An object recognition system, method and storage medium

Abstract

The present invention discloses an object recognition system, method and storage medium. The system includes: an object recognition chip and a data processing device; the object recognition chip includes at least two gallium nitride units, an upper electrode plate and a sapphire substrate; the gallium nitride unit is used to be lit when the corresponding upper electrode lead and the lower electrode layer receive the on-signal at the same time; it is also used to receive the reflected light of the lit gallium nitride units in the array when not lit, convert the light flux of the reflected light into an electrical signal, and send the electrical signal to the data processing device through the output port; the data processing device is respectively connected to the output ports of each gallium nitride unit, and is used to receive the electrical signals sent by each gallium nitride unit, and determine the object recognition result according to each electrical signal. It solves the problems of single function, large overall size and high packaging difficulty of the existing optoelectronic recognition chips, improves the practicability of the object recognition system, and enhances the accuracy of the object recognition system for object recognition.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of optoelectronic recognition technology, and in particular, to an object recognition system, method, and storage medium. Background Art

[0002] With the increasing maturity of optoelectronic technology, the recognition of object characteristics such as color and distance based on optoelectronic conversion has important and extensive applications in various fields such as industry and national defense. Existing optoelectronic recognition chips based on optoelectronic conversion are often composed of two independent components, a light-emitting diode (LED) and a photo-detector (PD). The distance of an object can be analyzed according to the time difference between the light emitted by the LED and the light received by the PD.

[0003] When the optoelectronic recognition chip composed of an LED and a PD is at a relatively small distance from the object to be recognized, the recognition accuracy of the distance deteriorates as the distance decreases, and the recognition performance is significantly reduced. Further, the optoelectronic recognition chip composed of an LED and a PD can also be used for color recognition, but when the chip is used for color recognition, a relatively small distance needs to be maintained between the chip and the object to be recognized. Therefore, the optoelectronic recognition chip composed of an LED and a PD has a single function and cannot simultaneously meet various types of object recognition requirements. At the same time, the existing optoelectronic recognition chip is only composed of one LED and the corresponding PD, and the LED and the PD are connected by an optical fiber with low strength, resulting in a large overall size and high packaging difficulty. Summary of the Invention

[0004] The present invention provides an object recognition system, method, and storage medium, which can meet different types of object recognition requirements through the same object recognition chip, reduce the size and packaging difficulty of the object recognition chip, and expand the applicable scenarios of the object recognition system.

[0005] In a first aspect, an embodiment of the present invention provides an object recognition system, including: an object recognition chip and a data processing device;

[0006] The object recognition chip includes at least two gallium nitride units, an upper electrode plate, and a sapphire substrate;

[0007] Each gallium nitride unit forms a uniformly arranged array. The upper electrode layers of the gallium nitride units in the same row in the array are sequentially connected through upper electrode leads, and each upper electrode lead is arranged on the upper electrode plate;

[0008] The lower electrode layers of the gallium nitride units in the same column in the array are connected to each other, and each lower electrode layer is arranged on the sapphire substrate;

[0009] A gallium nitride unit is used to light up when receiving an on signal at the corresponding upper electrode lead and lower electrode layer simultaneously; it is also used to receive the reflected light of the lit gallium nitride units in the array when not lit, convert the light flux of the reflected light into an electrical signal, and send the electrical signal to the data processing device through the output port;

[0010] The data processing device is respectively connected to the output ports of each gallium nitride unit, and is used to receive the electrical signals sent by each gallium nitride unit and determine the object recognition result according to each electrical signal.

[0011] Furthermore, the data processing device is further used for:

[0012] Obtain the target recognition type, and determine the target gallium nitride unit in the object recognition chip according to the target recognition type.

[0013] Furthermore, the object recognition system further includes: a drive selection circuit;

[0014] The drive selection circuit is connected to the output port of the data processing device, and is respectively connected to each upper electrode lead in the upper electrode plate and each lower electrode layer in the sapphire substrate;

[0015] The drive selection circuit is used to receive the target gallium nitride unit sent by the data processing device, generate an on control signal according to the target gallium nitride unit, and send the on control signal to the object recognition chip, so that the object recognition chip sends an on signal to the upper electrode lead and the lower electrode layer corresponding to the target gallium nitride unit according to the on control signal.

[0016] In a second aspect, an embodiment of the present invention further provides an object recognition method, which can be applied to the object recognition system provided in the first aspect above and is executed by the data processing device in the object recognition system. The method includes:

[0017] Obtain the object to be recognized and the target recognition type, where the target recognition type includes at least one of color recognition, distance recognition, and shape recognition;

[0018] Determine the target gallium nitride unit and the receiving gallium nitride unit in the object recognition chip according to the target recognition type, and receive the electrical signal corresponding to the gallium nitride unit after the target gallium nitride unit is lit;

[0019] Determine the object recognition result corresponding to the target recognition type according to the electrical signal.

[0020] Furthermore, if the target recognition type is color recognition or distance recognition, determining the target gallium nitride unit and the receiving gallium nitride unit in the object recognition chip according to the target recognition type, and receiving the electrical signal corresponding to the gallium nitride unit after the target gallium nitride unit is lit includes:

[0021] Identify the gallium nitride unit at the center position in the object recognition chip as the target gallium nitride unit, or identify the gallium nitride unit closest to the object to be recognized in the object recognition chip as the target gallium nitride unit;

[0022] Identify any gallium nitride unit in the object recognition chip other than the target gallium nitride unit as the receiving gallium nitride unit;

[0023] Control the target gallium nitride unit to light up and receive the electrical signal corresponding to the receiving gallium nitride unit.

