CN111562886B - Array type sensor chip and data output method thereof - Google Patents
Array type sensor chip and data output method thereof Download PDFInfo
- Publication number
- CN111562886B CN111562886B CN202010385945.5A CN202010385945A CN111562886B CN 111562886 B CN111562886 B CN 111562886B CN 202010385945 A CN202010385945 A CN 202010385945A CN 111562886 B CN111562886 B CN 111562886B
- Authority
- CN
- China
- Prior art keywords
- unit
- processing
- units
- data
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/061—Improving I/O performance
- G06F3/0611—Improving I/O performance in relation to response time
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0646—Horizontal data movement in storage systems, i.e. moving data in between storage devices or systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0683—Plurality of storage devices
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The invention provides an array type sensor chip and a data output method thereof, belonging to the technical field of sensors. An array type sensor chip comprising: the processing unit and the plurality of sensing units are respectively connected with the processing unit; the sensing unit is used for receiving an external signal, converting the external signal into a unit value and sending the unit value to the processing unit according to a preset rule; the processing unit is used for processing the data of the unit value by adopting a preset algorithm; and controlling the induction unit to send a unit value to the receiving part when the processed data or the processing result meets the preset condition. The invention aims to provide an array type sensor chip and a data output method thereof, which can reduce the data amount transmitted to a receiving part or reduce the calculation amount of the receiving part and improve the response speed of the receiving part.
Description
Technical Field
The invention relates to the technical field of sensors, in particular to an array type sensor chip and a data output method thereof.
Background
In the array type sensor chip, a plurality of sensing units in the sensor are arranged in an array manner, and electric signals (unit values) are obtained based on external signal conversion, and the unit values are required to be transmitted to a data processing center (receiving part) arranged outside the array type sensor chip for processing and calculation.
However, the number of sensing units in the array sensor chip is usually large, a large amount of data to be processed is input to the receiving unit during data transmission, and the receiving unit has a slow response speed due to the centralized transmission and calculation of the large amount of data.
Disclosure of Invention
The invention aims to provide an array type sensor chip and a data output method thereof, which can reduce the data amount transmitted to a receiving part and/or reduce the calculation amount of the receiving part, and improve the response speed of the receiving part.
The embodiment of the invention is realized by the following steps:
in one aspect of the embodiments of the present invention, there is provided an array type sensor chip including: the processing unit and the plurality of sensing units are respectively connected with the processing unit;
the sensing unit is used for receiving an external signal, converting the external signal into a unit value and sending the unit value to the processing unit according to a preset rule;
the processing unit is used for processing the data of the unit value by adopting a preset algorithm; and controlling the induction unit to send a unit value to the receiving part when the processed data or the processing result meets the preset condition.
Optionally, the preset rule includes a preset adjustment rule of a connection relationship and/or a corresponding relationship between the preset sensing unit and the processing unit.
Optionally, the processing unit comprises a computing unit and a storage unit;
the computing unit is used for carrying out data processing on at least one unit value of the received one or more sensing units and/or at least one stored value of the storage unit by adopting a preset algorithm;
and the storage unit is used for storing at least one unit value of one or more sensing units and/or at least one data processed by one or more computing units.
Optionally, the processing unit includes a computing unit and a storage unit connected to each other, and the one or more sensing units are respectively connected to the computing unit;
the computing unit is used for receiving the unit values sent by the one or more sensing units, respectively processing data based on the unit values and the storage values of the storage units, and sending the processed data to the storage units;
the storage unit is used for sending the processed data to the receiving part.
Optionally, the processing unit includes a computing unit and a storage unit connected to each other, and the sensing unit is connected to the storage unit respectively;
the storage unit is used for receiving at least one unit value sent by each sensing unit;
and the computing unit is used for processing by adopting a preset algorithm according to at least one unit value of each sensing unit stored in the storage unit and sending the processed data to the receiving part.
Optionally, the processing unit comprises a plurality of processing sub-modules connected in sequence; the sensing units are respectively connected with the processing sub-modules at the head end;
each processing submodule is used for calculating in sequence based on the unit value sent by the induction unit, generating preprocessed data and sending the preprocessed data to the receiving part.
Optionally, the processing sub-modules respectively include a computing unit and a storage unit connected to each other, between adjacent processing sub-modules, the computing unit of one is connected to the storage unit of the other, and the sensing unit is respectively connected to the computing unit of the processing sub-module at the head end;
each calculating unit is used for sequentially calculating and generating preprocessed data based on the corresponding unit value or the data in the storage unit and sending the preprocessed data to the receiving part;
and the storage unit is used for receiving and storing the data generated by the calculation of the corresponding calculation unit.
Optionally, the processing unit includes a plurality of first computing units, each of the first computing units is correspondingly connected with a storage unit, and any sensing unit is connected with each of the first computing units;
the first calculation unit is used for receiving the unit values sent by the induction units, processing the unit values meeting the preset processing conditions and/or the stored values of the corresponding storage units and sending the processed data to the corresponding storage units;
and a storage unit for storing the corresponding processed data and transmitting the processed data to the receiving unit.
Optionally, the processing unit includes a second computing unit and a plurality of first computing units, the first computing units are respectively and correspondingly connected with a storage unit, any sensing unit is respectively connected with each first computing unit, and each storage unit is respectively connected with the second computing unit;
the first calculating unit is used for receiving the unit values sent by the sensing units, calculating based on the unit values meeting the preset processing conditions and/or the stored values of the corresponding storage units, generating intermediate data and sending the intermediate data to the corresponding storage units;
the storage unit is used for storing corresponding intermediate data and sending the intermediate data to the second calculation unit;
and a second calculation unit configured to generate the preprocessed data based on the intermediate data calculation and to transmit the preprocessed data to the receiving unit.
Optionally, the processing unit includes a plurality of computing units and storage units, the computing units are respectively connected with the sensing units in a one-to-one correspondence manner, the computing units are connected with the storage units in a one-to-one correspondence manner, each computing unit includes at least one computing module, and the computing modules are respectively connected with the corresponding sensing units and the corresponding storage units;
the calculation module is used for receiving the unit value sent by the corresponding induction unit, calculating based on the unit value to generate preprocessed data, and sending the preprocessed data to the corresponding storage unit, wherein each calculation module of the same calculation unit adopts different algorithms to calculate;
and the storage unit is used for storing the corresponding preprocessed data and sending the preprocessed data to the receiving part.
Optionally, the processing unit includes a control unit and a plurality of computing units, the sensing units are connected with the computing units in a one-to-one correspondence manner, the computing units are respectively connected with the control unit, and the control unit is respectively connected with the sensing units;
the sensing unit is used for receiving an external signal, converting the external signal into a unit value and sending the unit value to the corresponding calculating unit;
the calculating unit is used for receiving the unit value sent by the corresponding sensing unit, processing the unit value by adopting a preset algorithm and sending the processed data to the control unit;
and the control unit is used for controlling the corresponding induction unit to send the unit value to the receiving part when the processed data meet the preset conditions.
Optionally, the storage unit comprises at least one of a capacitor, a latch, a flash memory, and a buffer.
Optionally, the preset algorithm includes at least one of a numerical operation, a logical operation, and a sorting operation.
Optionally, the sensing unit, the calculating unit and the storing unit are arranged on at least one integrated circuit.
In another aspect of the embodiments of the present invention, there is provided a data output method of an array type sensor chip, wherein the array type sensor chip includes: the processing unit and the plurality of sensing units are respectively connected with the processing unit; the method comprises the following steps:
the processing unit is used for receiving unit values sent by all the sensing units according to a preset rule, wherein the unit values are obtained by the sensing units according to external signal conversion;
the processing unit is used for carrying out data preprocessing on the unit value by adopting a preset algorithm; and controlling the induction unit to send a unit value to the receiving part when the processed data or the processing result meets the preset condition.
The embodiment of the invention has the beneficial effects that:
the array type sensor chip provided by the embodiment of the invention comprises a processing unit and a plurality of sensing units, wherein the sensing units are respectively connected with the processing unit. The sensing unit can be used for receiving an external signal, converting the external signal into a unit value and sending the unit value to the processing unit according to a preset rule; the processing unit may be configured to perform data processing on the unit value by using a preset algorithm, and then, control the sensing unit to send the unit value to the receiving portion when the processed data is sent to the receiving portion or a processing result satisfies a preset condition. By the array type sensor chip, after the received external signal is converted into the unit value, the corresponding unit value sent according to the preset rule is subjected to data processing according to the preset algorithm, and the processed data is sent to the receiving part. The array sensor chip is used for preprocessing the unit value obtained by converting the external signal and then transmitting the processed data to the receiving part, so that the data processing of the receiving part can be shared, the data calculation amount processed by the receiving part is reduced, and the response speed of the receiving part can be improved. Or after the received external signal is converted into the unit value through the array type sensor chip, the corresponding unit value is subjected to data processing according to a preset algorithm according to a preset rule, so that the corresponding sensing unit is controlled to send the unit value to the receiving part according to the result after the data processing and a preset condition. In this way, the number of cell values transmitted from the array sensor chip to the receiving unit can be reduced, the data processing amount of the receiving unit can be reduced, and the response speed of the receiving unit can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic diagram of an array-type sensor chip according to an embodiment of the present invention;
fig. 2 is a second schematic structural diagram of an array-type sensor chip according to an embodiment of the invention;
FIG. 3 is a third schematic structural diagram of an array type sensor chip according to an embodiment of the present invention;
FIG. 4 is a fourth schematic diagram of an array sensor chip according to an embodiment of the present invention;
FIG. 5 is a fifth schematic view of an array sensor chip according to an embodiment of the present invention;
FIG. 6 is a sixth schematic view of an array sensor chip according to an embodiment of the present invention;
FIG. 7 is a seventh schematic diagram illustrating an array-type sensor chip according to an embodiment of the present invention;
FIG. 8 is an eighth schematic diagram of an array-type sensor chip according to an embodiment of the present invention;
FIG. 9 is a ninth schematic diagram illustrating an array sensor chip according to an embodiment of the present invention;
FIG. 10 is a cross-sectional view of an array type sensor chip according to an embodiment of the present invention;
fig. 11 is a flowchart illustrating a data output method of an array sensor chip according to an embodiment of the present invention.
Icon: 110-a sensing unit; 120-a processing unit; 121-a calculation unit; 1210-a calculation module; 1211 — a first calculation unit; 1212-a second calculation unit; 122-a storage unit; 130-a control unit; 210-a receiving section.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
An embodiment of the present invention provides an array type sensor chip, as shown in fig. 1, which may include: a processing unit 120 and a plurality of sensing units 110, wherein the plurality of sensing units 110 are respectively connected with the processing unit 120.
The sensing unit 110 is configured to receive an external signal, convert the external signal into a unit value, and send the unit value to the processing unit 120 according to a preset rule; the processing unit 120 is configured to perform data processing on the cell value by using a preset algorithm; and when the processed data is transmitted to the receiving part 210 or the processing result meets a preset condition, the sensing unit 110 is controlled to transmit a unit value to the receiving part 210.
The plurality of sensing units 110 of the array type sensor chip are arranged in an array type, and the array type sensor chip can be an optical sensor for photosensitive imaging, an acoustic sensor for sound detection and the like according to different actual requirements and application scenes. The sensing unit 110 may be a piezoresistive element, a piezoelectric element, a photoelectric element, a capacitive element, or an electromagnetic element, according to the type of the array sensor chip, so that the array sensor chip can achieve the corresponding external signal sensing function. For example, when the array type sensor chip is an optical sensor, the sensing unit 110 may be correspondingly disposed as a photoelectric element (photodiode, photo resistor, or the like) as a pixel of the array type sensor chip. As another example, when the array-type sensor chip is an acoustic sensor, the sensing unit 110 may be an element capable of converting an acoustic signal into an electrical signal, such as a microphone.
In practical applications, the receiving unit 210 for receiving the data output from the array sensor chip may be a processor (e.g., a mobile phone, a digital camera, a computer, etc.) of an electronic device, a data processing center, etc., depending on the scene, and is not limited herein.
It should be noted that the sensing unit 110 sends the unit value to the processing unit 120 according to a preset rule, where the preset rule may be a screening rule for the sensing unit 110, that is, a rule for determining whether the sensing unit 110 sends the unit value to the processing unit 120, for example, only a part of the sensing unit 110 is required to send the unit value to the processing unit 120 each time. The preset rule may also add time domain limitation, for example, different sensing units 110 send unit values to the processing unit 120 at different time points. Or the preset rule may also be a rule for transmitting the cell values by the sensing unit 110, for example, the cell values are sequentially transmitted to the processing unit 120 in a form of row scanning or column scanning according to the array of the sensing unit 110. Therefore, in summary, in the embodiment of the present invention, the preset rule for the sensing unit 110 to send the unit value to the processing unit 120 is not specifically limited, and a person skilled in the art may adaptively set or configure the preset rule for the sensing unit 110 to send the unit value to the processing unit 120 according to different preset algorithms for the processing unit 120 to process the unit value, wherein for implementing the preset rule, that is, in a manner of controlling the unit value sent by the sensing unit 110 according to the preset rule, a control switch may be disposed on a line connecting each sensing unit 110 and the processing unit 120, and in a manner of controlling the on/off of the control switch according to the preset rule, may be implemented. Of course, if the sensing unit 110 is wirelessly connected to the processing unit 120, the sensing unit 110 may transmit the unit value according to the preset rule by controlling the signal transmission port of the sensing unit 110, which is not limited herein.
