CN111711744A - Camera and image processing method - Google Patents
Camera and image processing method Download PDFInfo
- Publication number
- CN111711744A CN111711744A CN201910204050.4A CN201910204050A CN111711744A CN 111711744 A CN111711744 A CN 111711744A CN 201910204050 A CN201910204050 A CN 201910204050A CN 111711744 A CN111711744 A CN 111711744A
- Authority
- CN
- China
- Prior art keywords
- image
- processor
- image analysis
- arm processor
- camera
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/10—Cameras or camera modules comprising electronic image sensors; Control thereof for generating image signals from different wavelengths
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Abstract
The embodiment of the invention discloses a camera and an image processing method. The camera comprises an image sensor, a data transmission interface and a main control chip, wherein the main control chip comprises a first ARM processor, an ISP image processor and at least two DSP digital processors; the image sensor is electrically connected with the ISP image processor, the ISP image processor is electrically connected with the first ARM processor, the first ARM processor is respectively and electrically connected with the at least two DSP digital processors, and the at least two DSP digital processors respectively carry out image analysis on the received image to obtain an image analysis result; the data transmission interface is respectively and electrically connected with the first ARM processor and the at least two DSP digital processors. The camera provided by the embodiment of the invention has the image shooting function and the image analysis processing function, does not need to upload the shot image to an edge server or a cloud end, can realize off-line processing, further avoids the problem of low response speed caused by data transmission, and simultaneously reduces the hardware cost.
Description
Technical Field
The embodiment of the invention relates to an image processing technology, in particular to a camera and an image processing method.
Background
Since a large amount of information is contained in an image, a large amount of feature information in the image can be extracted by an image processing technique, and thus the image processing technique is widely used in various fields.
At present, a conventional camera has only an image capturing function, and transmits a captured image to an image processing computing platform, such as cloud computing and edge computing. Illustratively, referring to fig. 1A, fig. 1A is a schematic diagram of a cloud computing-based image processing in the prior art. The camera collects image data, transmits the image data to the server, transmits the image data to the cloud end through the server, and performs intelligent operation at the cloud end, wherein the intelligent operation can be people or articles in an analysis image. Illustratively, referring to fig. 1B, fig. 1B is a schematic diagram of image processing based on edge calculation in the prior art. The image processing based on the edge calculation may be performed by a high-performance graphics card GPU at the edge server side. For example, the edge server may perform lightweight preprocessing, transmit the preprocessed data to the cloud, and perform complex image processing on the cloud.
In the process of implementing the invention, the inventor finds that at least the following technical problems exist in the prior art: image processing is carried out at the cloud, image data needs to be transmitted, and the problems of bandwidth and timeliness of response to an image processing result exist in the data transmission process; the image processing is carried out on the edge server, a high-performance edge server needs to be arranged, the cost is high, and meanwhile, the deployment is difficult due to the large size of the edge server; for the combination mode of cloud computing and edge computing, the cost is high, the response speed problem exists, and meanwhile, offline image data processing cannot be performed.
Disclosure of Invention
The invention provides a camera and an image processing method, which are used for realizing the acquisition and processing of images at a camera end.
In a first aspect, an embodiment of the present invention provides a camera, including an image sensor, a data transmission interface, and a main control chip, where the main control chip includes a first ARM processor, an ISP image processor, and at least two DSP digital processors;
the image sensor is electrically connected with the ISP image processor and used for acquiring image signals in a shooting range and transmitting the image signals to the ISP image processor;
the ISP image processor is electrically connected with the first ARM processor and is used for carrying out image processing on the received image signal to generate a shot image and sending the shot image to the first ARM processor;
the first ARM processor is electrically connected with the at least two DSP processors respectively and used for distributing the received images to the at least two DSP processors;
the at least two DSP digital processors respectively carry out image analysis on the received images to obtain image analysis results;
the data transmission interface is respectively electrically connected with the first ARM processor and the at least two DSP digital processors and is used for carrying out data transmission on the image analysis result and/or the shot image.
In a second aspect, an embodiment of the present invention further provides an image processing method, where the image processing method includes:
the camera collects image signals in a shooting range to generate a shot image;
the camera acquires an image analysis instruction, and performs image analysis on the shot image according to the image analysis instruction to generate an image analysis result;
and the camera outputs the shot image and/or the image analysis result.
