CN112132076A - Forgotten object addressing method based on computer vision - Google Patents
Forgotten object addressing method based on computer vision Download PDFInfo
- Publication number
- CN112132076A CN112132076A CN202011044578.9A CN202011044578A CN112132076A CN 112132076 A CN112132076 A CN 112132076A CN 202011044578 A CN202011044578 A CN 202011044578A CN 112132076 A CN112132076 A CN 112132076A
- Authority
- CN
- China
- Prior art keywords
- model
- articles
- computer vision
- carrying
- image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000013135 deep learning Methods 0.000 claims abstract description 5
- 238000002372 labelling Methods 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims description 4
- 230000006835 compression Effects 0.000 claims description 3
- 238000007906 compression Methods 0.000 claims description 3
- 238000013138 pruning Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 208000000044 Amnesia Diseases 0.000 claims description 2
- 208000031091 Amnestic disease Diseases 0.000 claims description 2
- 230000006986 amnesia Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001939 inductive effect Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/532—Query formulation, e.g. graphical querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Library & Information Science (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a forgetting object addressing method based on computer vision, which comprises the following steps: s1, collecting data, and collecting the image information of the articles easy to forget; s2, preprocessing the collected images, identifying the characteristics of the corresponding articles in the images, classifying the articles, and labeling each object in the image data according to the determined category; s3, creating a deep learning network model and carrying out model training; and S4, carrying out algorithm processing, carrying out scaling processing on the received video stream image to meet the requirements of the model, sending the processed image into the model for prediction, storing the position information of various articles predicted by the model, and recording the articles of other types closest to the article. Compared with the method for searching through the video, the method for addressing the forgotten object based on the computer vision avoids the long-time video turning and watching, does not need to manually search and position the position of the object in the video, and saves the time cost and the labor cost.
Description
Technical Field
The invention belongs to the technical field of video monitoring, and particularly relates to a forgetting object addressing method based on computer vision.
Background
In daily life, people often have the phenomenon that articles can not be found urgently, and the daily mood and the travel efficiency of people are often influenced without the disorderly finding of purposes and ideas. The prior technical scheme needs to add foreign matters on the surface of an object to realize the purposes of positioning and searching, not only influences the attractiveness of the object, but also has limited practicability on small objects or objects which are not suitable for adding foreign matters, and the use cost is gradually increased along with the increase of the objects. The position of the article is located based on big data, the position where the article is finally found needs to be collected, the user needs to perform operation processing, and the convenience of the method needs to be improved.
Disclosure of Invention
In view of the above, in order to overcome the above-mentioned drawbacks, the present invention is directed to a method for addressing a forgotten object based on computer vision,
in order to achieve the purpose, the technical scheme of the invention is realized as follows:
a method for amnesia addressing based on computer vision, comprising:
s1, collecting data, and collecting the image information of the articles easy to forget;
s2, preprocessing the collected images, identifying the characteristics of the corresponding articles in the images, classifying the articles, and labeling each object in the image data according to the determined category;
s3, creating a deep learning network model and carrying out model training;
and S4, carrying out algorithm processing, carrying out scaling processing on the received video stream image to meet the requirements of the model, sending the processed image into the model for prediction, storing the position information of various articles predicted by the model, and recording the articles of other types closest to the article.
Further, in the step S2, the labeled information includes the category to which the item belongs and the position where the item appears.
Further, in step S3, the training process is as follows:
training prepared image data by using a yolov3 network subjected to pruning compression, testing and comparing through a plurality of trained models, and selecting a weight model with the optimal reliability through an MAP value.
Further, after step S2 is executed, in order to increase the number of samples and the robustness of the model, the image data needs to be enhanced, which is specifically as follows:
and the image data is subjected to turning, scaling, clipping and brightness adjustment processing, so that objects can be conveniently recognized in different environments.
Compared with the prior art, the forgetting object addressing method based on computer vision has the following advantages:
the method does not depend on a database or foreign matter sticking, carries out the step of collecting the characteristics of the article in advance by using a deep learning technology through non-inductive video collection and image processing, inputs the category or name of the article when the position of the article is forgotten when a client uses the method, gives the position where the article possibly appears by one key, avoids long-time watching of the video compared with searching through the video, does not need to manually search and position the position where the article appears in the video, saves the time cost and the labor cost, provides convenience for life, and promotes the progress of intelligent life.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart of a method for addressing a forgotten object based on computer vision according to an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, the terms "first", "second", etc. 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," "second," etc. 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 otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to know the condition in the house in real time, the application of domestic intelligent camera is more and more popularized, and the video data through gathering domestic camera in real time carries out analysis processes, uses computer vision and video image processing count, provides the position that the article of forgetting appeared most often and appeared last time, provides a convenient and fast's solution for the searching of the article of forgetting. The method does not depend on a database or foreign matter sticking, the steps of collecting the characteristics of the object are carried out in advance by using a non-inductive video collection and image processing technology, the category or name of the object is input when the position of the object is forgotten when a client uses the method, the position where the object possibly appears is given by one key, and compared with the method of finding the position through a video, the method avoids long-time video turning over and watching, does not need to find and position the position where the object appears in the video manually, saves time cost and labor cost, provides convenience for life, and promotes the progress of intelligent life.