In the embodiment of the present invention, when the processing unit 120 sends the processed data to the receiving portion 210, the preset algorithm for the processing unit 120 to perform data processing on the unit value may be configured according to the calculation process of the target value to be finally obtained by the receiving portion 210, for example, the processing unit 120 may calculate the received unit value through the preset algorithm to obtain an intermediate value required in the calculation process of the receiving portion 210, and the processing unit 120 can make the receiving portion 210 directly perform corresponding calculation according to the intermediate value to finally obtain the target value by sending the intermediate value to the receiving portion 210, so that the calculation amount of the receiving portion 210 is reduced, and the receiving portion 210 can have a faster response speed.
When the data processed by the processing unit 120 satisfies the preset condition, the sensing unit 110 is controlled to send the unit value to the receiving unit 210, and the preset algorithm for the processing unit 120 to process the unit value may be configured according to the preset condition. For example, if the preset condition is a limiting condition of the signal-to-noise ratio of the unit value corresponding to each sensing unit 110, the processing unit 120 may calculate the signal-to-noise ratio of the unit value sent by each sensing unit 110 according to a preset algorithm, so as to filter the signal-to-noise ratio corresponding to each unit value according to the preset condition, so that the sensing unit 110 corresponding to the unit value whose signal-to-noise ratio satisfies the preset condition sends the corresponding unit value to the receiving portion 210. Of course, the preset condition may also be other parameter limiting conditions of the unit value, and is not limited herein, and accordingly, the preset algorithm of the processing unit 120 may also be other parameters for calculating the unit value.
The array-type sensor chip provided by the embodiment of the invention comprises a processing unit 120 and a plurality of sensing units 110, wherein the plurality of sensing units 110 are respectively connected with the processing unit 120. The sensing unit 110 may be configured to receive an external signal, convert the external signal into a unit value, and send the unit value to the processing unit 120 according to a preset rule; the processing unit 120 may be configured to perform data processing on the cell value by using a preset algorithm, and then transmit the processed data to the receiving unit 210, or control the sensing unit 110 to transmit the cell value to the receiving unit 210 when a processing result meets a preset condition. With the array type sensor chip, after the received external signal is converted into a unit value, data processing is performed on the corresponding unit value transmitted according to a preset rule according to a preset algorithm, so that the processed data is transmitted to the receiving part 210. By preprocessing the unit value converted from the external signal and then transmitting the processed data to the receiving unit 210, the array sensor chip can share the data processing of the receiving unit 210 to reduce the amount of data calculation processed by the receiving unit 210, thereby improving the response speed of the receiving unit 210. Or after the received external signal is converted into the cell value by the array type sensor chip, the corresponding cell value is subjected to data processing according to a preset algorithm according to a preset rule, so that the corresponding sensing unit 110 is controlled to transmit the cell value to the receiving part 210 according to a result after the data processing and a preset condition. In this way, the number of cell values transmitted from the array sensor chip to the receiver 210 can be reduced, the data processing amount of the receiver 210 can be reduced, and the response speed of the receiver 210 can be improved.
Optionally, the preset rule includes a preset adjustment rule of the connection relationship and/or the corresponding relationship between the sensing unit 110 and the processing unit 120.
The corresponding relationship may be the sequence and the number of times of sending the unit value between each sensing unit 110 and the processing unit 120. The connection relationship may be the connection between the sensing unit 110 and the processing unit 120.
The preset adjustment rule may be a rule for adjusting the corresponding relationship and/or the connection relationship, so that the policy for the sensing unit 110 of the array sensor chip to send the unit value to the processing unit 120 can be dynamically adjusted according to the preset adjustment rule, so that the processing unit 120 can perform complex operation on the unit value sent by the sensing unit 110.
Alternatively, as shown in fig. 2, the processing unit 120 includes a calculation unit 121 and a storage unit 122.
A calculating unit 121, configured to perform data processing on the received at least one cell value of the one or more sensing units 110 and/or at least one stored value of the storing unit 122 by using a preset algorithm; the storage unit 122 is configured to store at least one unit value of the one or more sensing units 110 and/or at least one data processed by the one or more calculating units 121.
The processing unit 120 is provided with modules including a calculation unit 121 and a storage unit 122, which enable relatively complex operations to be performed when processing the received cell values. For example, the cell value is received and processed by the calculation unit 121, and then the calculation result is stored to the storage unit 122. Alternatively, the calculating unit 121 receives and processes the unit value, and stores the calculation intermediate result in the storage unit 122, so that the calculating unit 121 can perform complex operations of multiple steps according to multiple unit values sent by the sensing unit 110 at different times by calling the intermediate result stored in the storage unit 122 during subsequent calculations performed by the calculating unit 121. The storage unit 122 may further store parameters required by the calculation unit 121 for the calculation unit 121 to call. Also, the cell value of the sensing unit 110 may be sent to the storage unit 122 or sent to the calculating unit 121, and those skilled in the art may set the cell value according to a specific configuration of a preset algorithm for processing the cell value by the processing unit 120.
Alternatively, as shown in fig. 2, the processing unit 120 includes a calculating unit 121 and a storage unit 122 connected to each other, and the one or more sensing units 110 are respectively connected to the calculating unit 121.
A calculating unit 121, configured to receive the cell values sent by one or more sensing units 110, perform data processing based on the cell values and the stored values of the storage unit 122, and send the processed data to the storage unit 122; the storage unit 122 is used to transmit the processed data to the receiving unit 210.
In practical applications, the received cell value may be subjected to data processing by the calculating unit 121, and during the processing of the cell value, the intermediate result may also be stored in the storage unit 122, so that the calculating unit 121 may call the intermediate result during the subsequent processing of the cell value. The storage unit 122 may further store parameters required in the process of processing the unit value by the calculation unit 121, so that the calculation unit 121 can call the corresponding parameters, where the storage in the storage unit 122 is not specifically limited.
For example, the sensing unit 110 connected to the calculating unit 121 may sequentially send unit values to the calculating unit 121 in regions according to different regions arranged in an array thereof, so that the calculating unit 121 can process the unit value corresponding to the sensing unit 110 of a corresponding one of the regions at a time, send the processing result after each processing to the storage unit 122, and send the processed data to the receiving unit 210 through the storage unit 122, so as to reduce the amount of operation of data processing of the receiving unit 210, thereby enabling the array type sensor chip to implement a partition scanning function while improving the response speed of the receiving unit 210 by preprocessing the unit values. Moreover, after the calculating unit 121 processes the cell value of the sensing unit 110 of the corresponding one area each time, the processing result is sent to the storage unit 122, and when the calculating unit 121 processes the cell value corresponding to the sensing unit 110 of the other area, the calculating unit 121 may call the processing result stored in the storage unit 122 to perform the corresponding cell value processing.
Alternatively, as shown in fig. 3, the processing unit 120 includes a computing unit 121 and a storage unit 122 connected to each other, and the sensing unit 110 is connected to the storage unit 122, respectively.
A storage unit 122, configured to receive at least one unit value sent by each sensing unit 110; the calculating unit 121 is configured to perform processing according to a preset algorithm based on at least one cell value of each sensing unit 110 stored in the storage unit 122, and send the processed data to the receiving unit 210.
In practical applications, the storage unit 122 may be connected to the sensing unit 110 to store the unit value transmitted by the sensing unit 110 according to a preset rule, so that the calculating unit 121 can process a plurality of unit values transmitted by the sensing unit 110 for a plurality of times (of course, one unit value transmitted at a time may also be used). When the sensing unit 110 sends a plurality of unit values, the sensing unit 110 may send the unit values to the storage unit 122 a plurality of times according to a time sequence, and the calculating unit 121 may process the unit values stored in the storage unit 122 after a period of time, or may process the unit values stored in the storage unit 122 each time the sensing unit 110 sends. And is not particularly limited herein.
For example, the sensing unit 110 may transmit the cell value to the storage unit 122 a plurality of times in time sequence, and after the storage unit 122 stores the plurality of cell values transmitted by the sensing unit 110 a plurality of times, the calculating unit 121 processes the plurality of cell values according to the plurality of cell values transmitted by the sensing unit 110 stored in the storage unit 122 to obtain processed data and transmits the processed data to the receiving unit 210, so as to reduce the amount of computation and the amount of reception of the cell value by the receiving unit 210 and improve the response speed of the receiving unit 210.
For example, the array type sensor chip is used for laser ranging, the external signal received by the sensing unit 110 may be ranging laser reflected by the target object, the ranging laser may be transmitted multiple times, and accordingly, the sensing unit 110 may receive the ranging laser multiple times and convert the ranging laser into a unit value to be transmitted to the calculating unit 121. In this case, the processing of the plurality of cell values transmitted by the sensing unit 110 in time series by the calculating unit 121 may be to calculate the flight times of the corresponding ranging lasers from the cell values of different time nodes, and transmit the mode (i.e., the flight time with the highest frequency of occurrence) in the set to the receiving unit 210 from the set of the obtained flight times, so that the receiving unit 210 only needs to calculate the target distance from the received flight time, thereby reducing the amount of calculation of the receiving unit 210 and improving the response speed. In addition, the laser ranging in a DTOF (direct time of flight) mode can be realized through the method.
Optionally, the processing unit 120 includes a plurality of processing sub-modules connected in sequence; the sensing units 110 are respectively connected with the processing submodules of the head end.
Each processing sub-module is configured to sequentially calculate based on the cell value transmitted by the sensing unit 110, generate preprocessed data, and transmit the preprocessed data to the receiving unit 210.
By configuring the processing unit 120 to be composed of a plurality of processing sub-modules connected to each other, the unit values sent by the sensing unit 110 can be sequentially calculated by calling each processing sub-module to each other, so as to implement a neural network algorithm (preset algorithm).
Illustratively, as shown in fig. 4, the processing sub-modules respectively include a computing unit 121 and a storage unit 122 connected to each other, between adjacent processing sub-modules, the computing unit 121 of one is connected to the storage unit 122 of the other, and the sensing unit 110 is respectively connected to the computing unit 121 of the processing sub-module at the head end.
Each calculation unit 121 for sequentially calculating and generating preprocessed data based on the corresponding cell value or data in the storage unit 122, and transmitting the preprocessed data to the reception unit 210; and the storage unit 122 is used for receiving and storing the data generated by the calculation of the corresponding calculation unit 121.
For example, the calculation unit 121 connected to the sensing unit 110 may receive and calculate the unit value sent by the sensing unit 110, and send the calculation result to the two storage units 122 connected to the same (corresponding to the same-level storage unit 122 and the storage unit 122 corresponding to the next-level calculation unit 121), while the next-level calculation unit 121 may continue to perform corresponding calculation according to the stored value stored in the corresponding same-level storage unit 122 until the last calculation unit 121 completes the calculation and then sends the processed result to the receiving unit 210, thereby performing multi-level calculation on the unit value sent by the sensing unit 110, so as to implement the neural network algorithm. Each storage unit 122 may further store a weight value required for calculation by the corresponding calculation unit 121 of the same stage, and the like, which is not limited herein, and those skilled in the art may preset data in the storage unit 122 according to an algorithm actually calculated by each calculation unit 121.
Optionally, as shown in fig. 5, the processing unit 120 includes a plurality of first calculating units 1211, each of the first calculating units 1211 is connected to the storage unit 122 correspondingly, and any sensing unit 110 is connected to each of the first calculating units 1211.
A first calculating unit 1211, configured to receive the cell values sent by each sensing unit 110, process the cell values meeting the preset processing condition and/or the stored values of the corresponding storage units 122, and send the processed data to the corresponding storage units 122; the storage unit 122 stores the corresponding processed data, and transmits the processed data to the receiving unit 210.
Illustratively, the storage unit 122 may include both flash memory and cache memory.
Here, the unit values satisfying the preset processing condition may be processing conditions set according to characteristics of the corresponding sensing units 110 to which the unit values are transmitted, and at this time, since there is a general variation in the unit values transmitted by the same sensing unit 110 each time, characteristics of the unit values calculated and processed by the first calculation unit 1211 each time may be different. Of course, the processing conditions may be set according to the characteristics of the received cell values, and in this case, since the cell values transmitted by the same sensing unit 110 at each time generally vary, the sensing unit 110 corresponding to the cell value calculated and processed by the first calculating unit 1211 at each time may be different.
The first calculation unit 1211 processes the cell values satisfying the preset processing conditions and/or the stored values of the corresponding storage unit 122, and thus the cell values can be filtered by the preset processing conditions, thereby further reducing the amount of data to be transmitted to the reception unit 210 and improving the response speed of the reception unit 210. Moreover, the preset processing conditions corresponding to each first calculating unit 1211 can also be set to be dynamically adjusted, so that the first calculating unit 1211 calculates only the cell values corresponding to a part of the sensing units 110 at a time according to the preset processing conditions, and thus calculates the cell values corresponding to different sensing units 110 for multiple times, so as to perform convolution calculation on the cell values sent by the sensing units 110. The storage unit 122 may further store therein a corresponding parameter required for the calculation by the first calculation unit 1211.
Optionally, as shown in fig. 6, the processing unit 120 includes a second calculating unit 1212 and a plurality of first calculating units 1211, the first calculating units 1211 are respectively connected to the storage units 122 correspondingly, any sensing unit 110 is respectively connected to each first calculating unit 1211, and each storage unit 122 is respectively connected to the second calculating unit 1212.
A first calculating unit 1211, configured to receive the cell values sent by each sensing unit 110, perform calculation based on the cell values satisfying the preset processing condition and/or the stored values of the corresponding storage units 122, generate intermediate data, and send the intermediate data to the corresponding storage units 122; the storage unit 122 is configured to store corresponding intermediate data, and send the intermediate data to the second computing unit 1212; the second calculation unit 1212 is configured to calculate and generate preprocessed data based on each intermediate data, and to transmit the preprocessed data to the reception unit 210.
Illustratively, the storage unit 122 may include both flash memory and cache memory.
Here, the unit values satisfying the preset processing condition may be processing conditions set according to characteristics of the corresponding sensing units 110 to which the unit values are transmitted, and at this time, since there is a general variation in the unit values transmitted by the same sensing unit 110 each time, characteristics of the unit values calculated and processed by the first calculation unit 1211 each time may be different. Of course, the processing conditions may be set according to the characteristics of the received cell values, and in this case, since the cell values transmitted by the same sensing unit 110 at each time generally vary, the sensing unit 110 corresponding to the cell value calculated and processed by the first calculating unit 1211 at each time may be different.
The first calculation unit 1211 processes the cell values satisfying the preset processing conditions and/or the corresponding storage values of the storage unit 122, and the second calculation unit 1212 calculates the calculation results in the storage unit 122 corresponding to the storage values calculated by the first calculation unit 1211, so that the cell values can be filtered by the preset processing conditions, thereby further reducing the amount of data transmitted to the receiving unit 210 and improving the response speed of the receiving unit 210. Moreover, the preset processing conditions corresponding to each first calculating unit 1211 can also be set to be dynamically adjusted, so that the first calculating unit 1211 calculates only the cell values corresponding to a part of the sensing units 110 at a time according to the preset processing conditions, and thus calculates the cell values corresponding to different sensing units 110 for multiple times, so as to perform convolution calculation on the cell values sent by the sensing units 110. The storage unit 122 may further store therein a corresponding parameter required for the calculation by the first calculation unit 1211. By calculating the results calculated by the first calculation units 1211 through the second calculation unit 1212, the mutual operation of the calculation results between the first calculation units 1211 can be realized, thereby realizing a more complicated convolution operation.
Optionally, as shown in fig. 7, the processing unit 120 includes a plurality of calculating units 121 and a storage unit 122, the calculating units 121 are respectively connected to the sensing units 110 in a one-to-one correspondence, the calculating units 121 are connected to the storage unit 122 in a one-to-one correspondence, the calculating unit 121 includes at least one calculating module 1210, and the calculating module 1210 is respectively connected to the corresponding sensing units 110 and the storage unit 122.
The calculation modules 1210 are configured to receive the unit values sent by the corresponding sensing units 110, perform calculation based on the unit values to generate preprocessed data, and send the preprocessed data to the corresponding storage units 122, where each calculation module 1210 of the same calculation unit 121 performs calculation by using different algorithms; and a storage unit 122 for storing the corresponding preprocessed data and transmitting the preprocessed data to the receiving unit 210.
By processing the cell value transmitted by the corresponding sensing cell 110 by the calculating module 1210 of each calculating cell 121, each calculating cell 121 can process only one corresponding sensing cell 110, thereby reducing the amount of data processing operation of each calculating cell 121, increasing the corresponding speed of each calculating cell 121, and increasing the response speed of the array-type sensor chip. When the number of the calculation modules 1210 of each calculation unit 121 is two or more, the calculation modules 1210 may perform different algorithm processing on the cell values transmitted by the corresponding sensing units 110, thereby performing preprocessing of different calculations performed on the cell values of the sensing units 110 by the receiving unit 210, and further reducing the computation load of the receiving unit 210 that needs to perform multiple calculations on each cell value. For example, each calculating unit 121 is provided with two calculating modules 1210, one of which is used for calculating a mean value of the cell value, and the other is used for calculating a variance of the cell value, so that the receiving unit 210 can directly calculate parameters such as the signal-to-noise ratio of the sensing unit 110 corresponding to the corresponding cell value according to the received mean value and variance, and the calculation amount of the receiving unit 210 for directly calculating the signal-to-noise ratio according to the cell value is reduced.
Optionally, as shown in fig. 8, the processing unit 120 includes a control unit 130 and a plurality of computing units 121, the sensing units 110 are connected to the computing units 121 in a one-to-one correspondence, the computing units 121 are respectively connected to the control unit 130, and the control units 130 are respectively connected to the sensing units 110.
The sensing unit 110 is configured to receive an external signal, convert the external signal into a unit value, and send the unit value to the corresponding calculating unit 121; the calculating unit 121 is configured to receive the unit value sent by the corresponding sensing unit 110, process the unit value by using a preset algorithm, and send the processed data to the control unit 130; and a control unit 130 for controlling the corresponding sensing unit 110 to transmit a unit value to the receiving unit 210 when the processed data satisfies a preset condition.
The control unit 130 may control a control switch, such as a Metal-Oxide-Semiconductor (MOS) transistor, on a line connected between each sensing unit 110 and the receiving unit 210, so as to control the corresponding sensing unit 110 to transmit a unit value to the receiving unit 210. By this means, it is possible to control the corresponding sensing unit 110 to transmit the unit value to the receiving unit 210 more conveniently and accurately according to the processing result of the unit value.
For example, the calculating unit 121 may calculate the signal-to-noise ratio of the cell value transmitted by the corresponding sensing unit 110, and the preset algorithm may calculate a variance and a mean value of a plurality of cell values transmitted by the same sensing unit 110, and calculate the signal-to-noise ratio according to the variance and the mean value, so that the control unit 130 can screen each sensing unit 110 according to the signal-to-noise ratio (accordingly, whether a preset condition is greater than the preset signal-to-noise ratio), and make the sensing unit 110 with the relatively high signal-to-noise ratio of the transmitted cell value transmit the cell value to the receiving portion 210, so that not only the amount of data transmitted to the receiving portion 210 can be reduced to improve the response speed of the receiving portion 210, but also adverse effects of interference signals on the processing result when the receiving portion 210 processes data can be reduced. Whether the processed data meets the preset condition may be determined in the calculating unit 121, or may be determined in the controlling unit 130, which is not limited herein.
In the embodiment of the present invention, it should be noted that the memory cells 122 may include one of a capacitor, a latch, a flash memory, a buffer, or a combination of two or more, which is not limited herein.
Also, the preset algorithm for the processing unit 120 to perform data processing on the unit value may be preset according to an intermediate calculation process of calculating the target value by the receiving part 210, or according to a specific setting of a preset condition. Illustratively, at least one of a numerical operation, a logical operation, and a sorting operation may be included.
The numerical operation may be four arithmetic operations, mean calculation, variance calculation, convolution operation, fourier transform, and the like performed on the cell value. Of course, in the embodiment of the present invention, the numerical operation may also be other operations performed on the unit value, for example, partial operations of convolution operation or fourier transform, a combination of the above example operations, and the like, which is not limited herein.
It is further noted that the sensing unit 110, the calculating unit 121 and the storing unit 122 may be disposed on at least one integrated circuit.
For example, as shown in fig. 9, the sensing unit 110, the calculating unit 121, and the storage unit 122 are disposed on the same integrated circuit and distributed according to a certain layout. Of course, as shown in fig. 10, the sensing unit 110, the calculating unit 121, and the storing unit 122 may also be disposed on different integrated circuits, respectively, and are not limited herein.
The sensing units 110 may be arranged in the same area in an array.
In another aspect of the embodiments of the present invention, a data output method for an array type sensor chip is provided, which can be applied to any one of the array type sensor chips. The array type sensor chip may include: a processing unit 120 and a plurality of sensing units 110, wherein the plurality of sensing units 110 are respectively connected with the processing unit 120.
As shown in fig. 11, a data output method of an array type sensor chip according to an embodiment of the present invention may include:
s11: the processing unit receives the unit values sent by the sensing units according to the preset rule. Wherein, the unit value is obtained by converting the sensing unit according to the external signal.
S12: the processing unit adopts a preset algorithm to carry out data preprocessing on the unit value; and controlling the induction unit to send a unit value to the receiving part when the processed data or the processing result meets the preset condition.
The method comprises the steps that firstly, an external signal is received through a sensing unit of an array type sensor chip, the external signal is converted into a unit value, and the unit value is sent to a processing unit according to a preset rule; and then, performing data preprocessing on the unit value by adopting a preset algorithm through a processing unit of the array type sensor chip, and then, controlling the sensing unit to send the unit value to the receiving part when the processed data or the processing result meets a preset condition. By the method, after the received external signal is converted into the unit value, the corresponding unit value sent according to the preset rule is subjected to data processing according to the preset algorithm, and the processed data are sent to the receiving part. Therefore, the array sensor chip sends the processed data to the receiving part after preprocessing the unit value obtained by converting the external signal, and can share the data processing of the receiving part to reduce the data processing operation amount of the receiving part, thereby improving the response speed of the receiving part. Or by the method, after the received external signal is converted into the unit value, the corresponding unit value is subjected to data processing according to a preset algorithm according to a preset rule, so that the corresponding induction unit is controlled to send the unit value to the receiving part according to the result after the data processing and the preset condition. Therefore, the number of unit values transmitted to the receiving unit by the array type sensor chip can be reduced, the data processing amount of the receiving unit is reduced, and the response speed of the receiving unit is improved.
Optionally, the preset rule includes a preset adjustment rule of a connection relationship and/or a corresponding relationship between the preset sensing unit and the processing unit.
Optionally, the processing unit comprises a computing unit and a storage unit; the processing unit may perform data processing on the cell values by using a preset algorithm, and the data processing may include:
the computing unit performs data processing on the received at least one unit value of the one or more sensing units and/or at least one stored value of the storage unit by adopting a preset algorithm.
The storage unit stores at least one unit value of one or more sensing units and/or at least one data processed by one or more computing units.
Optionally, the processing unit includes a computing unit and a storage unit connected to each other, and the one or more sensing units are respectively connected to the computing unit; the processing unit is used for carrying out data preprocessing on the unit value by adopting a preset algorithm; the transmitting the processed data to the receiving unit may include:
and the calculating unit is used for receiving the unit values sent by the one or more sensing units, respectively processing data based on the unit values and the storage values of the storage units, and sending the processed data to the storage units.
And a storage unit for transmitting the processed data to the receiving unit.
Optionally, the processing unit includes a computing unit and a storage unit connected to each other, and the sensing unit is connected to the storage unit respectively; the processing unit is used for carrying out data preprocessing on the unit value by adopting a preset algorithm; the transmitting the processed data to the receiving unit may include:
and the storage unit receives at least one unit value sent by each sensing unit.
And the calculating unit is used for processing by adopting a preset algorithm according to at least one unit value of each sensing unit stored in the storage unit and sending the processed data to the receiving part.
Optionally, the processing unit comprises a plurality of processing sub-modules connected in sequence; the sensing units are respectively connected with the processing sub-modules at the head end; the processing unit is used for carrying out data preprocessing on the unit value by adopting a preset algorithm; the transmitting the processed data to the receiving unit may include:
each processing submodule sequentially calculates based on the unit value sent by the induction unit, generates preprocessed data, and sends the preprocessed data to the receiving part.
Optionally, the processing sub-modules respectively include a computing unit and a storage unit connected to each other, between adjacent processing sub-modules, the computing unit of one is connected to the storage unit of the other, and the sensing unit is respectively connected to the computing unit of the processing sub-module at the head end; each processing submodule sequentially calculates based on the unit value transmitted by the sensing unit, generates preprocessed data, and transmits the preprocessed data to the receiving part, and the method may include:
each calculation unit sequentially calculates and generates preprocessed data based on the corresponding cell value or data in the storage unit, and transmits the preprocessed data to the reception unit.
The storage unit receives and stores the data calculated by the corresponding calculation unit.
Optionally, the processing unit includes a plurality of first computing units, each of the first computing units is correspondingly connected with a storage unit, and any sensing unit is connected with each of the first computing units; the processing unit is used for carrying out data preprocessing on the unit value by adopting a preset algorithm; the transmitting the processed data to the receiving unit may include:
and the first calculating unit is used for receiving the unit values sent by the sensing units, processing the unit values meeting the preset processing conditions and/or the stored values of the corresponding storage units and sending the processed data to the corresponding storage units.
And a storage unit for storing the corresponding processed data and transmitting the processed data to the receiving unit.
Optionally, the processing unit includes a second computing unit and a plurality of first computing units, the first computing units are respectively and correspondingly connected with a storage unit, any sensing unit is respectively connected with each first computing unit, and each storage unit is respectively connected with the second computing unit; the processing unit is used for carrying out data preprocessing on the unit value by adopting a preset algorithm; the transmitting the processed data to the receiving unit may include:
and the first calculating unit is used for receiving the unit values sent by the sensing units, calculating based on the unit values meeting the preset processing conditions and/or the stored values of the corresponding storage units, generating intermediate data and sending the intermediate data to the corresponding storage units.
And the storage unit is used for storing the corresponding intermediate data and sending the intermediate data to the second calculation unit.
