CN110615293B - Automatic image data acquisition system, automatic image data acquisition method and automatic image data identification system - Google Patents
Automatic image data acquisition system, automatic image data acquisition method and automatic image data identification system Download PDFInfo
- Publication number
- CN110615293B CN110615293B CN201810631957.4A CN201810631957A CN110615293B CN 110615293 B CN110615293 B CN 110615293B CN 201810631957 A CN201810631957 A CN 201810631957A CN 110615293 B CN110615293 B CN 110615293B
- Authority
- CN
- China
- Prior art keywords
- image data
- material storage
- storage box
- outlet
- inlet
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G65/00—Loading or unloading
- B65G65/005—Control arrangements
-
- 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
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
-
- 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
Abstract
The invention discloses an automatic image data acquisition system, which comprises: the material storage box, the outflow control device, the circulating power device and the camera device; the material storage box is provided with a material storage space, and the material storage space is used for loading materials needing to acquire images; the upper part and the lower part of the material storage box are respectively provided with an inlet and an outlet, and the inlet and the outlet are respectively used for the material to enter and flow out; the outflow control device is arranged at the outlet of the material storage box and is used for controlling the material to flow out from the outlet; the circulating power device is used for transmitting the material from the outlet of the material storage box to the inlet of the material storage box when the material flows out from the outlet, so that the material enters the material storage space of the material storage box again from the inlet; and the camera device is used for acquiring image data of the material in the material storage box according to a preset rule.
Description
Technical Field
The invention relates to the technical field of intelligent household appliances, in particular to an automatic image data acquisition system, an automatic image data acquisition method and an automatic image data identification system.
Background
At present, artificial intelligence is a challenging subject of a gate, including very extensive science, which is composed of different fields, such as machine learning, computer vision, bioscience, neural network science, energy technology, genetic engineering, and the like. The main goal of artificial intelligence research is to have machines perform complex tasks that require human intelligence to complete, such as recognition tasks. The premise of artificial intelligence implementation is to have sufficient and reliable data as a training set.
Data acquisition needs certain repeatability, and if the operation of gathering is carried out to the manual work obviously is a very big waste to the human cost, moreover, because the manual data acquisition can produce the problem that shooting angle, shooting distance change sometimes, consequently probably is unfavorable for comparing and referring to between the data. Also have the automatic device that carries out data acquisition among the prior art, these devices set up the automatic camera of shooing by the material that needs to gather usually, and the camera is taken a picture and is taken a sample once every certain time. However, when subsequent data processing is carried out, the problem that the acquired images are highly repeated frequently occurs due to no human intervention in the sampling process, the reliability of the acquired data is influenced, the confidence coefficient of an image training model is greatly reduced, and the accuracy of artificial intelligence recognition is further influenced.
Therefore, how to automatically acquire image data with high reliability becomes a technical problem which needs to be solved urgently at the present stage in the field.
Disclosure of Invention
In view of the above, the main objective of the present invention is to provide a system capable of automatically collecting image data, the reliability of the collected image data is high, and the whole collection process can realize full-automatic unmanned monitoring; further, the automatic identification of the material is realized by utilizing the acquired image data.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
the embodiment of the invention provides an automatic image data acquisition system, which comprises: the material storage box, the outflow control device, the circulating power device and the camera device;
the material storage box is provided with a material storage space, and the material storage space is used for loading materials needing to acquire images; the upper part and the lower part of the material storage box are respectively provided with an inlet and an outlet, and the inlet and the outlet are respectively used for the material to enter and flow out;
the outflow control device is arranged at the outlet of the material storage box and is used for controlling the material to flow out from the outlet;
the circulating power device is used for transmitting the material from the outlet of the material storage box to the inlet of the material storage box when the material flows out from the outlet, so that the material enters the material storage space of the material storage box again from the inlet;
and the camera device is used for acquiring image data of the material in the material storage box according to a preset rule.
In the above scheme, the horizontal cross-sectional area of the material storage space is gradually reduced from the inlet to the outlet.
In the above scheme, be provided with the helping hand landslide in the material storage box, the helping hand landslide is used for accelerating the gliding of the material that is located in the material storage space and assemble to the exit.
In the above scheme, be provided with transparent window of making a video recording on the box of material storage box, camera device passes through transparent window of making a video recording is right the material in the material storage box carries out image data acquisition.
In the above scheme, the transparent camera window with the box body mutual independence of material storage box, the material of transparent camera window includes ya keli or glass.
In the above aspect, the outflow control device is further configured to stir the material when controlling the material to flow out from the outlet.
In the above scheme, the outflow control device comprises a motor and a rotating part, the motor is used for driving the rotating part to rotate, and the rotating part comprises a rotating screw, a rotating fin, a turnover door or a three-wing door.
In the above arrangement, the inlet and the outlet are connected by a pipe outside the material storage tank, and the circulation power unit is connected to a portion of the pipe near the outlet.
In the above scheme, the circulation power device comprises a blower.
In the above scheme, the device further comprises a controller, and the outflow control device, the circulating power device and the camera device are all controlled by the controller.
In the above scheme, the entrance of material storage box is provided with the protection casing, the vertical section of material storage space is the shape of falling trapezium, the vertical section of protection casing is regular trapezium shape.
In the above scheme, the method further comprises: the system comprises an Internet of things gateway and a cloud server;
the Internet of things gateway is used for acquiring image data acquired by the camera device and uploading the image data to the cloud server;
the cloud server is used for performing at least one of the following processing on the image data: and (4) classifying, storing and analyzing the images.
In the above scheme, the method further comprises: an intranet gateway and a local memory;
the intranet gateway is used for acquiring image data acquired by the camera device and transmitting the image data to the local memory;
the local memory is used for carrying out at least one of the following processing on the image data: and (4) classifying, storing and analyzing.
The embodiment of the invention also provides an automatic image data acquisition method, which is used for acquiring image data by using the automatic image data acquisition system of the embodiment of the invention and comprises the following steps:
controlling the material in the material storage box to flow out of the outlet of the material storage box based on the outflow control device;
controlling an inlet through which the material flowing out of the outlet is transmitted back to the material storage box based on the circulation power device to circulate the material into the material storage box;
and acquiring image data aiming at the materials in the material storage box according to a preset rule.
The embodiment of the invention also provides an automatic image data acquisition control device, which comprises: a controller and a memory for storing a computer program capable of running on the controller,
wherein the controller is configured to execute the steps of the method according to the embodiment of the present invention when the computer program is executed.
The embodiment of the invention also provides an automatic image data identification system, which comprises the automatic image data acquisition system and a model training module, wherein the model training module is used for training according to a neural network algorithm by adopting the image data acquired by the automatic image data acquisition system as a training data set to obtain an identification model.
In the above scheme, the system further comprises an image recognition module, wherein the image recognition module is configured to obtain image data acquired by the image data automatic acquisition system, recognize the image data based on the recognition model obtained by the model training module, and obtain a recognition result of a material included in the image data.
The invention provides an automatic image data acquisition system, which comprises: the material storage box, the outflow control device, the circulating power device and the camera device; the material storage box is provided with a material storage space, and the material storage space is used for loading materials needing to acquire images; the upper part and the lower part of the material storage box are respectively provided with an inlet and an outlet, and the inlet and the outlet are respectively used for the material to enter and flow out; the outflow control device is arranged at the outlet of the material storage box and is used for controlling the material to flow out from the outlet; the circulating power device is used for transmitting the material from the outlet of the material storage box to the inlet of the material storage box when the material flows out from the outlet, so that the material enters the material storage space of the material storage box again from the inlet; and the camera device is used for acquiring image data of the material in the material storage box according to a preset rule. Therefore, the whole system has the characteristics of simple and portable structure, easy installation and disassembly and the like; through the synergistic effect of the outflow control device and the circulating power device, the material is continuously changed, the collected images are different, and the confidence coefficient of the image training model is increased; the camera device automatically takes pictures and samples the material according to a preset rule, so that automation is completely realized; the automatic image data acquisition system provided by the invention is used for acquisition operation, so that the workload can be greatly reduced, and the labor efficiency is improved.
Drawings
FIG. 1 is a schematic diagram of an automatic image data acquisition system according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of an automatic image data acquisition method according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples.
Example one
Fig. 1 is a schematic diagram of an automatic image data acquisition system according to an embodiment of the present invention. The system comprises: a material storage box 1, an outflow control device 3, a circulating power device 5 and an image pickup device 2;
the material storage box 1 is provided with a material storage space 11, and the material storage space 11 is used for loading materials needing to acquire images; the upper and lower parts of the material storage box 1 are respectively provided with an inlet and an outlet, which are respectively used for the material to enter and flow out;
the outflow control device 3 is arranged at the outlet of the material storage box 1 and is used for controlling the material to flow out from the outlet;
the circulating power device 5 is used for transmitting the material from the outlet of the material storage box to the inlet of the material storage box when the material flows out from the outlet, so that the material enters the material storage space of the material storage box again from the inlet;
and the camera device 2 is used for acquiring image data of the material in the material storage box according to a preset rule.
Further, the material storage box 1 can be optimally set in combination with the actual use condition. Specifically, the method comprises the following steps:
in the embodiment of the invention, the inlet can be set to be wide, so that the material is conveniently added; the outlet may be provided as a narrow interface to facilitate retention of material in the material storage bin.
In the embodiment of the present invention, the horizontal cross-sectional area of the material storage space 11 is preferably gradually reduced from the inlet to the outlet, for example, the vertical cross-section of the material storage space is an inverted trapezoid. Through such a setting mode, can be more favorable to the material to assemble towards the direction of export in the material storage box to be favorable to the intensive mixing of material.
As an embodiment, the above-described effect can be achieved by providing the power-assisted land 12. When the material enters the material storage space from the inlet, a part of the material directly falls to the outlet; the other part of the material falls onto the power-assisted landslide and slides towards the outlet under the action of spontaneous gravitational acceleration, namely the power-assisted landslide can assist the material to slide downwards in an accelerating manner and then converge towards the outlet. Furthermore, due to the difference between the motion tracks of the materials from the inlet to the outlet, the materials can be fully mixed. In addition, because the upper horizontal sectional area of the material storage space is large, the lower horizontal sectional area is small, and the moving speed of the lower half part of the material is relatively greater than that of the upper half part of the material, a wider choice is provided for an alignment area for image acquisition, and the probability of the displacement blurring phenomenon of the material acquired by the camera device is reduced.
Further, a transparent camera window 13 is arranged on the box body of the material storage box 1 and used for providing a photographing window for the camera device 2.
In the embodiment of the invention, the transparent camera shooting window is preferably an independent structural component, for example, the transparent camera shooting window is covered on the box body in a cover mode, so that the transparent camera shooting window can be conveniently detached and installed; the transparent camera window can be made of materials such as acrylic and glass; the size of the window is determined by the actual device size and the size of the image to be photographed.
Further, the image pickup device 2 is controlled by the controller to automatically photograph and sample the material in the material storage box 1 once at regular intervals. The camera device can be an independent camera or a camera module integrated on the core controller.
Further, at the outlet of the material storage box 1, there is provided material outflow control means 3 for controlling the outflow of the material from the outlet. Specifically, for example, the flow rate and the flow velocity of the material can be controlled, the material can be guided, whether the material flows out or not can be controlled, and the like; preferably, the outflow control device 3 further has a stirring function for stirring the material while the material flows out from the outlet.
In the embodiment of the present invention, the outflow control device 3 includes a motor 31 and a rotating member 32; the motor 31 drives the rotating part 32 to rotate according to certain steps and rules through the setting of a controller chip and a chip program. The rotating part can be a rotating screw, a rotating fin, a turnover door or a three-wing door and the like. For example, when the rotating member is a rotating screw, it is preferable that the rotating screw has a wide thread and is disposed longitudinally at the outlet of the material storage box; the rotating screw rod is driven by the motor to rotate, the material is continuously twisted into the outlet by the threads on the screw rod, and the material is stirred by rotation, so that the material is continuously updated and changed; when the motor stops operating, the rotating screw stops rotating, the threads on the screw block the material, and the material stops flowing out. When the rotating part selects the rotating fin, the turnover door or the three-wing door, the working principle is similar to that of a rotating screw, and the difference is that the parts rotate along a transverse rotating shaft, namely, the rotating shaft direction is vertical to the falling direction of the material, and at the moment, the stirring effect on the material is better.
It should be noted that, when the material is not suitable for being stirred for its own reason, the outflow control device 3 may be a valve structure such as a ball valve. In particular, the outflow control device may not be provided. Therefore, the outflow control device is preferably easily loaded, replaced and removed at the outlet, so that it can be selected according to different material conditions.
Further, the automatic image data acquisition system further comprises a pipeline 4, the pipeline 4 is arranged outside the material storage box 1, an inlet and an outlet of the material storage box are communicated through the pipeline 4, a circulating power device 5 is connected in the pipeline 4, and the circulating power device 5 is connected with a part, close to the outlet, of the pipeline 4.
Specifically, after the material is stranded into the material storage box outlet through the outflow control device, the material falls into the pipeline connected with the outlet along the trend, and moves to the inlet under the action of the circulating power device 5, and enters the material storage space again through the inlet, so that one circulation is completed.
It is noted that the pipe only serves to provide a loading space and a transfer channel for the material circulating outside the material storage box, and those skilled in the art can easily adopt other forms instead of the existence of the pipe.
In the present embodiment, the circulation power unit 5 is, for example, a blower. At this time, the blower is connected to a portion of the duct near the outlet of the material storage tank; when the material falls into the pipeline from the outlet, the blower blows the material through the pipeline to the inlet above the material storage box by strong wind power, so that the material returns to the material storage box again.
Further, the automatic image data acquisition system further comprises a controller, and the outflow control device 3, the circulating power device 5 and the camera device 2 are all controlled by the controller.
In the embodiment of the present invention, the outflow control device 3, the circulation power device 5, and the image pickup device 2 may be controlled by the same controller. The controller can control the camera device 2 to collect image data according to a certain pace, can control the outflow control device 3 to operate, and can control the circulating power device 5 to drive the material to circulate in the pipeline; of course, the above-mentioned devices may also be controlled by different controllers; in order to reduce the overall volume of the device, it is preferred that the three are controlled by the same controller. The controller controls the outflow control device 3, specifically, the controller controls the motor 31 in the outflow control device 3 to operate, and further drives the rotating component 32 to rotate. The controller is preferably an embedded core controller.
Further, a protective cover 14 is provided at an entrance of the material storage box 1, a vertical section of the material storage space 11 is an inverted trapezoidal shape, and a vertical section of the protective cover 14 may be a regular trapezoidal shape.
In this embodiment, the upper end of the protective cover 14 is connected to the pipeline 4, and the lower end thereof extends into the material storage space 11. The protection casing can prevent to get into the material storage space's material splashes everywhere, is favorable to the material to drop towards export direction and helping hand landslide.
Furthermore, in this embodiment, the protective cover 14 may be a fairing. When the circulating power device 5 is a blower, the protective cover 14 plays a role in rectifying; specifically, the wind force from the blower is transmitted to the inlet of the material storage tank along the duct 4, and forms air convection at the inlet, further promoting the mixing of the material.
In this embodiment, the upper portion of the material storage box 1 is fixedly connected to the pipe 4 through a fixing valve 15. Whereby the material storage tank inlet and/or the protective cover are prevented from being separated from the duct when the circulation power unit is operated.
The image data automatic acquisition system provided by the embodiment of the invention can further comprise a gateway and an output end. Therefore, after the front-stage process of image data acquisition is finished, the acquisition result is output and further classified, stored and analyzed.
For example, the system further comprises an internet of things gateway and a cloud server; the camera device 2 collects material images and returns the material images to the controller, the controller uploads the image data to the cloud server through the internet of things gateway, and the cloud data processing center on the cloud server can classify, store and analyze the images through sampling time nodes. The Internet of Things gateway is, for example, a Narrow-Band Internet of Things (NB-IOT) based on cellular.
As another example, the system may further include an intranet gateway and a local storage; the camera device 2 collects material images and returns the material images to the controller, the controller transmits the image data to the local storage through the intranet gateway, and the local storage classifies, stores and analyzes the image data. The intranet gateway can be in the form of a router and the like; the local storage is, for example, a memory card, a local server, a local database, or other systems.
Therefore, the automatic image data acquisition system provided by the embodiment of the invention completes the whole process of automatic image data acquisition, network data transmission and data classification and storage, and realizes full-automatic processing.
Example two
Based on the image data automatic acquisition system provided in the first embodiment, the embodiment of the invention also provides an image data automatic acquisition method, and fig. 2 is a schematic flow chart of the method. The method comprises the following steps:
step 101: controlling the material in the material storage box to flow out of the outlet of the material storage box based on the outflow control device;
step 102: controlling an inlet through which the material flowing out of the outlet is transmitted back to the material storage box based on the circulation power device to circulate the material into the material storage box;
step 103: and acquiring image data aiming at the materials in the material storage box according to a preset rule.
The automatic image data acquisition method provided by the embodiment of the invention can realize automatic acquisition of image data, and the material in the material storage box is continuously changed and updated through continuous outflow and circulation of the material, so that the acquired images are different during each photographing and sampling, and the confidence coefficient of an image training model is increased.
Further, before step 101, a step of loading material requiring image acquisition may be further included, so that the material enters the material storage box from the entrance.
Further, after step 103, that is, after the required image acquisition is completed, the method may further include the step of stopping the circulation power device and emptying the material in the material storage tank.
It is noted that all structures and components used in the above method can adopt the corresponding structures and components in fig. 1.
EXAMPLE III
Based on the image data automatic acquisition method provided in the second embodiment, the embodiment of the present invention further provides an image data automatic acquisition control device, which includes: a controller and a memory for storing a computer program capable of running on the controller,
wherein the controller is configured to execute, when running the computer program:
controlling the material in the material storage box to flow out of the outlet of the material storage box based on the outflow control device;
controlling an inlet through which the material flowing out of the outlet is transmitted back to the material storage box based on the circulation power device to circulate the material into the material storage box;
and acquiring image data aiming at the materials in the material storage box according to a preset rule.
It should be noted that: in the above embodiment, when the image data automatic acquisition control device performs control, only the division of the program modules is taken as an example, and in practical applications, the processing distribution may be completed by different program modules according to needs, that is, the internal structure of the apparatus is divided into different program modules to complete all or part of the processing described above. In addition, the automatic acquisition control device and the automatic acquisition method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments and are not described herein again.
Example four
The embodiment of the invention further provides an automatic image data identification system. The image data automatic identification system comprises the image data automatic acquisition system in the first embodiment, and further comprises a model training module, wherein the model training module is used for training according to a neural network algorithm by using the image data acquired by the image data automatic acquisition system as a training data set to obtain an identification model.
Specifically, the training data set adopted by the model training module may be image data acquired by the image data automatic acquisition system and subjected to preprocessing. The pre-processing may include Opencv image pre-processing and/or image enhancement processing that subjects the image data to changes in luminance and color space to facilitate feature extraction.
In this embodiment, the neural network algorithm is, for example, a deep neural network algorithm.
Further, the image data automatic identification system further comprises an image identification module, wherein the image identification module takes the identification model as an input interface, and is used for identifying materials included in the image data when the image data is input, so as to obtain an identification result.
In this embodiment, the material image data with a sufficient number and high confidence is automatically obtained by the image data automatic identification system, and the material identification model is obtained by training according to the obtained image data. The automatic identification system can work intelligently and automatically, and the accuracy of the identification result is high.
The automatic image data acquisition system, the automatic image data acquisition method and the automatic image data identification system are mainly applied to household appliances such as electric cookers, electric pressure cookers, automatic cooking machines, refrigerators, washing machines, water heaters and the like; of course, the present invention is not limited thereto, and those skilled in the art can apply the present invention to any apparatus requiring image data acquisition.
The above description is only exemplary of the present invention and should not be taken as limiting the scope of the present invention, and any modifications, equivalents, improvements, etc. that are within the spirit and principle of the present invention should be included in the present invention.
Claims (16)
1. An automatic image data acquisition system, characterized in that the system comprises: the material storage box, the outflow control device, the circulating power device and the camera device;
the material storage box is provided with a material storage space, and the material storage space is used for loading materials needing to acquire images; the upper part and the lower part of the material storage box are respectively provided with an inlet and an outlet, and the inlet and the outlet are respectively used for the material to enter and flow out; wherein, the horizontal sectional area of the material storage space is gradually reduced from the inlet to the outlet;
the outflow control device is arranged at the outlet of the material storage box and is used for controlling the material to flow out from the outlet;
the circulating power device is used for transmitting the material from the outlet of the material storage box to the inlet of the material storage box when the material flows out from the outlet, so that the material enters the material storage space of the material storage box again from the inlet;
and the camera device is used for acquiring image data of the material in the material storage box according to a preset rule.
2. The system of claim 1, wherein a power-assisted landslide is disposed within the material storage bin for accelerating the descent of material located within the material storage space and convergence towards an exit.
3. The system according to claim 1, wherein a transparent camera window is provided on the material storage box, and the camera device collects image data of the material in the material storage box through the transparent camera window.
4. The system of claim 3, wherein the transparent camera window is independent of the material storage box, and the material of the transparent camera window comprises acrylic or glass.
5. The system of claim 1, wherein the outflow control device is further configured to blend the material as the material is controlled to flow from the outlet.
6. The system of claim 1 or 5, wherein the outflow control device comprises a motor and a rotating member, the motor is used for driving the rotating member to rotate, and the rotating member comprises a rotating screw, a rotating fin, a turnover door or a three-wing door.
7. The system of claim 1 wherein the inlet and outlet communicate through a conduit external to the material storage tank, and the circulation power means is connected to a portion of the conduit adjacent the outlet.
8. The system of claim 1 or 7, wherein the circulation power plant comprises a blower.
9. The system of claim 1, further comprising a controller, wherein the outflow control device, the circulatory power device, and the camera device are all controlled by the controller.
10. The system of claim 1, wherein a protective cover is provided at an entrance of the material storage box, the material storage space has an inverted trapezoidal shape in vertical section, and the protective cover has a regular trapezoidal shape in vertical section.
11. The system of claim 1, further comprising: the system comprises an Internet of things gateway and a cloud server;
the Internet of things gateway is used for acquiring image data acquired by the camera device and uploading the image data to the cloud server;
the cloud server is used for performing at least one of the following processing on the image data: and (4) classifying, storing and analyzing the images.
12. The system of claim 1, further comprising: an intranet gateway and a local memory;
the intranet gateway is used for acquiring image data acquired by the camera device and transmitting the image data to the local memory;
the local memory is used for carrying out at least one of the following processing on the image data: and (4) classifying, storing and analyzing.
13. An automatic image data acquisition method for image data acquisition by using the automatic image data acquisition system according to any one of claims 1 to 12, the method comprising the steps of:
controlling the material in the material storage box to flow out of the outlet of the material storage box based on the outflow control device; wherein, the horizontal sectional area of the material storage space is gradually reduced from the inlet to the outlet;
controlling an inlet through which the material flowing out of the outlet is transmitted back to the material storage box based on the circulation power device to circulate the material into the material storage box;
and acquiring image data aiming at the materials in the material storage box according to a preset rule.
14. An image data automatic acquisition control apparatus, characterized by comprising: a controller and a memory for storing a computer program capable of running on the controller,
wherein the controller is adapted to perform the steps of the method of claim 13 when executing the computer program.
15. An automatic image data recognition system, comprising the automatic image data acquisition system according to any one of claims 1 to 12, and further comprising a model training module, wherein the model training module is configured to use image data acquired by the automatic image data acquisition system as a training data set, and train the image data according to a neural network algorithm to obtain a recognition model.
16. The system according to claim 15, further comprising an image recognition module, wherein the image recognition module is configured to obtain image data collected by the automatic image data collection system, recognize the image data based on the recognition model obtained by the model training module, and obtain a recognition result of a material included in the image data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810631957.4A CN110615293B (en) | 2018-06-19 | 2018-06-19 | Automatic image data acquisition system, automatic image data acquisition method and automatic image data identification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810631957.4A CN110615293B (en) | 2018-06-19 | 2018-06-19 | Automatic image data acquisition system, automatic image data acquisition method and automatic image data identification system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110615293A CN110615293A (en) | 2019-12-27 |
| CN110615293B true CN110615293B (en) | 2021-09-14 |
Family
ID=68920242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810631957.4A Active CN110615293B (en) | 2018-06-19 | 2018-06-19 | Automatic image data acquisition system, automatic image data acquisition method and automatic image data identification system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110615293B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743428A (en) * | 2020-05-27 | 2021-12-03 | 广东芬尼克兹节能设备有限公司 | Method and device for performing accurate defrosting control by combining camera |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000056056A3 (en) * | 1999-03-18 | 2001-01-04 | Showbites Inc | Method for optimization of video coverage |
| CN104949916A (en) * | 2015-05-29 | 2015-09-30 | 中国农业大学 | Fall type corn ear property measuring apparatus and measuring method thereof |
| CN105181513A (en) * | 2015-06-08 | 2015-12-23 | 洛阳理工学院 | Box-type cereal automatic detection device |
| CN106022854A (en) * | 2016-04-22 | 2016-10-12 | 天津至优科技有限公司 | Portable e-commerce photographic device |
| CN107146096A (en) * | 2017-03-07 | 2017-09-08 | 浙江工业大学 | A kind of intelligent video advertisement methods of exhibiting and device |
| CN107601064A (en) * | 2017-09-19 | 2018-01-19 | 中国计量大学 | Straight weight-loss type material blanking machine and its controller based on neutral net |
| CN108090518A (en) * | 2017-12-29 | 2018-05-29 | 美的集团股份有限公司 | A kind of cereal recognition methods, device and computer storage media |
| CN108124106A (en) * | 2018-02-05 | 2018-06-05 | 陈文� | A kind of sample acquisition system for image artificial intelligence |
-
2018
- 2018-06-19 CN CN201810631957.4A patent/CN110615293B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000056056A3 (en) * | 1999-03-18 | 2001-01-04 | Showbites Inc | Method for optimization of video coverage |
| CN104949916A (en) * | 2015-05-29 | 2015-09-30 | 中国农业大学 | Fall type corn ear property measuring apparatus and measuring method thereof |
| CN105181513A (en) * | 2015-06-08 | 2015-12-23 | 洛阳理工学院 | Box-type cereal automatic detection device |
| CN106022854A (en) * | 2016-04-22 | 2016-10-12 | 天津至优科技有限公司 | Portable e-commerce photographic device |
| CN107146096A (en) * | 2017-03-07 | 2017-09-08 | 浙江工业大学 | A kind of intelligent video advertisement methods of exhibiting and device |
| CN107601064A (en) * | 2017-09-19 | 2018-01-19 | 中国计量大学 | Straight weight-loss type material blanking machine and its controller based on neutral net |
| CN108090518A (en) * | 2017-12-29 | 2018-05-29 | 美的集团股份有限公司 | A kind of cereal recognition methods, device and computer storage media |
| CN108124106A (en) * | 2018-02-05 | 2018-06-05 | 陈文� | A kind of sample acquisition system for image artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110615293A (en) | 2019-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109389161B (en) | Garbage identification evolutionary learning method, device, system and medium based on deep learning | |
| US20210357879A1 (en) | Automatic classification system | |
| CN110874578B (en) | Unmanned aerial vehicle visual angle vehicle recognition tracking method based on reinforcement learning | |
| CN104360089B (en) | A kind of automatic microcolumn gel card detector | |
| CN109261539B (en) | Garbage sorting system and method based on visual identification and convolutional neural network | |
| DE102018113672A1 (en) | Mobile robot and control method for it | |
| CN108921218B (en) | Target object detection method and device | |
| CN105262991B (en) | A kind of substation equipment object identifying method based on Quick Response Code | |
| KR102503116B1 (en) | Automatic Data Set Generation Device and their Control Method for AI Machine Learning Learning | |
| CN103344583B (en) | A kind of praseodymium-neodymium (Pr/Nd) component concentration detection system based on machine vision and method | |
| CN102878647B (en) | Automatic monitoring system and automatic monitoring method for operating state of air conditioner | |
| CN110615293B (en) | Automatic image data acquisition system, automatic image data acquisition method and automatic image data identification system | |
| CN104239886A (en) | Image analysis based lawn and background boundary extraction method | |
| Sizkouhi et al. | RoboPV: An integrated software package for autonomous aerial monitoring of large scale PV plants | |
| Nodado et al. | Intelligent traffic light system using computer vision with android monitoring and control | |
| CN114063609A (en) | Obstacle avoidance control method and control system of intelligent mowing robot | |
| DE102020133445A1 (en) | CAMERA ARCHESTRY TECHNOLOGY TO IMPROVE AUTOMATIC PERSONAL IDENTIFICATION | |
| CN114135991B (en) | Temperature preset control and equipment early warning method for subway station public area | |
| Kyrkou | C 3 Net: end-to-end deep learning for efficient real-time visual active camera control | |
| CN110782484A (en) | Unmanned aerial vehicle video personnel identification and tracking method | |
| CN112455676A (en) | Intelligent monitoring and analyzing system and method for health state of photovoltaic panel | |
| CN109800661A (en) | A kind of road Identification model training method, roads recognition method and device | |
| CN105195438A (en) | Embedded type automatic pearl sorting device and method based on image recognition | |
| Ahmed et al. | Design of an automated secure garage system using license plate recognition technique | |
| CN204314305U (en) | A kind of automatic microcolumn gel card detector |
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 |