Image acquisition system

Abstract

The embodiment of the invention relates to the technical field of artificial intelligence, and particularly provides a sample image acquisition method, a model training method and an image acquisition system. The image acquisition system comprises an image acquisition platform, the image acquisition platform comprises a placing assembly, the placing assembly can rotate relative to the image acquisition platform, and the placing assembly is used for placing a target object to be subjected to image acquisition; the illumination mechanism is installed on the image acquisition platform and provides illumination for the image acquisition platform; the image acquisition device is arranged on the image acquisition platform, can move relative to the image acquisition platform and is used for acquiring image data of the target object; the image processing device and the controller are both connected with the image collecting device, and the controller is further connected with the rotating assembly and the lighting mechanism.

Description

[0001] This application is a divisional application with application number 202310204354.7, application date February 22, 2023, and invention name “Sample image acquisition method, model training method and image acquisition system”. Technical Field

[0002] The present application relates to the field of artificial intelligence technology, and in particular to an image acquisition system. Background Art

[0003] In the process of realizing artificial intelligence tasks based on deep learning, there are three basic elements that are indispensable, namely computing power, algorithms, and data. Under the premise that computing power and algorithms are basically determined, data plays a decisive role in the process of realizing deep learning tasks, and it can be considered that data is of great significance to the final effect of deep learning tasks. In other words, if there is a problem with the quality of data, a good model can be turned into treasure, and if the data quality is very high, it can also make a mediocre algorithm produce extraordinary results.

[0004] When obtaining a deep learning model, a large amount of data from relevant scenes needs to be collected as training samples. However, it takes a lot of economic costs to collect real scene data from relevant sites, and after the data is collected, it takes a lot of time to manually annotate the data. Therefore, the cost of obtaining training data for deep learning model training is expensive. Summary of the invention

[0005] The main purpose of the embodiments of the present application is to provide a sample image acquisition method, a model training method and an image acquisition system, aiming to achieve efficient acquisition of image data, and then provide data support for deep learning model training, thereby improving the effect of deep learning model training and reducing the economic costs required due to insufficient sample images.

[0006] In a first aspect, an embodiment of the present application provides a sample image acquisition method, which is applied to an image acquisition system, wherein the image acquisition system includes: an image acquisition platform for placing a target object to be imaged, an image acquisition device that can be displaced relative to the image acquisition platform and is used to acquire image data of the target object, and an image processing device connected to the image acquisition device, wherein the method includes:

[0007] The scene category parameters of the image processing device are set, and the image acquisition device is controlled to acquire image data of the target object located on the image acquisition platform with at least two different image acquisition parameters, and the image data is sent to the image processing device, wherein the image acquisition parameters include at least one of position parameters and lighting parameters.

[0008] After the image processing device receives the image data, the image processing device is controlled to preprocess the image data according to the scene category parameter to obtain a target sample image, wherein the preprocessing at least includes marking the target object.

[0009] In a second aspect, the embodiment of the present application further provides a model training method, comprising:

[0010] The basic model is trained using the target sample image as a training sample to obtain a target model, wherein the target sample image is obtained according to any step of a sample image acquisition method provided in the specification of the present application.

[0011] In a third aspect, an embodiment of the present application further provides an image acquisition system, the image acquisition system comprising: an image acquisition platform for placing a target object to be imaged, an image acquisition device that can be displaced relative to the image acquisition platform and is used to acquire image data of the target object, an image processing device connected to the image acquisition device, and a controller, wherein the controller is at least used to:

[0012] The scene category parameters of the image processing device are set, and the image acquisition device is controlled to acquire image data of the target object located on the image acquisition platform with at least two different image acquisition parameters, and the image data is sent to the image processing device, wherein the image acquisition parameters include at least one of position parameters and lighting parameters.

[0013] After the image processing device receives the image data, the image processing device is controlled to preprocess the image data according to the scene category parameter to obtain a target sample image, wherein the preprocessing at least includes marking the target object.

[0014] In a fourth aspect, an embodiment of the present application provides another image acquisition system, including:

[0015] An image acquisition platform, the image acquisition platform comprising a placement component, the placement component can rotate relative to the image acquisition platform, and the placement component is used to place a target object to be imaged;

[0016] An illumination mechanism, the illumination mechanism being installed on the image acquisition platform to provide illumination for the image acquisition platform;

[0017] An image acquisition device, which is disposed on the image acquisition platform and can be displaced relative to the image acquisition platform to acquire image data of the target object;

[0018] An image processing device and a controller, wherein the image processing device and the controller are both connected to the image acquisition device, and the controller is also connected to the rotating assembly and the lighting mechanism;

[0019] Wherein, the controller is used to control the rotation of the placement component and the illumination of the illumination mechanism, thereby changing the image acquisition parameters, and the image acquisition parameters include position parameters and illumination parameters;

[0020] The controller is used to control the image acquisition device to acquire image data of the target object located on the image acquisition platform with changed image acquisition parameters;

[0021] The controller is used to send the image data to the image processing device;

[0022] The image processing device receives the image data, and pre-processes the image data according to preset scene category parameters to obtain a target sample image.

[0023] The embodiment of the present application provides an image acquisition system, which includes an image acquisition platform, the image acquisition platform includes a placement component, the placement component can rotate relative to the image acquisition platform, and the placement component is used to place a target object to be imaged; an illumination mechanism, the illumination mechanism is installed on the image acquisition platform to provide illumination for the image acquisition platform; an image acquisition device, the image acquisition device is arranged on the image acquisition platform and can be displaced relative to the image acquisition platform to acquire image data of the target object; an image processing device and a controller, the image processing device and the controller are both connected to the image acquisition device, and the controller is also connected to the rotating component and the illumination mechanism; wherein the controller is used to control the rotation of the placement component and the illumination of the illumination mechanism, thereby changing image acquisition parameters, the image acquisition parameters including position parameters and illumination parameters; the controller is used to control the image acquisition device to acquire image data of the target object located on the image acquisition platform with the changed image acquisition parameters; the controller is used to send the image data to the image processing device; the image processing device receives the image data, and pre-processes the image data according to preset scene category parameters to obtain a target sample image. The present application first sets the scene category parameters of the image processing device, then adjusts the image acquisition parameters to control the image acquisition system, acquires the image data of the target object located on the image acquisition platform under the corresponding image acquisition parameters, and sends the acquired image data of the target object to the image processing device; after the image processing device receives the image data, the image data is preprocessed according to the scene category parameters, and then the image data annotation results and the image data background replacement results are obtained, and finally the target sample image is obtained. Therefore, the target sample image can be used to train the deep learning model, which improves the effect of deep learning model training and reduces the economic cost and a large amount of manpower cost of the sample data required for model training.