[0024] Further, if the target recognition type is shape recognition, determine the target gallium nitride unit and the receiving gallium nitride unit in the object recognition chip according to the target recognition type, and receive the electrical signal corresponding to the receiving gallium nitride unit after the target gallium nitride unit lights up, including:

[0025] Select one from each gallium nitride unit in the object recognition chip as the target gallium nitride unit;

[0026] Determine each gallium nitride unit other than the target gallium nitride unit as the receiving gallium nitride unit;

[0027] Control the target gallium nitride unit to light up and receive the electrical signal corresponding to each receiving gallium nitride unit;

[0028] Judge whether there is an unselected gallium nitride unit among each gallium nitride unit;

[0029] If so, return to the selection operation of the target gallium nitride unit until all gallium nitride units are selected.

[0030] Further, controlling the target gallium nitride unit to light up includes:

[0031] Send the target gallium nitride unit to the drive selection circuit connected to the object recognition chip;

[0032] The drive selection circuit generates a connection control signal according to the target gallium nitride unit and sends the connection control signal to the object recognition chip;

[0033] The object recognition chip sends a connection signal to the upper electrode lead and the lower electrode layer corresponding to the target gallium nitride unit according to the connection control signal to make the target gallium nitride unit light up.

[0034] Further, determining the object recognition result corresponding to the target recognition type according to the electrical signal includes:

[0035] If the target recognition type is color recognition, determine the color recognition result of the object to be recognized according to the corresponding relationship between the electrical signal and the preset color;

[0036] If the target recognition type is distance recognition, determine the distance recognition result of the object to be recognized according to the corresponding relationship between the electrical signal and the preset distance.

[0037] Further, determine the object recognition result corresponding to the target recognition type according to the electrical signal, including:

[0038] For each target gallium nitride unit in the object recognition chip, perform boundary recognition on each electrical signal corresponding to the target gallium nitride unit to determine the intermediate recognition result corresponding to the target gallium nitride unit;

[0039] Fit each intermediate recognition result, and determine the fitting result as the shape recognition result of the object to be recognized.

[0040] In a third aspect, an embodiment of the present invention further provides a storage medium containing computer-executable instructions, and the computer-executable instructions are used to execute the object recognition method provided in any embodiment of the present invention when executed by a computer processor.

[0041] An embodiment of the present invention provides an object recognition system, method and storage medium. The object recognition system includes: an object recognition chip and a data processing device; the object recognition chip includes at least two gallium nitride units, an upper electrode plate and a sapphire substrate; each gallium nitride unit forms a uniformly arranged array, and the upper electrode layers of the gallium nitride units in the same row in the array are sequentially connected through upper electrode leads, and each upper electrode lead is arranged on the upper electrode plate; the lower electrode layers of the gallium nitride units in the same column in the array are connected to each other, and each lower electrode layer is arranged on the sapphire substrate; the gallium nitride unit is used to light up when the corresponding upper electrode lead and the lower electrode layer receive the on signal at the same time; it is also used to receive the reflected light of the lit gallium nitride unit in the array when not lit, convert the light flux of the reflected light into an electrical signal, and send the electrical signal to the data processing device through the output port; the data processing device is respectively connected to the output ports of each gallium nitride unit, and is used to receive the electrical signals sent by each gallium nitride unit, and determine the object recognition result according to each electrical signal. By adopting the above technical solutions, an embodiment of the present invention forms a uniformly arranged array with multiple identical gallium nitride units and packages them into an object recognition chip. Each gallium nitride unit can be used as an LED and a PD. Different gallium nitride units can be selected as LEDs and PDs according to different types of object recognition requirements. Different types of object recognition can be realized through the same object recognition chip, and high-precision small-distance recognition can be performed. At the same time, since multiple gallium nitride units are integrated in an array on the same object recognition chip, the packaging difficulty and chip size of the object recognition chip are reduced, the problems of single function, large overall size and high packaging difficulty of the existing optoelectronic recognition chips are solved, the practicability of the object recognition system is improved, and the accuracy of the object recognition system for object recognition is improved. Description of the Drawings

[0042] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as a limitation of the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0043] Figure 1 It is a schematic structural diagram of an object recognition system in the first embodiment of the present invention;

[0044] Figure 2 It is a schematic structural diagram of an object recognition chip in the first embodiment of the present invention;

[0045] Figure 3 It is a schematic structural diagram of an object recognition system in the first embodiment of the present invention;

[0046] Figure 4 It is a flowchart of an object recognition method in the second embodiment of the present invention;

[0047] Figure 5 It is a flowchart of an object recognition method in the third embodiment of the present invention. Detailed implementation manners

[0048] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will further describe the embodiments of the present invention in detail in conjunction with the accompanying drawings. It should be clear that the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0049] When the following description involves the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are only examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0050] In the description of the present invention, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and do not have to be used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. In addition, in the description of the present invention, unless otherwise specified, "a plurality of" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally means that the associated objects before and after are in an "or" relationship.

[0051] Embodiment 1

[0052] Figure 1 FIG. is a schematic structural diagram of an object recognition system provided in Embodiment 1 of the present invention. By lighting the gallium nitride units in the object recognition chip encapsulating the gallium nitride unit array, and then converting the light flux received by other gallium nitride units into electrical signals, and determining the object recognition result according to the electrical signals, the recognition of the object to be recognized is realized. As Figure 1 shown, the object recognition system includes: an object recognition chip 10 and a data processing device 11, where:

[0053] The object recognition chip 10 includes at least two gallium nitride units 101, an upper electrode plate 102 and a sapphire substrate 103. Figure 1 Taking two gallium nitride units 101 as an example.