According to the technical scheme of the embodiment of the invention, the shot image can be obtained through the image sensor and the ISP image processor, the shot image can be subjected to image analysis and processing through the DSP image processor to obtain an image analysis result, and the image analysis method has the image shooting function and the image analysis processing function, so that the shot image is not required to be uploaded to an edge server or a cloud, offline processing can be realized, the problem of low response speed caused by data transmission is further avoided, and the hardware cost is reduced.
Drawings
FIG. 1A is a schematic diagram of a prior art cloud computing based image processing;
FIG. 1B is a schematic diagram of image processing based on edge calculation in the prior art;
fig. 2 is a schematic structural diagram of a camera according to a first embodiment of the present invention;
fig. 3 is a schematic structural diagram of another camera according to the first embodiment of the present invention;
fig. 4 is a flowchart illustrating an image processing method according to a second embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 2 is a schematic structural diagram of a camera according to an embodiment of the present invention, where the camera includes an image sensor 110, a data transmission interface 120, and a main control chip 130, and the main control chip 130 includes a first ARM processor 131, an ISP image processor 132, and at least two DSP digital processors 133; the image sensor 110 is electrically connected to the ISP image processor 132, and is configured to collect an image signal within a shooting range and transmit the image signal to the ISP image processor 132;
the ISP image processor 132 is electrically connected to the first ARM processor 131, and is configured to perform image processing on the received image signal, generate a captured image, and send the captured image to the first ARM processor 131;
the first ARM processor 131 is electrically connected to the at least two DSP digital processors 133, respectively, and is configured to distribute the received image to the at least two DSP digital processors 133;
the at least two DSP 133 respectively perform image analysis on the received images to obtain image analysis results;
the data transmission interface 120 is electrically connected to the first ARM processor 131 and the at least two DSP digital processors 133, respectively, and is configured to perform data transmission on the image analysis result and/or the captured image.
In this embodiment, the image sensor 110 is disposed inside the lens of the camera, collects an image Signal in a shooting range, transmits the collected image Signal to the ISP (large Signal processing) image processor 132, and the ISP image processor 132 processes the image Signal to generate a shot image in an RGB format.
The first ARM processor 131 is used to drive and manage the ISP image processor 132 and the dsp (digital signal processing) digital processor 133. The DSP 133 is configured to perform image analysis on the image transmitted by the first ARM processor 131, where the image analysis may include, but is not limited to, face recognition, article type recognition, location recognition, and the like, and accordingly, the image analysis result may be one or more of an article recognition result, article location information, a person information recognition result, a person or a partial limb position of the person in the image. In the embodiment, the image is analyzed by the DSP 133, which is faster than a conventional CPU (Central Processing Unit), and improves the image Processing efficiency. Further, in this embodiment, at least two DSP 133 are provided, and the at least two DSP 133 are independently provided, and perform independent image analysis processing on the received image, respectively, so as to improve the image processing efficiency by multiple times. In some embodiments, at least two DSP processors in the main control chip 130 may have the same image processing function, and perform the same image analysis on the image at the same time, thereby improving the processing efficiency. In some embodiments, it may also be that at least two DSP digital processors in the main control chip 130 may have different image processing functions, and the first ARM processor 131 sends an image to a corresponding DSP digital processor according to an image analysis requirement of a user, and by setting the DSP digital processors with different functions, diversity of image processing is improved.
The data transmission interface 120 may be, for example, a USB (Universal Serial Bus) interface, and may be configured to transmit the image analysis result and/or the captured image, and optionally, the camera may determine to-be-output according to the received control instruction and the control instruction according to the received control instruction
The image analysis method can also be used for receiving a control instruction input from outside, sending the control instruction to the first ARM processor 131, supplying power to a module of the camera, receiving an upgrade data packet input from outside, sending the upgrade data packet to the first ARM processor 131, and performing corresponding upgrade processing on the first ARM processor 131 based on the upgrade data packet, wherein the upgrade data packet can be a system upgrade data packet for updating a system of the camera, or an image analysis data packet for adding an image analysis function of a DSP digital processor or updating an existing image analysis data packet. In this embodiment, the camera is provided with a data transmission interface, and correspondingly, the camera is provided with an external cable, so that equipment deployment is facilitated, and the deployment cost is reduced.
The camera provided in this embodiment can acquire the shot image through image sensor and ISP image processor, can carry out image analysis and processing to the shot image through DSP image processor, obtains image analysis result, possesses image shooting function and image analysis processing function simultaneously, need not to upload the shot image to edge server or high in the clouds, can realize off-line processing, has further avoided the slow problem of response speed because data transmission leads to, has reduced the hardware cost simultaneously.
The first ARM processor 131 has an image distribution function, and before image distribution, the first ARM processor 131 is further configured to perform sharpness recognition on an image sent by the ISP image processor 132, and cancel transmission of the image to the DSP digital processor 133 when the image sharpness is smaller than a preset sharpness. The first ARM processor 131 pre-identifies the image definition, so that the distribution of the blurred image is cancelled, and the invalid analysis of the blurred image by the DSP is avoided. And when the image definition meets the definition requirement, the image is sent to at least two DSP.
Optionally, when the images to be distributed in the first ARM processor 131 are at least two consecutive video frame images, the first ARM processor 131 distributes the at least two video frame images to the at least two DSP digital processors 133 according to a distribution rule. That is, when the camera continuously captures video frame images and sends the video frame images to the first ARM processor 131 in real time, the first ARM processor 131 sends a plurality of images to the DSP digital processor 133 according to a distribution rule, optionally, the distribution rule may be, for example, uniform distribution, which may be, for example, round-robin distribution, for example, a first DSP digital processor and a second DSP digital processor are disposed in the main control chip, the first frame image may be sent to the first DSP digital processor, the second frame image may be sent to the second DSP digital processor, the third frame image may be sent to the first DSP digital processor, the fourth frame image may be sent to the second DSP digital processor, and so on. Similarly, when the number of the DSP digital processors is greater than 2, the image may be distributed in a polling manner. It should be noted that at least two DSP digital processors herein have the same image processing function. Through carrying out even distribution with multiframe image to two at least DSP digital processing units, two at least DSP digital processing units of being convenient for carry out image processing simultaneously, improve image processing efficiency.
Correspondingly, the first ARM processor 131 is further configured to receive image analysis results fed back by the at least two DSP digital processors 133, respectively, and combine the image analysis results to generate an analysis result of the video frame. Because the at least two DSP 133 processes the images of consecutive frames independently, the first ARM processor 131 combines the image analysis results fed back by each DSP in sequence according to the distribution rule, so as to obtain the comprehensive analysis result of the images of multiple frames.
Optionally, the main control chip 130 further includes a coding unit 134, where the coding unit 134 is electrically connected to the first ARM processor 131, and is configured to receive an image sent by the first ARM processor 131, perform video format coding on at least one received image, form a coded video stream, and transmit the coded video stream based on the data transmission interface 120. The first ARM processor 131 may simultaneously send at least two video frame images to the encoding unit 134 and the DSP 133, and the encoding unit 134 may encode the at least two video frame images to form a video file.
Optionally, when the image to be distributed in the first ARM processor 131 is a single image, the first ARM processor 131 determines the target DSP digital processor according to the current working states of the at least two DSP digital processors, and sends the single image to the target DSP digital processor. The working state of the DSP digital processor may include an idle state and a busy state, and when there is an image being processed or to be processed in the DSP digital processor, it is determined that the DSP digital processor is in the busy state, otherwise, when there is no image being processed or to be processed in the DSP digital processor, it is determined that the DSP digital processor is in the idle state. And the DSP in the idle state is determined as a target DSP, and the single image is sent to the target DSP, so that the single image can be analyzed and processed quickly, the waiting time is reduced, and the response efficiency is improved. When at least two DSP are in busy state, determining the number of images to be processed in the DSP, and sending the single image to the DSP with the minimum number of images to be processed to reduce the waiting time.
Optionally, when the image to be distributed in the first ARM processor 131 is a single image, the first ARM processor performs image segmentation on the single image, and distributes the segmented image to the at least two DSP digital processors 133. The single image may be segmented into a foreground region and a background region, and the foreground region and the background region are respectively sent to different DSP digital processors. Correspondingly, the first ARM processor 131 is further configured to receive image analysis results fed back by the at least two DSP digital processors 133, respectively, and combine the image analysis results to generate an analysis result of a single image. In the present embodiment, the processing efficiency of the image is improved by regularly distributing a plurality of images or a single image.
Optionally, at least one neural network model is disposed in any one of the DSP 133, and the DSP performs image analysis on the received image based on any one of the neural network models or at least one of the cascaded neural network models. The Neural Network model may be, for example, a CNN (Convolutional Neural Network) model, and the DSP digital processor may set a plurality of Neural Network models having different image analysis functions at the same time, for example, the Neural Network model may be, but is not limited to, a scene recognition model, a face recognition model, an article recognition model, a location recognition model, and the like, each Neural Network model may be pre-trained, receive system firmware including the pre-trained Network model based on the data transmission interface 120, and upgrade the DSP digital processor based on the Network model included in the system firmware. Optionally, the system firmware may further include a camera program for upgrading the camera system.
After receiving the image, the DSP 133 may analyze the image based on one or more network models to obtain an image analysis result. Optionally, the DSP 133 obtains an image analysis instruction based on the data transmission interface 120, determines at least one target neural network model for performing image analysis according to the image analysis instruction, and performs image analysis on the image based on the at least one target neural network model. Illustratively, the image analysis instruction may be input based on the data transmission interface 120, or may also be pre-stored in a camera, the DSP digital processor 133 recognizes the image analysis instruction, and determines at least one target neural network model for performing image analysis according to the type of image analysis in the image analysis instruction, illustratively, the camera is applied to an unmanned container, continuously collects multiple frames of images through the camera, and performs image analysis on the multiple frames of images based on the DSP digital processor 133, wherein the DSP digital processor 133 pre-stores the image analysis instruction, the pre-stored image analysis instruction may be a commodity identification instruction and a commodity track identification instruction, and according to the image analysis instruction, a single network model or a cascaded network model having a commodity identification function and a commodity track identification may be determined as the target neural network model, and inputting the image into the target neural network model to obtain an image analysis result.
In this embodiment, the network model in the DSP 133 is not limited, and the network model in the DSP 133 may be updated according to the user requirement.
For example, referring to fig. 3, fig. 3 is a schematic structural diagram of another camera provided by a third embodiment of the present invention, the main control chip 130 of the camera in fig. 3 further includes a second ARM processor 135, and the second ARM processor 135 is electrically connected to the at least two DSP digital processors 133 and the data transmission interface 120, respectively, and is configured to receive image analysis results sent by the at least two DSP digital processors 133, receive a user control instruction of the data transmission interface 120, and process the image analysis results according to the user control instruction. In this embodiment, the second ARM processor 135 is configured to provide for a user to perform autonomous development, for example, function development may be performed based on image analysis results sent by at least two DSP digital processors 133, optionally, the second ARM processor 135 may be configured to determine an association relationship of a plurality of feature information in the image analysis results of multiple frames of images, and for example, when multiple frames of images include the same face image, the face recognition result of the first frame of image may be determined as the face recognition result of the same face image in the multiple frames of images, so as to reduce the repeated calculation amount. Optionally, the second ARM processor 135 may be configured to execute user control instructions based on the image analysis results. For example, when the camera is applied to an unmanned shelf, the user control instruction may be a commodity and advertisement recommendation instruction, and the second ARM processor 135 determines the age and gender of the user in front of the shelf according to the face recognition information in the image analysis result, further determines a recommended commodity and a recommended advertisement according to the above information, and displays the recommended commodity and the recommended advertisement to the user in front of the shelf.
In this embodiment, the user control instruction in the second ARM processor 135 is not limited, and can be edited according to the application scenario of the camera and the user requirement. By arranging the two ARM processors, one ARM processor is used for controlling the normal operation of the camera (driving and managing the ISP processor, the DSP processor and the like), and the other ARM processor is independently developed according to a control instruction input by a user, so that the function personalization and flexibility of the camera are improved, the traditional camera with single and unified function is replaced, and the user experience is improved.
Example two
Fig. 4 is a schematic flowchart of an image processing method according to a second embodiment of the present invention, where the method is executed by the camera provided in the second embodiment of the present invention, and implements image processing. Specifically, the image processing method includes:
s210, the camera collects image signals in a shooting range to generate a shot image.
S220, the camera acquires an image analysis instruction, and performs image analysis on the shot image according to the image analysis instruction to generate an image analysis result.
And S230, the camera outputs the shot image and/or the image analysis result.
In the embodiment, the camera performs image analysis on the shot image on the basis of having an image shooting function to obtain an image analysis result, and outputs one or both of the shot image and the image analysis result according to the user requirement. The image analysis instruction may be pre-stored in the camera, or may be input by the user based on the input device, which is not limited in this embodiment. Illustratively, the image analysis instruction may be, but is not limited to, an article identification instruction, an article position identification instruction, a face identification instruction, a person or person local limb position identification instruction, and the like, and accordingly, the image analysis result includes at least one of the following: the object recognition result, the object position information, the person information recognition result, and the position of the person or the partial body of the person in the image. Optionally, the image analysis of the shot image is performed according to the image analysis instruction, and the image analysis includes inputting the shot image to a target neural network model according to the image analysis instruction, and analyzing the shot image based on the neural network model to obtain an image analysis result. The target neural network model can be a single neural network model or a cascaded neural network model, and is determined according to the image analysis type in the image analysis instruction.
When the camera continuously collects multiple frames of images, the camera determines the information and the action track of the articles and/or people in the shooting range of the camera according to the image analysis result of the multiple frames of images. Specifically, the positions of the objects and/or persons in the image analysis result may be stitched according to the image acquisition time stamp to form the motion track of the objects and/or persons within the shooting range. For example, when the camera is applied to an unmanned container, when a user is determined to shoot a range through the camera, multi-frame images are continuously collected, the position of a hand in each frame image and the position of a commodity held in the hand are identified, image analysis results in the multi-frame images are spliced, the action track of the user after entering the shooting range and the track of the commodity are determined, and when the track of the commodity is matched with a selling record, the selling success is determined. Specifically, when the user can obtain a box of milk from the unmanned container according to the image analysis result, the payment information of the milk exists in the unmanned container, and the selling success is determined.
Optionally, when the plurality of shot images are continuous video frame images, the camera performs video format coding on the shot images to generate and output a coded video stream. In this embodiment, the continuous images collected by the camera may be encoded into a video stream, which is convenient for storage and user lookup, and the images are compressed to reduce the occupied memory space.
According to the technical scheme, the camera can carry out image acquisition and image analysis locally, the image is not required to be sent to the edge server or the cloud, network data transmission is not involved, offline processing can be achieved, further, the image is shot, image analysis is carried out locally on the camera, hardware devices such as the edge server are not required to be arranged, the cost is low, data is not required to be transmitted, the response time is saved, and the response efficiency is accelerated.
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 (14)
1. A camera comprises an image sensor, a data transmission interface and a main control chip, and is characterized in that the main control chip comprises a first ARM processor, an ISP image processor and at least two DSP digital processors;
the image sensor is electrically connected with the ISP image processor and used for acquiring image signals in a shooting range and transmitting the image signals to the ISP image processor;
the ISP image processor is electrically connected with the first ARM processor and is used for carrying out image processing on the received image signal to generate a shot image and sending the shot image to the first ARM processor;
the first ARM processor is electrically connected with the at least two DSP processors respectively and used for distributing the received images to the at least two DSP processors;
the at least two DSP digital processors respectively carry out image analysis on the received images to obtain image analysis results;
the data transmission interface is respectively electrically connected with the first ARM processor and the at least two DSP digital processors and is used for carrying out data transmission on the image analysis result and/or the shot image.
2. The camera according to claim 1, wherein the main control chip further comprises an encoding unit, and the encoding unit is electrically connected to the first ARM processor, and configured to receive an image sent by the first ARM processor, perform video format encoding on at least one received image, form an encoded video stream, and transmit the encoded video stream based on the data transmission interface.
3. The camera according to claim 1, wherein when the image to be distributed in the first ARM processor is a succession of at least two video frame images, the first ARM processor distributes the at least two video frame images to the at least two DSP digital processors according to a distribution rule;
and the first ARM processor is also used for respectively receiving image analysis results fed back by the at least two DSP digital processors, merging the image analysis results and generating the analysis result of the video frame.
4. The camera according to claim 1, wherein when the image to be distributed in the first ARM processor is a single image, the first ARM processor determines a target DSP digital processor according to the current operating states of the at least two DSP digital processors, and sends the single image to the target DSP digital processor.
5. The camera according to claim 1, wherein when the image to be distributed in the first ARM processor is a single image, the first ARM processor performs image segmentation on the single image, and distributes the segmented image to the at least two DSP digital processors;
and the first ARM processor is also used for respectively receiving the image analysis results fed back by the at least two DSP digital processors, merging the image analysis results and generating the analysis result of the single image.
6. The camera according to any of claims 1 to 5, wherein at least one neural network model is provided in any of the DSP, and the DSP performs image analysis on the received image based on any of the neural network models or at least one neural network model in cascade.
7. The camera according to claim 6, wherein the DSP digital processor obtains image analysis instructions, determines at least one target neural network model for image analysis according to the image analysis instructions, and performs image analysis on the image based on the at least one target neural network model.
8. The camera of any of claims 1 to 5, wherein the image analysis results comprise at least one of: the object recognition result, the object position information, the person information recognition result, and the position of the person or the partial body of the person in the image.
9. The camera of any of claims 1 to 5, wherein the first ARM processor is further configured to perform sharpness recognition on the image sent by the ISP image processor, and when the sharpness of the image is less than a preset sharpness, the transmission of the image to the DSP digital processor is cancelled.
10. The camera according to any one of claims 1 to 5, wherein the main control chip further comprises a second ARM processor, and the second ARM processor is electrically connected to the at least two DSP digital processors and the data transmission interface, and is configured to receive image analysis results sent by the at least two DSP digital processors, receive user control instructions of the data transmission interface, and process the image analysis results according to the user control instructions.
11. An image processing method, comprising:
the camera collects image signals in a shooting range to generate a shot image;
the camera acquires an image analysis instruction, and performs image analysis on the shot image according to the image analysis instruction to generate an image analysis result;
and the camera outputs the shot image and/or the image analysis result.
12. The method of claim 11, further comprising:
and when the plurality of shot images are continuous video frame images, the camera carries out video format coding on the shot images to generate a coded video stream and outputs the coded video stream.
13. The method of claim 11, wherein the image analysis result comprises at least one of: the object recognition result, the object position information, the person information recognition result, and the position of the person or the partial body of the person in the image.
14. The method of claim 13, further comprising:
and the camera determines the information and the action track of the object and/or the person in the shooting range of the camera according to the image analysis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910204050.4A CN111711744B (en) | 2019-03-18 | 2019-03-18 | Camera and image processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910204050.4A CN111711744B (en) | 2019-03-18 | 2019-03-18 | Camera and image processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111711744A true CN111711744A (en) | 2020-09-25 |
| CN111711744B CN111711744B (en) | 2021-10-15 |
Family
ID=72536062
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910204050.4A Active CN111711744B (en) | 2019-03-18 | 2019-03-18 | Camera and image processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111711744B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201540568U (en) * | 2009-12-24 | 2010-08-04 | 中国航天科工集团第三研究院第八三五八研究所 | Double CPU system platform with coprocessing function |
| CN202395911U (en) * | 2012-01-12 | 2012-08-22 | 西安科技大学 | Embedded remote wireless real-time image processing system for industrial flaw detection |
| CN102881159A (en) * | 2011-07-14 | 2013-01-16 | 中国大恒(集团)有限公司北京图像视觉技术分公司 | Embedded double-DSP (digital signal processing) information data processing device and method |
| CN104092987A (en) * | 2014-07-10 | 2014-10-08 | 公安部第一研究所 | Bimodal dual-feedback self-adaptation target tracking system and method and control circuit |
| CN104715571A (en) * | 2013-12-12 | 2015-06-17 | 姚萍 | Fatigue driving alarming system based on multi-feature detection |
| CN104811597A (en) * | 2015-04-27 | 2015-07-29 | 江苏中科贯微自动化科技有限公司 | Integrated smart camera |
| CN105572541A (en) * | 2015-12-07 | 2016-05-11 | 浙江大学 | High-voltage line patrol fault detection method and system based on visual attention mechanism |
| CN105573204A (en) * | 2015-12-22 | 2016-05-11 | 深圳市东微智能科技有限公司 | Multi-processor digital audio frequency matrix control device and method |
| CN106910085A (en) * | 2017-01-06 | 2017-06-30 | 哈尔滨学院 | A kind of product intelligent based on electric business platform recommends method and its system |
| CN107203987A (en) * | 2017-06-07 | 2017-09-26 | 云南师范大学 | A kind of infrared image and low-light (level) image real time fusion system |
| CN107610108A (en) * | 2017-09-04 | 2018-01-19 | 腾讯科技（深圳）有限公司 | Image processing method and device |
| CN207008762U (en) * | 2017-01-18 | 2018-02-13 | 江苏阿瑞斯智能设备有限公司 | Paper money number intelligent identification device based on DSP |
| CN107993599A (en) * | 2017-12-29 | 2018-05-04 | 黄睿 | A kind of clothes recommend method and advertisement machine |
| CN208509142U (en) * | 2018-07-26 | 2019-02-15 | 苏州仓格汽车科技有限公司 | A kind of automatic driving car panorama monitoring and platform occupant detection system |
-
2019
- 2019-03-18 CN CN201910204050.4A patent/CN111711744B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201540568U (en) * | 2009-12-24 | 2010-08-04 | 中国航天科工集团第三研究院第八三五八研究所 | Double CPU system platform with coprocessing function |
| CN102881159A (en) * | 2011-07-14 | 2013-01-16 | 中国大恒(集团)有限公司北京图像视觉技术分公司 | Embedded double-DSP (digital signal processing) information data processing device and method |
| CN202395911U (en) * | 2012-01-12 | 2012-08-22 | 西安科技大学 | Embedded remote wireless real-time image processing system for industrial flaw detection |
| CN104715571A (en) * | 2013-12-12 | 2015-06-17 | 姚萍 | Fatigue driving alarming system based on multi-feature detection |
| CN104092987A (en) * | 2014-07-10 | 2014-10-08 | 公安部第一研究所 | Bimodal dual-feedback self-adaptation target tracking system and method and control circuit |
| CN104811597A (en) * | 2015-04-27 | 2015-07-29 | 江苏中科贯微自动化科技有限公司 | Integrated smart camera |
| CN105572541A (en) * | 2015-12-07 | 2016-05-11 | 浙江大学 | High-voltage line patrol fault detection method and system based on visual attention mechanism |
| CN105573204A (en) * | 2015-12-22 | 2016-05-11 | 深圳市东微智能科技有限公司 | Multi-processor digital audio frequency matrix control device and method |
| CN106910085A (en) * | 2017-01-06 | 2017-06-30 | 哈尔滨学院 | A kind of product intelligent based on electric business platform recommends method and its system |
| CN207008762U (en) * | 2017-01-18 | 2018-02-13 | 江苏阿瑞斯智能设备有限公司 | Paper money number intelligent identification device based on DSP |
| CN107203987A (en) * | 2017-06-07 | 2017-09-26 | 云南师范大学 | A kind of infrared image and low-light (level) image real time fusion system |
| CN107610108A (en) * | 2017-09-04 | 2018-01-19 | 腾讯科技（深圳）有限公司 | Image processing method and device |
| CN107993599A (en) * | 2017-12-29 | 2018-05-04 | 黄睿 | A kind of clothes recommend method and advertisement machine |
| CN208509142U (en) * | 2018-07-26 | 2019-02-15 | 苏州仓格汽车科技有限公司 | A kind of automatic driving car panorama monitoring and platform occupant detection system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111711744B (en) | 2021-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10593049B2 (en) | System and method for real-time detection of objects in motion | |
| CN107529098A (en) | Real-time video is made a summary | |
| CN110166796B (en) | Video frame processing method and device, computer readable medium and electronic equipment | |
| CN110674918A (en) | Information processing method, device, system and storage medium | |
| US20230154104A1 (en) | UNCERTAINTY-AWARE FUSION TOWARDS LARGE-SCALE NeRF | |
| CN114612987A (en) | Expression recognition method and device | |
| CN112714282A (en) | Image processing method, apparatus, device and program product in remote control | |
| WO2020062998A1 (en) | Image processing method, storage medium, and electronic device | |
| CN109698850B (en) | Processing method and system | |
| CN111711744B (en) | Camera and image processing method | |
| CN111507466A (en) | Data processing method and device, electronic equipment and readable medium | |
| CN113284055A (en) | Image processing method and device | |
| CN109121194B (en) | Method and apparatus for state transition of electronic device | |
| KR20200110257A (en) | Method for extracting joint information using machine learning based on cloud server and apparatus thereof | |
| US20220294971A1 (en) | Collaborative object detection | |
| CN115103204B (en) | Method and device for realizing edge intelligent application supporting AI engine | |
| CN113450276B (en) | Video image enhancement method, model training method thereof and related equipment | |
| CN109981969B (en) | Intelligent electronic equipment, image processing unit and image processing method | |
| Kim et al. | DNN inference offloading for object detection in 5G multi-access edge computing | |
| CN111417016A (en) | Attitude estimation method, server and network equipment | |
| CN115268285A (en) | Device control method, device, electronic device, and storage medium | |
| CN113887319A (en) | Three-dimensional attitude determination method and device, electronic equipment and storage medium | |
| CN111953897B (en) | Method and device for rapidly shooting image | |
| CN111385586A (en) | Robot video transmission method and system | |
| CN216661188U (en) | FPGA and ARM's waste classification 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |