CN108711152B - Image analysis method and device based on AI technology and user terminal - Google Patents
Image analysis method and device based on AI technology and user terminal Download PDFInfo
- Publication number
- CN108711152B CN108711152B CN201810500163.4A CN201810500163A CN108711152B CN 108711152 B CN108711152 B CN 108711152B CN 201810500163 A CN201810500163 A CN 201810500163A CN 108711152 B CN108711152 B CN 108711152B
- Authority
- CN
- China
- Prior art keywords
- environment
- image
- result
- matching
- identification
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Abstract
The invention provides an image analysis method, an image analysis device and a user terminal based on an AI technology, wherein the method comprises the following steps: acquiring an environment image; performing AI identification on the environment image to generate an identification result; and matching the recognition result with environment comparison information in an environment analysis library to generate a matching result so as to position the fault area of the environment image according to the matching result. Thereby through carrying out AI image recognition to the environment image who obtains and judge that the trouble is regional the work efficiency that has improved the troubleshooting, shortened maintenance time, avoided the condition that the missing of artifical maintenance was examined or can not be examined, guaranteed rail transit vehicle's safe operation to a certain extent.
Description
Technical Field
The present invention relates to the field of artificial intelligence technology, and more particularly, to an image analysis method and apparatus based on AI technology, and a user terminal.
Background
Rail transit refers to a type of vehicle or transportation system in which operating vehicles need to travel on a particular rail. The most typical rail transit is a railway system consisting of conventional trains and standard railways. With the diversified development of train and railway technologies, rail transit is more and more types, and is not only distributed in long-distance land transportation, but also widely applied to medium-short distance urban public transportation.
Common rail transit trouble includes vehicle trouble and track facility trouble, when overhauing common rail transit trouble, all need the technical staff artifical to carry out systematic investigation one by one including vehicle and track facility to all environments of track through the naked eye, the subjective factor is great, and is long efficient for a long time, has brought the inconvenience for the work of maintainer's troubleshooting investigation, and the condition that the artifical inspection easily appears lou examining, or can not be investigated, has brought huge potential safety hazard for rail transit vehicle's safe operation.
Disclosure of Invention
In view of the above, the present invention provides an image analysis method and apparatus based on AI technology, and a user terminal to solve the deficiencies of the prior art.
In order to solve the above problems, the present invention provides an image analysis method based on an AI technique, including:
acquiring an environment image;
performing AI identification on the environment image to generate an identification result;
and matching the recognition result with environment comparison information in an environment analysis library to generate a matching result so as to position the fault area of the environment image according to the matching result.
Preferably, the "AI recognition of the environment image and generation of a recognition result" includes:
determining a recognizable target environment in the environment image;
acquiring positioning information corresponding to the identifiable target environment;
acquiring a screenshot of the identifiable target environment corresponding to the positioning information according to the positioning information;
and generating a recognition result.
Preferably, the "determining a recognizable target environment in the environment image" includes:
and analyzing the environment image based on an object detection framework of deep learning to obtain an identifiable target environment in the environment image.
Preferably, before the "matching the recognition result with the environment comparison information in the environment analysis library", the method further includes:
extracting screenshot and positioning information corresponding to the identifiable target environment in the identification result;
obtaining relative position information of the screenshot in the environment image according to the positioning information;
based on the environment analysis library, judging whether the relative position of the identifiable target environment corresponding to the screenshot is correct or not according to the screenshot and the relative position information;
and if so, storing the identification result so as to execute 'matching the identification result with the environment comparison information in the environment analysis library'.
Preferably, after the step of determining whether the relative position of the identifiable target environment corresponding to the screenshot is correct according to the screenshot and the relative position information, the method further includes:
and if not, generating warning information of relative position error corresponding to the recognizable target environment.
Preferably, the environment comparison information includes normal environment setting data and fault environment setting data;
the "matching the recognition result with the environment comparison information in the environment analysis library to generate a matching result so as to determine the fault area of the environment image according to the matching result" includes:
comparing the identification result with the normal environment setting data in the environment comparison information;
if the identification result is not compared with the normal environment setting data, comparing the identification result with the fault environment setting data;
and if the identification result passes the comparison with the fault environment setting data, generating a matching result so as to position the fault area of the environment image according to the matching result.
Preferably, after the comparing the identification result with the fault environment setting data, the method further includes:
and if the identification result is not compared with the fault environment setting data, prompting to re-acquire the environment image corresponding to the identifiable target environment, and returning to the step of acquiring the environment image.
In order to solve the above problems, the present invention also provides an image analysis apparatus based on an AI technique, including: the device comprises a receiving module, an identification module and a matching module;
the receiving module is used for acquiring an environment image;
the identification module is used for carrying out AI identification on the environment image to generate an identification result;
and the matching module is used for matching the recognition result with the environment comparison information in the environment analysis library to generate a matching result so as to position the fault area of the environment image according to the matching result.
In addition, to solve the above problem, the present invention further provides a user terminal including a memory for storing an image analysis program based on an AI technique, and a processor for running the image analysis program based on the AI technique to make the user terminal perform the image analysis method based on the AI technique.
Further, to solve the above problems, the present invention also provides a computer-readable storage medium having stored thereon an AI-technology-based image analysis program that, when executed by a processor, implements the AI-technology-based image analysis method as described above.
The invention provides an image analysis method and device based on an AI technology and a user terminal. The method provided by the invention can be used for positioning the fault area in the environment image by acquiring the environment image, further carrying out AI identification on the environment image and then comparing the identification result with the comparison information in the environment analysis library. Thereby through carrying out AI image recognition to the environment image who obtains and judge that the trouble is regional the work efficiency that has improved the troubleshooting, shortened maintenance time, avoided the condition that the missing of artifical maintenance was examined or can not be examined, guaranteed rail transit vehicle's safe operation to a certain extent.
Drawings
Fig. 1 is a schematic structural diagram of a hardware operating environment according to an embodiment of an image analysis method based on an AI technique of the present invention;
FIG. 2 is a schematic flowchart of a first embodiment of an AI-based image analysis method according to the present invention;
FIG. 3 is a flowchart illustrating a second embodiment of an AI-based image analysis method according to the present invention;
FIG. 4 is a flowchart illustrating a third embodiment of an AI-based image analysis method according to the present invention;
FIG. 5 is a schematic flowchart of a fourth embodiment of an AI-based image analysis method according to the invention;
FIG. 6 is a flowchart illustrating a fifth embodiment of an AI-based image analysis method according to the present invention;
fig. 7 is a functional block diagram of an image analysis apparatus based on AI technology according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
Reference will now be made in detail to the embodiments of the present invention, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a schematic structural diagram of a hardware operating environment of a terminal according to an embodiment of the present invention.
The terminal of the embodiment of the invention can be a PC, and can also be a mobile terminal device with a display function, such as a smart phone, a tablet computer, an electronic book reader, an MP3 player, an MP4 player, a portable computer and the like.
As shown in fig. 1, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may comprise a display screen, an input unit such as a keyboard, a remote control, and the optional user interface 1003 may also comprise a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high speed RAM memory or a stable memory such as a disk memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Optionally, the terminal may further include a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WiFi module, and the like. In addition, the mobile terminal may further be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which are not described herein again.
Those skilled in the art will appreciate that the terminal shown in fig. 1 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, an operating system, a data interface control program, a network connection program, and an image analysis program based on the AI technique may be included in a memory 1005, which is one of computer-readable storage media.
The invention provides an image analysis method and device based on an AI technology and a user terminal. According to the method, the AI image recognition is carried out on the acquired environment image, so that the fault area is judged, the working efficiency of fault maintenance is improved, the maintenance time is shortened, the condition that the manual maintenance is missed or cannot be detected is avoided, and the safe operation of the rail transit vehicle is ensured to a certain extent.
Example 1:
referring to fig. 2, a first embodiment of the present invention provides an image analysis method based on an AI technique, including:
step S100, acquiring an environment image;
as described above, the image analysis method based on the AI technology provided in this embodiment can be applied between the terminal and the server. The service terminal is used for shooting and collecting the environmental image, and then the shot and collected environmental image is transmitted back to the service terminal. In addition, the system can also be an all-in-one machine for acquisition, identification and analysis, namely, a maintenance technician holds the all-in-one machine to carry out all-around image acquisition, data analysis and other work on the rail transit. The image acquisition step may include the steps of image capturing, acquisition, transmission, and the like.
As described above, the environment image, in this embodiment, may include a vehicle overall image, a vehicle component layout image, a locomotive internal circuit image, a vehicle wheel hub setting image, a hydraulic and pneumatic instrument setting image, a driver operation environment image, a track direction setting image, a track-to-track connection image, and the like; in addition, but not limited to, images of track related facilities, such as track surrounding base station setting images, track signal light setting images, and the like, may also be included.
Step S200, carrying out AI identification on the environment image to generate an identification result;
in the above, AI recognition is performed on the environment image, and a recognition result of the environment image is generated through AI recognition, so that further automatic troubleshooting work is performed.
In the above, AI recognition is also called an intelligent image recognition technology, and the image recognition technology is an important field of artificial intelligence. It refers to a technique of performing object recognition on an image to recognize various different modes of objects and objects. Image recognition techniques may be based on the main features of the image. Each image has its features such as the letter a having a tip, P having a circle, and the center of Y having an acute angle, etc. The study of eye movement in image recognition shows that the sight line is always focused on the main features of the image, namely, the places where the curvature of the contour of the image is maximum or the direction of the contour changes suddenly, and the information content of the places is maximum. And the scan path of the eye always goes from one feature to another in turn. Therefore, in the image recognition process, the perception mechanism needs to eliminate the input redundant information and extract the key information. At the same time, there must be a mechanism in the brain that is responsible for integrating information, which can organize the information obtained in stages into a complete perceptual map.
As described above, the recognition result is result information generated by the AI recognition technique corresponding to the environment image, and may include information such as arrangement, connection relationship, shape, or result for a specific component in the environment image.
And step S300, matching the recognition result with environment comparison information in an environment analysis library to generate a matching result so as to position a fault area of the environment image according to the matching result.
The environment analysis library is a preset database for further intelligent matching, wherein the analysis library may include setting information or pictures of a normal environment and also may be setting information or pictures of a fault environment, and whether a fault area exists in the acquired environment image is determined by comparing the obtained identification result with related information in the library, and if a fault area exists, the fault area can be further positioned, so that a maintainer or a background operator can be prompted to perform troubleshooting or maintenance on the specified area.
The method provided by the embodiment locates the fault area in the environment image by acquiring the environment image, further performing AI identification on the environment image, and then comparing the identification result with the comparison information in the environment analysis library. Thereby through carrying out AI image recognition to the environment image who obtains and judge that the trouble is regional the work efficiency that has improved the troubleshooting, shortened maintenance time, avoided the condition that the missing of artifical maintenance was examined or can not be examined, guaranteed rail transit vehicle's safe operation to a certain extent.
Example 2:
referring to fig. 3, a second embodiment of the present invention provides an image analysis method based on an AI technique, based on the first embodiment shown in fig. 2, where the step S200 "performs AI recognition on the environment image to generate a recognition result" includes:
step S210, determining a recognizable target environment in the environment image;
as described above, when performing AI recognition, data screening or data cleaning needs to be performed on the environment image, so as to extract a recognizable target environment therein. The method includes, but is not limited to, an automatic optimization step for the acquired environment image, a comparison and search step with preset data, and the like.
In the automatic optimization step, when troubleshooting is performed by a maintainer, when an image of a vehicle body or a rail running environment is acquired, shooting problems such as backlight, dim light, shaking ghost, color change, distortion and the like may exist, so that the acquired environment image is seriously distorted, and further identification is affected, so that the acquired environment image needs to be automatically optimized, and the automatic optimization can include but is not limited to functions of improving contrast, automatically adjusting light brightness and darkness, automatically processing ghost, automatically adjusting distortion and the like. The optimization step may also be performed by a manual operation selection performed by a service man or a system maintenance man when the picture is acquired, so as to optimize the environment image.
The comparison and search with the preset data are carried out through the comparison of the preset overhaul target data, so that whether the overhaul target exists in the image or not is determined. For example, a maintainer needs to overhaul a train central console, an environment image of the central console is acquired by shooting, the system compares the environment image with a preset overhaul target, whether an image of a direction control device, a pneumatic hydraulic control device, a train thermal management system control device and the like exists in the image or not is searched, and if the image exists, the image of the direction control device, the pneumatic hydraulic control device, the train thermal management system control device and the like in the image is used as a recognizable target environment in the image.
Step S220, acquiring positioning information corresponding to the identifiable target environment;
as described above, in the present embodiment, the identifiable target environment can be located through the AI identification technology. Wherein the positioning may be to generate frames of different shapes, e.g. polygons, rectangles, circles, etc., according to the shape. The positioning information may include generated pixel coordinates in the whole environment image for the recognizable target environment, a relative position of each generated frame, or an area and a size of the frame, and specific size information of the relevant equipment and facilities is calculated by acquiring relevant ranging data.
Step S230, acquiring a screenshot of the identifiable target environment corresponding to the positioning information according to the positioning information;
the frame of each identifiable target environment is obtained according to the positioning information, and the screenshot of each identifiable target environment is further performed according to the frame, so that the screenshot of each identifiable target environment in the environment image is obtained.
In step S240, a recognition result is generated.
As described above, the recognition result may include, but is not limited to, a screenshot of the recognizable target environment in the environment image, positioning information, specific size, shape, and other data, so as to further perform troubleshooting according to the recognition result.
Example 3:
referring to fig. 4, a third embodiment of the present invention provides an image analysis method based on an AI technique, and based on the second embodiment shown in fig. 3, the step S210 "determining a recognizable target environment in the environment image" includes:
step S211, analyzing the environment image based on the object detection framework of deep learning to obtain an identifiable target environment in the environment image.
From the above, it should be understood that object detection has been a relatively popular research direction, and has undergone the development of the traditional framework of artificially designed features + shallow classifiers To the object detection framework of End-To-End based on big data and deep neural network, and the detection and positioning of objects in images are mainly realized by the object detection framework. The object detection framework may include, but is not limited to CNN, YOLO, RCNN, SSD, NMS, etc., and the detection framework employed in the present embodiment is YOLO technology.
In the foregoing, the object detection framework needs to perform deep learning on the target, and through the deep learning, the environment image is analyzed, so that a recognizable target environment in the environment image is found out, and then operations such as positioning, framing the target environment, and extracting a screenshot of the corresponding target environment are performed.
Example 4:
referring to fig. 5, a fourth embodiment of the present invention provides an image analysis method based on an AI technique, and based on the third embodiment shown in fig. 4, before the step S300 "matching the recognition result with the environment comparison information in the environment analysis library", the method further includes:
step S400, extracting screenshot and positioning information corresponding to the identifiable target environment in the identification result;
s500, obtaining the relative position information of the screenshot in the environment image according to the positioning information;
before matching, related screenshot and positioning information of the identifiable target environment are extracted. And relative position information in the environment image is acquired through the positioning information. The relative location information may be the relative location of the identifiable target environment with other relevant components or facilities. Such as the placement of components at different locations, the placement of screws in the wheel drive system, etc.
And step S600, based on the environment analysis library, judging whether the relative position of the identifiable target environment corresponding to the screenshot is correct or not according to the screenshot and the relative position information.
Step S700, if yes, storing the recognition result so as to perform "matching the recognition result with the environment comparison information in the environment analysis library".
And step S800, if not, generating warning information of relative position error corresponding to the recognizable target environment.
As described above, the environment analysis library may include relative position information of different identifiable target environments, that is, correct placement and setting conditions of different facilities, devices, and the like. For example, a train wheel transmission rod is used for connecting a driving wheel and a driven wheel so as to output power; after the environment image is acquired, the transmission rod is arranged at other positions and is not connected with the driving wheel and the driven wheel, the fact that the transmission rod possibly has installation position deviation or falls off to other positions can be judged, and warning information of relative position errors corresponding to the recognizable target environment is generated. If the relative position of the identifiable target environment is judged to be correct after the acquired environment image is identified, the identification result can be stored so as to facilitate further analysis and judgment of the identification result.
Example 5:
referring to fig. 6, a fifth embodiment of the present invention provides an image analysis method based on an AI technique, where based on the first embodiment shown in fig. 2, the environment comparison information includes normal environment setting data and fault environment setting data; the step S300 "matching the recognition result with the environment comparison information in the environment analysis library to generate a matching result, so as to determine the fault area of the environment image according to the matching result" includes:
step S310, comparing the identification result with the normal environment setting data in the environment comparison information;
as described above, when analyzing the recognition result, it is necessary to compare the recognition result with the normal environment setting data.
The normal environment setting data is preset relevant information including normal states, normal layouts and normal setting conditions of the facilities, the equipment and the components with the overhaul targets. Picture information, relative position information, placement information, setting information, and the like may be included.
Step S320, if the identification result is not compared with the normal environment setting data, comparing the identification result with the fault environment setting data;
if the identification result is not compared with the normal environment data, the fault problem of the identifiable target environment is judged, the identified target environment is compared with the fault environment data for the second time, and whether the identification result is matched with the related data in the fault environment data is judged. In addition, if the comparison is passed, the recognizable target environment is judged to be in a normally set state, layout, setting or placement, and no relevant fault occurs.
Step S330, if the identification result passes the comparison with the fault environment setting data, a matching result is generated, so that the fault area of the environment image can be conveniently positioned according to the matching result.
As described above, if the comparison between the identification result and the fault environment setting data is performed, a matching result is generated through the comparison, where the matching result may include, but is not limited to, related comparison information, location information, relative location information, and the like of the identifiable target environment of the fault, so as to facilitate further location of the identifiable target environment, and notify or prompt a related operator, such as a service person, to perform service on the target.
Step S340, if the comparison between the identification result and the fault environment setting data fails, prompting to re-acquire the environment image corresponding to the identifiable target environment, and returning to "acquire environment image".
As described above, if the comparison between the identification result and the fault environment setting data is not passed, it is determined that there may be a problem in the image, which results in that the comparison between the fault environment setting data cannot be passed, for example, a shooting problem, and the like, and the environmental image at the position needs to be reacquired, so as to prompt the worker to reacquire and shoot the environmental image, and further perform the step of acquiring the environmental image again, and perform reanalysis and determination.
Further, referring to fig. 7, the present invention also provides an image analysis apparatus based on the AI technique, including: a receiving module 10, an identifying module 20 and a matching module 30;
the receiving module 10 is configured to acquire an environment image;
the identification module 20 is configured to perform AI identification on the environment image to generate an identification result;
the matching module 30 is configured to match the recognition result with environment comparison information in an environment analysis library to generate a matching result, so as to locate a fault area of the environment image according to the matching result.
In addition, the present invention also provides a user terminal, which includes a memory and a processor, wherein the memory is used for storing an image analysis program based on an AI technology, and the processor runs the image analysis program based on the AI technology to make the user terminal execute the image analysis method based on the AI technology.
Furthermore, the present invention also provides a computer-readable storage medium having stored thereon an AI-technology-based image analysis program that, when executed by a processor, implements the AI-technology-based image analysis method as described above.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system 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, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
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.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (5)
1. An image analysis method based on an AI technique, comprising:
acquiring an environment image, wherein the environment image is an image acquired by a handheld terminal or an all-in-one machine for acquisition, identification and analysis;
performing AI identification on the environment image to generate an identification result;
matching the recognition result with environment comparison information in an environment analysis library to generate a matching result so as to position a fault area of the environment image according to the matching result, wherein the environment comparison information comprises normal environment setting data and fault environment setting data;
the AI identifying the environmental image to generate an identification result includes:
determining a recognizable target environment in the environment image;
acquiring positioning information corresponding to the identifiable target environment;
acquiring a screenshot of the identifiable target environment corresponding to the positioning information according to the positioning information;
generating a recognition result;
the "determining a recognizable target environment in the environment image" includes:
analyzing the environment image based on an object detection framework of deep learning to obtain an identifiable target environment in the environment image;
before the "matching the recognition result with the environment comparison information in the environment analysis library", the method further includes:
extracting screenshot and positioning information corresponding to the identifiable target environment in the identification result;
obtaining relative position information of the screenshot in the environment image according to the positioning information;
based on the environment analysis library, judging whether the relative position of the identifiable target environment corresponding to the screenshot is correct or not according to the screenshot and the relative position information;
if so, storing the identification result so as to facilitate the execution of matching the identification result with environment comparison information in an environment analysis library;
if not, generating warning information of relative position error corresponding to the recognizable target environment;
the "matching the recognition result with the environment comparison information in the environment analysis library to generate a matching result so as to determine the fault area of the environment image according to the matching result" includes:
comparing the identification result with the normal environment setting data in the environment comparison information;
if the identification result is not compared with the normal environment setting data, comparing the identification result with the fault environment setting data;
and if the identification result passes the comparison with the fault environment setting data, generating a matching result so as to position the fault area of the environment image according to the matching result.
2. The AI-technology-based image analysis method according to claim 1, wherein, after comparing the recognition result with the failure environment setting data, further comprising:
and if the identification result is not compared with the fault environment setting data, prompting to re-acquire the environment image corresponding to the identifiable target environment, and returning to the step of acquiring the environment image.
3. An image analysis apparatus based on an AI technique, comprising: the device comprises a receiving module, an identification module and a matching module;
the receiving module is used for acquiring an environment image, wherein the environment image is acquired by a handheld terminal or an all-in-one machine for acquisition, identification and analysis;
the identification module is used for carrying out AI identification on the environment image to generate an identification result;
the matching module is used for matching the recognition result with environment comparison information in an environment analysis library to generate a matching result so as to position a fault area of the environment image according to the matching result, wherein the environment comparison information comprises normal environment setting data and fault environment setting data;
the AI identifying the environmental image to generate an identification result includes:
determining a recognizable target environment in the environment image;
acquiring positioning information corresponding to the identifiable target environment;
acquiring a screenshot of the identifiable target environment corresponding to the positioning information according to the positioning information;
generating a recognition result;
the "determining a recognizable target environment in the environment image" includes:
analyzing the environment image based on an object detection framework of deep learning to obtain an identifiable target environment in the environment image;
before the "matching the recognition result with the environment comparison information in the environment analysis library", the method further includes:
extracting screenshot and positioning information corresponding to the identifiable target environment in the identification result;
obtaining relative position information of the screenshot in the environment image according to the positioning information;
based on the environment analysis library, judging whether the relative position of the identifiable target environment corresponding to the screenshot is correct or not according to the screenshot and the relative position information;
if so, storing the identification result so as to facilitate the execution of matching the identification result with environment comparison information in an environment analysis library;
if not, generating warning information of relative position error corresponding to the recognizable target environment;
the "matching the recognition result with the environment comparison information in the environment analysis library to generate a matching result so as to determine the fault area of the environment image according to the matching result" includes:
comparing the identification result with the normal environment setting data in the environment comparison information;
if the identification result is not compared with the normal environment setting data, comparing the identification result with the fault environment setting data;
and if the identification result passes the comparison with the fault environment setting data, generating a matching result so as to position the fault area of the environment image according to the matching result.
4. A user terminal comprising a memory for storing an AI-technology-based image analysis program and a processor for executing the AI-technology-based image analysis program to cause the user terminal to perform the AI-technology-based image analysis method according to any one of claims 1-2.
5. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon an AI-technology-based image analysis program that, when executed by a processor, implements an AI-technology-based image analysis method according to any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810500163.4A CN108711152B (en) | 2018-05-23 | 2018-05-23 | Image analysis method and device based on AI technology and user terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810500163.4A CN108711152B (en) | 2018-05-23 | 2018-05-23 | Image analysis method and device based on AI technology and user terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108711152A CN108711152A (en) | 2018-10-26 |
| CN108711152B true CN108711152B (en) | 2021-08-13 |
Family
ID=63869287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810500163.4A Active CN108711152B (en) | 2018-05-23 | 2018-05-23 | Image analysis method and device based on AI technology and user terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108711152B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109685151B (en) * | 2018-12-27 | 2022-10-14 | 深圳市鹰眼在线电子科技有限公司 | Circuit board material number identification method and device and computer readable storage medium |
| CN109784336A (en) * | 2019-01-30 | 2019-05-21 | 云南电网有限责任公司电力科学研究院 | A kind of infrared image fault point recognition methods based on YOLO algorithm of target detection |
| CN110263623A (en) * | 2019-05-07 | 2019-09-20 | 平安科技（深圳）有限公司 | Train climbs monitoring method, device, terminal and storage medium |
| CN113161113B (en) * | 2021-06-02 | 2023-06-27 | 国家电网有限公司 | Transformer substation air cooling visual management system and method |
| CN114248818A (en) * | 2022-01-13 | 2022-03-29 | 南京融才交通科技研究院有限公司 | Intelligent information transportation supervision method and system based on rail transit |
| CN115966018A (en) * | 2022-12-26 | 2023-04-14 | 北京思维实创科技有限公司 | Anomaly monitoring method based on machine vision and related device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273802A (en) * | 2017-05-16 | 2017-10-20 | 武汉华目信息技术有限责任公司 | A kind of detection method and device of railroad train brake shoe drill ring failure |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101229232B1 (en) * | 2011-06-14 | 2013-02-04 | 한국철도기술연구원 | Detection apparatus and method of train outside fault |
| CN103512762B (en) * | 2012-06-29 | 2016-12-21 | 北京华兴致远科技发展有限公司 | Image processing method, device and train failure detection system |
| CN104200464B (en) * | 2014-08-19 | 2018-03-09 | 苏州华兴致远电子科技有限公司 | A kind of detection method and system for identifying that train is abnormal |
| CN104463235B (en) * | 2014-11-18 | 2019-01-18 | 中国铁道科学研究院电子计算技术研究所 | Fault recognition method and device based on EMU operation image |
| CN107392197A (en) * | 2017-07-27 | 2017-11-24 | 武汉汉云亚信科技有限公司 | A kind of locomotive identification identification and locomotive component fault detection method and system |
-
2018
- 2018-05-23 CN CN201810500163.4A patent/CN108711152B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273802A (en) * | 2017-05-16 | 2017-10-20 | 武汉华目信息技术有限责任公司 | A kind of detection method and device of railroad train brake shoe drill ring failure |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108711152A (en) | 2018-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108711152B (en) | Image analysis method and device based on AI technology and user terminal | |
| CN110705405B (en) | Target labeling method and device | |
| US11004234B2 (en) | Method and apparatus for annotating point cloud data | |
| KR102094341B1 (en) | System for analyzing pot hole data of road pavement using AI and for the same | |
| CN105787062A (en) | Method and equipment for searching for target object based on video platform | |
| CN112446852B (en) | Tunnel imaging plane display method and defect intelligent recognition system | |
| CN110569856B (en) | Sample labeling method and device, and damage category identification method and device | |
| CN110119725B (en) | Method and device for detecting signal lamp | |
| CN112100431A (en) | Evaluation method, device and equipment of OCR system and readable storage medium | |
| CN111121797B (en) | Road screening method, device, server and storage medium | |
| CN112949457A (en) | Maintenance method, device and system based on augmented reality technology | |
| CN110928620A (en) | Method and system for evaluating distraction of automobile HMI design to attract driving attention | |
| CN116152863A (en) | Personnel information identification method and device, electronic equipment and storage medium | |
| CN115810134A (en) | Image acquisition quality inspection method, system and device for preventing car insurance from cheating | |
| CN112215222A (en) | License plate recognition method, device, equipment and storage medium | |
| KR101560810B1 (en) | Space controled method and apparatus for using template image | |
| CN112794274B (en) | Safety monitoring method and system for oil filling port at bottom of oil tank truck | |
| CN115438945A (en) | Risk identification method, device, equipment and medium based on power equipment inspection | |
| CN114565780A (en) | Target identification method and device, electronic equipment and storage medium | |
| CN110427911B (en) | Road detection method, device, equipment and storage medium | |
| CN108363985B (en) | Target object perception system testing method and device and computer readable storage medium | |
| CN116033544A (en) | Indoor parking lot positioning method, computer device, storage medium and program product | |
| WO2021229195A1 (en) | Nonintrusive digital monitoring for existing equipment and machines using machine learning and computer vision | |
| CN106775701B (en) | Client automatic evidence obtaining method and system | |
| CN114419080B (en) | Curtain wall inspection system and method |
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 |