CN114488337A - High-altitude parabolic detection method and device - Google Patents
High-altitude parabolic detection method and device Download PDFInfo
- Publication number
- CN114488337A CN114488337A CN202210121063.7A CN202210121063A CN114488337A CN 114488337 A CN114488337 A CN 114488337A CN 202210121063 A CN202210121063 A CN 202210121063A CN 114488337 A CN114488337 A CN 114488337A
- Authority
- CN
- China
- Prior art keywords
- parabolic
- fitting
- data
- track
- pixel
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
Abstract
The application relates to a high-altitude parabolic detection method, which relates to the field of high-altitude parabolic detection and comprises an image acquisition step, wherein real-time image data are acquired from a residential building to be detected; a pixel movement detection step, namely determining pixel points or pixel blocks which move under the current static background; a parabolic analysis step, wherein the motion track of the falling object is determined, and the floor or the floor range from which the falling object comes is determined; and an alarm recording step, namely alarming the suspected high altitude parabolic phenomenon, recording and storing the related images and videos, and uploading the related images and videos to a management platform. The method has the effect of facilitating the rapid determination of the high-altitude parabolic responsible person.
Description
Technical Field
The present application relates to the field of high altitude parabolic detection, and in particular, to a high altitude parabolic detection method, apparatus, server, and readable storage medium.
Background
At present, with the continuous promotion of urbanization, more and more people live and work in high-rise buildings. The high-rise building brings convenience to life and work of people, and meanwhile, the life safety of pedestrians around the high-rise building is seriously threatened by high-altitude throwing. In order to clearly determine persons responsible in the high-altitude parabolic event and finally achieve the purpose of avoiding the high-altitude parabolic phenomenon, certain high-altitude parabolic detection equipment is arranged in the existing high-rise building.
The high-altitude parabolic detection equipment in the related art generally comprises a camera arranged on the ground, the whole building is monitored through the camera on the ground, and after a high-altitude parabolic event occurs, the recorded image file is manually called to be analyzed, so that a specific high-altitude parabolic floor is judged, and an accident responsible person is determined.
In the process of practical use, the inventor thinks that due to the fact that a common camera is limited in monitoring range and only has a video recording function, after a high-altitude parabolic event occurs, the high-altitude parabolic time needs to be determined manually, video recording segments are called manually and analyzed frame by frame through naked eyes, steps are complex, a person in charge cannot be determined at the first time, and a lot of uncertainty is brought to accident handling. And because the camera is arranged on the ground, the specific floor generating the high-altitude parabolic object can not be accurately determined only from the video shot by the camera for the high-altitude parabolic phenomenon generated on the higher floor, so that the responsible person can not be quickly and accurately determined for some high-altitude parabolic accidents generated by accidents.
Disclosure of Invention
In order to solve the problem that the existing high-altitude parabolic detection equipment is difficult to quickly determine a person in charge, the application provides the high-altitude parabolic detection equipment and the detection method thereof.
The technical scheme adopted by the high-altitude parabolic detection method, the high-altitude parabolic detection device, the server and the readable storage medium is as follows:
in a first aspect, the present application provides a high altitude parabolic detection method, which adopts the following technical scheme:
a high altitude parabolic detection method comprises the following steps:
an image acquisition step, wherein real-time image data are acquired from a residential building to be detected;
a pixel movement detection step, namely determining pixel points or pixel blocks which move under the current static background;
a parabolic analysis step, namely determining the motion track of the falling object and determining the floor or the floor range from which the falling object comes;
and an alarm recording step, namely alarming the suspected high altitude parabolic phenomenon, recording and storing the related images and videos, and uploading the related images and videos to a management platform.
Preferably, the pixel movement detecting step includes the steps of:
an image receiving step of receiving image data from an image acquisition device and temporarily storing the image data in an image registering unit;
a background identification step, wherein a static background extraction algorithm is adopted to carry out background identification on the currently collected image data to obtain background data, and a three-dimensional background model is established by the background data;
dividing pixel blocks, namely dividing all pixels of the current image data into a plurality of detection pixel blocks in a longitudinal averaging and transverse averaging mode;
and a detection step, namely setting a marked pixel block, determining a changed pixel area in a mode of comparing previous and next frames when background data is changed, taking the area as a parabolic identification area, overlapping the center of the parabolic identification area with the center of the marked pixel block, and then taking the current image data as parabolic data.
Preferably, the parabolic analyzing step comprises the steps of:
a judging step, namely analyzing the parabolic data, reserving the parabolic data meeting the judging conditions by setting a plurality of judging conditions, deleting the parabolic data not meeting the judging conditions, and finally obtaining a track formed by all marked pixel blocks as a parabolic motion track by taking a three-dimensional background model as a reference;
and a track analysis step, wherein parabolic fitting is carried out on the parabolic motion track to obtain a track fitting line after fitting, the track fitting line is complemented and is intersected with the ground of the three-dimensional background model and the plane where the residential building is located to respectively obtain a fitting falling point and a fitting parabolic point, a fitting falling point area and a fitting parabolic point area are obtained by taking the fitting falling point and the fitting parabolic point as centers, the fitting parabolic area is projected into the three-dimensional background model to obtain a corresponding parabolic floor or parabolic floor range, at least three parabolic fitting algorithms are adopted to obtain the track fitting line, and the final fitting falling point, fitting parabolic point area and fitting parabolic point area are a set of results obtained by each track fitting line.
Preferably, the determination step includes a plurality of sub-determination steps.
Preferably, in the step of analyzing the trajectory, at least three different parabolic fitting algorithms are adopted to obtain a trajectory fit line, and the final fitting falling point, fitting parabolic point, fitting falling point area and fitting parabolic point area are all a set of results obtained by each trajectory fit line.
Preferably, the alarm recording step includes:
an alarming step, namely generating an alarming signal after the parabolic motion track is generated in the judging step, and transmitting the alarming signal to a person in charge related to the residential building property;
and a record uploading step, namely generating a plurality of pieces of record data, and performing cloud encryption storage and local encryption storage on the record data.
Preferably, the alarm recording step further comprises a strong reminding step, and the strong reminding step is used for ensuring that the related responsible person receives the alarm signal and generates feedback.
By adopting the technical scheme, the method and the device can be used for collecting and analyzing the images near the residential building and analyzing the collected images, wherein the analysis mainly comprises two parts, namely a pixel movement detection step and a parabolic analysis step. When the high-altitude parabolic phenomenon occurs in the residential building, the collected images can change due to the high-altitude parabolic phenomenon, the pixel movement detection step is to respond to the change in time, and the changed pixels are subjected to mathematical modeling processing, so that the connection between the changed images and an object which actually generates parabolic motion is conveniently established. In practical situations, it is detected that the change of the image pixel is not necessarily the high-altitude parabolic phenomenon, so that the changed pixel needs to be further analyzed by a parabolic analysis step, the image part obviously not corresponding to the high-altitude parabolic phenomenon is removed by the determination step, the rest image is analyzed again, and then the parabolic motion trajectory is generated. The final fitting drop point, the fitting parabolic point, the fitting drop point area and the fitting parabolic point area can be obtained by fitting and completing the parabolic motion trajectory, so that the floor where high-altitude parabolic occurs can be quickly determined, the range is quickly reduced, and a responsible person is determined. And after the parabolic phenomenon is determined, the alarm information can be timely sent to the related responsible person through the alarm recording step, and the related image and video data are recorded and uploaded, so that the high-altitude parabolic responsible person can be further determined through subsequent use.
In the processing mode, the analysis processing of the images is carried out at the front end in a centralized mode, namely, the shot images do not need to be transmitted to the cloud server through the network and then are analyzed and processed, the uploading and reading processes of the intermediate images are reduced, the analysis and processing efficiency of the images is greatly improved, and the determination of the high-altitude person with parabolic responsibility can be realized in a shorter time.