[0054] Each gallium nitride unit 101 forms a uniformly arranged array. The upper electrodes of the gallium nitride units 101 in the same row in the array are sequentially connected through upper electrode leads, and each upper electrode lead is arranged on the upper electrode plate 102.

[0055] The lower electrode layers of the gallium nitride units 101 in the same column in the array are connected to each other, and each lower electrode layer is arranged on the sapphire substrate 103.

[0056] The gallium nitride unit 101 is used to light up when the corresponding upper electrode lead and the lower electrode layer receive the on signal at the same time; it is also used to receive the reflected light of the lit gallium nitride unit 101 in the array when not lit, convert the light flux of the reflected light into an electrical signal, and send the electrical signal to the data processing device 11 through the output port.

[0057] The data processing device 11 is respectively connected to the output ports of each gallium nitride unit 101, and is used to receive the electrical signals sent by each gallium nitride unit 101, and determine the object recognition result according to each electrical signal.

[0058] In this embodiment, the object recognition chip 10 can be understood as a monolithic integrated array chip that integrates multiple identical gallium nitride units 101 and has functions of color, distance, and shape recognition. The gallium nitride unit 101 can be understood as a direct bandgap semiconductor device composed of gallium nitride (GaN). After being powered on, it can be excited and lit up to be used as an LED, or it can also be used to absorb the light emitted by other gallium nitride units and be used as a PD matching the LED. Among them, the gallium nitride unit 101 consists of an upper electrode layer (P layer), a light-emitting layer, and a lower electrode layer (N layer). The lower electrode layers of the gallium nitride units 101 located in the same column in the object recognition chip 10 are connected to each other and can conduct electrical signals. The data processing device 11 can be understood as a computer device for data processing. It can process the received data signals such as electrical signals according to preset rules to obtain a data processing result. Optionally, the data processing device 11 can be a microcontroller unit (MCU), or it can also be other computer devices with data processing capabilities. The embodiments of the present invention do not limit this. The luminous flux can be understood as the radiation power of the light that can be received by semiconductor components.

[0059] Specifically, the data processing device 11 is connected to the output ports of each gallium nitride unit 101 in the object recognition chip 10 through wires. When performing object recognition, one or more gallium nitride units 101 in the object recognition chip 10 are lit up according to the received on-signal. The light emitted by the lit gallium nitride unit 101 can obtain corresponding reflected light after being reflected by the object to be recognized. The gallium nitride units 101 in the object recognition chip 10 except the lit gallium nitride unit 101 can receive the reflected light, generate an electrical signal with a corresponding intensity according to the luminous flux of the reflected light, and transmit the electrical signal to the data processing device 11 through the output port provided on the gallium nitride unit 101 via wires. The data processing device 11 processes each electrical signal according to the corresponding rules based on the electrical signals transmitted by each gallium nitride unit 101 received and the obtained target recognition type for the object to be recognized, and determines the processing result as the object recognition result of the object to be recognized.

[0060] In an embodiment of the present invention, each gallium nitride unit 101 in the object recognition chip 10 can be used as an LED or a PD. There is no need to connect them through optical fibers, and there is no failure caused by the breakage of fragile optical fibers, which improves the durability of the object recognition chip 10 and also improves the stability of the operation of the object recognition system. At the same time, the gallium nitride units 101 are integrated in an array on the same chip. There is no need for optical calibration during each recognition, which improves the recognition efficiency. Further, based on the characteristics of the gallium nitride unit 101 itself, the gallium nitride units 101 do not affect each other, so that the object recognition chip 10 can have better performance when used for distance recognition. It can recognize distances within 5 mm, and when the recognition distance is less than 1 mm, the recognition accuracy can still exceed 1 μm, making the recognition accuracy of the object recognition system higher.

[0061] Further, Figure 2 FIG. 5 is a schematic structural diagram of an object recognition chip provided in Embodiment 1 of the present invention. The object recognition chip 10 includes at least two gallium nitride units 101, an upper electrode plate 102, and a sapphire substrate 103, and each gallium nitride unit forms a uniformly arranged array. In this application, nine gallium nitride units 101 forming a 3×3 array are taken as an example, as Figure 2 shown.

[0062] Specifically, each gallium nitride unit 101 in the object recognition chip 10 is uniformly arranged at equal intervals to form a 3×3 array. Assuming that the top surface of the gallium nitride unit 101 is the upper electrode layer and the bottom surface is the lower electrode layer, the upper electrode layers of the gallium nitride units 101 in the same row in the array are sequentially connected by the same upper electrode lead wire, that is, as Figure 2 shown, the object recognition chip 10 has three upper electrode lead wires. Each upper electrode lead wire is connected in series with the upper electrode layers of three gallium nitride units 101 in the same row. The upper electrode lead wires are arranged at equal intervals on the upper electrode plate 102. Optionally, the upper electrode plate can be an insulating silicon dioxide plate, and the embodiment of the present invention does not limit this. Further, the lower electrode layers of the gallium nitride units 101 in the same column in the array are connected to each other, that is, as Figure 2 shown, the object recognition chip 10 has three columns of lower electrode layers connected to each other. Each column is connected in series with the lower electrode layers of three gallium nitride units 101 in the same column. The lower electrode layers are arranged at equal intervals on the sapphire substrate 103.

