that the field of view of the image acquisition device 102 covers the entire upper end surface of the workbench, or collects a two-dimensional image of the upper end surface of the recessed area of the object to be tested; the up and down movement instructions are determined by the control device a1 according to the shooting angle.
[0089] The disclosed embodiment, through the second sliding mechanism and four vertical rods arranged at the four corners of the rectangular bracket 101, can control the image acquisition device 102 to move vertically up and down, so that the image acquisition device 102 can capture two-dimensional images of the object to be tested at more angles, thereby ensuring the integrity of the constructed three-dimensional model.
[0090] In some specific embodiments, Figure 5 As shown, the bottom of the rectangular bracket 101 is also provided with a third sliding mechanism 501, a fourth crossbar 502 and a fifth crossbar 503 which are parallel to each other, and a sixth crossbar 504 which is slidably arranged on the fourth crossbar 502 and the fifth crossbar 503; the workbench 103 and the weight collection device 104 are arranged on the sixth crossbar 504; the sixth crossbar 504 is perpendicular to the fourth crossbar 502 or the fifth crossbar 503; the third sliding mechanism 501 is used to drive the sixth crossbar 504 to move in a third preset direction; the third preset direction is the setting direction of the fourth crossbar 502 and / or the fifth crossbar 503, for example Figure 5 The “505” in the video.
[0091] The disclosed embodiment arranges a third sliding mechanism 501, a fourth cross bar 502, a fifth cross bar 503, and a sixth cross bar 504 at the bottom of the rectangular bracket 101. The third sliding mechanism 501 can be controlled to drive the sixth cross bar 504 to move in a third preset direction 505, and the image acquisition device 102 and the workbench 103 can be controlled to move at the same time, so that the image acquisition device 102 can be more convenient for the image acquisition device 102 to capture two-dimensional images of the object to be tested at more angles, thereby ensuring the integrity of the constructed three-dimensional model.
[0092] In some specific embodiments, the fourth crossbar 502 and the fifth crossbar 503 overlap with the first crossbar 302 and the second crossbar 303 in the vertical direction.
[0093] In some specific embodiments, Figure 6 As shown, the rectangular support 101 also includes a target crossbar 601; the target crossbar 601 is slidably set on the third crossbar 304, and the sliding direction of the target crossbar 601 is perpendicular to the first preset direction 305; the image acquisition device 102 is set on the target crossbar 601.
[0094] The disclosed embodiment sets a slidable target cross bar 601 on the third cross bar 304, and sets the image acquisition device 102 on the target cross bar 601. It can control the image acquisition device to move along the sliding direction of the target cross bar 601, so that two-dimensional images of the object to be tested at more angles can be captured, which helps to build the integrity of the three-dimensional model and further improve the construction efficiency of the three-dimensional model.
[0095] In some specific embodiments, Figure 4 As shown, the rectangular support 101 is also provided with a data acquisition device 107 for collecting motion parameters of each sliding mechanism.
[0096] According to an embodiment of the present disclosure, an embodiment of an over-packaging detection method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0097] In this embodiment, a method for detecting excessive packaging is provided, and the method can apply the control device in the excessive packaging detection system described in the above embodiment; Figure 7 is a flow chart of an over-packaging detection method according to an embodiment of the present disclosure, such as Figure 7 As shown, the process includes the following steps:
[0098] Step S101, obtaining a plurality of two-dimensional images of an object to be tested at different viewing angles and the weight of the object to be tested set on a data acquisition device.
[0099] Specifically, the weight of the above-mentioned object to be measured is acquired by the weight acquisition device 104. The above-mentioned multiple two-dimensional images under different viewing angles are acquired by the image acquisition device 102 and the rotating mechanism 105 in cooperation with each other, for example: the rotating mechanism drives the object to be measured placed on the workbench to rotate at a preset rate, and during the rotation process, the image acquisition device takes an image of the object to be measured to obtain multiple two-dimensional images at different angles; wherein, the preset rate of the rotating mechanism and the image acquisition rate of the image acquisition device can be set according to actual conditions, and are not specifically limited here.
[0100] Step S102: Perform three-dimensional reconstruction based on the multiple two-dimensional images to obtain a three-dimensional model of the object to be tested.
[0101] In some specific embodiments, the above step S102 includes steps S1021 to S1023:
[0102] Step S1021, extracting image features of each two-dimensional image.
[0103] Specifically, the image features include but are not limited to the feature points, feature lines and feature regions of the image. The method for implementing feature extraction is not specifically limited, as long as the feature extraction function can be implemented.
