Method, apparatus, control device, system and storage medium for automatically capturing images

Abstract

The embodiment of the present specification provides a method, device, control equipment, system and storage medium for automatically collecting images, first movement information of a mechanical arm and second movement information of a turntable are determined through pre-acquired weight, size and other information of a target commodity, the mechanical arm is controlled to transfer the target commodity to the turntable according to the first movement information, the turntable is controlled to move according to the second movement information, and the camera is controlled to collect images of the target commodity in the movement process of the turntable, so that automatic collection of commodity images is realized, and the image collection speed and efficiency are effectively improved.

Description

Technical Field

[0001] The embodiments described in this specification relate to the field of second-hand goods recycling technology, specifically to automatic control technology in the field of second-hand goods recycling technology, and more specifically, to a method, apparatus, device, system, and storage medium for automatically acquiring images. Background Technology

[0002] E-commerce platforms typically use online image displays to enhance consumers' understanding of the products. For example, secondhand e-commerce platforms display images of secondhand goods from various angles online to help consumers understand the condition of the goods and thus promote secondhand transactions.

[0003] In existing technologies, product images are generally collected through manual photography, but manual collection is slow and inefficient. Summary of the Invention

[0004] This specification provides a method, apparatus, control device, system, and storage medium for automatically acquiring images, thereby addressing the problems of slow speed and low efficiency in acquiring commodity images in the prior art.

[0005] One embodiment of this specification provides a method for automatically acquiring images, including:

[0006] Based on the pre-acquired product information of the target product, the first movement information of the robotic arm and the second movement information of the turntable are determined; the product information includes product weight information and product size information;

[0007] The robotic arm is controlled to transfer the target product onto the turntable according to the first movement information.

[0008] The turntable is controlled to move according to the second movement information, and the camera is controlled to capture images of the target product during the movement of the turntable.

[0009] One embodiment of this specification provides an apparatus for automatically acquiring images, comprising:

[0010] The determination module is used to determine the first movement information of the robotic arm and the second movement information of the turntable based on the pre-acquired product information of the target product; the product information includes product weight information and product size information.

[0011] The first control module is used to control the robotic arm to transfer the target product to the turntable according to the first movement information;

[0012] The second control module is used to control the turntable to move according to the second movement information, and to control the camera to capture images of the target product during the movement of the turntable.

[0013] One embodiment of this specification provides a control device, comprising:

[0014] Memory and processor;

[0015] The memory is used to store programs;

[0016] The processor is configured to implement the automatic image acquisition method described above by running a program in the memory.

[0017] One embodiment of this specification provides an automatic image acquisition system, including a robotic arm, a turntable, a camera, and the control device described above;

[0018] The control device is communicatively connected to the robotic arm, the turntable, and the camera, respectively.

[0019] One embodiment of this specification provides a storage medium storing a computer program, which, when executed by a processor, implements the automatic image acquisition method described in any one of the above embodiments.

[0020] The various implementation methods provided in this specification determine the first movement information of the robotic arm and the second movement information of the turntable by pre-acquired information such as the weight and size of the target product. The robotic arm is controlled to transfer the target product onto the turntable according to the first movement information, and the turntable is controlled to move according to the second movement information. During the movement of the turntable, the camera is controlled to capture images of the target product, thereby realizing automatic acquisition of product images and effectively improving the speed and efficiency of image acquisition. Attached Figure Description

[0021] Figure 1 This is a schematic diagram illustrating an application scenario provided for one embodiment of this specification.

[0022] Figure 2 This is a schematic diagram illustrating another application scenario provided for one embodiment of this specification.

[0023] Figure 3 This is a schematic diagram of the structure of an automatic image acquisition system provided for one embodiment of this specification.

[0024] Figure 4 This is a flowchart illustrating a method for automatically acquiring images according to one embodiment of this specification.

[0025] Figure 5 This is a schematic diagram of a position calibration process provided for one embodiment of this specification.

[0026] Figure 6This is a schematic diagram of an automatic image acquisition device provided for one embodiment of this specification.

[0027] Figure 7 This is a schematic diagram of the control device provided for one embodiment of this specification. Detailed Implementation

[0028] Overview

[0029] With the advancement of internet technology, online shopping has become a very common form of shopping. To enhance consumers' understanding of products, e-commerce platforms display product images and text descriptions on their websites. Once a consumer decides to purchase, they can place an order online, thus completing the online shopping process. Currently, e-commerce platform staff typically collect product images manually, then process the images before uploading them to the product's website. However, this manual method of collecting product images is slow and inefficient.

[0030] For secondhand e-commerce platforms, due to the unique nature of the items traded, each item needs to be photographed and uploaded so that consumers can understand its condition. However, continuing to use existing technology to manually collect product images would significantly slow down the image collection process, resulting in excessively long listing cycles for secondhand goods.

[0031] Therefore, it is necessary to provide a method, apparatus, control device, system, and storage medium for automatically acquiring images, which can automatically acquire product images by controlling the coordinated operation of a robotic arm, turntable, and camera, thereby solving the technical problems of slow speed and low efficiency in manually acquiring product images.

[0032] Scenario Example

[0033] This specification provides an example application scenario for an automatic image acquisition method. The application scenario is an intelligent control system, which includes a control device and a robotic arm, turntable, camera, and supplementary lighting, all communicatively connected to the control device.

[0034] The control device can be any device with computing, storage and communication functions, such as servers, desktop computers, laptops, tablets, smartphones, etc., without limitation.

[0035] A robotic arm is a mechatronic device that simulates the functions of a human arm, wrist, and hand. It can grasp a target product to be photographed and move it to a predetermined location along a set route. A robotic arm consists of a robotic hand, a motion mechanism, and a robotic arm control mechanism. The robotic hand grasps the target product; the motion mechanism, connected to the robotic hand, performs movements such as movement, rotation, and extension under the control of the robotic arm control mechanism, thereby moving the robotic hand; the robotic arm control mechanism communicates with a control device and responds to movement commands from the control device. These commands contain information such as the set route and position, and the robotic arm control mechanism uses these commands to control the motion mechanism to move the robotic hand, moving the target product to the predetermined location along the set route.

[0036] A turntable is a platform with a rotating function, used to fix and hold the target product to be photographed. When the turntable rotates, it causes the target product to rotate as well. Simultaneously, the turntable in this embodiment also has a tilting function, enabling control of the target product to be in a tilted state. The turntable includes a rotating shaft, a cylinder, a placement platform, and a turntable control mechanism. The placement platform is used to fix the target product; the rotating shaft rotates under the control of the turntable control mechanism, thereby causing the placement platform to rotate; the cylinder extends and retracts under the control of the turntable control mechanism, thereby controlling the placement platform to be in a tilted state. In some embodiments, the cylinder is located at the bottom of the placement platform, and when the cylinder extends, the placement platform is in a tilted state; the turntable control mechanism is communicatively connected to a control device and responds to movement commands from the control device. These movement commands include rotation and tilt information, and the turntable control mechanism can control the rotating shaft to rotate and / or control the cylinder to extend and retract based on these movement commands.

[0037] The camera can be any device with recording and communication functions, such as a webcam or a smart device with a camera, and is not limited thereto. The camera communicates with the control device, responds to shooting commands from the control device, and captures images of the target product according to the shooting commands. The images of the target product can be videos or pictures, and this embodiment is not limited thereto.

[0038] A fill light is a lighting device with communication capabilities, such as incandescent lamps, halogen lamps, fluorescent lamps, daylight lamps, and LED lights, etc., without limitation here. A fill light can respond to lighting adjustment commands from control equipment and adjust the light accordingly. For example, it can adjust brightness, color temperature, etc., according to the lighting adjustment commands.

[0039] The communication connection between the control equipment and the robotic arm, turntable, camera, and fill light can be either wired or wireless.

[0040] Please refer to Figure 1 , Figure 1This is a schematic diagram illustrating one possible application scenario of the present invention. Figure 1 In the application scenario shown, the control device 10 is connected to the robotic arm 11, turntable 12, camera 13, and fill light 14 via wires.

[0041] Specifically, Figure 1 The application scenario shown includes a data bus 15, through which the control device 10 is connected to the robotic arm 11, turntable 12, and camera 13.

[0042] Please refer to Figure 2 , Figure 2 This is a schematic diagram illustrating another possible application scenario of the present invention. Figure 2 In the application scenario shown, the control device 10 is connected to the robotic arm 11, turntable 12, camera 13, and fill light 14 via a wireless network.

[0043] Specifically, Figure 2 The application scenario shown includes gateway 16. The control device 10 and gateway 16 establish a network connection via a wide area network or a local area network. Through this network connection, the control device 10 interacts with gateway 16, thereby enabling the control device 10 to control the robotic arm 11, turntable 12, camera 13, and fill light 14 connected to gateway 15 to execute corresponding instructions.

[0044] System Architecture

[0045] This specification provides a system for automatically acquiring images. For example... Figure 3 As shown, the automatic image acquisition system includes a control device, and a robotic arm 11, a turntable 12, and a camera 13 that are communicatively connected to the control device.

[0046] The control device is used to acquire product information of the target product A to be filmed. The product information of the target product A includes product weight information and product size information. Based on the above product information, the control device can determine the size and center position of the target product A, and then determine the first movement information of the robotic arm 11, the second movement information of the turntable 12, and the filming information of the camera 13 during the filming process.

[0047] The control device sends first movement information to the robotic arm 11, enabling the robotic arm 11 to move according to the first movement information, grasp the target product A, and transfer the target product A to the turntable 12. For example, the robotic arm 11 can be positioned on one side of the conveying device 18 used to transport the target product A. After receiving the first movement information, the robotic arm 11 can grasp the target product A from the conveying device 18 and transfer it to the turntable 12.

[0048] In some embodiments, the first movement information includes the movement path of the robotic arm 11 and the position at which the robotic arm should grasp the target product A. When the robotic arm 11 grasps the target product A at the grasping position specified by the first movement information and moves the target product A along the movement path specified by the first movement information, it can deliver the target product A onto the turntable 12 so that the turntable 12 can fix the target product A.

[0049] However, since the target product A is randomly positioned on the conveyor 18, when the robotic arm 11 grabs the target product A from the conveyor 18, it may grab any position of the target product A. In such a case, if the robotic arm 11 directly transfers the target product A to the turntable 12 according to the movement path specified in the first movement information, since the current grabbing position of the robotic arm 11 may not be the grabbing position specified in the first movement information, it may not be able to accurately deliver the target product A onto the turntable 12.

[0050] Based on this, the first movement information in this embodiment also includes a positioning position. The control device can first control the robotic arm 11 to transfer the target product A to the positioning position for precise positioning according to the movement path specified in the first movement information. The positioning area where the positioning position is located is provided with a limiting device 17 for precise positioning. After precise positioning by the limiting device 17, the target product A is sent into the set precise positioning area. With this configuration, when the control device knows the coordinates of the set precise positioning area, it can control the robotic arm 11 to pick up the target product A from the set precise positioning area according to the gripping position specified in the first movement information, and then transfer the target product A to the turntable 12 according to the movement path specified in the first movement information, so that the turntable 12 can fix the target product A.

[0051] For example, such as Figure 3As shown, the limiting device 17 may include four evenly distributed cylinders, with an angle of 90 degrees between any two adjacent cylinders. When all four cylinders are in the retracted return state, the area enclosed by the four cylinders is the positioning area S, and the positioning position is any position within the positioning area S. After the control device controls the robotic arm 11 to send the target product A into the positioning area, it first controls two oppositely arranged cylinders to advance simultaneously at the same speed. Pressure sensors can be installed on the top of the extension rods of all four cylinders. The pressure sensors are communicatively connected to the control device, and the pressure sensors send the detected pressure values ​​to the control device. When the pressure values ​​received by the control device are all greater than the set value, it controls the two oppositely arranged cylinders to retract and return to their original positions. Then, it controls the other two oppositely arranged cylinders to advance at the same speed. When the pressure values ​​received by the control device are all greater than the set value, it controls the other two oppositely arranged cylinders to retract and return to their original positions. Then, the control device controls the robotic arm 11 to pick up the target product A from the set precise positioning area according to the gripping position specified in the first movement information, and then transfers the target product A to the turntable 12 according to the movement path specified in the first movement information.

[0052] In some implementations, the second movement information includes rotation information and tilt information.

[0053] Specifically, after the control device controls the robotic arm 11 to transfer the target product A onto the turntable 12, the turntable 12 fixes the target product A in place. It should be noted that the surface of the target product A that contacts the turntable 12 is the surface that does not affect the sale of the product, and this surface does not need to be photographed. For example, if the target product A is a product with a surface that does not need to be photographed, including ornaments, figurines, etc., the surface of the target product A that contacts the turntable 12 is the base that does not affect the sale of the product, and the base does not need to be photographed. It should also be noted that in this embodiment, when placing the target product A onto the conveyor 18, the operator needs to confirm that the surface of the target product A that contacts the conveyor 18 is the surface that does not affect the sale of the product, so that after the robotic arm 11 grasps the target product A and places it onto the turntable 12, the surface of the target product A that contacts the turntable 12 is the surface that does not affect the sale of the product.

[0054] The control device controls the turntable 12 to rotate according to the rotation information specified in the second movement information. Each rotation can pause for a set time. The control device controls the camera 13 to capture all sides of the target product A until all sides are captured.

[0055] The control device controls the turntable 12 to tilt toward the position of the camera 13 according to the tilt information specified in the second movement information and pauses for a set time. The control device controls the camera 13 to capture the surface of the target product A in contact with the robotic arm 11.

[0056] In this embodiment, the control device can first control the turntable 12 to rotate and photograph the side of the target product A. After the side photograph is completed, the control device can then control the turntable 12 to tilt and photograph the surface of the target product A in contact with the robotic arm 11. Alternatively, the control device can first control the turntable 12 to tilt and photograph the surface of the target product A in contact with the robotic arm 11, and then control the turntable 12 to rotate and photograph the side of the target product A. Another possible implementation is to first control the turntable 12 to rotate and photograph the side of the target product A, then control the turntable 12 to tilt during the side photographing process to photograph the surface of the target product A in contact with the robotic arm 11, and then control the turntable 12 to reset and continue rotating to photograph the side of the target product A. This embodiment is not limited in its specific implementation.

[0057] After the filming is completed, the robotic arm 11 removes the target product A from the turntable 12. For example, the control device can control the robotic arm 11 to transfer the target product A to the conveyor 18.

[0058] In some implementations, certain target products A may not have a side that does not affect their sale; that is, all sides of such target products A need to be photographed. Examples include electronic products such as mobile phones and tablets.

[0059] For example, for such a product, the first movement information also includes a shooting position. The movement path in the first movement information is to first pass through the shooting position and then through the turntable 12. When the robotic arm 11 moves the target product A according to the movement path specified in the first movement information, it moves to the shooting position specified in the first movement information. This shooting position is generally directly opposite the camera 13. The control device controls the camera 13 to shoot the surface of the target product A that will come into contact with the turntable 12. After the shooting is completed, the control device controls the robotic arm 11 to transfer the target product A onto the turntable 12. Then, the remaining surfaces are shot on the turntable 12.

[0060] In another example, for such a product, the first movement information also includes a shooting position. The movement path in the first movement information is to first pass through the turntable 12 and then through the shooting position. When the robotic arm 11 grasps the target product A and moves according to the path specified in the first movement information, it moves to the turntable 12. After shooting all surfaces on the turntable 12 except the surface in contact with the turntable 12, the control device controls the robotic arm 11 to move the target product A to the shooting position specified in the first movement information, and controls the camera 13 to shoot the surface of the target product A in contact with the turntable 12. After the shooting is completed, the control device controls the robotic arm 11 to transfer the target product A back to the conveyor 18.

[0061] In some implementations, the automatic image acquisition system also includes supplementary lighting. For example, supplementary lighting is provided on the front, rear, left, right, and top surfaces of the turntable 12 to even out the lighting during the shooting process and improve the shooting effect. The control device can control the lighting parameters of the supplementary lighting, further improving the shooting effect of the target product A.

[0062] In the above embodiments, automatic acquisition of product images is achieved, effectively improving the speed and efficiency of image acquisition.

[0063] Example method

[0064] One embodiment of this specification provides a method for automatically acquiring images. This method for automatically acquiring images can be applied to the control device in the exemplary systems described above. For example... Figure 4 As shown, the method for automatically acquiring images may include the following steps.

[0065] Step S101: Based on the pre-acquired product information of the target product, determine the first movement information of the robotic arm and the second movement information of the turntable.

[0066] The target product refers to the product for which image acquisition is required. The product information includes its weight and dimensions. Staff can pre-detect the target product's information and store it in a database. In this embodiment, the target product's information can be retrieved from the database by scanning its identification code. This identification code can be a QR code or a barcode; this embodiment is not limited to either.

[0067] It should be noted that the scanning of the identification code on the target product can be done manually or automatically by a scanning mechanism controlled by a control device; this implementation method is not limited to either method. Furthermore, to avoid the identification code affixed to the target product affecting image capture, after obtaining the product information, staff can remove the identification code from the target product and then place the target product on the conveyor device.

[0068] Based on the product information of the target product, the first movement information of the robotic arm and the second movement information of the turntable can be further determined.

[0069] The robotic arm is used to grip the target product and transfer it from the conveyor to the turntable. The first movement information includes the movement path of the robotic arm when transferring the target product to the turntable.

[0070] For example, the optimal movement path for the robotic arm to transfer goods of different weights and sizes can be determined in advance through test experiments, and the determined movement path and its association with goods of different weights and sizes can be stored in a database. In this implementation, after obtaining the product information of the target product, the movement path corresponding to the product weight information and product size information of the target product can be determined from the database and used as the movement path of the robotic arm.

[0071] Another example is the pre-training of a robotic arm path determination model. The training samples for this model consist of product weight and size information for different goods, and the training labels are pre-labeled movement paths corresponding to different training samples. The training samples are input into the robotic arm path determination model to obtain its output. Based on the output and training labels, the loss value of the model is determined, and its parameters are adjusted to reduce this loss. This training process is repeated until the loss value is less than a set value, at which point the model training is complete. It should be noted that the set value can be adjusted according to actual conditions, and this implementation does not impose limitations.

[0072] After obtaining the weight and size information of the target product, inputting the weight and size information of the target product into the robotic arm path determination model will yield the movement path output by the robotic arm path determination model.

[0073] The turntable is used to move the target product, and during the movement of the target product, it controls the camera to capture images of the target product. The second movement information includes the angle of the turntable's movement.

[0074] The process for determining the second movement information is the same as that for determining the first movement information. It can be obtained by testing the robotic arm or by pre-training a model. Those skilled in the art can refer to the process for determining the first movement information, and it will not be elaborated here.

[0075] Step S102: Control the robotic arm to transfer the target product to the turntable according to the first movement information.

[0076] Once the first movement information is determined, the robotic arm can be controlled to transfer the target product to the turntable according to the movement path specified by the first movement information.

[0077] Step S103: Control the turntable to move according to the second movement information, and control the camera to capture images of the target product during the turntable movement.

[0078] After the control equipment controls the robotic arm to transfer the target product to the turntable, the turntable can fix the target product.

[0079] The control device controls the turntable to move according to the second movement information, and pauses for a set time after each movement, while controlling the camera to capture images of the target product. The set time can be set according to actual conditions, and this embodiment does not limit it.

[0080] For example, it should be noted that the surface of the target product that contacts the turntable is the surface that does not affect the sale of the product, and this surface does not need to be photographed. For instance, if the target product has a surface that does not need to be photographed, such as an ornament or figurine, the surface of the target product that contacts the turntable is the base that does not affect the sale of the product, and therefore does not need to be photographed.

[0081] It should be noted that in this embodiment, when placing the target product on the conveyor device, the staff needs to confirm that the surface of the target product in contact with the conveyor device is the surface that does not affect the sale of the product, so that the robotic arm can grasp the target product. When placing the target product on the turntable, the surface in contact with the turntable is also the surface that does not affect the sale of the product.

[0082] In the above embodiments, by pre-acquired information such as the weight and size of the target product, the first movement information of the robotic arm and the second movement information of the turntable are determined. The robotic arm is controlled to transfer the target product to the turntable according to the first movement information, and the turntable is controlled to move according to the second movement information. During the movement of the turntable, the camera is controlled to capture images of the target product, thereby realizing automatic acquisition of product images and effectively improving the speed and efficiency of image acquisition.

[0083] In some embodiments, the automatic image acquisition method of the above embodiments further includes the following step: during the process of the robotic arm transferring the target product to the turntable according to the first movement information, controlling the camera to acquire an image of the surface of the target product in contact with the turntable.

[0084] In some cases, certain target products do not have a side that does not affect their sale; that is, all sides of such target products need to be photographed, such as mobile phones, tablets, and other electronic products.

[0085] For example, for such a product, the first movement information also includes a shooting position. The movement path in the first movement information is that the robotic arm controls the target product to first pass through the shooting position and then through the turntable. When the robotic arm moves the target product along the path specified in the first movement information, it moves to the shooting position specified in the first movement information, which is generally directly facing the camera. The camera is controlled to shoot the surface of the target product that will come into contact with the turntable. After the shooting is completed, the robotic arm is controlled to transfer the target product onto the turntable, and then the remaining surfaces are shot on the turntable.

[0086] In the above embodiments, images of all sides of the target product can be captured, satisfying the requirement that all sides of the target product need to be photographed.

[0087] In some implementations, such as Figure 5 As shown, the steps in the above embodiments, controlling the robotic arm to transfer the target product onto the turntable according to the first movement information, include:

[0088] Step S201: Control the robotic arm to move the target product to the positioning area according to the first movement information, and perform position calibration on the target product.

[0089] Step S202: Control the robotic arm to transfer the target product, after position calibration, onto the turntable.

[0090] In this embodiment, the target product can first be transferred to the positioning area according to the movement path specified in the first movement information for position calibration. After position calibration, the robotic arm can accurately grip the target product from the set area according to the gripping position specified in the first movement information, and then transfer the target product to the turntable according to the movement path specified in the first movement information, so that the turntable can fix the target product. The specific position calibration process has been described in detail in the exemplary system, and those skilled in the art can refer to the description of the exemplary system, so it will not be repeated here.

[0091] In the above embodiments, by calibrating the position of the target product, the robotic arm can accurately pick up the target product from the set area according to the gripping position specified in the first movement information, and then accurately send the target product onto the turntable.

[0092] In some implementations, the position calibration of the target product specifically includes the following steps: controlling a limiting device located in the positioning area to calibrate the position of the target product.

[0093] Specifically, the positioning area of ​​this embodiment is provided with a limiting device for precise positioning. The specific structure and working process of the limiting device have been described in detail in the above exemplary system. Those skilled in the art can refer to the description of the exemplary system, and it will not be repeated here.

[0094] In some implementations, the second movement information includes rotation information and tilt information; controlling the turntable to move according to the second movement information, and controlling the camera to capture images of the target product during the turntable movement, specifically includes the following steps:

[0095] The turntable is controlled to rotate according to the rotation information, and the camera is controlled to capture an image of the target product after each rotation; the turntable is controlled to tilt according to the tilt information, and the camera is controlled to capture an image of the target product.

[0096] Specifically, the control turntable rotates according to the rotation angle specified in the second movement information. Each rotation pauses for a set time, and then the camera is controlled to capture images of all sides of the target product. The control turntable tilts according to the tilt angle specified in the second movement information and pauses for a set time, while the control device controls the camera to capture images of the surface of the target product in contact with the robotic arm. The aforementioned set time can be adjusted according to actual conditions; this embodiment does not impose limitations.

[0097] It should be noted that the following methods can be used: First, control the turntable to rotate and photograph the side of the target product. After photographing the side, control the turntable to tilt and photograph the surface of the target product in contact with the robotic arm. Alternatively, control the turntable to tilt and photograph the surface of the target product in contact with the robotic arm, and then control the turntable to rotate and photograph the side of the target product. Or, control the turntable to rotate and photograph the side of the target product, and then control the turntable to tilt and photograph the surface of the target product in contact with the robotic arm during the side photographing process. Finally, control the turntable to reset and continue rotating to photograph the side of the target product. This implementation method is not limited to any particular method.

[0098] In the above embodiments, images of the remaining surfaces of the target product, excluding the surface in contact with the turntable, can be captured by controlling the rotation and tilt of the turntable.

[0099] In some embodiments, the product information of the target product includes product color information; the automatic image acquisition method of the above embodiments further includes the following steps:

[0100] The system identifies the color information of the target product in its image; it checks at least whether the color information of the target product's image matches the product's color information, and whether the image of the target product meets the set quality requirements; if the color information of the target product's image does not match the product's color information, or if the image of the target product does not meet the set quality requirements, an alarm message is generated.

[0101] In this embodiment, after obtaining the image of the target product, the image of the target product needs to be reviewed.

[0102] The system detects the color information of the target product in an image. Specifically, it can determine the location of the target product from the image based on an image recognition model, then detect the pixel information of the target product's location, and determine the image color information of the target product based on the pixel information of the target product's location, such as RGB values.

[0103] The training samples for the above image recognition model consist of a large number of images of target products, and the labels are the pre-standard positions of the target products in each training sample. The specific training process of the image recognition model is the same as that of the robotic arm path determination model described in the above embodiments; those skilled in the art can refer to the descriptions in the above embodiments, and will not be elaborated upon here.

[0104] The review process includes: comparing the image color information of the target product determined in the above steps with the product color information to check if the image color information of the target product matches the product color information; and checking whether the image of the target product meets the set quality requirements. Specifically, if the image of the target product is not blurry or does not exceed the boundaries, it indicates that the image of the target product meets the set quality requirements.

[0105] If the color information of the target product image is inconsistent with the product color information, or if the image of the target product does not meet the set quality requirements, the review will fail and an alarm message will be generated.

[0106] In this implementation, the image of the target product is reviewed. If the review fails, an alarm message is generated to notify the staff and prevent photos that do not meet the requirements from entering the next process.

[0107] In some embodiments, the automatic image acquisition method described above further includes the following steps:

[0108] The lighting parameters that match the product information in the preset shooting database are determined as the lighting parameters of the target product; when controlling the camera to capture images of the target product, the fill light is controlled to adjust the light according to the lighting parameters.

[0109] In this embodiment, lighting parameters corresponding to different colored products are pre-stored in the database. The control device can select lighting parameters, including brightness and color temperature, from the pre-stored database based on the product's color information. When the camera captures an image of the target product, the supplementary lighting is adjusted according to the lighting parameters.

[0110] This implementation method uses lighting parameters that match the color of the target product for supplementary lighting, which can further improve the shooting effect of the target product.

[0111] In some implementations, since the appearance of the target product is of greater concern when recycling and reselling secondhand goods, especially secondhand electronic products, whose appearance is a significant factor affecting their value, the target product can be a secondhand item in some embodiments. More specifically, the target product can be a secondhand electronic device, such as a secondhand mobile phone or a secondhand computer. For example, if the target product is a secondhand mobile phone, the specific shooting process is as follows:

[0112] Staff scan the identification code affixed to the used mobile phone, and the control equipment can retrieve the mobile phone's product information from the database based on the identification code. The product information includes the mobile phone's weight, dimensions, and color. Based on the mobile phone's weight and dimensions, the robotic arm's first and second movement information can be determined.

[0113] After scanning the code, the staff will remove the identification code from the used mobile phone and place the mobile phone on the conveyor device.

[0114] Based on the first movement information, the control device controls the robotic arm to move the used mobile phone from the conveying device to the positioning area, and then controls the limiting device to precisely position the used mobile phone. After precise positioning, the control device controls the robotic arm to grasp the used mobile phone according to the grasping position specified in the first movement information, and sends the used mobile phone to the shooting position according to the movement path specified in the first movement information, controlling the camera to shoot the surface of the used mobile phone that will contact the turntable. After shooting, the control device sends the used mobile phone onto the turntable. The control device controls the turntable to fix the used mobile phone and controls the turntable to rotate according to the rotation information specified in the second movement information, so that the camera can shoot the four sides and four top corners of the used mobile phone. After the side and top corner shots are completed, the control device controls the turntable to tilt according to the tilt information specified in the second movement information, so that the camera can shoot the surface of the used mobile phone that previously contacted the robotic arm. After shooting, the control device controls the robotic arm to send the mobile phone into the conveying device, and the mobile phone shooting is completed.

[0115] During the shooting process, the control device retrieves the lighting parameters that match the color of the used mobile phone from the database and controls the fill light to adjust the light according to the lighting parameters.

[0116] After acquiring images of all sides of the used mobile phone, the control device verifies the images, including whether the color of the used mobile phone displayed in the image matches the actual color of the used mobile phone, and whether the image meets the set quality requirements. If it is determined that the color of the used mobile phone displayed in the image matches the actual color of the used mobile phone and the image meets the set quality requirements, the image is uploaded to the designated server; if it is determined that the color of the used mobile phone displayed in the image does not match the actual color of the used mobile phone, or the image does not meet the set quality requirements, an alarm message is generated to remind staff to conduct verification.

[0117] Example devices, control equipment, storage media, and software

[0118] One embodiment of this specification also provides an apparatus for automatically acquiring images. For example... Figure 6 As shown, the device for automatically acquiring images includes:

[0119] The determining module 100 is used to determine the first movement information of the robotic arm and the second movement information of the turntable based on the pre-acquired product information of the target product; the product information includes product weight information and product size information;

[0120] The first control module 110 is used to control the robotic arm to transfer the target product to the turntable according to the first movement information;

[0121] The second control module 120 is used to control the turntable to move according to the second movement information, and to control the camera to capture images of the target product during the movement of the turntable.

[0122] In some embodiments, the automatic image acquisition device of the above embodiments further includes:

[0123] The third control module is used to control the camera to capture images of the surface of the target product in contact with the turntable during the process of the robotic arm transferring the target product to the turntable according to the first movement information.

[0124] In some embodiments, the first control module 110 of the above embodiments includes:

[0125] The first control unit is used to control the robotic arm to move the target product to the positioning area according to the first movement information, and to perform position calibration on the target product;

[0126] The second control unit is used to control the robotic arm to transfer the target product, after position calibration, onto the turntable.

[0127] In some embodiments, when the first control unit of the above embodiments performs position calibration on the target product, it is specifically used for:

[0128] The limiting device located in the positioning area is controlled to calibrate the position of the target product.

[0129] In some implementations, the second movement information includes rotation information and tilt information:

[0130] The second control module 120 in the above embodiments includes:

[0131] The third control unit is used to control the turntable to rotate according to the rotation information, and to control the camera to capture an image of the target product after each turntable rotation;

[0132] The fourth control unit is used to control the turntable to tilt according to the tilt information and to control the camera to capture images of the target product.

[0133] In some implementations, the product information of the target product includes product color information;

[0134] The automatic image acquisition device according to the above embodiments further includes:

[0135] The recognition module is used to recognize the image color information of the target product in the image of the target product;

[0136] The detection module is used to detect at least whether the image color information of the target product is consistent with the product color information, and whether the image of the target product meets the set quality requirements;

[0137] The generation module is used to generate alarm information if the color information of the target product image is inconsistent with the product color information, or if the image of the target product does not meet the set quality requirements.

[0138] In some embodiments, the automatic image acquisition device of the above embodiments further includes:

[0139] The lighting parameter determination module is used to determine the lighting parameters that match the product information in the preset shooting database as the lighting parameters of the target product;

[0140] The fourth control module is used to control the fill light to adjust the light according to the light parameters when the camera is capturing an image of the target product.

[0141] This specification also provides a control device, see [link to embodiment]. Figure 7 As shown, the control device includes:

[0142] Memory 200 and processor 210;

[0143] The memory 200 is connected to the processor 210 and is used to store programs;

[0144] The processor 210 is configured to implement the automatic image acquisition method disclosed in any of the above embodiments by running a program stored in the memory 200.

[0145] Specifically, the aforementioned control device may also include: a bus, a communication interface 220, an input device 230, and an output device 240.

[0146] The processor 210, memory 200, communication interface 220, input device 230, and output device 240 are interconnected via a bus. Among them:

[0147] A bus can include a pathway for transmitting information between various components of a computer system.

[0148] The processor 210 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0149] Processor 210 may include a main processor, as well as a baseband chip, modem, etc.

[0150] The memory 200 stores a program for executing the technical solution of this application, and may also store an operating system and other critical business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 200 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.

[0151] Input device 230 may include a device for receiving user input data and information, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0152] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0153] The communication interface 220 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0154] The processor 210 executes the program stored in the memory 200 and calls other devices. It can be used to implement the various steps of the automatic image acquisition method provided in the above embodiments of this application.

[0155] This specification also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer, causes the computer to perform the automatic image acquisition method in any of the above embodiments.

[0156] This specification also provides a computer program product containing instructions that, when executed by a computer, cause the computer to perform the automatic image acquisition method in any of the above embodiments.

[0157] It is understood that the specific examples in this document are only intended to help those skilled in the art better understand the embodiments described herein, and are not intended to limit the scope of the invention.

[0158] It is understood that in the various embodiments described in this specification, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments described in this specification.

[0159] It is understood that the various implementation methods described in this specification can be implemented individually or in combination, and the implementation methods in this specification are not limited in this respect.

[0160] Unless otherwise stated, all technical and scientific terms used in the embodiments of this specification have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of this specification. The term "and / or" as used in this specification includes any and all combinations of one or more of the associated listed items. The singular forms "a," "the," and "the" as used in the embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0161] It is understood that the processor in the embodiments of this specification can be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this specification. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this specification can be directly implemented by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above methods.

[0162] It is understood that the memory in the embodiments of this specification may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM). It should be noted that the memory in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0163] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this specification.

[0164] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the aforementioned method implementations, and will not be repeated here.

[0165] In the several embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0166] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0167] In addition, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0168] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of this specification, in essence, or the parts that contribute to the prior art, or parts of the technical solutions, can be embodied in the form of software products. These computer software products are stored in a storage medium and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this specification. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0169] The above description is merely a specific embodiment of this specification, but the scope of protection of this invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this specification should be included within the scope of protection of this specification. Therefore, the scope of protection of this invention should be determined by the scope of the claims.

Claims

1. A method of automatically acquiring images, characterized by, include: Based on the pre-acquired product information of the target product, the first movement information of the robotic arm and the second movement information of the turntable are determined; the product information includes product weight information and product size information; the first movement information includes the shooting position facing the camera, and the movement path in the first movement information is that the robotic arm controls the target product to first pass through the shooting position and then pass through the turntable; The robotic arm is controlled to transfer the target product onto the turntable according to the first movement information. During the transfer process, when the target product moves to the shooting position, the camera is controlled to capture an image of the surface of the target product in contact with the turntable. The turntable is controlled to move according to the second movement information, and the camera is controlled to capture images of the target product during the movement of the turntable.

2. The method according to claim 1, characterized in that, Controlling the robotic arm to transfer the target product onto the turntable according to the first movement information includes: The robotic arm is controlled to move the target product to the positioning area according to the first movement information, and the position of the target product is calibrated. The robotic arm is controlled to transfer the target product, after position calibration, onto the turntable.

3. The method according to claim 2, characterized in that, Position calibration of the target product includes: The limiting device located in the positioning area is controlled to calibrate the position of the target product.

4. The method according to claim 1, characterized in that, The second movement information includes rotation information and tilt information; Controlling the turntable to move according to the second movement information, and controlling the camera to capture images of the target product during the turntable's movement, includes: The turntable is controlled to rotate according to the rotation information, and the camera is controlled to capture an image of the target product after each turntable rotation. The turntable is controlled to tilt according to the tilt information, and the camera is controlled to capture images of the target product.

5. The method according to claim 1, characterized in that, The product information of the target product includes product color information; The method further includes: Identify the color information of the target product in its image; At least it is necessary to detect whether the image color information of the target product is consistent with the product color information, and whether the image of the target product meets the set quality requirements; If the color information of the target product image is inconsistent with the product color information, or if the image of the target product does not meet the set quality requirements, an alarm message will be generated.

6. The method according to claim 1, characterized in that, The method further includes: The lighting parameters that match the product information in the preset shooting database are determined to be the lighting parameters of the target product; When controlling the camera to capture images of the target product, the fill light is adjusted according to the lighting parameters.

7. An automatic image acquisition device, characterized in that, include: The determining module is used to determine the first movement information of the robotic arm and the second movement information of the turntable based on the product information of the target product obtained in advance; the product information includes product weight information and product size information; the first movement information includes the shooting position facing the camera, and the movement path in the first movement information is that the robotic arm controls the target product to first pass through the shooting position and then pass through the turntable; The first control module is used to control the robotic arm to transfer the target product to the turntable according to the first movement information, and during the transfer process, when the target product moves to the shooting position, control the camera to capture an image of the surface of the target product in contact with the turntable; The second control module is used to control the turntable to move according to the second movement information, and to control the camera to capture images of the target product during the movement of the turntable.

8. A control device, characterized in that, include: Memory and processor; The memory is used to store programs; The processor is configured to implement the method for automatically acquiring images as described in any one of claims 1 to 6 by running a program in the memory.

9. A system for automatically acquiring images, characterized in that, Includes a robotic arm, a turntable, a camera, and the control device as described in claim 8; The control device is communicatively connected to the robotic arm, the turntable, and the camera, respectively.

10. The system for automatically acquiring images according to claim 9, characterized in that, It also includes fill lights; The supplementary light is communicatively connected to the control device.

11. A storage medium, characterized in that, include: The storage medium stores a computer program, which, when executed by a processor, implements the method for automatically acquiring images as described in any one of claims 1 to 6.

Images