And a second calculation unit that generates the preprocessed data based on the intermediate data calculation and transmits the preprocessed data to the reception unit.
Optionally, the processing unit includes a plurality of computing units and storage units, the computing units are respectively connected with the sensing units in a one-to-one correspondence manner, the computing units are connected with the storage units in a one-to-one correspondence manner, each computing unit includes at least one computing module, and the computing modules are respectively connected with the corresponding sensing units and the corresponding storage units; the processing unit is used for carrying out data preprocessing on the unit value by adopting a preset algorithm; the transmitting the processed data to the receiving unit may include:
and the calculation module is used for receiving the unit value sent by the corresponding induction unit, calculating based on the unit value to generate preprocessed data, and sending the preprocessed data to the corresponding storage unit. Wherein, each calculation module of the same calculation unit adopts different algorithms to carry out calculation.
And a storage unit for storing the corresponding preprocessed data and transmitting the preprocessed data to the receiving unit.
Optionally, the processing unit includes a control unit and a plurality of computing units, the sensing units are connected with the computing units in a one-to-one correspondence manner, the computing units are respectively connected with the control unit, and the control unit is respectively connected with the sensing units; the processing unit is used for carrying out data preprocessing on the unit value by adopting a preset algorithm; the controlling the sensing unit to transmit the unit value to the receiving part when the processing result satisfies the preset condition may include:
and the sensing unit is used for receiving the external signal, converting the external signal into a unit value and sending the unit value to the corresponding calculating unit.
And the computing unit is used for receiving the unit value sent by the corresponding sensing unit, processing the unit value by adopting a preset algorithm and sending the processed data to the control unit.
And the control unit controls the corresponding sensing unit to send a unit value to the receiving part when the processed data meet the preset conditions.
Optionally, the preset algorithm includes at least one of a numerical operation, a logical operation, and a sorting operation.
The implementation of the relevant steps in the above method embodiments and the beneficial effects thereof can be referred to the relevant description in the array type sensor chip, and are not repeated herein.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (14)
1. An array-type sensor chip, wherein the array-type sensor chip is an optical imaging sensor chip, comprising: the sensing units are respectively connected with the processing unit;
the sensing unit is used for receiving an external signal, converting the external signal into a unit value and sending the unit value to the processing unit according to a preset rule;
the processing unit is used for carrying out data processing on the unit value by adopting a preset algorithm; sending processed data to a receiving part, wherein the processed data is an intermediate value obtained by performing data processing on the unit value by adopting the preset algorithm; or when the processing result meets a preset condition, controlling the induction unit corresponding to the unit value of which the processing result meets the preset condition to send the unit value to a receiving part;
the processing unit comprises a plurality of computing units and storage units, the computing units are respectively connected with the sensing units in a one-to-one correspondence manner, the computing units are connected with the storage units in a one-to-one correspondence manner, each computing unit comprises at least one computing module, and the computing modules are respectively connected with the corresponding sensing units and the corresponding storage units;
the calculation module is used for receiving the unit value sent by the corresponding induction unit, calculating based on the unit value to generate preprocessed data, and sending the preprocessed data to the corresponding storage unit, wherein each calculation module of the same calculation unit adopts different algorithms to calculate;
the storage unit is used for storing the corresponding preprocessed data and sending the preprocessed data to the receiving part.
2. The array-type sensor chip of claim 1, wherein the predetermined rule comprises a predetermined adjustment rule of a connection relationship and/or a correspondence relationship between the sensing unit and the processing unit.
3. The array-type sensor chip of claim 1, wherein the processing unit comprises a computing unit and a storage unit;
the computing unit is used for performing data processing on at least one received unit value of one or more sensing units and/or at least one stored value of the storage unit by adopting a preset algorithm;
the storage unit is used for storing at least one unit value of one or more sensing units and/or at least one data processed by one or more computing units.
4. The array-type sensor chip of claim 1, wherein the processing unit comprises a computing unit and a storage unit connected to each other, and one or more of the sensing units are respectively connected to the computing unit;
the computing unit is used for receiving the unit values sent by one or more sensing units, performing data processing based on the unit values and the storage values of the storage units respectively, and sending the processed data to the storage units;
the storage unit is used for sending the processed data to the receiving part.
5. The array-type sensor chip of claim 1, wherein the processing unit comprises a computing unit and a storage unit connected to each other, the sensing units being connected to the storage unit, respectively;
the storage unit is used for receiving at least one unit value sent by each sensing unit;
the calculating unit is configured to perform processing by using the preset algorithm according to at least one unit value of each sensing unit stored in the storage unit, and send the processed data to the receiving unit.
6. The array-type sensor chip of claim 1, wherein the processing unit comprises a plurality of processing sub-modules connected in sequence; the sensing units are respectively connected with the processing sub-modules at the head ends;
each processing submodule is used for calculating in sequence based on the unit values sent by the sensing units, generating preprocessed data and sending the preprocessed data to the receiving part.
7. The array-type sensor chip of claim 6, wherein the processing sub-modules respectively include a computing unit and a storage unit connected to each other, and between adjacent ones of the processing sub-modules, the computing unit of one is connected to the storage unit of the other, and the sensing units are respectively connected to the computing units of the processing sub-modules at the head end;
each calculating unit is used for sequentially calculating and generating preprocessed data based on the corresponding unit value or data in the storage unit and sending the preprocessed data to the receiving part;
and the storage unit is used for receiving and storing the data generated by the calculation of the corresponding calculation unit.
8. The array type sensor chip of claim 1, wherein the processing unit comprises a plurality of first computing units, each of the first computing units is correspondingly connected with a storage unit, and any one of the sensing units is connected with each of the first computing units;
the first calculating unit is used for receiving the unit values sent by the sensing units, processing the unit values meeting the preset processing conditions and/or the stored values of the corresponding storage units, and sending the processed data to the corresponding storage units;
the storage unit is used for storing the corresponding processed data and sending the processed data to the receiving part.
9. The array-type sensor chip of claim 1, wherein the processing unit comprises a second computing unit and a plurality of first computing units, the first computing units are respectively and correspondingly connected with a storage unit, any sensing unit is respectively connected with each first computing unit, and each storage unit is respectively connected with the second computing unit;
the first calculating unit is used for receiving the unit values sent by the sensing units, calculating based on the unit values meeting the preset processing conditions and/or the stored values of the corresponding storage units, generating intermediate data, and sending the intermediate data to the corresponding storage units;
the storage unit is used for storing the corresponding intermediate data and sending the intermediate data to the second calculation unit;
the second calculation unit is configured to calculate and generate preprocessed data based on each of the intermediate data, and to transmit the preprocessed data to the reception unit.
10. The array-type sensor chip of claim 1, wherein the processing unit comprises a control unit and a plurality of computing units, the sensing units are connected with the computing units in a one-to-one correspondence, the computing units are respectively connected with the control unit, and the control units are respectively connected with the sensing units;
the sensing unit is used for receiving an external signal, converting the external signal into a unit value and sending the unit value to the corresponding calculating unit;
the computing unit is used for receiving the unit value sent by the corresponding induction unit, processing the unit value by adopting a preset algorithm and sending processed data to the control unit;
and the control unit is used for controlling the corresponding induction unit to send the unit value to the receiving part when the processed data meet a preset condition.
11. The array-type sensor chip of any one of claims 3 to 5 and 7 to 9, wherein the storage unit comprises at least one of a capacitor, a latch, a flash memory, and a buffer.
12. The array-type sensor chip of claim 1, wherein the predetermined algorithm comprises at least one of a numerical operation, a logical operation, and a sequencing operation.
13. The array-type sensor chip of claim 3, wherein the sensing unit, the computing unit and the storage unit are disposed on at least one integrated circuit.
14. A data output method of an array type sensor chip, wherein the array type sensor chip is an optical imaging sensor chip, the array type sensor chip comprising: the sensing units are respectively connected with the processing unit; the method comprises the following steps:
the processing unit is used for receiving unit values sent by all the sensing units according to a preset rule, wherein the unit values are obtained by the sensing units according to external signal conversion;
the processing unit is used for carrying out data preprocessing on the unit value by adopting a preset algorithm; when the processed data or the processing result is sent to the receiving part and meets a preset condition, controlling the induction unit corresponding to the unit value of which the processing result meets the preset condition to send the unit value to the receiving part; the processed data is an intermediate value obtained by processing the unit value by adopting the preset algorithm;
the processing unit comprises a plurality of computing units and storage units, the computing units are respectively connected with the sensing units in a one-to-one correspondence manner, the computing units are connected with the storage units in a one-to-one correspondence manner, each computing unit comprises at least one computing module, and the computing modules are respectively connected with the corresponding sensing units and the corresponding storage units;
the calculation module receives the unit value sent by the corresponding induction unit, performs calculation based on the unit value to generate preprocessed data, and sends the preprocessed data to the corresponding storage unit, wherein each calculation module of the same calculation unit performs calculation by adopting different algorithms;
the storage unit stores the corresponding preprocessed data and transmits the preprocessed data to the receiving unit.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010385945.5A CN111562886B (en) | 2020-05-09 | 2020-05-09 | Array type sensor chip and data output method thereof |
| PCT/CN2020/137319 WO2021174961A1 (en) | 2020-03-06 | 2020-12-17 | Array-type sensor chip and data output method therefor |
| US17/908,091 US20230099051A1 (en) | 2020-03-06 | 2020-12-17 | Array-type sensor chip and data output method therefor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010385945.5A CN111562886B (en) | 2020-05-09 | 2020-05-09 | Array type sensor chip and data output method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111562886A CN111562886A (en) | 2020-08-21 |
| CN111562886B true CN111562886B (en) | 2022-03-04 |
Family
ID=72074610
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010385945.5A Active CN111562886B (en) | 2020-03-06 | 2020-05-09 | Array type sensor chip and data output method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111562886B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021174961A1 (en) * | 2020-03-06 | 2021-09-10 | 宁波飞芯电子科技有限公司 | Array-type sensor chip and data output method therefor |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104792826A (en) * | 2015-03-23 | 2015-07-22 | 中国农业大学 | System and method for detecting milk freshness based on electronic nose |
| CN107220704A (en) * | 2016-03-21 | 2017-09-29 | 杭州海存信息技术有限公司 | Integrated neural network processor containing three-dimensional storage array |
| CN109862011A (en) * | 2019-02-01 | 2019-06-07 | 华南理工大学 | A kind of environment of internet of things real-time monitoring system calculated based on mist |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11347994B2 (en) * | 2018-10-15 | 2022-05-31 | Intel Corporation | Weight prefetch for in-memory neural network execution |
-
2020
- 2020-05-09 CN CN202010385945.5A patent/CN111562886B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104792826A (en) * | 2015-03-23 | 2015-07-22 | 中国农业大学 | System and method for detecting milk freshness based on electronic nose |
| CN107220704A (en) * | 2016-03-21 | 2017-09-29 | 杭州海存信息技术有限公司 | Integrated neural network processor containing three-dimensional storage array |
| CN109862011A (en) * | 2019-02-01 | 2019-06-07 | 华南理工大学 | A kind of environment of internet of things real-time monitoring system calculated based on mist |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111562886A (en) | 2020-08-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111562886B (en) | Array type sensor chip and data output method thereof | |
| EP0448121A2 (en) | Electronic noise attenuation method and apparatus for use in effecting such method | |
| Cembrano et al. | A 1000 FPS at 128/spl times/128 vision processor with 8-bit digitized I/O | |
| CN114424240A (en) | Target detection method and device, equipment and storage medium | |
| EP0525543B1 (en) | Neural processor device | |
| Hindi et al. | Robust solutions to l/sub 1/, l/sub 2/, and l/sub/spl infin//uncertain linear approximation problems using convex optimization | |
| Liñán-Cembrano et al. | A 1000 FPS at 128× 128 vision processor with 8-bit digitized I/O | |
| CN113489925A (en) | Focal plane detector reading circuit for realizing convolution calculation | |
| US5195171A (en) | Data processing system | |
| KR20200068560A (en) | Neuromorphic arithmetic device and operating method thereof | |
| EP1708493A2 (en) | Signal processing apparatus, signal processing method, and noise reducing apparatus | |
| JPH02197953A (en) | Information processor and information processing method | |
| WO2020093669A1 (en) | Convolution block array for implementing neural network application and method using the same, and convolution block circuit | |
| CN112243119A (en) | White balance processing method and device, electronic equipment and storage medium | |
| US6526157B2 (en) | Image processing apparatus, image processing method and transmission medium | |
| WO2021174961A1 (en) | Array-type sensor chip and data output method therefor | |
| CN114298291A (en) | Model quantization processing system and model quantization processing method | |
| US5621474A (en) | Filter working on image digital signals for video appliances | |
| KR102094275B1 (en) | Image sensor and image recognition apparatus using the same | |
| EP4290411A1 (en) | Semiconductor chip, device and system comprising the semiconductor chip, and method for manufacturing the semiconductor chip or the system | |
| CN109218634B (en) | Electronic device including image signal processor | |
| CN111380568A (en) | Array type sensor and signal output method thereof | |
| CN112803921A (en) | Adaptive filter, method, medium, and electronic device | |
| US20240346303A1 (en) | Hardware Realization of Neural Networks Using Buffers | |
| CN111294512A (en) | Image processing method, image processing apparatus, storage medium, and image pickup apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |