CN112365524B - High-altitude parabolic real-time alarm system based on time sequence image - Google Patents
High-altitude parabolic real-time alarm system based on time sequence image Download PDFInfo
- Publication number
- CN112365524B CN112365524B CN202011248813.4A CN202011248813A CN112365524B CN 112365524 B CN112365524 B CN 112365524B CN 202011248813 A CN202011248813 A CN 202011248813A CN 112365524 B CN112365524 B CN 112365524B
- Authority
- CN
- China
- Prior art keywords
- alarm
- algorithm
- time
- network
- image
- 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
- 238000001514 detection method Methods 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 14
- 238000005070 sampling Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 8
- 238000012935 Averaging Methods 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 230000004297 night vision Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000004044 response Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/02—Details
- H04L12/10—Current supply arrangements
-
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Geometry (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a high-altitude parabolic real-time alarm system based on time sequence images, which relates to the technical field of high-altitude security of medium-high-rise buildings and comprises a camera acquisition module, an algorithm detection module and a client alarm module, wherein the modules are connected and communicated through a local area network. The invention has the advantages of high alarm detection rate, high alarm response speed, wide detection range of the network cameras, small use quantity, good privacy protection, good expansibility and very convenient operation.
Description
Technical Field
The invention relates to the technical field of high-altitude security and protection of medium-high-rise buildings, in particular to a high-altitude parabolic real-time alarm system based on time sequence images.
Background
With the rapid growth of population and the increase of economic level, the height of buildings is also increasing. Homes also transition from multi-storey to medium-high storeys. As medium and high rise homes increase, so does the overhead parabolic event.
The scheme of erecting the upward camera can help accurate positioning. But the method also brings new problems that a specific floor is difficult to determine in a short time, the tracing is time-consuming and labor-consuming, the coverage of a camera is small, the privacy of a resident is easy to violate, and the like.
Aiming at the defects, a learner provides a high-altitude parabolic evidence obtaining system based on digital image processing, a data processing module of the system adopts a frame difference method to extract foreground points of a moving object, and then the position of the moving object in an image is determined according to color information, so that the speed and the acceleration of the moving object are calculated, and finally a complete moving track is obtained.
But this solution has the following problems:
1. the existing high-altitude parabolic image processing evidence obtaining system extracts the motion foreground by using a frame difference method, however, a few frame difference methods are not described in detail, if the traditional two-frame difference method or the three-frame difference method is simply used, the applicability to the complex environment is poor, and the foreground points can be greatly interfered by noise. Such as rain drops falling, camera shake, leaf shake, etc.;
2. the existing high-altitude parabolic detection method generally obtains the complete track of the falling of the object by calculating the speed and the acceleration of the object, and the method has higher requirements on the continuity of the foreground point of the object, and once the foreground point is interrupted in the falling process, for example, the foreground point is influenced by the change of ambient light, accurate speed and acceleration information cannot be obtained.
Accordingly, those skilled in the art have been working to develop a high-altitude parabolic real-time warning system based on time series images.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, the present invention aims to solve the technical problems of small camera coverage, privacy safety of households, foreground abrupt change and interference of more noise in background modeling under complex environment, and the problem that the traditional pure camera scheme cannot give an alarm in real time.
The inventor firstly analyzes the problems existing in the existing camera monitoring scheme, redesigns the camera installation and deployment scheme for detecting the high altitude parabolic object, optimizes the installation distance of the camera, adjusts the upward elevation angle of the camera, and uses the camera as few as possible to monitor the whole coverage of the building; in order to extract a moving object, a self-designed band-pass filtering frame difference method is adopted, so that interference such as camera shake, cloud layer movement, light change and the like can be effectively avoided aiming at a high-altitude scene; in order to give an alarm in real time, a high-altitude parabolic detection algorithm based on a time sequence image is designed, position information of foreground points of a moving target in different time dimensions is randomly sampled and fitted with a second-order curve, a fitting score of the second-order curve is calculated according to a designed loss function, whether an alarm condition of the high-altitude parabolic is met is finally judged, and real-time alarm is carried out on the condition that the alarm condition is met.
In one embodiment of the invention, a high altitude parabolic real-time alarm system based on time sequence images is provided, which comprises a camera acquisition module, an algorithm detection module and a client alarm module, wherein the camera acquisition module is connected and communicated through a local area network, and is used for carrying out all-weather monitoring on the outer wall surface and the sky of the outer wall of a building, sending image data acquired in real time to the algorithm detection module and simultaneously storing the image data to the local area for backup; the algorithm detection module carries out modeling detection on the image data to obtain a second-order curve fitting result and a corresponding score of the parabolic trajectory, and sends alarm information and an alarm video to the client alarm module; the client alarm module realizes the operation of a user on the control of the camera acquisition module and the algorithm detection module, and checks alarm information and alarm video sent by the algorithm detection module.
Optionally, in the high-altitude parabolic real-time alarm system based on time sequence images in the foregoing embodiment, the camera acquisition module includes a plurality of network cameras and POE switches, POE (PowerOverEthernet) refers to switches supporting power over ethernet, and provides direct current for IP-based terminals (such as IP phones, wireless local area network access points AP, webcams, and the like) while transmitting data signals for the IP-based terminals without any modification to the existing cat.5 wiring infrastructure.
Further, in the high-altitude parabolic real-time alarm system based on the time sequence image in the embodiment, the front surface of the network camera faces the outer wall of the building, is 5-15 meters away from the building, the upward elevation angle is 60-80 degrees, two network camera detection areas cover 4-33 floors of a building, on one hand, the field of view of the network camera only can see the outer wall surface and the outer wall space of the building, and the problem of invading the privacy of residents does not exist; on the other hand, the network cameras with fewer numbers can realize the coverage of more floors, reduce the hardware cost and facilitate the camera management.
Further, in the high-altitude parabolic real-time alarm system based on the time sequence image in the embodiment, the resolution of the network camera is 500 ten thousand pixels, the network camera has a starlight night vision function, POE network cable power supply is supported, and the network camera works outdoors and is waterproof and sun-proof.
Further, in the high-altitude parabolic real-time alarm system based on the time sequence image in the above embodiment, the POE switch is connected to all the network cameras, the algorithm detection module and the client alarm module to form a local area network, and supplies power to all the network cameras.
Further, in the high-altitude parabolic real-time alarm system based on the time sequence image in the above embodiment, the local area network is used for ensuring that all the network cameras, and the algorithm detection module and the client alarm module are in the same network and can communicate with each other.
Optionally, in the high-altitude parabolic real-time alarm system based on time sequence images in the above embodiment, the local area network is consistent with an IP address network segment, a subnet mask and a gateway used by a cell where a user is located.
Further, in the high-altitude parabolic real-time alarm system based on the time sequence image in the above embodiment, each path of network camera is pulled to the algorithm detection module through the static IP address.
Optionally, in the high-altitude parabolic real-time alarm system based on the time sequence image in any embodiment, a detection algorithm of the algorithm detection module operates on an algorithm server, the algorithm server is an operation carrier of the high-altitude parabolic algorithm, and the computing performance of the algorithm server meets the requirement that multiple network cameras detect simultaneously and operate in real time.
Optionally, in the high altitude parabolic real-time alarm system based on time sequence image in any of the foregoing embodiments, the flow of the detection algorithm includes data acquisition, data processing, data storage, and alarm sending: data acquisition, namely pulling a video stream with the resolution of 1920 pixels by 1080 pixels from a network camera according to an RTSP protocol to obtain real-time image data for detection;
data processing, namely performing foreground detection of a moving object on the real-time image data, randomly sampling and fitting a second-order curve on a foreground point, evaluating a fitting effect, and finally judging whether the object is a throwing object or not;
data storage, namely storing alarm video clips with falling objects and storing all-weather complete original video data;
and sending an alarm, namely sending alarm information of the moment when the parabolic event occurs to an alarm module of the client, wherein the alarm information comprises the time when the parabolic event is detected, a camera static IP and an alarm video storage path.
Further, in the high altitude parabolic real-time alarm system based on time series images in the above embodiment, the data processing includes the following steps:
s100, extracting foreground images, namely extracting foreground images of a moving object from continuous frame images by utilizing a band-pass filtering frame difference algorithm, wherein continuous three-frame images are subjected to frame difference averaging to extract high-frequency signals, continuous seven-frame images are subjected to frame difference averaging to extract low-frequency signals, and the high-frequency signals are subtracted from the low-frequency signals to obtain a final foreground image. The band-pass filtering frame difference method can effectively reduce the lens shake of the network camera and the foreground noise point generated by raindrops falling, and reduce the influence of shadows generated by light change;
s200, preprocessing a foreground image, namely firstly using Gaussian filtering in image processing, morphological open operation and threshold segmentation to filter some discrete noise points in a final foreground image, then using connected domain operation to count the area of each connected domain, and if the area of each connected domain is larger than a threshold value, removing the connected domain for filtering an abnormally large-area connected domain in the foreground image, wherein all pixels in the rest connected domains are foreground points, namely the foreground points are pixels of a continuous image, wherein the next frame of image is changed relative to the previous frame of image;
s300, carrying out random three-point sampling on all foreground points in the x direction of the image and the y direction of the image respectively by using a RANSAC method to obtain (x, t) and (y, t) distribution;
s400, fitting a second-order curve, wherein random three-point sampling is used for fitting the second-order curve by using a RANSAC method;
s500, counting supporting points, wherein points close to the second-order curve are counted in all foreground points to serve as supporting points;
s600, screening a second-order curve according to three conditions of whether the number of the supporting points is larger than a threshold value, whether the acceleration change range of the center point of the supporting point at the adjacent moment is smaller than the threshold value and whether the moment category of the supporting point is larger than the threshold value, and screening the second-order curve meeting the three conditions;
s700, judging whether the maximum sampling times are reached, if so, continuing to step S800, otherwise, repeating the steps S300-S700;
s800, outputting a parabolic fitting result, wherein the fitting result is a fitting score of a second-order curve, and judging whether an alarm condition is met or not according to the fitting score. The fitting score is the percentage of the supporting points to all foreground points.
Optionally, in the high-altitude parabolic real-time alarm system based on time-series images in any embodiment, the operation of the camera acquisition module by the user includes logging in, playing, stopping, grouping, renaming, and screen capturing, and the operation of the algorithm detection module by the user includes turning on or off the algorithm.
The invention extracts the foreground by using a band-pass filtering frame difference algorithm, combines an innovative foreground point second-order curve fitting algorithm based on time sequence, has an alarm detection rate of more than 90 percent and supports object detection of 8 pixels with minimum resolution; the alarm response speed is high, once a high-altitude parabolic event occurs, an alarm message can be received within one second, and a stored alarm video can be checked and verified at the client alarm module; the detection of a daytime color scene and a night infrared scene is supported, and the uninterrupted work of 24 hours in the whole day is ensured; the network cameras have wide detection range and small use quantity, can realize floor coverage of two units from 4 layers to 33 layers only by 2 cameras, and have good privacy protection; the invention has good expansibility, can work by supporting the access of the additional network cameras to the local area network, and has very convenient operation.
The conception, specific structure, and technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, features, and effects of the present invention.
Drawings
FIG. 1 is a topology diagram illustrating a time series image based high altitude parabolic real time alert system in accordance with an exemplary embodiment;
FIG. 2 is a diagram illustrating camera deployment according to an exemplary embodiment;
FIG. 3 is a flowchart illustrating a detection algorithm according to an exemplary embodiment;
FIG. 4 is a flowchart illustrating data processing according to an example embodiment;
FIG. 5 is a flowchart illustrating extraction of foreground images according to an example embodiment;
fig. 6 is a flowchart illustrating foreground image preprocessing according to an exemplary embodiment.
Detailed Description
The following description of the preferred embodiments of the present invention refers to the accompanying drawings, which make the technical contents thereof more clear and easy to understand. The present invention may be embodied in many different forms of embodiments and the scope of the present invention is not limited to only the embodiments described herein.
In the drawings, like structural elements are referred to by like reference numerals and components having similar structure or function are referred to by like reference numerals. The dimensions and thickness of each component shown in the drawings are arbitrarily shown, and the present invention is not limited to the dimensions and thickness of each component. The thickness of the components is schematically and appropriately exaggerated in some places in the drawings for clarity of illustration.
The inventor designs a high altitude parabolic real-time alarm system based on time sequence images, which comprises a camera acquisition module, an algorithm detection module and a client alarm module, wherein the modules are connected and communicated through a local area network as shown in figure 1.
The camera acquisition module monitors the outer wall surface and the sky of the outer wall of the building in all weather, and sends image data acquired in real time to the algorithm detection module, and meanwhile, the image data is stored locally for backup; the camera acquisition module designed by the inventor comprises a plurality of network cameras and POE switches, POE (PowerOverEthernet) refers to switches supporting power over Ethernet, and provides direct current for IP-based terminals (such as IP telephones, wireless local area network Access Points (AP), network cameras and the like) while transmitting data signals under the condition that the existing Ethernet Cat.5 wiring infrastructure is not changed. The front of the network cameras are arranged towards the outer wall of the building, as shown in fig. 2, the distance from the front of the network cameras to the building is 5-15 m, the upward elevation angle is 60-80 degrees, and the two network camera detection areas cover 4-33 floors of a building; on the other hand, the network cameras with fewer numbers can realize the coverage of more floors, reduce the hardware cost and facilitate the camera management. The network camera is preferably 500-ten-thousand-pixel in resolution, has starlight night vision function, supports POE network cable power supply, works outdoors and is waterproof and sun-proof; and the POE switch is connected with all the network cameras, the algorithm detection module and the client alarm module to form a local area network and supply power to all the network cameras. The local area network is used for ensuring that all network cameras, the algorithm detection module and the client alarm module are in the same network and can communicate with each other, the local area network is consistent with an IP address network segment, a subnet mask and a gateway used by a cell where a user is located, and each path of network camera is pulled to the algorithm detection module through a static IP address.
The algorithm detection module carries out modeling detection on the image data to obtain a second-order curve fitting result and a corresponding score of the parabolic trajectory, and sends alarm information and alarm video to the client alarm module. The detection algorithm of the algorithm detection module operates on an algorithm server, the algorithm server is an operation carrier of the high-altitude parabolic algorithm, and the calculation performance of the algorithm server meets the requirement that the multipath network cameras detect simultaneously and operate in real time.
The inventor designs the flow of the detection algorithm, as shown in fig. 3, including data acquisition, data processing, data storage, alarm sending, specifically as follows:
data acquisition, namely pulling a video stream with the resolution of 1920 pixels by 1080 pixels from a network camera according to an RTSP protocol to obtain real-time image data for detection;
data processing, namely performing foreground detection of a moving object on the real-time image data, randomly sampling and fitting a second-order curve on a foreground point, evaluating a fitting effect, and finally judging whether the object is a throwing object or not; the method specifically comprises the following steps, as shown in fig. 4:
s100, extracting a foreground image, namely extracting the foreground image of the moving object from continuous frame images by utilizing a band-pass filtering frame difference algorithm, wherein continuous three frame images are subjected to frame difference averaging to extract a high-frequency signal, continuous seven frame images are subjected to frame difference averaging to extract a low-frequency signal, and the high-frequency signal is subtracted from the low-frequency signal to obtain the foreground image. The band-pass filtering frame difference method can effectively reduce the foreground noise points generated by lens shake and raindrop falling of the network camera, and reduce the influence of shadows generated by light change;
s200, preprocessing a foreground image, namely, as shown in FIG. 6, firstly using Gaussian filtering in image processing, morphological open operation and threshold segmentation filtering to obtain a plurality of discrete noise points in the foreground image, then using connected domain operation to count the area of each connected domain, and if the area of the connected domain is larger than a threshold value, removing the connected domain, wherein the connected domain is used for filtering an abnormal large-area connected domain in the foreground image, and all pixel points in the rest connected domains are foreground points;
s300, carrying out random three-point sampling on foreground points in the x direction of the image and the y direction of the image respectively by using a RANSAC method to obtain (x, t) and (y, t) distribution;
s400, fitting a second-order curve, wherein random three-point sampling is used for fitting the second-order curve by using a RANSAC method;
s500, counting supporting points, wherein points close to the second-order curve are counted in all foreground points to serve as supporting points;
s600, screening a second-order curve according to three conditions of whether the number of the supporting points is larger than a threshold value, whether the acceleration change range of the center point of the supporting point at the adjacent moment is smaller than the threshold value and whether the moment category of the supporting point is larger than the threshold value, and screening the second-order curve meeting the three conditions;
s700, judging whether the maximum sampling times are reached, if so, continuing to step S800, otherwise, repeating the steps S300-S700;
s800, outputting a parabolic fitting result, wherein the fitting result is a fitting score of a second-order curve, judging whether an alarm condition is met or not according to the fitting score, and the fitting score is the percentage of the supporting points to all the foreground points.
Data storage, namely storing alarm video clips with falling objects and storing all-weather complete original video data;
and sending an alarm, namely sending alarm information of the moment when the parabolic event occurs to an alarm module of the client, wherein the alarm information comprises the time when the parabolic event is detected, a camera static IP and an alarm video storage path.
The client alarm module realizes the operation of a user on the control of the camera acquisition module and the algorithm detection module, and checks alarm information and alarm video sent by the algorithm detection module. The operation of the camera acquisition module by the user comprises logging, playing, stopping, grouping, renaming and screen capturing, and the operation of the algorithm detection module by the user comprises starting or closing the algorithm.
The foregoing describes in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention by one of ordinary skill in the art without undue burden. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by the person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (7)
1. The high-altitude parabolic real-time alarm system based on the time sequence image is characterized by comprising a camera acquisition module, an algorithm detection module and a client alarm module, wherein the camera acquisition module, the algorithm detection module and the client alarm module are connected and communicated through a local area network, the camera acquisition module monitors the outer wall surface and the sky of a building in all weather, and image data acquired in real time is sent to the algorithm detection module and is stored locally for backup; the algorithm detection module carries out modeling detection on the image data to obtain a second-order curve fitting result and a corresponding score of a parabolic trajectory, and sends alarm information and an alarm video to the client alarm module; the client alarm module realizes the operation of a user on the control of the camera acquisition module and the algorithm detection module, and checks the alarm information and the alarm video;
the detection algorithm of the algorithm detection module operates on an algorithm server, the algorithm server is an operation carrier of the high-altitude parabolic algorithm, and the flow of the detection algorithm comprises data acquisition, data processing, data storage and alarm sending; the data processing comprises the following steps:
s100, extracting foreground images, namely extracting foreground images of a moving object from continuous frame images by utilizing a band-pass filtering frame difference algorithm, wherein continuous three-frame images are subjected to frame difference averaging to extract high-frequency signals, continuous seven-frame images are subjected to frame difference averaging to extract low-frequency signals, and the high-frequency signals are subtracted from the low-frequency signals to obtain a final foreground image;
s200, preprocessing a foreground image, namely filtering a plurality of discrete noise points in the final foreground image by using Gaussian filtering in image processing, morphological open operation and threshold segmentation, and counting the area of each connected domain by using connected domain operation, wherein if the area of each connected domain is larger than a threshold value, the connected domain is removed and used for filtering an abnormal large-area connected domain in the foreground image, and all pixel points in the rest connected domains are foreground points;
s300, carrying out random three-point sampling on foreground points in the x direction of the image and the y direction of the image respectively by using a RANSAC method to obtain (x, t) and (y, t) distribution;
s400, fitting a second-order curve, wherein random three-point sampling is used for fitting the second-order curve by using a RANSAC method;
s500, counting supporting points, wherein points close to the second-order curve are counted in all foreground points to serve as supporting points;
s600, screening a second-order curve according to three conditions of whether the number of the supporting points is larger than a threshold value, whether the acceleration change range of the center point of the supporting point at the adjacent moment is smaller than the threshold value and whether the moment category of the supporting point is larger than the threshold value, and screening the second-order curve meeting the three conditions;
s700, judging whether the maximum sampling times are reached, if the RANSAC three-point sampling times reach the maximum sampling times, continuing to the next step S800, otherwise, repeating the steps S300-S700;
s800, outputting a parabolic fitting result, wherein the fitting result is a fitting score of a second-order curve, and judging whether an alarm condition is met or not according to the fitting score.
2. The time-series image-based high-altitude parabolic real-time alarm system according to claim 1, wherein the camera acquisition module comprises a plurality of network cameras and a POE switch.
3. The time sequence image based high altitude parabolic real-time alarm system according to claim 2, wherein the front of the network camera faces the outer wall of a building, is 5-15 m away from the building, has an upward elevation angle of 60-80 degrees, and two network camera detection areas cover 4-33 floors of a building.
4. The time sequence image based high altitude parabolic real-time alarm system according to claim 2 or 3, wherein the resolution of the network camera is 500 ten thousand pixels, the network camera has a starlight night vision function, and supports POE network cable power supply, works outdoors and is waterproof and sun-proof.
5. The time sequence image based high altitude parabolic real-time alarm system according to claim 2, wherein the POE switch is connected with all the network cameras, the algorithm detection module and the client alarm module to form the local area network, and supplies power to all the network cameras.
6. The time-series image-based high-altitude parabolic real-time alarm system according to claim 5, wherein the local area network ensures that all the network cameras, the algorithm detection module and the client alarm module are in the same network and can communicate with each other.
7. The time series image based high altitude parabolic real time alarm system as claimed in claim 5, wherein said local area network is consistent with the IP address network segment, subnet mask, gateway used by the cell in which the user is located.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011248813.4A CN112365524B (en) | 2020-11-10 | 2020-11-10 | High-altitude parabolic real-time alarm system based on time sequence image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011248813.4A CN112365524B (en) | 2020-11-10 | 2020-11-10 | High-altitude parabolic real-time alarm system based on time sequence image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112365524A CN112365524A (en) | 2021-02-12 |
CN112365524B true CN112365524B (en) | 2024-03-29 |
Family
ID=74509316
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011248813.4A Active CN112365524B (en) | 2020-11-10 | 2020-11-10 | High-altitude parabolic real-time alarm system based on time sequence image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112365524B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112926444A (en) * | 2021-02-24 | 2021-06-08 | 北京爱笔科技有限公司 | Method and device for detecting parabolic behavior |
CN112927201A (en) * | 2021-02-24 | 2021-06-08 | 北京爱笔科技有限公司 | Curve detection method and device |
CN113990009A (en) * | 2021-10-29 | 2022-01-28 | 西安文理学院 | Building falling object intelligent detection and interception system based on CPU and control method thereof |
CN114339367B (en) * | 2021-12-29 | 2023-06-27 | 杭州海康威视数字技术股份有限公司 | Video frame processing method, device and equipment |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103929592A (en) * | 2014-04-22 | 2014-07-16 | 杭州道联电子技术有限公司 | All-dimensional intelligent monitoring equipment and method |
US10078902B1 (en) * | 2015-08-27 | 2018-09-18 | Hrl Laboratories, Llc | Fast robust method for compensating ego-translations and detecting independent moving objects in video captured with a moving camera |
CN109164443A (en) * | 2018-08-27 | 2019-01-08 | 南京微达电子科技有限公司 | Rail track foreign matter detecting method and system based on radar and image analysis |
CN109309811A (en) * | 2018-08-31 | 2019-02-05 | 中建三局智能技术有限公司 | A kind of throwing object in high sky detection system based on computer vision and method |
CN110619735A (en) * | 2019-10-29 | 2019-12-27 | 宋春雨 | System for monitoring and alarming falling object |
CN110853295A (en) * | 2019-11-12 | 2020-02-28 | 江西赣鄱云新型智慧城市技术研究有限公司 | High-altitude parabolic early warning method and device |
CN111079663A (en) * | 2019-12-19 | 2020-04-28 | 深圳云天励飞技术有限公司 | High-altitude parabolic monitoring method and device, electronic equipment and storage medium |
CN111260693A (en) * | 2020-01-20 | 2020-06-09 | 北京中科晶上科技股份有限公司 | Detection method of high-altitude object throwing |
CN111488799A (en) * | 2020-03-13 | 2020-08-04 | 安徽小眯当家信息技术有限公司 | Falling object identification method and system based on image identification |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10803598B2 (en) * | 2017-06-21 | 2020-10-13 | Pankaj Chaurasia | Ball detection and tracking device, system and method |
-
2020
- 2020-11-10 CN CN202011248813.4A patent/CN112365524B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103929592A (en) * | 2014-04-22 | 2014-07-16 | 杭州道联电子技术有限公司 | All-dimensional intelligent monitoring equipment and method |
US10078902B1 (en) * | 2015-08-27 | 2018-09-18 | Hrl Laboratories, Llc | Fast robust method for compensating ego-translations and detecting independent moving objects in video captured with a moving camera |
CN109164443A (en) * | 2018-08-27 | 2019-01-08 | 南京微达电子科技有限公司 | Rail track foreign matter detecting method and system based on radar and image analysis |
CN109309811A (en) * | 2018-08-31 | 2019-02-05 | 中建三局智能技术有限公司 | A kind of throwing object in high sky detection system based on computer vision and method |
CN110619735A (en) * | 2019-10-29 | 2019-12-27 | 宋春雨 | System for monitoring and alarming falling object |
CN110853295A (en) * | 2019-11-12 | 2020-02-28 | 江西赣鄱云新型智慧城市技术研究有限公司 | High-altitude parabolic early warning method and device |
CN111079663A (en) * | 2019-12-19 | 2020-04-28 | 深圳云天励飞技术有限公司 | High-altitude parabolic monitoring method and device, electronic equipment and storage medium |
CN111260693A (en) * | 2020-01-20 | 2020-06-09 | 北京中科晶上科技股份有限公司 | Detection method of high-altitude object throwing |
CN111488799A (en) * | 2020-03-13 | 2020-08-04 | 安徽小眯当家信息技术有限公司 | Falling object identification method and system based on image identification |
Non-Patent Citations (1)
Title |
---|
基于双椭圆空间模型的校园视频监控高空抛物分析的应用;宁家锋;电子技术与软件工程;20180608(第11期);78-79 * |
Also Published As
Publication number | Publication date |
---|---|
CN112365524A (en) | 2021-02-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112365524B (en) | High-altitude parabolic real-time alarm system based on time sequence image | |
CN100504942C (en) | Module set of intelligent video monitoring device, system and monitoring method | |
CN101626489B (en) | Method and system for intelligently identifying and automatically tracking objects under unattended condition | |
Lin et al. | A vision-based parking lot management system | |
KR101853903B1 (en) | Invasion detecting method and system including CCTV, drone and fiber to the fence | |
CN105574468B (en) | Video flame detection method, device and system | |
WO2007015631A1 (en) | Smart video monitoring system and method communicating with auto-tracking radar system | |
CN112800953A (en) | High-altitude parabolic detection, tracking and alarming system and method based on computer vision | |
CN109948474A (en) | AI thermal imaging all-weather intelligent monitoring method | |
CN110049290A (en) | Public building intelligent monitor system | |
Fawzi et al. | Embedded real-time video surveillance system based on multi-sensor and visual tracking | |
KR102298063B1 (en) | Smart security drone system linked to cctv | |
KR20220000226A (en) | A system for providing a security surveillance service based on edge computing | |
CN107231546A (en) | The household monitoring system of autonomous tracking moving characteristic based on cloud security service device | |
CN112800846A (en) | High-altitude parabolic monitoring method and device, electronic equipment and storage medium | |
CN112257683A (en) | Cross-mirror tracking method for vehicle running track monitoring | |
CN109841022B (en) | Target moving track detecting and alarming method, system and storage medium | |
Ellis | Multi-camera video surveillance | |
Tamaki et al. | An automatic compensation system for unclear area in 360-degree images using pan-tilt camera | |
KR102193497B1 (en) | A Safety Network System Using Automatic and Remote Control of Bus Ride Stations by Using IOT Technology | |
CN110913333B (en) | Outdoor pedestrian flow warning method based on Wi-Fi probe | |
Koutsia et al. | Intelligent traffic monitoring and surveillance with multiple cameras | |
CN113740847A (en) | Multi-radar cooperative detection alarm system based on humanoid target recognition | |
KR20220000424A (en) | A camera system for providing a intelligent security surveillance service based on edge computing | |
KR20220000221A (en) | A camera apparatus for providing a intelligent security surveillance service based on edge computing |
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 | ||
CB02 | Change of applicant information |
Address after: 315048 room 5-1-1, building 22, East Zone, Ningbo new material innovation center, high tech Zone, Ningbo, Zhejiang Province Applicant after: Ningbo Boden Intelligent Technology Co.,Ltd. Address before: Room 1002, 288, 296 Baihe Road, hi tech Zone, Ningbo City, Zhejiang Province Applicant before: NINGBO BODEN INTELLIGENT TECHNOLOGY Co.,Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |