CN110969793B - Method, system and storage medium for preventing ship intrusion at periphery of roundabout electronic purse net - Google Patents
Method, system and storage medium for preventing ship intrusion at periphery of roundabout electronic purse net Download PDFInfo
- Publication number
- CN110969793B CN110969793B CN201911364610.9A CN201911364610A CN110969793B CN 110969793 B CN110969793 B CN 110969793B CN 201911364610 A CN201911364610 A CN 201911364610A CN 110969793 B CN110969793 B CN 110969793B
- Authority
- CN
- China
- Prior art keywords
- image
- intrusion
- suspicious
- ship
- roundabout
- 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
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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a perimeter ship intrusion prevention method, a system and a storage medium of a roundabout electronic purse net, which comprises the steps of receiving intrusion early warning information of the roundabout perimeter, and determining the occurrence position of the intrusion early warning information; sending control information for acquiring a real-time video image of an instruction position of the intrusion early warning information to a pan-tilt video monitoring camera close to the occurrence position of the intrusion early warning information according to the occurrence position of the intrusion early warning information; and receiving a real-time video image sent by the pan-tilt video monitoring camera, carrying out image analysis on the real-time video image, judging whether the real-time video image has a ship intrusion behavior, and if the judgment result shows that the ship intrusion behavior exists, sending alarm information. The ship intrusion prevention method can be used for remotely monitoring ships in offshore areas, monitoring suspicious intruding ship intrusion behaviors in advance, and taking corresponding alarming and preventing measures in time to prevent the problem that the suspicious intruding ships are not prevented from logging in time due to untimely alarming information.
Description
Technical Field
The invention relates to the technical field of electronic purse seine monitoring, in particular to a perimeter ship intrusion prevention method and system of a rotary island electronic purse seine and a storage medium.
Background
The customs supervision ships mainly refer to small ships and internal lane ships in port and Australia, domestic flow areas such as Yangtze river, Zhujiang river and the like have four-way and eight-reach waterway and a plurality of waterway freight routes, and a large number of customs supervision ships are actively in the areas of Yangtze river, Zhu river and the south-east coastal water.
At present, nearly 2000 small ships and nearly 10 tens of thousands of internal support line ships come and go to hong Kong, China Macau, and the ships are responsible for a large amount of in-and-out cargo transportation and internal support line cargo transfer tasks, and the ships are tied to a customs midway supervision station to handle related procedures by conscious berthing, and the customs routinely check the traditional supervision mode, so that the requirements of actual supervision are far from being met in the face of the actual situation that a waterway is four-way and eight-way, and the smuggling activity is difficult to be comprehensively prevented and restrained.
Disclosure of Invention
In order to overcome the defects of the traditional customs supervision mode, the invention provides a perimeter ship intrusion prevention method, a perimeter ship intrusion prevention system and a storage medium of an electronic purse net of a roundabout, which can strictly monitor a ship intruding the roundabout and comprehensively prevent and inhibit smuggling activities.
In order to solve the technical problems, the technical scheme of the invention is as follows:
according to a first aspect, the invention provides a perimeter anti-ship intrusion method for a roundabout electronic purse net, which comprises the following steps: receiving intrusion early warning information of a roundabout perimeter sent by a front-end detection device, and determining the occurrence position of the intrusion early warning information; sending control information for acquiring a real-time video image of the position indicated by the intrusion early warning information to the pan-tilt video monitoring cameras close to the position where the intrusion early warning information occurs according to the position where the intrusion early warning information occurs and the position information of the plurality of pan-tilt video monitoring cameras on the periphery of the roundabout; receiving the real-time video image sent by the pan-tilt video monitoring camera, carrying out image analysis on the real-time video image, judging whether the real-time video image has a ship intrusion behavior, and if the judgment result shows that the ship intrusion behavior exists, sending alarm information;
the image analysis is carried out on the real-time video image, and whether a ship intrusion behavior exists in the real-time video image is judged, including: acquiring a video clip in the real-time video image; intercepting a frame image of each frame from the real-time video image; judging whether the definition of each frame of the frame image is greater than a preset definition threshold, if so, executing the next step, and if not, quitting the processing of the frame image; performing feature recognition on each frame of the frame image to judge whether abnormal features exist, if so, executing the next step, and if not, exiting the processing of the frame image; identifying the position of a boundary point of a suspicious invading object from the frame image; outlook of the suspicious invading object is sketched according to the position of the boundary point, whether the size of the suspicious invading object is larger than the preset size is judged, if yes, the next step is executed, if not, the processing of the frame image is quitted; and comparing the outline of the suspicious invading object obtained by outlining with various ship images prestored in a database, and judging whether the suspicious invading object is a ship or not.
Further, the determining whether the sharpness of the frame image of each frame is greater than a preset sharpness threshold includes: processing to obtain an image definition parameter of the frame image; wherein the image sharpness parameter comprises an image blur parameter and/or a camera shake parameter of the frame image; processing according to the image definition parameter to obtain the definition of the frame image; and judging whether the definition of the frame image is greater than the preset definition threshold value.
Further, the performing feature recognition on the frame image of each frame to determine whether there is an abnormal feature includes: extracting a template image at the position of the intrusion early warning information from a pre-stored template image database of the perimeter of the roundabout according to the position of the intrusion early warning information; extracting feature points of each area from the template image at the position where the intrusion early warning information occurs; extracting feature points of each region from the frame image; and matching the feature points of each area in the frame image with the feature points of each area in the template image at the position of the intrusion early warning information, and judging whether abnormal features exist according to the matching result.
Further, the identifying the boundary point position of the suspicious invading object from the frame image comprises: removing the background in the frame image to obtain an image of a region to be analyzed; preprocessing the boundary characteristics of the image of the area to be analyzed; carrying out segmentation processing on the preprocessed image of the region to be analyzed to obtain a binary image; and determining the position of the boundary point of the suspicious invading object in the binary image.
Further, the preprocessing the boundary characteristics of the image of the region to be analyzed includes: carrying out noise reduction processing on the image of the area to be analyzed by adopting gamma conversion; calculating the gradient direction of each pixel in the image of the region to be analyzed; carrying out image sharpening processing on the gray level of the image of the area to be analyzed in the gradient direction of the pixel; and smoothing the gray scale of the image of the area to be analyzed in the vertical direction of the pixel gradient.
Further, the segmenting the preprocessed image of the region to be analyzed to obtain a binary image includes: acquiring the edge contour of the preprocessed image of the area to be analyzed by adopting a level set algorithm; performing binary conversion on the image of the region to be analyzed according to the edge contour to obtain a segmented binary image; and filtering noise points in the binary image by adopting a method based on the area of the regional pixel to obtain the noise-reduced binary image.
Further, the step of outlining the suspicious invading object according to the position of the boundary point and judging whether the size of the suspicious invading object is larger than the preset size includes: sequentially connecting all boundary points of the suspicious invading object to form the outline of the suspicious invading object; calculating the maximum value of the position distance between two boundary points which are randomly and oppositely arranged in the outline and taking the maximum value as the size of the suspicious invading object; and judging whether the size of the suspicious invading object is larger than the preset size.
According to a second aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions for causing the computer to execute the perimeter ship intrusion prevention method for the roundabout electronic purse net.
The technical scheme of the invention has the following advantages:
1. the invention provides a perimeter ship intrusion prevention method of a roundabout electronic purse net, which comprises the steps of firstly collecting intrusion early warning information of the roundabout perimeter through a front-end detection device; the monitoring platform receives the intrusion early warning information, determines the specific occurrence position of the intrusion early warning information, and then sends control information to the pan-tilt video monitoring cameras close to the occurrence position of the intrusion early warning information according to the determined occurrence position of the intrusion early warning information and the position information of the pan-tilt video monitoring cameras stored in the monitoring platform in advance on the periphery of the roundabout; responding to the control information and rotating a preset angle by a pan-tilt video monitoring camera positioned on the periphery of the roundabout, so that the shooting angle of the pan-tilt video monitoring camera faces to the indication position corresponding to the intrusion position information to obtain a real-time video image of the indication position of the intrusion early warning information; and finally, the monitoring platform receives the real-time video image sent by the pan-tilt video monitoring camera, performs image analysis on the real-time video image, judges whether the real-time video image has a ship intrusion behavior, and sends alarm information when the judgment result shows that the ship intrusion behavior exists. The perimeter anti-ship intrusion method of the roundabout electronic purse net comprises the steps that after a monitoring platform receives intrusion early warning information collected by a front-end detection device, a cloud deck video monitoring camera is used for obtaining a field real-time video image of an instruction position of the intrusion early warning information, whether ship intrusion behaviors exist in the real-time video image is automatically judged, the accuracy of a perimeter anti-ship intrusion monitoring result can be improved, remote ship monitoring of an offshore area can be carried out, when a suspicious intruding ship is further away from a roundabout coast for a long distance, the suspicious intruding ship intrusion behaviors can be monitored in advance, corresponding alarming and stopping measures can be taken timely, and the problem that the suspicious intruding ship is prevented from logging in time due to untimely alarming information is prevented.
2. The invention provides a perimeter anti-ship intrusion method of a roundabout electronic purse net, which comprises the steps of sequentially carrying out definition judgment and characteristic identification on each frame image of a real-time video image, extracting a frame image containing abnormal characteristics, identifying the boundary point position of a suspicious intrusion object from the frame image containing the abnormal characteristics, outlining the outline of the suspicious intrusion object according to the boundary point position, comparing the size of the outline of the suspicious intrusion object with the preset size, rejecting some very small suspicious intrusion objects, comparing the suspicious intrusion object meeting the size requirement with various ship images stored in a database in advance, thereby determining whether the suspicious intrusion object is a ship or not, and outputting corresponding alarm information when the suspicious intrusion object is a ship. When the suspicious invading object on the sea is a ship, the possibility of behavior such as suspected smuggling, escaping and the like is higher because the ship is more special relative to other types of suspicious invading objects, and correspondingly, the alarm level set by customs supervision personnel facing the ship invading behavior is higher, and more countermeasures need to be taken; the ship intrusion prevention method can accurately monitor ship intrusion, can send alarm information corresponding to suspicious intrusion objects according to the types of the suspicious intrusion objects, and can better monitor the perimeter of the roundabout. Before the suspicious invading object is judged, the definition judgment, the feature identification and the size comparison are carried out on the frame image, the calculation amount of the subsequent suspicious invading object type judgment can be reduced, and the identification speed and the accuracy of the suspicious invading object are improved.
3. According to the perimeter ship intrusion prevention method of the roundabout electronic purse net, the edge contour of the suspicious intrusion object can be determined by means of obtaining the image of the area to be analyzed by removing the background in the frame image and preprocessing and segmenting the image of the area to be analyzed to obtain the binary image, so that the continuity and the identifiability of the boundary point of the suspicious intrusion object are improved, and the accuracy of the subsequent classification identification result of the suspicious intrusion object 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 other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic layout diagram of a front-end detection device and a front-end video monitoring device on an island in a perimeter anti-ship intrusion system of an electronic purse seine of a roundabout according to an embodiment of the present invention;
fig. 2 is a flowchart of an implementation of a perimeter ship intrusion prevention method for an electronic purse net of a roundabout according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating an implementation of performing image analysis on a real-time video image and determining whether a vessel intrusion behavior exists in the real-time video image according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating an implementation of determining whether the sharpness of each frame of image is greater than a preset sharpness threshold according to an embodiment of the present invention;
fig. 5 is a flowchart illustrating an implementation of feature recognition on each frame of image to determine whether there is an abnormal feature according to an embodiment of the present invention;
fig. 6 is a flowchart illustrating an implementation of identifying positions of boundary points of a suspicious intrusion object from a frame image according to an embodiment of the present invention;
fig. 7 is a flowchart illustrating an implementation of preprocessing boundary characteristics of an image of an area to be analyzed according to an embodiment of the present invention;
fig. 8 is a flowchart illustrating an implementation of segmenting a preprocessed image of a region to be analyzed to obtain a binary image according to an embodiment of the present invention;
fig. 9 is a flowchart illustrating an implementation of outlining a suspicious invading object according to the position of a boundary point and determining whether the size of the suspicious invading object is larger than a preset size according to the embodiment of the present invention;
fig. 10 is a schematic diagram of a hardware structure of a monitoring platform according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood 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.
As shown in fig. 1, the perimeter ship intrusion prevention system of the roundabout electronic purse net comprises a front-end detection device 1, a front-end video monitoring device and a monitoring platform, wherein the monitoring platform is in communication connection with the front-end detection device and the front-end video monitoring device through optical fibers. The front-end detection device comprises a sensing optical cable which is arranged in the peripheral sea area of the roundabout boundary, the sensing optical cable is used for monitoring whether the roundabout peripheral sea area has intrusion behaviors or not and sending intrusion early warning information to the monitoring platform when the intrusion behaviors occur. The monitoring platform is used for receiving the intrusion early warning information sent by the front-end detection device, determining intrusion position information of an intrusion early warning information occurrence position, and sending control information to the front-end video monitoring device located on the periphery of the roundabout according to the intrusion position information. The front-end video monitoring device comprises a plurality of pan-tilt video monitoring cameras 2 arranged on the periphery of the roundabout, the pan-tilt video monitoring cameras 2 respond to control information and rotate preset angles, so that the shooting angles of the pan-tilt video monitoring cameras face the indication positions corresponding to the intrusion position information to acquire real-time video images of the intrusion early warning information indication positions, and the real-time video images of the early warning information indication positions are transmitted back to the monitoring platform. The monitoring platform receives the real-time video image sent by the pan-tilt video monitoring camera 2, performs image analysis on the real-time video image, judges whether the real-time video image has a ship intrusion behavior, and sends alarm information if the judgment result shows that the ship intrusion behavior exists.
The perimeter anti-ship intrusion system of the roundabout electronic purse net comprises a monitoring platform, a tripod head video monitoring camera, a platform video monitoring system and a control system, wherein the monitoring platform is used for acquiring a field real-time video image of an intrusion early warning information indicating position after receiving intrusion early warning information acquired by a front-end detection device, and automatically judging whether a ship intrusion behavior exists in the real-time video image, so that the accuracy of a perimeter anti-ship intrusion monitoring result can be improved, remote ship monitoring in an offshore area can be performed, when a suspicious intruding ship is further away from a roundabout coast for a longer distance, the suspicious intruding ship intrusion behavior can be monitored in advance, corresponding alarming and preventing measures can be taken in time, and the problem that the suspicious intruding ship is prevented from logging due to.
Specifically, the monitoring range of the sensing optical cable near the sea island is arranged in a mode that an underwater upright post is combined with an underwater pull net; the cloud platform device of cloud platform video surveillance camera machine rotates and installs the top at the pole setting, and the pole setting is fixed on the periphery of island, and cloud platform video surveillance camera machine's camera device can rotate around cloud platform device, and camera device adopts the camera lens that can automatic control camera lens zoom, focus, realizes the needs to suspicious invading object careful observation and snapshot, and the cooperation variable speed cloud platform device realizes tracking fast and enlargeing different speed suspicious invading object.
As shown in fig. 2, an embodiment of the present invention further provides a perimeter ship intrusion prevention method for an electronic purse net of a roundabout, which specifically includes the following steps:
and S100, receiving the intrusion early warning information of the roundabout perimeter sent by the front-end detection device, and determining the occurrence position of the intrusion early warning information.
S200, sending control information for acquiring real-time video images of the position indicated by the intrusion early warning information to the PTZ video surveillance cameras close to the position where the intrusion early warning information occurs according to the position where the intrusion early warning information occurs and the position information of the PTZ video surveillance cameras on the roundabout periphery
Step S300, receiving the real-time video image sent by the pan-tilt video monitoring camera, carrying out image analysis on the real-time video image, judging whether the real-time video image has a ship intrusion behavior, and if the judgment result shows that the ship intrusion behavior exists, sending alarm information.
Specifically, the alarm information is sent out through an alarm execution mechanism, and the alarm execution mechanism comprises but is not limited to an alarm lamp, a loudspeaker, linkage equipment, printing equipment, communication with the outside and the like.
The invention provides a perimeter ship intrusion prevention method of a roundabout electronic purse net, which comprises the steps of firstly collecting intrusion early warning information of the roundabout perimeter through a front-end detection device; the monitoring platform receives the intrusion early warning information, determines the specific occurrence position of the intrusion early warning information, and then sends control information to the pan-tilt video monitoring cameras close to the occurrence position of the intrusion early warning information according to the determined occurrence position of the intrusion early warning information and the position information of the pan-tilt video monitoring cameras stored in the monitoring platform in advance on the periphery of the roundabout; responding to the control information and rotating a preset angle by a pan-tilt video monitoring camera positioned on the periphery of the roundabout, so that the shooting angle of the pan-tilt video monitoring camera faces to the indication position corresponding to the intrusion position information to obtain a real-time video image of the indication position of the intrusion early warning information; and finally, the monitoring platform receives the real-time video image sent by the pan-tilt video monitoring camera, performs image analysis on the real-time video image, judges whether the real-time video image has a ship intrusion behavior, and sends alarm information when the judgment result shows that the ship intrusion behavior exists. The perimeter anti-ship intrusion method of the roundabout electronic purse net comprises the steps that after a monitoring platform receives intrusion early warning information collected by a front-end detection device, a cloud deck video monitoring camera is used for obtaining a field real-time video image of an instruction position of the intrusion early warning information, whether ship intrusion behaviors exist in the real-time video image is automatically judged, the accuracy of a perimeter anti-ship intrusion monitoring result can be improved, remote ship monitoring of an offshore area can be carried out, when a suspicious intruding ship is further away from a roundabout coast for a long distance, the suspicious intruding ship intrusion behaviors can be monitored in advance, corresponding alarming and stopping measures can be taken timely, and the problem that the suspicious intruding ship is prevented from logging in time due to untimely alarming information is prevented.
As shown in fig. 3, in step S300, the image analysis of the real-time video image to determine whether there is a ship intrusion behavior in the real-time video image specifically includes the following steps:
and step S310, acquiring a video clip in the real-time video image.
And step S320, intercepting a frame image of each frame from the real-time video image.
Step S330, judging whether the definition of each frame of the frame image is greater than a preset definition threshold, if so, executing the next step, and if not, quitting the processing of the frame image.
Step S340, performing feature recognition on each frame of the frame image to determine whether there is an abnormal feature, if so, executing the next step, otherwise, exiting the processing of the frame image.
And step S350, identifying the position of the boundary point of the suspicious invading object from the frame image.
Specifically, since the gray level of the suspicious intrusion object in the frame image is significantly different from the gray level of the background portion in the frame image, the position of the boundary point of the suspicious object can be identified from the frame image through the gray level difference.
And step S360, outlining the outline of the suspicious invading object according to the position of the boundary point, judging whether the size of the suspicious invading object is larger than the preset size, if so, executing the next step, and if not, quitting the processing of the frame image.
Step S370, comparing the outline of the suspicious invading object obtained by outlining with various ship images stored in a database in advance, and judging whether the suspicious invading object is a ship or not.
The method comprises the steps of sequentially carrying out definition judgment and feature identification on each frame image of a real-time video image, extracting a frame image containing abnormal features, identifying boundary point positions of suspicious invading objects from the frame image containing the abnormal features, outlining the outline of the suspicious invading objects according to the boundary point positions, comparing the size of the outline of the suspicious invading objects with a preset size, rejecting some very small suspicious invading objects, comparing the suspicious invading objects meeting the size requirement with various ship images stored in a database in advance, determining whether the suspicious invading objects are ships or not, and outputting corresponding alarm information when the suspicious invading objects are ships. When the suspicious invading object on the sea is a ship, the possibility of behavior such as suspected smuggling, escaping and the like is higher because the ship is more special relative to other types of suspicious invading objects, and correspondingly, the alarm level set by customs supervision personnel facing the ship invading behavior is higher, and more countermeasures need to be taken; the ship intrusion prevention method can accurately monitor ship intrusion, can send alarm information corresponding to suspicious intrusion objects according to the types of the suspicious intrusion objects, and can better monitor the perimeter of the roundabout. Before the suspicious invading object is judged, the definition judgment, the feature identification and the size comparison are carried out on the frame image, the calculation amount of the subsequent suspicious invading object type judgment can be reduced, and the identification speed and the accuracy of the suspicious invading object are improved.
As shown in fig. 4, in step S330, the determining whether the sharpness of the frame image of each frame is greater than a preset sharpness threshold specifically includes the following steps:
step S331, processing to obtain an image definition parameter of the frame image; wherein the image sharpness parameter comprises an image blur parameter and/or a camera shake parameter of the frame image;
s332, processing according to the image definition parameter to obtain the definition of the frame image;
step S333, judging whether the definition of the frame image is larger than the preset definition threshold value.
Before the subsequent judgment of whether the suspicious invading object is a ship or not, a part of frame images with unqualified definition are removed in an image definition comparison mode, so that the calculation amount of the subsequent suspicious invading object judgment can be reduced, and the identification speed and the accuracy of the suspicious invading object are improved.
As shown in fig. 5, in step S340, the performing feature identification on the frame image of each frame to determine whether there is an abnormal feature specifically includes the following steps:
step S341, according to the occurrence position of the intrusion alert information, extracting a template image at the occurrence position of the intrusion alert information from a pre-stored template image database around the island.
And step S342, extracting the characteristic points of each area from the template image at the position where the intrusion early warning information occurs.
Step S343, extracting feature points of each region from the frame image.
And step S344, matching the feature points of each area in the frame image with the feature points of each area in the template image at the position where the intrusion early warning information occurs, and judging whether abnormal features exist according to the matching result.
By adopting the method of matching the regional characteristic points, the judgment result of whether the frame image has abnormal characteristics can be quickly obtained, and the timeliness of sending out subsequent alarm information is improved.
Before the suspicious invading object is judged to be a ship or not in the follow-up process, the judgment result of whether the frame image has abnormal characteristics or not can be quickly obtained by adopting a regional characteristic point matching method, and the timeliness of sending out follow-up alarm information is improved.
As shown in fig. 6, in step S350, the identifying the boundary point position of the suspicious intrusion object from the frame image specifically includes the following steps:
and step S351, removing the background in the frame image to acquire an image of the area to be analyzed.
And S352, preprocessing the boundary characteristics of the to-be-analyzed area image.
And S353, carrying out segmentation processing on the preprocessed to-be-analyzed region image to obtain a binary image.
Step S354, determining a boundary point position of the suspicious invading object in the binary image.
The binary image of the frame image can be obtained by preprocessing and segmenting the frame image without the background, so that the position of the boundary point of the suspicious invading object is determined, the noise in the frame image can be suppressed by preprocessing, the continuity and the distinguishability of the boundary point of the suspicious invading object are improved, and the accuracy of the comparison result of whether the subsequent suspicious invading object is a ship or not is further improved.
As shown in fig. 7, in step S352, the preprocessing the boundary characteristics of the to-be-analyzed region image specifically includes the following steps:
and S3521, performing noise reduction processing on the to-be-analyzed area image by adopting gamma conversion.
Specifically, since the noise of other pixel points in the image of the area to be analyzed may cause the decrease of the contrast of the boundary point of the suspicious invading object in the frame image, and reduce the continuity of the boundary point of the suspicious invading object, the noise in the image of the area to be analyzed needs to be suppressed, and the continuity of the boundary point of the suspicious invading object is improved. In the embodiment, the preprocessing is performed on the frame image by using gamma transformation, so that the boundary points of the suspicious invading object with high brightness can be enhanced, and the influence of noise is reduced. In other embodiments, the noise reduction process may also be performed by, but not limited to, gaussian filtering, histogram equalization, and regularization.
And S3522, calculating the gradient direction of each pixel in the image of the area to be analyzed.
And S3523, carrying out image sharpening on the gray level of the image of the area to be analyzed in the gradient direction of the pixels.
And S3524, carrying out smoothing processing on the gray scale of the image of the area to be analyzed in the vertical direction of the pixel gradient.
Specifically, a specific mode of image sharpening processing adopts one-dimensional laplacian filtering; the specific way of smoothing is median or mean filtering. The anisotropic processing can improve the continuity and edge sharpness of the boundary points of the suspicious invading object in the image of the area to be analyzed, thereby improving the identifiability of the boundary points of the suspicious invading object in the frame image and being beneficial to the subsequent image segmentation. In other embodiments, other filtering methods may be used for the image sharpening and smoothing.
As shown in fig. 8, in step S353, the segmenting the preprocessed image of the region to be analyzed to obtain a binary image specifically includes the following steps:
s3531, a level set algorithm is adopted to obtain the edge contour of the preprocessed image of the area to be analyzed.
Specifically, the level set algorithm is a geometric contour model, and mainly expresses the evolution process of a low-dimensional target curve by a zero level set tangent plane of a level set function one-dimensional higher than the evolution process of the low-dimensional target curve. When minimizing the functional of the level set, the zero level set of the level set function will shrink to the target boundary under the action of internal and external forces. The specific calculation process is common knowledge of those skilled in the art and is not described in detail herein. And obtaining the edge contour of the suspicious invading object in the image of the area to be analyzed by a level set algorithm.
And S3532, performing binary conversion on the image of the area to be analyzed according to the edge contour to obtain a segmented binary image.
Specifically, taking a segmentation method based on a gray threshold as an example, the gray levels of all pixels with brightness greater than the threshold in the image of the area to be analyzed are set to 255, and other pixels are set to 0, that is, the whole image of the area to be analyzed shows an obvious black-and-white effect, and the binarization of the image of the area to be analyzed greatly reduces the data volume in the frame image, so that the edge contour of the suspicious invading object can be highlighted. The selection of the gray threshold value can be flexibly selected according to the specific characteristics and the specific situation of the target image according to the selection criteria including, but not limited to, maximum entropy, intra-class variance, inter-class variance, and the like.
In other embodiments, the image segmentation method may also be based on differences in image physical characteristics and parameter settings, and may also be an image segmentation method based on an active contour model or an image segmentation method based on clustering.
And S3533, filtering noise points in the binary image by adopting a method based on the area of the region pixel to obtain a denoised binary image.
As shown in fig. 9, in step S360, the step of outlining the suspicious invading object according to the position of the boundary point, and determining whether the size of the suspicious invading object is larger than a preset size includes the following steps:
and step S361, sequentially connecting all boundary points of the suspicious intrusion object to form the outline of the suspicious intrusion object.
And step S362, calculating the maximum value of the position distance between any two oppositely arranged boundary points in the outline, and taking the maximum value as the size of the suspicious invading object.
Step S363, determining whether the size of the suspicious intrusion object is larger than the preset size.
Specifically, in the process of step S501, after the boundary point position of the suspicious invading object is obtained, an approximate boundary of the suspicious invading object may be outlined on the image, but the approximate boundary is not necessarily completely closed, each broken part may generate two break points, an euclidean distance between two break points is calculated, two closest break points are connected together, then distances between other break points are recalculated, and the closed approximate boundary delineation is completed through successive iteration.
After the approximate boundaries of the suspected intruding object are outlined, further preprocessing determines the rough boundaries of the suspected intruding object. Selecting a first boundary point and a second boundary point on all boundary points in the image of the area to be analyzed, setting the first boundary point and the second boundary point as a minimum abscissa boundary point and a maximum abscissa boundary point, respectively marking the first boundary point and the second boundary point as a point A and a point B, setting an abscissa set of all points on a line segment AB as { x1, x 2., xn }, selecting a third boundary point and a fourth boundary point on all boundary points of the image of the area to be analyzed, setting the third boundary point and the fourth boundary point as a minimum ordinate boundary point and a maximum boundary point on a vertical coordinate, respectively marking the third boundary point and the fourth boundary point as a point C and a point D, setting an abscissa set of all points on a line segment CD as { y1, y 2.,. yn }, and setting the coordinates as { (x1+ x2+.. + xn)/n, (y1+ y2+.. + yn)/n } as the gravity center of the suspicious; moving the gravity center of the image of the area to be analyzed to the origin of the coordinate axis, and sequentially taking the vector directions which form an included angle of 0 degrees, 1 degree, 359 degrees with the positive direction of the transverse axis, namely the direction of the sampling scanning line; taking a sampling scanning line between an origin and an approximate boundary as a sampling line segment, and obtaining a sampling line segment set S ═ S0, S1, S2,.. and S359}, wherein the sets of all pixels in the direction from the origin to the boundary on the sampling line segment S0 are sequentially { d0, d1,... dn }, and dn }, the gray scale of each point is respectively { g0, g1, g2,... gn }, and the gray variation degree is respectively { g ' 0, g ' 1, g ' 2,..,. g ' n }, and then gi ' | i + 1-gi | and i ═ 0, 1, 2,..,. n-1, and g ' n ═ g ' n-1. And (3) taking the point with the maximum gray change degree as a color mutation pixel point of the sampling line segment S0, sequentially and respectively obtaining the color mutation pixel points of the sampling line segments S1, S2, and S359, and finally connecting the 360 points to obtain the outline of the suspicious invading object.
And after the outline of the suspicious invading object is obtained through the steps, further expanding the image of the area to be analyzed. Expanding each sampling line segment surrounded by the outline of the suspicious invading object to 105% of the length, and taking the line segment between 95% and 105% of the original sampling line segment to obtain a sampling strip; then, for a sampling line segment set S360 determined by the sampling strip and the sampling scan line, the image of the region to be analyzed is represented as G ═ f (x, y), G represents the pixel value of any point in the image, x and y are the horizontal and vertical coordinates of the point in the coordinate system, the first derivative of each point of each sampling line segment is sequentially calculated, and the point with the maximum derivative in each sampling line segment is taken as the set S ' ═ S ' 1, S ' 2. And counting S 'of adjacent sampling lines, if the current S' exceeds a certain value Tl, determining that the boundary caused by noise cannot be determined, and discarding the sampling point, wherein the rest points are the accurate boundary points of the suspicious intrusion object.
The method for outlining the suspicious invading object can effectively improve the truth of the suspicious invading object which is outlined, and further improve the accuracy of the judgment result whether the subsequent suspicious invading object is a ship or not.
Specifically, the various ship images pre-stored in the database include: ship images of various types, tonnage and posture.
As shown in fig. 10, the monitoring platform in the perimeter anti-ship intrusion system of the electronic purse net of roundabout according to the embodiment of the present invention includes, but is not limited to, a memory 72, a processor 71, and a computer program stored in the memory 72 and executable on the processor 71. It will be understood by those skilled in the art that fig. 10 is merely an example of a monitoring platform in the perimeter anti-ship intrusion system of the rotary island electronic purse, and does not constitute a limitation on the monitoring platform in the perimeter anti-ship intrusion system of the rotary island electronic purse, and may include more or less components than those shown, or combine some components, or different components, for example, the perimeter anti-intrusion apparatus based on the target location may further include an input-output device, a network access device, a bus, etc. The processor 71, when executing the computer program, implements the perimeter anti-ship intrusion method of the rotary island electronic purse net as described above.
The processor 71 may be a Central Processing Unit (CPU). The Processor 81 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or combinations thereof.
The memory 72 is a non-transitory computer readable storage medium, and can be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the perimeter anti-ship intrusion method of the electronic purse net of the roundabout in the embodiment of the present invention. The processor 71 executes various functional applications and data processing of the processor 71 by running non-transitory software programs, instructions and modules stored in the memory 72, namely, the perimeter ship intrusion prevention method of the roundabout electronic purse net in the above method embodiment is realized.
The memory 72 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor 71, and the like. Further, the memory 72 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 72 may optionally include memory 72 located remotely from the processor 71, and these remote memories 72 may be connected to the processor 71 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 72 and when executed by the processor 71 perform a perimeter anti-ship intrusion method of the rotary island electronic purse net as in the embodiment shown in fig. 2.
The specific details of the perimeter ship intrusion prevention method for the electronic purse seine of the roundabout can be understood by referring to the corresponding related description and effects in the embodiment shown in fig. 2, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory 72(Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like; the storage medium may also include a combination of memories 72 of the kind described above.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (8)
1. A perimeter ship intrusion prevention method of a roundabout electronic purse net is characterized by comprising the following steps:
receiving intrusion early warning information of a roundabout perimeter sent by a front-end detection device, and determining the occurrence position of the intrusion early warning information;
sending control information for acquiring a real-time video image of the position indicated by the intrusion early warning information to the pan-tilt video monitoring cameras close to the position where the intrusion early warning information occurs according to the position where the intrusion early warning information occurs and the position information of the plurality of pan-tilt video monitoring cameras on the periphery of the roundabout;
receiving the real-time video image sent by the pan-tilt video monitoring camera, carrying out image analysis on the real-time video image, judging whether the real-time video image has a ship intrusion behavior, and if the judgment result shows that the ship intrusion behavior exists, sending alarm information;
the image analysis is carried out on the real-time video image, and whether a ship intrusion behavior exists in the real-time video image is judged, including:
acquiring a video clip in the real-time video image;
intercepting a frame image of each frame from the real-time video image;
judging whether the definition of each frame of the frame image is greater than a preset definition threshold, if so, executing the next step, and if not, quitting the processing of the frame image;
performing feature recognition on each frame of the frame image to judge whether abnormal features exist, if so, executing the next step, and if not, exiting the processing of the frame image;
identifying the position of a boundary point of a suspicious invading object from the frame image;
outlook of the suspicious invading object is sketched according to the position of the boundary point, whether the size of the suspicious invading object is larger than the preset size is judged, if yes, the next step is executed, if not, the processing of the frame image is quitted;
and comparing the outline of the suspicious invading object obtained by outlining with various ship images prestored in a database, and judging whether the suspicious invading object is a ship or not.
2. A perimeter anti-ship intrusion method for an electronic purse net of roundabout according to claim 1, wherein the determining whether the definition of the frame image of each frame is greater than a preset definition threshold comprises:
processing to obtain an image definition parameter of the frame image; wherein the image sharpness parameter comprises an image blur parameter and/or a camera shake parameter of the frame image;
processing according to the image definition parameter to obtain the definition of the frame image;
and judging whether the definition of the frame image is greater than the preset definition threshold value.
3. A perimeter anti-ship intrusion method for an electronic purse net of roundabout according to claim 1, wherein the performing feature recognition on each frame of the frame image to determine whether there is an abnormal feature comprises:
extracting a template image at the position of the intrusion early warning information from a pre-stored template image database of the perimeter of the roundabout according to the position of the intrusion early warning information;
extracting feature points of each area from the template image at the position where the intrusion early warning information occurs;
extracting feature points of each region from the frame image;
and matching the feature points of each area in the frame image with the feature points of each area in the template image at the position of the intrusion early warning information, and judging whether abnormal features exist according to the matching result.
4. A perimeter anti-ship intrusion method for an electronic purse net of roundabout according to claim 1, wherein the identifying the position of the boundary point of the suspicious intrusion object from the frame image comprises:
removing the background in the frame image to obtain an image of a region to be analyzed;
preprocessing the boundary characteristics of the image of the area to be analyzed;
carrying out segmentation processing on the preprocessed image of the region to be analyzed to obtain a binary image;
and determining the position of the boundary point of the suspicious invading object in the binary image.
5. A perimeter anti-ship intrusion method for the roundabout electronic purse net according to claim 4, wherein the preprocessing of the boundary characteristics of the area image to be analyzed comprises:
carrying out noise reduction processing on the image of the area to be analyzed by adopting gamma conversion;
calculating the gradient direction of each pixel in the image of the region to be analyzed;
carrying out image sharpening processing on the gray level of the image of the area to be analyzed in the gradient direction of the pixel;
and smoothing the gray scale of the image of the area to be analyzed in the vertical direction of the pixel gradient.
6. The perimeter anti-ship intrusion method of the roundabout electronic purse net according to claim 5, wherein the step of segmenting the preprocessed image of the area to be analyzed to obtain a binary image comprises the steps of:
acquiring the edge contour of the preprocessed image of the area to be analyzed by adopting a level set algorithm;
performing binary conversion on the image of the region to be analyzed according to the edge contour to obtain a segmented binary image;
and filtering noise points in the binary image by adopting a method based on the area of the regional pixel to obtain the noise-reduced binary image.
7. The perimeter ship intrusion prevention method of the roundabout electronic purse net according to claim 1, wherein the step of determining whether the size of the suspicious intrusion object is larger than a preset size by outlining the outline of the suspicious intrusion object according to the position of the boundary point comprises the steps of:
sequentially connecting all boundary points of the suspicious invading object to form the outline of the suspicious invading object;
calculating the maximum value of the position distance between two boundary points which are randomly and oppositely arranged in the outline and taking the maximum value as the size of the suspicious invading object;
and judging whether the size of the suspicious invading object is larger than the preset size.
8. A computer-readable storage medium storing computer instructions for causing a computer to execute the method for perimeter ship intrusion prevention for a rotary island electronic purse net according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911364610.9A CN110969793B (en) | 2019-12-25 | 2019-12-25 | Method, system and storage medium for preventing ship intrusion at periphery of roundabout electronic purse net |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911364610.9A CN110969793B (en) | 2019-12-25 | 2019-12-25 | Method, system and storage medium for preventing ship intrusion at periphery of roundabout electronic purse net |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110969793A CN110969793A (en) | 2020-04-07 |
| CN110969793B true CN110969793B (en) | 2020-08-07 |
Family
ID=70036651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911364610.9A Active CN110969793B (en) | 2019-12-25 | 2019-12-25 | Method, system and storage medium for preventing ship intrusion at periphery of roundabout electronic purse net |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110969793B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111626204B (en) * | 2020-05-27 | 2022-01-11 | 汪海洋 | Railway foreign matter invasion monitoring method and system |
| CN111950618A (en) * | 2020-08-05 | 2020-11-17 | 中国建设银行股份有限公司 | Water area image data labeling method, device, equipment and storage medium |
| CN114339027A (en) * | 2021-11-16 | 2022-04-12 | 浙江大华技术股份有限公司 | Ship monitoring method, electronic device and storage medium |
| CN115225865B (en) * | 2022-07-18 | 2023-05-05 | 合肥英乾电子科技有限公司 | Side sea defense video monitoring device based on infrared thermal imaging |
| CN117877179A (en) * | 2023-11-08 | 2024-04-12 | 上海湃道智能科技有限公司 | Perimeter anti-intrusion alarm method, perimeter anti-intrusion alarm system, electronic equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101188036A (en) * | 2007-04-24 | 2008-05-28 | 华中科技大学 | Optical fiber surrounding guarding and laser night vision online monitoring system |
| JP2016082506A (en) * | 2014-10-21 | 2016-05-16 | キヤノン株式会社 | Monitoring device, monitoring method and program |
| CN104504830A (en) * | 2014-12-25 | 2015-04-08 | 桂林聚联科技有限公司 | Intelligent optical fiber sensing system for perimeter security guard of island |
| CN204315010U (en) * | 2014-12-25 | 2015-05-06 | 桂林聚联科技有限公司 | A kind of Intelligent optical fiber sensor-based system for island circumference security protection |
| CN207976974U (en) * | 2018-02-02 | 2018-10-16 | 贵州电网有限责任公司都匀供电局 | A kind of intrusion alarm system |
| CN108806144A (en) * | 2018-07-02 | 2018-11-13 | 俞雪利 | A kind of community alarm system based on 5G networks |
-
2019
- 2019-12-25 CN CN201911364610.9A patent/CN110969793B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110969793A (en) | 2020-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110969793B (en) | Method, system and storage medium for preventing ship intrusion at periphery of roundabout electronic purse net | |
| JP6797860B2 (en) | Water intrusion detection system and its method | |
| WO2020059706A1 (en) | Training data collection device, training data collection method, and program | |
| Bedruz et al. | Real-time vehicle detection and tracking using a mean-shift based blob analysis and tracking approach | |
| CN114926726B (en) | Unmanned ship sensing method based on multitask network and related equipment | |
| CN111435436B (en) | Perimeter anti-intrusion method and device based on target position | |
| CN110415208A (en) | A kind of adaptive targets detection method and its device, equipment, storage medium | |
| CN112528861B (en) | Foreign matter detection method and device applied to ballast bed in railway tunnel | |
| CN112417955B (en) | Method and device for processing tour inspection video stream | |
| US20220128358A1 (en) | Smart Sensor Based System and Method for Automatic Measurement of Water Level and Water Flow Velocity and Prediction | |
| CN116485779B (en) | Adaptive wafer defect detection method and device, electronic equipment and storage medium | |
| CN113420673B (en) | Garbage classification method, device, equipment and storage medium | |
| CN111898610B (en) | Card unfilled corner detection method, device, computer equipment and storage medium | |
| CN110781853A (en) | Crowd abnormality detection method and related device | |
| CN110969213A (en) | Ship detection method and device based on fast RCNN and electronic equipment | |
| CN114241370A (en) | Intrusion identification method and device based on digital twin transformer substation and computer equipment | |
| CN114140745A (en) | Method, system, device and medium for detecting personnel attributes of construction site | |
| CN111123251B (en) | Target object detection method and device of radar | |
| WO2021056501A1 (en) | Feature point extraction method, movable platform and storage medium | |
| CN114155470A (en) | River channel area intrusion detection method, system and storage medium | |
| CN113392779A (en) | Crowd monitoring method, device, equipment and medium based on generation of confrontation network | |
| Ahmed et al. | An observation of vision based underwater object detection and tracking | |
| CN112101134A (en) | Object detection method and device, electronic device and storage medium | |
| CN111582012A (en) | Method and device for detecting small target ship | |
| JP2008078926A (en) | Image processor, image processing method, and image processing program |
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 |