A carbon flux monitoring system, method, electronic device, and storage medium

Abstract

The present disclosure provides a carbon flux monitoring system, method, electronic device and storage medium, relating to the technical field of marine environment monitoring, the system comprises a plurality of water sample collectors, underwater microscopic imaging units, connecting cables and an upper computer; wherein the plurality of water sample collectors are arranged along the vertical direction and are connected through the connecting cables; the underwater microscopic imaging units are staggered and installed on the water sample collectors; the water sample collector is used for collecting water samples to be tested; the underwater microscopic imaging unit is used for optical imaging of the water samples to be tested to obtain initial images; the initial images are screened to obtain target images containing particulate organic carbon; the target images are transmitted to the upper computer; the upper computer is used for determining the carbon flux statistical data of particulate organic carbon based on the target images. The scheme of the present disclosure can stably and efficiently realize the monitoring of water body particulate organic carbon and the statistics of carbon flux.

Description

Technical Field

[0001] This disclosure relates to the field of marine environmental monitoring technology, and in particular to a carbon flux monitoring system, method, electronic device and storage medium. Background Technology

[0002] One of the core objectives of marine environmental surveys is to elucidate the intrinsic mechanisms of marine biogeochemical cycles, thereby enhancing the ability to predict and forecast marine environmental and climate change. Among these, research on biogeochemical cycle processes related to carbon flux is particularly crucial. This research possesses both fundamental theoretical value and significant applied value, serving as a core foundation and fundamental basis for understanding the patterns of global climate change and the evolution of the marine ecological environment. Traditional sampling and analysis methods are insufficient for accurately obtaining marine carbon flux. Summary of the Invention

[0003] This disclosure provides a carbon flux monitoring system, method, electronic device, and storage medium to at least solve the above-mentioned technical problems existing in the prior art.

[0004] According to a first aspect of this disclosure, a carbon flux monitoring system is provided, the system comprising a plurality of water sample collectors, an underwater microscopic imaging unit, a connecting cable, and a host computer; wherein the plurality of water sample collectors are arranged vertically and connected by the connecting cable; the underwater microscopic imaging unit is alternately installed on the water sample collectors; The water sample collector is used to collect water samples to be tested; The underwater microscopic imaging unit is used to perform optical imaging on the water sample to be tested to obtain an initial image; to screen the initial image to obtain a target image containing particulate organic carbon; and to transmit the target image to the host computer. The host computer is used to determine the carbon flux statistics of particulate organic carbon based on the target image.

[0005] In one possible embodiment, the underwater microscopic imaging unit includes an illumination module and an optical imaging module, wherein the optical imaging module includes an objective lens assembly, a rear lens assembly, and a CCD imaging assembly; wherein, The lighting module is used to emit a light source to illuminate the water sample to be tested; The objective lens assembly is used to magnify and converge light on the illuminated water sample to obtain a front-end microscopic image; The rear lens assembly is used to correct and optimize the front-end microscopic imaging to obtain the rear-end optical image; The CCD imaging component is used to convert the back-end optical image into an electrical signal to obtain an initial image.

[0006] In one embodiment, the underwater microscopic imaging unit further includes a circuit and a storage module; the circuit and storage module is used for: Based on the initial image, image noise parameters are obtained; Based on the image noise parameters, determine the block-level threshold parameters and the frame-level threshold parameters; The initial image is detected using the block-level threshold parameter and the frame-level threshold parameter respectively, to obtain a first detection result and a second detection result. Based on the first detection result and the second detection result, it is confirmed whether particulate organic carbon exists in the initial image; If particulate organic carbon is present, the initial image is stored as the target image.

[0007] In one possible implementation, the host computer is further configured to: Obtain image background features; The target image is segmented based on the background features of the image to obtain a specific foreground target; Feature extraction is performed on the specific foreground target to obtain the corresponding feature vector; Carbon flux statistics are obtained based on the feature vectors corresponding to adjacent video frames.

[0008] In one possible implementation, the host computer is further configured to: A cost function is constructed based on the target's location features, size features, and color grayscale features. Based on the cost function and the feature vectors corresponding to adjacent video frames, the particle organic carbon quantity, single particle morphology and size and spatial distribution information are obtained. The quantity of particulate organic carbon, the morphological size of individual particles, and their spatial distribution information are used as the carbon flux statistics.

[0009] In one possible implementation, the host computer is further configured to: Based on the image background features, the background grayscale distribution features are obtained; The image background features are updated based on the background grayscale distribution features, taking into account the learning rate. The target image is segmented based on the updated image background features to obtain specific foreground targets.

[0010] In one possible implementation, the host computer is further configured to: The target image is segmented based on the updated image background features to obtain the initial foreground target; The initial foreground target is morphologically optimized, and the optimized initial foreground target is input into the classification model for recognition and classification. The specific foreground target output by the classification model is obtained.

[0011] According to a second aspect of this disclosure, a carbon flux monitoring method is provided, the method being applied to a carbon flux monitoring system, the system comprising a plurality of water sample collectors, an underwater microscopic imaging unit, a connecting cable, and a host computer; wherein the plurality of water sample collectors are arranged vertically and connected by the connecting cable; the underwater microscopic imaging unit is alternately mounted on the water sample collector; the method includes: The water sampler collects the water sample to be tested. The underwater microscopic imaging unit performs optical imaging on the water sample to be tested to obtain an initial image; the initial image is screened to obtain a target image containing particulate organic carbon; the target image is transmitted to the host computer. The host computer determines the carbon flux statistics of particulate organic carbon based on the target image.

[0012] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods described in this disclosure.

[0013] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform the methods described in this disclosure.

[0014] This disclosed carbon flux monitoring system deploys multiple water samplers vertically, interleaved with underwater microscopic imaging units. This enables in-situ, non-contact observation of water samples at different depths and from multiple azimuths, effectively improving imaging quality and POC identification accuracy. The underwater microscopic imaging units automatically filter valid target images, significantly reducing the transmission and storage burden of invalid images. A host computer can perform long-term real-time analysis of the target images, outputting in-situ monitoring data. The beneficial effects of this system are: it not only solves the problems of insufficient sample representativeness, easy underestimation of POC abundance, and biased carbon flux measurement results associated with traditional manual sampling, but also significantly reduces the manpower and material costs of monitoring operations. It overcomes the limitations of traditional methods in conducting large-scale, long-term continuous observations, and can continuously output high-precision, large-volume, and highly reliable carbon flux statistical results.

[0015] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0016] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation, in which: In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

[0017] Figure 1 A schematic diagram of the composition structure of the carbon flux monitoring system according to an embodiment of this disclosure is shown. Figure 1 ; Figure 2 A schematic diagram of the composition structure of the carbon flux monitoring system according to an embodiment of this disclosure is shown. Figure 2 ; Figure 3 A schematic diagram of the composition structure of the underwater microscopic imaging unit according to an embodiment of this disclosure is shown. Figure 1 ; Figure 4 A schematic diagram of the composition structure of the underwater microscopic imaging unit according to an embodiment of this disclosure is shown. Figure 2 ; Figure 5 A schematic diagram of the composition structure of the circuit and memory module according to an embodiment of the present disclosure is shown; Figure 6 A schematic diagram illustrating the implementation flow of the carbon flux monitoring method according to an embodiment of this disclosure is shown; Figure 7 A schematic diagram of the composition structure of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0018] To make the objectives, features, and advantages of this disclosure more apparent and understandable, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0019] Current surveys and analyses of marine particulate organic carbon (POC) primarily employ a combination of trawl sampling and on-site water collection, along with laboratory microscopic observations to identify and count particles. While this method allows for direct observation of POC microstructures, it suffers from several limitations, significantly reducing the reliability and systematic nature of marine carbon flux research. Firstly, POC abundance in marine waters is generally low, and single-point sampling can lead to overgeneralization, easily underestimating the actual content and quantity of particles, resulting in distorted carbon flux parameter calculations. Secondly, this work demands high levels of expertise from personnel and relies on specialized research vessels, instruments, and dedicated voyages, resulting in high overall operating costs. Furthermore, the limited amount of sampled data makes it difficult to support regional or even global-scale carbon flux research. Thirdly, due to operational limitations, this method cannot conduct large-scale, long-term continuous monitoring, lacking comprehensive spatiotemporal POC data, which greatly hinders technological advancements in areas such as marine carbon cycling, red tide control, fisheries resource assessment, and marine climate prediction.

[0020] To address the aforementioned technical problems, the first aspect of this disclosure provides a carbon flux monitoring system, such as... Figure 1 and Figure 2 As shown, the system includes several water sample collectors 1, underwater microscopic imaging units 2, connecting cables 3, and a host computer (not shown in the figure). The water sample collectors 1 are arranged vertically and connected by the connecting cables 3. The underwater microscopic imaging units 2 are staggered on the water sample collectors 1. The water sample collectors 1 are used to collect water samples to be tested. The underwater microscopic imaging units 2 are used to perform optical imaging on the water samples to obtain an initial image. The initial image is then filtered to obtain a target image containing particulate organic carbon. The target image is transmitted to the host computer. The host computer is used to determine the carbon flux statistics of particulate organic carbon based on the target image.

[0021] Specifically, the water sampler adopts a funnel-shaped structure, with filters installed at both the top and bottom to remove suspended impurities from seawater, reduce interference, and improve the accuracy of the underwater microscopic imaging unit in identifying particulate organic carbon. For example... Figure 1As shown, multiple water samplers are arranged vertically and connected together by cables. Fastening nuts are installed at both the top and bottom of the entire device to ensure that each sampler remains vertical. The connecting cables at the top of the device can be connected to buoys or deployed vessels, enabling fixed-point deployment and long-term continuous monitoring in the target sea area. The number of water samplers deployed can be determined according to actual monitoring needs. Due to the limitations of the imaging field of view, the underwater microscopic imaging units in this embodiment are staggered on both sides of the water samplers. This deployment method allows for multi-directional and multi-depth detection and identification of POCs, while continuously monitoring the sedimentation changes of particulate organic carbon.

[0022] A carbon flux monitoring system is deployed to the target sea area, where a water sampler collects the water samples to be tested. An underwater microscopic imaging unit mounted on the sampler performs optical imaging on the collected water samples to generate initial images. Due to the large amount of initial image data collected on-site, the initial images are quickly screened to extract target images containing particulate organic carbon (POC), and then transmitted to a host computer. This host computer, using an embedded architecture, receives the target images sent by the underwater microscopic imaging unit, analyzes and processes them to obtain statistical data on particulate organic carbon flux, specifically including indicators such as particle number, morphology, size, and spatial distribution.

[0023] The carbon flux monitoring system in this embodiment deploys multiple water samplers vertically and alternately integrates underwater microscopic imaging units. This enables in-situ observation of water samples at different depths and from multiple azimuths, effectively improving imaging quality and POC identification accuracy. The underwater microscopic imaging units automatically filter valid target images, significantly reducing the transmission and storage burden of invalid images. The host computer can perform long-term real-time analysis of the target images and output in-situ monitoring data. Based on the above structural design, this system has the following beneficial effects: it can solve the problems of insufficient representativeness of traditional manual sampling, easy underestimation of POC abundance, and deviation in carbon flux measurement results; it significantly reduces the manpower and material costs of monitoring operations; it compensates for the shortcomings of traditional methods in conducting large-scale, long-term continuous observations; and it can continuously output high-precision, large-volume, and highly reliable carbon flux statistical results.

[0024] In another possible embodiment of this disclosure, such as Figure 3 and Figure 4As shown, the underwater microscopic imaging unit includes an illumination module 21 and an optical imaging module. The optical imaging module includes an objective lens assembly 22, a rear lens assembly 23, and a CCD imaging assembly 24. The illumination module 21 is used to emit a light source to illuminate the water sample to be tested. The objective lens assembly 22 is used to magnify and converge the light on the illuminated water sample to obtain a front-end microscopic image. The rear lens assembly 23 is used to correct and optimize the front-end microscopic image to obtain a rear-end optical image. The CCD imaging assembly 24 is used to convert the rear-end optical image into an electrical signal to obtain an initial image.

[0025] Specifically, given the high-speed flow of water samples within the monitoring area, a high-speed industrial CCD image sensor can be used as the CCD imaging component to obtain clear and distortion-free image signals. Leveraging its high-speed acquisition and image stabilization capabilities, combined with increased shutter speed and higher ISO sensitivity to shorten exposure time, image distortion is effectively avoided, ensuring image quality. The underwater microscopic imaging unit features a full-spectrum, dispersion-free sealed window made of corundum material. This material has excellent resistance to marine organism adhesion, effectively mitigating biofouling caused by long-term underwater operations and maintaining stable light transmission. The equipment employs a transmissive optical path layout. After the water sampler collects the water sample, the illumination module outputs light to uniformly illuminate the sample. The objective lens assembly performs optical magnification and light convergence, forming the front-end microscopic image. The rear lens assembly performs aberration correction and optical optimization to obtain the back-end optical image. Finally, the CCD imaging component performs photoelectric conversion, outputting a clear and stable initial image. The image signal is transmitted in the standard PAL (Phase Alternating Line) video format.

[0026] The underwater microscopic imaging unit in this embodiment relies on the coordinated operation of the illumination module, multi-level optical components and CCD imaging components to achieve image acquisition in flowing water. The entire imaging link structure is complete and operates in an orderly manner, and can continuously output high-quality images, providing reliable data support for subsequent particulate organic carbon identification and carbon flux analysis.

[0027] In another possible embodiment of this disclosure, such as Figure 3 and Figure 4 As shown, the underwater microscopic imaging unit further includes a circuit and storage module 25; the circuit and storage module 25 is used to obtain image noise parameters based on the initial image; determine block-level threshold parameters and frame-level threshold parameters based on the image noise parameters; detect the initial image using the block-level threshold parameters and the frame-level threshold parameters respectively to obtain a first detection result and a second detection result; confirm whether particulate organic carbon exists in the initial image based on the first detection result and the second detection result; if particulate organic carbon exists, store the initial image as a target image.

[0028] In this embodiment, the underwater microscopic imaging unit integrates circuitry and a storage module. This circuitry and storage module first analyzes the acquired initial image, calculating the noise parameters of the most recent image sequence to characterize the noise intensity of the image sequence, thus obtaining the image noise parameters. Based on these parameters, a block-level threshold parameter t(N) characterizing the local noise level and a frame-level threshold parameter T(N) characterizing the global noise level are calculated. Subsequently, the initial image is subjected to dual detection using both the block-level and frame-level threshold parameters, yielding two sets of detection results. Based on these detection results, the presence of POC in the image is comprehensively determined. If the target substance is determined to be present in the image, the initial image is marked as a target image and stored. Otherwise, image storage is stopped, and image sequences without particulate organic carbon are no longer saved, thereby achieving pre-screening and effective retention of images.

[0029] In one possible implementation, such as Figure 5 As shown, the circuit and storage module can be implemented using a hardware architecture based on a digital signal processor (DSP). The system uses the DSP as the core control unit, and the front end receives image data from the underwater microscopic imaging unit through a video decoder. Under the control of the DSP, the video decoder completes analog-to-digital conversion and outputs a digital video stream. The DSP is externally connected to DDR2 SDRAM as running memory, and NOR Flash is used to store the program and configuration parameters, providing computing resources to support the image processing algorithms.

[0030] The image data processing and storage process is as follows: The DSP first performs noise analysis on the initial image sequence, calculates the image noise parameters, and generates block-level threshold parameters t(N) and frame-level threshold parameters T(N) accordingly. Then, through block-level and frame-level dual detection, it comprehensively determines whether a Point of Content (POC) exists in the image. If the image is determined to be a valid target image, the DSP connects to a 1.8V to 3.3V level converter via the EMIF interface to write the data to a CF card via CF I / F (CF interface) or to a hard disk drive via IDE I / F (IDE interface) for persistent storage. If the image is determined to be invalid, no storage operation is performed, thereby reducing data redundancy and minimizing storage resource consumption.

[0031] In addition, the module integrates a rich set of peripheral interfaces: it supports SD connectors via the SDIO interface; it connects to an external Ethernet physical layer chip via the EMAC interface to achieve 100M Ethernet communication; it connects to the ADM3202 chip via the UART0 interface to enable interaction with the super terminal; it also carries an RTC real-time clock module via I2C to provide timestamp information for image data; it enables program debugging and firmware upgrades via the JTAG interface; and the USB 2.0 I / F interface supports data export and peripheral expansion. The entire module is powered by an independent power control module, providing stable and reliable hardware support for long-term underwater monitoring.

[0032] The circuit and storage module in this embodiment achieves intelligent pre-screening of initial images through a block-level and frame-level dual threshold detection mechanism driven by image noise parameters. Only valid images containing particulate organic carbon are stored as target images, which not only greatly reduces the storage and transmission overhead of invalid data and alleviates the computing pressure on the host computer, but also effectively eliminates worthless images.

[0033] In another embodiment of this disclosure, the host computer is further configured to acquire image background features; segment the target image based on the image background features to obtain a specific foreground target; extract features from the specific foreground target to obtain a corresponding feature vector; and obtain carbon flux statistics based on the feature vectors corresponding to adjacent video frames.

[0034] First, the target image is preprocessed: denoising and scaling operations are performed on the real-time decoded target image. A spatial mean filtering algorithm is used to remove image sampling noise and interference from small, uniform impurities in the seawater, thereby improving target segmentation accuracy. The filter template window size is M, and the calculation formula is as follows:

[0035] in, Characterizes the grayscale values ​​of the image before preprocessing.

[0036] Subsequently, image background features characterizing the grayscale and texture information of the entire water body are obtained, and the preprocessed target image is segmented based on these image background features to obtain specific foreground targets containing particulate organic carbon.

[0037] Next, features are extracted from specific foreground targets to construct corresponding feature vectors. Feature dimensions may include target boundary shape compactness, color grayscale mean, grayscale co-occurrence matrix texture features, and invariant moment features. Finally, target matching and tracking are performed based on the feature vectors corresponding to adjacent video frames to achieve consistent labeling of the same particulate organic carbon target across frames, avoiding duplicate counting. Combining target quantity, morphology, size, and sedimentation motion information, carbon flux statistics are obtained, completing the quantitative monitoring of particulate organic carbon.

[0038] In another embodiment of this disclosure, the host computer is further configured to obtain background grayscale distribution features based on image background features; update the image background features based on the background grayscale distribution features in conjunction with a learning rate; and segment the target image based on the updated image background features to obtain a specific foreground target.

[0039] First, offline learning is performed on water images free of particulate organic carbon. An adaptive single Gaussian model is used to obtain the image background features, and the background grayscale distribution features are extracted from them. Based on the learning rate, the image background features are iteratively updated according to the background grayscale distribution features, using the following update formula:

[0040]

[0041] in, , These are the average background grayscale values ​​of frame t and frame (t+1), respectively. Let be the grayscale value of the pixel at the (t+1)th frame; α is the learning rate, used to control the speed of background updates, with a value range of 0 < α < 1; L is the reciprocal of the learning rate α. The above formula realizes adaptive iterative updates of the background mean, replacing floating-point multiplication with integer division, effectively improving computational efficiency. , Let L and L be the background grayscale variances of the t-th and t+1-th frames, respectively. This formula, together with the mean update formula, synchronously updates the dispersion of the background grayscale distribution. By relying on the parameter L to simplify the calculation, the computational cost is reduced while ensuring the adaptive capability of the background model.

[0042] Subsequently, the updated image background features are combined to extract the target using the background subtraction method. In the model, μ and σ are the mean and root mean square error of the background gray-level normal distribution, respectively. The target pixel determination criteria are as follows:

[0043] Image segmentation is performed according to this rule, ultimately yielding a specific foreground target.

[0044] This embodiment relies on an adaptive single Gaussian model to complete background modeling and dynamic updates, and combines background difference method to accurately segment targets. Integer division is used to optimize the operation logic and reduce computational overhead. At the same time, morphological processing is used to filter out interference. It can adapt to changes in the underwater environment, ensure the real-time effectiveness of background features, and efficiently and accurately separate specific foreground targets.

[0045] In another embodiment of this disclosure, the host computer is further configured to: segment the target image based on the updated image background features to obtain an initial foreground target; perform morphological optimization processing on the initial foreground target; input the optimized initial foreground target into a classification model for recognition and classification; and obtain a specific foreground target output by the classification model.

[0046] Combining the updated image background features, the target image is segmented using the aforementioned target pixel determination criteria. If the pixel grayscale difference is greater than three times the background grayscale fluctuation range, the pixel is determined to be a particle target pixel. By summing all pixels that meet the determination criteria, underwater particles can be segmented, generating an initial foreground target image. This result usually contains interference areas such as tiny seawater specks and large irrelevant impurities. Therefore, the initial foreground target is first subjected to erosion and dilation morphological optimization processing. For example, a 3×3 full-1 rectangular structuring element is selected, and the entire initial foreground target is eroded using this structuring element to shrink the target edges and filter out isolated tiny seawater specks. Then, the same structuring element is used to dilate the eroded image to restore the effective particle target outline and fill in the small cavities inside the target. This step can initially improve the segmentation quality, while the remaining large-volume impurities are further filtered out by the classification process. Subsequently, the optimized image is fed into a classification model to complete the identification and classification. The model can use the AdaBoost algorithm or a backpropagation neural network to achieve intelligent identification of underwater observation targets and finally output accurate specific foreground targets.

[0047] In another embodiment of this disclosure, the host computer is further configured to: construct a cost function based on target location features, size features, and color grayscale features; obtain information on the quantity of particulate organic carbon, the size of a single particle, and its spatial distribution based on the cost function and the feature vectors corresponding to adjacent video frames; and use the quantity of particulate organic carbon, the size of a single particle, and its spatial distribution as the carbon flux statistics.

[0048] Among them, target location features are used to characterize the coordinate position of particulate organic carbon in the image, size features are used to characterize the outline size and proportion of the particles, and color grayscale features are used to characterize the grayscale and color attributes of the particles. A cost function is constructed based on these three types of features, as shown in the following formula:

[0049] In the formula, For the target of the previous and next frames i With the goal j Matching cost value; , These are the coordinates of the target center in the two frames, 、 These are the horizontal and vertical normalization coefficients; 、 、 and 、 、 These are the three-channel color grayscale values ​​for the corresponding target; 、 For target size parameters; α, β, γ These are weighting coefficients, which respectively adjust the influence of position, color, and size features in the matching process.

