CN115115980A - Method and system for automatically acquiring and classifying images based on AI algorithm - Google Patents
Method and system for automatically acquiring and classifying images based on AI algorithm Download PDFInfo
- Publication number
- CN115115980A CN115115980A CN202210682025.9A CN202210682025A CN115115980A CN 115115980 A CN115115980 A CN 115115980A CN 202210682025 A CN202210682025 A CN 202210682025A CN 115115980 A CN115115980 A CN 115115980A
- Authority
- CN
- China
- Prior art keywords
- image
- processed
- images
- algorithm
- inference
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a system for automatically acquiring and classifying images based on an AI algorithm, wherein the method comprises the following steps: the method comprises the steps of collecting images to be processed from video equipment at regular time, inputting the images to be processed into a preset AI algorithm model to obtain an inference result of the images to be processed, screening the images to be processed based on the inference result to obtain a classification result of the images to be processed, and storing the classification result. The model trained by utilizing the image data is more suitable for the actual scene; the huge cost generated by upgrading a large amount of video equipment can be reduced, and the problem that image characteristics cannot be analyzed due to the fact that image analysis is directly performed by a general image library by performing image screening after the inference result of the image to be processed is obtained by the AI algorithm model can be avoided; meanwhile, the inference result can be reserved as image marking information, so that the huge cost of manual screening and marking is reduced, and the aims of automatically acquiring, classifying and storing the image are fulfilled.
Description
Technical Field
The invention relates to the technical field of image processing AI algorithms, in particular to a method and a system for automatically acquiring and classifying images based on an AI algorithm.
Background
Along with popularization of AI technology, intelligent reconstruction can be seen in a plurality of scenes in life, and particularly, an image recognition technology based on a computer vision recognition technology is prominent. Machine vision recognition is a technique in which a computer processes, analyzes, and understands images to recognize various patterns of targets and objects. In brief, the computer learns the picture from the image. The deep learning technique is one of computer vision recognition techniques for understanding an image and forming a model. The computer vision recognition technology can obtain an AI algorithm reasoning model by analyzing a large number of images with labels, and the model can be applied in more scenes to realize the image recognition process.
However, in an actual intelligent reconstruction scene, image features that cannot be analyzed by a general image library always appear, so that the computer vision recognition technology is not fully satisfactory in the actual scene. Moreover, if the image classification labeling process adopts manpower, a large amount of labor cost is required.
Disclosure of Invention
In view of the above technical problems, an object of the present invention is to provide a method and a system for automatically acquiring and classifying images based on an AI algorithm, so as to solve the problem that a general image library cannot analyze the features of the images in the image recognition process, or the labor cost is high due to manual labeling and classification of a large number of images.
The invention adopts the following technical scheme:
a method for automatically acquiring and classifying images based on an AI algorithm comprises the following steps:
acquiring an image to be processed from video equipment at regular time;
inputting the image to be processed into a preset AI algorithm model, and obtaining an inference result of the image to be processed through the AI algorithm model;
and screening the images to be processed based on the reasoning result to obtain a classification result of the images to be processed, and storing the classification result.
Optionally, the obtaining of the inference result of the image to be processed through the AI algorithm model includes:
the AI algorithm model obtains preset image classification rules and score rules, and obtains the classification result of the image to be processed according to the image classification rules and the score rules.
Optionally, the inference result includes one or more of an inference target type of the image to be processed, a position of the inference target within the image to be processed, and an inference score corresponding to the target.
Optionally, the screening the to-be-processed image based on the inference result to obtain a classification result of the to-be-processed image, and storing the classification result, including:
and eliminating the images to be processed of which the target types do not meet the preset type range in the inference results of the images to be processed, eliminating the images to be processed of which the inference scores are smaller than the preset threshold scores, and then classifying and storing the residual images to be processed according to the target types.
Optionally, the acquiring the to-be-processed image from the video device at regular time includes:
collecting video data output by video equipment according to a certain time interval;
acquiring an image from the video data through image capture or acquiring an image through analyzing a video stream;
and storing the acquired image locally and pushing an image acquisition message to a local message queue.
Optionally, the AI algorithm model adopts a YOLOv5 model, obtains an inference result of the image to be processed through the YOLOv5 model, stores the inference result, and uses the inference result as a training sample of other AI models.
