CN114913323A - Method for detecting open fire at night in charging pile area - Google Patents
Method for detecting open fire at night in charging pile area Download PDFInfo
- Publication number
- CN114913323A CN114913323A CN202210828781.8A CN202210828781A CN114913323A CN 114913323 A CN114913323 A CN 114913323A CN 202210828781 A CN202210828781 A CN 202210828781A CN 114913323 A CN114913323 A CN 114913323A
- Authority
- CN
- China
- Prior art keywords
- area
- flame
- open fire
- suspected
- flame area
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 84
- 238000012544 monitoring process Methods 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims description 21
- 238000012937 correction Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 14
- 238000006073 displacement reaction Methods 0.000 claims description 9
- 238000013459 approach Methods 0.000 claims description 3
- 210000000988 bone and bone Anatomy 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 239000003550 marker Substances 0.000 claims description 3
- 230000002688 persistence Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010000369 Accident Diseases 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Images
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
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
- B60L53/30—Constructional details of charging stations
- B60L53/31—Charging columns specially adapted for electric vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
- B60L53/60—Monitoring or controlling charging stations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- 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
- G06V2201/08—Detecting or categorising vehicles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/7072—Electromobility specific charging systems or methods for batteries, ultracapacitors, supercapacitors or double-layer capacitors
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/12—Electric charging stations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Artificial Intelligence (AREA)
- Power Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Human Computer Interaction (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention is suitable for the technical field of charging pile monitoring, and provides a method for detecting open fire at night in a charging pile area, which comprises the following steps: marking a light emitting area such as an indicator light in a scene, and dividing the scene into a non-light area and a light area; collecting a night flame image, marking a flame area, and establishing a suspected flame area detection model; step three, detecting a suspected flame area appearing in the scene by using a night suspected flame area detection model for the no-light area in the scene; according to the method for detecting the open fire in the charging pile area at night, disclosed by the invention, the open fire picture is captured through the monitoring camera and the image recognition, and interference information such as field light, vehicle light irradiation and the like is discharged in detail, so that the open fire detection precision can be effectively improved, meanwhile, by matching with an automatic early warning mode, a worker can be reminded to check and process the early warning picture, and the misjudgment caused by the influence of the vehicle light in the area at night can be effectively reduced.
Description
Technical Field
The invention belongs to the technical field of charging pile monitoring, and particularly relates to a method for detecting open fire at night in a charging pile area.
Background
Under the promotion of policies such as energy conservation and emission reduction, carbon peak-reaching and the like, the electric vehicle industry develops rapidly, and a new safety problem is inevitably brought. In recent years, charging safety accidents of electric vehicles are frequent, and the electric vehicle on fire is very easy to quickly ignite other electric vehicles, so that a larger fire accident is caused.
Most of the prior art adopt a monitoring camera and image recognition to capture an open fire picture and remind workers to check and process an early warning picture, but in a night scene, the detection technology is easily interfered by field light and vehicle light irradiation, so that the open fire detection precision is poor, and therefore, an open fire detection method capable of eliminating light interference is needed.
Disclosure of Invention
The embodiment of the invention provides a method for detecting open fire in a charging pile area at night, which is characterized in that an open fire picture is captured through a monitoring camera and image recognition, interference information such as field light, vehicle light irradiation and the like is discharged in detail, the open fire detection precision can be effectively improved, meanwhile, a worker can be reminded to check and process an early warning picture by matching with an automatic early warning mode, and misjudgment caused by the influence of the vehicle light in the area at night can be effectively reduced.
The embodiment of the invention is realized in such a way that a method for detecting the open fire at night in a charging pile area comprises the following steps:
marking a light-emitting area such as an indicator light in a scene, and dividing the scene into a non-light area and a light area;
collecting a night flame image, marking a flame area, and establishing a suspected flame area detection model;
step three, detecting a suspected flame area appearing in the scene by using a night suspected flame area detection model for the no-light area in the scene;
step four, when a continuous flame area is detected in the monitoring video, detecting vehicles appearing in the scene by using a trained vehicle detection model, and judging whether the continuous flame area is an open flame area;
step five, when a suspected open fire area is detected in the monitoring video, further judging whether open fire exists or not, and sending early warning information when open fire exists;
and step six, when open fire is detected in the scene, extracting open fire information and personnel information, comprehensively judging whether the personnel are suspected fire personnel, and sending early warning of the fire personnel to a relevant management department for processing in real time.
In embodiment 1, the suspected flame area detection model in the second step is obtained by training the labeled data based on a YOLO training model.
In embodiment 1, the third step of detecting a suspected flame area occurring in the scene using a nighttime suspected flame area detection model for the no light area in the scene includes:
detecting and judging whether the flame area is a flame area or a false flame area;
if the flame area is judged whether a continuous flame area exists or not.
Embodiment 1, the detailed steps of the detection and judgment of whether the flame area is a flame area or a false fire area are as follows:
when monitoring videoFrame detection of suspected flame regionsWhereinThe abscissa is fixed for the top left corner of the suspected flame region detection box,the abscissa is fixed for the top left corner of the suspected flame region detection box,the width of the box is detected for the area of suspected flame,calculating a size score for the suspected flame area for detecting a high of the box
Wherein
When in useIn whichAnd if the set fifth judgment threshold value is adopted, the suspected flame area is judged as the flame area, otherwise, the false flame area is judged.
Example 1 details of the procedure for determining whether a flame zone has a continuous flame zoneThe detailed step of judging whether the flame area has the continuous flame area is as follows when the monitoring video is in the first placeThe frame detects the flame area, adds the mark score for the frame imageThe absence of flame zone is marked with a score of 0, recorded fromFrame start continuationCalculating flame persistence score based on the detected flame region in the frame image
When in useIn whichTo set the sixth judgment threshold, judgeThe continuous flame area exists in the frame, otherwise, the continuous flame area does not exist.
Example 1, the detailed procedure of step four is as follows:
when a vehicle is detected within a sceneIn whichThe fixed-point abscissa of the upper left corner of the vehicle detection box,a fixed point ordinate of the upper left corner of the vehicle detection box,for the width of the vehicle detection box,calculating a vehicle flame correlation score for a high vehicle detection frame
When in useIn whichA seventh judgment threshold value is set, the vehicle is judged to be related to the existence of flame, otherwise, the vehicle is judged not to exist,
marking vehicles associated with the presence of flames and extracting vehicle features, obtained fromFrame startDetection frame for marking vehicle in image after frameWhen the vehicle approximates the speed
Is greater than the set eighth judgment threshold valueWhen the vehicle is judged to have displacement, otherwise, the vehicle is judged not to move,
when the displacement of the marked vehicle is detected, the slave computer is calculatedFrame continuationCompanion score within post-frame images
When in useGreater than a set ninth judgment thresholdWhen the flame is detected to be a non-open flame region, otherwise, the flame is detected to be a suspected open flame region,
when the marked vehicle is detected to have displacement, the continuous flame area is judged to be a suspected open flame area,
when the vehicle is not associated with flames, determining that the continuous flame area is a suspected open flame area,
and when the vehicle is not detected in the scene, judging the continuous flame area as a suspected open flame area.
Example 1, the detailed procedure of step five is as follows:
when monitoring videoFrame detection of suspected open fire regionsSetting the regionFor detecting areas of open fireWhereinThe fixed-point horizontal coordinate of the upper left corner of the detection frame of the open fire detection area,a fixed point vertical coordinate is arranged at the upper left corner of the detection frame of the open fire detection area,the width of the detection box for the open fire detection area,detecting a high of a box for an open flame detection area
A first correction constant obtained by training historical data, W is the width of a monitoring picture,a second correction constant trained for historical data,a third correction constant obtained by historical data training is obtained, and H is the height of the monitoring picture;
extracting gray values of pixels in non-suspected open fire areas in the open fire detection areaWhereinIndicating the coordinates of the pixel point whenGreater than the set tenth judgment thresholdAdding the bright spot mark score to the pixel pointPositive and negative;
Collecting the speckle marker scoreThe pixel points form a bright spot setClustering pixels in the bright spot set according to pixel coordinates by using a K-means-based clustering model, and for any O in a clustering result, when the number of elements of O is equal to that of the elements of OCluster radius with OSatisfy the requirement of
In whichIn order to set the eleventh determination threshold value,in order to set the twelfth judgment threshold value,judging that O is a Mars region for a set thirteenth judgment threshold value, and recording the number of the Mars regions in a clustering result;
When coming fromFrame start continuationSum of Mars region number of frameGreater than a fourteenth determination thresholdAnd judging that open fire exists in the suspected open fire area, and sending open fire early warning to a related management department in real time.
In embodiment 1, the vehicle detection model trained in the fourth step is obtained by training the labeled image using a YOLO-based training model.
Example 1, the detailed procedure of step six is as follows: extracting open fire information when open fire is detected in a sceneBefore the open fire appears, the extraction is continuedFrame image, extracting person in imageInformation whereinThe abscissa is fixed for the upper left corner of the human frame,for the top left hand fixed point ordinate of the personnel box,the width of the square frame for the person,the high of the human box.
When the personnel meets the requirements of open fire
In whichJudging whether the person approaches the open fire area or not for a set fifteenth judgment threshold value, and acquiring the elbow coordinates of the personWrist coordinatesKnee coordinatesHip bone coordinatesHead coordinatesCalculating the pilot fire score
Where k is the number of frames
A fourth correction constant trained for historical data,fifth correction constant obtained for historical data training
Calculating the continuity before the occurrence of open fireSum of the person's crazing score for each frame within a frame image
When in useIn whichAnd if the judgment result is the set eighteenth judgment threshold, judging that the personnel are suspected fire-leading personnel, and sending the early warning of the fire-leading personnel to a related management department in real time for processing.
A charging pile area night open fire detection system comprises:
the monitoring module is used for acquiring video information of a target area;
the processing module is used for receiving the information collected by the monitoring module and analyzing and processing the information;
and the communication early warning module is used for receiving the information of the processing module and carrying out communication early warning operation.
The invention has the beneficial effects that: catch the naked light picture through surveillance camera head and image recognition to interference information such as place light, vehicle light shine is discharged in detail, can effectively improve naked light and detect the precision, and the mode of automatic early warning is cooperated simultaneously, can remind the staff to look over the processing to the early warning picture, and the regional influence of vehicle light at night that effectively reduces leads to the erroneous judgement.
Drawings
FIG. 1 is a block diagram of the method of the present invention;
fig. 2 is a system block diagram of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1-2, according to the scheme, an open fire picture is captured through a monitoring camera and image recognition, interference information such as field light and vehicle light irradiation is discharged in detail, open fire detection precision can be effectively improved, meanwhile, a worker can be reminded to check and process an early warning picture in a matched automatic early warning mode, and misjudgment caused by influence of vehicle light in a night area is effectively reduced.
Example one
A method for detecting a nighttime open fire in a charging pile area comprises the following steps:
marking a light emitting area such as an indicator light in a scene, and dividing the scene into a non-light area and a light area;
collecting a night flame image, marking a flame area, and establishing a suspected flame area detection model;
step three, detecting a suspected flame area appearing in the scene by using a night suspected flame area detection model for the no-light area in the scene;
step four, when a continuous flame area is detected in the monitoring video, detecting vehicles appearing in the scene by using a trained vehicle detection model, and judging whether the continuous flame area is an open flame area;
step five, when a suspected open fire area is detected in the monitoring video, further judging whether open fire exists or not, and sending early warning information when open fire exists;
and step six, when open fire is detected in the scene, extracting open fire information and personnel information, comprehensively judging whether the personnel are suspected fire personnel, and sending early warning of the fire personnel to a relevant management department for processing in real time.
And the suspected flame area detection model in the second step is obtained by training the labeled data based on a training model of the YOLO.
Example two
The third step of detecting the suspected flame area appearing in the scene by using a night suspected flame area detection model for the no-light area in the scene comprises the following steps:
detecting and judging whether the flame area is a flame area or a false flame area;
if the flame area is judged whether a continuous flame area exists or not.
EXAMPLE III
The detailed steps of the detection and judgment of whether the flame area is the flame area or the false flame area are as follows:
when monitoring videoFrame detection of a suspected flame regionWhereinThe abscissa is fixed for the top left corner of the suspected flame region detection box,the top left fixed point ordinate of the suspected flame area detection box,the width of the box is detected for the area of suspected flame,calculating a size score for the suspected flame area for detecting a high of the box
Wherein
When the temperature is higher than the set temperatureIn whichAnd if the set fifth judgment threshold value is adopted, the suspected flame area is judged as the flame area, otherwise, the false flame area is judged.
In the fourth embodiment, the detailed step of judging whether the flame area has the continuous flame area is as follows, and the detailed step of judging whether the flame area has the continuous flame area is as follows when the video is monitoredFrame detection of flameRegion for adding mark score to the frame imageThe absence of flame zone is marked with a score of 0, recorded fromFrame start continuationCalculating flame persistence score based on the detected flame region in the frame image
When in useIn whichTo set the sixth judgment threshold, judgeThe continuous flame area exists in the frame, otherwise, the continuous flame area does not exist.
EXAMPLE five
The detailed steps of the step four are as follows:
when a vehicle is detected within a sceneIn whichThe fixed-point abscissa for the upper left corner of the vehicle detection box,a fixed point ordinate of the upper left corner of the vehicle detection box,for the width of the vehicle detection box,calculating a vehicle flame correlation score for a high vehicle detection frame
When in useIn whichFor the set seventh judgment threshold value, judging that the vehicle is associated with the flame existence, otherwise, judging that the vehicle does not exist, marking the vehicle associated with the flame existence, extracting the vehicle characteristics, and acquiring the flame from the flame existenceFrame startDetection frame for marking vehicle in image after frameWhen the vehicle approximates the speed
Is greater than the set eighth judgment threshold valueWhen the vehicle is judged to have displacement, otherwise, the vehicle is judged not to move,
when the displacement of the marked vehicle is detected, the method calculatesFrame continuationCompanion score within post-frame images
When in useGreater than a set ninth judgment thresholdWhen the flame is detected to be a non-open flame region, otherwise, the flame is detected to be a suspected open flame region,
when the marked vehicle is detected to have displacement, the continuous flame area is judged to be a suspected open flame area,
when the vehicle is not associated with flames, determining that the continuous flame area is a suspected open flame area,
and when the vehicle is not detected in the scene, judging the continuous flame area as a suspected open flame area.
EXAMPLE six
The detailed steps of the fifth step are as follows:
when monitoring videoFrame detection of suspected open fire regionsSetting the regionIs an open flame detection area, whereinFor detecting areas of open fireThe fixed-point abscissa of the upper left corner of the square frame is detected,a fixed point vertical coordinate is arranged at the upper left corner of the detection frame of the open fire detection area,the width of the detection box for the open fire detection area,detecting a high of a box for an open flame detection area
A first correction constant obtained by training historical data, W is the width of a monitoring picture,a second correction constant trained for historical data,a third correction constant obtained by historical data training is obtained, and H is the height of the monitoring picture;
extracting non-suspected naked fire in the naked fire detection areaGray value of regional pixel pointWhereinIndicating the coordinates of the pixel point whenGreater than the set tenth judgment thresholdAdding the bright spot mark score to the pixel pointPositive and negative;
Collecting the speckle marker scoreThe pixel points form a bright spot setClustering pixels in the bright spot set according to pixel coordinates by using a K-means-based clustering model, and for any O in a clustering result, when the number of elements of O is equal to that of the elements of OCluster radius with OSatisfy the requirements of
In whichIn order to set the eleventh determination threshold value,in order to set the twelfth judgment threshold value,judging that O is a Mars region for a set thirteenth judgment threshold value, and recording the number of the Mars regions in a clustering result;
When coming fromFrame start continuationSum of Mars region number of frameAt the fourteenth determination threshold valueAnd judging that open fire exists in the suspected open fire area, and sending open fire early warning to a related management department in real time.
And the vehicle detection model trained in the fourth step is obtained by training the labeled image by using a training model based on YOLO.
EXAMPLE seven
The detailed steps of the step six are as follows: when in useExtracting open fire information when open fire is detected in a sceneBefore the open fire appears, the extraction is continuedFrame image, extracting person in imageInformation whereinThe abscissa is fixed for the upper left corner of the human frame,for the top left hand fixed point ordinate of the personnel box,the width of the square frame for the person,the high of the human box.
When the personnel meets the requirements of open fire
In whichJudging whether the person approaches the open fire area or not for a set fifteenth judgment threshold value, and acquiring the elbow coordinates of the personWrist coordinatesKnee coordinatesHip bone coordinatesHead coordinatesCalculating the pilot fire score
Where k is the number of frames
A fourth correction constant trained for historical data,fifth correction constant obtained for historical data training
Calculating the continuity before the occurrence of open fireSum of the person's crazing score for each frame within a frame image
When in useIn whichAnd judging that the personnel is suspected pilot fire personnel for the set eighteenth judgment threshold, and sending the pilot fire personnel early warning to a related management department for processing in real time.
Example eight
A charging pile area night open fire detection system comprises:
the monitoring module is used for acquiring video information of a target area, the monitoring module is a plurality of cameras arranged in a charging pile concentrated area, and dead angles of the monitoring area are reduced through the multi-angle cameras;
the processing module is used for receiving the information collected by the monitoring module and analyzing and processing the information, and a storage module for storing model information is arranged in the processing module;
and the communication early warning module is used for receiving the information of the processing module and carrying out communication early warning operation.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
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 and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (9)
1. A charging pile area night open fire detection method is characterized by comprising the following steps:
marking a light emitting area of an indicator light in a scene, and dividing the scene into a non-light area and a light area;
collecting a night flame image, marking a flame area, and establishing a suspected flame area detection model;
step three, detecting a suspected flame area appearing in the scene by using a night suspected flame area detection model for the no-light area in the scene;
step four, when a continuous flame area is detected in the monitoring video, detecting vehicles appearing in the scene by using a trained vehicle detection model, and judging whether the continuous flame area is an open flame area;
step five, when a suspected open fire area is detected in the monitoring video, further judging whether open fire exists or not, and sending early warning information when open fire exists;
and step six, when open fire is detected in the scene, extracting open fire information and personnel information, comprehensively judging whether the personnel are suspected fire personnel, and sending early warning of the fire personnel to a relevant management department for processing in real time.
2. The method according to claim 1, wherein the suspected flame area detection model in the second step is obtained by training labeled data based on a training model of YOLO.
3. The method for detecting the nighttime open fire in the charging pile area according to claim 1, wherein the step three of detecting the suspected flame area in the scene by using the nighttime suspected flame area detection model for the no-light area in the scene comprises the following steps:
detecting and judging whether the flame area is a flame area or a false flame area;
if the flame area is judged whether a continuous flame area exists or not.
4. The method for detecting the nighttime open fire in the charging pile area according to claim 3, wherein the detailed steps of detecting and judging whether the flame area is the flame area or the false flame area are as follows:
when monitoring videoFrame detection of suspected flame regionsWhereinThe abscissa is fixed for the top left corner of the suspected flame region detection box,the ordinate of the fixed point at the upper left corner of the suspected flame area detection box,the width of the box is detected for the area of suspected flame,calculating a size score for the suspected flame area for detecting a high of the box
Wherein
5. The method for detecting the nighttime open fire in the charging pile area according to claim 4, wherein the detailed step of judging whether the flame area has the continuous flame area is as follows when the step of judging whether the flame area has the continuous flame area is as follows when a monitoring video is usedThe frame detects the flame area, adds the mark score for the frame imageThe absence of flame zone is marked with a score of 0, recorded fromFrame start continuationCalculating flame persistence score based on the detected flame region in the frame image
6. The method for detecting the nighttime open fire in the charging pile area according to claim 1, wherein the detailed steps of the fourth step are as follows:
when a vehicle is detected within a sceneIn whichThe fixed-point abscissa for the upper left corner of the vehicle detection box,a fixed point ordinate of the upper left corner of the vehicle detection box,for the width of the vehicle detection box,calculating a vehicle flame correlation score for a high vehicle detection frame
When in useIn whichDetermining that the vehicle is associated with the presence of flames for a set seventh determination threshold, otherwise determining that the vehicle is not present,
marking vehicles associated with the presence of flames and extracting vehicle features, obtained fromFrame startDetection frame for marking vehicle in image after frameWhen the vehicle approximates the speed
Is greater than the set eighth judgment threshold valueIf so, judging that the marked vehicle has displacement, otherwise, judging that the vehicle does not move;
when the displacement of the marked vehicle is detected, the method calculatesFrame continuationCompanion score within post-frame images
When in useGreater than a set ninth judgment thresholdIf so, judging that the continuous flame area is a non-open flame area, otherwise, judging that the continuous flame area is a suspected open flame area;
when the marked vehicle is detected to have displacement, the continuous flame area is judged to be a suspected open flame area;
when the vehicle is not associated with the flame, determining that the continuous flame area is a suspected open flame area;
and when the vehicle is not detected in the scene, judging the continuous flame area as a suspected open flame area.
7. The method for detecting the night open fire in the charging pile area according to claim 1, characterized in that the detailed steps in the fifth step are as follows:
when monitoring videoFrame detection of suspected open fire regionsSetting the regionIs an open fire detection area, in whichThe fixed-point horizontal coordinate of the upper left corner of the detection frame of the open fire detection area,a fixed point vertical coordinate is arranged at the upper left corner of the detection frame of the open fire detection area,the width of the detection box for the open fire detection area,detecting a high of a box for an open flame detection area
A first correction constant obtained by training historical data, W is the width of a monitoring picture,a second correction constant trained for historical data,a third correction constant obtained for historical data training, H is monitoringThe height of the picture;
extracting gray values of pixels in non-suspected open fire areas in the open fire detection areaWhereinIndicating the coordinates of the pixel point whenGreater than the set tenth judgment thresholdAdding the bright spot mark score to the pixel pointPositive and negative;
Collecting the speckle marker scoreThe pixel points form a bright spot setClustering pixels in the bright spot set according to pixel coordinates by using a K-means-based clustering model, and for any O in a clustering result, when the number of elements of O is equal to that of the elements of OCluster radius with OSatisfy the requirement of
In whichIn order to set the eleventh determination threshold value,in order to set the twelfth judgment threshold value,judging that O is a Mars region for a set thirteenth judgment threshold value, and recording the number of the Mars regions in a clustering result;
8. The method for detecting the nighttime open fire in the charging pile area according to claim 1, wherein the vehicle detection model trained in the fourth step is obtained by training the labeled image by using a training model based on YOLO.
9. The method for detecting the nighttime open fire in the charging pile area according to claim 1, wherein the detailed steps of the sixth step are as follows: extracting open fire information when open fire is detected in a sceneBefore the open fire appears, the extraction is continuedFrame image, extracting person in imageInformation whereinThe abscissa is fixed for the upper left corner of the human frame,for the top left hand fixed point ordinate of the personnel box,the width of the square frame for the person,height of the person box;
when the personnel meets the requirements of open fire
In whichJudging whether the person approaches the open fire area or not for a set fifteenth judgment threshold value, and acquiring the elbow coordinates of the personWrist coordinateKnee coordinatesHip bone coordinatesHead coordinatesCalculating the pilot fire score
Where k is the number of frames
A fourth correction constant trained for historical data,a fifth correction constant obtained by training historical data;
in order to set the sixteenth determination threshold,a seventeenth determination threshold value set;
Calculating the continuity before the occurrence of open fireSum of the person's crazing score for each frame within a frame image;
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210828781.8A CN114913323B (en) | 2022-07-15 | 2022-07-15 | Charging pile area night open fire detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210828781.8A CN114913323B (en) | 2022-07-15 | 2022-07-15 | Charging pile area night open fire detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114913323A true CN114913323A (en) | 2022-08-16 |
CN114913323B CN114913323B (en) | 2022-11-15 |
Family
ID=82772537
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210828781.8A Active CN114913323B (en) | 2022-07-15 | 2022-07-15 | Charging pile area night open fire detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114913323B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116259167A (en) * | 2023-03-14 | 2023-06-13 | 东莞先知大数据有限公司 | Charging pile area high-temperature risk early warning method, device, equipment and medium |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100119210A1 (en) * | 2007-05-21 | 2010-05-13 | Mitsubishi Electric Corporation | Image difference detection method and apparatus, scene change detection method and apparatus, and image difference value detection method and apparatus |
CN101872526A (en) * | 2010-06-01 | 2010-10-27 | 重庆市海普软件产业有限公司 | Smoke and fire intelligent identification method based on programmable photographing technology |
CN103761529A (en) * | 2013-12-31 | 2014-04-30 | 北京大学 | Open fire detection method and system based on multicolor models and rectangular features |
WO2017161747A1 (en) * | 2016-03-25 | 2017-09-28 | 乐视控股(北京)有限公司 | Charging post control system, multifunctional charging post and electric vehicle |
US20170274789A1 (en) * | 2016-03-25 | 2017-09-28 | Le Holdings (Beijing) Co., Ltd. | Charging pile control system, multi-functional charging pile and electric vehicle |
US20180376305A1 (en) * | 2017-06-23 | 2018-12-27 | Veniam, Inc. | Methods and systems for detecting anomalies and forecasting optimizations to improve smart city or region infrastructure management using networks of autonomous vehicles |
CN110667435A (en) * | 2019-09-26 | 2020-01-10 | 武汉客车制造股份有限公司 | Fire monitoring and early warning system and method for new energy automobile power battery |
CN111626188A (en) * | 2020-05-26 | 2020-09-04 | 西南大学 | Indoor uncontrollable open fire monitoring method and system |
CN215537956U (en) * | 2021-03-29 | 2022-01-18 | 国网重庆市电力公司永川供电分公司 | Electric vehicle charging station fire automatic alarm fire extinguishing system |
US20220041076A1 (en) * | 2020-08-05 | 2022-02-10 | BluWave Inc. | Systems and methods for adaptive optimization for electric vehicle fleet charging |
CN114394100A (en) * | 2022-01-12 | 2022-04-26 | 深圳力维智联技术有限公司 | Unmanned prowl car control system and unmanned car |
WO2022098365A1 (en) * | 2020-11-05 | 2022-05-12 | GRID20/20, Inc. | Fire mitigation and downed conductor detection systems and methods |
CN114475305A (en) * | 2021-12-03 | 2022-05-13 | 上海众石信息科技有限公司 | High-safety intelligent charging shed and use method thereof |
-
2022
- 2022-07-15 CN CN202210828781.8A patent/CN114913323B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100119210A1 (en) * | 2007-05-21 | 2010-05-13 | Mitsubishi Electric Corporation | Image difference detection method and apparatus, scene change detection method and apparatus, and image difference value detection method and apparatus |
CN101872526A (en) * | 2010-06-01 | 2010-10-27 | 重庆市海普软件产业有限公司 | Smoke and fire intelligent identification method based on programmable photographing technology |
CN103761529A (en) * | 2013-12-31 | 2014-04-30 | 北京大学 | Open fire detection method and system based on multicolor models and rectangular features |
WO2017161747A1 (en) * | 2016-03-25 | 2017-09-28 | 乐视控股(北京)有限公司 | Charging post control system, multifunctional charging post and electric vehicle |
US20170274789A1 (en) * | 2016-03-25 | 2017-09-28 | Le Holdings (Beijing) Co., Ltd. | Charging pile control system, multi-functional charging pile and electric vehicle |
US20180376305A1 (en) * | 2017-06-23 | 2018-12-27 | Veniam, Inc. | Methods and systems for detecting anomalies and forecasting optimizations to improve smart city or region infrastructure management using networks of autonomous vehicles |
CN110667435A (en) * | 2019-09-26 | 2020-01-10 | 武汉客车制造股份有限公司 | Fire monitoring and early warning system and method for new energy automobile power battery |
CN111626188A (en) * | 2020-05-26 | 2020-09-04 | 西南大学 | Indoor uncontrollable open fire monitoring method and system |
US20220041076A1 (en) * | 2020-08-05 | 2022-02-10 | BluWave Inc. | Systems and methods for adaptive optimization for electric vehicle fleet charging |
WO2022098365A1 (en) * | 2020-11-05 | 2022-05-12 | GRID20/20, Inc. | Fire mitigation and downed conductor detection systems and methods |
CN215537956U (en) * | 2021-03-29 | 2022-01-18 | 国网重庆市电力公司永川供电分公司 | Electric vehicle charging station fire automatic alarm fire extinguishing system |
CN114475305A (en) * | 2021-12-03 | 2022-05-13 | 上海众石信息科技有限公司 | High-safety intelligent charging shed and use method thereof |
CN114394100A (en) * | 2022-01-12 | 2022-04-26 | 深圳力维智联技术有限公司 | Unmanned prowl car control system and unmanned car |
Non-Patent Citations (1)
Title |
---|
王旭: "学校电动车充电桩安全问题排查和研究", 《产业科技创新》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116259167A (en) * | 2023-03-14 | 2023-06-13 | 东莞先知大数据有限公司 | Charging pile area high-temperature risk early warning method, device, equipment and medium |
CN116259167B (en) * | 2023-03-14 | 2023-11-21 | 东莞先知大数据有限公司 | Charging pile area high-temperature risk early warning method, device, equipment and medium |
Also Published As
Publication number | Publication date |
---|---|
CN114913323B (en) | 2022-11-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106650620B (en) | A kind of target person identification method for tracing using unmanned plane monitoring | |
CN111445524B (en) | Scene understanding-based construction site worker unsafe behavior identification method | |
CN113516076B (en) | Attention mechanism improvement-based lightweight YOLO v4 safety protection detection method | |
CN106295551A (en) | A kind of personal security cap wear condition real-time detection method based on video analysis | |
CN106446926A (en) | Transformer station worker helmet wear detection method based on video analysis | |
CN110136172B (en) | Detection method for wearing of underground protective equipment of miners | |
CN108416968A (en) | Fire alarm method and apparatus | |
CN104504369A (en) | Wearing condition detection method for safety helmets | |
CN106128022A (en) | A kind of wisdom gold eyeball identification violent action alarm method and device | |
CN111325048B (en) | Personnel gathering detection method and device | |
CN113743256B (en) | Intelligent early warning method and device for site safety | |
CN111428617A (en) | Video image-based distribution network violation maintenance behavior identification method and system | |
CN112396658A (en) | Indoor personnel positioning method and positioning system based on video | |
CN103996203A (en) | Method and device for detecting whether face in image is sheltered | |
CN112434669B (en) | Human body behavior detection method and system based on multi-information fusion | |
CN114913323B (en) | Charging pile area night open fire detection method | |
CN111062373A (en) | Hoisting process danger identification method and system based on deep learning | |
CN111079722A (en) | Hoisting process personnel safety monitoring method and system | |
CN113506416A (en) | Engineering abnormity early warning method and system based on intelligent visual analysis | |
CN101859376A (en) | Fish-eye camera-based human detection system | |
CN114359712A (en) | Safety violation analysis system based on unmanned aerial vehicle inspection | |
CN113537019A (en) | Detection method for identifying wearing of safety helmet of transformer substation personnel based on key points | |
CN112377265A (en) | Rock burst alarm method based on image recognition acceleration characteristics | |
KR101560810B1 (en) | Space controled method and apparatus for using template image | |
CN113554682B (en) | Target tracking-based safety helmet detection method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP03 | Change of name, title or address | ||
CP03 | Change of name, title or address |
Address after: Building 7, No. 124 Dongbao Road, Dongcheng Street, Dongguan City, Guangdong Province, 523015 Patentee after: Guangdong Prophet Big Data Co.,Ltd. Country or region after: China Address before: Room 102, Building 7, No. 124, Dongbao Road, Dongcheng Street, Dongguan City, Guangdong Province, 523015 Patentee before: Dongguan prophet big data Co.,Ltd. Country or region before: China |