[0024] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1 is a schematic block diagram of an image acquisition system provided in an embodiment of the present application;

[0027] Figure 2 It is a schematic diagram of the structural coordination of an image acquisition device and an image acquisition platform of an image acquisition system provided in an embodiment of the present application;

[0028] Figure 3 is a partial schematic diagram of a driving mechanism of an image acquisition device provided in an embodiment of the present application;

[0029] Figure 4 It is a schematic diagram of the overall effect of the driving mechanism of the image acquisition system provided in the embodiment of the present application;

[0030] Figure 5 It is a schematic diagram of the steps of a sample image acquisition method provided in an embodiment of the present application;

[0031] Figure 6 is a flow chart of the steps of a sample image acquisition method provided in an embodiment of the present application;

[0032] Figure 7 It is a flowchart of the steps of a method for acquiring sample images based on dynamic scene pictures provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0035] In the description of this application, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0036] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0037] The embodiment of the present application provides a sample image acquisition method, a model training method and an image acquisition system. The sample image acquisition method can be applied to the image acquisition system.

[0038] Among them, the sample image acquisition method first sets the scene category parameters of the image processing device, and then controls the image acquisition system by adjusting the image acquisition parameters, collects the image data of the target object located on the image acquisition platform under the corresponding image acquisition parameters, and sends the collected image data of the target object to the image processing device; after the image processing device receives the image data, it pre-processes the image data to obtain the annotation results of the image data and the results of fusing the background of the image data according to the scene category set by the scene category parameters, and then obtains the target sample image. Therefore, the target sample image can be used to train the deep learning model, which improves the effect of deep learning model training and reduces the economic cost and a large amount of manpower cost of the sample data required for model training.

[0039] Some embodiments of the present application are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0040] See also Figure 1 , Figure 1 A schematic block diagram of an image acquisition system provided in an embodiment of the present application.

[0041] like Figure 1 As shown, the image acquisition system 100 includes an image acquisition device 110 , an image acquisition platform 120 , an image processing device 130 , and a controller 140 .

[0042] The image acquisition platform 120 is used to place the target object to be imaged, the image acquisition device 110 can be displaced relative to the image acquisition platform 120 and used to acquire image data of the target object, and the image processing device 130 is used to process the image data acquired by the image acquisition device 110.

[0043] The controller 140 is connected to the image acquisition device 110 and the image processing device 130, and is at least used to control the image acquisition device 110 to perform image acquisition operations, transmit the acquired image data to the image processing device 130, and control the image processing device 130 to process the received image data to obtain a target image.

[0044] The controller 140 can also be used to set the scene category parameters of the image processing device 130. When the image acquisition device 110 performs an image acquisition operation and transmits the acquired image data to the image processing device 130, after sending the image data to the image processing device 130, the image processing device 130 automatically annotates the image processing and also needs to update the background picture of the received image data according to the scene category parameters to obtain the target image.

[0045] See also Figure 2 Optionally, the image acquisition platform 120 is provided with a placement component 1201, and the placement component 1201 forms a placement area for placing the target object, and the placement component 1201 can rotate relative to the image acquisition platform 120 to drive the target object placed in the placement area to rotate relative to the image acquisition platform 120, so that the image acquisition device 110 can capture images of the target object placed on the placement component 1201 from multiple angles.

[0046] Exemplarily, when it is necessary to collect first-angle image data of the target object, the target object can be placed on the placement component 1201, and the controller 140 can be used to control the placement component 1201 to perform a rotation operation to adjust the placement angle of the target object to a preset angle. After the placement angle of the target object is adjusted to the preset angle, the controller 140 controls the image acquisition device 110 to perform an image acquisition operation to obtain the first-angle image data of the target object.

[0047] For example, the rotation angle of the placement component 1201 relative to the image acquisition platform 120 can be divided into 0-360 degrees, and the step size can be set to 5 degrees, 10 degrees, etc., which can be adjusted according to needs. By continuously adjusting the rotation angle of the placement component 1201 relative to the image acquisition platform 120 to collect target object information at different rotation angles, the target object has sampling data at different rotation angles, providing good data support for subsequent model training.

[0048] By setting the placement component 1201, the image acquisition mechanism can acquire data of the target object from different angles, thereby obtaining image data of the target object at different angles, making the data of the target object richer. Therefore, the rotation angle of the placement component 1201 can be used as one of the parameter information in the image acquisition parameters, thereby expanding the diversity of target object data acquisition.

[0049] See also Figure 2In some embodiments, the image acquisition device 110 includes an image acquisition mechanism 111, a driving mechanism 112 for driving the image acquisition mechanism 111 to move relative to the image acquisition platform 120, and an illumination mechanism 113 for providing illumination to the image acquisition platform 120.

[0050] The driving mechanism 112 is disposed on the image acquisition platform 120 and can be displaced relative to the image acquisition platform 120. The image acquisition mechanism 111 is connected to the driving mechanism 112, so that the driving mechanism 112 can drive the image acquisition mechanism 111 to be displaced relative to the image acquisition platform 120. The lighting mechanism 113 is installed on the image acquisition platform 120 to provide lighting for the image acquisition platform 120. The controller 140 can adjust the image acquisition parameters of the image acquisition device 110, so that the image acquisition device 110 can acquire images of the target object with the corresponding image acquisition parameters.

[0051] For example, the image acquisition parameters include at least one of the position parameters and the illumination parameters. The controller 140 adjusts the illumination parameters in the image acquisition parameters, thereby controlling the illumination mechanism 113 to perform corresponding illumination operations according to the preset illumination parameters, and the illumination operations are used to provide the image acquisition platform 120 with illumination effects that match the illumination parameters.