[0063] When it is necessary to light up the gallium nitride unit 101, the upper electrode lead wire and the lower electrode layer in series with the gallium nitride unit 101 to be lit can be determined, and a connection signal is input into the above upper electrode lead wire and lower electrode layer at the same time, so that the gallium nitride unit 101 connected to the upper electrode lead wire and the lower electrode layer at the same time is powered on and lit. Exemplarily, if you want to light up the gallium nitride unit 101 in the center of the object recognition chip 10 in Figure 2 SinceFigure 2 In the object recognition chip 10, if the gallium nitride units 101 are arranged in a 3×3 pattern, the coordinates of the central gallium nitride unit 101 in the array can be represented by (2, 2). Further, an on signal needs to be sent to the second upper electrode lead and the second column of the lower electrode layer of the object recognition chip 10 simultaneously, so that the gallium nitride unit 101 with coordinates (2, 2) in the array is lit. After the gallium nitride units 101 to be lit in the object recognition chip 10 are lit, the other unlit gallium nitride units 101 can receive the reflected light after the light emitted by the lit gallium nitride units 101 in the array is reflected by the object to be recognized. Due to the different distances between the object to be recognized and the gallium nitride units 101, the different colors of the object to be recognized itself, and the different positions of the unlit gallium nitride units 101 on the object recognition chip 10, the light fluxes of the reflected light received by different gallium nitride units 101 are different. The light fluxes can be converted into corresponding electrical signals according to their magnitudes, and the electrical signals are sent to the data processing device 11 through the output ports provided on the gallium nitride units 101.

[0064] Furthermore, the data processing device 11 is further configured to: obtain a target recognition type, and determine target gallium nitride units in the object recognition chip 10 according to the target recognition type.

[0065] In this embodiment, the target recognition type can be understood as the types of features for which the object to be recognized needs to be recognized. Optionally, the target recognition type may include color recognition, distance recognition, and shape recognition, that is, it is necessary to recognize the color of the object to be recognized, the distance of the object to be recognized relative to the object recognition chip 10, and the shape of the object to be recognized. The target gallium nitride units can be understood as the gallium nitride units that need to be lit in the object recognition chip 10 determined according to the obtained target recognition type.

[0066] Specifically, when object recognition needs to be performed on the object to be recognized, the data processing device 11 can receive the target recognition type given by the user or determined according to a preset, and determine one or more gallium nitride units 101 that are most suitable to be lit in the object recognition chip 10 according to the target recognition type, and use the determined gallium nitride units 101 as the target gallium nitride units.

[0067] Furthermore, the object recognition system further includes: a drive selection circuit 12. Figure 3 This is a schematic structural diagram of an object recognition system provided in Embodiment 1 of the present invention. As Figure 3As shown in the figure, the drive selection circuit 12 is connected to the output port of the data processing device 11, and is respectively connected to each upper electrode lead in the upper electrode plate 102 of the object recognition chip 10 and each lower electrode layer in the sapphire substrate 103. It should be noted that, in order to make the structural schematic diagram clear, the connection relationship between the data processing device 11 and the output ports of each gallium nitride unit 101 has been omitted, but it is not in a non-connected state.

[0068] The drive selection circuit 12 is configured to receive the target gallium nitride unit sent by the data processing device 11, generate a connection control signal according to the target gallium nitride unit, and send the connection control signal to the object recognition chip 10, so that the object recognition chip sends a connection signal to the upper electrode lead and the lower electrode layer corresponding to the target gallium nitride unit according to the connection control signal.

[0069] Specifically, the drive selection circuit 12 is connected to the output port of the data processing device 11, receives the target gallium nitride unit determined by the data processing device 11 according to the target recognition type, and generates a connection control signal for controlling the energization of the upper electrode lead and the lower electrode layer at the corresponding position in the gallium nitride unit array of the object recognition chip 10 according to the position of the target gallium nitride unit in the gallium nitride unit array of the object recognition chip 10; the drive selection circuit 12 is also respectively connected to each upper electrode lead in the upper electrode plate 102 of the object recognition chip 10 and each lower electrode layer in the sapphire substrate 103. After the drive selection circuit 12 generates the connection control signal, it can determine the upper electrode lead and the lower electrode layer corresponding to the target gallium nitride unit, and then send the connection control signal to the object recognition chip 10 via the corresponding wire. The object recognition chip 10 simultaneously sends a connection signal to the upper electrode lead and the lower electrode layer corresponding to the target gallium nitride unit according to the received connection control signal, so that the target gallium nitride unit is successfully energized and lit. Optionally, the target gallium nitride unit in the object recognition chip 10 can be driven by the ASCII addressing method, or other passive drive methods can be used to drive the target gallium nitride unit to light up. The embodiments of the present invention do not limit this.

