Moving target optical detection and identification system under large airspace coverage

Abstract

The invention provides a moving target optical detection and identification system under large airspace coverage, and belongs to the field of optical imaging and detection. According to the system, a large airspace is segmented in an optical detection array mode, each piece of optical detection equipment can cover part of the airspace with high imaging precision, the restrictive relation between airspace coverage and imaging precision is broken through, and large-airspace optical imaging for a tiny target is achieved; after spatial domain segmentation, the imaging frame rate is greatly improved on the premise of ensuring the imaging precision, and a solution is provided for high-precision optical detection of a moving target under large spatial domain coverage; through the optical domain transmission link, the requirements of high imaging frame rate and high capacity and high transmission rate can be met at the same time; and the detection and identification rear end realizes real-time processing and identification of each sub-airspace optical image of the front end. According to the invention, high-precision, high-frame-rate and high-transmission-rate imaging and identification of a tiny moving target under large-airspace coverage are realized, and the mutual restriction relationship in optical detection is broken through.

Description

Technical Field

[0001] The invention belongs to the field of optical imaging and detection, and relates to a moving target optical detection and recognition system under large airspace coverage. Background Art

[0002] Optical inspection can detect product surface information, measure product appearance dimensions without contact, determine target position, and identify target feature information. It is widely used in automated inspection, intelligent manufacturing, traffic monitoring, autonomous driving, logistics automation, medical imaging and other fields. There is a contradiction between the large airspace coverage requirement of optical inspection and high-precision imaging. On the one hand, scenes that cover a large enough airspace, such as traffic monitoring and autonomous driving, will not set centimeter-level imaging accuracy; on the other hand, scenes with high enough imaging accuracy, such as intelligent manufacturing and medical imaging, often only need to cover a part of the airspace around the target. For scenes that require both large airspace coverage and high imaging accuracy, current optical inspection equipment is difficult to take both into account. There is also a contradiction between the high imaging accuracy of optical inspection and the imaging frame rate. For some high-speed optical inspection scenes, such as bullet penetration, explosion effects, fluid collisions, etc., it is necessary to capture instantaneous material interactions continuously and quickly, so the imaging accuracy is low. To ensure imaging accuracy, it is necessary to compromise in airspace coverage. Industrial cameras are widely used optical inspection equipment. The highest pixel that can be achieved is 150 million, but the frame rate is only 6.2fps, which is completely unable to meet the real-time optical inspection of moving targets under large airspace coverage conditions. Even if the airspace coverage is reduced to ensure imaging accuracy with lower pixels, high imaging frame rates will generate a large amount of optical image data, which will double the pressure on data transmission. In optical inspection application scenarios, airspace coverage, imaging accuracy, imaging frame rate, and data transmission rate are mutually constrained, and it is necessary to balance and choose between the four indicators based on actual optical imaging needs. Summary of the invention

[0003] In order to solve the above problems in the prior art, the present invention provides an all-optical long-distance transmission moving target optical detection and recognition system under large spatial coverage, which can realize high-precision, high frame rate, and high transmission rate imaging and recognition of tiny moving targets under large spatial coverage, and break through the mutual constraints among spatial coverage, imaging accuracy, frame rate, and data transmission rate in optical detection.

[0004] In order to achieve the above technical objectives, the present invention adopts the following technical solutions:

[0005] A moving target optical detection and recognition system under large airspace coverage includes: a data acquisition front end, an optical domain transmission link, a detection and recognition back end, and a real-time display terminal; the data acquisition front end, the optical domain transmission link, and the detection and recognition back end are sequentially connected through a network cable and a network port that meet the data transmission rate requirements; the detection and recognition back end transmits images to the real-time display terminal through a display line;

[0006] The data acquisition front end is used to divide the large airspace including the moving target into a field of view, collect optical images of each sub-airspace, convert them into a transmission data format, and then send them;

[0007] The optical domain transmission link is used to transmit the optical image data of each sub-spatial domain obtained by the data acquisition front end in large capacity, high speed, long distance and low loss;

[0008] The detection and identification backend is used to receive the sub-spacespace optical image data, and use the optical image data of each sub-spacespace to detect whether there is a moving target in the large spacespace and identify the moving target;

[0009] The real-time display terminal is used to receive and display the optical images of each sub-space domain processed by the detection and recognition backend.

[0010] In some possible implementations, the data acquisition front end includes: a spatial coverage optical detection array and a data acquisition industrial computer;

[0011] The spatial coverage optical detection array includes a plurality of optical detection devices, which are used to divide the field of view of the large spatial area. Each optical detection device is responsible for collecting optical images of a part of the spatial area in the large spatial area, obtaining a plurality of sub-spatial area optical images, and converting the plurality of sub-spatial area optical images into a transmission format.

[0012] The data acquisition industrial control computers are provided in plurality and the number is the same as the number of optical detection devices in the airspace coverage optical detection array. The plurality of data acquisition industrial control computers are connected one by one with the plurality of optical detection devices through data acquisition lines, and are used to receive the optical image data of each sub-airspace converted into a transmission format and temporarily store it in the storage medium of the industrial control computer.

[0013] In some possible implementations, the optical domain transmission link includes: an optical network unit and an optical line terminal; the optical network unit transmits the sub-spatial domain optical image data to the optical line terminal through an optical fiber;

[0014] The optical network unit is provided in plurality and the number is the same as the number of the data acquisition industrial control computers, and is used to modulate the sub-spatial domain optical image data received by the data acquisition industrial control computers into the optical domain;

[0015] The optical line terminal is used to integrate and demodulate multi-channel optical domain signals.

[0016] In some possible implementations, the optical line terminal further includes: an optical port module and an electrical port module;

[0017] The optical port modules are provided in plurality and the number is the same as the number of the optical network units, and are used to be inserted into the optical line terminal interface to receive the optical image data of each sub-space domain;

[0018] The electrical port module is used to be inserted into the optical line terminal interface to send the demodulated optical image data of each sub-spatial domain.

[0019] In some possible implementations, the detection and identification backend includes an image processing server; the image processing server receives and stores optical image data of each sub-airspace, and is used to detect whether there are moving targets in a large airspace and to identify the moving targets.

[0020] The beneficial effects of the present invention are:

[0021] 1) The large airspace is divided by an optical detection array. Each optical detection device can cover part of the airspace with high imaging accuracy, breaking the restrictive relationship between airspace coverage and imaging accuracy. It can achieve large airspace optical imaging for tiny targets according to actual needs.

[0022] 2) After spatial segmentation, the imaging frame rate is greatly improved while ensuring imaging accuracy, providing a solution for high-precision optical detection of moving targets in large spatial coverage;

[0023] 3) Building a sub-spatial optical image data transmission channel through an optical domain transmission link can ensure high imaging frame rate requirements while taking into account large capacity and high transmission rate requirements;

[0024] 4) The detection and recognition backend can realize real-time processing and recognition of optical images in each sub-spatial domain of the front end, improve the recognition accuracy, effectively reduce the probability of false detection and missed detection, and suppress the amplification of noise and the loss of details while improving the brightness and contrast of the image, retaining the detail information, and thus realizing accurate and stable detection and recognition of the enhanced image;

[0025] 5) The real-time display terminal will present the real-time optical images of each sub-airspace and key information of tiny moving targets. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a schematic diagram of the structure of the optical detection and recognition system for moving targets with all-optical long-distance transmission under large airspace coverage of the present invention;

[0027] Figure 2 It is a schematic diagram of large spatial field of view segmentation and optical detection array arrangement according to an embodiment of the present invention;

[0028] Figure 3 This is a schematic diagram of the optical image data transmission link of each sub-spacespace under the large spacespace coverage according to an embodiment of the present invention;

[0029] Figure 4 The figure is a flowchart of a large airspace moving target detection and recognition algorithm according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The present invention is described in detail below in conjunction with the drawings and embodiments, wherein the drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0031] See also Figure 1 , Figure 1 The present invention is a schematic diagram of the structure of the all-optical long-distance transmission moving target optical detection and identification system under large airspace coverage, which discloses a moving target optical detection and identification system under large airspace coverage, including: a data acquisition front end, an optical domain transmission link, a detection and identification back end and a real-time display terminal; wherein the data acquisition front end, the optical domain transmission link, and the detection and identification back end are connected in sequence through a network cable and a network port that meet the data transmission rate requirements; the detection and identification back end transmits the picture to the real-time display terminal through the display line;

[0032] The data acquisition front end is used to divide the large airspace including the moving target into a field of view, collect optical images of each sub-airspace, convert them into a transmission data format, and then send them;

[0033] The optical domain transmission link is used for transmitting the optical image data of each sub-spatial domain collected by the data collection front end in a large capacity, high speed, long distance and low loss manner;

[0034] The detection and identification backend is used to receive the optical image data of each sub-spacespace, and use the received optical image data of each sub-spacespace to detect whether there is a moving target in the large spacespace and identify the moving target;

[0035] The real-time display terminal is used to receive and display the optical images of each sub-space domain processed by the detection and recognition backend.

[0036] In the above embodiment, the large airspace range is 12.0 m long × 11.3 m wide × 1.0 m high, and the tiny moving target falls vertically into the airspace range at a maximum speed of 20 m / s, and its minimum size is 5 mm.

[0037] The data acquisition front end includes an optical detection array covering the airspace and an industrial computer for data acquisition. Among them, the optical detection array equipment uses the Hikvision MV-CH210-90YM / YC industrial camera, which has a resolution of 5120×4096 and a frame rate of 222fps. The design field of view range is 3.5m×2.8m, which corresponds to the resolution of the industrial camera 5120×4096, and the imaging accuracy can reach 0.68mm / pix. With the Hikvision MVL-AF3528M-M42 lens, its focal length is 35mm, and a working distance of 5.3m is achieved. The viewing angle corresponding to the long side of the field of view of 3.5m is 36.44°, and the viewing angle corresponding to the short side of the field of view of 2.8m is 29.50°. With the Hikvision MVL-AF5040M-M42 lens, its focal length is 50mm, and a working distance of 7.4m is achieved. The viewing angle corresponding to the long side of the field of view of 3.5m is 25.95°, and the viewing angle corresponding to the short side of the field of view of 2.8m is 20.88°. The same model of industrial camera is matched with two focal length lenses to realize the layered layout of the optical detection array. The 10 industrial cameras on the upper layer are arranged opposite to each other 5 meters above the large airspace, and the installation positions of the 10 industrial cameras on the lower layer correspond to the industrial cameras on the upper layer. The distance between the two layers of cameras is 1 meter. For the schematic diagram of the large airspace field of view segmentation and optical detection array layout, please refer to Figure 2 .

[0038] The sub-spacespace optical image data is transmitted between the industrial camera and the acquisition card via a CoaXPress line. Each industrial camera is equipped with a data acquisition card, and each data acquisition card needs to be equipped with a data acquisition industrial computer to temporarily store the sub-spacespace optical image data.

[0039] See also Figure 3 , Figure 3 It is a schematic diagram of the optical image data transmission link of each sub-airspace under the large airspace coverage of this embodiment. The optical domain transmission link includes several optical network units and optical line terminals; the sub-airspace optical image data is transmitted through the Category 5e or Category 6 network cable between the data acquisition industrial computer and the optical network unit. The sub-airspace optical image data is transmitted at 24fps per second. According to the resolution of the industrial camera, it can be calculated that the transmission rate of a single data transmission channel needs to reach 480Mbps. Therefore, each data acquisition industrial computer and optical network unit needs to be equipped with a Gigabit network port.

[0040] The optical line terminal also includes an optical port module and an electrical port module; the optical network unit, optical port module, optical line terminal, and 10G electrical port module can be TP-LINK products, and the models are TL-NGP650-S2-4G, TL-SM610-OLT64, TL-NOLT800-16-24T2Q, and TL-SM510U, respectively. After the sub-airspace optical image data of 20 channels are integrated, the data volume per second is as high as 9.6GB, and the maximum transmission rate of 10Gbps just meets the needs of real-time transmission of each sub-airspace optical image data to the image processing server in the detection and identification backend. At the same time, the image processing server needs to have a 10G network port, and the optical line terminal and the image processing server must be connected through a Category 6 network cable to achieve the maximum transmission rate indicator of 10Gbps.

[0041] See also Figure 4 , the optical image data of each sub-spatial domain from the data acquisition front end is stored in the storage medium of the image processing server through the optical domain transmission link, which is used to detect whether there is a moving target in the large airspace with changing illumination conditions, and to identify the moving target. The sub-spatial domain optical image under the condition of exceeding the normal illumination is used as the reference illumination image. The specific implementation method is as follows:

[0042] S1: annotating and preprocessing the sub-spatial domain optical image and the corresponding reference illumination image to obtain a small target data set;

[0043] S2: construct a multi-scale enhancement model, and use the sub-spatial domain optical images and the corresponding reference illumination images in the small target data set to train the multi-scale enhancement model to obtain an MSEM model; through the constructed MSEM model, the enhancement of each sub-spatial domain optical image is completed, which helps to better retain and transmit multi-scale feature information, complete the fusion of deep-level features, and capture more detailed features; by optimizing the network architecture of the MSEM model to reduce redundancy and improve computational efficiency, the network is made lighter and easier to train, and recognition in complex environments can be achieved;

[0044] S3: Construct a small target semantic segmentation model, use the sub-spatial domain optical image enhanced by the MSEM model and the label map in the small target data set to train the small target semantic segmentation model, obtain a DR-UNet model, and realize the segmentation and recognition of the enhanced image; through the constructed DR-UNet model, embed the channel space attention mechanism in the backbone network to enhance the model's perception of small targets; the structure of the network model is more in-depth, and its feature extraction and expression capabilities are improved, which can make the model better adapt to image segmentation tasks of different scales and complexities, improve the generalization ability of the model, and optimize the network structure and performance;

[0045] S4: Perform contour detection on the segmented image to extract target edge features of the segmented image;

[0046] S5: locating the center of the target based on the target edge features to obtain the position of the small target.

[0047] In step S2, the multi-scale enhancement model includes a decomposition module and an enhancement module;

[0048] The decomposition module includes three submodules: shallow feature extraction, activation layer sequence and final reconstruction layer; the shallow feature extraction submodule includes a convolution layer, the number of channels of the convolution layer is 64, the size of the convolution kernel is 3, and is used to perform preliminary feature extraction on the input sub-spatial domain optical image and the corresponding reference illumination image; the activation sequence layer submodule performs deep feature extraction on the initially extracted feature information, which is connected in sequence through five convolution blocks composed of convolution layers and Leaky-ReLu activation functions, wherein the number of channels of the convolution layer is 64, and the size of the convolution kernel is 3; the final reconstruction layer submodule remaps the feature map extracted by the activation sequence layer submodule back to the original image space to generate a reconstructed image or feature map, and the final reconstruction layer submodule includes a convolution layer and a sigmoid function, wherein the convolution layer converts the feature map output by the activation sequence layer submodule from 64 channels back to 4 channels, and the sigmoid function maps the output to the interval of 0-1, and the feature map is divided into a reflection component and an illumination component;

[0049] The enhancement module includes three submodules: feature extraction, multi-scale feature fusion and output generation; the feature extraction submodule includes a convolution layer and three deep feature extraction layers; the convolution layer has 64 channels and a convolution kernel size of 3, receives reflection component and illumination component as input, and concatenates them along the channel dimension. Through this layer, the network can capture the basic texture and edge information in the input image and complete the preliminary extraction of feature information; the output of the convolution layer is used as the input of the first deep feature extraction layer, and is downsampled through a convolution operation with a step size of 2 to reduce the spatial resolution of the feature map and increase its receptive field; the second deep feature extraction layer receives the output of the first deep feature extraction layer as input, and again passes through a Downsampling is performed with a convolution operation with a step size of 2. Compared with the first layer, this layer can capture more abstract and higher-level feature information; the third deep feature extraction layer receives the output of the second deep feature extraction layer as input, and downsamples through the third convolution operation with a step size of 2. Through this layer, the network can further extract and refine feature information, providing strong support for the final enhancement effect; the multi-scale feature fusion submodule restores the output of each deep feature extraction layer to the spatial resolution of the previous layer through an upsampling operation, and splices it with the output of the previous layer along the channel dimension to complete the fusion of features of different scales and levels; the output generation submodule outputs the fused feature map as an enhanced illumination component.

[0050] The reflection component and the enhanced illumination component are reconstructed, and the specific method is: the reflection component and the enhanced illumination component are multiplied and fused element by element to generate an enhanced target image.

[0051] In step S2, during the training of the multi-scale enhancement model, each training batch randomly extracts a pair of sub-spatial domain optical images and reference illumination images; the loss is calculated by forward propagation of the model, and the optimizer is used to backpropagate the loss and update the model parameters; at the end of every 5 epochs, the model performance is evaluated and the best model is recorded.

[0052] In step S3, the small object semantic segmentation model includes a backbone network DCSR and a feature fusion layer;

[0053] The backbone network DCSR includes an input layer, a convolution layer and a layer composed of multiple basic building blocks (CSResidual block); the input of the input layer is the enhanced sub-spatial domain optical image and the label map in the small target data set; the convolution layer performs preliminary feature extraction on the input image; the layer composed of multiple basic building blocks includes four layers, wherein layer1 includes 3 basic building blocks, layer2 includes 4 basic building blocks, layer3 includes 6 basic building blocks, layer4 includes 3 basic building blocks and a void space pyramid pooling module; each basic building block is composed of two DC modules connected in sequence, and the DC module includes a convolution layer, a batch normalization layer and a Leaky-ReLu activation function connected in sequence, and the batch normalization in the second DC module The channel attention module and the spatial attention module are inserted between the normalization layer and the Leaky-ReLu activation function in sequence, thereby improving the network's ability to capture important information in the image; in the DC module, the convolution layer is used to extract image features, and the convolution kernel is applied to each input channel to generate the same number of channels, and then these channels are stacked according to the channel dimension, and a new feature map is generated by combining the generated multi-channel feature maps for point-by-point convolution, and the information of different channels is weighted and combined to output the feature map; the batch normalization layer normalizes each channel of the output feature map so that the output data has a stable distribution; the Leaky-ReLu activation function maps the normalized feature map to the new space to generate the final feature map. The atrous spatial pyramid pooling module processes the output feature information of layer3 through four atrous convolution layers to obtain four feature maps of different scales; then it is processed by the global average pooling branch to obtain the global context feature map; it is restored to the size of the original input feature map by upsampling, and the feature maps of four different scales and the global context feature map are spliced ​​in the channel dimension to obtain the spliced ​​feature map.

[0054] The feature fusion layer adopts a dense connection mechanism. In each module of the overall network framework, the outputs of all previous modules are spliced ​​and input into the basic building blocks of the backbone network DCSR contained in the current layer, and then transmitted to the next layer.

[0055] The specific implementation method of the dense connection mechanism adopted by the feature fusion layer is as follows: when building the overall network framework of the small target semantic segmentation model, the input image is first sent to the backbone network DCSR, and then the initial feature extraction module X is used to extract the image. 0_0 Convolution operation is performed to extract basic feature information from the image; then, the extracted preliminary features are sent to a series of deep feature extraction modules X 1_0 , X 2_0 , X 3_0 , X4_0 The above five modules constitute the backbone network DCSR, which gradually mines the deep feature information in the image by downsampling the features and further extracting the features; with the increase of the number of layers, the depth of feature extraction gradually deepens, so that more complex and subtle image features can be captured; module X 1_0 The output is upsampled with X 0_0 The outputs are concatenated in the channel dimension and fed into module X 0_1 , the module X 0_1 It contains a basic building block of the backbone network DCSR, which completes the fusion and output of feature information of different scales, and enhances the model's ability to capture detailed features; other layers also complete the above operations in sequence, and after splicing with the output of each previous layer, they are jointly input into the basic building block of the backbone network DCSR contained in each layer, and continue to be transmitted to the next layer; finally, the dense connection of the entire network is completed, so that each layer in the network is connected to all previous layers to obtain richer feature information.

[0056] In step S3, when training the small object semantic segmentation model, the loss function adopts a loss function combining Diceloss and Focalloss to better deal with the problems of category imbalance and pixel level imbalance; the loss function is:

[0057] Loss=βDice·DiceLoss+(1-βDice)·FocalLoss (1)

[0058] Among them, βDice is a hyperparameter used to adjust the weight between Diceloss and Focalloss loss functions;

[0059] The Diceloss loss function is calculated based on the Dice coefficient. The calculation formulas of the Dice coefficient and DiceLoss are as follows:

[0060]

[0061] Where X represents the predicted output image obtained by inputting the sub-spatial domain optical image into the small target semantic segmentation model, Y represents the real label segmentation result, |X∩Y| represents the number of intersection elements between X and Y, and |X| and |Y| represent the number of elements in X and Y respectively;

[0062] The FocalLoss loss function reduces the loss weight of easy-to-classify samples and increases the loss weight of difficult-to-classify samples, so that the model can pay more attention to difficult-to-classify samples (such as small targets); the formula of the FocalLoss loss function is as follows:

[0063] FocalLoss = -a(1-p)λ log(p) (4)

[0064] Among them, p is the probability that the small object semantic segmentation model predicts the correct category; α is a sample weight used to adjust the weights of easy-to-classify samples and difficult-to-classify samples, which is usually the inverse of the category frequency; λ represents the difficult-to-classify sample weight, which is used to weigh the difficult-to-classify samples and easy-to-classify samples.

[0065] In step S4, edge detection mainly includes multiple links such as noise reduction filtering, calculation of gradient amplitude and direction, non-maximum suppression and hysteresis threshold processing. First, in the Gaussian filtering stage, the traditional Canny algorithm uses a Gaussian function to smooth the image to reduce the impact of noise on edge detection. However, while removing noise, Gaussian filtering may also cause some important edge information in the image to be blurred or lost. Considering the image recognition for small targets, the blurring of edge information may greatly affect the final positioning and tracking problems. Therefore, this embodiment uses bilateral filtering instead of Gaussian filtering to pre-process the image to eliminate noise interference and better preserve the edge information of the target. The Canny operator is selected to perform contour detection on the segmented image, the Sobel operator is used to calculate the gradient amplitude and gradient, the image edge is finely extracted by the first-order differential operator, and then the non-maximum suppression operation is performed using the gradient information to ensure that only the local maximum at the edge is retained. In the application of the first-order differential operator, the horizontal and vertical directions are particularly selected to effectively extract edge features. Finally, the threshold is selected according to actual needs using an adaptive threshold method, and the processed image is edge connected to obtain a complete and accurate edge detection result, effectively suppressing false edges and noise edges, significantly improving the performance of edge detection to ensure positioning accuracy.

[0066] In step S5, when obtaining the coordinates of the target center point, the target is regarded as a two-dimensional object with uniform density, and then the center point position is determined by finding its center of gravity. In a two-dimensional image, the center of gravity of the target body is the average position of all the pixels, which can also be called the center of mass or the centroid. The method of calculating the spatial moment is used to locate the center of gravity of the contour; in order to ensure the stability of the positioning result and make the center positioning coordinates more accurate, the Kalman filter method is used to further smooth and denoise and dynamically adjust the weights to ensure the accuracy of the center positioning coordinates.

[0067] The image processed by the detection and recognition backend is transmitted to the display terminal through the display line to form a real-time optical picture covering a large airspace and a moving target.

[0068] The above-described embodiments are all preferred implementations of the present invention, and do not limit the present invention in other forms. Any technician familiar with the profession may use the above content to make changes or follow suit. However, any changes made to the above embodiments based on the essence of the method of the present invention without departing from the content of the scheme in the present invention still fall within the scope of protection of the present invention.

Claims

1. A moving target optical detection and recognition system with large airspace coverage, characterized in that: It includes a data acquisition front end, an optical domain transmission link, a detection and identification back end and a real-time display terminal; the data acquisition front end, the optical domain transmission link, and the detection and identification back end are connected in sequence through a network cable and a network port that meet the data transmission rate requirements; the detection and identification back end transmits the picture to the real-time display terminal through a display line; The data acquisition front end is used to divide the large airspace including the moving target into a field of view, collect optical images of each sub-airspace, convert them into a transmission data format, and then send them; The optical domain transmission link is used to transmit the optical image data of each sub-spatial domain obtained by the data acquisition front end; The detection and identification backend is used to receive the sub-spacespace optical image data, and use the optical image data of each sub-spacespace to detect whether there is a moving target in the large spacespace and identify the moving target; The real-time display terminal is used to receive and display the optical images of each sub-space domain processed by the detection and recognition backend.

2. The moving target optical detection and recognition system under large airspace coverage according to claim 1 is characterized in that: The data acquisition front end includes a spatial coverage optical detection array and a data acquisition industrial computer; The spatial coverage optical detection array includes a plurality of optical detection devices, each of which is responsible for collecting optical images of a portion of a large spatial domain, obtaining a plurality of sub-spatial domain optical images, and converting the sub-spatial domain optical images into a transmission format; There are multiple data acquisition industrial computers and the number is the same as the number of optical detection devices. The multiple data acquisition industrial computers are connected to multiple optical detection devices one by one through data acquisition lines, and are used to receive the optical image data of each sub-spatial domain converted into a transmission format and temporarily store it in the storage medium of the industrial computer.

3. The moving target optical detection and recognition system under large airspace coverage according to claim 2 is characterized in that: The optical domain transmission link includes an optical network unit and an optical line terminal; The optical network unit transmits the sub-spatial domain optical image data to the optical line terminal via an optical fiber; The optical network unit is provided in plurality and the number is the same as the number of the data acquisition industrial control computers, and is used to modulate the sub-spatial domain optical image data received by the data acquisition industrial control computers into the optical domain; The optical line terminal is used to integrate and demodulate the optical domain signals of a plurality of the optical network units.

4. The moving target optical detection and recognition system under large airspace coverage according to claim 3 is characterized in that: The optical line terminal also includes an optical port module and an electrical port module; The optical port modules are provided in plurality and the number is the same as the number of the optical network units, and are used to be inserted into the optical line terminal interface to receive the optical image data of each sub-space domain; The electrical port module is used to be inserted into the optical line terminal interface to send the demodulated optical image data of each sub-spatial domain.

5. A moving target optical detection and recognition system under large airspace coverage according to any one of claims 1 to 4, characterized in that: The detection and identification backend includes an image processing server; the image processing server receives and stores optical image data of each sub-airspace, and is used to detect whether there is a moving target in a large airspace and identify the moving target.

Images