CN117690189B - Charging station dangerous behavior identification method and monitoring system based on artificial intelligence - Google Patents
Charging station dangerous behavior identification method and monitoring system based on artificial intelligence Download PDFInfo
- Publication number
- CN117690189B CN117690189B CN202410113087.7A CN202410113087A CN117690189B CN 117690189 B CN117690189 B CN 117690189B CN 202410113087 A CN202410113087 A CN 202410113087A CN 117690189 B CN117690189 B CN 117690189B
- Authority
- CN
- China
- Prior art keywords
- preset
- charging
- crowd
- charging station
- vehicle
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000012544 monitoring process Methods 0.000 title claims abstract description 40
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 25
- 230000006399 behavior Effects 0.000 claims abstract description 80
- 230000000007 visual effect Effects 0.000 claims abstract description 24
- 238000001514 detection method Methods 0.000 claims description 31
- 238000007689 inspection Methods 0.000 claims description 21
- 238000005516 engineering process Methods 0.000 claims description 8
- 230000033001 locomotion Effects 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 8
- 230000036541 health Effects 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 17
- 230000008569 process Effects 0.000 description 10
- 230000009471 action Effects 0.000 description 9
- 230000001960 triggered effect Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 230000006378 damage Effects 0.000 description 7
- 238000013135 deep learning Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000000779 smoke Substances 0.000 description 4
- 208000027418 Wounds and injury Diseases 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 208000014674 injury Diseases 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000001303 quality assessment method Methods 0.000 description 2
- 230000000391 smoking effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000010561 standard procedure Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Landscapes
- Alarm Systems (AREA)
Abstract
A charging station dangerous behavior identification method and a monitoring system based on artificial intelligence are applied to the field of artificial intelligence, and the method comprises the following steps: acquiring a video image of a charging station; determining preset crowds in the video image, wherein the preset crowds comprise old people, pregnant women, disabled people and children; detecting whether preset dangerous behaviors exist in preset crowds or not through video images; under the condition that preset dangerous behaviors exist in preset crowds, determining whether running vehicles exist in a preset range of the preset crowds or not; when the preset range of the preset crowd is stored in the running vehicles, determining whether the preset crowd is in the visual line of sight of the running vehicles; triggering an alarm device when the preset crowd is determined to be outside the visible sight line of the running vehicle; judging whether the running vehicle decelerates or not when the preset crowd is determined to be in the visual line of sight of the running vehicle; and if the running vehicle is not decelerated, triggering an alarm device. The method and the device have the effect of improving the accuracy of identifying the abnormal condition of the charging station.
Description
Technical Field
The application relates to the field of artificial intelligence, in particular to a charging station dangerous behavior identification method and a monitoring system based on artificial intelligence.
Background
With the popularization of new energy automobiles, charging stations have also been rapidly developed as important supporting facilities. However, due to the specificity of the charging station, such as complex charging equipment, uneven user quality, and the like, the charging station has certain potential safety hazards. Therefore, how to effectively identify and monitor dangerous behaviors of a charging station becomes a current urgent problem to be solved.
In the related art, the charging station monitoring system monitors various data in the charging station in real time, such as temperature, humidity, smoke concentration and the like, and the use condition of a vehicle is used for identifying dangerous behaviors of the charging station, wherein excessive temperature means that the charging station equipment is overheated or has fire hazards, the excessive humidity can cause short circuit of electrical equipment or leakage of a battery, and the excessive smoke concentration indicates that dangerous behaviors such as smoking of personnel exist. Although some achievements have been achieved, due to the complex and changeable environment of the charging station, it is difficult for the related art to accurately capture many other abnormal situations, so as to alert dangerous behaviors in the charging station.
Disclosure of Invention
The application provides a charging station dangerous behavior identification method and a monitoring system based on artificial intelligence, which are used for accurately identifying abnormal conditions of a charging station.
In a first aspect, the present application provides an artificial intelligence based charging station dangerous behavior identification method, including:
acquiring a video image of a charging station;
Determining preset crowds in the video image, wherein the preset crowds comprise old people, pregnant women, disabled people and children;
Detecting whether preset dangerous behaviors exist in preset crowds or not through video images, wherein the preset dangerous behaviors comprise falling, gathering and playing of the people;
under the condition that preset dangerous behaviors exist in preset crowds, determining whether running vehicles exist in a preset range of the preset crowds or not;
when the preset range of the preset crowd is stored in the running vehicles, determining whether the preset crowd is in the visual line of sight of the running vehicles;
triggering an alarm device when the preset crowd is determined to be outside the visible sight line of the running vehicle;
Judging whether the running vehicle decelerates or not when the preset crowd is determined to be in the visual line of sight of the running vehicle;
And if the running vehicle is not decelerated, triggering an alarm device.
Through adopting above-mentioned technical scheme, through image recognition technology real-time supervision preset crowd, can effectively protect preset crowd's safety fast when detecting that there is dangerous action. On the basis of monitoring the preset crowd, the method further combines detection and analysis of the running vehicles in the preset range of the preset crowd, judges the relative position relationship between the running vehicles and the preset crowd, and distinguishes different situations to perform accurate early warning. The early warning is directly triggered under the condition that the visual line of sight of the running vehicle is out, and whether the early warning is performed is judged according to whether the running vehicle is decelerated or not when the visual line of sight of the running vehicle is in. The intelligent collaborative early warning is realized by the method, and the accuracy of the dangerous behavior identification of the charging station is improved.
Optionally, detecting whether a person falls in the target image based on pedestrian detection and pose estimation; detecting whether people gather in the target image based on a target detection and tracking technology; based on object detection and motion recognition, it is detected whether or not there is person playing in the target image.
By adopting the technical scheme, the intelligent monitoring of the preset dangerous behavior is realized, and the preset dangerous behavior is comprehensively and accurately detected and identified by pertinently applying various computer vision technical means.
Optionally, obtaining an image sequence from the video image; carrying out noise reduction treatment and enhancement treatment on the image sequence to obtain a target image; and classifying the crowd in the target image to obtain a preset crowd.
By adopting the technical scheme, the image sequence is acquired, noise reduction and enhancement are carried out, the image quality can be effectively improved, and the subsequent processing and analysis are more reliable. The crowd in the target image can be classified to locate the preset crowd in advance, so that the monitoring range is more clear, and the monitoring efficiency is improved. Compared with the method for directly using the original image, the method optimizes the steps of targeted image enhancement, crowd classification and the like, so that the whole monitoring system can run more stably and reliably.
Optionally, acquiring a charging state of the new energy vehicle, wherein the charging state comprises a real-time electric quantity, a current charging power, a charging time and an expected ending time; and when the real-time electric quantity exceeds the preset electric quantity threshold value, sending a notification to the new energy vehicle user to inform the new energy vehicle user of moving the vehicle.
By adopting the technical scheme, the charging state of the new energy vehicle is obtained, and whether the new energy vehicle user needs to be prompted to move is determined by judging whether the real-time electric quantity reaches the preset electric quantity threshold value. This approach may avoid unnecessary alerting that is too frequent compared to simple charging time alerting. Compared with a single electric quantity parameter, the method also considers information such as charging time, current charging power and the like, and is beneficial to realizing more intelligent prompt decision.
Optionally, extracting a video picture of the charging gun when the new energy vehicle user finishes charging from the video image; and triggering a preset alarm device when the amplitude of the pulled-out charging gun is larger than a preset amplitude threshold value.
By adopting the technical scheme, the technical means of forcibly pulling out the charging gun is judged, so that improper operation which can damage equipment can be effectively identified. When the fact that the charging gun is pulled out forcibly is judged, the preset alarm device is triggered, equipment damage is avoided, and meanwhile safety operation consciousness of a user can be enhanced. According to the scheme, the use safety of the equipment is improved through monitoring of the charging ending process.
Optionally, carrying out face recognition on the patrol personnel to obtain patrol personnel information; comparing the patrol personnel information with a preset face database to determine whether the patrol personnel are on duty for patrol; recording the time to post and the inspection state of the inspector; and evaluating the inspection quality of the charging station according to the on-duty time and the inspection state.
Through adopting above-mentioned technical scheme, realized the automatic attendance management to the inspection personnel, compare artifical record attendance more accurate and intelligent. Further, the inspection work quality is quantitatively evaluated by recording the post time and the inspection state, so that the operation service level of the charging station is continuously improved. Unlike simple monitoring, the attendance scheme integrated with artificial intelligence can actively analyze and judge various conditions, and greatly reduces labor cost. The intelligent attendance checking and quality assessment are realized by combining face recognition and database comparison peer-to-peer algorithms, so that the automation degree of the whole flow is high.
Optionally, acquiring and monitoring a charging state of the charging pile, wherein the charging state comprises charging power, charging current and charging voltage of the charging pile; and determining the health state of the charging pile according to the charging state.
By adopting the technical scheme, the charging power, the charging current and the charging voltage of the charging pile are obtained, so that the health state of the charging pile is actively and continuously monitored, and the grasping capability of the health state of the charging pile is greatly improved.
In a second aspect, an embodiment of the present application provides a monitoring system, including:
The image acquisition module is used for acquiring video images of the charging station;
the image recognition module is used for determining preset crowds in the video image, wherein the preset crowds comprise old people, pregnant women, disabled people and children; whether preset dangerous behaviors exist in preset crowds or not is detected through video images, and the preset dangerous behaviors comprise falling, gathering and playing.
The behavior detection module is used for determining whether traveling vehicles exist in a preset range of a preset crowd under the condition that the preset crowd has preset dangerous behaviors; when the preset range of the preset crowd is stored in the running vehicles, determining whether the preset crowd is in the visual line of sight of the running vehicles;
The dangerous alarm module is used for triggering the alarm device when the preset crowd is determined to be out of the visible sight of the running vehicle; judging whether the running vehicle decelerates or not when the preset crowd is determined to be in the visual line of sight of the running vehicle; and if the running vehicle is not decelerated, triggering an alarm device.
In a third aspect, an embodiment of the present application provides a monitoring system, including: one or more processors and memory; the memory is coupled to the one or more processors, the memory for storing computer program code comprising computer instructions that the one or more processors call for causing the monitoring system to perform the method as described in the first aspect and any one of the possible implementations of the first aspect.
In a fourth aspect, an electronic device is provided in a third aspect of the application.
A monitoring system comprises a memory, a processor and a program stored in the memory and capable of running on the processor, wherein the program can be loaded and executed by the processor to realize an artificial intelligence-based charging station dangerous behavior identification method.
In a fifth aspect, embodiments of the present application provide a computer readable storage medium comprising instructions which, when run on a monitoring system, cause the monitoring system to perform a method as described in the first aspect and any possible implementation manner of the first aspect.
It will be appreciated that the monitoring system provided in the second aspect, the third aspect, the computer program product provided in the fourth aspect and the computer storage medium provided in the fifth aspect are each configured to perform the method provided by the embodiment of the present application. Therefore, the advantages achieved by the method can be referred to as the advantages of the corresponding method, and will not be described herein.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
1. The application monitors the preset crowd in real time through the image recognition technology, and can quickly and effectively protect the safety of the preset crowd when dangerous behaviors are detected. On the basis of monitoring the preset crowd, the method further combines detection and analysis of the running vehicles in the preset range of the preset crowd, judges the relative position relationship between the running vehicles and the preset crowd, and distinguishes different situations to perform accurate early warning. The early warning is directly triggered under the condition that the visual line of sight of the running vehicle is out, and whether the early warning is performed is judged according to whether the running vehicle is decelerated or not when the visual line of sight of the running vehicle is in. The intelligent collaborative early warning is realized by the method, and the accuracy of the dangerous behavior identification of the charging station is improved.
