CN117437470A - Fire hazard level assessment method and system based on artificial intelligence - Google Patents
Fire hazard level assessment method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN117437470A CN117437470A CN202311400912.3A CN202311400912A CN117437470A CN 117437470 A CN117437470 A CN 117437470A CN 202311400912 A CN202311400912 A CN 202311400912A CN 117437470 A CN117437470 A CN 117437470A
- Authority
- CN
- China
- Prior art keywords
- fire
- scene
- data
- artificial intelligence
- image data
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 239000000779 smoke Substances 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims abstract description 9
- 230000000007 visual effect Effects 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000004088 simulation Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 230000006978 adaptation Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 4
- 238000013210 evaluation model Methods 0.000 abstract description 4
- 238000012502 risk assessment Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/54—Extraction of image or video features relating to texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention discloses a fire hazard level assessment method and a fire hazard level assessment system based on artificial intelligence, which relate to the technical field of fire treatment and comprise the following steps: acquiring video image data and coordinate information of a fire scene; judging scene types of the fire scene based on the acquired video image data and the coordinate information; the scene type can be business area, office, residence, outdoor activity area, factory area, natural environment and the like, and is not limited thereto; the scene type of the fire scene is adapted to the algorithm weight of the corresponding model in the artificial intelligent model library; determining the number of people, flame color and smoke movement trend data on the fire scene based on the video image data, applying the data to the algorithm weight of the corresponding model for calculation, and determining the risk level of the fire; outputting a corresponding alarm processing result based on the determined risk level; the method solves the problem that the traditional evaluation model is more in one-to-many, and cannot be matched with the specific situation of the actual unit accurately.
Description
Technical Field
The invention relates to the technical field of fire disaster treatment, in particular to a fire disaster risk level assessment method and system based on artificial intelligence.
Background
When a fire disaster occurs, a decision maker often needs to make a reasonable decision according to the dangerous degree of the fire disaster, and the scene type, the fire disaster scale, the fire disaster position, the type of combustible materials nearby, the number of people and the like of the fire disaster scene are all important factors influencing the dangerous degree of the fire disaster, so that whether the dangerous degree of the fire disaster can be accurately judged in time often becomes an important factor for the decision maker to make a reasonable decision.
In the related art, temperature information and smoke concentration information of a fire scene can be acquired based on a temperature sensing and smoke sensing detection technology to alarm the fire, however, the effective information of the fire scene considered in the mode is too small, so that the dangerous degree of the fire scene cannot be accurately determined.
For example, patent document CN114494944a discloses a method, device, equipment and storage medium for determining fire hazard class, and synchronously discloses obtaining video data of fire scene; according to the video data, determining the number of people, flame color, flame trend and scene type of the fire scene; and determining the dangerous level of the fire disaster according to the personnel number, the flame color, the flame trend and the scene type.
However, the assessment model is usually adapted to a plurality of scenes, however, the fire hazard levels in different scenes are different, and the accuracy of the fire alarm hazard level assessment model is further affected.
Disclosure of Invention
The invention aims to provide a fire hazard level assessment method based on artificial intelligence, which solves the following technical problems:
the existing evaluation model is usually adapted to a plurality of scenes, however, fire hazard levels in different scenes are different, and the accuracy of the fire alarm hazard level evaluation model is further affected.
The aim of the invention can be achieved by the following technical scheme:
an artificial intelligence-based fire hazard level assessment method comprises the following steps:
acquiring video image data and coordinate information of a fire scene;
judging scene types of the fire scene based on the acquired video image data and the coordinate information; the scene type can be business area, office, residence, outdoor activity area, factory area, natural environment and the like, and is not limited thereto;
the scene type of the fire scene is adapted to the algorithm weight of the corresponding model in the artificial intelligent model library;
determining the number of people, flame color and smoke movement trend data on the fire scene based on the video image data, applying the data to the algorithm weight of the corresponding model for calculation, and determining the risk level of the fire;
and outputting a corresponding alarm processing result based on the determined danger level.
Preferably, acquiring video image data of a fire scene includes:
acquiring video image data of a fire scene based on video monitoring equipment;
and acquiring coordinate information of the fire scene based on a GPS positioning device arranged on the video monitoring equipment.
Preferably, the acquiring of the video image data of the fire scene further comprises the steps of:
extracting key frames based on the acquired video image data;
acquiring visual features in the key frames, wherein the visual features comprise building information, landmark information and natural landscape information;
and matching the acquired visual characteristics with an image database of a known place to obtain a shooting place of the video monitoring equipment.
Preferably, when the visual features in the key frame photo are obtained, the photo is compared with the images in the image database;
by comparing features of the images, such as color, texture, and edges, images that are similar to the input photographs are found and the results are ranked according to the similarity.
Preferably, the artificial intelligence model library comprises the steps of:
acquiring fire scene data in a plurality of different fire scenes;
performing numerical simulation based on the fire scene data;
an artificial intelligence model library is constructed based on the results of the numerical simulation performed in the numerical simulation step.
Preferably, the artificial intelligence model library further comprises a model training step of:
training based on an artificial intelligence algorithm to obtain devices capable of evaluating different fire scenarios, wherein the devices capable of evaluating different fire scenarios are capable of building a database based on fire scenario data, determining fire hazard classes based on received data about fire scenarios;
preferably, the corresponding risk coefficients are respectively determined based on the number of people, flame color and smoke movement trend data of the fire scene, and then the final risk assessment value is determined according to the weight corresponding to each index;
an artificial intelligence based fire hazard class assessment system comprising:
the data acquisition module is used for acquiring video image data and coordinate information of the fire scene;
the scene judging module is used for judging the scene type of the fire scene according to the acquired video image data and the coordinate information;
the model adaptation module is used for adapting the scene type of the fire scene to the algorithm weight of the corresponding model in the artificial intelligent model library;
the risk level determining module is used for determining the number of people, flame color and smoke movement trend data of the fire scene from the video image data, applying the data to the algorithm weight of the corresponding model for calculation, and determining the risk level of the fire;
and the alarm module is used for outputting the determined danger level to a corresponding alarm processing result.
The invention has the beneficial effects that:
(1) The invention obtains video image data and coordinate information of a fire scene; judging scene types of the fire scene based on the acquired video image data and the coordinate information; the scene type of the fire scene is adapted to the algorithm weight of the corresponding model in the artificial intelligent model library; determining the number of people, flame color and smoke movement trend data on the fire scene based on the video image data, applying the data to the algorithm weight of the corresponding model for calculation, and determining the risk level of the fire; outputting a corresponding alarm processing result based on the determined risk level;
(2) According to different scene types, different algorithm weights are adapted to the chemical industry park, the factory building, the office building, the business superelevation and the like, and the algorithm model can be optimized according to the accumulated emphasis data of daily management operation, so that the ideal effect of one unit and one model is realized, and the problem that the traditional evaluation model has more than one unit and cannot be accurately matched with the specific situation of an actual unit is solved;
(3) According to the invention, the optimal artificial intelligent model is selected in the artificial intelligent model library for data processing, the fire hazard level result in the scene is updated in real time, and the confirmed result is input into the data source for training the algorithm model, so that the accuracy of the fire alarm hazard level assessment model is improved.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a flow chart of an artificial intelligence based fire hazard class assessment method of the present invention;
FIG. 2 is a schematic diagram of an artificial intelligence based fire hazard class assessment system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention discloses a fire hazard level assessment method based on artificial intelligence, which comprises the following steps:
s100, acquiring video image data and coordinate information of a fire scene;
specifically, in the present embodiment, acquiring video image data of a fire scene includes:
acquiring video image data of a fire scene based on video monitoring equipment;
acquiring coordinate information of a fire scene based on a GPS positioning device installed on video monitoring equipment;
it can be noted that, the specific geographic position shot by the video monitoring device can be determined by the coordinate information acquired by the GPS positioning device, the coordinate information specifically comprises latitude, longitude and altitude information, and the shot place can be accurately acquired based on the information;
s200, judging scene types of the fire scene based on the acquired video image data and the coordinate information; the scene type can be business area, office, residence, outdoor activity area, factory area, natural environment and the like, and is not limited thereto;
specifically, in this embodiment, the method further includes the following steps:
extracting key frames based on the acquired video image data;
acquiring visual features in the key frames, wherein the visual features comprise building information, landmark information and natural landscape information;
matching the obtained visual characteristics with an image database of a known place to obtain a shooting place of the video monitoring equipment;
it should be noted that the image database includes a large number of images and corresponding labeling information, for example ImageNet, COCO, flickr k, etc.;
when a key frame photo is identified, comparing the photo with images in an image database;
by comparing the features of the images, such as color, texture and edges, images similar to the input photos are found, and the results are ranked according to the similarity;
in this way, the global image database may help identify objects, scenes, characters, etc. in the photograph;
in addition, the image database can also provide useful data for tasks such as image description generation, generation of sparse codebooks of large-scale visual vocabulary (Visual Vocabulary Size), image annotation based on convolutional neural networks and the like;
s300, adapting scene types of a fire scene to algorithm weights of corresponding models in an artificial intelligent model library;
specifically, in this embodiment, the artificial intelligence model library includes the steps of:
s301, acquiring fire scene data of a plurality of different fire scenes;
s302, performing numerical simulation based on fire scene data;
s303, constructing an artificial intelligent model library based on the result of the numerical simulation performed in the numerical simulation step;
in addition, the artificial intelligence model library further comprises a model training step:
training based on an artificial intelligence algorithm to obtain devices capable of evaluating different fire scenarios, wherein the devices capable of evaluating different fire scenarios are capable of building a database based on fire scenario data, determining fire hazard classes based on received data about fire scenarios;
s400, determining the number of people, flame color and smoke movement trend data on the fire scene based on the video image data, applying the data to the algorithm weight of the corresponding model for calculation, and determining the risk level of the fire;
specifically, in this embodiment, the corresponding risk coefficients are respectively determined based on the number of people, flame color and smoke movement trend data in the fire scene, and then the final risk assessment value is determined according to the weight corresponding to each index;
it can be stated that the collected data are sent to the service end through the fire alarming equipment, and the data comprise smoke values, current, voltage values and the like;
further, the risk degree can be re-separated, so that the final risk level of the fire scene, such as general risk, relatively dangerous, serious risk and extra heavy risk, can be determined, which is not limited;
the smoke movement data comprises the steps of:
s401, intercepting two frames of images g (t, x, y) and g (t-1, x, y) in a video image data sequence frame;
s402, converting the image type from a color image to a gray image, subtracting the two gray images, and calculating the difference value of each pixel point of the gray image in the front frame and the rear frame:
d(t，x，y)＝|g(t，x，y)-g(t-1，x，y)|
wherein g (t, x, y) is the t-th frame in the image sequence, g (t-1, x, y) is the t-1 th frame;
s403, performing binarization processing on the subtracted image, presetting a threshold value, and judging the relation between the absolute value after subtraction and the threshold value:
wherein M (x, y) ∈M t ；M t The method comprises the steps that a two-dimensional image at a moment T is obtained, and T is a preset threshold value;
s404, when the absolute value is smaller than a preset threshold value, the pixel point is indicated to have small change in the front and rear frame images, and the pixel point is treated as a background image; when the absolute value is larger than a preset threshold value, the pixel point is treated as a foreground because the pixel point causes obvious difference in the front and rear frame images due to motion;
s500, outputting a corresponding alarm processing result based on the determined danger level.
Example 2
Referring to fig. 2, an artificial intelligence based fire hazard level assessment system, comprising:
the data acquisition module is used for acquiring video image data and coordinate information of the fire scene;
the scene judging module is used for judging the scene type of the fire scene according to the acquired video image data and the coordinate information;
the model adaptation module is used for adapting the scene type of the fire scene to the algorithm weight of the corresponding model in the artificial intelligent model library;
the risk level determining module is used for determining the number of people, flame color and smoke movement trend data of the fire scene from the video image data, applying the data to the algorithm weight of the corresponding model for calculation, and determining the risk level of the fire;
the alarm module is used for outputting a corresponding alarm processing result from the determined danger level;
the working principle of the embodiment is as follows: acquiring video image data and coordinate information of a fire scene through a data acquisition module; the scene judging module judges the scene type of the fire scene according to the acquired video image data and the coordinate information; the model adaptation module adapts the scene type of the fire scene to the algorithm weight of the corresponding model in the artificial intelligent model library; the dangerous grade determining module determines the number of people, flame color and smoke movement trend data of the fire scene from the video image data, and applies the data to the algorithm weight of the corresponding model for calculation to determine the dangerous grade of the fire; and the alarm module outputs the corresponding alarm processing result from the determined danger level.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
The foregoing describes one embodiment of the present invention in detail, but the description is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.
Claims (8)
1. The fire hazard level assessment method based on artificial intelligence is characterized by comprising the following steps:
acquiring video image data and coordinate information of a fire scene;
judging scene types of the fire scene based on the acquired video image data and the coordinate information;
the scene type of the fire scene is adapted to the algorithm weight of the corresponding model in the artificial intelligent model library;
determining the number of people, flame color and smoke movement trend data on the fire scene based on the video image data, applying the data to the algorithm weight of the corresponding model for calculation, and determining the risk level of the fire;
and outputting a corresponding alarm processing result based on the determined danger level.
2. The artificial intelligence based fire hazard level assessment method of claim 1, wherein acquiring video image data of a fire scene comprises:
acquiring video image data of a fire scene based on video monitoring equipment;
and acquiring coordinate information of the fire scene based on a GPS positioning device arranged on the video monitoring equipment.
3. The fire hazard level assessment method based on artificial intelligence of claim 2, wherein the step of acquiring video image data of a fire scene further comprises the steps of:
extracting key frames based on the acquired video image data;
acquiring visual features in the key frames, wherein the visual features comprise building information, landmark information and natural landscape information;
and matching the acquired visual characteristics with an image database of a known place to obtain a shooting place of the video monitoring equipment.
4. The fire hazard level assessment method based on artificial intelligence of claim 3, wherein when visual features in a key frame photo are obtained, the photo is compared with images in an image database;
by comparing features of the images, such as color, texture, and edges, images that are similar to the input photographs are found and the results are ranked according to the similarity.
5. The fire hazard classification evaluation method based on artificial intelligence according to claim 1, wherein the artificial intelligence model library comprises the steps of:
acquiring fire scene data in a plurality of different fire scenes;
performing numerical simulation based on the fire scene data;
an artificial intelligence model library is constructed based on the results of the numerical simulation performed in the numerical simulation step.
6. The artificial intelligence based fire hazard level assessment method of claim 5, wherein the artificial intelligence model library further comprises a model training step of:
training is performed based on an artificial intelligence algorithm to obtain devices capable of evaluating different fire scenarios, wherein the devices capable of evaluating different fire scenarios are capable of building a library based on fire scenario data, and determining fire hazard classes based on the received fire scenario data.
7. The fire hazard level assessment method based on artificial intelligence according to claim 6, wherein the corresponding hazard coefficients are respectively determined based on the number of people, flame color and smoke movement trend data of the fire scene, and then the final hazard assessment value is determined according to the weight corresponding to each index.
8. An artificial intelligence based fire hazard level assessment system, comprising:
the data acquisition module is used for acquiring video image data and coordinate information of the fire scene;
the scene judging module is used for judging the scene type of the fire scene according to the acquired video image data and the coordinate information;
the model adaptation module is used for adapting the scene type of the fire scene to the algorithm weight of the corresponding model in the artificial intelligent model library;
the risk level determining module is used for determining the number of people, flame color and smoke movement trend data of the fire scene from the video image data, applying the data to the algorithm weight of the corresponding model for calculation, and determining the risk level of the fire;
and the alarm module is used for outputting the determined danger level to a corresponding alarm processing result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311400912.3A CN117437470A (en) | 2023-10-26 | 2023-10-26 | Fire hazard level assessment method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311400912.3A CN117437470A (en) | 2023-10-26 | 2023-10-26 | Fire hazard level assessment method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117437470A true CN117437470A (en) | 2024-01-23 |
Family
ID=89549368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311400912.3A Pending CN117437470A (en) | 2023-10-26 | 2023-10-26 | Fire hazard level assessment method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117437470A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117688485A (en) * | 2024-02-02 | 2024-03-12 | 北京中卓时代消防装备科技有限公司 | Fire disaster cause analysis method and system based on deep learning |
-
2023
- 2023-10-26 CN CN202311400912.3A patent/CN117437470A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117688485A (en) * | 2024-02-02 | 2024-03-12 | 北京中卓时代消防装备科技有限公司 | Fire disaster cause analysis method and system based on deep learning |
| CN117688485B (en) * | 2024-02-02 | 2024-04-30 | 北京中卓时代消防装备科技有限公司 | Fire disaster cause analysis method and system based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108830145B (en) | People counting method based on deep neural network and storage medium | |
| US11893538B1 (en) | Intelligent system and method for assessing structural damage using aerial imagery | |
| US9551579B1 (en) | Automatic connection of images using visual features | |
| CN112528974B (en) | Distance measuring method and device, electronic equipment and readable storage medium | |
| JP5388829B2 (en) | Intruder detection device | |
| CN117437470A (en) | Fire hazard level assessment method and system based on artificial intelligence | |
| CN110852164A (en) | YOLOv 3-based method and system for automatically detecting illegal building | |
| CN114022910A (en) | Swimming pool drowning prevention supervision method and device, computer equipment and storage medium | |
| CN116343103B (en) | Natural resource supervision method based on three-dimensional GIS scene and video fusion | |
| CN109063549A (en) | High-resolution based on deep neural network is taken photo by plane video moving object detection method | |
| CN110909672A (en) | Smoking action recognition method based on double-current convolutional neural network and SVM | |
| CN114445780A (en) | Detection method and device for bare soil covering, and training method and device for recognition model | |
| CN112131951A (en) | System for automatically identifying behaviors of illegal ladder use in construction | |
| CN110969642B (en) | Video filtering method and device, electronic equipment and storage medium | |
| CN111815576B (en) | Method, device, equipment and storage medium for detecting corrosion condition of metal part | |
| CN113569956A (en) | Mountain fire disaster investigation and identification method based on AI algorithm | |
| CN111598793A (en) | Method and system for defogging image of power transmission line and storage medium | |
| CN113569801B (en) | Distribution construction site live equipment and live area identification method and device thereof | |
| CN107633527B (en) | Target tracking method and device based on full convolution neural network | |
| CN116884192A (en) | Power production operation risk early warning method, system and equipment | |
| CN112380985A (en) | Real-time detection method for intrusion foreign matters in transformer substation | |
| CN117726162A (en) | Community risk level assessment method and system based on multi-mode data fusion | |
| CN116152745A (en) | Smoking behavior detection method, device, equipment and storage medium | |
| SRITARAPIPAT et al. | Urban Growth Modeling based on the Multi-centers of the Urban Areasand Land Cover Change in Yangon, Myanmar | |
| CN114708508A (en) | Method for identifying moving small animal |
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 |