A system for automatically acquiring and classifying images based on an AI algorithm, comprising:
the image acquisition unit is used for acquiring images to be processed from the video equipment at regular time;
the inference unit is used for inputting the image to be processed into a preset AI algorithm model and obtaining an inference result of the image to be processed through the AI algorithm model;
and the classification unit is used for screening the image to be processed based on the inference result to obtain a classification result of the image to be processed and storing the classification result.
Optionally, the image acquiring unit includes: the system comprises a video access module, a timing execution module, an image acquisition module, an image storage module and a local message queue module; wherein the content of the first and second substances,
the video access module is used for accessing video data of the video equipment to the image acquisition module;
the timing execution module is used for calling the image acquisition module according to a certain time interval to acquire images from the video data through image capture or acquiring images through analyzing video streams;
the image storage module is used for storing the acquired image locally;
and the local message queue module is used for receiving and sending the image information to be processed.
An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for automatically acquiring and classifying images based on an AI algorithm.
A computer storage medium on which a computer program is stored which, when being executed by a processor, carries out the method for automatically acquiring and classifying images based on an AI algorithm.
Compared with the prior art, the invention has the beneficial effects that:
the method comprises the steps of acquiring an image to be processed from video equipment at regular time, inputting the image to be processed into a preset AI algorithm model, obtaining an inference result of the image to be processed through the AI algorithm model, screening the image to be processed based on the inference result, obtaining a classification result of the image to be processed, and storing the classification result; in the process of acquiring the image to be processed, the video equipment can be video equipment in an actual scene, and the video equipment in the actual scene is subjected to image acquisition, so that image data better conforms to a service scene, and a model trained by utilizing the image data is more suitable for the actual scene; the image is collected on the premise of not needing to replace the existing video equipment, so that the huge cost generated by upgrading a large amount of video equipment can be reduced; the AI algorithm model is adopted to obtain the inference result of the image to be processed, and then the image is screened, so that the problem that the image characteristics cannot be analyzed due to the fact that the image analysis is directly carried out by adopting a general image library can be avoided; meanwhile, on one hand, the cost of manual screening can be reduced; on the other hand, the inference result can be reserved as image annotation information, for example, the position of the target in the inference result in the image to be processed is reserved as image annotation information, so that the huge labor cost generated by the annotated image can be reduced, and the method can be used for training other AI models.
Drawings
Fig. 1 is a schematic flow chart of a method for automatically acquiring and classifying images based on an AI algorithm according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a method for automatically acquiring an image from a video device according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a method for classifying images by an AI algorithm according to an embodiment of the invention;
FIG. 4 is a schematic diagram of a system for automatically acquiring and classifying images based on an AI algorithm according to an embodiment of the invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and specific embodiments, and it should be noted that, in the premise of no conflict, the following described embodiments or technical features may be arbitrarily combined to form a new embodiment:
the first embodiment is as follows:
referring to fig. 1-5, a method for automatically acquiring and classifying images based on an AI algorithm as shown in fig. 1 includes the following steps:
step S1, collecting the image to be processed from the video device at regular time;
in this embodiment, the video device may be a video device in an actual scene, and image acquisition is performed on the video device in the actual scene, so that image data better conforms to a service scene, and a model trained by using the image data is more suitable for the actual scene. And the image is collected on the premise of not needing to replace the existing video equipment, so that the huge cost generated by upgrading a large amount of video equipment is reduced.
Step S2, inputting the image to be processed into a preset AI algorithm model, and obtaining an inference result of the image to be processed through the AI algorithm model;
and step S3, screening the images to be processed based on the reasoning result to obtain the classification result of the images to be processed, and storing the classification result.
Optionally, the obtaining of the inference result of the image to be processed through the AI algorithm model includes:
the AI algorithm model obtains preset image classification rules and score rules, and obtains the classification result of the image to be processed according to the image classification rules and the score rules.
In this embodiment, the image classification rule and the scoring rule may be set according to actual requirements.
For example, a preset scoring rule is defined as: and the inference score is 100 points, if the target of the image to be processed is not in the central position of the image to be processed, 50 points are deducted, the inference score is 50 points, or the image resolution of the image to be processed is smaller than the preset resolution, 20 points are further deducted, and the inference score is equal to the inference score obtained by subtracting the deduction from the full point, namely the inference score is 100-50-20-30 points.
Optionally, the AI algorithm model adopts a YOLOv5 model, obtains an inference result of the image to be processed through the YOLOv5 model, stores the inference result, and uses the inference result as a training sample of other AI models.
It should be noted that the YOLOv5 model originates from expanding the basic CNN concept from classification task to detection, and consists of a backbone network, a neck and a head, and the implementation steps include inputting data into the model to obtain inference information; NMS processes the prediction information, and all prediction frames are obtained at the moment; and traversing the prediction information, and meanwhile, obtaining the labeling information and then counting.
In specific implementation, the hardware device carrying the AI algorithm model may specifically include a GPU chip, an operation memory, a local hard disk for storing image data, and a computer general configuration, where the GPU chip and the operation memory carry the AI model for inference.
Specifically, the inference result includes one or more of an inference target type of the image to be processed, a position of the inference target in the image to be processed, and an inference score corresponding to the target.
Optionally, the screening the to-be-processed image based on the inference result to obtain a classification result of the to-be-processed image, and storing the classification result, including:
and rejecting the images to be processed of which the target types do not meet the preset type range in the inference results of the images to be processed, rejecting the images to be processed of which the inference scores are smaller than the preset threshold score, and then classifying and storing the rest images to be processed according to the target types.
In specific implementation, if the target type in the inference result of the image to be processed is not within the preset type range, the image to be processed is abandoned.
For example, if the preset type range is a person image and the target type in the inference result of the image to be processed is flowers and plants, it is determined that the image to be processed does not meet the preset type range.
For example, the preset threshold score is 60, and if the inference score of the image to be processed is 30, the image to be processed is removed and does not enter the category of classified storage;
if the inference score of the image to be processed is 80, the target type is the object image, and the preset type range is the object image, the image to be processed can be classified as the object image and stored.
Optionally, the step S1 may include:
step S11, collecting video data output by the video equipment according to a certain time interval;
step S12, obtaining images from the video data through capturing pictures or analyzing video streams;
in this embodiment, the capture may adopt an apparatus capture capability attached by an apparatus manufacturer when the video apparatus is delivered, and the acquiring of the image by the video stream is a capability of capturing the image from the video stream after the image is analyzed by the video stream.
And step S13, storing the collected images locally and pushing image acquisition messages to a local message queue.
In this embodiment, the pushed image obtaining message may specifically include an image local storage address and device information.
In the implementation process, images to be processed are collected from video equipment at regular time, the images to be processed are input into a preset AI algorithm model, an inference result of the images to be processed is obtained through the AI algorithm model, the images to be processed are screened based on the inference result, and classification results of the images to be processed are obtained and stored; in the process of acquiring the image to be processed, the video equipment can be the video equipment in the actual scene, and the image acquisition is carried out on the video equipment in the actual scene, so that the image data more conforms to the service scene, and the model trained by utilizing the image data can be more suitable for the actual scene. The image is collected on the premise of not needing to replace the existing video equipment, so that the huge cost generated by upgrading a large amount of video equipment can be reduced; the AI algorithm model is adopted to obtain the reasoning result of the image to be processed, and then the image is screened, so that on one hand, the cost of manual screening can be reduced; on the other hand, the inference result can be reserved as image annotation information, for example, the position of the target in the inference result in the image to be processed is reserved as image annotation information, so that the huge labor cost generated by the annotated image can be reduced, and the method can be used for training other AI models.
The process according to the invention is illustrated below by means of specific examples:
firstly, automatically collecting images from video equipment; referring to fig. 2, fig. 2 is a schematic flow chart illustrating a method for automatically acquiring an image from a video device according to the present invention;
1. video access;
2. collecting timing images;
3. storing locally;
4. and sending the image information to a message queue.
Classifying the image through an AI algorithm; referring to fig. 3, fig. 3 is a flow chart illustrating a method for classifying images by an AI algorithm according to the present invention;
1. obtaining an image type rule and a grading rule which need to be acquired when the algorithm is started;
2. after the inference result is obtained, judging whether the target type contained in the inference result is in the range specified by the target rule, if not, abandoning the image;
3. judging whether the inference score corresponding to the target contained in the inference result is higher than the set scoring rule, and if the inference score is lower than the set scoring rule, giving up the image;
4. and classifying and storing the images within the range specified by the target rule and the scoring rule according to the target type.
Example two:
referring to fig. 4, fig. 4 shows a system for automatically acquiring and classifying images based on an AI algorithm according to the present invention, which includes:
the image acquisition unit 10 is used for acquiring images to be processed from the video equipment at regular time;
the inference unit 20 is configured to input the image to be processed into a preset AI algorithm model, and obtain an inference result of the image to be processed through the AI algorithm model;
and the classification unit 30 is configured to screen the to-be-processed image based on the inference result, obtain a classification result of the to-be-processed image, and store the classification result.
Specifically, the image acquiring unit 10 includes: the system comprises a video access module, a timing execution module, an image acquisition module, an image storage module and a local message queue module; wherein the content of the first and second substances,
the video access module is used for accessing video data of the video equipment to the image acquisition module;
the timing execution module is used for calling the image acquisition module according to a certain time interval to acquire images from the video data through image capture or acquiring images through analyzing video streams;
the image storage module is used for storing the acquired image locally;
and the local message queue module is used for receiving and sending the image information to be processed.
Specifically, the inference unit 20 and the classification unit 30 may specifically include an image receiving module, an AI algorithm inference module, an image classification module, a data storage module, a data server, and a local message queue, where the image receiving module obtains image information from the local message queue, the AI algorithm inference module inputs the image information into the AI model for inference and obtains an inference result, the image classification module screens an image according to the inference result, and the data storage module stores the selected image inference information into the data server.
Example three:
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application, and in the present application, an electronic device 100 for implementing a method for automatically acquiring and classifying images based on an AI algorithm according to the present invention according to the embodiment of the present application can be described by using the schematic diagram shown in fig. 5.
As shown in fig. 5, an electronic device 100 includes one or more processors 102, one or more memory devices 104, and/or other types of connections (not shown) that interconnect the components. It should be noted that the components and structure of the electronic device 100 shown in fig. 5 are only exemplary and not limiting, and the electronic device may have some of the components shown in fig. 5 and may also have other components and structures not shown in fig. 5, as desired.
The processor 102 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 100 to perform desired functions.
The storage 104 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. On which one or more computer program instructions may be stored that may be executed by processor 102 to implement the functions of the embodiments of the application (as implemented by the processor) described below and/or other desired functions. Various applications and various data, such as various data used and/or generated by the applications, may also be stored in the computer-readable storage medium.
The invention also provides a computer storage medium on which a computer program is stored, in which the method of the invention, if implemented in the form of software functional units and sold or used as a stand-alone product, can be stored. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer storage medium and used by a processor to implement the steps of the embodiments of the method. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer storage medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer storage media may include content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer storage media that does not include electrical carrier signals and telecommunications signals as subject to legislation and patent practice.
Various other modifications and changes may be made by those skilled in the art based on the above-described technical solutions and concepts, and all such modifications and changes should fall within the scope of the claims of the present invention.
Claims (10)
1. A method for automatically acquiring and classifying images based on an AI algorithm is characterized by comprising the following steps:
acquiring an image to be processed from video equipment at regular time;
inputting the image to be processed into a preset AI algorithm model, and obtaining an inference result of the image to be processed through the AI algorithm model;
and screening the images to be processed based on the reasoning result to obtain a classification result of the images to be processed, and storing the classification result.
2. The AI algorithm-based method for automatically capturing and classifying images according to claim 1, wherein the obtaining of the inference result of the image to be processed through the AI algorithm model comprises:
the AI algorithm model obtains preset image classification rules and score rules, and obtains the classification result of the image to be processed according to the image classification rules and the score rules.
3. The AI algorithm-based automatic image collection and categorization method of claim 1, wherein the reasoning results include one or more of a reasoning objective type of the image to be processed, a position of the reasoning objective within the image to be processed, and a reasoning score corresponding to the objective.
4. The AI algorithm based image automatic acquisition and classification method according to claim 3 wherein the filtering of the images to be processed based on the inference results to obtain the classification results of the images to be processed for storage comprises:
and eliminating the images to be processed of which the target types do not meet the preset type range in the inference results of the images to be processed, eliminating the images to be processed of which the inference scores are smaller than the preset threshold scores, and then classifying and storing the residual images to be processed according to the target types.
5. The AI algorithm-based automatic image acquisition and classification method according to claim 1, wherein the timed acquisition of the images to be processed from the video device comprises:
acquiring video data output by video equipment according to a set time interval;
acquiring an image from the video data through image capture or acquiring an image through analyzing a video stream;
and storing the acquired image locally and pushing an image acquisition message to a local message queue.
6. The AI algorithm-based automatic image collection and classification method of claim 3, wherein the AI algorithm model uses a YOLOv5 model, and the YOLOv5 model is used to obtain the inference result of the image to be processed, and the inference result is stored and used as a training sample for other AI models.
7. A system for automatically acquiring and classifying images based on an AI algorithm, comprising:
the image acquisition unit is used for acquiring images to be processed from the video equipment at regular time;
the inference unit is used for inputting the image to be processed into a preset AI algorithm model and obtaining an inference result of the image to be processed through the AI algorithm model;
and the classification unit is used for screening the image to be processed based on the inference result to obtain a classification result of the image to be processed and storing the classification result.
8. The AI algorithm-based automatic acquisition and categorization image system of claim 7, characterized in that the image acquisition unit comprises: the system comprises a video access module, a timing execution module, an image acquisition module, an image storage module and a local message queue module; wherein the content of the first and second substances,
the video access module is used for accessing video data of the video equipment to the image acquisition module;
the timing execution module is used for calling the image acquisition module according to a set time interval to acquire images from the video data through capturing images or analyzing video streams to acquire images;
the image storage module is used for storing the acquired image locally;
and the local message queue module is used for receiving and sending the image information to be processed.
9. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of automatically acquiring and classifying images based on an AI algorithm of any of claims 1-6.
10. A computer storage medium on which a computer program is stored, which, when being executed by a processor, carries out the method of automatically acquiring and classifying images based on an AI algorithm according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210682025.9A CN115115980A (en) | 2022-06-15 | 2022-06-15 | Method and system for automatically acquiring and classifying images based on AI algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210682025.9A CN115115980A (en) | 2022-06-15 | 2022-06-15 | Method and system for automatically acquiring and classifying images based on AI algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115115980A true CN115115980A (en) | 2022-09-27 |
Family
ID=83328081
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210682025.9A Pending CN115115980A (en) | 2022-06-15 | 2022-06-15 | Method and system for automatically acquiring and classifying images based on AI algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115115980A (en) |
-
2022
- 2022-06-15 CN CN202210682025.9A patent/CN115115980A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108288027B (en) | Image quality detection method, device and equipment | |
KR102220174B1 (en) | Learning-data enhancement device for machine learning model and method for learning-data enhancement | |
CN110602526A (en) | Video processing method, video processing device, computer equipment and storage medium | |
CN110414321B (en) | Method and system for automatically identifying shaking video | |
CN111223129A (en) | Detection method, detection device, monitoring equipment and computer readable storage medium | |
CN110610123A (en) | Multi-target vehicle detection method and device, electronic equipment and storage medium | |
CN108241662B (en) | Data annotation optimization method and device | |
CN114445768A (en) | Target identification method and device, electronic equipment and storage medium | |
CN111462167A (en) | Intelligent terminal video analysis algorithm combining edge calculation and deep learning | |
CN114359669A (en) | Picture analysis model adjusting method and device and computer readable storage medium | |
CN109977875A (en) | Gesture identification method and equipment based on deep learning | |
CN115269438A (en) | Automatic testing method and device for image processing algorithm | |
CN113822110B (en) | Target detection method and device | |
US20210117686A1 (en) | Methods and systems for customized image and video analysis | |
CN115115980A (en) | Method and system for automatically acquiring and classifying images based on AI algorithm | |
CN116824135A (en) | Atmospheric natural environment test industrial product identification and segmentation method based on machine vision | |
CN115879002A (en) | Training sample generation method, model training method and device | |
CN113010736A (en) | Video classification method and device, electronic equipment and storage medium | |
CN112818984B (en) | Title generation method, device, electronic equipment and storage medium | |
CN115311680A (en) | Human body image quality detection method and device, electronic equipment and storage medium | |
CN114241363A (en) | Process identification method, process identification device, electronic device, and storage medium | |
CN115049963A (en) | Video classification method and device, processor and electronic equipment | |
CN111553408B (en) | Automatic test method for video recognition software | |
Grabs et al. | Supervised Machine Learning based Classification of Video Traffic Types | |
CN114170271A (en) | Multi-target tracking method with self-tracking consciousness, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |