CN112933481A - Fire-fighting early warning robot, system and method based on image analysis - Google Patents
Fire-fighting early warning robot, system and method based on image analysis Download PDFInfo
- Publication number
- CN112933481A CN112933481A CN202110283406.5A CN202110283406A CN112933481A CN 112933481 A CN112933481 A CN 112933481A CN 202110283406 A CN202110283406 A CN 202110283406A CN 112933481 A CN112933481 A CN 112933481A
- Authority
- CN
- China
- Prior art keywords
- fire
- module
- fighting
- image analysis
- early warning
- 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
-
- A—HUMAN NECESSITIES
- A62—LIFE-SAVING; FIRE-FIGHTING
- A62C—FIRE-FIGHTING
- A62C27/00—Fire-fighting land vehicles
-
- A—HUMAN NECESSITIES
- A62—LIFE-SAVING; FIRE-FIGHTING
- A62C—FIRE-FIGHTING
- A62C37/00—Control of fire-fighting equipment
- A62C37/04—Control of fire-fighting equipment with electrically-controlled release
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
Landscapes
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Fire-Detection Mechanisms (AREA)
- Alarm Systems (AREA)
- Fire Alarms (AREA)
Abstract
The invention discloses a fire-fighting early warning robot, a fire-fighting early warning system and a fire-fighting early warning method based on image analysis, wherein the fire-fighting early warning robot comprises a body, a crawler walking mechanism, a control module, a lighting module, a rectangular supporting frame, a fire extinguishing module, an image information acquisition module, an alarm device and a sensor module, wherein the crawler walking mechanism is fixed on the left side and the right side of the body; the hollow part in the body is provided with a control module; the upper surface of the body is provided with a fire extinguishing module and a support frame, and the support frame is provided with an image information acquisition module and an alarm device; the front side surface of the body is provided with an illuminating module; a sensor module is arranged at one end of the upper surface of the body close to the lighting device; control module, image information acquisition module, sensor module, power module, alarm device, lighting module and fire extinguishing module electricity in proper order are connected, are convenient for carry out accurate early warning to the conflagration under unmanned condition to can put out a fire in real time, eliminate the conflagration hidden danger at the source.
Description
Technical Field
The invention belongs to the technical field of fire detection and fire fighting equipment, and particularly relates to a fire fighting early warning robot, system and method based on image analysis.
Background
In recent years, site fire accidents frequently occur, and huge losses are caused to the safety of the society and the lives and properties of people. Compared with other industries, the construction site operation environment is more complex. On one hand, the engineering construction period is long, the flow process is more, and all the procedures are mutually crossed; on the other hand, the construction site area is limited, flammable and combustible materials are stacked out of order, electrical circuits are not managed in a standard mode, and the like. These factors tend to induce a fire in the construction site. In the initial stage of open fire, due to insufficient fire-proof space of temporary facilities, the speed of fire spreading is accelerated due to insufficient fire-fighting facilities and the like, so that the high casualty rate and the high damage of building components are caused.
The most effective and rapid method for preventing fire is to find and dispose the hidden danger of flame in time. The conventional fire detection equipment is influenced by factors such as detection distance, installation position and the like, so that the prediction accuracy is low, for example, a temperature-sensitive detector installed in a factory building can give an alarm signal when flame burns enough to excite an alarm threshold of the temperature-sensitive detector. 12.4.5 in the specification of automatic fire alarm system design (GB50116-2013) also indicates that "a spot type infrared flame detector or an image type flame detector with level 1 sensitivity should be selected and the detector setting height should be reduced" at the initial stage of a fire where a small amount of smoke is generated and a sharp flame is generated.
