Ultra-fast All-optical Intelligent Sensing and Computing Chip System and Architecture

Abstract

The present disclosure relates to the field of optical computing technologies, and particularly to an ultrafast all-optical intelligent sensing and computing chip system and architecture. The system includes an all-optical parallel computing array chip and a demultiplexing device. The chip includes a plurality of microlenses, a plurality of resonator rings, and a bus waveguide. The microlenses are configured to obtain natural light of a first image in a target area where the microlenses are located; the plurality of resonator rings are connected to the plurality of microlens arrays, configured to obtain the light focused by the corresponding microlenses, and perform coherent combination with the light propagating in the bus waveguide to modulate the light propagating in the bus waveguide and obtain a first modulation result; the bus waveguide serially connects the plurality of resonator rings, configured to obtain incident light and propagate the incident light in the plurality of resonator rings, and combine the first modulation results to obtain an output light result; the demultiplexing device is connected to the all-optical parallel computing array chip, configured to determine a classification result of the first image based on the output light result. The present disclosure realizes parallel processing of multiple features and improves the image recognition efficiency.

Description

Technical Field

[0001] The present disclosure relates to the field of optical computing technology, and in particular, to an ultrafast all-optical intelligent sensing and computing chip system and architecture. Background Art

[0002] With the rapid development of the fields of artificial intelligence and scientific computing, the complexity and scale of computing requirements are also continuously increasing. However, the performance of existing electronic circuits has tended to saturate, limiting the potential for significantly improving signal processing speed and energy efficiency. Light has the advantages of high throughput and low latency during propagation. Based on this, performing image processing in parallel in the optical domain is regarded as the key to breaking through the bottleneck of existing electronic circuits. Summary of the Invention

[0003] The present disclosure aims to at least partly solve one of the technical problems in the related art.

[0004] To this end, the first object of the present disclosure is to propose an ultrafast all-optical intelligent sensing and computing chip system.

[0005] The second object of the present disclosure is to propose an image classification method for an ultrafast all-optical intelligent sensing and computing chip system.

[0006] To achieve the above object, an embodiment of the first aspect of the present disclosure proposes an ultrafast all-optical intelligent sensing and computing chip system, the system includes an all-optical parallel computing array chip and a demultiplexing device, the chip includes a plurality of microlenses, a plurality of resonant rings and a bus waveguide, wherein,

[0007] The microlens is configured to obtain natural light of a first image in a target area where the microlens is located;

[0008] The plurality of resonant rings are connected to the plurality of microlens arrays, configured to obtain the light focused by the corresponding microlenses, and perform coherent combination with the light propagating in the bus waveguide, so as to modulate the light propagating in the bus waveguide to obtain a first modulation result;

[0009] The bus waveguide connects the plurality of resonant rings in series, configured to obtain incident light and propagate the incident light in the plurality of resonant rings, and combine the first modulation results to obtain an output light result;

[0010] The demultiplexing device is connected to the all-optical parallel computing array chip, configured to determine a classification result of the first image based on the output light result.

[0011] Optionally, the plurality of microlenses are distributed in an array, and each microlens has a corresponding resonant ring.

[0012] Optionally, the resonant ring is a high-Q all-pass resonant ring; the obtaining of the light focused by the corresponding microlens and the modulation of the light propagating in the bus waveguide to obtain a first modulation result includes:

[0013] Obtain the light focused by the corresponding microlens, and the focused light is absorbed by the resonant ring silicon waveguide to generate photo-generated carriers;

[0014] Based on the high Q value of the resonant ring and the refractive index of the photo-generated carriers, perform phase and / or amplitude modulation on the light propagating in the bus waveguide to obtain a first modulation result.

[0015] Optionally, the multiple resonant rings are divided into different groups, and different groups of resonant rings correspond to different wavelengths of the light in the bus waveguide.

[0016] Optionally, the obtaining of the incident light, propagating the incident light in the multiple resonant rings, and obtaining an output light result based on the first modulation result includes:

[0017] Obtain the incident light and propagate the incident light in the multiple resonant rings to obtain a first modulation result for each resonant ring;

[0018] Based on the coherent combination of the incident light in the bus waveguide, obtain a second modulation result for each group of resonant rings;

[0019] Based on the second modulation result of each group of resonant rings, obtain an output light result.

[0020] Optionally, the determining of the classification result of the first image based on the output light result includes:

[0021] Based on the information intensity under different wavelength components in the output light result, determine the classification result of the first image. Optionally, the system further includes an optical renderer, which is connected to the all-optical parallel computing array chip through an optical fiber, and is used to obtain the output light result and perform all-optical reconstruction based on the output light result to obtain a second image in the target area.

[0022] Optionally, the optical renderer includes a blazed grating and a diffraction module; the performing of all-optical reconstruction based on the output light result to obtain a second image in the target area includes:

[0023] Reflect the light with different wavelengths in the output light result to different spatial positions through the blazed grating;

[0024] The diffraction module diffracts the light at different spatial positions by using a phase mask to obtain a second image in the target area.

[0025] To achieve the above object, an embodiment of the second aspect of the present disclosure provides an image classification method using the ultrafast all-optical intelligent sensing and computing chip system described in the first aspect, including:

[0026] Obtain the natural light and incident light of the first image in the target area;

[0027] Input the natural light and the incident light into the ultrafast all-optical intelligent sensing and computing chip to obtain an output light result;

[0028] Input the output light result into a demultiplexing device to obtain the classification result of the first image.

[0029] Optionally, the method further includes:

[0030] Input the output light result into an optical renderer through an optical fiber to obtain a second image in the target area.

[0031] Another object of the present invention is to provide an electronic device, including:

[0032] At least one processor; and

[0033] A memory communicatively connected to the at least one processor; wherein,

[0034] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the methods described in the foregoing two aspects.

[0035] Another object of the present invention is to provide a computer storage medium, wherein the computer storage medium stores computer-executable instructions; the computer-executable instructions, when executed by a processor, cause the computer to execute the methods described in the foregoing two aspects.

[0036] In summary, the ultrafast all-optical intelligent sensing and computing chip system and architecture provided by the present disclosure process spatial intensity images through an all-optical parallel computing array chip and a demultiplexing device, make full use of coherence and interference effects, and achieve parallel processing of multiple features, thereby improving the image recognition efficiency. At the same time, the ultrafast all-optical intelligent sensing and computing chip system can be applied to fields such as edge computing and intelligent robots, demonstrating the wide applicability of the ultrafast all-optical intelligent sensing and computing chip in modern technologies.

[0037] Additional aspects and advantages of the present disclosure will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and / or additional aspects and advantages of the present disclosure will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, wherein:

[0039] Figure 1 A structural schematic diagram of an ultra-fast all-optical intelligent sensing and computing chip system provided by an embodiment of the present disclosure;

[0040] Figure 2 A structural schematic diagram of an ultra-fast all-optical intelligent sensing and computing chip architecture provided by an embodiment of the present disclosure;

[0041] Figure 3 A flowchart of a computing method for an ultra-fast all-optical intelligent sensing and computing chip system provided by an embodiment of the present disclosure. Detailed implementation manners

[0042] The embodiments of the present disclosure will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present disclosure and should not be construed as limiting the present disclosure.

[0043] With the wide deployment of sensing and computing modules at the edge of the Internet, image processing, transmission, and reconstruction have become increasingly important. Optics plays a key role in the fields of imaging, communication, and display, while digital CMOS electronics dominates the field of image sensing and processing. The separate development of optics and electronics has successfully increased their respective transmission bandwidths and processing speeds. However, the frame rate and energy efficiency of operations such as spatial image processing, transmission, and reconstruction have approached their limits. The above challenges mainly come from two aspects: (1) The performance of electronic circuits is gradually saturated, limiting the potential for significantly improving signal processing speed and energy efficiency; (2) Image operations require frequent serial conversions between the electronic domain and the optical domain during image sensing and transmission, resulting in a large amount of energy consumption and restricting the frame rate of the above operations.

[0044] Among them, image processing can be performed in parallel in the optical domain to alleviate the bottleneck problem of integrated electronic circuits. In the prior art, a spatial optical modulation element can be used to preprocess an image and input it into an electronic system for post-processing. However, existing photonic computing methods cannot directly process spatial intensity images.

[0045] In addition, intelligent sensors can be developed to transfer part of the digital operations to the sensor or near it. Instead of extracting the original image pixels, only the valid data therein is read, including spatial image features and temporal dynamics, which reduces the bandwidth pressure between sensing and computing. Among them, the above-mentioned sensor does not need to read out the original pixels. However, since current cannot achieve multiplexing, based on this, the output still needs to be read out sequentially, which limits the increase in the sensing and processing frame rates. Moreover, the transmission and reconstruction operations require EO (electrical / optical) / OE (optical / electrical) and DA (digital / analog) / AD (analog / digital) conversions, and the above conversions are limited by the current saturation of the development of electronic circuits.

[0046] In the prior art, all-optical computing modes have the potential to solve the inherent bandwidth limitations in optoelectronic hybrid processing, transmission, and reconstruction. However, in the above prior art, intensity image recording and image processing are separated. Although the effectiveness of optical computing has been proven, directly processing optical intensity inputs is still challenging.

[0047] The present disclosure will be described in detail below with reference to specific embodiments.

[0048] Figure 1 The following is a schematic structural diagram of an ultrafast all-optical intelligent sensing and computing chip system provided by an embodiment of the present disclosure. As Figure 1 shown, the ultrafast all-optical intelligent sensing and computing chip system includes an all-optical parallel computing array chip (OPCA chip) and a demultiplexing device. The all-optical parallel computing array chip includes a plurality of microlenses, a plurality of resonant rings, and a bus waveguide. Among them,

[0049] The microlenses are used to obtain natural light of a first image in a target area where the microlenses are located;

[0050] The plurality of resonant rings are connected to the plurality of microlens arrays, and are used to obtain the light focused by the corresponding microlenses and coherently combine the light propagating in the bus waveguide to modulate the light propagating in the bus waveguide to obtain a first modulation result;

[0051] The bus waveguide serially connects the plurality of resonant rings, and is used to obtain incident light and propagate the incident light in the plurality of resonant rings, and combine the first modulation result to obtain an output light result;

[0052] The demultiplexing device is connected to the all-optical parallel computing array chip, and is used to determine a classification result of the first image based on the output light result.

[0053] In one embodiment of the present disclosure, each of the above-mentioned microlenses includes a matching period and a numerical aperture (N.A.), and a plurality of microlenses are distributed in an array (e.g., 8×8), and each microlens has a corresponding resonant ring. Among them, the microlens array confines the input natural light field to the sensing area of the resonant ring, and the object is imaged onto the resonant ring array, so that the light in the target area passes through the corresponding microlens and is focused onto the resonant ring.

[0054] Among them, in one embodiment of the present disclosure, the above-mentioned resonant ring is a high-Q all-pass resonant ring, and a plurality of resonant rings are divided into different groups, and different groups of resonant rings correspond to different wavelengths of light in the bus waveguide. In one embodiment of the present disclosure, the method for obtaining the light focused by the corresponding microlens and modulating it with the light propagating in the bus waveguide to obtain the first modulation result may include: obtaining the light focused by the corresponding microlens, and the focused light is absorbed by the resonant ring silicon waveguide to generate photo-generated carriers, and based on the high Q value of the resonant ring and the refractive index of the photo-generated carriers, the light propagating in the bus waveguide is phase and / or amplitude modulated to obtain the first modulation result.

[0055] Specifically, in one embodiment of the present disclosure, based on the high Q value of the resonant ring, the refractive index change caused by the carriers is amplified, so as to phase and / or amplitude modulate the light propagating in the bus waveguide, and different resonators are biased to different resonant wavelengths.

[0056] And, in one embodiment of the present disclosure, the method for obtaining the incident light, propagating the incident light in a plurality of resonant rings, and obtaining the output light result based on the first modulation result may include the following steps:

[0057] Step 1, obtain the incident light and propagate the incident light in a plurality of resonant rings to obtain the first modulation result of each resonant ring;

[0058] Step 2, based on the coherent combination of the incident light in the bus waveguide, obtain the second modulation result of each group of resonant rings;

[0059] Step 3, based on the second modulation result of each group of resonant rings, obtain the output light result.

[0060] Specifically, in an embodiment of the present disclosure, it is assumed that a group of resonant rings processes wavelength 1, and the group of resonant rings includes resonant ring 1 and resonant ring 2. Among them, when resonant ring 1 receives ambient light with an intensity of 1, it modulates wavelength 1 by π, and when resonant ring 2 receives ambient light with an intensity of 1, it modulates wavelength 1 by -π. Then, the phase of the wavelength 1 light in the bus waveguide passing through resonant ring 1 and resonant ring 2 remains unchanged; when resonant ring 1 receives ambient light with an intensity of 1, it modulates wavelength 1 by π, and when resonant ring 2 receives ambient light with an intensity of 0, it modulates wavelength 1 by 0. Then, the phase of the wavelength 1 light in the bus waveguide passing through resonant ring 1 and resonant ring 2 changes by π after passing through the two resonant rings. Based on this, the phase value of wavelength 1 in the bus waveguide can reflect the difference value of the ambient light intensities received by resonant ring 1 and resonant ring 2.

[0061] Further, in an embodiment of the present disclosure, the above demultiplexing device can be connected to the all-optical parallel computing array chip through an optical fiber, and is used to determine the classification result of the first image based on the output optical result. Among them, in an embodiment of the present disclosure, the method for determining the classification result of the first image based on the output optical result may include: determining the classification result of the first image based on the information intensity under different wavelength components in the output optical result.

[0062] Among them, in an embodiment of the present disclosure, the above demultiplexing device can disperse lights of different wavelengths, so that the classification result of the first image can be obtained according to the characteristics of the wavelengths. Exemplarily, in an embodiment of the present disclosure, it is assumed that wavelength 1 corresponds to image H. Then, when the amplitude of wavelength 1 in the output optical result is the largest, the classification result of the first image corresponding to the output optical result is image H.

[0063] Moreover, in an embodiment of the present disclosure, the above system may further include an optical renderer, which can be connected to the all-optical parallel computing array chip through an optical fiber, and is used to obtain the output optical result and perform all-optical reconstruction based on the output optical result to obtain a second image in the target area, so as to realize the remote transmission and restoration of the optical image. Among them, in an embodiment of the present disclosure, the above optical renderer includes a blazed grating and a diffraction module, and among them, the blazed grating is paired and designed with a plurality of resonant rings and a plurality of microlens arrays.

[0064] Specifically, in an embodiment of the present disclosure, the method for performing all-optical reconstruction based on the output optical result to obtain a second image in the target area may include the following steps:

[0065] Step a: Reflect lights of different wavelengths in the output optical result to spatial positions through the blazed grating;

[0066] Step b: The diffraction module diffracts different phase masks in the spatial position to obtain a second image in the target area.

[0067] Among them, in an embodiment of the present disclosure, the second image is the same as the first image. Based on this, the output light result can be transmitted to the far field in real time and calculated and reconstructed through a co-designed optical renderer without serial reading through an electronic camera, so that the frame rate of imaging and image processing will not be restricted.

[0068] It should be noted that, in an embodiment of the present disclosure, the response time of the above-mentioned ultrafast all-optical intelligent sensing and computing chip can reach 6 nanoseconds, and the optical bandwidth is 160 nanometers (from 1480 nanometers to 1640 nanometers), thereby significantly improving the energy efficiency and computing speed of image processing. At the same time, the above solutions are all completed in the optical domain, so they can be applied to fields such as edge computing and intelligent robots, demonstrating the wide applicability of the ultrafast all-optical intelligent sensing and computing chip in modern technologies.

[0069] In summary, the ultrafast all-optical intelligent sensing and computing chip system provided in this embodiment processes the spatial intensity image through an all-optical parallel computing array chip and a demultiplexing device, makes full use of coherence and interference effects, and realizes parallel processing of multiple features, thereby improving the image recognition efficiency. At the same time, the ultrafast all-optical intelligent sensing and computing chip system can be applied to fields such as edge computing and intelligent robots, demonstrating the wide applicability of the ultrafast all-optical intelligent sensing and computing chip in modern technologies.

[0070] Figure 2 This is the architecture of the ultrafast all-optical intelligent sensing and computing chip of the present invention. As Figure 2 shown, this architecture is composed of cascaded multi-layer ultrafast all-optical intelligent sensing and computing chips. Each part in the chip is reverse-designed driven by an intelligent task target, so it can ensure optimal image processing performance.

[0071] To implement the above embodiment, Figure 3 The present disclosure also proposes an image classification method applying the ultrafast all-optical intelligent sensing and computing chip system. As Figure 3 shown, this method may include the following steps:

[0072] Step 301: Obtain the natural light and incident light of the first image in the target area;

[0073] Step 302: Input the natural light and incident light into the ultrafast all-optical intelligent sensing and computing chip to obtain an output light result;

[0074] Step 303: Input the output light result into the demultiplexing device to obtain the classification result of the first image.

[0075] Wherein, in one embodiment of the present disclosure, the above method may further include: inputting the output optical result into an optical renderer through an optical fiber to obtain a second image in the target area.

[0076] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the present disclosure all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0077] It should be noted that personal information from users should be collected for legal and reasonable purposes and should not be shared or sold outside of these legal uses. In addition, such collection / sharing should be carried out after obtaining the informed consent of the user, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization including authorizing relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0078] The present disclosure anticipates providing embodiments in which users can selectively block the use or access of personal information data. That is, the present disclosure anticipates providing hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, the risk can be minimized by restricting data collection and deleting data. In addition, when applicable, personal identifiers are removed from such personal information to protect the privacy of users.

[0079] In the technical solution of the present disclosure, the acquisition, transmission, storage, use, processing, etc. of data all comply with the relevant provisions of national laws and regulations.

[0080] It should be noted that in the embodiments of the present disclosure, certain industry-existing solutions such as software, components, models, etc. may be mentioned. They should be considered exemplary, and their purpose is only to illustrate the feasibility in the implementation of the technical solution of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0081] In the descriptions of the foregoing embodiments, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0082] In addition, 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 quantity of the technical features indicated. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0083] Any process or method description represented in a flowchart or described otherwise herein may be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a customized logical function or process. The scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may be executed in a substantially simultaneous manner or in an order opposite to that shown or discussed, according to the functions involved, which should be understood by those skilled in the art to which the embodiments of the present disclosure pertain.

[0084] The logic and / or steps represented in a flowchart or described otherwise herein, for example, may be considered as a sequenced list of executable instructions for implementing a logical function and may be specifically implemented in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions. As used in this specification, "a computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection portion having one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable medium on which a program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0085] It should be understood that various parts of the present disclosure can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0086] Those of ordinary skill in the art can understand that all or part of the steps carried by the method of the above embodiments can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0087] In addition, in each of the various embodiments of the present disclosure, the functional units can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0088] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disc, or the like. Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. An ultrafast all-optical intelligent sensing and computing chip system, characterized in that: The system includes an all-optical parallel computing array chip and a demultiplexing device, wherein the chip includes a plurality of microlenses, a plurality of resonant rings and a bus waveguide, wherein: The microlens is used to obtain natural light of a first image in a target area where the microlens is located; The multiple resonant rings are connected to the multiple microlens arrays, and are used to obtain light focused by the corresponding microlenses, and coherently combine the light with the light propagating in the bus waveguide to achieve modulation of the light propagating in the bus waveguide to obtain a first modulation result, wherein the resonant ring is a high-Q value all-pass resonant ring; the light focused by the corresponding microlens is obtained, and the focused light is absorbed by the resonant ring silicon waveguide to generate photogenerated carriers, and based on the high Q value of the resonant ring and the refractive index of the photogenerated carriers, the light propagating in the bus waveguide is phase- and / or amplitude-modulated to obtain a first modulation result; The bus waveguide connects the multiple resonant rings in series, and is used to obtain incident light and propagate the incident light in the multiple resonant rings, and combine the first modulation results to obtain output light results; The demultiplexing device is connected to the all-optical parallel computing array chip and is used to determine the classification result of the first image based on the output light result.

2. The system according to claim 1, characterized in that The plurality of micro lenses are distributed in an array, and each micro lens has a corresponding resonant ring.

3. The system according to claim 1, characterized in that The plurality of resonant rings are divided into different groups, and different groups of resonant rings correspond to different wavelengths of light in the bus waveguide.

4. The system according to claim 3, characterized in that The step of acquiring incident light and propagating the incident light in the plurality of resonant rings, and obtaining an output light result based on the first modulation result, comprises: Acquire incident light and propagate the incident light in the plurality of resonant rings to obtain a first modulation result of each resonant ring; Based on the coherent combination of the incident light in the bus waveguide, a second modulation result of each group of resonant rings is obtained; Based on the second modulation result of each group of resonant rings, an output light result is obtained.

5. The system according to claim 1, characterized in that The determining, based on the output light result, a classification result of the first image comprises: The classification result of the first image is determined based on the information intensity of different wavelength components in the output light result.

6. The system according to claim 1, characterized in that The system also includes an optical renderer, which is connected to the all-optical parallel computing array chip through an optical fiber, and is used to obtain the output light result, and perform all-optical reconstruction based on the output light result to obtain a second image in the target area.

7. The system according to claim 6, characterized in that The optical renderer includes a blazed grating and a diffraction module; the full optical reconstruction is performed based on the output light result to obtain a second image in the target area, including: Reflecting lights of different wavelengths in the output light result to different spatial positions by the blazed grating; The diffraction module diffracts the light at different spatial positions using a phase mask to obtain a second image in the target area.

8. An image classification method using the ultrafast all-optical intelligent sensing chip system as claimed in claim 1, characterized in that: include: Acquire natural light and incident light of a first image in a target area; Inputting the natural light and the incident light into an ultrafast all-optical intelligent sensing chip to obtain an output light result; The output light result is input into a demultiplexing device to obtain a classification result of the first image.

9. The method according to claim 8, characterized in that The method further comprises: The output light result is input into an optical renderer through an optical fiber to obtain a second image in the target area.

Images