[0104] Step S1022: establishing a correspondence between two-dimensional image pairs based on the image features of each two-dimensional image.
[0105] Specifically, the two-dimensional image pair refers to two two-dimensional images with overlapping areas among the multiple two-dimensional images, such as two two-dimensional images captured from adjacent perspectives; the corresponding relationship refers to a one-to-one correspondence between the imaging points of the same physical space point of the object to be tested in the two two-dimensional images, for example: the kitten's nose in two-dimensional image 1 corresponds to the kitten's nose in two-dimensional image 2.
[0106] Step S1023: Perform three-dimensional reconstruction according to the corresponding relationship to obtain a three-dimensional model of the object to be tested.
[0107] Specifically, before 3D reconstruction, camera calibration is required to solve the internal and external parameters of the camera, and then the 3D scene information is restored based on the correspondence between the internal and external parameters of the camera and the 2D image pair to obtain the 3D model of the object to be measured. Among them, since the accuracy of 3D reconstruction is affected by factors such as matching accuracy and the error of the internal and external parameters of the camera, it is necessary to perform multiple rounds of iterative optimization work on the previous steps to ensure high accuracy and small errors in each link.
[0108] Step S103, determining whether the three-dimensional model is complete.
[0109] In some specific embodiments, the above step S103 further includes steps S1031 and S1032:
[0110] Step S1031: If the three-dimensional model covers all observable areas of the object to be tested, it is determined that the three-dimensional model is complete.
[0111] Specifically, the observable area here includes, but is not limited to: various observable areas on a regular object or an irregular object, such as a plane area, a convex area, and a concave area.
[0112] Step S1032: If the three-dimensional model does not cover all observable areas of the object to be tested, it is determined that the three-dimensional model is incomplete.
[0113] Step S104: if the three-dimensional model is complete, determining the volume of the object to be tested according to the three-dimensional model.
[0114] Specifically, when the three-dimensional model is complete, the volume of the object to be tested can be determined based on the three-dimensional model. Otherwise, if the three-dimensional model is incomplete, it is necessary to collect images of the object to be tested again until the constructed three-dimensional model is complete.
[0115] In some specific embodiments, the method further comprises steps b1 to b4:
[0116] Step b1: if the three-dimensional model is incomplete, determine the target area of the object to be tested.
[0117] Specifically, the target area refers to the observable area of the object to be tested that is not covered by the three-dimensional model. For example, when the object to be tested is too large, there may be areas that are not captured by the image acquisition device. For another example: there is a sunken area in the object to be tested, and the image of the sunken area cannot be captured by the current shooting position and shooting angle of the image acquisition device.
[0118] Step b2: adjusting the shooting position and shooting angle of the image acquisition device according to the target area, and / or adjusting the position of the workbench, so that the image acquisition device can capture a two-dimensional image of the target area.
[0119] Specifically, the shooting angle of the image acquisition device can be adjusted by adjusting the rotating device of the image acquisition device itself, for example Figure 1 The image acquisition device 102 in.
[0120] Specifically, the shooting position of the image acquisition device can be adjusted in the following ways:
[0121] Method 1: Figure 3As shown, the first sliding mechanism 301 is controlled to drive the third crossbar 304 to move in the first preset direction 305 , so that the image acquisition device moves in the first preset direction; wherein the image acquisition device is arranged on the third crossbar 304 .
[0122] Method 2: If Figure 4 As shown, the second sliding mechanism is controlled to drive the first cross bar 302 and the second cross bar 303 to move in the second preset direction 405, so that the image acquisition device 102 moves in the second preset direction; wherein the image acquisition device 102 is arranged on the third cross bar 304; the third cross bar 304 is arranged on the first cross bar 302 and the second cross bar 303.
[0123] Method 3: If Figure 6 As shown, the target cross bar 601 is controlled to move in its sliding direction so that the image acquisition device 102 moves in the sliding direction; wherein the image acquisition device 102 is arranged on the target cross bar 601, and the sliding direction is perpendicular to the first preset direction 305.
[0124] More specifically, the position of the workbench can be adjusted in the following ways:
[0125] Method 4: Figure 5 As shown, the third sliding mechanism 501 is controlled to drive the sixth crossbar 504 to move in the third preset direction 505 , so that the image acquisition device moves in the third preset direction 505 ; wherein the workbench is arranged on the sixth crossbar 504 .
[0126] In some specific embodiments, the above step b2 further includes step b21:
[0127] Step b21, if the target area is a recessed area of the object to be tested, adjust the position of the image acquisition device and / or adjust the position of the workbench so that the image acquisition device and the target area are in the same vertical direction; and adjust the camera direction of the image acquisition device so that the camera direction is perpendicular to the upper end surface of the workbench.
[0128] In step b21, when the observable area of the object to be tested that is not covered by the three-dimensional model is a recessed area, it is necessary to move the image acquisition device to a position directly above the recessed area, and point the camera of the image acquisition device toward the recessed area, so as to capture a two-dimensional image of the recessed area. The movement of the image acquisition device can be achieved by the above-mentioned methods 1, 2, and 3, or the position of the workbench can be adjusted by the above-mentioned method 4, so as to achieve the purpose of indirectly adjusting the position of the image acquisition device.
[0129] Step b3, completing the three-dimensional model using the two-dimensional image of the target area to obtain a target three-dimensional model.
[0130] Specifically, the two-dimensional image of the target area can be used to complete the areas not captured in the three-dimensional model, thereby obtaining a target three-dimensional model covering all observable areas of the object to be tested.
[0131] Step b4, determining the volume of the object to be tested according to the target three-dimensional model.
[0132] Specifically, the volume of the object to be measured is calculated by using a high-precision numerical analysis and calculation method through the reconstructed three-dimensional model of the object to be measured. The selection of the high-precision numerical analysis and calculation method is not specifically limited, and the volume of the object to be measured can be calculated through the three-dimensional model.
[0133] Step S105: determining whether the object to be tested is over-packaged according to the volume and weight of the object to be tested.
[0134] Specifically, after calculating the volume and weight of the object to be tested, the packaging void ratio and packaging mass ratio of the object to be tested can be calculated according to the volume, weight, number of packaging layers and number of contents of the object to be tested; then the packaging void ratio and packaging mass ratio are compared with the corresponding thresholds to determine whether the object to be tested is over-packaged.
[0135] Corresponding to the implementation of the above over-packaging detection method, the present disclosure also provides an over-packaging detection device for executing the over-packaging detection method described in the above embodiment. Figure 8 As shown, the over-packaging detection device includes:
[0136] A data acquisition module, used to acquire a plurality of two-dimensional images of the object to be tested set at different viewing angles and the weight of the object to be tested, which are set on the data acquisition device; the plurality of two-dimensional images are acquired by the image acquisition device, and the weight is acquired by the weight acquisition device;
[0137] A three-dimensional reconstruction module, used for performing three-dimensional reconstruction based on the multiple two-dimensional images to obtain a three-dimensional model of the object to be tested;
[0138] A model judgment module, used to judge whether the three-dimensional model is complete;
[0139] A volume determination module, configured to determine the volume of the object to be tested according to the three-dimensional model if the three-dimensional model is complete;
[0140] The over-packaging determination module is used to determine whether the object to be tested is over-packed according to the volume and weight of the object to be tested.
[0141] Optionally, the model judgment module is further used to: if the three-dimensional model covers all observable areas of the object to be tested, determine that the three-dimensional model is complete; if the three-dimensional model does not cover all observable areas of the object to be tested, determine that the three-dimensional model is incomplete.
[0142] Optionally, the device further comprises:
[0143] A target area determination module, used to determine a target area of the object to be tested if the three-dimensional model is incomplete; the target area refers to an observable area of the object to be tested that is not covered by the three-dimensional model;
[0144] A position adjustment module, used to adjust the shooting position and shooting angle of the image acquisition device according to the target area, and / or adjust the position of the workbench, so that the image acquisition device can capture a two-dimensional image of the target area;
[0145] A model completion module, used to complete the three-dimensional model through the two-dimensional image of the target area to obtain a target three-dimensional model;
[0146] The volume determination module is used to determine the volume of the object to be tested according to the target three-dimensional model.
[0147] Optionally, the position adjustment module is also used to: if the target area is a recessed area of the object to be tested, adjust the position of the image acquisition device, and / or adjust the position of the workbench so that the image acquisition device and the target area are in the same vertical direction; and adjust the camera direction of the image acquisition device so that the camera direction is perpendicular to the upper end surface of the workbench.
[0148] Optionally, the position adjustment module is further used to control the first sliding mechanism to drive the third crossbar to move in the first preset direction, so that the image acquisition device moves in the first preset direction.
[0149] Optionally, the position adjustment module is further used to control the second sliding mechanism to drive the first crossbar and the second crossbar to move in the second preset direction, so that the image acquisition device moves in the second preset direction.