At present, the flame detection technology based on video images can realize large-view-field remote monitoring without sensing flame temperature and the like, and is widely applied. However, the fluidity of the operation of workers is strong, and blind areas are easy to appear when flame hidden dangers possibly existing in a construction site are detected only by a fixed camera of a construction site, so that video data are discontinuously acquired and are not easy to obtain, the early warning capability is weak, and the flame hidden dangers cannot be timely treated after being found. The robot has the characteristics of strong maneuverability, high fire extinguishing safety and the like, and gradually starts to be applied to various fire safety fields in recent years. However, most of the currently applied fire-fighting robots pay attention to the disposal link after a fire occurs, and need to be connected with a water bag externally or be provided with a water tank large enough to extinguish the fire (for example, the application No. 201910033326.7 discloses a tunnel fire-fighting robot and a fire-fighting device, the application No. 201922224356.4 discloses a range-moving type fire-fighting robot), so that the flexibility is weak, and the capabilities of flame hidden danger inspection and early disposal are lacked.
Disclosure of Invention
At present, a fire-fighting early warning robot in the prior art only has the function of detecting hidden dangers in a fixed area and the function of extinguishing fire in real time after a disaster occurs, and the early warning accuracy is not high.
In order to solve the problems, the invention provides a fire-fighting early warning robot based on image analysis, which comprises a body, a crawler walking mechanism, a control module, an illumination module, a rectangular support frame, a fire extinguishing module, an image information acquisition module, an alarm device and a sensor module;
the crawler traveling mechanisms are fixed on the left side and the right side of the body, and the body is far away from the ground; the body is hollow, and a control module is arranged in the hollow part;
the control module consists of a wireless signal receiving and transmitting device, a data storage module, a control module and a GPS (global positioning system) positioner which are electrically connected in sequence;
the front side surface of the body is provided with the lighting module;
the rectangular support frame is arranged on the upper surface of the body, and the fire extinguishing module is arranged on the support frame;
the image information acquisition module and the alarm device are arranged on one side of the support frame far away from the lighting module;
the sensor module is arranged at the front part of the body;
the image information acquisition module, the sensor module, the first power module, the alarm device, the lighting module and the fire extinguishing module are respectively electrically connected with the control module.
Furthermore, the fire extinguishing module comprises a bracket, a trigger device and a fire extinguisher, and the bracket and the trigger device are sequentially arranged on the upper surface of the vehicle body; the bracket is positioned between the sensor module and the triggering device; one end of the fire extinguisher is movably arranged on the bracket, and the other end of the fire extinguisher is fixed on the trigger device.
Further, the fire extinguishing module comprises a bracket, a triggering device and a fire extinguisher, and the bracket is fixed on a support frame between the lighting module and the triggering device; the trigger device is arranged on the vehicle body between the support and the alarm device, and the fire extinguisher is fixed on the support and the trigger device.
Furthermore, the trigger device comprises a trigger frame, a trigger drive and a pressing plate, wherein the trigger drive is electrically connected with the pressing plate and sequentially arranged on the upper surface of the body in a front-back manner; the trigger frame is fixed on the trigger drive, the fire extinguisher is erected on the trigger frame, and the pressing plate is located right below the fire extinguisher switch.
Furthermore, the support frame is a hollow tube with a clamping groove on the surface, and the fire extinguishing module, the image information acquisition module and the alarm device are clamped on the hollow tube.
Furthermore, the image information acquisition module is a spherical camera and is fixed at one end of the supporting rod, and the other end of the supporting rod is fixed on the supporting frame.
Further, the sensor module comprises an ultrasonic sensor, an infrared sensor and a flame sensor, and the three sensors are arranged on the upper surface of the vehicle body side by side.
Furthermore, the alarm device is two interconnected audible and visual alarms which are respectively arranged at two sides of the image information acquisition module.
A fire-fighting early warning system based on image analysis comprises a robot command system and a mobile platform control system, wherein the robot command system is formed by electrically connecting a first power supply module, a man-machine interaction module and a wireless signal receiving and transmitting device; the mobile platform control system is composed of a second power supply module, an image information acquisition module, a sensor module, an alarm lighting module and a fire extinguishing module, wherein the second power supply module, the image information acquisition module, the sensor module, the alarm lighting module and the fire extinguishing module are electrically connected with the control module.
Further, the wireless signal transceiver is electrically connected with the control module.
In another aspect of the invention, a fire-fighting early warning method based on image analysis is disclosed, comprising the following steps:
pre-storing first environment information in a control module;
the control module judges a routing inspection path according to the first environment information and controls the fire-fighting early warning robot to move along the routing inspection path;
initializing parameter information of a video image information acquisition module;
collecting second environment information on the routing inspection path;
processing the second environment information based on a deep learning algorithm;
outputting early warning information according to the processed second environment information;
judging the real-time positions of the fire-fighting early warning robot and the flame based on the early warning information;
controlling the fire-fighting early warning robot to move to a fire-fighting distance threshold according to the real-time position information;
controlling a trigger device to trigger a fire extinguisher to extinguish fire;
acquiring image information of a fire extinguishing area;
and judging whether open fire exists or not according to the image information, if so, continuing to extinguish the fire, and otherwise, stopping extinguishing the fire.
Further, the processing the second environment information based on the deep learning algorithm includes:
collecting a sample data set to train a deep learning detection model;
and inputting the second environment information into the trained deep learning detection model for flame detection.
The invention discloses a fire-fighting early-warning robot, a fire-fighting early-warning system and a fire-fighting early-warning method based on image analysis.A video image acquisition module of intelligent environmental parameters is carried, video image information of existing construction flames is converted into digital signals through the video image information acquisition module and is sent to a control module for processing, the control module controls a fire extinguishing module to start an aerosol fire extinguisher for fire extinguishing according to a monitoring processing result, a fire-fighting linkage response mechanism of construction site inspection, flame detection and intelligent fire extinguishing is established, and the fire can be extinguished in real time; carry on intelligent fire extinguishing module, be connected in order to receive the signal of putting out a fire with the control system electricity and put out a fire intelligently, increased the accuracy that the robot was put out a fire.
In a word, the fire-fighting early-warning robot, the fire-fighting early-warning system and the fire-fighting early-warning method based on image analysis disclosed by the invention have higher intelligent degree, are convenient for carrying out accurate early warning on fire under the unmanned condition, can suppress the flame growth situation in time, eliminate the fire hazard at the source, assist managers in strengthening the fire-fighting safety management of a construction site, and do not generate secondary damage to the working environment.
Drawings
In order to more clearly describe the embodiments of the present invention or the technical solutions in the prior art, the embodiments will be described in detail below with reference to the accompanying drawings.
FIG. 1 is a schematic structural diagram of an intelligent early warning and fire fighting robot;
FIG. 2 is a schematic view of the interior of a box of the intelligent early warning and fire fighting robot;
FIG. 3 is a diagram of a system architecture of the intelligent pre-warning robot;
FIG. 4 is a fire extinguishing flow chart of the intelligent early warning robot system;
FIG. 5 is a side view of a trigger module of the intelligent pre-warning robot;
FIG. 6 is a rear view of the intelligent pre-warning robot;
in the drawings: 1. a vehicle body; 2. a crawler-type traveling mechanism; 3. a box body; 4. a driving wheel; 5. a crawler belt; 6. a support frame; 7. a spherical camera; 8. an ultrasonic sensor; 9. an infrared sensor; 10. a flame sensor; 11. an audible and visual alarm; 12. an illuminating lamp; 13. an aerosol fire extinguisher holder; 14. an aerosol fire extinguisher trigger device; 15. aerosol fire extinguishers; 16. a trigger frame; 17. triggering the drive; 18. pressing a plate; 19. the wireless signal is connected with the transceiver; 20. a data storage module; 21. a processor module; 22. a GPS locator; 23. a lithium battery; 24 extinguisher button.
Detailed Description
The present invention will now be described in detail with reference to the drawings, wherein the specific embodiments and descriptions are provided for illustration only and not for the purpose of limiting the invention.
As shown in fig. 1, the first embodiment discloses an intelligent fire-fighting early warning robot based on video image analysis, which comprises a vehicle body 1.
The vehicle body 1 comprises a box body 3 and crawler-type traveling mechanisms 2 arranged on two sides of the box body 3; the crawler belt walking structure 2 comprises a driving wheel 4 and a pair of crawler belts 5 on the left side and the right side; a wireless signal receiving and transmitting device 19, a data storage module 20, a processor module 21, a GPS positioner 22 and a lithium battery 23 are arranged in the box body 3 of the robot body and electrically connected; a support frame 6 is arranged on the body box body, the support frame 6 is a rectangle formed by four support rods, two support rods are arranged on the box body in parallel along the advancing direction of the crawler belt walking mechanism, a third support rod is horizontally fixed on the two support rods, and a fourth support rod is fixed between the two support rods and is connected with the two support rods; a fifth supporting rod is vertically fixed on the third supporting rod, and the other end of the fifth supporting rod is provided with a video image information acquisition module; the bracing piece is inside cavity and the surface has APS aluminium alloy pipe of the draw-in groove of caving in, the draw-in groove can make fire module, sensor module and audible-visual alarm module of robot etc. along the optional position of draw-in groove direction joint at the support frame.
The video image information acquisition module, the control module, the alarm lighting module and the fire extinguishing module are electrically connected, so that the functions of acquiring video images, performing sound-light alarm and extinguishing fire in real time are realized.
The sensor module, the control module and the power module are electrically connected, so that the function of providing required parameters for the walking path and the flame identification of the robot is realized.
The alarm lighting module is respectively connected with the control module, the video image information acquisition module and the power module, so that the functions of robot flame early warning response and lighting for robot walking are realized.
The fire extinguishing module is respectively connected with the control module, the video image information acquisition module and the power supply module and used for recognizing flame and extinguishing fire during moving inspection.
As shown in fig. 1 and 6, the video image information acquisition module adopts a spherical camera 7 to realize horizontal, pitching or 360-degree rotation monitoring.
The sensor modules include, but are not limited to, an ultrasonic sensor 8, an infrared sensor 9, a flame sensor 10.
The power module is a lithium battery pack which comprises two lithium batteries and is connected with the power supply voltage stabilizing module through a power line to supply power.
The alarm lighting module comprises an alarm device and a lighting device, wherein the alarm device adopts an audible and visual alarm 11 and is arranged on two sides of the video image information acquisition module; the illuminating lamps 12 are respectively arranged on the left side and the right side of the front side face of the body box body and used for realizing night illumination.
The fire extinguishing module comprises an aerosol fire extinguisher bracket 13, an aerosol fire extinguisher trigger device 14 and an aerosol fire extinguisher 15, the aerosol fire extinguisher bracket is arranged on the box body 3, and the aerosol fire extinguisher is arranged on the aerosol fire extinguisher bracket and can rotate in a pitching manner; the aerosol fire extinguisher trigger device comprises a trigger frame 16, a trigger drive 17 arranged on the trigger frame and a pressure plate 18 connected to the trigger drive, and the aerosol fire extinguisher is fixed on the aerosol fire extinguisher bracket and is positioned between the trigger drive and the trigger frame.
As shown in fig. 1 and 5, the trigger module includes a trigger frame, a trigger driver and a pressing plate, the trigger frame is a frame with an outer frame in a rectangle shape and an inner frame in a circular shape, the trigger driver is connected with the pressing plate, when the image information is analyzed to find flames, the controller sends an instruction to the control driver, and then the pressing plate is controlled to press the fire extinguisher to extinguish the fire by spraying; when the robot can not detect the flame, the flame is sprayed out, namely the fire extinguishing is finished, the pressure plate is retracted, and the fire extinguisher is closed.
Compared with a conventional fire extinguisher, the fire extinguisher adopted by the embodiment is an aerosol fire extinguishing device, has the advantages of light weight, high efficiency, small volume and the like, can be moved in a narrow space (such as a scaffold area erected during construction) when being carried on a mobile robot, improves the cruising ability and prolongs the patrol inspection time; in addition, aerosol extinguishment does not need a pipe network, the problems of pressure relief and leakage do not exist, maintenance is not needed within the service life, and the cost is low; moreover, compared with the traditional dry powder extinguishing agent, the dry powder extinguishing agent is cleaner to use, and the aerosol fire extinguisher is more suitable to be arranged on a mobile robot to realize the fire extinguishing function.
The APS aluminum profile pipe adopted by the embodiment is used as the support frame, has small density, light weight, good heat conduction and electric conduction performance, strong plasticity, no magnetism, stable chemical property, corrosion resistance and recyclability.
In another embodiment, as shown in fig. 3, a fire-fighting early warning robot system based on image analysis is disclosed, which comprises a robot command system and a mobile platform control system:
the robot command system consists of a power module 1 and a human-computer interaction interface module; the power supply module 1 supplies power to the robot command system; the human-computer interaction interface module is used for outputting an operation instruction, sensor parameters and detecting the video image acquired by the video image information acquisition module in real time; the robot can be according to the operation instruction adjustment route of patrolling and examining, and the video image that detects is used for judging whether there is flame.
The mobile platform control system consists of a power supply module, a video image information acquisition module, a sensor module, an alarm lighting module, a fire extinguishing module, a wireless signal receiving and transmitting device and a control module.
The sensor module, the control module and the power module are electrically connected to realize the function of providing parameters for the walking path and the flame identification of the robot.
The alarm lighting module is respectively and electrically connected with the control module, the video image information acquisition module and the power supply module, so that the functions of robot flame early warning response and lighting for robot walking are realized.
The fire extinguishing module is respectively connected with the control module, the video image information acquisition module and the power supply module and used for recognizing flame and extinguishing fire during moving inspection.
The wireless signal receiving and sending device is electrically connected with the man-machine interaction interface module and the control module, and is used for receiving the digital signal output by the man-machine interaction interface module, processing the digital signal, transmitting the processed digital signal to the control module in the mobile platform control system, and sending a corresponding instruction according to the digital signal.
In another embodiment, as shown in fig. 4, an intelligent fire-fighting early warning method is disclosed, which comprises the following steps:
the data storage module stores a route track of a construction operation environment to be monitored in advance, the processor module judges a walking route according to current positioning information provided by the GPS positioner, and the control module drives the robot to walk along a planned route and transmits a traveling picture to the robot command system in real time through the wireless signal transceiver.
The video image information acquisition module initializes the spherical camera, acquires a video image of an area in front of a construction site in real time by using the spherical camera, and transmits the acquired image to the robot command system through a digital signal; and the robot command system analyzes and processes the transmitted video image by using a flame detection algorithm based on deep learning and returns the analysis and processing result to the control system of the mobile platform.
The flame detection algorithm based on deep learning specifically comprises the following steps: a flame detection model is constructed by taking a Single-point multi-box Detector (SSD) and a lightweight MobileNet network as examples, so that automatic detection of flames in a construction site is realized, the model normalizes the size of an input flame image, performs flame detection by using 6 convolution layers in the network, and finally adopts non-maximum value to inhibit and eliminate redundant interference terms to obtain a final flame detection result.
Compared with the traditional machine learning method, the deep convolutional network can automatically extract target features and perform classification recognition, the step of manually extracting the features is avoided, the robustness of the system is improved, the model combines the advantages of two types of networks, the resource consumption is reduced on the basis of ensuring good accuracy, and the running detection speed is increased.
The steps for training the detection model are as follows:
collecting a plurality of flame video images of a construction site, and dividing the images into a training set, a verification set and a test set according to a proportion;
sending the images of the training set into a flame detection model for training in batches, and adjusting training parameters to obtain a model with the best performance;
and deploying the obtained optimal flame detection model to an early warning robot end, and detecting the flame information collected on the construction site by using a verification set and a test set.
The control module sends out fire early warning through an audible and visual alarm according to the video flame image analysis result, meanwhile, the spherical camera tracks the flame, and the position information of the vehicle body and the flame is judged through the GPS positioner and the sensor; the control module sends an instruction for controlling the vehicle body crawler to rotate by a certain angle and then moves to a specified position.
When the robot finds fire, the robot moves according to a preset fire extinguishing distance threshold (the threshold is more than or equal to 1.5m and more than or equal to 1m), if the flame is small, the robot moves to a position 1m away from the flame, and if the flame is large, the robot moves to a position 1.5m away from the flame, and the aerosol fire extinguisher is triggered and driven to trigger the aerosol fire extinguisher to extinguish fire in a eruption mode.
The video image information acquisition module through the robot gathers the regional image of putting out a fire in real time to the real-time image processing who will gather is converted into digital signal and is sent into robot command system and discerns the control, shows that flame is put out when can not discern that the regional flame of putting out a fire exists and put out fire, and flame sensor also can assist simultaneously and judge whether flame is put out.
The robot command system sends the processing result of each period to the control module, and the control module controls the trigger drive arranged on the trigger frame to continuously open or close the aerosol fire extinguisher according to the processing result.
If the flame is extinguished, the aerosol fire extinguisher is closed, the control module sends out a command for controlling the crawler driving of the vehicle body to continue to patrol according to a preset route, and the video image information acquisition module checks the construction operation environment in real time.
The invention discloses a fire-fighting early-warning robot, a fire-fighting early-warning system and a fire-fighting early-warning method based on image analysis.A video image acquisition module of intelligent environmental parameters is carried, video image information of existing construction flames is converted into digital signals through the video image information acquisition module and is sent to a control module for processing, the control module controls trigger drive mounted on a trigger frame to continuously open an aerosol fire extinguisher for fire extinguishment according to a monitoring processing result, a fire-fighting linkage response mechanism of construction site inspection, flame detection and intelligent fire extinguishment is established, and the fire extinguishment can be carried out at the initial stage of fire occurrence; the intelligent fire extinguishing module who carries adopts aerosol fire extinguisher to replace original artifical external water bag, big water tank technique, and the rotatory every single move of fire extinguisher can be realized to fire extinguisher carrying structure to be connected in order to receive the signal of putting out a fire with the control system electricity and put out a fire in real time, thereby increased the flexibility and the real-time of robot putting out a fire, it is more convenient.
The above description is only exemplary of the present invention and should not be taken as limiting the invention, as any modification, equivalent replacement, or improvement made within the spirit and scope of the present invention should be included in the present invention.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
Claims (10)
1. A fire-fighting early-warning robot based on image analysis is characterized by comprising a body, a crawler walking mechanism, a control module, an illumination module, a rectangular support frame, a fire-extinguishing module, an image information acquisition module, a warning device and a sensor module;
the crawler traveling mechanisms are fixed on the left side and the right side of the body, and the body is far away from the ground; the body is hollow, and a control module is arranged in the hollow part;
the control module consists of a wireless signal receiving and transmitting device, a data storage module, a control module and a GPS (global positioning system) positioner which are electrically connected in sequence;
the front side surface of the body is provided with the lighting module;
the rectangular support frame is arranged on the upper surface of the body, and the fire extinguishing module is arranged on the support frame;
the image information acquisition module and the alarm device are arranged on one side of the support frame far away from the lighting module;
the sensor module is arranged at the front part of the body;
the image information acquisition module, the sensor module, the first power module, the alarm device, the lighting module and the fire extinguishing module are respectively electrically connected with the control module.
2. A fire-fighting pre-warning robot based on image analysis as recited in claim 1, wherein: the fire extinguishing module comprises a bracket, a trigger device and a fire extinguisher, and the bracket is fixed on a support frame between the lighting module and the trigger device; the trigger device is arranged on the vehicle body between the support and the alarm device, and the fire extinguisher is fixed on the support and the trigger device.
3. A fire-fighting pre-warning robot based on image analysis as recited in claim 2, wherein: the trigger device comprises a trigger frame, a trigger drive and a pressing plate, wherein the trigger drive is electrically connected with the pressing plate and is sequentially arranged on the upper surface of the body in a front-back manner; the trigger frame is fixed on the trigger drive, the fire extinguisher is erected on the trigger frame, and the pressing plate is located right below the fire extinguisher switch.
4. A fire-fighting pre-warning robot based on image analysis as recited in claim 1, wherein: the support frame is a hollow tube with a clamping groove on the surface, and the fire extinguishing module, the image information acquisition module and the alarm device are clamped on the hollow tube.
5. A fire-fighting pre-warning robot based on image analysis as recited in claim 1, wherein: the image information acquisition module is a spherical camera and is fixed at one end of the supporting rod, and the other end of the supporting rod is fixed on the supporting frame.
6. A fire-fighting pre-warning robot based on image analysis as recited in claim 1, wherein: the sensor module comprises an ultrasonic sensor, an infrared sensor and a flame sensor, wherein the ultrasonic sensor is arranged on the support frame, and the infrared sensor and the flame sensor are arranged on the body.
7. A fire-fighting pre-warning robot based on image analysis as recited in claim 1, wherein: the alarm device is two sound-light alarms electrically connected.
8. A fire-fighting early-warning system based on image analysis is characterized in that the fire-fighting early-warning system based on image analysis is applied to the fire-fighting early-warning robot based on image analysis according to any one of claims 1-7: the system comprises a command system and a control system, wherein the command system is formed by electrically connecting a first power supply module, a man-machine interaction module and a wireless signal receiving and transmitting device; the control system consists of a second power supply module, an image information acquisition module, a sensor module, an alarm lighting module and a fire extinguishing module which are respectively and electrically connected with the control module; the wireless signal receiving and transmitting device is electrically connected with the control module.
9. An image analysis-based fire early warning method, which is applied to the image analysis-based fire early warning robot according to any one of claims 1-7, and comprises the following steps:
pre-storing first environment information in a control module;
the control module judges a routing inspection path according to the first environment information and controls the fire-fighting early warning robot to move along the routing inspection path;
initializing parameter information of a video image information acquisition module;
collecting second environment information on the routing inspection path;
processing the second environment information based on a deep learning algorithm;
outputting early warning information according to the processed second environment information;
judging the real-time positions of the fire-fighting early warning robot and the flame based on the early warning information;
controlling the fire-fighting early warning robot to move to a fire-fighting distance threshold according to the real-time position information;
controlling a trigger to trigger a fire extinguisher to extinguish fire;
acquiring image information of a fire extinguishing area;
and judging whether open fire exists or not according to the image information, if so, continuing to extinguish the fire, and otherwise, stopping extinguishing the fire.
10. A fire-fighting early warning method based on image analysis as set forth in claim 9, wherein the processing the second environmental information based on the deep learning algorithm comprises:
collecting a sample data set to train a deep learning detection model;
and inputting the second environment information into a trained deep learning detection model for flame detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110283406.5A CN112933481A (en) | 2021-03-16 | 2021-03-16 | Fire-fighting early warning robot, system and method based on image analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110283406.5A CN112933481A (en) | 2021-03-16 | 2021-03-16 | Fire-fighting early warning robot, system and method based on image analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112933481A true CN112933481A (en) | 2021-06-11 |
Family
ID=76230205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110283406.5A Pending CN112933481A (en) | 2021-03-16 | 2021-03-16 | Fire-fighting early warning robot, system and method based on image analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112933481A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106843240A (en) * | 2017-04-18 | 2017-06-13 | 哈尔滨理工大学 | System is coordinated by fire prevention robot and multimachine based on intelligent video |
| CN108992825A (en) * | 2018-06-06 | 2018-12-14 | 北方工业大学 | Intelligent fire-fighting robot and control method thereof |
| CN109276833A (en) * | 2018-08-01 | 2019-01-29 | 吉林大学珠海学院 | A kind of robot patrol fire-fighting system and its control method based on ROS |
| CN110232380A (en) * | 2019-06-13 | 2019-09-13 | 应急管理部天津消防研究所 | Fire night scenes restored method based on Mask R-CNN neural network |
| CN111402541A (en) * | 2020-03-11 | 2020-07-10 | 五邑大学 | Forest fire extinguishing method and system based on unmanned aerial vehicle cluster |
-
2021
- 2021-03-16 CN CN202110283406.5A patent/CN112933481A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106843240A (en) * | 2017-04-18 | 2017-06-13 | 哈尔滨理工大学 | System is coordinated by fire prevention robot and multimachine based on intelligent video |
| CN108992825A (en) * | 2018-06-06 | 2018-12-14 | 北方工业大学 | Intelligent fire-fighting robot and control method thereof |
| CN109276833A (en) * | 2018-08-01 | 2019-01-29 | 吉林大学珠海学院 | A kind of robot patrol fire-fighting system and its control method based on ROS |
| CN110232380A (en) * | 2019-06-13 | 2019-09-13 | 应急管理部天津消防研究所 | Fire night scenes restored method based on Mask R-CNN neural network |
| CN111402541A (en) * | 2020-03-11 | 2020-07-10 | 五邑大学 | Forest fire extinguishing method and system based on unmanned aerial vehicle cluster |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108890657B (en) | Intelligent inspection robot for power distribution room | |
| CN105056457B (en) | A kind of mobile fire-fighting fire extinguishing method for electric power tunnel | |
| CN110496355B (en) | Wisdom fire extinguishing system based on thing networking | |
| CN111672045B (en) | Fire-fighting robot, fire-fighting system and fire-fighting control method | |
| CN201164675Y (en) | Intelligent robot system for tunnel fire-fighting emergency | |
| CN109331378B (en) | Fire-fighting robot based on image processing and intelligent fire-fighting method | |
| CN111408089A (en) | Fire-fighting robot and fire-fighting robot fire extinguishing system | |
| CN109432658B (en) | Crawler-type fire-extinguishing robot | |
| CN112093050B (en) | Modularized unmanned aerial vehicle fire engine | |
| CN205670368U (en) | A kind of transmission line of electricity network intellectuality mountain fire monitoring system | |
| CN112043991A (en) | Tunnel guide rail traveling fire-fighting robot system and using method | |
| CN111150953A (en) | Compound multi-functional intelligent fire-fighting robot | |
| CN212569979U (en) | Tunnel guide rail traveling fire-fighting robot system | |
| CN112915420A (en) | Fire scene positioning and fire extinguishing method of warehouse intelligent fire extinguishing robot | |
| CN212439798U (en) | Fire-fighting robot | |
| CN108939384A (en) | A kind of Initial Stage of Fire automatic fire extinguishing system based on robot | |
| CN211682148U (en) | Fire rescue robot | |
| CN115246121A (en) | Patrol robot and patrol robot system | |
| CN111390927A (en) | Intelligent robot inspection system for tunnel cable inspection | |
| CN209108492U (en) | Level land formula Initiative Defense intelligent alarm firefighting robot | |
| Hossain et al. | design and implementation of an IoT based firefighting and affected area monitoring robot | |
| CN111508194A (en) | Intelligent building monitoring system based on big data | |
| CN213964918U (en) | Unmanned indoor intelligent fire-fighting robot | |
| CN110053047A (en) | A kind of portable fire inspection machine people based on laser radar | |
| CN214971405U (en) | Fire-fighting early warning robot and system based on image analysis |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210611 |