CN113050872A - Data processing system on sensor, method thereof and de-identification sensing device - Google Patents
Data processing system on sensor, method thereof and de-identification sensing device Download PDFInfo
- Publication number
- CN113050872A CN113050872A CN202010298954.0A CN202010298954A CN113050872A CN 113050872 A CN113050872 A CN 113050872A CN 202010298954 A CN202010298954 A CN 202010298954A CN 113050872 A CN113050872 A CN 113050872A
- Authority
- CN
- China
- Prior art keywords
- data
- sensing
- decoding
- identified
- processing system
- 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.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 39
- 238000013503 de-identification Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims description 21
- 230000004044 response Effects 0.000 claims abstract description 22
- 238000010801 machine learning Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000004891 communication Methods 0.000 claims abstract 2
- 230000003287 optical effect Effects 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 230000006698 induction Effects 0.000 claims description 3
- 239000000758 substrate Substances 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 description 6
- 239000004033 plastic Substances 0.000 description 5
- 229920003023 plastic Polymers 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000000576 coating method Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 238000003672 processing method Methods 0.000 description 4
- 239000011248 coating agent Substances 0.000 description 3
- 230000001965 increasing effect Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000000985 reflectance spectrum Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- WFKWXMTUELFFGS-UHFFFAOYSA-N tungsten Chemical compound [W] WFKWXMTUELFFGS-UHFFFAOYSA-N 0.000 description 1
- 229910052721 tungsten Inorganic materials 0.000 description 1
- 239000010937 tungsten Substances 0.000 description 1
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
- G06F3/05—Digital input using the sampling of an analogue quantity at regular intervals of time, input from a/d converter or output to d/a converter
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
A data processing system on a sensor comprising: a de-identification sensing device and a decoding device. The de-identification sensing device is used for receiving sensing data of an object to be detected and processing the sensing data to generate de-identification data. The decoding device is in communication connection with the de-recognition sensing device and is used for generating decoding data according to the de-recognition data and decoding parameters, and the decoding parameters are obtained from the database after machine learning training. The de-identified sensing device includes an analog encoder for encoding sensed data to generate response data.
Description
Technical Field
The present invention relates to compressive sensing, and more particularly, to a data processing system on a sensor and a method thereof.
Background
In response to the sensing requirement of high resolution signals, the conventional micro spectrometer based on filters needs a large number of filters and sensing elements for capturing a large number of target wavelengths, and a non-ideal filtering mechanism necessitates signal reconstruction, which results in an increase in hardware cost and an increase in sensor size, and thus cannot realize the requirement of sensor miniaturization.
On the other hand, in the sensor chip architecture developed in the future, as the amount of processed data is increasing, the power consumption of data processing and the flow of data transmission are both increased. Although it is simple and convenient to transmit all the sensing data to the cloud server for processing, the burden of the cloud server is increased.
Disclosure of Invention
In view of the above, in order to reduce the large size and high cost of the sensor, the present invention provides a data processing system on the sensor and a method thereof. In addition, the invention can process the data in advance to the computing device on the sensor for computation, thereby effectively reducing the data transmission quantity and realizing the concept of edge computation of computing in the sensor.
According to an embodiment of the present invention, a data processing system on a sensor is described, including: a de-identification sensing device and a decoding device. The de-identification sensing device is used for receiving sensing data of an object to be detected and processing the sensing data to generate de-identification sensing data. The decoding device is communicatively coupled to the de-identification sensing device. The decoding device generates decoding data according to the de-identified sensing data and decoding parameters, wherein the decoding parameters are obtained by the decoding device from a database of machine learning training, the sensing module comprises an analog coding unit, and the sensing module codes the sensing data by the analog coding unit to obtain response data.
According to an embodiment of the present invention, a data processing method for a sensor is applied to a data processing system on the sensor, wherein the data processing system includes a de-identification sensing device and a decoding device, and the method includes: the de-identification sensing device receives sensing data of the object to be detected and processes the sensing data to obtain de-identification sensing data; the decoding device generates decoding data according to the de-identified sensing data and decoding parameter operation, wherein the decoding parameters are obtained by the decoding device from a database of machine learning training; the de-identified sensing device comprises an analog encoder, wherein the analog encoder is used for encoding sensing data to obtain response data.
According to an embodiment of the present invention, a de-identification sensing apparatus for receiving sensing data of an object to be tested and processing the sensing data to generate de-identification data includes an analog encoder. The analog encoder is used for encoding the sensing data to generate response data; the de-identified sensing data is transmitted to the decoding device so that the decoding device can calculate the decoding data according to the de-identified sensing data and the decoding parameters, and the decoding parameters are obtained by the decoding device from a database of machine learning training.
The foregoing description of the disclosure and the following description of the embodiments are provided to illustrate and explain the spirit and principles of the invention and to provide further explanation of the invention's claimed scope.
Drawings
FIG. 1 is a block diagram illustrating a data processing system on a sensor in accordance with one embodiment of the present invention;
FIG. 2 is an exploded view of a de-identified sensing device of a data processing system on a sensor in accordance with one embodiment of the present invention;
FIG. 3A is a flow chart illustrating a method of processing data on a sensor in accordance with one embodiment of the present invention;
FIG. 3B is a detailed flowchart of step S1 in FIG. 3A;
FIG. 4A is a flow chart illustrating a method of data processing at a sensor in accordance with one embodiment of the present invention;
FIG. 4B is a detailed flowchart of step A5 of FIG. 4A;
FIG. 4C is a detailed flowchart of step A7 of FIG. 4A; and
FIG. 5 is a flow chart of building a database.
List of reference numerals
100: data processing system
10: de-identification sensing device
30: decoding device
12: analog encoder
13: filter array
14: detector array
16: reading circuit
18: quantizer
32: database with a plurality of databases
34: arithmetic device
341: artificial intelligence learning engine
343: decoder
N: signal transmissible connection
S1-S7, S11-S13, A1-A7, A51-A53, A71-A75 and B0-B4: step (ii) of
Detailed Description
The detailed features and advantages of the present invention are described in detail in the following embodiments, which are sufficient for anyone skilled in the art to understand the technical contents of the present invention and to implement the present invention, and the related objects and advantages of the present invention can be easily understood by anyone skilled in the art from the disclosure of the present specification, the claims and the drawings. The following examples further illustrate aspects of the invention in detail, but are not intended to limit the scope of the invention in any way.
The data processing system on the sensor uses a small number of filters to simultaneously acquire information of a plurality of wavelengths. The invention provides a high-quality signal reconstruction method based on a sparse signal recovery (sparse signal recovery) principle in compressed sensing and the characteristic that a spectrum signal usually shows a smooth curve with a small number of peaks.
Referring to fig. 1, a block diagram of a data processing system on a sensor according to an embodiment of the invention is shown. As shown in FIG. 1, the data processing system 100 includes a de-identification sensing device 10 and a decoding device 30.
The de-identified sensing device 10 is communicatively coupled to the decoding device 30. The de-discrimination sensing apparatus 10 includes an analog encoder 12 and a quantizer 18.
The de-identification sensing device 10 is used for receiving the sensing data of the object to be detected and processing the sensing data to generate de-identification data. For example, the sensed data is spectral data or spatial data. In one embodiment, the de-discrimination sensing apparatus 10 includes an analog encoder 12. The analog encoder 12 is used to encode the sensing data to generate response data.
The decoding device 30 is communicatively connected to the de-identified sensing device 10 via a signal-transmissible link N, such as a cable, a local area network, or the Internet. For example, the decoding device 30 is located at a place remote from the de-identified sensing device 10, and uses the internet or a local area network as the link N that can transmit signals. For another example, the signal transmission link N is a signal line, so that the data processing system 100 can be integrated into a single device. The decoding device 30 is used for generating decoding data according to the de-identified data and the decoding parameters, and the decoding parameters are obtained from the database 32 trained by machine learning.
Referring to fig. 2, an exploded view of a de-identification sensing device 10 according to an embodiment of the invention is shown. For example, analog encoder 12 includes a filter array 13, a detector array 14, and a read circuit 16. Regarding the positional relationship of the above three components, the detector array 14 is disposed on the reading circuit 16 and the filter array 13 is disposed on the detector array 14. In other words, the detector array 14 is disposed between the filter array 13 and the readout circuit 16, as shown in FIG. 2
Please refer to fig. 2. The filter array 13 includes a plurality of filters. For example, the filter array 13 is used to perform a random optical response (random optical response) on the sensing data of the object. The filter array 13 is used to perform physical coding or electrical signal coding. The physical parameters of the filter array 13 may be considered as sensor information.
In practice, each filter of the filter array 13 can be physically encoded according to the physical quantity of the object to be measured. For example, the encoding is performed on the wavelength range of the incident light of the object to be measured, or the encoding is performed on the spatial information of the object to be measured, however, the present invention is not limited thereto.
Regarding the implementation of the physical coding based on the wavelength range, for example, each filter of the filter array 13 employs a coating (coating) of a specific material capable of changing transmittance (transmission), so that only the incident light in a specific wavelength range can pass through the filter, in other words, the filter is a wavelength-selective filter. Thus, multiple filters with different transmission wavelength ranges can produce diverse information for incident light.
Regarding the implementation of the physical coding based on the spatial information, for example, an optical component with diffraction or interference effect is added to each filter of the filter array 13, so that the filter can receive the incident light from a plurality of points of the object. With respect to the coating or coding assembly exemplified above, it is preferred to employ a random arrangement for the plurality of filters in the filter array 13 to obtain diverse physical information associated with the incident light.
Please refer to fig. 2. The detector array 14 includes a plurality of detectors, each corresponding to a plurality of filters of the filter array 13. For example, and each detector has the same frequency sensing range or wavelength sensing range for incident light. For example, the wavelength measurement range of each detector is the wavelength range of visible light, i.e. 400-700 nm (nanometer). In one embodiment, at least two detectors in the detector array 14 have an intersection with respect to the wavelength sensing range or the frequency sensing range of the incident light.
Please refer to fig. 2. The read out Circuit (ROIC) 16 is used for generating analog data according to the sensing data. For example, the analog data is, for example, spectral data or spatial data, which is not limited in the present invention. In one embodiment, the read circuit 16 can electrically encode the sensing data, thereby reducing the data amount of the analog data.
The quantizer 18 is an Analog-to-digital Converter (ADC) for converting the response data into de-identified data.
Please refer to fig. 1. The decoding device 30 includes a database 32 and a computing device 34 based on machine learning. In one embodiment, the decoding device 30 is, for example, a cloud server. The database 32 is used for storing a plurality of decoding parameters, which are generated in a machine learning manner after training data are collected, and the dimensionality of the training data is larger than that of the simulation data. The computing device 34 is used for obtaining a decoding parameter from the database 32 according to the de-identified data, and converting the de-identified data into output data according to the decoding parameter, wherein the dimension of the output data is greater than the resolution of the de-identified data. In one embodiment, the computing device 34 includes an artificial intelligence learning engine 341 and a decoder 343.
Referring to fig. 3A, a flow chart of a data processing method on a sensor according to an embodiment of the invention is shown.
Referring to step S1, the sensing data of the object to be tested is received and processed to generate de-identified data. Please refer to fig. 3B, which shows a detailed flowchart of step S1 in fig. 3A. Referring to step S11, input sensing data is received. In this step, the de-identified sensing device 10 receives input sensing data through the analog encoder 12. The analog encoder 12 includes a physical encoding component or an electronic encoding component. The input sensing data is generated by the analog encoding component and the sensor information. Referring to step S13, the quantizer 18 outputs de-identified data.
Referring to step S3, data is collected from the pre-acquired signal sources and decoded data.
Referring to step S5, the artificial intelligence engine 341 calculates decoding parameters.
Referring to step S7, decoding data is generated according to the de-identified data and the decoding parameters obtained from the database 32.
Details of the above steps S1, S3, S5 and S7 are shown in fig. 4A and 5.
Referring to fig. 4A, a detailed flowchart illustrating a data processing method on a sensor according to an embodiment of the invention is shown. In detail, in fig. 4A, steps a1 and A3 correspond to an implementation example of step S1 in fig. 3A; steps a5 and a7 correspond to an implementation example of step S7 of fig. 3A.
Referring to step a1, sensing data of the object to be tested is received and response data is generated. For example, the filter array 13 includes a plurality of filters having random coatings, and performs physical encoding or electrical signal encoding on the sensing data. The detector array 14 and read circuit 16 combine the sensor information to generate response data. In one embodiment, the response data is random optical response data, wherein each detector of the detector array 14 may take incident light having multiple wavelengths.
Referring to step A3, the response data is converted into de-identified data. For example, an analog-to-digital converter is employed as quantizer 18 to convert the response data to de-identified data.
Referring to step a5, the de-identified data is decomposed into sparse (sparse) and smooth (smooth) portions and decoded parameters are obtained. Please refer to fig. 4B, which shows a detailed flowchart of step a5 in fig. 4A. Referring to step a51, the signal is decomposed into a sparse portion and a smooth portion. Such as de-identified data. In particular, since the true signal is not completely sparse or smooth, the present invention employs step a5 to recover a complex signal of, for example, a true plastic material. According to compressive sensing theory, the sparse nature of the signal can be extracted and represented at a rate that is significantly below and significantly below the Nyquist rate. The decoder 343 of the arithmetic device 34 of the decoding device 30 decomposes the de-identified data into a thinned portion and a smoothed portion. Referring to step A53, regularization parameters are selected based on the data characteristics of the sparse and smooth portions. Specifically, the decoder 343 of the arithmetic device 34 of the decoding device 30 selects the regularization parameter as the decoding parameter in accordance with the data characteristics of the sparse portion and the smooth portion. For example, the decoding parameters include a regularization parameter corresponding to a sparse portion and a regularization parameter corresponding to a smooth portion.
Referring to step A7, decoded data is generated according to the de-identified data and the decoding parameters. Referring to FIG. 4C, a detailed flowchart of step A7 of FIG. 4A is shown. Referring to step A71, a sparse basis is calculated based on the de-identified data and the sparse induction database stored in database 32. In detail, the decoder 343 of the computing device 34 of the decoding device 30 determines the sparse basis according to the characteristics of the sparse portion data, wherein the sparse basis is stored in the database 32. The database 32 collects the sparsity inducing database from the pre-fetched signals and decoded signals, and executes a machine learning algorithm using the artificial intelligence learning engine 341 of the computing device 34 to generate a plurality of sparse bases. In one embodiment, the computing device 34 further obtains the decoding parameters according to the sparse basis and the regularization parameter.
Referring to step A73, adaptive regularization is performed based on regularization parameters and sparse basis. For example, to convert the de-identified data into decoded data, the decoder 343 of the computing device 34 may employ adaptive regularization or near-end gradient descent methods (gradient methods) to solve the following optimization problem.
Wherein y is de-identified data, Φ is a pre-obtained filter feature sensing matrix (or called sensing matrix), v is a smoothing portion, Ψ is a sparse basis, z is a sparse portion, λ1For regularization parameters corresponding to sparse portion data, λ2To correspond to the regularization parameters of the smooth portion data, A is a bidiagonalal matrix of (1, -1) such that Av can capture the gradient of the adjacent term v in the smooth portion. Sparse basis Ψ and regularization parameter λ1And λ2In this example as decoding parameters. Based on the sparse basis and the decoding parameters obtained in step a5, the decoder 343 of the computing device 34 performs adaptive regularization to find the appropriate v and z and generates decoded data, wherein the dimensions of the decoded data are larger than those of the simulated data.
Referring to step a75, a recovery signal is calculated based on the regularization result. Since the training data reaching the resolution requirement has a dimension larger than that of the simulation data, the dimension (or resolution) corresponding to the decoded data can still meet the requirement even though the dimension of the simulation data may be relatively smaller than that of the requirement. In addition, the number of detector arrays 14 may also be reduced accordingly.
The foregoing and methods of generating decoding parameters are further described below. Please refer to fig. 5, which is a flowchart illustrating the database 32. Specifically, in fig. 5, step B0 corresponds to an example of step S3 in fig. 3A, and steps B2 and B4 correspond to an example of step S5 in fig. 3A.
Referring to step B0, a plurality of training data are obtained and stored in the database 32. For example, another spectrometer may be employed to collect spectral signals having a high dimension (high resolution), wherein the other spectrometer includes another detector array having a greater number of detectors than the number of detectors in the array 14. For example, the present invention employs a RED-Wave-NIRX-SR spectrometer with SL1 tungsten lamps to obtain reflectance spectra of plastics from 1000 nm to 1656 nm at very high resolution (1 nm). The present invention uses seven different types of plastics according to the American Society for Testing and Materials (ASTM) international standard to measure multiple spectra for different articles using the same plastic, or to measure variations between different plastics, or to measure multiple spectra of the same article at different distances, locations and angles to achieve variations in measurements of the same material.
Referring to step B2, sparse dictionary learning (sparse dictionary learning) is performed according to the training data to generate a plurality of sparse bases. The step B2 may use a conventional machine learning algorithm, or learn the training data by using the artificial intelligence learning engine 341 of the computing device 34 to execute the neural network model.
Referring to step B4, the sparse substrate is stored in the database 32. The artificial intelligence learning engine 341 of the computing device 34 stores the sparse basis generated in step B2 in the database 32 for subsequent retrieval.
In summary, the data processing system on a sensor and the data processing method on a sensor provided by the present invention can save the number of optical path components (including the detectors of the detector array), and can achieve high-resolution signal sensing with a smaller number of detectors, thereby further miniaturizing the sensor. On the other hand, the decoding reconstruction method based on machine learning also helps to realize a low-cost sensor and meets the privacy requirement of sensor de-identification.
Claims (18)
1. A data processing system on a sensor, comprising:
the de-identification sensing device is used for receiving sensing data of an object to be detected and processing the sensing data to generate de-identification sensing data; and
the decoding device is in communication connection with the de-identification sensing device and generates decoding data according to the de-identification sensing data and decoding parameters, and the decoding parameters are obtained by the decoding device from a database of machine learning training;
the sensing module comprises an analog coding unit, and the sensing module codes the sensing data by the analog coding unit to obtain response data.
2. The data processing system of claim 1, wherein the sensed data is spectral data or spatial data.
3. The data processing system of claim 1, wherein the analog encoder comprises a filter array, a detector array, and a read circuit, the detector array disposed on the read circuit and the filter array disposed on the detector array, the filter array to perform physical encoding or electrical signal encoding.
4. The data processing system of claim 3, wherein the filter array is configured to perform a random optical response on the sensed data of the test object.
5. The data processing system of claim 3, wherein the detector array comprises a plurality of detectors having the same sensing frequency range or sensing wavelength range.
6. The data processing system of claim 1, wherein the de-identified sensing device further comprises a quantizer, the quantizer being an analog-to-digital converter, for converting the response data into the de-identified sensing data.
7. A method for processing data on a sensor, the method being applied to a data processing system on the sensor, wherein the data processing system includes a de-identified sensing device and a decoding device, the method comprising:
receiving the sensing data of the object to be detected by the de-identification sensing device and processing the sensing data to obtain de-identification sensing data; and
calculating by the decoding device according to the de-identified sensing data and decoding parameters to generate decoding data, wherein the decoding parameters are obtained by the decoding device from a database of machine learning training;
the de-identified sensing device comprises an analog encoder for encoding the sensing data to obtain response data.
8. The method of claim 7, wherein the analog encoder comprises a filter array, a detector array and a readout circuit, and the step of receiving the sensing data of the object with the de-identified sensing device and processing the sensing data to obtain the de-identified sensing data comprises:
the sensing data is physically or electrically encoded with the filter array.
9. The method of claim 7, wherein the generating the decoded data according to the de-identified sensing data and the decoding parameter operation by the decoding device comprises:
decomposing the de-identified sensing data into sparse and smooth portions with the decoding device; and
and respectively selecting a regularization parameter according to the characteristic data of the sparse part and the characteristic data of the smooth part.
10. The method of claim 9, wherein the generating the decoded data according to the de-identified sensing data and the decoding parameter operation by the decoding device comprises:
the decoding device calculates a sparse basis according to a database, wherein the database comprises a sparse induction database; wherein the decoding device calculates the sparse basis according to the de-identified sensing data and the sparse induction database.
11. The method of claim 10, wherein the generating the decoded data according to the de-identified sensing data and the decoding parameter operation by the decoding device comprises:
obtaining the decoding parameter by the decoding device according to the sparse substrate and the regularization parameter; and
adaptive regularization is performed to produce the decoded data.
12. The method of data processing on a sensor of claim 8, wherein the de-identified sensing device further comprises a quantizer, the quantizer being an analog-to-digital converter, the receiving the sensed data of the test object with the de-identified sensing device and processing the sensed data to obtain the de-identified sensed data comprises:
the response data is converted into the de-identified sensing data by the analog-to-digital converter.
13. A de-identified sensing device for receiving sensed data of an object to be tested and processing the sensed data to generate de-identified data, the de-identified sensing device comprising:
an analog encoder for encoding the sensing data to generate response data; wherein
The de-identified sensing data is transmitted to a decoding device so that the decoding device can calculate decoding data according to the de-identified sensing data and decoding parameters, wherein the decoding parameters are obtained by the decoding device from a database of machine learning training.
14. The de-discriminative sensing device of claim 13, wherein the sensing data is spectral data or spatial data.
15. The de-discriminative sensing device of claim 13, wherein the analog encoder comprises a filter array, a detector array and a read circuit, the detector array disposed on the read circuit and the filter array disposed on the detector array, the filter array configured to perform physical encoding or electrical signal encoding.
16. The de-discriminative sensing device of claim 15, wherein the filter array is configured to randomly optically respond to the sensing data of the test object.
17. The de-discriminative sensing device of claim 15, wherein the detector array comprises a plurality of detectors having the same sensing frequency range or sensing wavelength range.
18. The de-identified sensing device as recited in claim 15 further comprising a quantizer, the quantizer being an analog-to-digital converter for converting the response data into the de-identified sensing data.
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US16/727,382 | 2019-12-26 | ||
| US16/727,382 US20210199503A1 (en) | 2019-12-26 | 2019-12-26 | Data processing system disposed on sensor and method thereof |
| TW109108286A TWI740411B (en) | 2019-12-26 | 2020-03-13 | Data processing system disposed on sensor and method thereof and de-identified device |
| TW109108286 | 2020-03-13 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113050872A true CN113050872A (en) | 2021-06-29 |
Family
ID=76507571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010298954.0A Pending CN113050872A (en) | 2019-12-26 | 2020-04-16 | Data processing system on sensor, method thereof and de-identification sensing device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113050872A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7095355B1 (en) * | 2005-05-09 | 2006-08-22 | Raytheon Company | Low power ADC for imaging arrays |
| US20060239336A1 (en) * | 2005-04-21 | 2006-10-26 | Baraniuk Richard G | Method and Apparatus for Compressive Imaging Device |
| US20090222226A1 (en) * | 2005-10-25 | 2009-09-03 | Baraniuk Richard G | Method and Apparatus for On-Line Compressed Sensing |
| US20130297048A1 (en) * | 2011-01-14 | 2013-11-07 | William Marsh Rice University | Method and device for real-time differentiation of analog and digital signals |
| US20160014129A1 (en) * | 2014-07-08 | 2016-01-14 | Google Inc. | User Control of Data De-Idenfication |
| CN106455974A (en) * | 2014-06-20 | 2017-02-22 | 拉姆伯斯公司 | Systems and methods for lensed and lensless optical sensing |
| US20180226143A1 (en) * | 2017-02-08 | 2018-08-09 | Groundbreaking Technology Llc | Medical diagnostic platform |
| CN109074775A (en) * | 2016-01-29 | 2018-12-21 | 巴科股份有限公司 | Digital image processing chain and process block and display including them |
| CN109409177A (en) * | 2017-08-17 | 2019-03-01 | 联咏科技股份有限公司 | Sense the processing method and its image sensing circuit of data |
-
2020
- 2020-04-16 CN CN202010298954.0A patent/CN113050872A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060239336A1 (en) * | 2005-04-21 | 2006-10-26 | Baraniuk Richard G | Method and Apparatus for Compressive Imaging Device |
| US7095355B1 (en) * | 2005-05-09 | 2006-08-22 | Raytheon Company | Low power ADC for imaging arrays |
| US20090222226A1 (en) * | 2005-10-25 | 2009-09-03 | Baraniuk Richard G | Method and Apparatus for On-Line Compressed Sensing |
| US20130297048A1 (en) * | 2011-01-14 | 2013-11-07 | William Marsh Rice University | Method and device for real-time differentiation of analog and digital signals |
| CN106455974A (en) * | 2014-06-20 | 2017-02-22 | 拉姆伯斯公司 | Systems and methods for lensed and lensless optical sensing |
| US20160014129A1 (en) * | 2014-07-08 | 2016-01-14 | Google Inc. | User Control of Data De-Idenfication |
| CN109074775A (en) * | 2016-01-29 | 2018-12-21 | 巴科股份有限公司 | Digital image processing chain and process block and display including them |
| US20180226143A1 (en) * | 2017-02-08 | 2018-08-09 | Groundbreaking Technology Llc | Medical diagnostic platform |
| CN109409177A (en) * | 2017-08-17 | 2019-03-01 | 联咏科技股份有限公司 | Sense the processing method and its image sensing circuit of data |
Non-Patent Citations (4)
| Title |
|---|
| LU: ""Signal recovery for compressive spectrometers "", SPIE DIGITAL 网站, pages 1 - 6 * |
| LU: ""Signal recovery for compressive spectrometers"", SPIEDI GITAL 网站, 11 May 2018 (2018-05-11), pages 1 - 6 * |
| OLIVER: ""Filters with random transmittance for improving resolution in filter-array-based spectrometers"", OPG网站, 31 December 2013 (2013-12-31), pages 1 - 3 * |
| OLIVER: ""Filters with random transmittance for improving resolution in filter-array-based spectrometers"", OPG网站, pages 1 - 3 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101423964B1 (en) | Method and apparutus for processing optical signal of spectrometer | |
| CN111626317B (en) | Semi-supervised hyperspectral data analysis method based on double-flow conditional countermeasure generation network | |
| US8125549B2 (en) | Methods and apparatus to capture compressed images | |
| WO2016029276A1 (en) | Imaging method and apparatus | |
| CN109073357A (en) | Filter array reconstructs spectroscopic assay | |
| CN113506235B (en) | Adaptive weighted spectrum reconstruction method for resisting exposure change | |
| WO2023125329A1 (en) | Living-body fingerprint identification system and living-body identification method thereof | |
| CN115931123A (en) | Spectrum reconstruction calculation method and spectrum system based on self-adaptive optimization sparse dictionary | |
| CN113050872A (en) | Data processing system on sensor, method thereof and de-identification sensing device | |
| TWI740411B (en) | Data processing system disposed on sensor and method thereof and de-identified device | |
| CN112862906A (en) | Color space conversion method based on neural network | |
| CN117571128B (en) | High-resolution polarized spectrum image imaging method and system | |
| CN115791628A (en) | Spectrum recovery method, spectrum recovery device and electronic equipment | |
| Chang et al. | Accurate sensing of LED spectra via low-cost spectrum sensors | |
| CN117288705B (en) | Miniature ultraviolet absorption method multipath absorption tank ozone gas sensor based on Internet of things | |
| CN117346891A (en) | Spectral sensor output classification and method of using the same | |
| CN102158659A (en) | A method and an apparatus for difference measurement of an image | |
| CN110793920A (en) | Atmospheric remote measurement method combining chemical imaging and hyperspectral | |
| CN115049917A (en) | Neural network training method, object detection method and intelligent terminal device | |
| Wang et al. | Spatial-spectral compressive sensing of hyperspectral image | |
| Brady et al. | Compressive sampling strategies for integrated microspectrometers | |
| Medina Rojas et al. | A quantitative and qualitative performance analysis of compressive spectral imagers | |
| Jiao et al. | Image recognition based on compressive imaging and optimal feature selection | |
| Sippel et al. | Optimal Filter Selection for Multispectral Object Classification Using Fast Binary Search | |
| CN107147396B (en) | Signal sampling method, signal sampling system and signal sampling device |
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 |