Image acquisition system, image acquisition method and electronic equipment

Abstract

The present application provides an image acquisition system, an image acquisition method, and an electronic device, which relate to the field of image acquisition. The image acquisition system includes multiple controllers and multiple DMS cameras corresponding to each controller, and the multiple controllers are connected through a first external pin. Among them, the controller is used to generate an image output trigger signal when receiving an image storage signal, and send the image output trigger signal to the multiple DMS cameras; the multiple DMS cameras are used to collect and output a specific number of frames of image data in response to the image output trigger signal; the controller is also used to select target frame image data from the specific number of frames of image data corresponding to each of the multiple DMS cameras for storage after a target time interval. The present application ensures the synchronization of image acquisition, while reducing data redundancy and improving the efficiency and accuracy of data processing.

Description

Technical Field

[0001] The present application relates to the field of image acquisition technology, and in particular to an image acquisition system, an image acquisition method and an electronic device. Background Art

[0002] The application of synchronized image acquisition technology with multiple cameras is crucial in the field of artificial intelligence, especially when training algorithms for character models, emotion models, and personality trait models. Specifically, by synchronously capturing images of a person from different angles at the same moment, the algorithm is provided with rich perspective information, thereby improving the accuracy of the model's judgment of the person's state. However, in practical applications, synchronized image acquisition faces some challenges. For example, the synchronization accuracy of the cameras must be very high to ensure that all images are captured at the exact same moment. Summary of the Invention

[0003] In view of this, embodiments of the present application provide an image acquisition system, an image acquisition method, and an electronic device.

[0004] In a first aspect, an embodiment of the present application provides an image acquisition system, comprising multiple controllers and multiple DMS cameras corresponding to each controller, wherein the multiple controllers are connected via a first external pin. The controller is configured to generate an image output trigger signal upon receiving an image storage signal and transmit the image output trigger signal to the multiple DMS cameras; the multiple DMS cameras are configured to acquire and output a specific number of frames of image data in response to the image output trigger signal; and the controller is further configured to select and store target frames of image data from the specific number of frames of image data corresponding to each of the multiple DMS cameras after a target time interval.

[0005] In combination with the first aspect, in certain implementations of the first aspect, the controller is further used to control other controllers connected to the controller to receive the image storage signal through the first external pin when the image storage signal is received, so that the other controllers can generate an image output trigger signal based on the image storage signal, and send the image output trigger signal to the multi-channel DMS cameras corresponding to each of the other controllers.

[0006] In conjunction with the first aspect, in certain implementations of the first aspect, each controller is connected to the multiple DMS cameras via a second external pin. The controller is further configured to trigger MIPI mode to control the multiple DMS cameras to synchronously capture and output a specific number of frames of image data upon receiving an image output trigger signal.

[0007] In combination with the first aspect, in certain implementations of the first aspect, the controller is further used to select a target DMS camera from multiple DMS cameras based on the performance indicators of the CPU, so as to select target frame image data from the image data of a specific number of frames corresponding to the target DMS camera for saving.

[0008] In combination with the first aspect, in certain implementations of the first aspect, the target time is determined based on a delay time of an image output trigger signal, an image acquisition cycle, and a specific number of frames.

[0009] In combination with the first aspect, in certain implementations of the first aspect, the target frame image data includes the second frame image data among the image data of a specific frame number.

[0010] In a second aspect, an embodiment of the present application provides an image acquisition method, which is applied to a first controller in a controller system, the first controller corresponding to multiple DMS cameras, and the controller system further including at least one second controller, the first controller being connected to the at least one second controller via a first external pin. The method comprises: upon receiving an image storage signal, generating an image output trigger signal, and sending the image output trigger signal to the multiple DMS cameras, so that the multiple DMS cameras capture and output a specific number of frames of image data in response to the image output trigger signal; and after a target time interval, selecting target frame image data from the specific number of frames of image data corresponding to each of the multiple DMS cameras for storage.

[0011] In combination with the second aspect, in certain implementations of the second aspect, when a storage image signal is received, the second controller connected to the first controller is controlled through the first external pin to receive the storage image signal, so that the second controller generates an output image trigger signal based on the storage image signal, and sends the output image trigger signal to the multiple DMS cameras corresponding to each of the second controllers.

[0012] In conjunction with the second aspect, in certain implementations of the second aspect, each first controller is connected to the multiple DMS cameras via a second external pin. The method further includes: triggering MIPI mode to control the multiple DMS cameras to synchronously capture and output a specific number of frames of image data upon receiving an image output trigger signal.

[0013] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: a processor; a memory for storing processor-executable instructions; and the processor is configured to execute the image acquisition method described in the second aspect.

[0014] The image acquisition system of the present application realizes an efficient image acquisition architecture through the design of multiple controllers and corresponding multi-channel DMS cameras. This design allows the system to synchronously capture images of people from different angles, providing rich perspective information for algorithm training, which helps to improve the accuracy of the model's judgment of the person's status. Secondly, the system ensures the synchronization of image acquisition through the mechanism of the controller receiving the image storage signal and generating the image output trigger signal. The pin connection and coordination between the controllers ensure the synchronization accuracy. Even when facing the synchronization challenges in actual applications, it can ensure that all images are captured at very close time points, thereby meeting the needs of high-precision synchronous image acquisition. Furthermore, the system saves after the target time interval, so that the system can selectively save the most valuable image data according to specific needs or conditions, optimizing the use of storage resources. Finally, the system saves the target frame image data from the image data of a specific frame number, which can reduce data redundancy and improve the efficiency and accuracy of data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 The figure shows an execution diagram of each component in the image acquisition system provided by one embodiment of the present application.

[0017] Figure 2 The figure shows the schematic diagram of traditional triggering output.

[0018] Figure 3 Shown is a schematic diagram of triggering image output using an image acquisition system provided by an embodiment of the present application.

[0019] Figure 4 The figure is a flow chart of an image acquisition method provided in one embodiment of the present application.

[0020] Figure 5 Shown is a structural schematic diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0022] In a multi-camera system, each controller independently receives signals from its connected cameras. Each controller has a hardware timestamp function that records the exact time the controller receives the signal. Based on this recorded timestamp, the controller determines a time point and then saves the image at that time or a later time point. While this method theoretically enables synchronized image acquisition, in practice, due to hardware and software limitations, there are slight differences in the timing of signal reception between controllers. This time difference results in different cameras starting image acquisition at the same time after receiving the signal.

[0023] Furthermore, after powering on, each camera continuously outputs images at a fixed rate (e.g., 25 frames per second, or approximately 40 milliseconds per frame). However, due to differences in the timing of signal reception by the controller and the camera's own startup and response time, the cameras may not start outputting images at exactly the same time. This asynchrony can result in some frames not being captured correctly, a phenomenon known as "frame dropout."

[0024] Frame loss means that in a continuous image sequence, some frames are lost due to temporal mismatch, which destroys the integrity of the image sequence. Ultimately, these unsynchronized images are saved, resulting in temporal deviations in the collected data, which is a serious problem for analysis and processing tasks that require precise time alignment. For example, when performing 3D reconstruction, motion analysis, or other applications that require high-precision temporal information (model training), image asynchrony can seriously affect the accuracy of the final results.

[0025] In order to overcome the above problems, Figures 1 to 3 , elaborate on the image acquisition system in this application.

[0026] First, the image acquisition system of the present application includes multiple controllers and a multi-channel DMS (Digital Multimedia System) camera corresponding to each controller, and the multiple controllers are connected via a first external pin.

[0027] Specifically, a controller generally refers to an electronic device that can receive signals, process data, and control camera operations, and is responsible for coordinating and managing the cameras connected to it. A DMS camera is a device that can capture digital video and is commonly used in monitoring, traffic management, security systems, and other fields. Multi-channel means that each controller can be connected to multiple such cameras, thereby expanding the monitoring range of the system. The first external pin refers to the physical interface or communication interface used for connection between controllers. This connection allows the controllers to exchange information, such as synchronization signals or control instructions, to ensure the coordinated operation of the entire system.

[0028] In the application, the connection method between the controller and the DMS camera in the image acquisition system allows the system to perform distributed processing. Each controller can independently manage the DMS camera to which it is connected, and communicate with other controllers through external pins to achieve synchronization and coordination of the entire system.

[0029] Figure 1 FIG2 is a schematic diagram showing the execution of various components in the image acquisition system provided by an embodiment of the present application. Specifically, the execution steps between the controller and the DMS camera in the image acquisition system can be referred to as follows.

[0030] The controller 110 generates an image output trigger signal upon receiving the image storage signal, and sends the image output trigger signal to the multiple DMS cameras.

[0031] The save-image signal is an input signal that indicates to the controller 110 that image data needs to be stored. For example, the save-image signal can be triggered by an external event, such as a timer expiration, motion detection, or other conditions, indicating that the controller can capture and save the image. Upon receiving the save-image signal, the controller 110 generates a output trigger signal, which is used by the controller 110 to synchronize the DMS camera 120 with the image data capture process, thereby triggering the DMS camera 120 to capture the image.

[0032] Specifically, when the controller 110 detects the image storage signal, it first generates an image output trigger signal according to the system design and preset logic. The signal is specifically used to instruct the DMS camera 120 to capture the image. After generating the corresponding signal, the controller 110 uses the first external pin connected to the DMS camera 120 to transmit the signal. For example, in this process, signal encoding is first required, that is, converting the image output trigger signal into a format suitable for transmission on the communication medium. For example, encoding includes converting the signal into a level change, a pulse sequence or other form so that it can be effectively transmitted on the transmission line. Then, the encoded image output trigger signal is sent to each DMS camera 120 through a physical connection (such as a cable or a wireless connection). During the transmission process, the signal may be affected by noise or interference. Therefore, some measures can also be taken, such as using shielded cables, adding signal amplifiers or adopting error detection and correction mechanisms to ensure the integrity and accuracy of the signal.

[0033] The multi-channel DMS cameras 120 collect and output a specific number of frames of image data in response to the image output trigger signal.

[0034] When the DMS camera 120 receives the signal, it first performs a decoding operation, converting the received coded signal back into the original control signal (i.e., the image output trigger signal). The decoding process involves performing necessary signal processing, such as filtering, amplification, and decoding, to ensure that the signal can be correctly identified. Once the DMS camera 120 correctly decodes the image output trigger signal, they will synchronously respond to this signal and perform corresponding operations according to the signal instructions, such as adjusting settings and capturing images.

[0035] Furthermore, the DMS camera 120 captures a specific number of frames of image data, providing the system with a series of representative and critical visual information. These specific frames of image data can capture important moments or changes in the scene being monitored or recorded, thereby meeting the system's requirements for accurate capture and detailed analysis of image information. For example, in a surveillance scenario, these frames may include the start and end of a movement, the occurrence of abnormal behavior, or the key stages of a specific event. In the field of industrial automation, this image data may be used to accurately measure product dimensions or detect defects.

[0036] It's understandable that by capturing a specific number of frames rather than a continuous video stream, the system can more efficiently utilize resources, reduce unnecessary data processing and storage, and ensure that high-quality image information is obtained at critical moments for further processing, analysis, or recording. This strategy enables image acquisition systems to perform their functions more intelligently and efficiently, whether in security monitoring, traffic management, production monitoring, or other situations requiring precise image capture.

[0037] In some embodiments, to ensure accurate signal transmission and system reliability, the communication protocol may also include control mechanisms, such as response signals or confirmation messages, to allow controller 110 to verify that the image output trigger signal has been successfully received and executed. Through the aforementioned encoding, transmission, decoding, and verification processes, controller 110 can effectively transmit the image output trigger signal to multiple DMS cameras 120, effectively managing and controlling the image capture process of these multiple DMS cameras 120 and achieving precise image acquisition control.

[0038] The controller 110 selects target frame image data from the specific number of frames of image data corresponding to the multiple DMS cameras and saves them after a target time interval.

[0039] For example, the target time in this embodiment is preset or dynamically adjusted based on real-time conditions. Simultaneously, controller 110 selects target frame image data from the captured image data based on system requirements or a preset algorithm. These frames represent critical moments or images with specific analytical value for subsequent analysis, recording, or reporting. For example, in a driver monitoring system, these images can be used to train models for assessing driver fatigue, distraction, or other potentially risky behaviors, thereby improving driving safety.

[0040] The image acquisition system of the present application realizes an efficient image acquisition architecture through the design of multiple controllers and corresponding multi-channel DMS cameras. This design allows the system to synchronously capture images of people from different angles, providing rich perspective information for algorithm training, which helps to improve the accuracy of the model's judgment of the person's status. Secondly, the system ensures the synchronization of image acquisition through the mechanism of the controller receiving the image storage signal and generating the image output trigger signal. The pin connection and coordination between the controllers ensure the synchronization accuracy. Even when facing the synchronization challenges in actual applications, it can ensure that all images are captured at very close time points, thereby meeting the needs of high-precision synchronous image acquisition. Furthermore, the system saves after the target time interval, so that the system can selectively save the most valuable image data according to specific needs or conditions, optimizing the use of storage resources. Finally, the system saves the target frame image data from the image data of a specific frame number, which can reduce data redundancy and improve the efficiency and accuracy of data processing.

[0041] Combine Figure 1 In the embodiment shown, in other embodiments of the present application, the target time is determined based on the delay time of the image output trigger signal, the image acquisition cycle and the specific frame number.

[0042] The image output trigger signal delay refers to the time from when the controller 110 receives the trigger signal to when the DMS camera 120 actually starts outputting images. The image acquisition cycle refers to the frequency at which the camera captures images. For example, if the DMS camera 120 captures images at a frequency of 25 frames per second, the acquisition cycle is 1 / 25 second.

[0043] Based on the above, the target time is determined as follows: First, determine the delay time T1 of the image output trigger signal. Then, determine the image acquisition period T2, which is the time required to acquire each image frame. Next, determine the specific frame number N, which is the number of image frames to be acquired. Based on this information, calculate the time from trigger signal reception to image saving start: T = T1 + N1 × T2. N1 represents the sequence number within the specific frame number.

[0044] For example, assume that the delay time T1 of the image output trigger signal is 100 milliseconds, the image acquisition period T2 is 40 milliseconds, the specific frame number is 3, and the target frame image data to be acquired is the second frame in the feature frame number. Then, the target time T == 100ms + 2 × 40ms = 180ms. This means that after 180 milliseconds from the time the image output trigger signal is received, the controller 110 will begin saving the image data. This time point ensures that the DMS camera 120 has output three frames of images and that the controller 110 has sufficient time to process and save this image data, thus avoiding black screen or frame loss issues.

[0045] Combine Figure 1 In the illustrated embodiment, in other embodiments of the present application, the target frame image data includes the second frame image data among the image data of a specific frame number.

[0046] As previously mentioned, after receiving a signal, multiple DMS cameras 120 may experience image acquisition asynchrony due to timing differences between controllers 110. This asynchrony can lead to different image startup times, resulting in frame loss and compromising the integrity and accuracy of image data. To address this issue, the present application connects the first external pins of multiple controllers 110 to achieve synchronized triggering, ensuring that all cameras begin operating simultaneously upon receiving the synchronization signal.

[0047] At the same time, in this solution, the DMS camera 120 outputs a specific number of frames of image data after being triggered. However, after being triggered once, the DMS camera 120 requires a certain amount of startup time to start capturing images from a static state. Therefore, the first frame of image output by a single DMS camera 120 is very likely to appear black. Furthermore, during the continuous capture process, some frames may not be successfully captured, resulting in frame loss in the third frame. Therefore, to ensure that the captured image data is both high-quality and synchronized, this embodiment selects the second frame of image data as the target frame of image data. In most cases, the second frame of image data can avoid the black screen issue of the first frame. Since it follows the first frame, it can maintain good synchronization and reduce the risk of frame loss.

[0048] As can be seen from the above, this embodiment not only improves the availability and accuracy of image data, but also reduces the requirements on CPU performance by reducing the number of images that need to be processed and stored, making the system more efficient and stable.

[0049] In combination with the foregoing embodiments, in other embodiments of the present application, the controller 110 is also used to, when receiving a storage image signal, control other controllers connected to the controller to receive the storage image signal through a first external pin, so that the other controllers can generate an output image trigger signal based on the storage image signal, and send the output image trigger signal to the multi-channel DMS cameras corresponding to each of the other controllers.

[0050] In this embodiment, the controller 110 also plays a collaborative role in the image acquisition system. In particular, after receiving the image storage signal, it interacts with other controllers through the first external pin to achieve synchronous image acquisition of multiple DMS cameras 120.

[0051] Specifically, after the controller 110 receives the image storage signal, it not only processes its own image storage signal, but also establishes a connection with other controllers through the first external pin to ensure that these controllers can also receive the image storage signal at the same time. Since they all respond based on the same initial signal, this design allows all controllers in the system to achieve synchronous operation.

[0052] Once the other controllers receive the image storage signal transmitted via the first external pin, they will generate their own image output trigger signals based on this signal. As mentioned above, the image output trigger signal is a signal used by the controller to instruct the multiple DMS cameras 120 connected to it to begin capturing images. This means that when the controller 110 triggers the other controllers to receive the image storage signal, all DMS cameras 120 in the entire system will receive the instruction to start working at the same time.

[0053] The key to this synchronization mechanism is ensuring that all DMS cameras 120 capture images at the same time, thus avoiding image asynchrony caused by time differences. This is crucial for applications requiring highly precise image synchronization, such as algorithm training for character models, emotion models, and character feature models. This embodiment achieves synchronized image capture between multiple controllers 110 and their connected multi-channel DMS cameras 120, improving overall system performance and reliability while ensuring the synchronization and integrity of image data.

[0054] In conjunction with the aforementioned embodiments, in other embodiments of the present application, each controller is connected to multiple DMS cameras via a second external pin. Controller 110 is further configured to trigger MIPI mode to control the multiple DMS cameras to synchronously capture and output a specific number of frames of image data upon receiving an image output trigger signal.

[0055] MIPI mode, which is a Mobile Industry Processor Interface (MIPI) used to transmit high-speed data between devices.

[0056] In this embodiment, the controller 110 is connected to the DMS camera 120 via a second external pin. When the controller 110 receives a specific image output trigger signal, it triggers the MIPI mode, allowing the controller 110 to send a signal to multiple connected DMS cameras 120, enabling them to begin operating synchronously. Once the MIPI mode is triggered, each DMS camera 120 begins synchronous image acquisition upon receiving the signal. The specific number of frames in this embodiment refers to the DMS camera 120 outputting a certain number of image frames after being triggered, rather than continuously outputting images. For example, according to actual testing, two frames are output per trigger.

[0057] In this way, the controller 110 can ensure that the multiple DMS cameras 120 can start working and output images at the same time after receiving the synchronization signal, thereby avoiding the frame loss problem during the image acquisition process and ensuring the synchronization and integrity of the image data.

[0058] In combination with the foregoing embodiments, in other embodiments of the present application, the controller 110 is further used to select a target DMS camera from multiple DMS cameras based on the performance indicators of the CPU, so as to select target frame image data from the image data of a specific number of frames corresponding to the target DMS camera for saving.

[0059] In this embodiment, the controller 110 evaluates the performance of its own CPU (Central Processing Unit) to ensure that the CPU can process and store the required image data when simultaneously capturing image data from multiple DMS cameras 120. For example, CPU performance indicators may include processing speed, memory capacity, and multitasking capabilities. These indicators determine the amount of image data the CPU can process and store per unit time.

[0060] For example, the controller 110 selects a specific target DMS camera from the multiple connected DMS cameras 120 based on these performance indicators, along with the camera's location, viewing angle, image quality, or other required characteristics. For example, if CPU performance is sufficiently high, the controller 110 may select data from all DMS cameras 120; if performance is limited, only image data from key viewing angles may be selected. The controller 110 then filters a specific number of frames of image data captured by the selected target DMS camera to obtain target frame image data. Finally, the controller 110 saves this target frame image data.

[0061] The solution in this embodiment can optimize resource utilization, ensuring that critical image data can be efficiently acquired, processed, and stored under limited CPU performance conditions, thereby improving the overall performance and reliability of the system. In addition, in this way, this application not only solves the problem of synchronous acquisition of multiple cameras, but also considers the impact of CPU performance on data acquisition and storage, making the entire image acquisition system more intelligent and efficient.

[0062] Figure 2 The figure shows the schematic diagram of traditional triggering output. Figure 3 Shown is a schematic diagram of triggering image output using an image acquisition system provided by an embodiment of the present application.

[0063] In traditional trigger-based image output solutions, each controller receives signals independently and then saves the image based on its own hardware timestamp. However, each controller relies on its own internal clock and processing speed, so the controller and its connected DMS camera are not completely synchronized. In this case, when multiple cameras are started simultaneously, due to slight differences in the time at which each controller receives the signal, the camera startup time will be inconsistent, resulting in asynchronous image acquisition. This in turn causes temporal misalignment of the image data, affecting the integrity of the image data and the accuracy of subsequent algorithm model training. In addition, because DMS cameras may start collecting images at different time points, frame loss may occur, that is, some image frames are not captured and saved.

[0064] The image acquisition system of the present application is used to acquire images. Figure 3 In this system, when one controller receives a signal, the external pins of all connected controllers change simultaneously, ensuring that all controllers receive the signal at the same time. This synchronization mechanism effectively solves the timing discrepancy problem found in traditional solutions. Furthermore, the multiple DMS cameras within each controller are configured not to output an image immediately upon power-up, but to wait for a trigger signal from the first external pin. Once the trigger signal is received, the controller controls the cameras via MIPI mode, causing them to output images simultaneously.

[0065] Figure 4 The figure shows a flow chart of an image acquisition method provided by one embodiment of the present application. Exemplarily, the method is applied to a first controller in a controller system, the first controller corresponding to multiple DMS cameras, and the controller system also including at least one second controller, the first controller being connected to the at least one second controller via a first external pin.

[0066] Specifically, if Figure 4 As shown, the method includes the following steps.

[0067] Step S410: When a picture storage signal is received, a picture output trigger signal is generated and sent to multiple DMS cameras.

[0068] The purpose of step S410 is to facilitate the multi-channel DMS cameras to collect and output a specific number of frames of image data in response to the image output trigger signal.

[0069] Specifically, when the controller detects the image storage signal, it first generates an image output trigger signal according to the system design and preset logic, which is specifically used to instruct the DMS camera to capture the image. After generating the corresponding signal, the controller uses the first external pin connected to the DMS camera to transmit the signal. Exemplarily, in this process, signal encoding is first performed, that is, the image output trigger signal is converted into a format suitable for transmission on the communication medium. For example, encoding includes converting the signal into a level change, a pulse sequence or other form for efficient transmission on the transmission line. Then, the encoded image output trigger signal is sent to each DMS camera through a physical connection (such as a cable or a wireless connection). During the transmission process, the signal may be affected by noise or interference. Therefore, some measures can also be taken, such as using shielded cables, adding signal amplifiers or adopting error detection and correction mechanisms to ensure the integrity and accuracy of the signal.

[0070] Step S420 : After a target time interval, target frame image data is selected from the specific number of frames of image data corresponding to the multiple DMS cameras for storage.

[0071] For example, the target time is preset or dynamically adjusted based on real-time conditions. Simultaneously, the controller selects target frames from the captured image data based on system requirements or a preset algorithm. These frames represent critical moments or images with specific analytical value for subsequent analysis, recording, or reporting. For example, in a driver monitoring system, these images can be used to train models to assess driver fatigue, distraction, or other potentially risky behaviors, thereby improving driving safety.

[0072] The image acquisition method of the present application realizes an efficient image acquisition architecture through the design of multiple controllers and corresponding multi-channel DMS cameras in the image acquisition system. This design allows the synchronous acquisition of character images from different angles, providing rich perspective information for algorithm training, which helps to improve the accuracy of the model's judgment of the character's status. Secondly, the method ensures the synchronization of image acquisition through the mechanism of the controller receiving the image storage signal and generating the image output trigger signal. The pin connection and coordination between the controllers ensure the synchronization accuracy. Even when facing the synchronization challenges in practical applications, it can ensure that all images are captured at very close time points, thereby meeting the needs of high-precision synchronous image acquisition. Furthermore, saving after the target time interval makes it possible to selectively save the most valuable image data according to specific needs or conditions, optimizing the use of storage resources. Finally, saving the target frame image data from the image data of a specific frame number not only reduces data redundancy, but also improves the efficiency and accuracy of data processing.

[0073] Combine Figure 4 In the embodiment shown, in other embodiments of the present application, the method further includes: when a storage image signal is received, controlling a second controller connected to the first controller to receive the storage image signal through a first external pin, so that the second controller generates an output image trigger signal based on the storage image signal, and sends the output image trigger signal to the multiple DMS cameras corresponding to each of the second controllers.

[0074] Specifically, after receiving the image storage signal, the first controller not only processes its own image storage signal, but also establishes a connection with other second controllers through the first external pin to ensure that these second controllers can also receive the image storage signal at the same time. Since they all respond based on the same initial signal, this design allows all controllers to achieve synchronous operation.

[0075] Once the second controller receives the image storage signal transmitted via the first external pin, it will generate its own image output trigger signal based on this signal. In other words, when the first controller triggers the second controller to receive the image storage signal, all DMS cameras in the image acquisition system will receive the instruction to start working at the same time.

[0076] The method in this embodiment ensures that all DMS cameras capture images at the same time, thus avoiding image desynchronization issues caused by time differences. This is crucial for applications requiring high-precision image synchronization, such as algorithm training for character models, emotion models, and personality trait models. It also improves the overall performance and reliability of the system, ensuring the synchronization and integrity of image data.

[0077] Combine Figure 4 In the embodiment shown, in other embodiments of the present application, each first controller is connected to multiple DMS cameras via a second external pin. Furthermore, the method further includes: triggering MIPI mode to control the multiple DMS cameras to synchronously capture and output a specific number of frames of image data upon receiving an image output trigger signal.

[0078] In this embodiment, the first controller is connected to the DMS camera via a second external pin. When the first controller receives a specific image output trigger signal, it triggers the MIPI mode, allowing the first controller to send a signal to multiple connected DMS cameras, enabling them to begin operating synchronously. Once the MIPI mode is triggered, each DMS camera begins synchronous image acquisition upon receiving the signal. Furthermore, the specific number of frames in this embodiment refers to the DMS camera outputting a certain number of image frames after being triggered, rather than continuously outputting images. For example, according to actual testing, two frames are output per trigger.

[0079] Through the method in this embodiment, the first controller can ensure that multiple DMS cameras can start working and output images at the same time after receiving the synchronization signal, thereby avoiding the frame loss problem during the image acquisition process and ensuring the synchronization and integrity of the image data.

[0080] It should be noted that the descriptions of the image acquisition method embodiment and the image acquisition system embodiment correspond to each other. Therefore, for the parts not fully described in the image acquisition method embodiment, reference can be made to the previous image acquisition system embodiment.

[0081] Below, reference Figure 5 To describe the electronic device according to the embodiment of the present application. Figure 5 Shown is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present application.

[0082] like Figure 5 As shown, the electronic device 50 includes one or more processors 501 and a memory 502 .

[0083] The processor 501 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 50 to perform desired functions.

[0084] The memory 502 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 501 may execute the program instructions to implement the image acquisition method of each embodiment of the present application described above and / or other desired functions. Various contents such as image storage signals, image output trigger signals, image data of characteristic frames, target frame image data, etc. may also be stored in the computer-readable storage medium.

[0085] In one example, the electronic device 50 may further include an input device 503 and an output device 504 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0086] The input device 503 may include, for example, a keyboard, a mouse, and the like.

[0087] The output device 504 can output various information to the outside, including image storage signals, image output trigger signals, image data of characteristic frames, target frame image data, etc. The output device 504 can include, for example, a display, a speaker, a printer, a communication network and its connected remote output devices, etc.

[0088] Of course, to simplify, Figure 5 Only some of the components related to the present application in the electronic device 50 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device 50 may further include any other appropriate components according to specific application scenarios.

[0089] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this application are merely illustrative and not restrictive, and it should not be assumed that these advantages, strengths, and effects are required of each embodiment of this application. In addition, the specific details disclosed above are merely illustrative and facilitating understanding, and are not restrictive. The above details do not limit this application to necessarily being implemented using the above specific details.

[0090] The block diagrams of the devices, devices, equipment, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0091] It should also be noted that in the apparatus, device, and method of the present application, each component or each step can be decomposed and / or recombined, and such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0092] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0093] The above description has been provided for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. An image acquisition system, characterized in that: The device comprises a plurality of controllers and a plurality of DMS cameras corresponding to each of the controllers, wherein the plurality of controllers are connected to each other via a first external pin; The controller is configured to generate an image output trigger signal upon receiving an image storage signal, and send the image output trigger signal to the multi-channel DMS cameras; The multi-channel DMS camera is used to collect and output a specific number of frames of image data in response to the image output trigger signal; The controller is further configured to select and save target frame image data from the specific number of frames of image data corresponding to each of the multiple DMS cameras after a target time interval, wherein the target time is determined based on a delay time of the image output trigger signal, an image acquisition cycle, and the specific number of frames, and the target time is determined based on a product of the delay time of the image output trigger signal plus the image acquisition cycle and an arrangement sequence number of the target frame image data in the specific number of frames; The controller is also used to control other controllers connected to the controller to receive the image storage signal through the first external pin when the image storage signal is received, so that the other controllers can generate the image output trigger signal based on the image storage signal and send the image output trigger signal to the multi-channel DMS cameras corresponding to each of the other controllers.

2. The image acquisition system according to claim 1, wherein: Each of the controllers is connected to the multi-channel DMS cameras via a second external pin; The controller is further configured to trigger the MIPI mode to control the multiple DMS cameras to synchronously capture and output a specific number of frames of image data after receiving the image output trigger signal.

3. The image acquisition system according to claim 1, wherein: The controller is further configured to select a target DMS camera from the multiple DMS cameras based on a CPU performance indicator, so as to select target frame image data from the specific number of frames of image data corresponding to the target DMS camera for storage.

4. The image acquisition system according to claim 1, wherein: The target frame image data includes the second frame image data among the specific number of frames of image data.

5. An image acquisition method, characterized in that: A first controller is applied to a controller system, the first controller corresponds to multiple DMS cameras, the controller system further includes at least one second controller, the first controller is connected to the at least one second controller via a first external pin; the method includes: When receiving the image storage signal, generating an image output trigger signal, and sending the image output trigger signal to the multi-channel DMS camera, so that the multi-channel DMS camera collects and outputs a specific number of frames of image data in response to the image output trigger signal; After a target time interval, target frame image data is selected from the specific number of frames of image data corresponding to each of the multiple DMS cameras for storage, wherein the target time is determined based on a delay time of the image output trigger signal, an image acquisition cycle, and the specific number of frames, and the target time is determined based on a product of the delay time of the image output trigger signal plus the image acquisition cycle and an arrangement sequence number of the target frame image data in the specific number of frames; When the image storage signal is received, the second controller connected to the first controller is controlled through the first external pin to receive the image storage signal, so that the second controller generates the image output trigger signal based on the image storage signal, and sends the image output trigger signal to the multiple DMS cameras corresponding to the second controllers.

6. The image acquisition method according to claim 5, characterized in that: Each of the first controllers is connected to the multi-channel DMS cameras via a second external pin; the method further includes: By triggering the MIPI mode, the multi-channel DMS cameras are controlled to synchronously collect and output a specific number of frames of image data after receiving the image output trigger signal.

7. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to execute the image acquisition method described in any one of claims 5 to 6.

Images