[0052] Alternatively, the controller 140 adjusts the position parameters in the image acquisition parameters, thereby controlling the driving mechanism 112 to perform a corresponding driving operation according to the position parameters in the image acquisition parameters. During the driving operation, the driving mechanism 112 drives the image acquisition mechanism 111 to perform a displacement operation in a two-dimensional or three-dimensional space, so that the image acquisition mechanism 111 is relatively displaced relative to a target object placed on the image acquisition platform 120, and the relative position of the image acquisition mechanism 111 and the target object is adjusted to the corresponding target relative position.

[0053] Optionally, the driving mechanism 112 can drive the image acquisition mechanism 111 to move in a first direction and a second direction, wherein the first direction and the second direction are perpendicular to each other, and the first direction is a horizontal direction approaching or moving away from the target object, and the second direction is a vertical direction or a height direction approaching or moving away from the target object.

[0054] See also Figure 3 and Figure 4 Exemplarily, the driving mechanism 112 includes a first driving mechanism 1121 and a second driving mechanism 1122. The first driving mechanism 1121 is used to drive the image acquisition mechanism 111 to move relative to the image acquisition platform 120 in a first direction, and the second driving mechanism 1122 is used to drive the image acquisition mechanism 111 to move relative to the image acquisition platform 120 in a second direction.

[0055] Optionally, the first driving mechanism 1121 is connected to the image acquisition platform 120 and can be displaced in a first direction relative to the image acquisition platform 120, and the second driving mechanism 1122 is connected to the first driving mechanism 1121 and the image acquisition mechanism 111, and is used to drive the image acquisition mechanism 111 to displace in at least a second direction relative to the first driving mechanism 1121. For example, when the first driving mechanism 1121 drives the image acquisition mechanism 111 to displace in a first direction relative to the image acquisition platform 120, the horizontal distance between the image acquisition mechanism 111 and the target object placed on the image acquisition platform 120 increases or decreases. When the second driving mechanism 1122 drives the image acquisition mechanism 111 to displace in a second direction relative to the image acquisition platform 120, the vertical distance between the image acquisition mechanism 111 and the target object placed on the image acquisition platform 120 increases or decreases.

[0056] Optionally, the second driving mechanism 1122 is further used to drive the image acquisition mechanism 111 to rotate a preset angle α relative to the first driving mechanism 1121, so that the image acquisition mechanism 111 can acquire images of a target object placed on the image acquisition platform 120 from different angles. Optionally, the preset angle α is 360°, preferably, the preset angle α is 180°.

[0057] In some embodiments, the lighting mechanism 113 includes a lighting assembly and a lighting driving assembly connected to the lighting assembly and the image acquisition platform 120. The lighting driving assembly is at least used to drive the lighting assembly to emit a lighting beam to the image acquisition platform 120 at a preset angle.

[0058] Specifically, the controller 140 adjusts the image acquisition parameters, and the lighting mechanism 113 controls the lighting driving component to adjust the angle information with the image acquisition platform 120 according to the preset angle information in the lighting parameters according to the lighting parameters, and adjusts the lighting component to the corresponding lighting parameters. In this way, the image acquisition mechanism 111 can acquire the image data of the target object of the image acquisition platform 120 under the image acquisition parameters corresponding to the lighting mechanism 113.

[0059] For example, the image acquisition platform 120 includes a first platform portion and a second platform portion, the placement component 1201 is arranged on the first platform portion, and the first platform portion is provided with a moving track corresponding to the placement component 1201, and the first driving mechanism 1121 of the image acquisition device 110 can approach or move away from the placement component 1201 along the moving track.

[0060] One end of the second platform portion is connected to the first platform portion, and after the first platform portion and the second platform portion are connected and adapted, the first platform portion and the second platform portion are arranged at an angle β, preferably, the angle β is 90°. The lighting mechanism 113 is arranged at one end of the second platform portion away from the first platform portion, preferably, there are multiple lighting mechanisms 113, and they are arranged at intervals at one end of the second platform portion away from the first platform portion.

[0061] When it is necessary to collect images of the target object, the target object is placed on the placement component 1201, and the scene category parameters of the image processing device 130 are set and the image collection parameters are adjusted through the controller 140, so that the lighting mechanism 113 is controlled to perform corresponding lighting operations according to the preset lighting parameters and the first driving mechanism 1121 and the second driving mechanism 1122 in the driving mechanism 112 are controlled to drive the image collection mechanism 111 to adjust to corresponding position parameters relative to the image collection platform 120. When the lighting mechanism 113 emits an illumination beam to the image collection platform 120 with the preset lighting parameters and the driving mechanism 112 drives the image collection mechanism 111 to adjust to corresponding position parameters relative to the image collection platform 120, the image collection mechanism 111 is used to collect image data corresponding to the target object, and the image data is sent to the image processing device 130. After the image processing device 130 receives the image data, it pre-processes the image data according to the scene category parameters to obtain the labeling results of the image data and the results of image background replacement, thereby obtaining the target sample image.

[0062] By setting the scene category parameters of the image processing device 130 and adjusting the image acquisition parameters in the controller 140 to control the image acquisition system 100, the image acquisition device 110 is used to acquire the image data of the target object located on the image acquisition platform 120 under the corresponding image acquisition parameters, and the acquired image data of the target object is sent to the image processing device 130; after the image processing device 130 receives the image data, the image data is preprocessed according to the scene category parameters to obtain the image data annotation results and the image background replacement results, and then the target sample image is obtained. Therefore, the target sample image can be used to train the deep learning model, which improves the effect of deep learning model training and reduces the economic cost and a large amount of manpower cost of the sample data required for model training.

[0063] Optionally, the controller 140 may be one or more, and may be integrated or set in at least one of the image acquisition device 110, the image acquisition platform 120, and the image processing device 130, or may be independently set. There is no limitation on this, and it is only necessary that the controller 140 can control each device of the image acquisition system 100 to execute the corresponding preset operation process.

[0064] like Figure 1As shown, in some embodiments, the controller 140 includes at least a processor 1401, a memory 1402, a communication interface (not shown) and an I / O interface (not shown). The processor 1401, the memory 1402, the communication interface, and the I / O interface communicate through a bus. The processor 1401 can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0065] The memory 1402 is installed with various computer programs such as operating systems and application programs for the processor 1401 to execute, and data required to execute the computer programs. During the sample image acquisition process, if there is data that needs to be stored locally, it can be stored in the memory 1402. At the same time, the controller 140 calls the computer program stored in the memory 1402 through the processor 1401 to control the corresponding devices and / or mechanisms in the sample image acquisition process to execute the preset operation process respectively, so as to realize their respective preset functions.

[0066] In an embodiment provided in the present application, the processor 1401 is used to execute a computer program stored in the memory 1402, and when executing the computer program, the following method steps may be implemented:

[0067] Setting a scene category parameter of the image processing device 130, and controlling the image acquisition device 110 to acquire image data of a target object located on the image acquisition platform 120 with at least two different image acquisition parameters, and sending the image data to the image processing device 130, wherein the image acquisition parameters include at least one of a position parameter and a lighting parameter;

[0068] After the image processing device 130 receives the image data, the image processing device 130 is controlled to pre-process the image data according to the scene category parameter to obtain a target sample image, wherein the pre-processing at least includes marking the target object.

[0069] In some embodiments, the processor 1401 controls the image acquisition device 110 to acquire image data of a target object located on the image acquisition platform 120 using at least two different image acquisition parameters, including:

[0070] Controlling the image acquisition device 110 to acquire first image data of a target object located on the image acquisition platform 120 with a first image acquisition parameter, and sending the first image data to the image processing device 130;

[0071] After the image acquisition device 110 acquires the first image data, the image acquisition device 110 is controlled to adjust the first image acquisition parameters to second image acquisition parameters, and the image acquisition device 110 is controlled to acquire second image data of the target object located on the image acquisition platform 120 with the second image acquisition parameters.

[0072] In some embodiments, the image acquisition device 110 includes an image acquisition mechanism 111, a driving mechanism 112 for driving the image acquisition mechanism 111 to move relative to the image acquisition platform 120, and an illumination mechanism 113 for providing illumination to the image acquisition platform 120. The processor 1401 controls the image acquisition device 110 to acquire first image data of a target object located on the image acquisition platform 120 with a first image acquisition parameter, including:

[0073] Controlling the lighting mechanism 113 to perform a first lighting operation, so that the lighting mechanism 113 provides the image acquisition platform 120 with a first lighting parameter;

[0074] Controlling the driving mechanism 112 to perform a first driving operation, so that the driving mechanism 112 drives the image acquisition mechanism 111 to move relative to a target object placed on the image acquisition platform 120 with a first position parameter;

[0075] After the first driving operation is completed, the image acquisition mechanism 111 is controlled to acquire first image data of the target object 121 placed on the image acquisition platform 120 .

[0076] In some embodiments, the driving mechanism 112 includes a first driving mechanism 1121 and a second driving mechanism 1122, wherein the first driving mechanism 1121 is connected to the image acquisition platform 120 and can be displaced relative to the image acquisition platform 120, and the second driving mechanism 1122 is connected to the first driving mechanism 1121 and the image acquisition mechanism 111, and is used to drive the image acquisition mechanism 111 to displace at least in the height direction relative to the first driving mechanism 1121 and / or drive the image acquisition mechanism 111 to rotate a preset angle relative to the first driving mechanism 1121;

[0077] When the driving mechanism 112 performs the first driving operation, at least one of the first driving mechanism 1121 and the second driving mechanism 1122 drives the image acquisition mechanism 111 to change its relative position relative to the target object 121 placed on the image acquisition platform 120 .

[0078] In some embodiments, the lighting parameters include at least one of the lighting angle and the lighting intensity. The lighting mechanism 113 includes a lighting component and a lighting driving component connecting the lighting component and the image acquisition platform 120. The lighting driving component is at least used to drive the lighting component to emit a lighting beam to the image acquisition platform 120 at a preset angle.

[0079] During the lighting mechanism 113 performs the first lighting operation, the processor 1401 is used to drive the lighting component to emit a lighting beam of a first lighting intensity to the image acquisition platform 120; and / or the lighting driving component drives the lighting component to emit a lighting beam to the image acquisition platform 120 at a first lighting angle.

[0080] In some embodiments, the processor 1401 controls the image processing device 130 to pre-process the image data according to the scene category parameter to obtain a target sample image, including:

[0081] Controlling the image processing device to extract contour information of the target object in the image data, and determining a labeling box of the target object in the image data according to the contour information;

[0082] According to the scene category parameter, the target object in the image data is selected using the annotation box to obtain a target sample image.

[0083] In some embodiments, the processor 1401 controls the image processing device 130 to select the target object in the image data using the annotation box according to the scene category parameter to obtain the target sample image, including:

[0084] dividing the image data into a target object image and a background image according to a target object in the image data;

[0085] The background image style is determined according to the scene category parameters, the background image is updated to the background image style, and the updated background image and the target object image are fused to form a target sample image.

[0086] In some embodiments, before controlling the image processing device 130 to pre-process the image data according to the scene category parameter, the processor 1401 is further configured to:

[0087] Acquire type information of a target object placed on the image acquisition platform 120;

[0088] Controlling the image processing device 130 to pre-process the image data according to the scene category parameter to obtain a target sample image, including:

[0089] Controlling the image processing device 130 to extract contour information of the target object in the image data, and confirming a labeling box of the target object in the image data according to the contour information;

[0090] According to the scene category parameters, a target object in the image data is selected by using a marked box, and the type of the target object selected by the marked box is marked according to the type information to obtain a target sample image.

[0091] In some specific embodiments, the image acquisition platform 120 is provided with a placement component 1201, which forms a placement area for placing the target object, and the placement component 1201 can rotate relative to the image acquisition platform 120 to drive the target object placed in the placement area to rotate relative to the image acquisition platform 120.

[0092] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the processor described above can refer to the corresponding working process of the sample image acquisition method described below, and will not be repeated here.

[0093] See also Figure 5 , Figure 5 : is a flowchart of a sample image acquisition method provided in an embodiment of the present application. The prompt method is applied to the aforementioned image acquisition system 100. The method includes steps S1 to S2, which are specifically as follows:

[0094] Step S1: Set the scene category parameters of the image processing device 130, and control the image acquisition device 110 to acquire image data of the target object located on the image acquisition platform 120 with at least two different image acquisition parameters, and send the image data to the image processing device 130, wherein the image acquisition parameters include at least one of the position parameters and the lighting parameters.

[0095] When training a robot's deep learning model, it is necessary to collect a large amount of scene image data as training samples. It may be necessary to carry the deployed robot to the real scene to collect a large amount of data, which consumes a lot of time in the process of scene deployment and robot handling. At the same time, after the data is collected, it takes a lot of time to manually label the data and check the data. This also makes the cost of training deep learning models very high. Therefore, the image acquisition system can be used to collect the required scene data according to the image acquisition parameters, reducing the large amount of time consumed in the process of scene deployment and robot handling.

[0096] Exemplarily, the scene category parameters of the image processing device 130 are set to provide scene settings for subsequent preprocessing of the collected image data, so that the collected image data can be preprocessed under the corresponding scene category parameters to better meet actual needs.

[0097] For example, scene categories may include but are not limited to living room, bedroom, kitchen, factory, warehouse, shopping mall, etc. Therefore, corresponding scene category parameters can be set according to the actual needs of generating data.

[0098] Under the corresponding scene category, there is a corresponding scene background picture library. For example, if the scene category parameter is living room, multiple pictures of the living room as the scene background picture will be constructed to provide guarantee for the preprocessing of subsequent collected images.

[0099] Exemplarily, when training a deep learning model, a large amount of scene image data is required as training samples. Therefore, the image acquisition device 110 needs to acquire image data of the target object located on the image acquisition platform 120 with multiple sets of different image acquisition parameters, and the image data acquired by the image acquisition device 110 needs to be sent to the image processing device 130 to improve the diversity of the acquired data and facilitate subsequent processing of the image data.

[0100] Exemplarily, the image acquisition parameters include at least one of a position parameter and an illumination parameter. The position parameter is used to indicate the position information of the target object located on the image acquisition platform 120 photographed by the image acquisition device 110; the illumination parameter is used to indicate the light beam intensity, angle and other information provided to the target object on the image acquisition platform 120.

[0101] For example, when selecting multiple sets of image acquisition parameters, the differences between the image acquisition parameters may be different position parameters, different illumination parameters, or both position parameters and illumination parameters are different, thereby enabling the image acquisition device 110 to obtain image data of the target object of the image acquisition platform 120 under different image acquisition parameters, making the acquired image data richer and providing sufficient data support for subsequent image data processing.

[0102] In some embodiments, controlling the image acquisition device 110 to acquire image data of a target object located on the image acquisition platform 120 with at least two different image acquisition parameters includes: controlling the image acquisition device 110 to acquire first image data of the target object located on the image acquisition platform 120 with a first image acquisition parameter, and sending the first image data to the image processing device 130; after the image acquisition device 110 acquires the first image data, controlling the image acquisition device 110 to adjust the first image acquisition parameter to a second image acquisition parameter, and controlling the image acquisition device 110 to acquire second image data of the target object located on the image acquisition platform 120 with the second image acquisition parameter.

[0103] Exemplarily, the image acquisition device 110 is controlled to acquire the target object located on the image acquisition platform 120 according to the first image acquisition parameters, the first image data under the first image acquisition parameters are obtained, and then the first image data is sent to the image processing device 130; after the image acquisition device 110 acquires the first image data, the first image acquisition parameters are modified to be adjusted to the second image acquisition parameters, and then the image acquisition device 110 is controlled to acquire the second image data located on the image acquisition platform 120 according to the second image acquisition parameters, until enough image data is acquired, the image acquisition parameters are stopped from being adjusted, and then the image acquisition is ended.

[0104] For example, the first image acquisition parameter and the second image acquisition parameter may be different position parameters, or different illumination parameters, or both position parameters and illumination parameters are different, so that the image acquisition device 110 can obtain image data of the target object of the image acquisition platform 120 under different image acquisition parameters, so that the acquired image data is richer. For example, the first image acquisition parameter and the second image acquisition parameter may be different position parameters under the same illumination parameters, so that the image acquisition device 110 can obtain image data of the target object under different image acquisition platforms 120.

[0105] In some embodiments, controlling the image acquisition device 110 to acquire first image data of a target object located on the image acquisition platform 120 with first image acquisition parameters includes: controlling the lighting mechanism 113 to perform a first lighting operation so that the lighting mechanism 113 provides first lighting to the image acquisition platform 120 with the first lighting parameters; controlling the driving mechanism 112 to perform a first driving operation so that the driving mechanism 112 drives the image acquisition mechanism 111 to move relative to the target object placed on the image acquisition platform 120 with the first position parameters; after the first driving operation is completed, controlling the image acquisition mechanism 111 to acquire first image data of the target object placed on the image acquisition platform 120.

[0106] like Figure 2 As shown, the image acquisition device 110 includes an image acquisition mechanism 111, a driving mechanism 112 for driving the image acquisition mechanism 111 to move relative to an image acquisition platform 120, and an illumination mechanism 113 for providing illumination to the image acquisition platform 120, wherein the position parameters in the image acquisition parameters are used to control the movement position of the driving mechanism 112, and the illumination parameters are used to control the illumination effect of the illumination mechanism 113.

[0107] Exemplarily, the lighting mechanism 113 is controlled to perform a first lighting operation according to the lighting parameters in the image acquisition parameters, so that the lighting mechanism 113 provides the image acquisition platform 120 with a first lighting corresponding to the first lighting parameters. And the driving mechanism 112 is controlled to perform a first driving operation according to the position parameters in the image acquisition parameters, so that the driving mechanism 112 can enable the image acquisition mechanism 111 to reach a displacement with respect to the target object 121 placed on the image acquisition platform 120 under the first position parameter condition, thereby enabling the image acquisition mechanism 111 to acquire image data of the target object 121 of the image acquisition platform 120 under the image acquisition parameters corresponding to the driving mechanism 112 and the lighting mechanism 113.

[0108] After obtaining the first image data, the image acquisition parameters can be modified to obtain the second image acquisition parameters, by controlling the lighting mechanism 113 to perform a second lighting operation under the second image acquisition parameters, so that the lighting mechanism 113 provides the second lighting to the image acquisition platform 120 with the second lighting parameters; controlling the driving mechanism 112 to perform a second driving operation under the second image acquisition parameters, so that the driving mechanism 112 drives the image acquisition mechanism 111 to move relative to the target object placed on the image acquisition platform 120 with the second position parameters; after the second driving operation is completed, controlling the image acquisition mechanism 111 to acquire the second image data of the target object placed on the image acquisition platform 120.

[0109] In some embodiments, the driving mechanism 112 includes a first driving mechanism 1121 and a second driving mechanism 1122, wherein the first driving mechanism 1121 is connected to the image acquisition platform 120 and can be displaced relative to the image acquisition platform 120, and the second driving mechanism 1122 is connected to the first driving mechanism 1121 and the image acquisition mechanism 111, and is used to drive the image acquisition mechanism 111 to displace at least in the height direction relative to the first driving mechanism 1121 and / or drive the image acquisition mechanism 111 to rotate a preset angle relative to the first driving mechanism 1121; during the driving mechanism 112 performing the first driving operation, at least one of the first driving mechanism 1121 and the second driving mechanism 1122 drives the image acquisition mechanism 111 to change its relative position relative to a target object placed on the image acquisition platform 120.

[0110] like Figure 3As shown, the first driving mechanism 1121 and the second driving mechanism 1122 are connected via a connecting component 1123, and the image acquisition mechanism 111 can acquire image data according to the position parameter information in the image acquisition parameter through the connecting component 1121. In actual scenes, pictures are not always taken from the front, so in most cases, the scene pictures obtained are taken from the side. Therefore, when obtaining sample pictures, the image sampling mechanism 111 should be able to take pictures from a certain angle, which is more in line with the actual data scenario.

[0111] For example, when the position parameter information in the image acquisition parameter is 3 meters horizontally from the target object in the image acquisition platform 120, 1.5 meters above the plane of the image acquisition platform 120, and the image acquisition mechanism 111 is rotated 60 degrees from the second drive mechanism 1122 to the first drive mechanism 1121, the image data is acquired. The description of the position parameter information is related to the selected reference object and can be defined according to the convenience of the actual description.

[0112] In some embodiments, the lighting parameters include at least one of the lighting angle and the lighting intensity. The lighting mechanism 113 includes a lighting component and a lighting driving component connected to the lighting component and the image acquisition platform 120. The lighting driving component is at least used to drive the lighting component to emit a lighting beam to the image acquisition platform 120 at a preset angle. During the lighting mechanism 113 performing a first lighting operation, the lighting component emits a lighting beam of a first lighting intensity to the image acquisition platform 120; and / or the lighting driving component drives the lighting component to emit a lighting beam to the image acquisition platform 120 at a first lighting angle.

[0113] Exemplarily, by modifying the illumination intensity or illumination angle in the illumination parameters, the illumination component can emit an illumination beam to the image acquisition platform 120 according to the illumination intensity in the illumination parameters and / or emit an illumination beam to the image acquisition platform 120 according to the illumination intensity in the illumination parameters and / or emit an illumination beam to the image acquisition platform 120 according to a preset illumination angle in the illumination parameters.

[0114] For example, lighting has the functions of controlling exposure, showing contours, enhancing contrast, rendering emotions, etc. for image shooting. Different lighting intensities or lighting angles can make the photographed objects present different shooting effects. For example, under sufficient lighting conditions, good-quality photos can be taken, but under weak light conditions, the pictures taken will have a lot of noise. Therefore, different lighting parameters will obtain different image data.

[0115] For example, the illumination angle makes the target object have different effects when the light source illuminates the target object due to different directions and angles. The illumination angle can be divided into flat light, side light, backlight, top light, and bottom light. The angle formed between the lighting component and the reference object can also be divided. For example, if the reference object is set as the image acquisition platform 120, the angle can be divided from 0-180 degrees. The illumination intensity can be divided according to the standard illumination value, for example, it can be divided into 0.5, 1, 2, 3, 5, 10, 15, 20, 30, 50, 75, 100, 150, 200, 300, 500, 750, 1000, 1500, 2000, 3000, 5000 lx grades, where lx is the lux unit of illumination. The illumination intensity can also be divided according to the size of the luminous flux transmitted by the light source in a certain direction.

[0116] Step S2: After the image processing device 130 receives the image data, the image processing device 130 is controlled to pre-process the image data according to the scene category parameter to obtain a target sample image, and the pre-processing at least includes marking the target object.

[0117] Exemplarily, after the image processing device 130 receives the image data, it is necessary to preprocess the obtained image data according to the scene category parameters, so as to obtain the target sample image for subsequent deep learning model training. The image data received by the image processing device 130 does not have annotation information, so the image data needs to be annotated when preprocessing the image data.

[0118] In some embodiments, the image processing device 130 is controlled to preprocess the image data according to the scene category parameters to obtain the target sample image, including: controlling the image processing device 130 to extract the contour information of the target object in the image data, and determining the annotation box of the target object in the image data according to the contour information; according to the scene category parameters, using the annotation box to select the target object in the image data to obtain the target sample image.

[0119] Exemplarily, the obtained image data can be preprocessed to obtain the contour information of the target object using edge extraction technology, and then the size of the annotation box that completely frames the target object in the image data is determined based on the contour information, that is, the annotation box information of the target object in the image data is determined, and the annotation box information of the target object in the image data and the image data together constitute the target sample image. That is, the target sample image data contains the image data and the annotation box information of the target object in the image data. Then, the model training can be performed based on the target sample image.

[0120] For example, the extraction of the contour information of the target object in the image data can be achieved by setting the background image in the image acquisition platform 120 during image acquisition to a green cloth, and then through preset green cloth color thresholds C1 and C2, where C1 < C2. By using the preset color thresholds C1 and C2 to extract the pixel points of the green background in the image data, and then extracting all non-green background pixel points as the target object in the image data. Then, the contour algorithm and bounding box algorithm commonly used in the opencv algorithm package can be used to automatically extract the contour and bounding box information of the target object in the image data, and thus obtain the annotation box information of the target object in the image data.

[0121] Exemplarily, after obtaining the image data, the target object in the image data is boxed by an annotation box through preprocessing the image data. In the real scene, the background of the image data is diverse. Therefore, the green cloth background of the image data needs to be converted into the real scene background according to the scene category parameter. Specifically, digital synthesis technology is used to achieve seamless synthesis of the target object and the real scene background, making the collected image data more realistic.

[0122] In some embodiments, according to the scene category parameter, the target object in the image data is boxed by an annotation box to obtain a target sample image, including: dividing the image data into a target object image and a background image according to the target object in the image data; determining the background image style according to the scene category parameter, updating the background image to the background image style, and fusing the updated background image and the target object image to form a target sample image.

[0123] Exemplarily, the scene background picture corresponding to the scene category parameter can be composed of a static scene picture or a dynamic scene picture. Among them, the static scene picture is a picture under the scene category collected in advance, and the dynamic scene picture is jointly collected in real time according to the rotation angle corresponding to the rotation operation of the placement component 1201 controlled by the controller 140 during the image acquisition process and constructing a virtual scene under the scene category parameter.

[0124] Exemplarily, the controller 140 sets the scene category parameters of the image processing device 130, and places the target object on the placement component 1201, and controls the placement component 1201 to perform a rotation operation through the controller 140 to adjust the placement angle of the target object to a preset angle, and after the placement angle of the target object is adjusted to the preset angle, the controller 140 controls the image acquisition device 110 to perform an image acquisition operation, thereby obtaining image data corresponding to the rotation angle of the target object. The controller 140 sends the preset angle executed by the control placement component 1201 to the image processing device 130. After receiving the rotation angle and image data corresponding to the target object, the image processing device 130 also rotates the virtual scene established under the scene category parameters according to the rotation angle corresponding to the target object, thereby obtaining a dynamic background picture under the scene category parameters and the rotation angle, so that the background picture is more realistic and diverse.

[0125] For example, the scene category parameter is set to the living room, and the placement component 1201 is rotated 5 degrees relative to the image acquisition platform 120. At this time, the information that the placement component 1201 is rotated 5 degrees relative to the image acquisition platform 120 is sent to the image processing device 130. After receiving the rotation angle information and the scene category parameter as the living room, the image processing device 130 constructs a corresponding virtual scene for the living room according to the scene category parameter, rotates the virtual scene by 5 degrees, and obtains the background picture under this setting for subsequent image fusion.

[0126] Exemplarily, after obtaining the image data, the target object in the image data is obtained by preprocessing the image data according to the scene category, the image data can be divided into a target object image and a background image according to the target object, the background image can be selected from a background library under the scene category parameters, and the selected background image and the target object image can be fused to form a target sample image.

[0127] For example, Figure 6 As shown, the target object to be collected is placed on the placement component 1201, and image collection parameters such as illumination parameters, position parameters, etc. are adjusted. The image collection device 110 is controlled to collect image data corresponding to the target object; the target object in the image data is obtained by using a green cloth removal algorithm on the image data, and the image data is divided into a background image and a target object image according to the target object, that is, the image data is divided into a target object image and a non-target object image, wherein the non-target object image is an image to be replaced by the background screen.

[0128] A background picture is selected from the background library corresponding to the scene category parameter to replace the background image in the image data with the background picture, so that the background picture and the target object image are fused, and the target object in the image data is automatically labeled. Please refer to the above for the specific implementation process.

[0129] Among them, the background image in the image data is replaced with a background picture, and the background picture can be divided into a first background picture and a second background picture. The first background picture can be understood as the background picture for placing the target object, and the second background picture can be understood as the background picture perpendicular to the first background picture.

[0130] The first background image can be various ground materials, and the second background image can be a wall, a bookshelf, a bed, etc. The first background image and the second background image can be combined with each other to increase the diversity of the target scene. The first background image and the second background image can be selected from the corresponding background library under the scene category parameter.

[0131] The target object is obtained by removing the green cloth algorithm and the image data is divided into the target object image and the background image according to the target object. The background image in the image data is replaced with the background image by selecting the static background picture according to the static background library corresponding to the scene category parameter. A variety of target sample data can be obtained. However, when this method is used, when the target object rotates, when the static background picture and the target object image are fused, the content of the static background picture will not rotate accordingly, which makes the fused image lack a certain degree of authenticity. Moreover, the data in the static scene library is limited, which also leads to a lack of diversity in the fused image data. Based on this defect, the present application proposes to introduce a virtual scene to construct a dynamic scene picture, so that when the target object rotates, the background picture can also change accordingly.

[0132] For example, Figure 7 As shown, the target object to be collected is placed on the placement component 1201, and image collection parameters such as illumination parameters, position parameters, etc. are adjusted. The image collection device 110 is controlled to collect image data corresponding to the target object; the target object in the image data is obtained by using a green cloth removal algorithm on the image data, and the image data is divided into a background image and a target object image according to the target object, that is, the image data is divided into a target object image and a non-target object image, wherein the non-target object image is an image to be replaced by the background screen.

[0133] The rotation angle of the placement component 1201 relative to the image acquisition platform 120 is sent to the image processing device 130. After receiving the rotation angle information and the scene category parameter, the image processing device 130 constructs a corresponding virtual scene according to the scene category parameter, such as a living room, and rotates the virtual scene by the rotation angle to obtain the background image corresponding to the virtual scene under the rotation angle, so that when the target object rotates, the background image can also change accordingly, thereby increasing the authenticity and diversity of the data and facilitating the subsequent use of the data.

[0134] In some embodiments, before controlling the image processing device 130 to preprocess the image data according to the scene category parameters, the method also includes: obtaining type information of the target object placed on the image acquisition platform 120; controlling the image processing device 130 to preprocess the image data according to the scene category parameters to obtain a target sample image, including: controlling the image processing device 130 to extract contour information of the target object in the image data, and marking a labeling box for the target object in the image data according to the contour information; selecting the target object in the image data using the labeling box according to the scene category parameters, and marking the type of the target object selected by the labeling box according to the type information to obtain a target sample image.

[0135] Exemplarily, after obtaining the annotation box information of the target object in the image data, one can only select a target object at that location through the model training box, but the type of the target object is unclear. Therefore, the type information of the target object placed on the image acquisition platform 120 can be obtained during the image data acquisition stage, and then the model can be trained based on the type information of the target object, thereby reducing the annotation cost of the image data and improving the efficiency of the model training.

[0136] For example, when placing the target object on the image acquisition platform 120, it can be understood as changing the shooting object. A type setting can be added to the image acquisition parameters, and the type indicates the type of the target object. The information of the image acquisition parameters and the image data are sent to the image processing device 130 together, and then the type of the target object in the image acquisition parameters is parsed when the image data is preprocessed, thereby obtaining the type information of the target object, wherein the target object type setting in the image acquisition parameters can be a person, a vehicle, etc., and can be set according to actual training needs. Therefore, the image acquisition parameters include at least one of the position parameters, the lighting parameters, and the target object type. Among them, the form used to express the target object type can be text, voice, etc.

[0137] The present application also provides a model training method, the method comprising: training a basic model using a target sample image as a training sample to obtain a target model, wherein the target sample image is obtained according to any sample image acquisition method. For a detailed description of the relevant content, please refer to the above-mentioned sample image acquisition method section, which will not be repeated here.

[0138] Exemplarily, the type of target object in the target sample image and the annotation box information of the target object are obtained by analyzing the target sample image, the type of target object for the target sample image classification is determined, and the target sample image is divided into training samples, test samples, and verification samples. When the accuracy of the verification sample reaches a set threshold or the number of training rounds reaches a preset value, the model training is stopped, and when the accuracy of the test sample meets the actual needs, the model training is completed and used in practice. When the accuracy of the test sample does not meet the actual needs, it is necessary to analyze the model, re-train the model, or increase the number of collected samples before training the model, or increase the number of training rounds for training.

[0139] The image data obtained by the sample image acquisition method of the present application can be used for image target recognition or image target type recognition. The model obtained by model training using the data obtained by the sample image acquisition method can be used in the field of autonomous driving, such as smart cars, smart electric wheelchairs, drones, etc., and can also be used in the field of intelligent robots, such as sweeping robots, mowing robots, etc.

[0140] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0141] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. An image acquisition system, characterized in that: The image acquisition system comprises: An image acquisition platform, the image acquisition platform comprising a placement component, the placement component can rotate relative to the image acquisition platform, and the placement component is used to place a target object to be imaged; An illumination mechanism, the illumination mechanism being installed on the image acquisition platform to provide illumination for the image acquisition platform; An image acquisition device, which is disposed on the image acquisition platform and can be displaced relative to the image acquisition platform to acquire image data of the target object; An image processing device and a controller, wherein the image processing device and the controller are both connected to the image acquisition device, and the controller is also connected to the rotating assembly and the lighting mechanism; Wherein, the controller is used to control the rotation of the placement component and the illumination of the illumination mechanism, thereby changing the image acquisition parameters, and the image acquisition parameters include position parameters and illumination parameters; The controller is used to control the image acquisition device to acquire image data of the target object located on the image acquisition platform with changed image acquisition parameters; The controller is used to send the image data to the image processing device; The image processing device receives the image data, and pre-processes the image data according to preset scene category parameters to obtain a target sample image.

2. The image acquisition system according to claim 1, characterized in that: The image acquisition device comprises an image acquisition mechanism and a driving mechanism; Wherein, the driving mechanism is used to drive the image acquisition mechanism to move relative to the image acquisition platform.

3. The image acquisition system according to claim 2, characterized in that: The driving mechanism includes a first driving mechanism and a second driving mechanism, wherein the first driving mechanism is connected to the image acquisition platform and can be displaced relative to the image acquisition platform, and the second driving mechanism is connected to the first driving mechanism and the image acquisition mechanism, and is used to drive the image acquisition mechanism to displace at least in a height direction relative to the first driving mechanism and / or drive the image acquisition mechanism to rotate a preset angle relative to the first driving mechanism; During the process in which the driving mechanism performs the first driving operation, at least one of the first driving mechanism and the second driving mechanism drives the image acquisition mechanism to change its relative position relative to the target object placed on the image acquisition platform.

4. The image acquisition system according to claim 1, characterized in that: The lighting mechanism includes a lighting component and a lighting driving component connected to the lighting component and the image acquisition platform; Wherein, the illumination driving component is at least used to drive the illumination component to emit an illumination beam to the image acquisition platform at a preset angle; During the first illumination operation performed by the illumination mechanism, the illumination component emits an illumination light beam of a first illumination intensity to the image acquisition platform; and / or the illumination driving component drives the illumination component to emit an illumination light beam to the image acquisition platform at a first illumination angle.

5. The image acquisition system according to claim 1, characterized in that: The image acquisition platform is provided with a placement component, which forms a placement area for placing the target object, and the placement component can rotate relative to the image acquisition platform to drive the target object placed in the placement area to rotate relative to the image acquisition platform.

6. The image acquisition system according to claim 5, characterized in that: The image acquisition platform comprises a first platform portion and a second platform portion, the placement component is arranged on the first platform portion, and the first platform portion is provided with a moving track corresponding to the placement component; The first driving mechanism of the image acquisition device can move closer to or farther from the placement component along the moving track.

7. The image acquisition system according to claim 6, characterized in that: One end of the second platform portion is connected to the first platform portion, and the first platform portion and the second platform portion are arranged at an angle β.

8. The image acquisition system according to claim 7, characterized in that: The lighting mechanism is arranged at an end of the second platform portion away from the first platform portion; There are multiple lighting mechanisms, and each of the lighting mechanisms is arranged at intervals at an end of the second platform portion away from the first platform portion.

9. The image acquisition system according to any one of claims 1 to 8, characterized in that: The controller is used to control the image acquisition device to acquire image data of the target object located on the image acquisition platform with changed image acquisition parameters, including: Controlling the image acquisition device to acquire first image data of the target object located on the image acquisition platform with a first image acquisition parameter, and sending the first image data to the image processing device; After the image acquisition device acquires the first image data, the image acquisition device is controlled to adjust the first image acquisition parameter to a second image acquisition parameter, and the image acquisition device is controlled to acquire second image data of the target object located on the image acquisition platform with the second image acquisition parameter.

10. The image acquisition system according to any one of claims 1 to 8, characterized in that: The preprocessing of the image data according to preset scene category parameters to obtain a target sample image includes: Extracting contour information of a target object in the image data, and determining a labeling box of the target object in the image data according to the contour information; According to the scene category parameter, the target object in the image data is selected using the annotation box to obtain a target sample image.

Images