In a second aspect, the present application provides a high altitude parabolic detection apparatus, which adopts the following technical scheme:
a high altitude parabolic detection apparatus comprising:
the image acquisition and analysis unit is used for acquiring real-time image data of the residential building to be detected;
the pixel movement detection unit is used for determining pixel points or pixel blocks which move under the current static background;
the parabolic analysis unit is used for determining the motion track of the falling object and determining the floor or the floor range from which the falling object comes;
and the alarm recording unit is used for alarming the suspected high-altitude parabolic phenomenon, recording and storing the related images and videos and uploading the related images and videos to the management platform.
In a third aspect, the present application provides a high altitude parabolic detection server, which adopts the following technical scheme:
a high altitude parabolic detection server comprising a memory, a processor and a computer program stored on the memory and executable in the processor, wherein the processor implements the steps of a high altitude parabolic detection method as described above when executing the program.
In a fourth aspect, the present application provides a readable storage medium, which adopts the following technical solutions:
a readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the steps of a high altitude parabolic detection method as described above.
In summary, the present application includes at least one of the following beneficial technical effects:
1. through the arrangement of the image acquisition step, the pixel movement detection step and the parabola analysis step, the effect of quickly processing the image information and quickly judging whether the high-altitude parabola phenomenon is generated or not can be achieved.
Drawings
Fig. 1 is a schematic flow chart of a high altitude parabolic detection method according to embodiment 1 of the present application.
Fig. 2 is a schematic flow chart of a high altitude parabolic detection method according to embodiment 1 of the present application.
Fig. 3 is a schematic flow chart of a high altitude parabolic detection server according to embodiment 3 of the present application.
Reference number legend, 11, bus; 12. a receiver; 13. a processor; 14. a transmitter; 15. a memory; 16. a bus interface.
Detailed Description
The present application is described in further detail below with reference to figures 1-3.
Example 1
The embodiment of the application discloses a high-altitude parabolic detection method. Referring to fig. 1, the high altitude parabolic detection method comprises an image acquisition step, a pixel movement detection step, a parabolic analysis step and an alarm recording step. The method comprises an image acquisition step, a pixel movement detection step, a parabolic analysis step and a network alarm recording step, wherein the image acquisition step acquires real-time image data of a residential building to be detected, the acquired image is temporarily and locally stored, the pixel movement detection step and the parabolic analysis step directly read the data from the local storage for analysis, the parabolic phenomenon is determined after the analysis, and the network alarm recording step is realized through the network.
Referring to fig. 1 and 2, the pixel movement detecting step includes the following steps:
an image receiving step of receiving image data from the image acquisition device and temporarily storing the image data in an image registering unit;
a background identification step, wherein a static background extraction algorithm is adopted to carry out background identification on the currently collected image data to obtain background data, and a three-dimensional background model is established by the background data;
dividing pixel blocks, namely dividing all pixels of the current image data into a plurality of detection pixel blocks in a longitudinal averaging and transverse averaging mode;
and a detection step, namely setting a marked pixel block, determining a changed pixel area in a mode of comparing previous and next frames when background data is changed, taking the area as a parabolic identification area, overlapping the center of the parabolic identification area with the center of the marked pixel block, and then taking the current image data as parabolic data.
In this embodiment, the original resolution of the image data of the capturing device is 1920 × 1080, and in the pixel block division step, each image data is divided equally into 32 × 30 detection pixel blocks, that is, each detection pixel block has a size of 60 × 36, and each detection pixel block includes 2160 pixels. Each of the marked pixel blocks has a size of 4 × 4, whereby higher detection accuracy can be achieved. And because the image data is divided into a plurality of detection pixel blocks, when pixel movement detection is carried out, only the detection pixel blocks with pixel changes need to be analyzed and recorded, and other detection pixel blocks without pixel changes can not be analyzed, so that the amount of images to be analyzed is greatly reduced, and the analysis speed is improved.
Referring to fig. 1 and 2, the parabolic analyzing step includes the steps of:
a judging step, namely analyzing the parabolic data, reserving the parabolic data meeting the judging conditions by setting a plurality of judging conditions, deleting the parabolic data not meeting the judging conditions, and finally obtaining a track formed by all marked pixel blocks as a parabolic motion track by taking a three-dimensional background model as a reference;
and a track analysis step, wherein parabolic fitting is carried out on the parabolic motion track to obtain a track fitting line after fitting, the track fitting line is complemented and is intersected with the ground of the three-dimensional background model and the plane where the residential building is located to respectively obtain a fitting falling point and a fitting parabolic point, a fitting falling point area and a fitting parabolic point area are obtained by taking the fitting falling point and the fitting parabolic point as centers, the fitting parabolic area is projected into the three-dimensional background model to obtain a corresponding parabolic floor or parabolic floor range, at least three parabolic fitting algorithms are adopted to obtain the track fitting line, and the final fitting falling point, fitting parabolic point area and fitting parabolic point area are a set of results obtained by each track fitting line.
Referring to fig. 1 and 2, the determining step includes a plurality of sub-determining steps, respectively:
a first judgment step of analyzing the parabolic data, and when the number of marked pixel blocks detected by the same detection pixel block in a certain first judgment duration is larger than a first judgment threshold, deleting the batch of parabolic data from the image registration unit and marking a time period corresponding to the deleted batch of parabolic data;
a second determination step, in which the residual parabolic data after the determination by the first determination module is analyzed, a coordinate value of a marking pixel block in the current parabolic data in the vertical direction is determined by taking a three-dimensional background model determined in the background data as a reference, the coordinate value is taken as a first characteristic value of the current parabolic data, the vertical downward direction is taken as the positive direction of the vertical direction in the three-dimensional background model, and when the first characteristic value of the parabolic data of the next frame is smaller than the first characteristic value of the parabolic data of the previous frame, the parabolic data of the next frame is deleted from the image registration unit, and the time point of the parabolic data deleted in the second determination module is marked;
a third judging step, namely analyzing the residual parabolic data after the judgment of the second judging module, wherein the module is provided with a third judging threshold and a third judging time length, dividing the residual parabolic data into a plurality of groups by taking the third judging time length as a unit, picking out groups with the number of the parabolic data of two frames and more than two frames in the parabolic data groups as a third judging group, and when the number of the third judging group is more than or equal to the third judging threshold, completely retaining the residual parabolic data in the image registering unit, otherwise deleting the parabolic data and marking the time point of the deleted parabolic data;
and a fourth judgment step of analyzing the residual parabolic data judged by the third judgment module, wherein the module is provided with a fourth judgment threshold, the three-dimensional coordinate value of the marked pixel block in the current parabolic data is determined by taking the three-dimensional background model as a reference, the parabolic motion track of the marked pixel block is obtained, the parabolic motion track is subjected to straight line fitting to obtain a track characteristic line, the track characteristic line is intersected with the vertical direction of the three-dimensional background model to obtain a track characteristic included angle, when the value of the track characteristic included angle is smaller than the fourth judgment threshold, the residual parabolic data are marked, and otherwise, the residual parabolic data are deleted from the image registration unit.
The first determination step is based on the fact that if the high altitude parabolic phenomenon occurs, the changed pixel blocks are detected to pass through a plurality of different detection pixel blocks in a short time, and therefore parabolic data which do not meet the conditions can be removed quickly only by setting a proper first determination time length and a proper first determination threshold value.
The second determination step is based on the determination that if the high altitude parabolic phenomenon occurs, the changed pixel block is detected to move from top to bottom, so that the parabolic data which do not meet the condition can be quickly removed by calculating the size of the first characteristic value and analyzing the change trend of the first characteristic value.
The third determination step is based on the fact that if the high-altitude parabolic phenomenon occurs, the motion trajectory of the pixel block which changes should be continuous, and therefore discontinuous parabolic data can be removed by setting a suitable third determination threshold and a suitable third determination duration.
The fourth determination step is based on the determination that, if the high altitude parabolic phenomenon occurs, the high altitude parabolic objects all perform free-fall motion, that is, the objects have no initial velocity or only a small initial velocity, and the objects need to have the ability to overcome the influence of air resistance. If the object has a larger initial velocity in the horizontal direction, the secondary high-altitude parabolic probability is intentional, and if actual harm is generated, the person in charge can be found and determined quickly by calling on-site monitoring. If the mass of the object is too small or the surface area of the object is too large, the object is easily influenced by large air resistance in the falling process, and casualties cannot be caused even if the object falls to the ground, so that the trajectory characteristic included angle is limited by setting a proper fourth judgment threshold value, and in the embodiment, only parabolic data of the trajectory characteristic included angle within 30 degrees is kept.
By the aid of the judging step, useless data in a large amount of parabolic data can be quickly discriminated and removed, and accordingly invalid alarm frequency is effectively reduced.
Referring to fig. 1 and 2, in the trajectory analysis step, at least three different parabolic fitting algorithms are required to obtain trajectory fit lines, and the final fitting falling point, fitting parabolic point, fitting falling point area, and fitting parabolic point area are all sets of results obtained by each trajectory fit line. By adopting a plurality of different parabolic fitting algorithms, the situation that the final result has larger deviation caused by errors existing in detection can be reduced as much as possible. In order to reduce errors generated in the process of determining the responsible person, the final result obtained in the trajectory analysis step is only used as a reference result to help the responsible person to narrow the range and provide sufficient judgment basis.
Referring to fig. 1 and 2, the alarm recording step includes:
an alarming step, namely generating an alarming signal after the parabolic motion track is generated in the judging step, and transmitting the alarming signal to a person in charge related to the residential building property;
a strong reminding step, wherein the strong reminding step is used for ensuring that the related responsible person receives the alarm signal and generates feedback;
and a record uploading step, namely generating a plurality of pieces of record data, and performing cloud encryption storage and local encryption storage on the record data.
Referring to fig. 1 and 2, in the strong reminding step, after the alarm step occurs, and when the relevant responsible person does not feed back the alarm signal for many times, the relevant responsible person needs to arrive at the scene where the high altitude object occurs within a specified time after receiving the alarm signal, and inputs and uploads specific responsible person information after investigation, and if the relevant responsible person does not feed back the alarm signal correctly, the responsible person is forcibly reminded to process in the strong reminding step in the forms of sound, light, electricity and the like, and the condition that the responsible person does not process the alarm signal for a long time is recorded.
Referring to fig. 1 and 2, in the recording and uploading step, the recorded data includes first recorded data and second recorded data, wherein a plurality of single-frame images of the parabolic data are selected to obtain the first recorded data, and partial continuous image videos before and after a time period corresponding to the parabolic data are captured to obtain the second recorded data. The recorded data needs to be encrypted and stored in two modes of local storage and cloud storage, so that the occurrence of data loss or tampering is effectively reduced.
The implementation principle of the high-altitude parabolic detection method in the embodiment of the application is as follows:
the method comprises the steps of collecting and analyzing images near a residential building, and analyzing the collected images, wherein the analyzing process mainly comprises two parts, namely a pixel movement detection step and a parabolic analysis step. When the high-altitude parabolic phenomenon occurs in the residential building, the collected images can change due to the high-altitude parabolic phenomenon, the pixel movement detection step is to respond to the change in time, and the changed pixels are subjected to mathematical modeling processing, so that the connection between the changed images and an object which actually generates parabolic motion is conveniently established. In practical situations, it is detected that the change of the image pixel is not necessarily the high-altitude parabolic phenomenon, so that the changed pixel needs to be further analyzed by a parabolic analysis step, the image part obviously not corresponding to the high-altitude parabolic phenomenon is removed by the determination step, the rest image is analyzed again, and then the parabolic motion trajectory is generated. The final fitting drop point, the fitting parabolic point, the fitting drop point area and the fitting parabolic point area can be obtained by fitting and completing the parabolic motion trajectory, so that the floor where high-altitude parabolic occurs can be quickly determined, the range is quickly reduced, and a responsible person is determined. And after the parabolic phenomenon is determined, alarm information can be timely sent to related responsible persons through the alarm recording step, and related image and video data are recorded and uploaded, so that the high-altitude parabolic responsible person can be further determined through subsequent use.
In the processing mode, the analysis processing of the images is carried out at the front end in a centralized mode, namely, the shot images do not need to be transmitted to the cloud server through the network and then are analyzed and processed, the uploading and reading processes of the intermediate images are reduced, the analysis and processing efficiency of the images is greatly improved, and the determination of the high-altitude person with parabolic responsibility can be realized in a shorter time.
Example 2
Based on the same inventive concept of the high altitude parabolic detection method in the foregoing embodiment 1, the present invention also provides a high altitude parabolic detection apparatus, including:
the image acquisition and analysis unit is used for acquiring real-time image data of the residential building to be detected;
the pixel movement detection unit is used for determining pixel points or pixel blocks which move under the current static background;
the parabolic analysis unit is used for determining the motion track of the falling object and determining the floor or the floor range from which the falling object comes;
and the alarm recording unit is used for alarming the suspected high-altitude parabolic phenomenon, recording and storing the related images and videos and uploading the related images and videos to the management platform.
Example 3
Example 3
Based on the same inventive concept as that of the high altitude parabolic detection method in the foregoing embodiment, the present invention further provides a high altitude parabolic detection server, as shown in fig. 3, including a memory 15, a processor 13, and a computer program stored on the memory 15 and executable on the processor 13, where the processor 13 implements any one of the steps of the high altitude parabolic detection method when executing the program.
Wherein in the figure a bus 11 architecture (represented by bus 11), bus 11 may include any number of interconnected buses 11 and bridges, bus 11 linking together various circuits including one or more processors 13, represented by processor 13, and memory 15, represented by memory 15. The bus 11 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus 11 interface provides an interface between the bus 11 and the receiver 12 and transmitter 14. The receiver 12 and the transmitter 14 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 13 is responsible for managing the bus 11 and general processing, while the memory 15 may be used for storing data used by the processor 13 in performing operations.
The processor is responsible for managing the bus and general processing, while the memory may be used for storing data used by the processor in performing operations.
Example 4
Based on the same inventive concept as the high altitude parabola detection method in the previous embodiment, the present invention further provides a readable storage medium, on which a computer program is stored, which when executed by a processor, implements the following steps: the method comprises an image acquisition step, a pixel movement detection step, a parabola analysis step and an alarm recording step.
One or more technical solutions in the embodiments of the present invention at least have one or more of the following technical effects:
the method comprises the steps of collecting and analyzing images near a residential building, and analyzing the collected images, wherein the analyzing process mainly comprises two parts, namely a pixel movement detection step and a parabolic analysis step. When the high-altitude parabolic phenomenon occurs in the residential building, the collected images can change due to the high-altitude parabolic phenomenon, the pixel movement detection step is to respond to the change in time, and the changed pixels are subjected to mathematical modeling processing, so that the connection between the changed images and an object which actually generates parabolic motion is conveniently established.
And the step of parabolic analysis is used for further analyzing the changed pixels, removing the image part which obviously does not correspond to the high-altitude parabolic phenomenon through the step of judging, analyzing the rest images again and then generating a parabolic motion track. The final fitting drop point, the fitting parabolic point, the fitting drop point area and the fitting parabolic point area can be obtained by fitting and completing the parabolic motion trajectory, so that the floor where high-altitude parabolic occurs can be quickly determined, the range is quickly reduced, and a responsible person is determined. And after the parabolic phenomenon is determined, the alarm information can be timely sent to the related responsible person through the alarm recording step, and the related image and video data are recorded and uploaded, so that the high-altitude parabolic responsible person can be further determined through subsequent use.