The data required by the method is video image data, and can be realized through a household intelligent camera and a corresponding mobile phone APP or a computer terminal at present when the household camera is more and more popular.
The specific implementation method is as follows (as shown in figure 1):
first, data is prepared. The method is characterized in that common household environment information and articles easy to forget in life, including sofas, television cabinets, mobile phones, remote controllers, keys, wallets and the like, are collected in advance, and a large amount of video image data are collected.
And secondly, preprocessing the image, classifying the articles, and labeling each object in the image data according to the determined category, wherein the labeling information mainly comprises the article category and the position where the article appears.
And thirdly, enhancing the data, namely, in order to increase the number of samples and the robustness of the model, the image data is subjected to processes such as overturning, scaling, clipping, brightness adjustment and the like, so that the object can be conveniently recognized in different environments.
And fourthly, preparing a deep learning network for model training. Training prepared image data by using a yolov3 network subjected to pruning compression, testing and comparing through a plurality of trained models, and selecting a weight model with the optimal reliability through an MAP value.
And fifthly, processing of the algorithm. And carrying out scaling processing on the received video stream image to meet the requirement of the model, sending the processed image into the model for prediction, storing the position information of various articles predicted by the model, and recording the articles (accompanying articles) of other types closest to the article.
The first five parts are finished in the previous processing without any operation of the user.
And the sixth is the use by the user. When a user forgets the position of a required article, a mobile phone APP or a computer terminal is opened, the function of searching the forgotten article is found, the name or the category of the forgotten article is input, and the most frequently appearing position of the article and the accompanying articles can be popped out by clicking for searching, and the position information of the most recently appearing position of the article is provided. The user can quickly and efficiently find the position of the article according to the prompt messages, and time and labor are saved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (4)
1. A method for addressing a amnesia based on computer vision, comprising:
s1, collecting data, and collecting the image information of the articles easy to forget;
s2, preprocessing the collected images, identifying the characteristics of the corresponding articles in the images, classifying the articles, and labeling each object in the image data according to the determined category;
s3, creating a deep learning network model and carrying out model training;
and S4, carrying out algorithm processing, carrying out scaling processing on the received video stream image to meet the requirements of the model, sending the processed image into the model for prediction, storing the position information of various articles predicted by the model, and recording the articles of other types closest to the article.
2. A computer vision based amnestic addressing method according to claim 1, characterized by: in step S2, the labeled information includes the category to which the item belongs and the position where the item appears.
3. The computer vision based amnestic addressing method according to claim 1, wherein in step S3, the training process is as follows:
training prepared image data by using a yolov3 network subjected to pruning compression, testing and comparing through a plurality of trained models, and selecting a weight model with the optimal reliability through an MAP value.
4. The method for addressing a forgotten object based on computer vision according to claim 1, wherein after step S2 is executed, in order to increase the number of samples and the robustness of the model, the image data needs to be enhanced, specifically as follows:
and the image data is subjected to turning, scaling, clipping and brightness adjustment processing, so that objects can be conveniently recognized in different environments.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011044578.9A CN112132076A (en) | 2020-09-28 | 2020-09-28 | Forgotten object addressing method based on computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011044578.9A CN112132076A (en) | 2020-09-28 | 2020-09-28 | Forgotten object addressing method based on computer vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112132076A true CN112132076A (en) | 2020-12-25 |
Family
ID=73844469
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011044578.9A Pending CN112132076A (en) | 2020-09-28 | 2020-09-28 | Forgotten object addressing method based on computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112132076A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113051944A (en) * | 2021-03-24 | 2021-06-29 | 海南电网有限责任公司信息通信分公司 | Wireless distributed rapid object searching method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050505A (en) * | 2013-03-11 | 2014-09-17 | 江南大学 | Multilayer-perceptron training method based on bee colony algorithm with learning factor |
| US20140347473A1 (en) * | 2013-05-22 | 2014-11-27 | Cognex Corporation | System and method for efficient surface measurement using a laser displacement sensor |
| US20150104068A1 (en) * | 2013-10-16 | 2015-04-16 | Cognex Corporation | System and method for locating fiducials with known shape |
| CN108052860A (en) * | 2017-11-06 | 2018-05-18 | 珠海格力电器股份有限公司 | Article retrieval method and device |
| CN109634999A (en) * | 2018-11-21 | 2019-04-16 | 安徽云融信息技术有限公司 | Forgetting article addressing method and device based on big data |
| CN109934873A (en) * | 2019-03-15 | 2019-06-25 | 百度在线网络技术（北京）有限公司 | Mark image acquiring method, device and equipment |
| CN109993045A (en) * | 2017-12-29 | 2019-07-09 | 杭州海康威视系统技术有限公司 | Articles seeking method and lookup device search system and machine readable storage medium |
| CN111159452A (en) * | 2019-11-26 | 2020-05-15 | 恒大智慧科技有限公司 | Method and system for reminding forgetful article, computer equipment and storage medium |
-
2020
- 2020-09-28 CN CN202011044578.9A patent/CN112132076A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050505A (en) * | 2013-03-11 | 2014-09-17 | 江南大学 | Multilayer-perceptron training method based on bee colony algorithm with learning factor |
| US20140347473A1 (en) * | 2013-05-22 | 2014-11-27 | Cognex Corporation | System and method for efficient surface measurement using a laser displacement sensor |
| US20150104068A1 (en) * | 2013-10-16 | 2015-04-16 | Cognex Corporation | System and method for locating fiducials with known shape |
| CN108052860A (en) * | 2017-11-06 | 2018-05-18 | 珠海格力电器股份有限公司 | Article retrieval method and device |
| CN109993045A (en) * | 2017-12-29 | 2019-07-09 | 杭州海康威视系统技术有限公司 | Articles seeking method and lookup device search system and machine readable storage medium |
| CN109634999A (en) * | 2018-11-21 | 2019-04-16 | 安徽云融信息技术有限公司 | Forgetting article addressing method and device based on big data |
| CN109934873A (en) * | 2019-03-15 | 2019-06-25 | 百度在线网络技术（北京）有限公司 | Mark image acquiring method, device and equipment |
| CN111159452A (en) * | 2019-11-26 | 2020-05-15 | 恒大智慧科技有限公司 | Method and system for reminding forgetful article, computer equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113051944A (en) * | 2021-03-24 | 2021-06-29 | 海南电网有限责任公司信息通信分公司 | Wireless distributed rapid object searching method and system |
| CN113051944B (en) * | 2021-03-24 | 2022-11-04 | 海南电网有限责任公司信息通信分公司 | Wireless distributed rapid object searching method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11393205B2 (en) | Method of pushing video editing materials and intelligent mobile terminal | |
| CN104239408B (en) | Data access based on content of images recorded by a mobile device | |
| CN107392238B (en) | Outdoor plant knowledge expansion learning system based on mobile visual search | |
| US20150055879A1 (en) | Method, Server and System for Setting Background Image | |
| CN108289057B (en) | Video editing method and device and intelligent mobile terminal | |
| US20090280859A1 (en) | Automatic tagging of photos in mobile devices | |
| US20080118160A1 (en) | System and method for browsing an image database | |
| CN106156347A (en) | Cloud photograph album classification methods of exhibiting, device and server | |
| CN105677728A (en) | Object image recognition and classification managing method | |
| CN101635005A (en) | Mobile terminal and information retrieval method thereof | |
| CN101479728A (en) | Visual and Multidimensional Search | |
| CN112115906A (en) | Open dish identification method based on deep learning target detection and metric learning | |
| CN101751566B (en) | Method and device for identifying and annotating menu based on handheld device | |
| WO2013131480A1 (en) | Image capturing apparatus based information acquisition method and device, and mobile communication apparatus | |
| US20210117467A1 (en) | Systems and methods for filtering of computer vision generated tags using natural language processing | |
| CN104702759A (en) | Address list setting method and address list setting device | |
| CN109872214A (en) | One key ordering method of food materials, system, electronic equipment and storage medium | |
| CN104217718A (en) | Method and system for voice recognition based on environmental parameter and group trend data | |
| CN109993234A (en) | A kind of unmanned training data classification method, device and electronic equipment | |
| CN112132076A (en) | Forgotten object addressing method based on computer vision | |
| CN106777071B (en) | Method and device for acquiring reference information by image recognition | |
| CN112327659A (en) | Intelligent household control method, device and system based on 5G | |
| CN110222245A (en) | A kind of reminding method and device | |
| CN106777066B (en) | Method and device for image recognition and media file matching | |
| CN106027746A (en) | Call control device and call control 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201225 |
|
| RJ01 | Rejection of invention patent application after publication |