CN113259604B - Intelligent perception image acquisition device and method - Google Patents
Intelligent perception image acquisition device and method Download PDFInfo
- Publication number
- CN113259604B CN113259604B CN202110525713.XA CN202110525713A CN113259604B CN 113259604 B CN113259604 B CN 113259604B CN 202110525713 A CN202110525713 A CN 202110525713A CN 113259604 B CN113259604 B CN 113259604B
- Authority
- CN
- China
- Prior art keywords
- image acquisition
- acquisition device
- intelligent
- data processing
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
- H04N5/765—Interface circuits between an apparatus for recording and another apparatus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/268—Signal distribution or switching
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- User Interface Of Digital Computer (AREA)
- Image Input (AREA)
Abstract
The invention discloses an intelligent perception image acquisition device and method, wherein the device comprises a universal channel interface socket, a universal channel interface controller, a central processing unit, a tensor processor, an image signal processor, a DDR memory and an image sensor; the central processing unit realizes a firmware for processing the intelligent perception function configuration request of the data processing system, and the configuration of the intelligent perception image acquisition device is realized by performing configuration operation on the universal channel interface controller, the tensor processor, the image signal processor and the image sensor according to the request content. The device can realize understanding of the semantics expressed by the image data, thereby realizing the intelligent image sensing function, has an interface compatible with the traditional image sensor, can be used by all data processing systems with the connection capability of the traditional image acquisition device, does not destroy the original system, has high compatibility and is convenient to use.
Description
Technical Field
The invention relates to the field of image acquisition, in particular to an image acquisition device and method with intelligent perception capability based on an artificial intelligent deep learning technology.
Background
Image acquisition is achieved using an image sensor. The image sensor is a semiconductor device that converts light imaging on a photosensitive surface into a corresponding electrical signal using a photoelectric device. The data processing system collects the electric signals output by the image sensor, and then the image acquisition can be completed.
In the conventional image acquisition method, the data processing system directly acquires the electric signal from the image sensor, the acquired image data is only the data expression of light imaging, the image data is only meaningful to human beings, the data processing system cannot directly respond to the image data (for example, whether the image content is qualified or not according to the image data) and can only store the image data, and the image data can be used for carrying out additional calculation operation according to the requirement by using an algorithm.
In recent years, with the rapid development of artificial intelligence deep learning algorithms, it has become mainstream to use deep learning technology to perform intelligent computation on image data so as to obtain semantics contained in an image, for example, to implement positioning and feature extraction of key targets (such as faces) of the image.
However, deep learning computing requires high computational effort, and typically requires hardware such as a high performance GPU or a dedicated AI processor (e.g., NPU) to efficiently complete the computation. This therefore requires a high computational effort on the data processing system that acquires the image data, which is typically done in two ways: (1) The data processing system is externally connected with high-calculation-force computing hardware (such as a display card), and (2) the data processing system itself has high calculation force (such as a built-in NPU).
In any of the above ways, the data processing system is changed by a broadsword, and the change is difficult to implement for most miniature, handheld or portable data processor systems due to various challenges such as energy consumption, cost, volume, software and hardware architecture.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, an object of the present invention is to provide an intelligent image acquisition device and method, so as to optimize the software and hardware architecture of a data processor system and improve the system energy consumption.
In order to achieve the above object, the present invention provides an intelligent sensing image acquisition device, comprising a universal channel interface socket, a universal channel interface controller, a central processing unit, a tensor processor, an image signal processor, a DDR memory, and an image sensor; the tensor processor is used for accelerating calculation of the deep learning algorithm; the image signal processor is used for accelerating calculation of an image quality adjustment algorithm; the image sensor is used for converting light imaging into an electric signal; the DDR memory is used for caching image data and intelligent sensing results thereof; the universal channel interface controller is connected with an external data processing system through a universal channel interface socket; the central processing unit realizes a firmware for processing the intelligent perception function configuration request of the data processing system, and the configuration of the intelligent perception image acquisition device is realized by performing configuration operation on the universal channel interface controller, the tensor processor, the image signal processor and the image sensor according to the content of the intelligent perception function configuration request.
Further, the central processing unit is connected with the universal channel interface controller, the tensor processor, the image signal processor and the image sensor through an internal configuration bus; the DDR memory is connected with the universal channel interface controller, the tensor processor, the image signal processor and the image sensor through an internal data bus; the universal channel connected with the data processing system by the universal channel interface controller comprises: a data bus for transmitting image data and intelligent sensing results thereof and a configuration bus for transmitting configuration information; the universal channel data bus and the universal channel configuration bus are converted into an internal data bus and an internal configuration bus through the universal channel interface controller. And the image and intelligent perception result request of the data processing system is directly processed by the universal channel interface controller, and the image data cached by the DDR memory and the intelligent perception result thereof are directly read.
Furthermore, the universal channel data bus adopts an MIPI bus or a DVP bus, and the transmission method of the image data and the intelligent sensing result between the data processing system and the intelligent sensing image acquisition device is a standard method regulated by the MIPI bus standard or the DVP bus standard.
Further, the general channel configuration bus is an I2C bus, and the method for transmitting configuration information between the data processing system and the image acquisition device is a standard method specified by the I2C bus standard.
Further, the universal channel interface socket comprises an MIPI bus or a DVP bus, an I2C bus and a power interface; the universal channel interface socket is connected with the data processing system through a universal channel bus cable.
In order to achieve the above object, the present invention further provides an intelligent perceived image acquisition method, including: setting a firmware in the intelligent perception image acquisition device, wherein the firmware is used for processing an operation request of the data processing system and realizing configuration operation of the intelligent image acquisition device;
the operation request includes: the data processing system reads configuration information of the intelligent perception image acquisition device; the data processing system writes configuration information of the intelligent perception image acquisition device.
Further, the reading of the configuration information of the intelligent perception image acquisition device by the data processing system comprises the following steps:
step S101: the upper operating system of the data processing system receives a configuration reading command of a user;
step S102: the upper operating system of the data processing system sends a configuration read command to the driver;
step S103: the driver program converts the configuration read command into a configuration read operation command which can be understood by the firmware and sends the configuration read operation command to a bottom operating system of the data processing system;
step S104: the bottom operating system transmits the configuration read operation instruction converted in the step S103 to the firmware of the intelligent perception image acquisition device through the universal channel control circuit;
step S105: and the firmware executes the configuration read operation instruction and transmits the configuration information abstract back to the data processing system through the universal channel.
Further, the writing of the configuration information of the image acquisition device by the data processing system includes the following steps:
step S201: an upper operating system of the data processing system receives a configuration writing command of a user;
step S202: the upper operating system of the data processing system sends a configuration write command to the driver;
step S203: the driver program converts the configuration writing command into a configuration information abstract writing operation command, a configuration information writing end operation command and a plurality of configuration information writing operation commands which can be understood by the firmware, and firstly sends the configuration information abstract writing operation command to a bottom operating system of the data processing system;
step S204: the bottom operating system transmits the configuration information abstract writing operation instruction to the firmware of the intelligent perception image acquisition device through a general channel;
step S205: the firmware executes a configuration information abstract writing operation instruction, configures a universal channel interface controller in the intelligent perception image acquisition device into a memory direct writing mode, and transmits the state back to the data processing system through a universal channel;
step S206: the driver program sends a plurality of configuration information writing operation instructions to a bottom operating system of the data processing system one by one;
step S207: the bottom operating system transmits the plurality of configuration information writing operation instructions converted in the step S203 through a universal channel control circuit and directly writes the configuration information writing operation instructions into a DDR memory in the intelligent perception image acquisition device;
step S208: the driver program sends a configuration information write end operation instruction to a bottom operating system of the data processing system;
step S209: the bottom operating system transmits the configuration information writing ending operation instruction converted in the step S203 to the firmware of the intelligent perception image acquisition device through the universal channel control circuit;
step S210: the firmware completes the final configuration operation and communicates the results and status back to the data processing system over the common channel.
Further, the data organization mode of the intelligent sensing result is as follows: the smart sensing result is arranged next to the last line of the processed image data and has the same line width as the image data.
Further, the intelligent sensing result includes: at least one of the total category of the image data, the category of each pixel of the image data, the category of the key target in the image data and the coordinate information.
The invention realizes the following technical effects:
(1) The intelligent perception image acquisition device provided by the invention has an interface compatible with the traditional image sensor, can be used by all data processing systems with the connection capability of the traditional image acquisition device, does not damage the original system, has high compatibility and is convenient to use.
(2) The intelligent perception image acquisition device provided by the invention has intelligent perception computing capability, and an intelligent perception result is integrated with image data and has an easily separated data organization mode.
(3) For a traditional data processing system without intelligent perception computing capability, the intelligent perception image acquisition device provided by the invention can realize understanding of semantics expressed by image data by directly using the intelligent perception result, thereby realizing an image intelligent perception function. The mode does not destroy the original system, has high compatibility and has the characteristics of natural and easy popularization.
Drawings
FIG. 1 is a system block diagram of an intelligent perceived image acquisition device of the present invention;
FIG. 2 is a system block diagram of a smart perceived image acquisition device employing a MIPI bus;
FIG. 3 is a system block diagram of an intelligent perceived image acquisition device employing a DVP bus;
FIG. 4 is a flow chart of the intelligent perceived image acquisition method of the present invention;
fig. 5 is a data format of image data and smart perception results.
Detailed Description
For further illustration of the various embodiments, the invention is provided with the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments and together with the description, serve to explain the principles of the embodiments. With reference to these matters, one of ordinary skill in the art will understand other possible embodiments and advantages of the present invention. The components in the figures are not drawn to scale and like reference numerals are generally used to designate like components.
The invention will now be further described with reference to the drawings and detailed description.
Example 1
As shown in fig. 1, the present invention provides an intelligent sensing image acquisition device, which comprises a universal channel interface socket, a universal channel interface controller, a central processing unit, a tensor processor, an image signal processor, a DDR memory, and an image sensor; the tensor processor is used for accelerating calculation of the deep learning algorithm; the image signal processor is used for accelerating calculation of an image quality adjustment algorithm; the image sensor is used for converting light imaging into an electric signal; the DDR memory is used for caching image data and intelligent sensing results thereof; the central processing unit is connected with the universal channel interface controller, the tensor processor, the image signal processor and the image sensor through the internal configuration bus. The universal channel interface socket is connected with an external data processing system through a universal channel bus cable, and two groups of universal channels are arranged on the universal channel interface socket, and the universal channel interface socket comprises: a universal channel data bus for transmitting image data and intelligent sensing results thereof and a universal channel configuration bus for transmitting configuration information. The intelligent perception function configuration request of the data processing system is transmitted through a universal channel configuration bus, and the image and intelligent perception result request of the data processing system are transmitted through a universal channel data bus.
The universal channel data bus and the universal channel configuration bus are converted into an internal data bus and an internal configuration bus via the universal channel interface controller. The universal channel interface controller is connected with the central processing unit through an internal configuration bus, and the universal channel interface controller is connected with the DDR memory through an internal data bus. The image and intelligent sensing result request of the data processing system is directly processed by the universal channel interface controller, and the image data cached by the DDR memory and the intelligent sensing result thereof are directly read.
The central processing unit is connected with the universal channel interface controller, the tensor processor, the image signal processor and the image sensor through the internal configuration bus. The central processing unit realizes a Firmware (Firmware) for processing the intelligent perception function configuration request of the data processing system, and the configuration of the intelligent perception image acquisition device is realized by performing configuration operation on the universal channel interface controller, the tensor processor, the image signal processor and the image sensor according to the intelligent perception function configuration request content of the data processing system.
The DDR memory is connected with the universal channel interface controller, the image signal processor, the tensor processor and the image sensor through an internal data bus. The DDR memory caches image data and intelligent sensing results thereof. The image sensor generates original image data and caches the original image data in the DDR memory; the image signal processor inputs the original image data, generates optimized image data by using an image signal processing algorithm specified by the configuration operation and caches the optimized image data in the DDR memory; the tensor processor inputs the optimized image data, generates an intelligent sensing result by using a deep learning algorithm specified by the configuration operation and caches the intelligent sensing result in the DDR memory; and the universal channel interface controller sends the optimized image data and the intelligent sensing result thereof in the DDR memory to a data processing system in a direct reading mode according to the mode appointed by the configuration operation.
The universal channel data bus is used for transmitting image data and intelligent sensing results between the data processing system and the image acquisition device, and in specific application, the universal channel data bus adopts bus formats such as an MIPI bus, a DVP bus and the like.
As shown in the example of fig. 2, the universal channel data bus is an MIPI bus, and the data transfer method between the data processing system and the intelligent perceived image acquisition device is a canonical method specified by the MIPI standard.
As shown in the example of fig. 3, the universal channel data bus is a DVP bus, and the data transfer method between the data processing system and the intelligent perceived image acquisition device is a specification method specified by the DVP standard.
As shown in the examples of fig. 2 and 3, the common channel configuration buses are all I2C buses, and the data transmission method between the data processing system and the intelligent perception image acquisition device is a standard method specified by the I2C standard.
In this embodiment, the working power supply of the intelligent sensing image acquisition device is accessed from the universal channel interface socket. The universal channel bus cable of the intelligent perception image acquisition device is compatible with the bus cable adopted by the traditional image sensor, and comprises an MIPI data bus or DVP data bus, an I2C configuration bus and a power supply, so that the intelligent perception image acquisition device provided by the invention can be used by all data processing systems with the connection capability of the traditional image acquisition device, and the original system is not damaged, and the intelligent perception image acquisition device is high in compatibility and convenient to use.
The invention also provides an intelligent perception image acquisition method, which relates to the transmission of configuration information between a data processing system and an intelligent perception image acquisition device, and the data processing system acquires image data and intelligent perception results and organizes the data of the intelligent perception results. The specific implementation method comprises the following steps: setting a Firmware (Firmware) in the intelligent perception image acquisition device, wherein the Firmware is used for processing operation requests of a data processing system and realizing configuration operation of the intelligent image acquisition device; the operation request includes: the data processing system reads configuration information of the intelligent perception image acquisition device; writing configuration information of the intelligent perception image acquisition device by the data processing system and the like.
The transmission of the configuration information between the data processing system and the intelligent perception image acquisition device uses an I2C channel in the universal channel, and the transmission method of the configuration information between the data processing system and the intelligent perception image acquisition device is a standard method specified by the I2C standard.
Referring to FIG. 4, the information interaction between the data processing system and the intelligent perceived image acquisition device includes: an upper operating system of the data processing system and an intelligent perception image acquisition device driver; an intelligent perception image acquisition device driver and a data processing system bottom operating system; the data processing system is provided with an underlying operating system and intelligent perception image acquisition device firmware.
The method for reading the configuration information of the intelligent perception image acquisition device by the data processing system comprises the following steps:
(1) The upper operating system of the data processing system receives a configuration reading command of a user;
(2) The upper operating system of the data processing system sends the configuration read command to a driver;
(3) The driver program converts the configuration read command into a configuration read operation command which can be understood by the firmware and sends the configuration read operation command to a bottom operating system of the data processing system;
(4) The bottom operating system transmits the configuration read operation instruction converted in the step (3) to the intelligent perception image acquisition device firmware through a universal channel control circuit;
(5) The firmware executes the configuration read operation instruction and transmits the configuration information abstract back to the data processing system through the universal channel.
The method for writing the configuration information of the image acquisition device by the data processing system comprises the following steps:
(1) An upper operating system of the data processing system receives a configuration writing command of a user;
(2) The upper operating system of the data processing system sends the configuration write command to a driver;
(3) The driver program converts the configuration writing command into a configuration information abstract writing operation command, a configuration information writing end operation command and a plurality of configuration information writing operation commands which can be understood by the firmware, and firstly sends the configuration information abstract writing operation command to a bottom operating system of the data processing system;
(4) The bottom operating system transmits the configuration information abstract writing operation instruction converted in the step (3) to the intelligent perception image acquisition device firmware through a universal channel control circuit;
(5) And the firmware of the intelligent perception image acquisition device executes the configuration information abstract writing operation instruction, configures a universal channel interface controller in the intelligent perception image acquisition device into a memory direct writing mode, and transmits the state back to the data processing system through a universal channel.
(6) The driver program sends a plurality of configuration information writing operation instructions to the bottom operating system of the data processing system one by one;
(7) The bottom operating system directly writes the configuration information writing operation instructions converted in the step (3) into a DDR memory in the intelligent perception image acquisition device through a universal channel control circuit;
(8) The driver program sends a configuration information write end operation instruction to a bottom operating system of the data processing system;
(9) The bottom operating system transmits the configuration information writing ending operation instruction converted in the step (3) to the intelligent perception image acquisition device firmware through a universal channel control circuit;
(10) The intelligent perception image acquisition device firmware completes the final configuration operation and transmits the result and the state back to the data processing system through the universal channel.
The image data and the smart sensing result are organized in the data format of the image as shown in fig. 5, and the smart sensing result is arranged next to the last line of the image data and has the same line width as the image data. As shown in fig. 5, if the size of the image data is (HI, W) and the size of the smart sensing result is (HR, W), the size of the new smart sensing image data including the image data and the smart sensing result is (hi+hr, W).
The data processing system obtains intelligent perception image data with the size of (HI+HR, W) through a standard method specified by the MIPI or DVP standard, and can easily separate the image data and the intelligent perception result from the intelligent perception image data by intercepting the data with the sizes of (HI, W) and (HR, W) in the intelligent perception image data respectively.
The intelligent perception image acquisition device provided by the invention has intelligent perception computing capability, integrates the intelligent perception result and the image data, and adopts a standard method specified by the MIPI standard or a standard method specified by the DVP standard for transmission. The intelligent perception result can be the total category of the image data, the category of each pixel of the image data, or the category and coordinate information of a key target in the image data.
For a traditional data processing system without intelligent perception computing capability, the intelligent perception image acquisition device provided by the invention can realize understanding of semantics expressed by image data by directly using the intelligent perception result, thereby realizing an image intelligent perception function. The mode does not destroy the original system, has high compatibility and has the characteristics of natural and easy popularization.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. The intelligent perception image acquisition device is characterized by comprising a universal channel interface socket, a universal channel interface controller, a central processing unit, a tensor processor, an image signal processor, a DDR memory and an image sensor;
the tensor processor is used for accelerating calculation of the deep learning algorithm;
the image signal processor is used for accelerating calculation of an image quality adjustment algorithm;
the image sensor is used for converting light imaging into an electric signal;
the DDR memory is used for caching image data and intelligent sensing results thereof; the image sensor generates original image data and caches the original image data in the DDR memory; the image signal processor inputs the original image data, generates optimized image data by using an image signal processing algorithm designated by configuration operation and caches the optimized image data in the DDR memory; the tensor processor inputs optimized image data, generates an intelligent sensing result by using a deep learning algorithm appointed by configuration operation and caches the intelligent sensing result in the DDR memory;
the universal channel interface controller is connected with an external data processing system through a universal channel interface socket; the universal channel interface controller sends the optimized image data and the intelligent perception result thereof in the DDR memory to a data processing system in a direct reading mode according to the mode appointed by the configuration operation;
the central processing unit realizes a firmware for processing the intelligent perception function configuration request of the data processing system, and the configuration of the intelligent perception image acquisition device is realized by performing configuration operation on the universal channel interface controller, the tensor processor, the image signal processor and the image sensor according to the content of the intelligent perception function configuration request.
2. The intelligent perceived image acquisition device of claim 1 wherein the central processor is coupled to the universal channel interface controller, the tensor processor, the image signal processor, and the image sensor via an internal configuration bus; the DDR memory is connected with the universal channel interface controller, the tensor processor, the image signal processor and the image sensor through an internal data bus;
the universal channel connected with the data processing system by the universal channel interface controller comprises: a data bus for transmitting image data and intelligent sensing results thereof and a configuration bus for transmitting configuration information;
the universal channel data bus and the universal channel configuration bus are converted into an internal data bus and an internal configuration bus through the universal channel interface controller.
3. The intelligent perceived image acquisition device of claim 2, wherein: the universal channel data bus adopts an MIPI bus or a DVP bus, and the transmission method of the image data and the intelligent sensing result between the data processing system and the intelligent sensing image acquisition device is a standard method specified by the MIPI bus standard or the DVP bus standard.
4. The intelligent perceived image acquisition device of claim 2, wherein: the general channel configuration bus adopts an I2C bus, and the transmission method of configuration information between the data processing system and the image acquisition device is a standard method specified by the I2C bus standard.
5. The intelligent perceived image acquisition device of claim 1, wherein: the universal channel interface socket comprises an MIPI bus or a DVP bus, an I2C bus and a power interface; the universal channel interface socket is connected with the data processing system through a universal channel bus cable.
6. An intelligent perception image acquisition method is characterized in that: applied to the intelligent perceived image acquisition device of any of claims 1-5, the firmware being configured to process operational requests of the data processing system and to implement configuration operations of the intelligent image acquisition device;
the operation request includes:
the data processing system reads configuration information of the intelligent perception image acquisition device;
writing configuration information of the intelligent perception image acquisition device by the data processing system;
the information interaction between the data processing system and the intelligent perception image acquisition device comprises the following steps:
the upper operating system of the data processing system interacts with the driver of the intelligent perception image acquisition device;
the driver of the intelligent perception image acquisition device interacts with the underlying operating system of the data processing system;
interaction of the underlying operating system of the data processing system and the firmware of the intelligent perception image capture device.
7. The intelligent perceived image acquisition method of claim 6 wherein the data processing system reading of configuration information for the intelligent perceived image acquisition device includes the steps of:
step S101: the upper operating system of the data processing system receives a configuration reading command of a user;
step S102: the upper operating system of the data processing system sends a configuration reading command to a driving program of the intelligent perception image acquisition device;
step S103: the driver of the intelligent perception image acquisition device converts the configuration read command into a configuration read operation command which can be understood by the firmware of the intelligent perception image acquisition device and sends the configuration read operation command to a bottom operating system of the data processing system;
step S104: the bottom operating system of the data processing system transmits the configuration read operation instruction converted in the step S103 to the firmware of the intelligent perception image acquisition device through the universal channel control circuit;
step S105: and the firmware of the intelligent perception image acquisition device executes the configuration read operation instruction and transmits the configuration information abstract back to the data processing system through the universal channel.
8. The intelligent perceived image acquisition method of claim 6, wherein the data processing system writing configuration information for the image acquisition device includes the steps of:
step S201: an upper operating system of the data processing system receives a configuration writing command of a user;
step S202: the upper operating system of the data processing system sends a configuration writing command to a driving program of the intelligent perception image acquisition device;
step S203: the method comprises the steps that a driver of an intelligent perception image acquisition device converts a configuration writing command into a configuration information abstract writing operation command, a configuration information writing end operation command and a plurality of configuration information writing operation commands which can be understood by firmware of the intelligent perception image acquisition device, and firstly, the configuration information abstract writing operation command is sent to a bottom operating system of a data processing system;
step S204: the bottom operating system of the data processing system transmits a configuration information abstract writing operation instruction to the firmware of the intelligent perception image acquisition device through a general channel;
step S205: the firmware of the intelligent perception image acquisition device executes a configuration information abstract writing operation instruction, configures a universal channel interface controller in the intelligent perception image acquisition device into a memory direct writing mode, and transmits the state back to the data processing system through a universal channel;
step S206: the method comprises the steps that a driver of the intelligent perception image acquisition device sends a plurality of configuration information writing operation instructions to a bottom operating system of a data processing system one by one;
step S207: the bottom operating system transmits the plurality of configuration information writing operation instructions converted in the step S203 through a universal channel control circuit and directly writes the configuration information writing operation instructions into a DDR memory in the intelligent perception image acquisition device;
step S208: the method comprises the steps that a driver of the intelligent perception image acquisition device sends a configuration information writing ending operation instruction to a bottom operating system of a data processing system;
step S209: the bottom operating system transmits the configuration information writing ending operation instruction converted in the step S203 to the firmware of the intelligent perception image acquisition device through the universal channel control circuit;
step S210: the firmware of the intelligent perception image acquisition device completes the final configuration operation, and the result and the state are transmitted back to the data processing system through the universal channel.
9. The intelligent perceived image acquisition method of claim 6 wherein the data organization of the intelligent perceived results is: the smart sensing result is arranged next to the last line of the processed image data and has the same line width as the image data.
10. The intelligent perceived image acquisition method of claim 9, wherein the intelligent perceived results include: at least one of the total category of the image data, the category of each pixel of the image data, the category of the key target in the image data and the coordinate information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110525713.XA CN113259604B (en) | 2021-05-14 | 2021-05-14 | Intelligent perception image acquisition device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110525713.XA CN113259604B (en) | 2021-05-14 | 2021-05-14 | Intelligent perception image acquisition device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113259604A CN113259604A (en) | 2021-08-13 |
| CN113259604B true CN113259604B (en) | 2023-05-30 |
Family
ID=77181886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110525713.XA Active CN113259604B (en) | 2021-05-14 | 2021-05-14 | Intelligent perception image acquisition device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113259604B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117176933B (en) * | 2023-11-02 | 2024-01-23 | 摩尔线程智能科技(北京)有限责任公司 | Image signal processing method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102903074A (en) * | 2012-10-12 | 2013-01-30 | 湖南大学 | Image processing apparatus based on field-programmable gate array (FPGA) |
| CN103079051A (en) * | 2012-12-19 | 2013-05-01 | 华南理工大学 | Embedded image processing system and method based on BF (blackfin531) processor |
| CN108804376A (en) * | 2018-06-14 | 2018-11-13 | 山东航天电子技术研究所 | A kind of small-sized heterogeneous processing system based on GPU and FPGA |
| CN208888840U (en) * | 2018-10-30 | 2019-05-21 | 深圳灵图慧视科技有限公司 | Image object detection device |
| CN111324081A (en) * | 2018-12-13 | 2020-06-23 | 汉能移动能源控股集团有限公司 | Intelligent integrated control device and system comprising same |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11100664B2 (en) * | 2019-08-09 | 2021-08-24 | Google Llc | Depth-aware photo editing |
| US20210064987A1 (en) * | 2019-09-03 | 2021-03-04 | Nvidia Corporation | Processor and system to convert tensor operations in machine learning |
-
2021
- 2021-05-14 CN CN202110525713.XA patent/CN113259604B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102903074A (en) * | 2012-10-12 | 2013-01-30 | 湖南大学 | Image processing apparatus based on field-programmable gate array (FPGA) |
| CN103079051A (en) * | 2012-12-19 | 2013-05-01 | 华南理工大学 | Embedded image processing system and method based on BF (blackfin531) processor |
| CN108804376A (en) * | 2018-06-14 | 2018-11-13 | 山东航天电子技术研究所 | A kind of small-sized heterogeneous processing system based on GPU and FPGA |
| CN208888840U (en) * | 2018-10-30 | 2019-05-21 | 深圳灵图慧视科技有限公司 | Image object detection device |
| CN111324081A (en) * | 2018-12-13 | 2020-06-23 | 汉能移动能源控股集团有限公司 | Intelligent integrated control device and system comprising same |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113259604A (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9906713B2 (en) | Camera command set host command translation | |
| CN111090603B (en) | LVDS-to-USB 3.0 adapter | |
| KR101654053B1 (en) | Enabling a metadata storage subsystem | |
| CN113259604B (en) | Intelligent perception image acquisition device and method | |
| US11144197B2 (en) | Electronic device performing function according to gesture input and operation method thereof | |
| CN112235525A (en) | ZYNQ-based GigE interface camera target identification method and system | |
| CN110730304B (en) | Intelligent camera for accelerating image acquisition and display | |
| CN113329166A (en) | Image capturing apparatus, device, control method, and computer-readable storage medium | |
| KR102442921B1 (en) | Electronic device capable of increasing the task management efficiency of the digital signal processor | |
| TW202344977A (en) | Memory device and method thereof | |
| US11601590B2 (en) | Interface connected to image sensor and electronic device comprising interfaces connected among plurality of processors | |
| US11611708B2 (en) | Apparatus for stabilizing digital image, operating method thereof, and electronic device having the same | |
| US10911687B2 (en) | Electronic device and method for controlling display of images | |
| WO2019196634A1 (en) | Data processing method and apparatus | |
| CN104394371A (en) | System for large amount continuous image collection and quick storage | |
| KR20220132865A (en) | Electronic device including storage and method of the same | |
| WO2014105138A1 (en) | Executing a command within a transport mechanism based on a get and set architecture | |
| CN208367733U (en) | Embedded A I machine vision hardware configuration | |
| CN209895383U (en) | High-speed transmission device for digital image big data | |
| KR102390798B1 (en) | An electronic device providing graphical content and control method | |
| KR20220016695A (en) | Electronic device and method for image segmentation based on deep learning | |
| CN114630152A (en) | Parameter transmission method and device for image processor and storage medium | |
| CN112214444A (en) | Inter-core communication method, ARM, DSP and terminal | |
| CN112771605A (en) | Electronic device and method for extending time interval during amplification based on horizontal synchronization signal | |
| CN110728934B (en) | Holographic projection brightness adjusting system and method, vehicle and storage medium |
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 |