The above embodiments are preferred embodiments of the present application, and the protection scope of the present application is not limited by the above embodiments, so: all equivalent changes made according to the structure, shape and principle of the present application shall be covered by the protection scope of the present application.
Claims (10)
1. A high altitude parabolic detection method is characterized in that: the detection method comprises the following steps:
an image acquisition step, wherein real-time image data are acquired from a residential building to be detected;
a pixel movement detection step, namely determining pixel points or pixel blocks which move under the current static background;
a parabolic analysis step, wherein the motion track of the falling object is determined, and the floor or the floor range from which the falling object comes is determined;
and an alarm recording step, namely alarming the suspected high altitude parabolic phenomenon, recording and storing the related images and videos, and uploading the related images and videos to a management platform.
2. The high altitude parabola detection method according to claim 1, characterized in that: the pixel movement detecting step includes the steps of:
an image receiving step of receiving image data from the image acquisition device and temporarily storing the image data in an image registering unit;
a background identification step, wherein a static background extraction algorithm is adopted to carry out background identification on the currently collected image data to obtain background data, and a three-dimensional background model is established by the background data;
dividing pixel blocks, namely dividing all pixels of the current image data into a plurality of detection pixel blocks in a longitudinal averaging and transverse averaging mode;
and a detection step, namely setting a marked pixel block, determining a changed pixel area in a mode of comparing previous and next frames when background data is changed, taking the area as a parabolic identification area, overlapping the center of the parabolic identification area with the center of the marked pixel block, and then taking the current image data as parabolic data.
3. The high altitude parabola detection method, device, server and readable storage medium as claimed in claim 2, wherein: the parabolic analyzing step includes the steps of:
a judging step, namely analyzing the parabolic data, reserving the parabolic data meeting the judging conditions by setting a plurality of judging conditions, deleting the parabolic data not meeting the judging conditions, and finally obtaining a track formed by all marked pixel blocks as a parabolic motion track by taking a three-dimensional background model as a reference;
and a track analysis step, wherein parabolic fitting is carried out on the parabolic motion track to obtain a track fitting line after fitting, the track fitting line is complemented and is intersected with the ground of the three-dimensional background model and the plane where the residential building is located to respectively obtain a fitting falling point and a fitting parabolic point, a fitting falling point area and a fitting parabolic point area are obtained by taking the fitting falling point and the fitting parabolic point as centers, the fitting parabolic area is projected into the three-dimensional background model to obtain a corresponding parabolic floor or parabolic floor range, at least three parabolic fitting algorithms are adopted to obtain the track fitting line, and the final fitting falling point, fitting parabolic point area and fitting parabolic point area are a set of results obtained by each track fitting line.
4. A high altitude parabolic detection method according to claim 3, characterized in that: the deciding step includes a plurality of sub-deciding steps.
5. The high altitude parabola detection method, device, server and readable storage medium according to claim 3, characterized in that: in the step of analyzing the track, at least three different parabola fitting algorithms are needed to obtain a track fitting line, and the final fitting falling point, the fitting parabolic point, the fitting falling point area and the fitting parabolic point area are all a set of results obtained by each track fitting line.
6. The high altitude parabola detection method, device, server and readable storage medium according to claim 3, characterized in that: the alarm recording step comprises:
an alarming step, namely generating an alarming signal after the parabolic motion track is generated in the judging step, and transmitting the alarming signal to a person in charge related to the residential building property;
and a record uploading step, namely generating a plurality of pieces of record data, and performing cloud encryption storage and local encryption storage on the record data.
7. The high altitude parabolic detection method according to claim 6, characterized in that: the alarm recording step also comprises a strong reminding step, and the strong reminding step is used for ensuring that the related responsible person receives the alarm signal and generates feedback.
8. A high altitude parabolic detection device is characterized in that: the method comprises the following steps:
the image acquisition and analysis unit is used for acquiring real-time image data of the residential building to be detected;
the pixel movement detection unit is used for determining pixel points or pixel blocks which move under the current static background;
the parabolic analysis unit is used for determining the motion track of the falling object and determining the floor or the floor range from which the falling object comes;
and the alarm recording unit is used for alarming the suspected high-altitude parabolic phenomenon, recording and storing the related images and videos and uploading the related images and videos to the management platform.
9. A high altitude parabolic detection server is characterized in that: comprising a memory, a processor and a computer program stored on the memory and executable in the processor, wherein the processor implements the steps of the method according to any of the claims 1-7 when executing the program.
10. A readable storage medium, characterized by: such readable storage medium has stored thereon computer program instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 7.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2021101857549 | 2021-02-11 | ||
| CN202110185754 | 2021-02-11 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114488337A true CN114488337A (en) | 2022-05-13 |
Family
ID=81479579
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210121063.7A Withdrawn CN114488337A (en) | 2021-02-11 | 2022-02-09 | High-altitude parabolic detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114488337A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116844115A (en) * | 2023-08-29 | 2023-10-03 | 深圳鲲云信息科技有限公司 | Method for tracing and monitoring high-altitude parabolic objects and computing equipment |
-
2022
- 2022-02-09 CN CN202210121063.7A patent/CN114488337A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116844115A (en) * | 2023-08-29 | 2023-10-03 | 深圳鲲云信息科技有限公司 | Method for tracing and monitoring high-altitude parabolic objects and computing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110889350B (en) | Line obstacle monitoring and alarming system and method based on three-dimensional imaging | |
| CN108319926A (en) | A kind of the safety cap wearing detecting system and detection method of building-site | |
| CN110659397B (en) | Behavior detection method and device, electronic equipment and storage medium | |
| CN110852219A (en) | Multi-pedestrian cross-camera online tracking system | |
| CN111488799B (en) | Falling object identification method and system based on image identification | |
| CN112235537B (en) | Transformer substation field operation safety early warning method | |
| CN105141885A (en) | Method for video monitoring and device | |
| CN110738178A (en) | Garden construction safety detection method and device, computer equipment and storage medium | |
| CN110781853B (en) | Crowd abnormality detection method and related device | |
| CN111368615B (en) | Illegal building early warning method and device and electronic equipment | |
| CN111241913A (en) | Method, device and system for detecting falling of personnel | |
| CN114359976B (en) | Intelligent security method and device based on person identification | |
| CN112184773A (en) | Helmet wearing detection method and system based on deep learning | |
| CN113362374A (en) | High-altitude parabolic detection method and system based on target tracking network | |
| CN114548912A (en) | Whole-process tracking method and system for building engineering project management | |
| KR102511287B1 (en) | Image-based pose estimation and action detection method and appratus | |
| CN114248819A (en) | Railway intrusion foreign matter unmanned aerial vehicle detection method, device and system based on deep learning | |
| CN114488337A (en) | High-altitude parabolic detection method and device | |
| CN114494845A (en) | Artificial intelligence hidden danger troubleshooting system and method for construction project site | |
| CN106803937B (en) | Double-camera video monitoring method, system and monitoring device with text log | |
| CN113822151A (en) | Method and system for monitoring population density within a market | |
| JPH08180276A (en) | Method and device for obstacle detection | |
| CN104392201A (en) | Human fall identification method based on omnidirectional visual sense | |
| KR101542134B1 (en) | The apparatus and method of surveillance a rock fall based on smart video analytic | |
| CN115880631A (en) | Power distribution station fault identification system, method and medium |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220513 |
|
| WW01 | Invention patent application withdrawn after publication |