[0070] The technical solution of this embodiment provides an object recognition system, method, and storage medium. The object recognition system includes an object recognition chip and a data processing device. The object recognition chip includes at least two gallium nitride units, an upper electrode plate, and a sapphire substrate. Each gallium nitride unit forms a uniformly arranged array. The upper electrode layers of the gallium nitride units in the same row of the array are sequentially connected through upper electrode leads, and each upper electrode lead is arranged on the upper electrode plate. The lower electrode layers of the gallium nitride units in the same column of the array are connected to each other, and each lower electrode layer is arranged on the sapphire substrate. The gallium nitride unit is used to light up when the corresponding upper electrode lead and the lower electrode layer receive an on signal at the same time. It is also used to receive the reflected light of the lit gallium nitride units in the array when not lit, convert the light flux of the reflected light into an electrical signal, and send the electrical signal to the data processing device through the output port. The data processing device is respectively connected to the output ports of each gallium nitride unit, and is used to receive the electrical signals sent by each gallium nitride unit and determine the object recognition result according to each electrical signal. By adopting the above technical solution, the embodiments of the present invention form a uniformly arranged array of multiple identical gallium nitride units and package them into an object recognition chip. Each gallium nitride unit can be used as an LED and a PD. Different gallium nitride units can be selected as LEDs and PDs according to different types of object recognition requirements. Different types of object recognition can be achieved through the same object recognition chip, and high-precision small-distance recognition can be performed. At the same time, since multiple gallium nitride units are integrated in an array in the same object recognition chip, the packaging difficulty and chip size of the object recognition chip are reduced, the problems of single function, large overall size, and high packaging difficulty of the existing optoelectronic recognition chips are solved, the practicability of the object recognition system is improved, and the accuracy of object recognition by the object recognition system is enhanced.

[0071] Embodiment 2

[0072] Figure 4 The flowchart of an object recognition method provided by Embodiment 2 of the present invention. This embodiment is applicable to the situation of determining the target gallium nitride unit to be lit on the object recognition chip in the object recognition system and the receiving gallium nitride unit for receiving light by obtaining the object to be recognized and the target recognition type, and determining the object recognition result according to the electrical signal generated by the receiving gallium nitride unit. This method can be applied to the object recognition system provided in the above embodiment and is executed by the data processing device in the object recognition system.

[0073] As Figure 4 shown, an object recognition method provided by Embodiment 2 of the present invention specifically includes the following steps:

[0074] S201. Obtain the object to be recognized and the target recognition type.

[0075] Among them, the target recognition types include at least one of color recognition, distance recognition, and shape recognition.

[0076] In this embodiment, the object to be recognized can be understood as an object for which an object recognition system needs to recognize its distance, color, or shape. The target recognition type can be understood as the type of features for which the object to be recognized needs to be recognized. Color recognition can be understood as the need to recognize the color features of the object to be recognized. Distance recognition can be understood as the need to recognize the distance feature between the object to be recognized and the object recognition chip. Shape recognition can be understood as the need to recognize the shape features of the object to be recognized, that is, the appearance boundary features.

[0077] Specifically, when object recognition is required, the data processing device in the object recognition system identifies the object to be recognized that needs to be recognized, and can receive the target recognition type input from the outside, or can determine the type of features for which the object to be recognized should be recognized according to the pre-set recognition type selection method, and determine the target recognition type according to the type of features.

[0078] S202. Determine the target gallium nitride unit and the receiving gallium nitride unit in the object recognition chip according to the target recognition type, and receive the electrical signal corresponding to the receiving gallium nitride unit after the target gallium nitride unit is lit;

[0079] In this embodiment, the target gallium nitride unit can be understood as the gallium nitride unit that needs to be lit in the gallium nitride unit array of the object recognition chip. The receiving gallium nitride unit can be understood as the gallium nitride unit in the gallium nitride unit array of the object recognition chip that needs to receive light and generate an electrical signal according to the received reflected light flux.

[0080] Specifically, due to different target recognition types, the positions and numbers of the gallium nitride units that need to be lit in the object recognition chip are different, and the positions and numbers of the gallium nitride units that need to receive the reflected light of the object to be recognized are also different. Exemplarily, if the target recognition type is color recognition, only one gallium nitride unit needs to be lit, and the color of the object to be recognized can be determined by another gallium nitride unit receiving the reflected light; if the target recognition type is shape recognition, the boundary of the object to be recognized cannot be determined only by one gallium nitride unit receiving the reflected light. Therefore, the target gallium nitride unit and the receiving gallium nitride unit suitable for recognizing the features corresponding to the target recognition type can be selected according to the specific target recognition type. Further, after the determined target gallium nitride unit is lit, all the unlit gallium nitride units in the object recognition chip can receive the reflected light of the object to be recognized. At this time, the data processing device only needs to receive the electrical signal determined by the determined receiving gallium nitride unit according to the reflected light flux to process the received electrical signal to obtain the object recognition result, rather than receiving the electrical signals of all the unlit gallium nitride units, reducing the data calculation amount in the data processing device.

[0081] S203. Determine the object recognition result corresponding to the target recognition type according to the electrical signal.

[0082] Specifically, determine the correspondence between the electrical signal and the characteristics of the object to be recognized according to the obtained target recognition type, and then process the obtained electrical signal according to the determined correspondence, and determine the processing result as the object recognition result corresponding to the target recognition type.

[0083] In the technical solution of this embodiment, when it is necessary to recognize the object to be recognized, obtain the target recognition type corresponding to the object to be recognized, and determine the target gallium nitride unit to be lit in the gallium nitride unit array composed of the same gallium nitride units in the object recognition chip according to the target recognition type, and the receiving gallium nitride unit that needs to receive the reflected light and generate an electrical signal, and determine the object recognition result corresponding to the target recognition type according to the electrical signal generated by the received receiving gallium nitride unit. By adopting the above technical solution, since the object recognition chip is encapsulated with an array of uniformly arranged multiple identical gallium nitride units, and each connection correspondence can be used as an LED and a PD, different characteristics of the object to be recognized can be recognized by the same object recognition chip, enriching the object recognition type and improving the accuracy of object recognition at the same time.

[0084] Embodiment III

[0085] Figure 5 The flowchart of an object recognition method provided by Embodiment III of the present invention. The technical solution of the embodiment of the present invention is further optimized on the basis of the above-mentioned optional technical solutions, and gives the selection methods of the target gallium nitride unit and the receiving gallium nitride unit when the target recognition types are color recognition, distance recognition and shape recognition respectively, and at the same time gives the method of determining the object recognition result according to the received electrical signal under each target recognition type, improving the richness and practicability of the object recognition type, and improving the accuracy of object recognition at the same time.

[0086] As Figure 5 shown, an object recognition method provided by Embodiment II of the present invention specifically includes the following steps:

[0087] S301. Obtain the object to be recognized and the target recognition type.

[0088] Among them, the target recognition type includes at least one of color recognition, distance recognition and shape recognition.

[0089] S302. Judge whether the target recognition type is shape recognition. If so, execute step S303. If not, execute step S309.

[0090] Specifically, since when the target recognition type is shape recognition, it is necessary to determine the target gallium nitride unit and the receiving gallium nitride unit multiple times, and it is necessary to receive the electrical signals transmitted by each receiving gallium nitride unit multiple times, it is necessary to first determine whether the target recognition type is shape recognition before performing object recognition. If so, step S303 is executed; otherwise, step S309 is executed.

[0091] S303. Select one from each gallium nitride unit in the object recognition chip as the target gallium nitride unit.

[0092] Specifically, arbitrarily select a gallium nitride unit from the gallium nitride unit array in the object recognition chip. If this gallium nitride unit has never been used as a target gallium nitride unit during the recognition process of the current object to be recognized, then this gallium nitride unit is determined as the target gallium nitride unit; otherwise, select a gallium nitride unit that has not been used as a target gallium nitride unit from the remaining gallium nitride units in the object recognition chip and determine it as the target gallium nitride unit.

[0093] S304. Determine each gallium nitride unit other than the target gallium nitride unit as a receiving gallium nitride unit.

[0094] Specifically, since when performing shape recognition on the object to be recognized, the light fluxes of the reflected light of the object to be recognized on the gallium nitride units at different positions in the object recognition chip are different, and it is necessary to perform boundary recognition according to the different light fluxes received by each gallium nitride unit, all the unlit gallium nitride units in the object recognition chip need to receive the reflected light of the object to be recognized. At this time, each gallium nitride unit other than the target gallium nitride unit is determined as a receiving gallium nitride unit.

[0095] S305. Control the target gallium nitride unit to light up and receive the electrical signals corresponding to each receiving gallium nitride unit.

[0096] Specifically, the target gallium nitride unit in the object recognition chip is controlled to light up through the drive selection circuit. The light emitted by the target gallium nitride unit can be received by each receiving gallium nitride unit after being reflected by the object to be recognized. Each receiving gallium nitride unit performs photoelectric conversion on the received reflected light flux to obtain the corresponding electrical signal and sends the electrical signal to the data processing device, so that the data processing device can receive the electrical signals corresponding to each gallium nitride unit. Optionally, the electrical signal can be a characteristic quantity such as voltage, electric quantity, and current used to characterize electrical characteristics. The embodiments of the present invention do not limit this.

[0097] Further, controlling the target gallium nitride unit to light up specifically includes the following steps:

[0098] A. Send the target gallium nitride unit to the drive selection circuit connected to the object recognition chip.

[0099] B. The drive selection circuit generates a turn-on control signal based on the target gallium nitride unit and sends the turn-on control signal to the object recognition chip.

[0100] C. The object recognition chip sends a turn-on signal to the upper electrode lead and the lower electrode lead corresponding to the target gallium nitride unit according to the turn-on control signal, so that the target gallium nitride unit is lit.

[0101] S306. Determine whether there is an unselected gallium nitride unit among all gallium nitride units. If so, return to step S303; if not, execute step S307.

[0102] Specifically, determine whether there is a gallium nitride unit in the object recognition chip that has not been selected as the target gallium nitride unit, that is, determine whether there is a gallium nitride unit that has not been lit as the target gallium nitride unit. If so, return to step S303 to light the unlit gallium nitride unit and obtain the corresponding electrical signals; if not, it can be considered that all gallium nitride units in the object recognition chip have been traversed and lit, and the electrical signal set corresponding to each gallium nitride unit when it is lit can be obtained. At this time, execute step S307.

[0103] S307. For each target gallium nitride unit in the object recognition chip, perform boundary recognition on the corresponding electrical signals of the target gallium nitride unit to determine the intermediate recognition result corresponding to the target gallium nitride unit.

[0104] Specifically, when each target gallium nitride unit in the object recognition chip is lit, the data processing device can receive a group of electrical signals sent by the corresponding receiving gallium nitride units of the target gallium nitride unit. Since the receiving gallium nitride units closer to the object to be recognized will receive more reflected light, and the light flux of the reflected light is larger, the electrical signal value converted from the light flux of the reflected light is higher. The array formed by the electrical signals sent by each gallium nitride unit can be subjected to boundary recognition, that is, determine the adjacent electrical signals where mutations occur in the electrical signals. The boundary of the electrical signal mutation is determined as the boundary of the object to be recognized, and the result obtained after boundary recognition is determined as the intermediate recognition result corresponding to the target gallium nitride unit. That is, the intermediate recognition results equal to the number of gallium nitride units in the object recognition chip can be obtained.

[0105] S308. Fit the intermediate recognition results and determine the fitting result as the shape recognition result of the object to be recognized.

[0106] Specifically, fit the boundaries of the objects to be recognized obtained in each intermediate recognition result, determine the overlapping parts of the object boundaries obtained in each intermediate recognition result as the fitting result, and determine the fitting result as the shape recognition result of the object to be recognized.

[0107] S309. Determine the gallium nitride unit at the central position in the object recognition chip as the target gallium nitride unit, or determine the gallium nitride unit closest to the object to be recognized in the object recognition chip as the target gallium nitride unit.

[0108] Specifically, when the target recognition type is not shape recognition, that is, when the target recognition type is color recognition or distance recognition, it is only necessary to light the gallium nitride unit in the object recognition chip once, and the corresponding object recognition result can be determined according to the electrical signal corresponding to the reflected light obtained after this lighting. Therefore, only one gallium nitride unit in the object recognition chip needs to be selected as the target gallium nitride unit for lighting operation. To make the light received by the receiving gallium nitride unit in the object recognition chip for receiving the reflected light basically the same, the gallium nitride unit at the central position of the object recognition chip can be determined as the target gallium nitride unit; or the gallium nitride unit closest to the object to be recognized in the object recognition chip can be determined as the target gallium nitride unit, so that the object to be recognized can obtain the best lighting effect. It should be clear that in theory, any gallium nitride unit in the object recognition chip can be used as the target gallium nitride unit. The two options provided in this application are only partial cases, and the embodiments of the present invention do not limit this.

[0109] S310. Determine any gallium nitride unit in the object recognition chip other than the target gallium nitride unit as the receiving gallium nitride unit.

[0110] Specifically, after determining the target gallium nitride unit, it is necessary to select a gallium nitride unit that is not the target gallium nitride unit in the object recognition chip as its corresponding PD. Since the object recognition chip is small, when the object recognition chip is used for distance recognition and color recognition, the influence of the position of each gallium nitride unit on receiving the reflected light will not affect the recognition result. Therefore, any gallium nitride unit other than the target gallium nitride unit in the object recognition chip can be selected as the receiving gallium nitride unit.

[0111] S311. Control the target gallium nitride unit to light up and receive the electrical signal corresponding to the receiving gallium nitride unit.

[0112] Specifically, the content executed in this step is basically the same as that in step S305, and the relevant content has been specifically explained at step S305, so no detailed description will be given here.

[0113] S312. Determine whether the target recognition type is color recognition. If so, execute step S313; if not, execute step S314.

[0114] S313. Determine the color recognition result of the object to be recognized according to the correspondence between the electrical signal and the preset color.

[0115] Specifically, since the absorption and reflection rates of light emitted by the object recognition chip by objects of different colors are different, the corresponding relationship between different colors and electrical signals can be determined at the same distance, and this corresponding relationship is determined as the preset color corresponding relationship. Then, when performing color recognition on the object to be recognized, the corresponding color recognition result can be determined according to the received electrical signal and the preset color corresponding relationship.

[0116] Exemplarily, for an object to be recognized of the same material, when it is white and blue, it has the highest reflectivity and the lowest absorption rate. That is, the light intensity of the same light reflected by the object to be recognized of the above colors is higher, and thus the intensity of the electrical signal obtained after conversion is higher; while when the object to be recognized is black, it has the highest absorption rate and the lowest reflectivity, that is, the light intensity of the same light reflected by the black object to be recognized is lower, and thus the intensity of the electrical signal obtained after conversion is lower. Based on the above principle, the corresponding relationship between different colors and electrical signals can be obtained, and this corresponding relationship can be determined as the preset color corresponding relationship.

[0117] S314. Determine the distance recognition result of the object to be recognized according to the corresponding relationship between the electrical signal and the preset distance.

[0118] Specifically, since the light emitted by the gallium nitride unit in the object recognition chip when used as an LED is uniform in all angles, for an object to be recognized of the same color, the closer its distance to the object recognition chip, the more light will be reflected and received by the receiving gallium nitride unit used as a PD, and then converted into an electrical signal. Therefore, the corresponding relationship between different distances and electrical signals under the same color can be determined, and this corresponding relationship is determined as the preset distance corresponding relationship. Then, when performing distance recognition on the object to be recognized, the corresponding distance recognition result can be determined according to the received electrical signal and the preset distance corresponding relationship.

[0119] The technical solution of this embodiment determines the target gallium nitride unit and the corresponding receiving gallium nitride unit according to different target recognition types. For the target recognition type that does not require multiple receiving gallium nitride units to receive light and convert electrical signals, only the electrical signals of the determined receiving gallium nitride units are received and processed, reducing the amount of data calculation required in the data processing device; the electrical signals obtained through the same object recognition chip can be used to recognize the color, distance and shape of the object to be recognized, improving the richness of the object recognition types and at the same time improving the practicality of object recognition.

[0120] Embodiment Four

[0121] Embodiment Four of the present invention further provides a storage medium containing computer-executable instructions, and the computer-executable instructions are used to execute an object recognition method when executed by a computer processor. The method includes:

[0122] Obtain the object to be recognized and the target recognition type, where the target recognition type includes at least one of color recognition, distance recognition, and shape recognition;

[0123] Determine the target gallium nitride unit and the receiving gallium nitride unit in the object recognition chip according to the target recognition type, and receive the electrical signal corresponding to the receiving gallium nitride unit after the target gallium nitride unit is lit;

[0124] Determine the object recognition result corresponding to the target recognition type according to the electrical signal.

[0125] Of course, the storage medium containing computer-executable instructions provided by the embodiments of the present invention, the computer-executable instructions are not limited to the method operations described above, and can also execute the related operations in the object recognition method provided by any embodiment of the present invention.

[0126] From the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software and necessary general hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk, or optical disc of a computer, including several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0127] It should be noted that in the embodiments of the above search device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0128] Note that the above is only the preferred embodiment of the present invention and the applied technical principle. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described here, and various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, more other equivalent embodiments can be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An object recognition system, characterized in that, Comprising: An object recognition chip and a data processing device; The object recognition chip includes at least two gallium nitride units, an upper electrode plate and a sapphire substrate; Each of the gallium nitride units forms a uniformly arranged array, and the upper electrode layers of the gallium nitride units in the same row in the array are sequentially connected through upper electrode leads, and each of the upper electrode leads is arranged on the upper electrode plate; The lower electrode layers of the gallium nitride units in the same column in the array are connected to each other, and each of the lower electrode layers is arranged on the sapphire substrate; The gallium nitride unit is configured to be lit when a connection signal is received simultaneously by the corresponding upper electrode lead and the lower electrode layer; and is further configured to receive the reflected light of the lit gallium nitride unit in the array when not lit, convert the luminous flux of the reflected light into an electrical signal, and send the electrical signal to the data processing device through an output port; The data processing device is respectively connected to the output ports of each of the gallium nitride units, and is configured to receive the electrical signals sent by each of the gallium nitride units, and determine an object recognition result according to each of the electrical signals; The object recognition system further includes: a drive selection circuit; The drive selection circuit is connected to the output port of the data processing device, and is respectively connected to each of the upper electrode leads in the upper electrode plate and each of the lower electrode layers in the sapphire substrate; The drive selection circuit is configured to receive the target gallium nitride unit sent by the data processing device, generate a connection control signal according to the target gallium nitride unit, and send the connection control signal to the object recognition chip, so that the object recognition chip sends a connection signal to the upper electrode lead and the lower electrode layer corresponding to the target gallium nitride unit according to the connection control signal.

2. The system according to claim 1, wherein The data processing device is further configured to: Obtain a target recognition type, and determine the target gallium nitride unit in the object recognition chip according to the target recognition type.

3. An object recognition method, characterized in that, Applied to the object recognition system according to any one of claims 1-2, executed by the data processing device in the object recognition system, the method includes: Obtain an object to be recognized and a target recognition type, where the target recognition type includes at least one of color recognition, distance recognition, and shape recognition; Determine the target gallium nitride unit and the receiving gallium nitride unit in the object recognition chip according to the target recognition type, and receive the electrical signal corresponding to the receiving gallium nitride unit after the target gallium nitride unit is lit; Determine the object recognition result corresponding to the target recognition type according to the electrical signal.

4. The method according to claim 3, characterized in that If the target recognition type is color recognition or distance recognition, the determining the target gallium nitride unit and the receiving gallium nitride unit in the object recognition chip according to the target recognition type, and receiving the electrical signal corresponding to the receiving gallium nitride unit after the target gallium nitride unit is lit includes: Determine the gallium nitride unit located at the center position in the object recognition chip as the target gallium nitride unit, or determine the gallium nitride unit closest to the object to be recognized in the object recognition chip as the target gallium nitride unit; Determine any gallium nitride unit in the object recognition chip other than the target gallium nitride unit as the receiving gallium nitride unit; Control the target gallium nitride unit to light up and receive the electrical signal corresponding to the receiving gallium nitride unit.

5. The method according to claim 3, wherein If the target recognition type is shape recognition, determining the target gallium nitride unit and the receiving gallium nitride unit in the object recognition chip according to the target recognition type, and receiving the electrical signal corresponding to the receiving gallium nitride unit after the target gallium nitride unit lights up, includes: Select one from each gallium nitride unit in the object recognition chip as the target gallium nitride unit; Determine each gallium nitride unit other than the target gallium nitride unit as the receiving gallium nitride unit; Control the target gallium nitride unit to light up and receive the electrical signals corresponding to each receiving gallium nitride unit; Judge whether there is an unselected gallium nitride unit among each gallium nitride unit; If so, return to the selection operation of the target gallium nitride unit until all gallium nitride units are selected.

6. The method according to claim 4 or 5, characterized in that, The controlling the target gallium nitride unit to light up includes: Send the target gallium nitride unit to the drive selection circuit connected to the object recognition chip; The drive selection circuit generates a turn-on control signal according to the target gallium nitride unit and sends the turn-on control signal to the object recognition chip; The object recognition chip sends a turn-on signal to the upper electrode lead and the lower electrode layer corresponding to the target gallium nitride unit according to the turn-on control signal to make the target gallium nitride unit light up.

7. The method according to claim 4, characterized in that The determining the object recognition result corresponding to the target recognition type according to the electrical signal includes: If the target recognition type is color recognition, determine the color recognition result of the object to be recognized according to the corresponding relationship between the electrical signal and the preset color; If the target recognition type is distance recognition, determine the distance recognition result of the object to be recognized according to the corresponding relationship between the electrical signal and the preset distance.

8. The method according to claim 5, wherein The determining the object recognition result corresponding to the target recognition type according to the electrical signal includes: For each target gallium nitride unit in the object recognition chip, perform boundary recognition on each electrical signal corresponding to the target gallium nitride unit to determine the intermediate recognition result corresponding to the target gallium nitride unit; Fit each intermediate recognition result and determine the fitting result as the shape recognition result of the object to be recognized.

9. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions are used to execute the object recognition method according to any one of claims 3-8 when executed by a computer processor.

Images