2. The application acquires the image sequence and carries out noise reduction and enhancement, thereby effectively improving the image quality and ensuring more reliable subsequent processing and analysis. The crowd in the target image can be classified to locate the preset crowd in advance, so that the monitoring range is more clear, and the monitoring efficiency is improved. Compared with the method for directly using the original image, the method optimizes the steps of targeted image enhancement, crowd classification and the like, so that the whole monitoring system can run more stably and reliably.
3. The application realizes the automatic attendance management of the patrol personnel, and is more accurate and intelligent compared with manual recording attendance. Further, the inspection work quality is quantitatively evaluated by recording the post time and the inspection state, so that the operation service level of the charging station is continuously improved. Unlike simple monitoring, the attendance scheme integrated with artificial intelligence can actively analyze and judge various conditions, and greatly reduces labor cost. The intelligent attendance checking and quality assessment are realized by combining face recognition and database comparison peer-to-peer algorithms, so that the automation degree of the whole flow is high.
Drawings
FIG. 1 is a flow chart of an artificial intelligence based charging station hazard behavior identification method in an embodiment of the application;
FIG. 2 is a schematic diagram of a functional module of a monitoring system according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.
Reference numerals illustrate: 300. an electronic device; 301. a processor; 302. a communication bus; 303. a user interface; 304. a network interface; 305. a memory.
Detailed Description
The terminology used in the following embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates to the contrary. It should also be understood that the term "and/or" as used in this disclosure is intended to encompass any or all possible combinations of one or more of the listed items.
The terms "first," "second," and the like, are used below for descriptive purposes only and are not to be construed as implying or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature, and in the description of embodiments of the application, unless otherwise indicated, the meaning of "a plurality" is two or more.
In order to facilitate understanding of the method and system provided by the embodiments of the present application, a description of the background of the embodiments of the present application is provided before the description of the embodiments of the present application.
At present, the charging station monitoring system monitors various data in the charging station in real time, such as temperature, humidity, smoke concentration and the like, and the service condition of a vehicle to realize the identification of dangerous behaviors of the charging station, wherein the fact that the temperature is too high means that charging station equipment is overheated or fire hazards exist, the fact that the humidity is too high can lead to short circuit of electrical equipment or leakage of a battery, and the fact that the smoke concentration is too high indicates that dangerous behaviors such as smoking of personnel exist. Although some achievements have been achieved, it is difficult for the related art to accurately capture all abnormal conditions due to the complicated and changeable environments of the charging station, so as to alert dangerous behaviors in the charging station.
The embodiment of the application discloses a charging station dangerous behavior identification method based on artificial intelligence, which comprises the steps of acquiring a charging station video image, detecting preset dangerous behaviors of preset dangerous people in the image, detecting and analyzing traveling vehicles in a preset range of the preset people, judging the relative position relationship between the traveling vehicles and the preset people, and distinguishing different situations to perform accurate early warning. The early warning is directly triggered under the condition that the visual line of sight of the running vehicle is out, and whether the early warning is performed is judged according to whether the running vehicle is decelerated or not when the visual line of sight of the running vehicle is in. The charging station dangerous behavior identification method based on the artificial intelligence further comprises the steps of identifying the behavior of forcibly pulling out the charging gun by a charging user, identifying the condition of a patrol person reaching a post, evaluating the patrol quality of the charging station and the like, and finally, the charging station dangerous behavior identification method further comprises the steps of obtaining the working state of the charging pile and judging the health state of the charging pile. The charging station is mainly used for solving the problem that the environment of the charging station is complex and changeable, and all abnormal conditions are difficult to accurately capture.
Those skilled in the art will appreciate that the problems associated with the prior art are solved by the present application, and a detailed description of a technical solution according to an embodiment of the present application is provided below, wherein the detailed description is given with reference to the accompanying drawings.
Referring to fig. 1, an artificial intelligence based charging station dangerous behavior recognition method includes S10 to S40, and specifically includes the steps of:
s10: acquiring a video image of a charging station; and determining preset crowds in the video images, wherein the preset crowds comprise old people, pregnant women, disabled people and children.
Specifically, as camera devices are becoming more popular, cameras provided in charging stations can monitor and record charging station areas in all weather. Acquiring video images of the charging station is the basis for implementing the whole technical scheme. After the video image is obtained, preprocessing is carried out on the video image, including noise reduction, correction and the like, then detection and classification of people in the video image are realized by utilizing a computer vision and deep learning algorithm, and preset people, namely old people, pregnant women, disabled people and children, are identified. These groups are selected as preset groups because they have weaker physical conditions, and have poorer self-protection ability in case of dangerous situations, and need to be protected with priority. The method for identifying the preset crowd comprises the steps of obtaining face images of each person through face detection, inputting the face images into a convolutional neural network trained in advance to obtain feature vectors of each face, and matching the feature vectors with different crowd feature vectors of old people, pregnant women, disabled people and children to judge which crowd the person belongs to, so that the preset crowd is identified. Compared with simple environment monitoring, the computer vision recognition mode can directly judge all crowd types in the video picture, accurately position preset crowd, and lay a foundation for subsequent key monitoring.
On the basis of the above embodiment, there is also a process of detecting that the charging gun is pulled out during charging, specifically including: the vehicle being charged may be continuously detected using an object detection algorithm in a video image of the charging area. When a vehicle drive-off is detected, the end of charging is indicated. At this time, the video image of the period of time when the charging is completed can be extracted individually for analysis processing, and whether the user has a behavior of forcibly pulling out the charging gun is detected. Typical forced extraction of the gun includes a quick pull of the gun, failure to follow standard operating procedures, and the like. And judging whether the behavior of forcedly pulling out the charging gun exists or not by tracking the information such as the hand movement of the user, the movement speed of the charging gun and the like. If it is determined that the user has a forced tendency to pull out the charging gun, indicating that the device may be damaged, an audible and visual alarm may be triggered. In the embodiment of the application, if the amplitude of the pulled-out charging gun is determined to be larger than the preset amplitude threshold value through the image recognition technology, a preset alarm device is triggered. The alarm mode can be a mode that a warning lamp and sound on the charging pile or a station broadcast, so that a user is aware of the error operation of the user and prompts the user to normally pull out the charging gun. The method can effectively identify the improper behavior of the user by analyzing and detecting the picture when the charging is finished, and timely warn the user, thereby avoiding equipment damage and potential safety hazard.
S20: determining preset crowds in the video image, wherein the preset crowds comprise old people, pregnant women, disabled people and children; whether preset dangerous behaviors exist in preset crowds or not is detected through video images, and the preset dangerous behaviors comprise falling, gathering and playing.
Specifically, after the preset crowd in the charging station video image is identified, the preset crowd including old people, pregnant women, disabled people and children need to be continuously monitored through the video image, whether preset dangerous behaviors exist in the preset crowd or not, and the preset dangerous behaviors include three behaviors of falling, gathering and playing. These three behaviors are chosen as preset dangerous behaviors because in a charging station environment, people fall, people gather and people are likely to cause injury to preset people. For example, the old may fall down to cause fracture, people gathering may cause trampling accidents, children playing with each other may cause accidents without watching the car, etc. Monitoring these dangerous behaviors prepares for subsequent steps to deal with or intervenes in advance. In the technical realization, a computer vision and deep learning algorithm can be continuously applied, a corresponding deep neural network model is trained for different behaviors, then video images are processed, key points of a human body are extracted, and the human body posture and movement trend are judged, so that whether the target behaviors exist or not can be judged. For example, when a human body is detected to fall down for a certain period of time, no turn-over is detected as a criterion for judging fall, a plurality of people stand too close for a certain period of time as a criterion for judging aggregation, and severe limb contact is judged as a criterion for judging playfulness. Compared with simple data monitoring, the technical means for directly analyzing and judging the image can judge the dangerous behavior more accurately, distinguish different dangerous behaviors accurately, and provide basis for subsequent processing reaction, so that the risk of injury to personnel of the charging station is effectively reduced.
On the basis of the above embodiment, the specific steps of determining the preset crowd including the elderly, pregnant women, disabled persons, and children further include S21 to S23:
s21: an image sequence is obtained from the video images.
Wherein an image sequence refers to a collection of consecutive image frames arranged in chronological order. In video processing, video segments are parsed into successive still image frames that make up a video, and then rearranged according to a temporal order to make up a sequence of images.
Illustratively, the image sequence is formed by extracting each frame of image in the video and arranging in time order. At the time of extraction, a fixed time interval may be selected, such as extracting one frame every 0.5 seconds, or a fixed frame number interval may be selected, such as extracting one frame every 5 adjacent frames. The appropriate interval can reduce the amount of redundant computation in subsequent processing. After the image sequence is obtained, various subsequent image processing algorithms can be enabled to detect and identify the targets in the video. For example, a motion change in the image sequence may be detected, identifying a moving object; the position change of the target in the continuous frames can be tracked; abnormal conditions and the like can be found by image comparison.
S22: carrying out noise reduction treatment and enhancement treatment on the image sequence to obtain a target image; and classifying the crowd in the target image to obtain a preset crowd.
For example, after obtaining the image sequence of the charging station, the image sequence needs to be preprocessed to improve the effect of subsequent recognition. Firstly, noise reduction processing is required, because noise of a camera and image transmission compression and the like can influence image quality, and conditions such as blurring, distortion and the like can influence the effect of a subsequent recognition algorithm. Common noise reduction methods include median filtering, gaussian smoothing, and the like. Then, the image is required to be enhanced, so that the visual characteristics such as contrast, sharpness and the like of the image are improved, and the recognition is facilitated. Common methods include histogram equalization, boundary sharpening, color enhancement, and the like. The two-step preprocessing can effectively improve the image quality and provide clear and high-quality image input. The preprocessed image is the target image and can be used as the input of crowd classification. The crowd classification utilizes the computer vision technology to extract the characteristics of each detected independent human body target, and then inputs the characteristics into a pre-trained deep neural network to finish the crowd classification, namely, classifying each human body target into different preset crowds such as old people, pregnant women, disabled people and the like. Compared with a video image, the preprocessed target image has higher quality and more obvious characteristics, and the classification accuracy of the neural network model can be improved. Compared with Shan Zhen images, the processing image sequence can integrate a plurality of visual angles, so that classification is more stable, and the influence of occlusion is reduced.
In an optional embodiment of the present application, detecting whether a preset dangerous behavior exists in a preset crowd through a video image, where the specific steps of preset dangerous behavior include falling, gathering, and playing, further include S23 to S25:
s23: based on pedestrian detection and posture estimation, it is detected whether a person falls in the target image.
Illustratively, pedestrian detection is performed on the image, implemented by a pedestrian detection algorithm, or a pedestrian target in the image is located based on a deep-learned pedestrian detection model. Pedestrian detection can quickly locate an area where a pedestrian appears in the image. And extracting key point information of pedestrians in the detected pedestrian area, judging the distance between two feet and the head height information, and estimating the posture of the pedestrians. If the head is detected to be too close to the ground and the distance between the two feet is larger, the person is judged to be abnormal in standing posture, the pedestrian area is further tracked to judge whether the posture continuously exceeds a certain time threshold, and if so, the person is judged to fall down. Compared with the direct analysis of image change, the technical means combining detection and gesture analysis can more accurately judge the falling behavior, avoid confusion with normal sitting and lying gesture and be more reliable.
S24: based on the target detection and tracking technique, it is detected whether there is a person gathering in the target image.
By means of the target detection algorithm, detection of each independent humanoid target area in the image is achieved through the existing deep learning target detection model, positions of all people are located, different human bodies are detected, and coordinate information of the different human bodies in the image is output. After detecting multiple human targets, features of each target region may be extracted and the targets tracked in a continuous sequence of images. The tracking technology can adopt a tracking algorithm based on feature matching or deep learning to judge the position change relation of different human targets among the adjacent frames. If the positions of the plurality of human targets are detected to be continuously close and the distance is kept close beyond the threshold time period, it can be determined that the person gathering behavior occurs. The technical means does not depend on global image change, but realizes accurate tracking judgment by positioning each target, and can reliably detect crowd gathering phenomenon.
S25: based on object detection and motion recognition, it is detected whether or not there is person playing in the target image.
Illustratively, an object detection algorithm is applied to the image to locate the humanoid objects in the image. The common object detection algorithm comprises a fast R-CNN, an SSD and the like, and can efficiently detect different human body examples. After a plurality of human targets are detected, target region characteristics can be extracted, and then the target region characteristics are input into a pre-trained human body action recognition model based on deep learning, so that actions of different human targets are judged. Common models such as LSTM based timing action recognition models, and the like. If severe limb actions such as contact, entanglement, alarm and the like are detected among a plurality of human body targets, and SUCH actions last for more than a threshold time, it can be determined that a playful action exists among people. The technical means combines detection and action recognition, not only can locate people, but also can analyze specific behaviors of the people, avoid confusion with normal exercises and the like, and can accurately distinguish the playful dangerous behaviors. Through detecting whether personnel play the alarm condition exists, the occurrence of collision injury events caused by the collision can be prevented in a targeted manner, and the safety of personnel in the charging station is protected.
S30: under the condition that preset dangerous behaviors exist in preset crowds, determining whether running vehicles exist in a preset range of the preset crowds or not; and when the preset range of the preset crowd is stored in the running vehicles, determining whether the preset crowd is in the visual line of sight of the running vehicles.
Specifically, in the process of recognizing dangerous behaviors of the preset crowd, it is necessary to determine whether or not there are running vehicles around the preset crowd that can cause damage to the preset crowd. Specifically, a preset range may be determined, for example, a 3-meter range in the center of the preset crowd may be determined as the preset range. The technology can continue to apply the target detection algorithm in computer vision to detect whether the vehicle exists in the preset range. Common vehicle detection algorithms include the YOLO series, fast R-CNN, and the like. And if the running vehicle is detected to enter the preset range, judging that the potential threat exists. Then, it is further determined whether the preset crowd is in the visual line of sight of the vehicle. The method is characterized in that the position relation between the vehicle and the crowd target is calculated by combining detected vehicle boundary box information, and whether shielding exists between the vehicle and the crowd target or not is judged, such as a building and other obstacles affecting the sight. If the two are judged to be free from shielding, namely the sight line is communicated, the crowd is judged to be in the visible sight line range of the vehicle. Such further judgment may avoid false alarms when not in line of sight of the vehicle. Only when the dangerous behavior crowd is confirmed to be in the visible range of the vehicle, the next safety early warning is carried out, false warning can be avoided, and the pertinence of early warning is improved.
On the basis of the above embodiment, there is also a process of notifying the user of the movement of the vehicle, and the specific steps include S31 to S32:
s31: acquiring a charging state of the new energy vehicle, wherein the charging state comprises real-time electric quantity, current charging power, charging time and expected ending time;
The real-time electric quantity is the electric quantity of the vehicle at present; current charging power, i.e. how high power the vehicle is charging; charging time, i.e., time when charging has been performed; and the calculated total charging end time can be estimated according to the current electric quantity and the charging power.
For example, after determining that the preset crowd has a dangerous situation, in order to further make a judgment whether the user needs to be prompted to move, charging state information of the new energy vehicle needs to be obtained, and the charging state is a basis for judging whether the user needs to be prompted.
S32: and when the real-time electric quantity exceeds the preset electric quantity threshold value, sending a notification to the new energy vehicle user to inform the new energy vehicle user of moving the vehicle.
For example, after the charging state of the new energy vehicle is obtained, whether the user needs to be prompted to move is determined according to whether the real-time electric quantity exceeds a preset electric quantity threshold value. The preset charge threshold may be set according to the range requirements of the vehicle, for example, to 80% soc. When the real-time electric quantity is detected to be more than 80%, the electric quantity can be judged to be sufficient, and the user can be prompted to consider moving the vehicle to vacate a charging potential for other users needing quick charging. The specific prompting mode can display prompting information through a display screen of the charging pile, or push a mobile App message through the vehicle-mounted system to remind a user. The push message can enable the user who is not beside the charging pile to receive the prompt. Compared with the method for pushing the prompt according to the charging time, the method for judging the threshold according to the real-time electric quantity can more intelligently determine the moment when the user is really required to be prompted to move, avoid too frequent unnecessary prompts, and not interrupt the charging of the user when the electric quantity is low. When the real-time electric quantity is lower than the threshold value, the user is not prompted to move, and whether prompt is needed is judged after the electric quantity is sufficient. The method fully considers the demands of users, is convenient for subsequent vehicle dispatching, and is the best scheme for balancing the demands of all parties under the current condition.
S40: triggering an alarm device when the preset crowd is determined to be outside the visible sight line of the running vehicle; judging whether the running vehicle decelerates or not when the preset crowd is determined to be in the visual line of sight of the running vehicle; and if the running vehicle is not decelerated, triggering an alarm device.
Specifically, after dangerous behaviors of a preset crowd are judged, and vehicles pass around the preset crowd, corresponding alarm measures are required to be triggered according to the sight relation between the crowd and the vehicles. If the preset crowd is judged not to be in the visible sight range of the vehicle, the alarm device can be directly triggered. This is because the vehicle cannot see the crowd at risk, and the warning device is required to draw attention from the vehicle to the crowd, avoiding collision events. The corresponding alarm device can be a warning lamp, an alarm and the like which are arranged around the charging station. The display screen and the sound system of the charging pile can be used for realizing the alarm. The prominent audible and visual signal can alert surrounding vehicles and pedestrians to notice. If the preset crowd is judged to be in the visual line of sight of the vehicle, whether the vehicle takes the deceleration avoidance action or not needs to be continuously judged. This can be determined by calculating whether a significant drop in the speed of the vehicle occurs in the image sequence. If the vehicle is not decelerated, the collision with the crowd cannot be avoided, and an alarm device needs to be triggered to warn the driver of the vehicle. And the vehicle can be decelerated to avoid accidents. The alarming mode judged according to the sight line factors can avoid false alarming when the vehicle takes avoidance measures in the sight line range. Meanwhile, the dangerous condition outside the line of sight can be covered. And more intelligent and accurate danger early warning is realized.