[0150] The over-packaging detection device provided in the above-mentioned embodiments of the present disclosure and the over-packaging detection method provided in the embodiments of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.
[0151] The present disclosure also provides an electronic device to perform the above-mentioned over-packaging detection method. Fig. 9 , which shows a schematic diagram of an electronic device provided by some embodiments of the present disclosure. Fig. 9 As shown, the electronic device 9 includes: a processor 900, a memory 901, a bus 902 and a communication interface 903, wherein the processor 900, the communication interface 903 and the memory 901 are connected via the bus 902; the memory 901 stores a computer program that can be run on the processor 900, and when the processor 900 runs the computer program, the over-packaging detection method provided in the aforementioned embodiment of the present disclosure is executed.
[0152] The memory 901 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 903 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.
[0153] The bus 902 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 901 is used to store programs, and the processor 900 executes the program after receiving an execution instruction. The overpackaging detection method disclosed in the above-mentioned embodiment may be applied to the processor 900, or implemented by the processor 900.
[0154] The processor 900 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 900 or the instruction in the form of software. The above processor 900 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 901, and the processor 900 reads the information in the memory 901 and completes the steps of the above method in combination with its hardware.
[0155] The electronic device provided by the embodiment of the present disclosure and the excessive packaging detection method provided by the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented by them.
[0156] The present disclosure also provides a computer-readable storage medium corresponding to the excessive packaging detection method provided in the above embodiment. Fig.10 The computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is run by a processor, it executes the over-packaging detection method provided by any of the aforementioned embodiments.
[0157] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.
[0158] The computer-readable storage medium provided in the above-mentioned embodiments of the present disclosure and the excessive packaging detection method provided in the embodiments of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.
[0159] It should be noted that:
[0160] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present disclosure can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail so as not to obscure the understanding of this description.
[0161] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present disclosure, the various features of the present disclosure are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting that the claimed disclosure requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present disclosure.
[0162] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of this disclosure and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.
[0163] The above is only a preferred specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed in the present disclosure should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.
Claims
1. An over-packaging detection system, characterized in that: The system comprises: a control device and a data acquisition device; The data acquisition device comprises a rectangular bracket, an image acquisition device arranged on the top of the rectangular bracket, a weight acquisition device and a workbench arranged at the bottom of the rectangular bracket, wherein the workbench is located above the upper end surface of the weight acquisition device; a rotating mechanism is arranged at the connection between the workbench and the weight acquisition device, and the rotating mechanism is fixedly connected to the lower end surface of the workbench; The control device is used to send a driving instruction to the data acquisition device to control the field of view of the camera of the image acquisition device to cover the entire upper end surface of the workbench, and to control the workbench to rotate according to a preset angle in a direction parallel to the top of the rectangular support; The control device is also used to receive multiple two-dimensional images of the object to be tested captured by the image acquisition device and the weight collected by the weight acquisition device when the object to be tested is placed on the end surface of the workbench, and determine whether the object to be tested is over-packaged based on the multiple two-dimensional images and the weight.
2. The system according to claim 1, characterized in that The top of the rectangular bracket is provided with a first sliding mechanism, a first crossbar and a second crossbar parallel to each other, and a third crossbar slidably arranged on the first crossbar and the second crossbar; the image acquisition device is arranged on the third crossbar; the third crossbar is perpendicular to the first crossbar or the second crossbar; the first sliding mechanism is used to drive the third crossbar to move in a first preset direction; the preset direction is the setting direction of the first crossbar and / or the second crossbar; The data acquisition device is used to send the shooting angle of the image acquisition device to the control device; The data acquisition device is also used to receive left and right movement instructions from the control device, and drive the image acquisition device to move left and right by controlling the first sliding mechanism, so that the field of view of the image acquisition device covers the entire upper end surface of the workbench, or collects a two-dimensional image of the upper end surface of the recessed area of the object to be tested; the left and right movement instructions are determined by the control device according to the shooting angle.
3. The system according to claim 2, characterized in that A vertical rod is respectively arranged at the four corners of the rectangular bracket; wherein the top ends of the first vertical rod and the second vertical rod are respectively connected to the two ends of the first cross rod; the top ends of the third vertical rod and the fourth vertical rod are respectively connected to the two ends of the second cross rod; the rectangular bracket is also provided with a second sliding mechanism for driving the first cross rod and the second cross rod to move in a second preset direction; the second preset direction is the setting direction of the first vertical rod, the second vertical rod, the third vertical rod and / or the fourth vertical rod; The data acquisition device is also used to receive the up and down movement instructions of the control device, and drive the image acquisition device to move up and down by controlling the second sliding mechanism, so that the field of view of the image acquisition device covers the entire upper end surface of the workbench, or collects a two-dimensional image of the upper end surface of the recessed area of the object to be tested; the up and down movement instructions are determined by the control device according to the shooting angle.
4. A method for detecting excessive packaging, characterized in that: A control device for an over-packaging detection system according to any one of claims 1 to 3, wherein the method comprises: Acquire a plurality of two-dimensional images of the object to be measured at different viewing angles and the weight of the object to be measured set on the data acquisition device; the plurality of two-dimensional images are acquired by the image acquisition device, and the weight is acquired by the weight acquisition device; Performing three-dimensional reconstruction based on the multiple two-dimensional images to obtain a three-dimensional model of the object to be tested; Determining whether the three-dimensional model is complete; If the three-dimensional model is complete, determining the volume of the object to be tested according to the three-dimensional model; Determine whether the object to be tested is over-packaged according to the volume and weight of the object to be tested.
5. The method according to claim 4, characterized in that Determining whether the three-dimensional model is complete includes: If the three-dimensional model covers all observable areas of the object to be tested, it is determined that the three-dimensional model is complete; If the three-dimensional model does not cover all observable areas of the object to be tested, it is determined that the three-dimensional model is incomplete.
6. The method according to claim 5, characterized in that The method further comprises: If the three-dimensional model is incomplete, determining a target area of the object to be tested; the target area refers to an observable area of the object to be tested that is not covered by the three-dimensional model; Adjusting the shooting position and shooting angle of the image acquisition device according to the target area, and / or adjusting the position of the workbench, so that the image acquisition device can capture a two-dimensional image of the target area; Completing the three-dimensional model through the two-dimensional image of the target area to obtain a target three-dimensional model; The volume of the object to be tested is determined according to the target three-dimensional model.
7. The method according to claim 6, characterized in that Adjusting the shooting position and shooting angle of the image acquisition device according to the target area, or adjusting the position of the workbench, includes: If the target area is a recessed area of the object to be tested, adjust the position of the image acquisition device and / or adjust the position of the workbench so that the image acquisition device and the target area are in the same vertical direction; and adjust the camera direction of the image acquisition device so that the camera direction is perpendicular to the upper end surface of the workbench.
8. The method according to claim 6, characterized in that The shooting position of the image acquisition device is adjusted by: The first sliding mechanism is controlled to drive the third crossbar to move in the first preset direction, so that the image acquisition device moves in the first preset direction.
9. The method according to claim 8, characterized in that The method further comprises: The second sliding mechanism is controlled to drive the first crossbar and the second crossbar to move in the second preset direction, so that the image acquisition device moves in the second preset direction.
10. The method according to claim 4, characterized in that Performing three-dimensional reconstruction based on the multiple two-dimensional images to obtain a three-dimensional model of the object to be tested includes: extracting image features of each two-dimensional image; Based on the image features of each two-dimensional image, a correspondence relationship between two-dimensional image pairs is established; the two-dimensional image pair refers to two two-dimensional images with overlapping areas among the multiple two-dimensional images; the correspondence relationship refers to a one-to-one correspondence between the imaging points of the same physical space point of the object to be tested in the two two-dimensional images; A three-dimensional reconstruction is performed according to the corresponding relationship to obtain a three-dimensional model of the object to be tested.
11. An over-packaging detection device, characterized in that: The device comprises: A data acquisition module, used to acquire a plurality of two-dimensional images of the object to be tested set at different viewing angles and the weight of the object to be tested, which are set on the data acquisition device; the plurality of two-dimensional images are acquired by the image acquisition device, and the weight is acquired by the weight acquisition device; A three-dimensional reconstruction module, used for performing three-dimensional reconstruction based on the multiple two-dimensional images to obtain a three-dimensional model of the object to be tested; A model judgment module, used to judge whether the three-dimensional model is complete; A volume determination module, configured to determine the volume of the object to be tested according to the three-dimensional model if the three-dimensional model is complete; The over-packaging determination module is used to determine whether the object to be tested is over-packed according to the volume and weight of the object to be tested.
Citation Information
Patent Citations
Method for calculating object package size, and storage device
CN109373893A
Object packaging volume detection method and device, terminal and readable storage medium
CN112833775A
Commodity over-packing detection device based on two-dimensional scanning
CN204473278U
Winding packer with weighing function
CN219584530U
Excessive packaging volume measuring device
CN220136279U
