CN111047032A - Image detection acceleration method and device and storage medium - Google Patents
Image detection acceleration method and device and storage medium Download PDFInfo
- Publication number
- CN111047032A CN111047032A CN201911024692.2A CN201911024692A CN111047032A CN 111047032 A CN111047032 A CN 111047032A CN 201911024692 A CN201911024692 A CN 201911024692A CN 111047032 A CN111047032 A CN 111047032A
- Authority
- CN
- China
- Prior art keywords
- detection
- image detection
- task
- image
- nnie
- 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
Images
Classifications
-
- 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
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Neurology (AREA)
- Facsimiles In General (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to the field of object detection, and in particular, to an acceleration method and apparatus for image detection, and a storage medium. The acceleration method of image detection includes step S10: receiving a detection task; step S20: setting a delay time; step S30: executing the detection task through a neural Network forward Inference engine (NNIE) to perform a first operation; step S40: according to the first operation result, continuously executing the detection task through a Central Processing Unit (CPU) to perform a second operation; step S50: and when the execution time of the detection task reaches the delay time, triggering the next NNIE to execute the next detection task. By the technical scheme provided by the invention, the real-time processing speed is increased, the detection effect is improved while the timeliness is ensured, and the utilization rate of a CPU is increased.
Description
Technical Field
The present invention relates to the field of object detection, and in particular, to an acceleration method and apparatus for image detection, and a storage medium.
Background
The NNIE is a hardware unit which is specially used for accelerating the Neural Network, particularly a deep learning convolutional Neural Network, and is used for accelerating the processing of the Neural Network, when the NNIE is used for detecting pictures/images, a single NNIE can only process the detection task of one picture/image at the same time point, and meanwhile, the NNIE and a Central Processing Unit (CPU) must be in a serial operation mode, namely, after the NNIE is processed, the NNIE can be handed to the CPU for the next operation, so that the existing detection processing cannot simultaneously meet the problems of high processing speed and good detection effect, the resolution of a model input picture with good detection effect is large, the Network model is large, but the processing speed is slow, and the real-time requirement is difficult to meet; the resolution of a model input picture with good real-time performance is small, a network model is small, but the detection effect is poor, and meanwhile, when a large number of pictures and images are detected, the problems of low detection efficiency and low CPU utilization rate exist.
Disclosure of Invention
The invention mainly aims to provide an image detection acceleration method, an image detection acceleration device and a storage medium, and aims to solve the problem that image detection by using NNIE in the prior art cannot meet real-time performance and detection effect.
In order to achieve the above object, the present invention provides an acceleration method of image detection, the method comprising:
step S10: receiving a detection task;
step S20: setting a delay time;
step S30: executing the detection task through a neural Network forward Inference engine (NNIE) to perform a first operation;
step S40: according to the first operation result, continuously executing the detection task through a Central Processing Unit (CPU) to perform a second operation;
step S50: and when the execution time of the detection task reaches the delay time, triggering the next NNIE to execute the next detection task.
Further, the delay time is greater than 0 and less than the time for completing the detection task once.
Preferably, the delay time is 40 milliseconds.
Further, the first operation and the second operation are sequentially executed in a single detection task cycle until the detection task is completed at the current time.
Further, after the last NNIE starts to receive and execute the inspection task, the delay time also elapses, the first NNIE is triggered to receive and execute the next inspection task, and the inspection tasks are executed in a cycle in sequence.
Further, the detection task includes image detection in an image or video sequence.
Further, a neural network is used to detect images or images in a sequence of video frames.
Preferably, the frame rate of the image is 30fps (Frames Per Second).
In order to achieve the above object, the present invention further provides an image detection acceleration apparatus, which includes a memory and a processor, wherein the memory stores an image detection acceleration program executable on the processor, and the image detection acceleration program implements the image detection acceleration method when executed by the processor.
In addition, to achieve the above object, the present invention further provides a storage medium, wherein the storage medium is a computer-readable storage medium, and the storage medium stores thereon an image detection acceleration program, which is executable by one or more processors to implement the steps of the image detection acceleration method.
Compared with the prior art, the image detection acceleration method, the image detection acceleration device and the storage medium provided by the invention have the advantages that the parallel processing of detection tasks is realized, each NNIE is ensured to process different detection tasks through a delay trigger mechanism, the detection speed is improved, the real-time speed is ensured to be high, the detection effect is improved, and the utilization rate of a Central Processing Unit (CPU) is also improved.
Drawings
Fig. 1 is a schematic flow chart of an acceleration method for image detection according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating an operation principle of an acceleration method for image detection according to an embodiment of the present invention;
FIG. 3 is a diagram of a prior art single NNIE processing detection task;
FIG. 4 is a schematic diagram illustrating an internal structure of an acceleration apparatus for image detection according to an embodiment of the present invention;
fig. 5 is a block diagram illustrating an acceleration procedure of image detection in an acceleration apparatus for image detection according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit 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.
Referring to fig. 1, fig. 1 is a flowchart illustrating an image detection acceleration method according to an embodiment of the present invention, for accelerating image detection and improving image detection efficiency. The method may be performed by an apparatus, which may be implemented by software and/or hardware. The image detection acceleration method comprises the following steps:
step S10: a detection task is received. Specifically, the detection task is as follows: after the images in the video frame sequence are acquired, the images in the video frame sequence are detected by adopting a neural network. In more detail, in practical application, the present invention acquires video data through a camera to acquire an image with a sequence of video frames.
Step S20: setting a delay time; and setting the delay time as d, wherein the delay time d is greater than 0 and less than the detection time of the detection task at a single time.
Step S30: the detection task is executed by a first Neural Network Inference Engine (NNIE) to perform a first operation. Referring to FIG. 2, in particular, the end of the time when the first operation of the detection task is performed by the first NNIE1 is T1; the first NNIE1 produces a first operation result after performing a first operation.
Step S40: and executing the detection task through a Central Processing Unit (CPU) according to the first operation result so as to perform a second operation. The time end point of the second operation of the detection task executed by the CPU is T2, please refer to fig. 2, the time point T1 is the start point of the second operation, the time point T2 is the end point of the second operation, and is also the start point of the next first operation, and the first operation and the second operation are sequentially and circularly executed until the detection task is completed once.
Step S50: and when the execution time of the detection task reaches the delay time, triggering the next NNIE to execute the next detection task. Specifically, when the inspection task being executed reaches the delay time d, the second NNIE is triggered to execute the next inspection task.
In more detail, by analogy, when there is an nth NNIEn to perform an nth sensing task, n delay times d are set in sequence, and an n +1 th NNIE is triggered to perform an n +1 th sensing task.
Further, after the last NNIE executes the detection task, similarly, the delay time d is set, and when the first NNIE is in an idle state, the first NNIE is triggered to execute the new detection task again, and the new detection task is executed in a cycle mode sequentially.
In the embodiment of the invention, for each received detection task, the detection task needs to be executed twice: the first time is for a first operation by the NNIE and the second time is for a second operation by the CPU. The second operation is dependent on the first operation result. And when the first NNIE is used for carrying out first operation, the CPU is in an idle state.
Referring to fig. 2, in an embodiment, the time required for executing a detection task is set to be 100 milliseconds (ms), the delay time d is set to be 40ms, wherein the first operation time required for the NNIE to perform the first operation is 70ms, the Second operation time T2 required for the CPU to perform the Second operation is 30ms, and the frame rate of the image is 30fps (Frames Per Second), that is, the image is updated 33 ms; the speed of executing the detection task by using a single NNIE is set to be 10fps, the task detection of a single image needs to be executed for 3 times by using the single NNIE, and the single NNIE is executed after being executed, and the utilization rate of a single CPU is 30%.
In the present invention, different single NNIEs are triggered by a delayed trigger mechanism. The method comprises the steps that when the first NNIE starts to execute a detection task 40ms after the first NNIE starts to execute the detection task, the second NNIE is triggered to start to execute the detection task, so that an input image of the second NNIE and an input image of the first NNIE are not in the same frame, unnecessary repeated operation is avoided, the second NNIE is triggered to start to execute after the first NNIE executes 40ms, the two NNIEs are guaranteed to be input into different images, the detection speed is greatly improved, supposing that a single NNIE can detect x pictures within T +40ms, the multiple NNIEs can detect nx pictures within T +40ms, the detection task is executed for a long time, the processing speed of the multiple NNIEs is improved by n times, and meanwhile, the utilization rate of a CPU is improved.
Referring to fig. 3, a schematic diagram of a single NNIE processing inspection task in the prior art is shown, in a case of using the model, the speed of the single NNIE running the inspection task is 10fps, the real-time performance is poor, and most of the time is running under NNIE, at this time, the CPU is in an idle state, and the usage rate of the CPU is low.
Compared with the prior art, the image detection acceleration method, the image detection acceleration device and the storage medium provided by the invention have the advantages that the parallel processing of detection tasks is realized, the delay trigger mechanism is adopted to ensure that each NNIE processes different detection tasks, the detection speed of n NNIEs is increased by n times compared with the processing speed of the original NNIE during the detection task for a long time, the real-time speed is ensured to be high, the detection effect is improved, and the utilization rate of a Central Processing Unit (CPU) is also improved.
The invention also provides an accelerating device for image detection. Fig. 4 is a schematic diagram illustrating an internal structure of an acceleration apparatus for image detection according to an embodiment of the present invention.
In this embodiment, the image detection acceleration device may be a PC (Personal Computer), or may be a terminal device such as a smart phone, a tablet Computer, or a mobile Computer. The image detection acceleration device comprises at least a memory 11, a processor 12, a communication bus 13, and a network interface 14.
The memory 11 includes at least one type of readable storage medium, which includes a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like. The memory 11 may in some embodiments be an internal storage unit of the image-detecting acceleration device, for example a hard disk of the image-detecting acceleration device. The memory 11 may also be an external storage device of the image detection acceleration apparatus in other embodiments, such as a plug-in hard disk provided on the image detection acceleration apparatus, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the memory 11 may also include both an internal storage unit of the acceleration apparatus for image detection and an external storage device. The memory 11 may be used not only to store application software installed in the acceleration apparatus for image detection and various types of data, such as a code of an acceleration program for image detection, but also to temporarily store data that has been output or is to be output.
The processor 12 may be, in some embodiments, a Central Processing Unit (CPU), an Inference Engine (NNIE), a controller, a microcontroller, a microprocessor or other data Processing chip, which is configured to run program code stored in the memory 11 or process data, such as an acceleration program for performing image detection.
The communication bus 13 is used to realize connection communication between these components.
The network interface 14 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), and is typically used to establish a communication link between the image detection acceleration apparatus and other electronic devices.
Optionally, the image detection acceleration device may further include a user interface, the user interface may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface may further include a standard wired interface and a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the image-capturing acceleration device and for displaying a visual user interface.
Fig. 4 only shows the image detection acceleration device with the components 11-14 and the acceleration program of the image detection, and it will be understood by those skilled in the art that the structure shown in fig. 4 does not constitute a limitation of the image detection acceleration device, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
In the embodiment of the acceleration device for image detection shown in fig. 4, the memory 11 stores an acceleration program for image detection; the processor 12, when executing the acceleration program for image detection stored in the memory 11, implements the following steps:
step S10: receiving a detection task;
step S20: setting a delay time;
step S30: executing the detection task through the NNIE to perform a first operation;
step S40: according to the first operation result, continuously executing the detection task through a CPU to perform a second operation;
step S50: and when the execution time of the detection task reaches the delay time, triggering the next NNIE to execute the next detection task.
Referring to fig. 5, a schematic diagram of program modules of an acceleration procedure of image detection in an embodiment of the acceleration apparatus for image detection according to the present invention is shown, in which the acceleration procedure of image detection can be divided into a receiving module 10, a first operation module 20, a second operation module 30, a setting module 40, and a triggering module 50, and exemplarily:
a receiving module 10, configured to receive a detection task;
a first operation module 20, wherein the NNIE executes the detection task to perform a first operation;
a second operation module 30, configured to execute the detection task through a CPU according to the first operation result to perform a second operation;
a setting module 40, configured to set a delay time;
and the triggering module 50 is used for triggering the next NNIE to execute the next detection task when the execution time of the detection task reaches the delay time.
The functions or operation steps implemented when the program modules such as the receiving module 10, the first operation module 20, the second operation module 30, the setting module 40, and the triggering module 50 are executed are substantially the same as those of the above embodiments, and are not described herein again.
Furthermore, an embodiment of the present invention further provides a storage medium, where the storage medium is a computer-readable storage medium, and the storage medium stores thereon an acceleration program for image detection, where the acceleration program for image detection is executable by one or more processors to implement the following operations:
step S10: receiving a detection task;
step S20: setting a delay time;
step S30: executing the detection task through the NNIE to perform a first operation;
step S40: according to the first operation result, continuously executing the detection task through a CPU to perform a second operation;
step S50: and when the execution time of the detection task reaches the delay time, triggering the next NNIE to execute the next detection task.
The storage medium of the present invention is substantially the same as the above-mentioned embodiments of the acceleration method and apparatus for image detection, and will not be described in detail herein.
It should be noted that the above-mentioned numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method 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, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. An acceleration method for image detection, the method comprising:
step S10: receiving a detection task;
step S20: setting a delay time;
step S30: executing the detection task through a neural Network forward Inference engine (NNIE) to perform a first operation;
step S40: according to the first operation result, continuously executing the detection task through a Central Processing Unit (CPU) to perform a second operation;
step S50: and when the execution time of the detection task reaches the delay time, triggering the next NNIE to execute the next detection task.
2. The method according to claim 1, wherein the delay time is greater than 0 and less than the time for completing a single detection task.
3. An acceleration method of image detection according to claim 1 or 2, characterized in that said delay time is 40 milliseconds.
4. The method according to claim 1 or 2, wherein the first operation and the second operation are sequentially executed in a single detection task loop until the current detection task is completed.
5. The method for accelerating image inspection as claimed in claim 1 or 2, wherein after the last NNIE starts to receive and execute the inspection task, a delay time also elapses, the first NNIE is triggered to receive and execute the next inspection task, and the inspection tasks are executed circularly in sequence.
6. An accelerated method of image detection as claimed in claim 1 or 2, characterized in that the detection task comprises image detection in an image or video sequence.
7. An accelerated method of image detection as claimed in claim 6, characterized in that the images or images in a sequence of video frames are detected using a neural network.
8. The image detection acceleration method according to claim 6, wherein the frame rate of the image is 30fps (Frames Per Second, number of transmission Frames Per Second).
9. An image detection acceleration device, characterized in that the image detection acceleration device comprises a memory and a processor, the memory stores an image detection acceleration program which can run on the processor, and the image detection acceleration program is executed by the processor to realize the steps of the image detection acceleration method according to any one of claims 1 to 8.
10. A storage medium, characterized in that the storage medium is a computer-readable storage medium, and the storage medium stores thereon an image detection acceleration program, which is executable by one or more processors to implement the steps of the image detection acceleration method according to any one of claims 1 to 8.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911024692.2A CN111047032A (en) | 2019-10-25 | 2019-10-25 | Image detection acceleration method and device and storage medium |
| PCT/CN2020/123320 WO2021078271A1 (en) | 2019-10-25 | 2020-10-23 | Method and device for accelerating image detection, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911024692.2A CN111047032A (en) | 2019-10-25 | 2019-10-25 | Image detection acceleration method and device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111047032A true CN111047032A (en) | 2020-04-21 |
Family
ID=70231810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911024692.2A Pending CN111047032A (en) | 2019-10-25 | 2019-10-25 | Image detection acceleration method and device and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111047032A (en) |
| WO (1) | WO2021078271A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021078271A1 (en) * | 2019-10-25 | 2021-04-29 | 深圳市道通智能航空技术有限公司 | Method and device for accelerating image detection, and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170300362A1 (en) * | 2016-04-14 | 2017-10-19 | International Business Machines Corporation | Performance optimization of hardware accelerators |
| CN109800705A (en) * | 2019-01-17 | 2019-05-24 | 深圳英飞拓科技股份有限公司 | Accelerate the method and device of Face datection rate |
| CN110109764A (en) * | 2019-05-15 | 2019-08-09 | 重庆天蓬网络有限公司 | Delayed tasks creation method, device, medium and electronic equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8670149B2 (en) * | 2009-08-03 | 2014-03-11 | Printable Technologies Inc. | Apparatus and methods for image processing optimization for variable data printing |
| CN104267965B (en) * | 2014-10-14 | 2018-05-04 | 北京国双科技有限公司 | A kind of data processing method, device and server |
| CN110334577B (en) * | 2019-05-05 | 2022-09-16 | 四川盛通智联网络科技有限公司 | Face recognition method based on Haisi security chip |
| CN111047032A (en) * | 2019-10-25 | 2020-04-21 | 深圳市道通智能航空技术有限公司 | Image detection acceleration method and device and storage medium |
-
2019
- 2019-10-25 CN CN201911024692.2A patent/CN111047032A/en active Pending
-
2020
- 2020-10-23 WO PCT/CN2020/123320 patent/WO2021078271A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170300362A1 (en) * | 2016-04-14 | 2017-10-19 | International Business Machines Corporation | Performance optimization of hardware accelerators |
| CN109800705A (en) * | 2019-01-17 | 2019-05-24 | 深圳英飞拓科技股份有限公司 | Accelerate the method and device of Face datection rate |
| CN110109764A (en) * | 2019-05-15 | 2019-08-09 | 重庆天蓬网络有限公司 | Delayed tasks creation method, device, medium and electronic equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021078271A1 (en) * | 2019-10-25 | 2021-04-29 | 深圳市道通智能航空技术有限公司 | Method and device for accelerating image detection, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021078271A1 (en) | 2021-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11016641B2 (en) | Method and apparatus for taking screenshot of screen of application in mobile terminal | |
| CN106021421B (en) | method and device for accelerating webpage rendering | |
| CN107247540B (en) | Application icon adjusting method and device | |
| US20150234522A1 (en) | Touch event scan method, electronic device and storage medium | |
| CN110825458A (en) | Background application cleaning method and device and computer readable storage medium | |
| EP3671627A1 (en) | Image processing method and device | |
| CN113535364A (en) | Task scheduling method and device | |
| CN109388737B (en) | Method and device for sending exposure data of content item and storage medium | |
| CN111047032A (en) | Image detection acceleration method and device and storage medium | |
| US20170169042A1 (en) | Webpage display method, mobile terminal, intelligent terminal, computer program and storage medium | |
| CN112363919B (en) | User interface AI automatic test method, device, equipment and storage medium | |
| CN105893908A (en) | Two-dimensional code image identification method and device | |
| CN113190427A (en) | Caton monitoring method and device, electronic equipment and storage medium | |
| CN109246468B (en) | Video list switching method, device and storage medium based on education system | |
| US8922491B2 (en) | Method and apparatus enabling keystroke acceleration | |
| US20150145749A1 (en) | Image processing apparatus and image processing method | |
| CN113037997A (en) | Image processing method and device and electronic equipment | |
| CN114554110B (en) | Video generation method, device, electronic equipment and storage medium | |
| CN110515834B (en) | Interface testing method and device, mobile terminal and storage medium | |
| CN111506499B (en) | Method and device for detecting availability of parameters in applet and electronic equipment | |
| CN112347902A (en) | Method for performing touch interaction by using camera, electronic equipment and storage medium | |
| US20220027111A1 (en) | Adjusting camera operation for encoded images | |
| CN108052525B (en) | Method and device for acquiring audio information, storage medium and electronic equipment | |
| KR20130141259A (en) | Method for processing executing image by separating screen and recording-medium recorded program thereof | |
| JP2019518255A (en) | Presentation method of network activity indicator, electronic device, computer readable storage medium and system |
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 | ||
| CB02 | Change of applicant information |
Address after: 518055 Shenzhen, Guangdong, Nanshan District Xili street, No. 1001, Zhiyuan Road, B1 9. Applicant after: Shenzhen daotong intelligent Aviation Technology Co.,Ltd. Address before: 518055 Shenzhen, Guangdong, Nanshan District Xili street, No. 1001, Zhiyuan Road, B1 9. Applicant before: AUTEL ROBOTICS Co.,Ltd. |
|
| CB02 | Change of applicant information |