On the basis of the above embodiment, the method further includes a process of inspection quality evaluation, and the specific steps include S41 to S43:
S41: carrying out face recognition on the patrol personnel to obtain patrol personnel information; and comparing the patrol personnel information with a preset face database to determine whether the patrol personnel are on duty for patrol.
Illustratively, face detection is performed using faces in the video image, and a face image of the patrol personnel is extracted. And then inputting the detected face images into a pre-trained face recognition model to acquire the identity information corresponding to each face, namely finishing the face recognition of the patrol personnel. The face recognition can be accomplished by adopting an algorithm based on deep learning, such as FaceNet, deepFace and the like, and the characteristic extraction and comparison of the face Embedding can avoid the situations that different individuals cannot be distinguished by simple monitoring, the identification information of the identified patrol personnel is compared with a patrol personnel information database preset by the charging station, whether the employee should be patrolled in the time period, whether the employee arrives at the post, whether the employee asks for the false, and the like. If the identified staff is not in the planned duty time period or the staff information is not in the database, the staff can be judged to be not normally planned to the post or enter by someone else, and the staff belongs to an abnormal situation.
S42: recording the time to post and the inspection state of the inspector; and evaluating the inspection quality of the charging station according to the on-duty time and the inspection state.
For example, after identifying the patrolling personnel of the charging station, further relevant information needs to be recorded in addition to the attendance check to evaluate the quality of the patrolling work. Specifically, the time to post of each patrol person, i.e., the point in time when the charging station starts to patrol, may be recorded to determine whether to time to post. Meanwhile, the patrol state, such as patrol path, residence time point and other information, needs to be recorded. This may be obtained by monitoring a monitoring system or by monitoring a positioning device worn by the patrolling personnel themselves. After the on-duty time and complete inspection state information of the inspection personnel are obtained, the working quality can be evaluated according to the preset inspection standard. For example, the method can evaluate whether the actual time reaches the standard or not by comprehensively inspecting for 20 minutes according to the specification; it can be checked whether there are missing non-passing areas etc. throughout the process. If the inspection time is too long or the passing area is incomplete, the inspection quality can be judged to need improvement. Conversely, if the time control is reasonable and the path is complete, then a positive evaluation can be made.
In another optional embodiment of the present application, the method further includes a process for detecting the health status of the charging pile, specifically including: acquiring a charging state of a charging pile, wherein the charging state comprises charging power, namely the instantaneous power output by the charging pile to a vehicle end; the state of charge includes the charging current, i.e. the real-time value of the output current; the charging state includes a charging voltage, i.e., a voltage value at the output of the charging post. These parameters may be obtained by a monitoring module on the charging stake or from a vehicle charging management system. After the real-time charging state data are obtained, whether each parameter is in a specified range can be judged according to the set normal working range. If all the charging parameters are changed in the normal range, the health state of the charging pile can be judged to be good, and the equipment operates normally. If the state exceeding the normal working range exists, such as overlarge fluctuation of charging voltage, unsmooth charging current and the like, the charging pile can be judged to have faults or abnormality, and the health state is poor, so that a basis is provided for the subsequent processing.
Referring to fig. 2, an artificial intelligence based charging station dangerous behavior identification system according to an embodiment of the present application includes: the system comprises an image acquisition module, an image identification module, a behavior detection module and a danger alarm module, wherein:
The image acquisition module is used for acquiring video images of the charging station;
The image recognition module is used for determining preset crowds in the video image, wherein the preset crowds comprise old people, pregnant women, disabled people and children; detecting whether preset dangerous behaviors exist in preset crowds or not through video images, wherein the preset dangerous behaviors comprise falling, gathering and playing of the people;
The behavior detection module is used for determining whether traveling vehicles exist in a preset range of a preset crowd under the condition that the preset crowd has preset dangerous behaviors; when the preset range of the preset crowd is stored in the running vehicles, determining whether the preset crowd is in the visual line of sight of the running vehicles;
The dangerous alarm module is used for triggering the alarm device when the preset crowd is determined to be out of the visible sight of the running vehicle; judging whether the running vehicle decelerates or not when the preset crowd is determined to be in the visual line of sight of the running vehicle; and if the running vehicle is not decelerated, triggering an alarm device.
It should be noted that: in the device provided in the above embodiment, when implementing the functions thereof, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be implemented by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the embodiments of the apparatus and the method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the embodiments of the method are detailed in the method embodiments, which are not repeated herein.
The application also discloses electronic equipment. Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, at least one communication bus 302.
Wherein the communication bus 302 is used to enable connected communication between these components.
The user interface 303 may include a Display screen (Display) interface and a Camera (Camera) interface, and the optional user interface 303 may further include a standard wired interface and a standard wireless interface.
The network interface 304 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.
Wherein the processor 301 may include one or more processing cores. The processor 301 utilizes various interfaces and lines to connect various portions of the overall server, perform various functions of the server and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and invoking data stored in the memory 305. Alternatively, the processor 301 may be implemented in at least one hardware form of digital signal Processing (DIGITAL SIGNAL Processing, DSP), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 301 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface diagram, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 301 and may be implemented by a single chip.
The Memory 305 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). Memory 305 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 305 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described respective method embodiments, etc.; the storage data area may store data or the like involved in the above respective method embodiments. Memory 305 may also optionally be at least one storage device located remotely from the aforementioned processor 301. Referring to fig. 3, an operating system, a network communication module, a user interface module, and an application program of an artificial intelligence-based charging station dangerous behavior recognition method may be included in the memory 305 as a computer storage medium.
In the electronic device 300 shown in fig. 3, the user interface 303 is mainly used for providing an input interface for a user, and acquiring data input by the user; and processor 301 may be configured to invoke an application program in memory 305 that stores an artificial intelligence based charging station hazard behavior recognition method that, when executed by one or more processors 301, causes electronic device 300 to perform the method as in one or more of the embodiments described above. It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all of the preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as a division of units, merely a division of logic functions, and there may be additional divisions in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in whole or in part in the form of a software product stored in a memory, comprising several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method of the various embodiments of the present application. And the aforementioned memory includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a magnetic disk or an optical disk.
The above are merely exemplary embodiments of the present disclosure and are not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure.
This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.
Claims (7)
1. An artificial intelligence-based charging station dangerous behavior identification method, which is characterized by comprising the following steps:
acquiring a video image of a charging station;
Determining a preset crowd in the video image, wherein the preset crowd comprises old people, pregnant women, disabled people and children;
detecting whether preset dangerous behaviors exist in the preset crowd through the video image, wherein the preset dangerous behaviors comprise falling, gathering and playing of people;
Under the condition that the preset crowd has preset dangerous behaviors, determining whether traveling vehicles exist in a preset range of the preset crowd;
When the preset range of the preset crowd is stored in the running vehicles, determining whether the preset crowd is in the visual line of sight of the running vehicles;
Triggering an alarm device when the preset crowd is determined to be outside the visible sight line of the running vehicle;
judging whether the running vehicle decelerates or not when the preset crowd is determined to be in the visual line of sight of the running vehicle;
triggering an alarm device if the running vehicle is not decelerated;
After the step of acquiring the video image of the charging station, the method further comprises: extracting a video picture of a charging gun when a new energy vehicle user finishes charging from the video image; triggering a preset alarm device when the amplitude of the pulled-out charging gun is larger than a preset amplitude threshold value;
After the step of triggering an alarm device, which determines that the preset crowd is outside the visible line of sight of the driving vehicle, the method further comprises: carrying out face recognition on the patrol personnel to obtain patrol personnel information; comparing the patrol personnel information with a preset face database to determine whether the patrol personnel arrives at a post for patrol; recording the on-duty time and the inspection state of the inspection personnel; and evaluating the inspection quality of the charging station according to the on-duty time and the inspection state.
2. The charging station dangerous behavior identification method based on artificial intelligence according to claim 1, wherein the detecting whether the preset crowd has preset dangerous behaviors through the video image, wherein the preset dangerous behaviors include people falling, people gathering and people playing, specifically comprises:
Detecting whether a person falls down in the target image based on pedestrian detection and gesture estimation;
Detecting whether people gather in the target image based on a target detection and tracking technology;
Based on object detection and motion recognition, it is detected whether there is person playing in the target image.
3. The charging station dangerous behavior identification method based on artificial intelligence according to claim 1, wherein the determining of the preset crowd in the video image includes old people, pregnant women, disabled people and children, and the method specifically includes:
obtaining an image sequence according to the video image;
carrying out noise reduction treatment and enhancement treatment on the image sequence to obtain a target image;
And classifying the crowd in the target image to obtain a preset crowd.
4. The method for identifying dangerous behavior of a charging station based on artificial intelligence according to claim 1, wherein after the step of determining whether there is a traveling vehicle within a preset range of the preset crowd in the case that the preset crowd has preset dangerous behavior, the method further comprises:
acquiring a charging state of a new energy vehicle, wherein the charging state comprises real-time electric quantity, current charging power, charging time and expected ending time;
and when the real-time electric quantity exceeds the preset electric quantity threshold value, sending a notification to a new energy vehicle user to inform the new energy vehicle user of moving the vehicle.
5. The artificial intelligence based charging station hazard behavior recognition method of claim 1, wherein after the step of evaluating the patrol quality of the charging station according to the on-duty time and the patrol status, the method further comprises:
Acquiring and monitoring the charging state of a charging pile, wherein the charging state comprises charging power, charging current and charging voltage of the charging pile;
And determining the health state of the charging pile according to the charging state.
6. An electronic device comprising a processor, a memory, a user interface, and a network interface, the memory for storing instructions, the user interface and the network interface for communicating to other devices, the processor for executing the instructions stored in the memory to cause the electronic device to perform the artificial intelligence based charging station hazard behavior recognition method of any one of claims 1-5.
7. A computer readable storage medium comprising instructions that when run on a monitoring system cause the monitoring system to perform the artificial intelligence based charging station hazard behavior identification method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410113087.7A CN117690189B (en) | 2024-01-26 | 2024-01-26 | Charging station dangerous behavior identification method and monitoring system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410113087.7A CN117690189B (en) | 2024-01-26 | 2024-01-26 | Charging station dangerous behavior identification method and monitoring system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117690189A CN117690189A (en) | 2024-03-12 |
| CN117690189B true CN117690189B (en) | 2024-05-17 |
Family
ID=90126766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410113087.7A Active CN117690189B (en) | 2024-01-26 | 2024-01-26 | Charging station dangerous behavior identification method and monitoring system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117690189B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103797677A (en) * | 2011-08-10 | 2014-05-14 | 北京Abb低压电器有限公司 | A charging pole for EV and a detecting method thereof |
| CN109085833A (en) * | 2018-08-15 | 2018-12-25 | 深圳市烽焌信息科技有限公司 | A kind of patrol robot and storage medium |
| CN109733391A (en) * | 2018-12-10 | 2019-05-10 | 北京百度网讯科技有限公司 | Control method, device, equipment, vehicle and the storage medium of vehicle |
| CN110682825A (en) * | 2019-10-14 | 2020-01-14 | 北京嘀嘀无限科技发展有限公司 | Safe charging method, storage medium, electronic device and system |
| CN110956714A (en) * | 2019-11-26 | 2020-04-03 | 湖北佳狮盾智能技术有限公司 | Inspection system based on face recognition |
| CN111175752A (en) * | 2020-02-05 | 2020-05-19 | 成都多普勒科技有限公司 | Multi-purpose vehicle (MPV) millimeter wave radar early warning system |
| CN112489241A (en) * | 2020-11-16 | 2021-03-12 | 江苏联峰金盾智能科技有限公司 | Electronic patrol system capable of supervising patrol personnel |
| CN113869126A (en) * | 2021-08-30 | 2021-12-31 | 浙江大华技术股份有限公司 | Evaluation method, early warning device, electronic device, and readable storage medium |
| CN114943948A (en) * | 2022-05-06 | 2022-08-26 | 杭州鸿泉物联网技术股份有限公司 | Blind zone pedestrian detection method, system, vehicle and storage medium |
| CN115482684A (en) * | 2022-07-20 | 2022-12-16 | 慧之安信息技术股份有限公司 | Safe driving control method and system |
| CN115601922A (en) * | 2022-09-22 | 2023-01-13 | 上海应用技术大学（Cn） | Warning device based on endowment personnel |
| CN115817241A (en) * | 2022-12-13 | 2023-03-21 | 深圳市瑞晶实业有限公司 | Community electric vehicle charging pile and charging method |
| CN116552305A (en) * | 2023-05-30 | 2023-08-08 | 广东电网有限责任公司 | Electric vehicle charging station safety monitoring system and method |
| CN117372954A (en) * | 2023-10-13 | 2024-01-09 | 中国南方电网有限责任公司 | Charging station safety monitoring method, device, system and computer equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109693740B (en) * | 2019-01-02 | 2021-05-18 | 京东方科技集团股份有限公司 | Vehicle danger avoiding apparatus, method, and storage medium |
-
2024
- 2024-01-26 CN CN202410113087.7A patent/CN117690189B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103797677A (en) * | 2011-08-10 | 2014-05-14 | 北京Abb低压电器有限公司 | A charging pole for EV and a detecting method thereof |
| CN109085833A (en) * | 2018-08-15 | 2018-12-25 | 深圳市烽焌信息科技有限公司 | A kind of patrol robot and storage medium |
| CN109733391A (en) * | 2018-12-10 | 2019-05-10 | 北京百度网讯科技有限公司 | Control method, device, equipment, vehicle and the storage medium of vehicle |
| CN110682825A (en) * | 2019-10-14 | 2020-01-14 | 北京嘀嘀无限科技发展有限公司 | Safe charging method, storage medium, electronic device and system |
| CN110956714A (en) * | 2019-11-26 | 2020-04-03 | 湖北佳狮盾智能技术有限公司 | Inspection system based on face recognition |
| CN111175752A (en) * | 2020-02-05 | 2020-05-19 | 成都多普勒科技有限公司 | Multi-purpose vehicle (MPV) millimeter wave radar early warning system |
| CN112489241A (en) * | 2020-11-16 | 2021-03-12 | 江苏联峰金盾智能科技有限公司 | Electronic patrol system capable of supervising patrol personnel |
| CN113869126A (en) * | 2021-08-30 | 2021-12-31 | 浙江大华技术股份有限公司 | Evaluation method, early warning device, electronic device, and readable storage medium |
| CN114943948A (en) * | 2022-05-06 | 2022-08-26 | 杭州鸿泉物联网技术股份有限公司 | Blind zone pedestrian detection method, system, vehicle and storage medium |
| CN115482684A (en) * | 2022-07-20 | 2022-12-16 | 慧之安信息技术股份有限公司 | Safe driving control method and system |
| CN115601922A (en) * | 2022-09-22 | 2023-01-13 | 上海应用技术大学（Cn） | Warning device based on endowment personnel |
| CN115817241A (en) * | 2022-12-13 | 2023-03-21 | 深圳市瑞晶实业有限公司 | Community electric vehicle charging pile and charging method |
| CN116552305A (en) * | 2023-05-30 | 2023-08-08 | 广东电网有限责任公司 | Electric vehicle charging station safety monitoring system and method |
| CN117372954A (en) * | 2023-10-13 | 2024-01-09 | 中国南方电网有限责任公司 | Charging station safety monitoring method, device, system and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 基于OpenPose人体姿态识别的变电站危险行为检测;朱建宝 等;自动化与仪表;20200224(第02期);53-57 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117690189A (en) | 2024-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111507308B (en) | Transformer substation safety monitoring system and method based on video identification technology | |
| CN107911653B (en) | Intelligent video monitoring module, system, method and storage medium for residence | |
| WO2019153193A1 (en) | Taxi operation monitoring method, device, storage medium, and system | |
| CN110544360B (en) | Train safe driving monitoring system and method | |
| CN107818312A (en) | A kind of embedded system based on abnormal behaviour identification | |
| CN111783744A (en) | Operation site safety protection detection method and device | |
| CN102164270A (en) | Intelligent video monitoring method and system capable of exploring abnormal events | |
| CN106056079A (en) | Image acquisition device and facial feature occlusion detection method | |
| CN111126153B (en) | Safety monitoring method, system, server and storage medium based on deep learning | |
| CN104068868A (en) | Method and device for monitoring driver fatigue on basis of machine vision | |
| CN111127943A (en) | Electric vehicle illegal parking prohibition management system | |
| CN113484858A (en) | Intrusion detection method and system | |
| CN103700220A (en) | Fatigue driving monitoring device | |
| CN114202711A (en) | Intelligent monitoring method, device and system for abnormal behaviors in train compartment | |
| CN210110004U (en) | Oil field behavior monitoring system based on artificial intelligence | |
| CN112289031A (en) | Method and device for detecting and alarming abnormal conditions in bus driving process | |
| CN111179551A (en) | Real-time monitoring method for dangerous chemical transport driver | |
| CN113990101B (en) | Method, system and processing device for detecting vehicles in no-parking area | |
| CN116403377A (en) | Abnormal behavior and hidden danger detection device in public place | |
| CN111383248B (en) | Pedestrian red light running judging method and device and electronic equipment | |
| CN110809137A (en) | Campus safety trampling prevention monitoring system and method | |
| CN117690189B (en) | Charging station dangerous behavior identification method and monitoring system based on artificial intelligence | |
| CN111241918B (en) | Vehicle tracking prevention method and system based on face recognition | |
| CN112349058A (en) | Regional security alarm system based on Internet of things | |
| CN116778657A (en) | Method and system for intelligently identifying intrusion behavior |
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 |