[0050] Based on this cost function and combined with the feature vectors of adjacent video frames, cross-frame association matching of particulate organic carbon is completed, thereby statistically obtaining information on particle quantity, single particle morphology and size, and spatial distribution. This information is then integrated into carbon flux statistics. Simultaneously, real-time statistical data is stored locally, and corresponding target image frames are calibrated, supporting subsequent data playback, information retrieval, and other operations.

[0051] This embodiment integrates multiple features such as location, size, and color grayscale to construct a cost function for cross-frame target matching, which can accurately associate particulate organic carbon in different video frames, effectively improving the accuracy of target recognition and statistics. The obtained data such as quantity, shape, size, and spatial distribution can be directly used as the basis for carbon flux statistics. At the same time, it is equipped with local data recording and image frame calibration functions to facilitate subsequent playback and query, and ensure that the monitoring data is traceable and reusable.

[0052] A second aspect of this disclosure provides a carbon flux monitoring method, which is applied to the carbon flux monitoring system described in the above embodiments, such as... Figure 6 As shown, the method includes: Step 101: Collect the water sample to be tested using the water sample collector; Step 102: Optical imaging of the water sample to be tested is performed using the underwater microscopic imaging unit to obtain an initial image; the initial image is screened to obtain a target image containing particulate organic carbon; the target image is transmitted to the host computer. Step 103: The host computer determines the carbon flux statistics of particulate organic carbon based on the target image.

[0053] In another embodiment of this disclosure, optical imaging of the water sample to be tested to obtain an initial image includes: emitting a light source to illuminate the water sample to be tested; magnifying and converging the light on the illuminated water sample to obtain a front-end microscopic image; correcting and optimizing the front-end microscopic image to obtain a back-end optical image; and converting the back-end optical image into an electrical signal to obtain the initial image.

[0054] In another embodiment of this disclosure, the initial image is screened to obtain a target image containing particulate organic carbon, including: obtaining image noise parameters based on the initial image; determining block-level threshold parameters and frame-level threshold parameters based on the image noise parameters; detecting the initial image using the block-level threshold parameters and the frame-level threshold parameters respectively to obtain a first detection result and a second detection result; confirming whether particulate organic carbon exists in the initial image based on the first detection result and the second detection result; if particulate organic carbon exists, storing the initial image as a target image.

[0055] In another embodiment of this disclosure, determining carbon flux statistics of particulate organic carbon based on the target image includes: acquiring image background features; segmenting the target image based on the image background features to obtain a specific foreground target; extracting features from the specific foreground target to obtain a corresponding feature vector; and obtaining carbon flux statistics based on the feature vectors corresponding to adjacent video frames.

[0056] In another embodiment of this disclosure, carbon flux statistics are obtained based on feature vectors corresponding to adjacent video frames, including: constructing a cost function based on target location features, size features, and color grayscale features; obtaining particulate organic carbon quantity, single particle morphology and size, and spatial distribution information based on the cost function and feature vectors corresponding to adjacent video frames; and using particulate organic carbon quantity, single particle morphology and size, and spatial distribution information as the carbon flux statistics.

[0057] In another embodiment of this disclosure, segmenting the target image based on the image background features to obtain a specific foreground target includes: obtaining background grayscale distribution features based on the image background features; updating the image background features based on the background grayscale distribution features in conjunction with a learning rate; and segmenting the target image based on the updated image background features to obtain a specific foreground target.

[0058] In another embodiment of this disclosure, segmenting the target image based on updated image background features to obtain a specific foreground target includes: segmenting the target image based on updated image background features to obtain an initial foreground target; performing morphological optimization processing on the initial foreground target; inputting the optimized initial foreground target into a classification model for recognition and classification; and obtaining the specific foreground target output by the classification model.

[0059] According to embodiments of this disclosure, this disclosure also provides an electronic device and a readable storage medium.

[0060] Figure 7A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0061] like Figure 7 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0062] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0063] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as carbon flux monitoring methods. For example, in some embodiments, the carbon flux monitoring method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the carbon flux monitoring method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the carbon flux monitoring method by any other suitable means (e.g., by means of firmware).

[0064] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0065] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0066] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0067] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0068] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0069] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0070] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0071] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise explicitly specified.

[0072] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A carbon flux monitoring system, characterized in that, The system includes several water sample collectors, underwater microscopic imaging units, connecting cables, and a host computer; wherein, the several water sample collectors are arranged vertically and connected by the connecting cables; the underwater microscopic imaging units are staggered on the water sample collectors; The water sample collector is used to collect water samples to be tested; The underwater microscopic imaging unit is used to perform optical imaging on the water sample to be tested to obtain an initial image; to screen the initial image to obtain a target image containing particulate organic carbon; and to transmit the target image to the host computer. The host computer is used to determine the carbon flux statistics of particulate organic carbon based on the target image.

2. The system according to claim 1, characterized in that, The underwater microscopic imaging unit includes an illumination module and an optical imaging module. The optical imaging module includes an objective lens assembly, a rear lens assembly, and a CCD imaging assembly. The lighting module is used to emit a light source to illuminate the water sample to be tested; The objective lens assembly is used to magnify and converge light on the illuminated water sample to obtain a front-end microscopic image; The rear lens assembly is used to correct and optimize the front-end microscopic imaging to obtain the rear-end optical image; The CCD imaging component is used to convert the back-end optical image into an electrical signal to obtain an initial image.

3. The system according to claim 1, characterized in that, The underwater microscopic imaging unit also includes a circuit and a storage module, which are used for: Based on the initial image, image noise parameters are obtained; Based on the image noise parameters, determine the block-level threshold parameters and the frame-level threshold parameters; The initial image is detected using the block-level threshold parameter and the frame-level threshold parameter respectively, to obtain a first detection result and a second detection result; Based on the first detection result and the second detection result, it is confirmed whether particulate organic carbon exists in the initial image; If particulate organic carbon is present, the initial image is stored as the target image.

4. The system according to claim 1, characterized in that, The host computer is also used for: Obtain image background features; The target image is segmented based on the background features of the image to obtain a specific foreground target; Feature extraction is performed on the specific foreground target to obtain the corresponding feature vector; Carbon flux statistics are obtained based on the feature vectors corresponding to adjacent video frames.

5. The system according to claim 4, characterized in that, The host computer is also used for: A cost function is constructed based on the target's location features, size features, and color grayscale features. Based on the cost function and the feature vectors corresponding to adjacent video frames, the particle organic carbon quantity, single particle morphology and size and spatial distribution information are obtained. The quantity of particulate organic carbon, the morphological size of individual particles, and their spatial distribution information are used as the carbon flux statistics.

6. The system according to claim 4, characterized in that, The host computer is also used for: Based on the image background features, the background grayscale distribution features are obtained; The image background features are updated based on the background grayscale distribution features, taking into account the learning rate. The target image is segmented based on the updated image background features to obtain specific foreground targets.

7. The system according to claim 6, characterized in that, The host computer is also used for: The target image is segmented based on the updated image background features to obtain the initial foreground target; The initial foreground target is morphologically optimized, and the optimized initial foreground target is input into the classification model for recognition and classification. The specific foreground target output by the classification model is obtained.

8. A method for monitoring carbon flux, characterized in that, The method is applied to a carbon flux monitoring system, which includes several water sample collectors, an underwater microscopic imaging unit, connecting cables, and a host computer; wherein the several water sample collectors are arranged vertically and connected by the connecting cables; the underwater microscopic imaging units are alternately installed on the water sample collectors; the method includes: The water sampler collects the water sample to be tested. The underwater microscopic imaging unit performs optical imaging on the water sample to be tested to obtain an initial image; the initial image is screened to obtain a target image containing particulate organic carbon; the target image is transmitted to the host computer. The host computer determines the carbon flux statistics of particulate organic carbon based on the target image.

9. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of claim 8.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to claim 8.

Images