CN110796819A - Detection method and system for platform yellow line invasion border crossing personnel - Google Patents
Detection method and system for platform yellow line invasion border crossing personnel Download PDFInfo
- Publication number
- CN110796819A CN110796819A CN201910994518.4A CN201910994518A CN110796819A CN 110796819 A CN110796819 A CN 110796819A CN 201910994518 A CN201910994518 A CN 201910994518A CN 110796819 A CN110796819 A CN 110796819A
- Authority
- CN
- China
- Prior art keywords
- yellow line
- yellow
- target pedestrian
- platform
- distance
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Abstract
The embodiment of the invention provides a detection method and a system for platform yellow line invasion border crossing personnel, wherein the method comprises the following steps: obtaining a platform detection video picture, and determining a yellow line warning area and a yellow line boundary position in the platform detection video picture; acquiring the position of a target pedestrian in the yellow line warning area, and starting an intrusion border crossing alarm if the distance between the position of the target pedestrian and the boundary position of the yellow line is greater than a first preset distance; and if the distance between the pedestrian position and the yellow line boundary position is between the first preset distance and the second preset distance and the lingering time exceeds a first preset time, starting loitering alarm tracking. The detection method and the system for the border crossing personnel invaded by the platform yellow line provided by the embodiment of the invention ensure the safety of train entering, and can accurately position and track suspicious personnel in a yellow line warning area in real time, thereby improving the automation level of a station and improving the operation efficiency of related working personnel of the station.
Description
Technical Field
The invention relates to the technical field of intelligent detection and identification, in particular to a detection method and a detection system for platform yellow line invasion border-crossing personnel.
Background
The train is used as the most main transportation junction tool at the present stage, and the passenger flow rate of the train station is dense. In order to effectively guarantee the personal and property safety of each passenger, great manpower and material resources are usually required to be paid by station security personnel. The station monitoring video detection technology, especially pedestrian cross-border intrusion detection, is widely applied to station security because the operation efficiency of workers can be greatly improved.
At present, the mode of calling videos or images afterwards to compare frame by frame is commonly adopted in the aspect of pedestrian border crossing intrusion detection in China, the traditional detection mode consumes huge manpower and material resources, the operation efficiency of railway passenger transportation management is greatly reduced, meanwhile, the detection method is often adopted after an accident occurs, the guidance of advanced pretreatment cannot be provided for on-site security personnel, and the real-time performance is poor.
Therefore, the station monitoring video detection technology capable of rapidly, accurately and timely completing the platform yellow line out-of-range intrusion alarm of the railway passenger station is provided, so that the working efficiency is improved, the waste of manpower and material resources is reduced, and the technical problem which needs to be solved urgently is provided.
Disclosure of Invention
The embodiment of the invention provides a detection method and a detection system for platform yellow line invasion border crossing personnel, which are used for solving the defects of poor instantaneity and low efficiency of a station monitoring video detection technology in the prior art.
In a first aspect, an embodiment of the present invention provides a method for detecting border crossing people invading a platform yellow line, including:
acquiring a platform detection video picture, and determining a yellow line warning area and a yellow line boundary position in the platform detection video picture; acquiring the position of a target pedestrian in a yellow line warning area; if the distance between the position of the target pedestrian and the boundary position of the yellow line is greater than a first preset distance, starting an intrusion border crossing alarm; and if the distance between the position of the target pedestrian and the boundary position of the yellow line is between a first preset distance and a second preset distance and the lingering time exceeds a first preset time, starting the loitering alarm tracking.
Further, before the acquiring the position of the target pedestrian in the yellow-line warning area, the method further comprises the following steps: judging whether the detection condition is met, and if the detection condition is met, starting to acquire the position of the target pedestrian in the yellow-line warning area; the detection conditions include: and receiving a train arrival signal and enabling the train to be in a second preset time period before the train is stably stopped.
Further, after acquiring the position of the target pedestrian in the yellow-line warning area, the method further comprises the following steps: carrying out yellow line distance normalization on the position of the target pedestrian, specifically comprising the following steps: and multiplying the distance between the center point of the feet of the target pedestrian and the position of the yellow line boundary by a normalization matrix.
Further, acquiring the position of the target pedestrian in the yellow-line warning area comprises the following steps: inputting the platform detection video picture into a pre-trained detection network model to obtain a pedestrian characteristic map in a yellow line warning area; combining the candidate region to generate a network to obtain the target pedestrian probability of the pedestrian feature map; and if the probability of the target pedestrian is greater than the preset probability value, acquiring the position of the target pedestrian.
Further, after the intrusion-crossing alarm or the loitering alarm tracking is started, the method further comprises the following steps: and comparing the image of the target pedestrian with the image of the key person in the image database.
Further, the first preset distance is 10cm, and the second preset distance is 5 cm; the first preset time is 10 seconds.
Further, the second preset time period is 5 minutes.
In a second aspect, an embodiment of the present invention further provides a system for detecting a platform yellow line intrusion border crossing person, including: the system comprises at least one camera device, an image processing unit and an alarm tracking unit;
the camera device is used for acquiring a platform detection video picture; the image processing unit is used for determining a yellow line warning area and a yellow line boundary position in a platform detection video picture and acquiring a target pedestrian position in the yellow line warning area; if the distance between the position of the target pedestrian and the boundary position of the yellow line is greater than a first preset distance, an alarm tracking unit starts intrusion boundary crossing alarm; and if the distance between the position of the target pedestrian and the position of the yellow line boundary is between a first preset distance and a second preset distance and the lingering time exceeds a first preset time, the alarm tracking unit starts loitering alarm tracking.
In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the program to implement the steps of the method for detecting the platform yellow line intrusion boundary crossing people according to any one of the above first aspects.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for detecting the platform yellow line intrusion border crossing people according to any one of the above first aspects.
According to the detection method and system for the platform yellow line invasion border crossing personnel, provided by the embodiment of the invention, the platform detection video is processed in real time, and corresponding security measures are taken according to different positions of the target pedestrians in the yellow line warning area, so that the train arrival safety is effectively ensured, meanwhile, suspicious personnel in the yellow line warning area can be accurately positioned and tracked in real time, the automation level of a station is improved, and the operation efficiency of relevant working personnel of the station is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for detecting border-crossing personnel of platform yellow line intrusion according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating determination of detection conditions in the method for detecting platform yellow line intrusion boundary-crossing personnel according to the embodiment of the present invention;
fig. 3 is a schematic diagram illustrating loitering alarm tracking of a target pedestrian position in the detection method for platform yellow line intrusion border crossing personnel according to the embodiment of the present invention;
fig. 4 is a schematic diagram of another method for detecting the platform yellow line intrusion border crossing personnel according to the embodiment of the present invention;
fig. 5 is a schematic structural diagram of a detection system for platform yellow line intrusion border crossing personnel according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of another method for detecting platform yellow line intrusion border crossing personnel according to an embodiment of the present invention;
fig. 7 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a detection method for platform yellow line invasion border crossing personnel, which aims at the problem that the overall range of a station is large and the safety of the station is effectively guaranteed, wherein the railway traffic is taken as the largest passenger transport hub system at present, the flow of people is large and the mobility of personnel is complex. As shown in fig. 1, the method includes, but is not limited to, the following steps:
step S1, obtaining a platform detection video picture, and determining a yellow line warning area and a yellow line boundary position in the platform detection video picture;
step S2, acquiring the position of the target pedestrian in the yellow line warning area;
step S31, if the distance between the position of the target pedestrian and the boundary position of the yellow line is larger than a first preset distance, starting an intrusion border crossing alarm;
step S32, if the distance between the position of the target pedestrian and the position of the yellow line boundary is between a first preset distance and a second preset distance, and the lingering time exceeds a first preset time, the loitering alarm tracking is started.
Specifically, in step S1, the platform detection video image may be obtained by setting at least one camera device in a predetermined area of the train platform, and the camera device may be set to obtain real-time video of the platform area all the day; in view of reducing the storage cost and the processing amount of data processing, the real-time video may be captured at a time before and after the arrival of each train, and the embodiment of the present invention is not particularly limited. The camera device transmits the acquired real-time video to a remote video processing center in a wired or wireless mode, and the video processing center is used for extracting the detection video picture of the received real-time video in a centralized mode.
Further, an image processing unit may be further disposed in the video processing center, and configured to extract important information from the extracted detection video picture, where the image processing unit includes: a yellow line warning area and a yellow line boundary position. The image processing unit stores a pre-trained convolutional neural network model, and when a detection video picture to be processed is received, the detection video picture is input into the convolutional neural network model, so that a yellow line warning area and a yellow line boundary position contained in the detection video picture can be obtained.
For example, the convolutional neural network model may be pre-trained by using a yellow line color, a line shape, and other feature labels, and after the yellow line warning region is determined, a peripheral edge line of the yellow line warning region is set as a yellow line boundary position.
In step S2, since the convolutional neural network model has powerful feature extraction and feature expression capability, in the embodiment of the present invention, the same or another convolutional neural network model stored in the above-mentioned image processing unit may also be used to acquire the position of the target pedestrian in the yellow-line alert area determined in step S1.
Further, if there may be a plurality of target pedestrians in the same yellow-line alert area in step S2, it is necessary to determine whether each target pedestrian is a person threatening station safety according to the specific position of the target pedestrian, and the determination may be made according to the position of the target pedestrian obtained in step S2.
Specifically, in step S31, according to an acquired detection video picture, if a distance between a position of a target pedestrian and a position of a yellow line boundary is greater than a first preset distance, an intrusion violation alarm is started. The intrusion crossing alarm can be arranged in a central control system of a station, namely, if a detection video picture shot by a certain camera system exists, the position of a target pedestrian enters a yellow line warning area, but the distance from the position of the boundary of the yellow line is larger than a first preset distance, and the central control system sends the intrusion crossing alarm to remind corresponding workers of paying attention so as to prepare for taking a corresponding preparation scheme.
Further, in step S32, when the position where the target pedestrian is acquired is in the yellow-line caution region but is located only between the first preset distance and the second preset distance, the threat of the target pedestrian to the station safety is lower than the threat of the target pedestrian described in step S31. Meanwhile, if the target pedestrian not only temporarily passes the second preset distance, but also stays for a time longer than the first preset time, the system can calibrate the target pedestrian, namely, initiate loitering alarm tracking. The loitering alarm tracking can be realized by starting all monitoring equipment in a station to master the behavior and action of the target pedestrian in real time, and can further perform data interaction with a security camera of a public security system to track and report the behavior of the target pedestrian after leaving the station.
According to the detection method for the border crossing personnel invaded by the yellow line of the platform, provided by the embodiment of the invention, the platform detection video is processed in real time, and corresponding security measures are taken according to different positions of the target pedestrians in the yellow line warning area, so that the train arrival safety is effectively ensured, meanwhile, suspicious personnel in the yellow line warning area can be accurately positioned and tracked in real time, the automation level of the station is improved, and the operation efficiency of the relevant working personnel of the station is improved.
Based on the content of the foregoing embodiments, as an alternative embodiment, before acquiring the position of the target pedestrian in the yellow-line warning area, the method further includes, but is not limited to: judging whether the detection condition is met, and if the detection condition is met, starting to acquire the position of the target pedestrian in the yellow-line warning area; the detection conditions include: and receiving a train arrival signal and enabling the train to be in a second preset time period before the train is stably stopped.
Specifically, because the number of train platforms and train numbers is large, and it is not necessary to detect the yellow line intrusion border crossing personnel in the platform area before the train enters the station, in order to save the detection cost and improve the detection efficiency, in the embodiment of the present application, after receiving a train arrival signal and within a second preset time period before the train is stationary, the acquired platform detection video picture may be processed to acquire the position of a target pedestrian in the yellow line warning area, and further determine the threat of the target pedestrian to the station safety according to the area where the position of the target pedestrian is located, so that a preparation scheme may be timely adopted before the train opens the door, and the safety of passengers and the train may be ensured.
The detection process may adopt the method shown in fig. 2, and after receiving a signal of arrival of the train, the method starts to detect pedestrians in the designated area of the platform and detects the yellow line of the platform (i.e. obtains the boundary position of the yellow line and the yellow line warning area); and then judging the train stability stopping information in a second preset time period, if the train is determined to be stably stopped, stopping the pedestrians in the detection area, and if not, continuously detecting until the train stability stopping signal position is received. The second preset time can be set according to actual needs, and may be, for example, 1 minute or 30 seconds.
According to the embodiment of the invention, the data processing amount of the detection method for the platform yellow line invasion border crossing personnel is effectively reduced and the detection efficiency is improved by setting the trigger condition for acquiring the position of the target pedestrian in the yellow line warning area.
Based on the content of the foregoing embodiment, as an optional embodiment, after acquiring the position of the target pedestrian in the yellow-line warning area, the method further includes: carrying out yellow line distance normalization on the position of the target pedestrian, specifically comprising the following steps: and multiplying the distance between the center point of the feet of the target pedestrian and the position of the yellow line boundary by a normalization matrix.
Specifically, after the detected video frame is processed to obtain the target pedestrian position, the yellow line alert area and the yellow line boundary position, and due to the difference of the shooting angle, the shooting device, the shooting distance and the like, when the target pedestrian position and the yellow line boundary position are calculated and judged according to the calculation result to determine the measures to be taken next step, in the embodiment of the invention, the distance between the center between two legs of the target pedestrian and the yellow line boundary is converted according to the normalization matrix to normalize the distance, so that the judgment is facilitated, for example, the distance normalization can be performed by adopting a mean square error normalization matrix.
According to the embodiment of the invention, the distance between the target pedestrian and the optical fiber boundary position is processed by utilizing the normalized matrix, so that the detection precision is effectively improved.
Based on the content of the foregoing embodiments, as an alternative embodiment, the position of the target pedestrian in the yellow-line warning area is obtained, which includes but is not limited to: inputting the platform detection video picture into a pre-trained detection network model to obtain a pedestrian characteristic map in a yellow line warning area; combining the candidate region to generate a network to obtain the target pedestrian probability of the pedestrian feature map; and if the probability of the target pedestrian is greater than the preset probability value, acquiring the position of the target pedestrian.
Specifically, the detection network model may be a neural network model established based on a convolutional neural network, and the pedestrian semantic features and the pedestrian position features of the video image to be detected are obtained through convolution, so as to obtain a pedestrian feature map and a plurality of candidate regions, where the pedestrian feature map includes the pedestrian features of the entire video image to be detected. Further, the candidate regions are screened by using a pre-established candidate region generation network (the candidate region generation network may also be established based on a convolutional neural network), so as to further determine a candidate region in which a pedestrian may exist. Then, the candidate regions with the potential pedestrians are combined with the characteristic map to carry out fusion comparison, and the target pedestrian probability of the potential pedestrian in each candidate region is calculated. And finally, judging the probability of the target pedestrian, and judging that the position of the target pedestrian is positioned in the candidate region with the maximum probability value of the target pedestrian when the probability of the target pedestrian is greater than the preset probability value. The preset probability value can be set to be 0.5, and in an allowable range, when the preset probability value is larger, the acquired target position of the pedestrian position is about accurate.
Further, as shown in fig. 3, an embodiment of the present invention further provides a method for tracking a target pedestrian location, including but not limited to: through the detection network model (such as a convolutional neural network model) in the above embodiment, a detection video image (i.e., the next frame original image in the figure) including the candidate region image (i.e., the pedestrian detection result in the figure) where the target pedestrian is located and the adjacent frame is obtained; inputting the image of the candidate area into a convolutional neural network to obtain pedestrian characteristic information of a target pedestrian, and simultaneously inputting the next frame of original image into the convolutional neural network to obtain global pedestrian characteristic information; and finally, comparing to obtain a region containing the pedestrian characteristic information of the target pedestrian in the global pedestrian characteristic information, and taking the region as the position of the target pedestrian in the next frame of image. And sequentially carrying out the processing on each frame of image, so that the motion trail of the target pedestrian can be obtained, and the position tracking of the target pedestrian is completed.
Based on the content of the foregoing embodiments, as an optional embodiment, after initiating an intrusion-crossing alarm or initiating loitering alarm tracking, the method further includes: and comparing the image of the target pedestrian with the image of the key person in the image database.
Specifically, since the target pedestrian has fluidity, after the position of the target pedestrian is determined to be in the yellow-line alert region as described in the above embodiment, the intrusion-crossing alarm is started; or when the target pedestrian further approaches the yellow line and crosses a first preset distance, the loitering alarm tracking is triggered, at the moment, the image of the target pedestrian is obtained through the detection video picture, and the image is compared with the prestored image of the key pedestrian. The image of the key person may be a key person in a public security image library, and the embodiment of the present invention is not particularly limited.
Based on the content of the foregoing embodiment, as an alternative embodiment, the first preset distance is 10cm, and the second preset distance is 5 cm; the first preset time is 10 seconds.
Specifically, the first preset distance and the second preset distance are set to 10cm and 5cm, and may be set to other distances, in consideration of the actual distance of the yellow line boundary position from the train. Wherein the first preset distance is greater than the second preset distance.
Based on the content of the above embodiment, as an alternative embodiment, the second preset time period is 5 minutes. Because the system needs a certain time for processing the acquired platform detection video image, and in addition, if the position of the target pedestrian is judged to be greater than the first preset distance, the field staff is required to immediately take corresponding measures (including preventing the target pedestrian from further approaching the train, and the like) to require a certain processing time, the second preset time is reasonably set to be 5 minutes, and can also be additionally set according to actual conditions.
As shown in fig. 4, the method for detecting the platform yellow line intrusion border crossing people according to the embodiment of the present invention includes, but is not limited to, the following steps:
firstly, a platform detection video picture is obtained and is input into a pre-trained convolutional neural network as an input image, and a feature map and a plurality of candidate areas of a target pedestrian are obtained; and combining the two to calculate the probability value of the target pedestrian in each monkey punch area. When the probability value is greater than a preset probability value (for example, 0.5), the candidate region where the target pedestrian is located can be determined to be the specific position of the target pedestrian.
Comparing the specific position of the target pedestrian with the position of the yellow line boundary, and if the distance between the specific position and the position of the yellow line boundary is greater than a first preset distance (such as 10cm), starting an intrusion border crossing alarm; if the distance between the two is larger than the second preset distance but smaller than the first preset distance, the loitering alarm tracking is started (namely pedestrian tracking monitoring is carried out); and if the distance is less than the second preset distance, judging that the behavior of the target pedestrian is normal, and taking no measures at the moment.
As shown in fig. 5, an embodiment of the present invention provides a system for detecting a platform yellow line intrusion border crossing person, including but not limited to the following structures: at least one camera 501, an image processing unit 502 and an alarm tracking unit 503.
The camera 501 is configured to obtain a platform detection video frame; the image processing unit 502 is configured to determine a yellow-line alert area and a yellow-line boundary position in the platform detection video frame, and acquire a position of a target pedestrian in the yellow-line alert area.
If the distance between the position of the target pedestrian and the position of the yellow line boundary is greater than a first preset distance, an intrusion border crossing alarm is started through an alarm tracking unit 503;
if the distance between the position of the target pedestrian and the position of the yellow line boundary is between a first preset distance and a second preset distance, and the lingering time exceeds a first preset time, the alarm tracking unit 503 starts the loitering alarm tracking.
Specifically, referring to fig. 6, when the detection system for the platform yellow line intrusion border crossing personnel provided by the embodiment of the present invention is in operation, the following steps are mainly performed:
firstly, the system judges whether a detection condition is met or not according to whether a received train arrival signal is received or not and further according to whether the received train arrival signal is received or not and whether the stability stopping information of the train is received or not, and if the detection condition is met, a pedestrian identification program in a yellow line area is started; wherein, the detection condition mainly comprises: and receiving a train arrival signal and enabling the train to be in a second preset time period before the train is stably stopped.
The yellow line area pedestrian identification program mainly comprises: acquiring a platform detection video picture through a camera device 501 arranged at a platform; and determines the yellow-line alert area and the position of the target pedestrian in the yellow-line alert area included in the platform detection video picture through the image processing unit 502, and determines whether the target pedestrian is in the yellow-line alert area.
If the target pedestrian is located in the yellow-line warning area, further performing yellow-line boundary position identification by using the image processing unit 502; and distance normalization is carried out on the distance between the target pedestrian and the yellow line boundary position. Further, the normalized yellow line distance and a set threshold value are subjected to border crossing detection to judge whether the target pedestrian threatens the safety of the train.
Specifically, if the normalized yellow line distance is greater than a first set distance (such as 10cm), a driving signal is sent to the alarm tracking unit, so that the alarm tracking unit starts intrusion border crossing alarm; if the normalized yellow line distance is smaller than the first set distance but larger than a second set distance (such as 5cm), another driving signal is sent to the alarm tracking unit, so that the alarm tracking unit starts loitering alarm tracking. If the distance from the target pedestrian to the yellow line is smaller than the first set distance and larger than the second set distance, the pedestrian tracking is performed first, and at this time, if the staying time of the target pedestrian in the area exceeds a first preset time (such as 10S), the loitering alarm tracking is further started, and whether a corresponding processing scheme is adopted or not is determined according to the next action track of the target pedestrian. If the staying time of the target pedestrian in the area does not reach the first preset time (such as 10S), the target pedestrian can also be judged to be normal.
Furthermore, the detection system for the platform yellow line intrusion border crossing personnel provided by the embodiment of the invention can also be provided with a portrait comparing unit, and the portrait comparing unit stores portrait library data. When the portrait of the target pedestrian with threat (namely the pedestrian triggering the intrusion crossing alarm or the loitering alarm tracking) is acquired, the portrait is compared with the portrait library data. When the matching degree of the portrait of the target pedestrian and any image in the portrait library data exceeds a set threshold value, triggering a linkage alarm device; if the portrait of the target pedestrian is not matched with any image in the portrait base data, the cross-domain tracking device can be triggered and can be in communication connection with the public security system security camera device.
According to the detection system for the platform yellow line invasion border crossing personnel provided by the embodiment of the invention, the platform detection video is processed in real time, and corresponding security measures are taken according to different positions of the target pedestrians in the yellow line warning area, so that the train arrival safety is effectively ensured, meanwhile, suspicious personnel in the yellow line warning area can be accurately positioned and tracked in real time, the automation level of a station is improved, and the operation efficiency of the relevant working personnel of the station is improved.
Fig. 7 illustrates a physical structure diagram of an electronic device, and as shown in fig. 7, the electronic device may include: a processor (processor)710, a communication Interface (Communications Interface)720, a memory (memory)730, and a communication bus 740, wherein the processor 710, the communication Interface 720, and the memory 730 communicate with each other via the communication bus 740. Processor 710 may call logic instructions in memory 730 to perform the following method: acquiring a platform detection video picture, and determining a yellow line warning area and a yellow line boundary position in the platform detection video picture; acquiring the position of a target pedestrian in a yellow line warning area; if the distance between the position of the target pedestrian and the boundary position of the yellow line is greater than a first preset distance, starting an intrusion border crossing alarm; and if the distance between the position of the target pedestrian and the boundary position of the yellow line is between a first preset distance and a second preset distance and the lingering time exceeds a first preset time, starting the loitering alarm tracking.
In addition, the logic instructions in the memory 730 can be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention or a part thereof, which essentially contributes to the prior art, can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, an intelligent storage and analysis unit, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the transmission method provided in the foregoing embodiments when executed by a processor, and for example, the method includes: acquiring a platform detection video picture, and determining a yellow line warning area and a yellow line boundary position in the platform detection video picture; acquiring the position of a target pedestrian in a yellow line warning area; if the distance between the position of the target pedestrian and the boundary position of the yellow line is greater than a first preset distance, starting an intrusion border crossing alarm; and if the distance between the position of the target pedestrian and the boundary position of the yellow line is between a first preset distance and a second preset distance and the lingering time exceeds a first preset time, starting the loitering alarm tracking.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on such understanding, the above technical solutions may be essentially or partially implemented in the form of software products, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and include instructions for causing a computer device (which may be a personal computer, an intelligent storage analysis unit, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A detection method for border crossing personnel of platform yellow line intrusion is characterized by comprising the following steps:
obtaining a platform detection video picture, and determining a yellow line warning area and a yellow line boundary position in the platform detection video picture;
acquiring the position of a target pedestrian in the yellow line warning area;
if the distance between the position of the target pedestrian and the position of the yellow line boundary is greater than a first preset distance, starting an intrusion boundary crossing alarm;
and if the distance between the position of the target pedestrian and the position of the yellow line boundary is between the first preset distance and the second preset distance and the lingering time exceeds a first preset time, starting loitering alarm tracking.
2. The method for detecting the yellow-line intrusion border crossing people on the platform according to claim 1, further comprising, before the obtaining the position of the target pedestrian in the yellow-line surveillance area:
judging whether the detection condition is met, and if the detection condition is met, starting to acquire the position of the target pedestrian in the yellow-line warning area;
the detection conditions include: and receiving a train arrival signal and enabling the train to be in a second preset time period before the train is stably stopped.
3. The method for detecting the yellow-line intrusion border crossing people on the platform according to claim 1, further comprising, after the obtaining the position of the target pedestrian in the yellow-line surveillance area: carrying out yellow line distance normalization on the position of the target pedestrian, specifically comprising the following steps:
and multiplying the distance between the center point of the feet of the target pedestrian and the position of the yellow line boundary by a normalization matrix.
4. The method for detecting the yellow-line intrusion border crossing people at the platform according to claim 1, wherein the obtaining the position of the target pedestrian in the yellow-line surveillance area comprises:
inputting the platform detection video picture into a pre-trained detection network model to obtain a pedestrian feature map and a plurality of candidate areas in the yellow line warning area;
combining the pedestrian feature map with candidate regions to generate a network, and acquiring the target pedestrian probability of each candidate region;
and if the probability of the target pedestrian is greater than the preset probability value, acquiring the position of the target pedestrian.
5. The method for detecting the platform yellow line intrusion transboundary personnel according to claim 1, wherein after the initiating the intrusion-crossing alarm or the initiating the loitering alarm tracking, the method further comprises:
and comparing the image of the target pedestrian with the image of the key person in the image database.
6. The method of claim 1, wherein the method further comprises the step of detecting the platform yellow line invasion border crossing people,
the first preset distance is 10cm, and the second preset distance is 5 cm; the first preset time is 10 seconds.
7. The method as claimed in claim 2, wherein the second predetermined time period is 5 minutes.
8. A detection system for a platform yellow line intrusion border crossing person, comprising:
the system comprises at least one camera device, an image processing unit and an alarm tracking unit;
the camera device is used for acquiring a platform detection video picture;
the image processing unit is used for determining a yellow line warning area and a yellow line boundary position in the platform detection video picture and acquiring a target pedestrian position in the yellow line warning area;
if the distance between the position of the target pedestrian and the position of the yellow line boundary is greater than a first preset distance, the alarm tracking unit starts intrusion boundary crossing alarm;
and if the distance between the position of the target pedestrian and the position of the yellow line boundary is between the first preset distance and the second preset distance and the lingering time exceeds a first preset time, the alarm tracking unit starts the loitering alarm tracking.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for detecting the platform yellow line intrusion boundary crossing personnel according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for detecting a platform yellow line intrusion boundary crossing person according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910994518.4A CN110796819B (en) | 2019-10-18 | 2019-10-18 | Detection method and system for platform yellow line invasion border crossing personnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910994518.4A CN110796819B (en) | 2019-10-18 | 2019-10-18 | Detection method and system for platform yellow line invasion border crossing personnel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110796819A true CN110796819A (en) | 2020-02-14 |
| CN110796819B CN110796819B (en) | 2021-07-13 |
Family
ID=69439395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910994518.4A Active CN110796819B (en) | 2019-10-18 | 2019-10-18 | Detection method and system for platform yellow line invasion border crossing personnel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110796819B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639765A (en) * | 2020-05-15 | 2020-09-08 | 视若飞信息科技(上海)有限公司 | Interaction method for using point track and detection domain |
| CN112183264A (en) * | 2020-09-17 | 2021-01-05 | 国网天津静海供电有限公司 | Method for judging people lingering under crane boom based on spatial relationship learning |
| CN112634623A (en) * | 2020-11-06 | 2021-04-09 | 武汉长江通信智联技术有限公司 | Vehicle epidemic prevention and control method based on inbound turn-back and inbound loitering |
| CN112863121A (en) * | 2021-03-01 | 2021-05-28 | 哈尔滨市科佳通用机电股份有限公司 | Railway platform end line-crossing monitoring method |
| CN113537007A (en) * | 2021-07-02 | 2021-10-22 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Non-worker intrusion detection and alarm method and device applied to railway platform |
| CN114283544A (en) * | 2021-12-10 | 2022-04-05 | 中国电子科技集团公司第三十八研究所 | Railway platform intrusion monitoring system and method based on artificial intelligence |
| CN116012787A (en) * | 2023-01-10 | 2023-04-25 | 山东高速建设管理集团有限公司 | Safety monitoring method and system based on high-altitude balloon and unmanned aerial vehicle bee colony |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000306167A (en) * | 1999-04-16 | 2000-11-02 | Furukawa Electric Co Ltd:The | Detection line |
| KR100618203B1 (en) * | 2006-05-19 | 2006-09-06 | (주) 한백종합기술공사 | Road drive safety device for a way on a foggy zone |
| CN101048806A (en) * | 2004-08-27 | 2007-10-03 | 新加坡科技劲力私人有限公司 | Multi-sensor intrusion detection system |
| CN101577006A (en) * | 2009-06-15 | 2009-11-11 | 北京中星微电子有限公司 | Loitering detecting method and loitering detecting system in video monitoring |
| CN101835035A (en) * | 2010-06-04 | 2010-09-15 | 天津市亚安科技电子有限公司 | Regional invasion real-time detection method |
| CN104809840A (en) * | 2015-04-25 | 2015-07-29 | 无锡智感星际科技有限公司 | Intrusion detection method and system based on multiple sensors |
| CN104992142A (en) * | 2015-06-03 | 2015-10-21 | 江苏大学 | Pedestrian recognition method based on combination of depth learning and property learning |
| CN105260719A (en) * | 2015-10-16 | 2016-01-20 | 南京工程学院 | Railway platform line-crossing detection method |
| CN106128053A (en) * | 2016-07-18 | 2016-11-16 | 四川君逸数码科技股份有限公司 | A kind of wisdom gold eyeball identification personnel stay hover alarm method and device |
| CN107437314A (en) * | 2017-07-19 | 2017-12-05 | 成都华安视讯科技有限公司 | Personnel's intrusion detection detecting system |
| CN107818651A (en) * | 2017-10-27 | 2018-03-20 | 华润电力技术研究院有限公司 | A kind of illegal cross-border warning method and device based on video monitoring |
| CN108596040A (en) * | 2018-03-29 | 2018-09-28 | 中山大学 | A kind of channels in series fusion pedestrian detection method based on binocular vision |
| CN108765817A (en) * | 2018-08-17 | 2018-11-06 | 西南交大(上海)智能系统有限公司 | A kind of railroad platform intrusion alarm system |
| CN109368473A (en) * | 2018-09-19 | 2019-02-22 | 厦门市特种设备检验检测院 | Handrail anti-drag in escalator inlet climbs safety device and its application method |
| CN109920186A (en) * | 2019-04-19 | 2019-06-21 | 沈阳风驰软件股份有限公司 | A kind of detection of platform edge and geofence control system and method |
| CN110009857A (en) * | 2019-05-14 | 2019-07-12 | 沈阳风驰软件股份有限公司 | A kind of detection of platform one-meter line and geofence control system |
| CN110113580A (en) * | 2019-06-06 | 2019-08-09 | 天津艾思科尔科技有限公司 | A kind of platform crosses the border detection system |
-
2019
- 2019-10-18 CN CN201910994518.4A patent/CN110796819B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000306167A (en) * | 1999-04-16 | 2000-11-02 | Furukawa Electric Co Ltd:The | Detection line |
| CN101048806A (en) * | 2004-08-27 | 2007-10-03 | 新加坡科技劲力私人有限公司 | Multi-sensor intrusion detection system |
| KR100618203B1 (en) * | 2006-05-19 | 2006-09-06 | (주) 한백종합기술공사 | Road drive safety device for a way on a foggy zone |
| CN101577006A (en) * | 2009-06-15 | 2009-11-11 | 北京中星微电子有限公司 | Loitering detecting method and loitering detecting system in video monitoring |
| CN101835035A (en) * | 2010-06-04 | 2010-09-15 | 天津市亚安科技电子有限公司 | Regional invasion real-time detection method |
| CN104809840A (en) * | 2015-04-25 | 2015-07-29 | 无锡智感星际科技有限公司 | Intrusion detection method and system based on multiple sensors |
| CN104992142A (en) * | 2015-06-03 | 2015-10-21 | 江苏大学 | Pedestrian recognition method based on combination of depth learning and property learning |
| CN105260719A (en) * | 2015-10-16 | 2016-01-20 | 南京工程学院 | Railway platform line-crossing detection method |
| CN106128053A (en) * | 2016-07-18 | 2016-11-16 | 四川君逸数码科技股份有限公司 | A kind of wisdom gold eyeball identification personnel stay hover alarm method and device |
| CN107437314A (en) * | 2017-07-19 | 2017-12-05 | 成都华安视讯科技有限公司 | Personnel's intrusion detection detecting system |
| CN107818651A (en) * | 2017-10-27 | 2018-03-20 | 华润电力技术研究院有限公司 | A kind of illegal cross-border warning method and device based on video monitoring |
| CN108596040A (en) * | 2018-03-29 | 2018-09-28 | 中山大学 | A kind of channels in series fusion pedestrian detection method based on binocular vision |
| CN108765817A (en) * | 2018-08-17 | 2018-11-06 | 西南交大(上海)智能系统有限公司 | A kind of railroad platform intrusion alarm system |
| CN109368473A (en) * | 2018-09-19 | 2019-02-22 | 厦门市特种设备检验检测院 | Handrail anti-drag in escalator inlet climbs safety device and its application method |
| CN109920186A (en) * | 2019-04-19 | 2019-06-21 | 沈阳风驰软件股份有限公司 | A kind of detection of platform edge and geofence control system and method |
| CN110009857A (en) * | 2019-05-14 | 2019-07-12 | 沈阳风驰软件股份有限公司 | A kind of detection of platform one-meter line and geofence control system |
| CN110113580A (en) * | 2019-06-06 | 2019-08-09 | 天津艾思科尔科技有限公司 | A kind of platform crosses the border detection system |
Non-Patent Citations (1)
| Title |
|---|
| 张秋亮: "基于微波雷达技术的站台两端监测告警系统研究", 《铁路计算机应用》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639765A (en) * | 2020-05-15 | 2020-09-08 | 视若飞信息科技(上海)有限公司 | Interaction method for using point track and detection domain |
| CN112183264A (en) * | 2020-09-17 | 2021-01-05 | 国网天津静海供电有限公司 | Method for judging people lingering under crane boom based on spatial relationship learning |
| CN112183264B (en) * | 2020-09-17 | 2023-04-21 | 国网天津静海供电有限公司 | Method for judging someone remains under crane boom based on spatial relationship learning |
| CN112634623A (en) * | 2020-11-06 | 2021-04-09 | 武汉长江通信智联技术有限公司 | Vehicle epidemic prevention and control method based on inbound turn-back and inbound loitering |
| CN112863121A (en) * | 2021-03-01 | 2021-05-28 | 哈尔滨市科佳通用机电股份有限公司 | Railway platform end line-crossing monitoring method |
| CN113537007A (en) * | 2021-07-02 | 2021-10-22 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Non-worker intrusion detection and alarm method and device applied to railway platform |
| CN114283544A (en) * | 2021-12-10 | 2022-04-05 | 中国电子科技集团公司第三十八研究所 | Railway platform intrusion monitoring system and method based on artificial intelligence |
| CN114283544B (en) * | 2021-12-10 | 2023-08-01 | 中国电子科技集团公司第三十八研究所 | Railway platform intrusion monitoring system and method based on artificial intelligence |
| CN116012787A (en) * | 2023-01-10 | 2023-04-25 | 山东高速建设管理集团有限公司 | Safety monitoring method and system based on high-altitude balloon and unmanned aerial vehicle bee colony |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110796819B (en) | 2021-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110796819B (en) | Detection method and system for platform yellow line invasion border crossing personnel | |
| CN109598885B (en) | Monitoring system and alarm method thereof | |
| KR101748121B1 (en) | System and method for detecting image in real-time based on object recognition | |
| CN109993789A (en) | A kind of the separated of shared bicycle stops determination method, device and camera | |
| CN104318578A (en) | Video image analyzing method and system | |
| CN110674761B (en) | Regional behavior early warning method and system | |
| CN112380892B (en) | Image recognition method, device, equipment and medium | |
| CN110189355A (en) | Safe escape channel occupies detection method, device, electronic equipment and storage medium | |
| CN110675586A (en) | Airport enclosure intrusion monitoring method based on video analysis and deep learning | |
| CN113470374A (en) | Vehicle overspeed monitoring method and device, computer equipment and storage medium | |
| CN113484858A (en) | Intrusion detection method and system | |
| CN112016528A (en) | Behavior recognition method and device, electronic equipment and readable storage medium | |
| CN116311727A (en) | Intrusion response method, device, equipment and readable storage medium | |
| CN105227918B (en) | A kind of intelligent control method | |
| CN113850995B (en) | Event detection method, device and system based on tunnel radar vision data fusion | |
| CN111062238A (en) | Escalator flow monitoring method and system based on human skeleton information and multi-target tracking | |
| CN114170272A (en) | Accident reporting and storing method based on sensing sensor in cloud environment | |
| CN116778673A (en) | Water area safety monitoring method, system, terminal and storage medium | |
| CN111539254A (en) | Target detection method, target detection device, electronic equipment and computer-readable storage medium | |
| KR101407394B1 (en) | System for abandoned and stolen object detection | |
| KR102434154B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| WO2015180252A1 (en) | Method, device and system for detecting multi-object reverse violation | |
| Dalka et al. | Distributed framework for visual event detection in parking lot area | |
| CN115019463B (en) | Water area supervision system based on artificial intelligence technology | |
| Lodha et al. | Covid-19 crowd detection and alert system using image processing |
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 |