CN111553274A - High-altitude parabolic detection method and device based on trajectory analysis - Google Patents
High-altitude parabolic detection method and device based on trajectory analysis Download PDFInfo
- Publication number
- CN111553274A CN111553274A CN202010348684.XA CN202010348684A CN111553274A CN 111553274 A CN111553274 A CN 111553274A CN 202010348684 A CN202010348684 A CN 202010348684A CN 111553274 A CN111553274 A CN 111553274A
- Authority
- CN
- China
- Prior art keywords
- moving object
- image
- frame
- frame image
- motion
- 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- Withdrawn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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a high-altitude parabolic detection method and device based on track analysis, and the method comprises the steps of obtaining a plurality of frames of images of a current monitoring video, detecting a moving object on the plurality of frames of images, determining the moving object on each frame of image, processing each frame of image of the determined moving object, determining the center coordinate of the moving object on each frame of image, performing straight line fitting according to the center coordinate of the moving object on each frame of image to obtain a motion track equation of the moving object, verifying the motion track equation of the moving object, and determining the high-altitude parabolic object. The method comprises the steps of firstly carrying out motion detection on each frame of image to obtain a moving object on each frame of image, then carrying out motion trajectory equation verification according to a motion trajectory equation of coordinates of the moving object on each frame of image, and thus determining the object with the parabolic high altitude, realizing active detection of the parabolic high altitude, solving the problem that deep learning is difficult to identify, and improving detection accuracy.
Description
Technical Field
The embodiment of the invention relates to the technical field of smart home, in particular to a high-altitude parabolic detection method and device based on trajectory analysis.
Background
The high-altitude parabolic model is called as 'urban toxoma', in recent years, high-altitude parabolic injury events frequently occur, the physical and mental health of other people is injured, the safety and the happiness of the public are influenced, and the requirement of an intelligent community on a high-altitude parabolic scene is higher and higher. The current detection mode of high altitude parabola mainly adopts a high frequency camera and an infrared camera to record video, and then carries out manual tracing afterwards. The method for actively detecting the high altitude parabolic object is to perform training learning through deep learning and then use a trained model to identify the high altitude parabolic object, but the reason for limiting the detection success rate of the method for actively detecting the high altitude parabolic object is that the method is interfered too strongly, such as birds or a person appearing on a window can be identified. Therefore, an effective solution for actively detecting high altitude parabolas is still lacking.
Disclosure of Invention
The embodiment of the invention provides a high-altitude parabolic detection method and device based on trajectory analysis, which are used for effectively detecting high-altitude parabolic and improving the detection accuracy and are low in interference degree.
In a first aspect, an embodiment of the present invention provides a high altitude parabola detection method based on trajectory analysis, including:
acquiring a multi-frame image of a current monitoring video;
carrying out moving object detection on the multiple frames of images to determine moving objects on each frame of image;
processing each frame image of which the moving object is determined, and determining the center coordinate of the moving object on each frame image;
performing linear fitting according to the central coordinates of the moving object on each frame image to obtain a motion trail equation of the moving object;
and verifying the motion trail equation of the moving object to determine the high-altitude parabolic object.
According to the technical scheme, the moving object on each frame image is obtained by performing motion detection on each frame image, and then the motion trajectory equation is verified according to the motion trajectory equation of the coordinate of the moving object on each frame image, so that the object with the parabolic high altitude is determined, the object with the parabolic high altitude can be actively detected, the problem that deep learning is difficult to identify is solved, and the detection accuracy is improved.
Optionally, the performing moving object detection on the multiple frames of images to determine a moving object on each frame of image includes:
performing background subtraction processing on any frame of image in the multiple frames of images and a previous frame of image of the any frame of image to determine different points in the any frame of image and the previous frame of image of the any frame of image;
and carrying out image filtering processing on different points in any frame image and the previous frame image of any frame image to obtain a moving object on each frame image.
Optionally, the performing linear fitting according to the central coordinates of the moving object on each frame image to obtain the motion trajectory equation of the moving object includes:
and performing linear fitting on the central coordinates of the moving object on each frame image by using a least square method to obtain a motion trail equation of the moving object.
Optionally, the verifying the motion trajectory equation of the moving object includes:
determining whether the slope in the motion trail equation of the moving object meets a preset range;
determining a fitting error of the motion trail equation according to the motion trail equation and the central coordinates of the moving object on each frame image, and determining whether the fitting error is smaller than a preset error;
and determining the motion acceleration of the moving object according to the motion track equation and the central coordinates of the moving object on each frame image, and determining whether the motion acceleration accords with a preset acceleration range.
In a second aspect, an embodiment of the present invention provides a high altitude parabola detection apparatus based on trajectory analysis, including:
the acquisition unit is used for acquiring multi-frame images of the current monitoring video;
the processing unit is used for carrying out moving object detection on the multi-frame images and determining moving objects on each frame image; processing each frame image of which the moving object is determined, and determining the center coordinate of the moving object on each frame image; performing linear fitting according to the central coordinates of the moving object on each frame image to obtain a motion trail equation of the moving object; and verifying the motion trail equation of the moving object to determine the high-altitude parabolic object.
Optionally, the processing unit is specifically configured to:
performing background subtraction processing on any frame of image in the multiple frames of images and a previous frame of image of the any frame of image to determine different points in the any frame of image and the previous frame of image of the any frame of image;
and carrying out image filtering processing on different points in any frame image and the previous frame image of any frame image to obtain a moving object on each frame image.
Optionally, the processing unit is specifically configured to:
and performing linear fitting on the central coordinates of the moving object on each frame image by using a least square method to obtain a motion trail equation of the moving object.
Optionally, the processing unit is specifically configured to:
determining whether the slope in the motion trail equation of the moving object meets a preset range;
determining a fitting error of the motion trail equation according to the motion trail equation and the central coordinates of the moving object on each frame image, and determining whether the fitting error is smaller than a preset error;
and determining the motion acceleration of the moving object according to the motion track equation and the central coordinates of the moving object on each frame image, and determining whether the motion acceleration accords with a preset acceleration range.
In a third aspect, an embodiment of the present invention further provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instructions stored in the memory and executing the high-altitude parabolic detection method based on the track analysis according to the obtained program.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable non-volatile storage medium, which includes computer-readable instructions, and when the computer-readable instructions are read and executed by a computer, the computer is caused to execute the above-mentioned trajectory analysis-based high altitude parabolic detection method.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic diagram of a system architecture according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a high altitude parabolic detection method based on trajectory analysis according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a background image according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating a moving object according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating a moving object according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating a moving object according to an embodiment of the present invention;
FIG. 7 is a diagram of a moving object according to an embodiment of the present invention;
FIG. 8 is a diagram illustrating a moving object according to an embodiment of the present invention;
FIG. 9 is a diagram illustrating a moving object according to an embodiment of the present invention;
FIG. 10 is a diagram illustrating a moving object according to an embodiment of the present invention;
FIG. 11 is a schematic diagram of a center coordinate system provided by an embodiment of the present invention;
FIG. 12 is a schematic diagram of a center coordinate provided by an embodiment of the present invention;
FIG. 13 is a schematic diagram of a center coordinate system provided by an embodiment of the present invention;
FIG. 14 is a schematic diagram of a center coordinate provided by an embodiment of the present invention;
FIG. 15 is a schematic diagram of a center coordinate provided by an embodiment of the present invention;
FIG. 16 is a schematic diagram of a formula for calculating a center coordinate according to an embodiment of the present invention;
FIG. 17 is a diagram illustrating a set of coordinate points according to an embodiment of the present invention;
FIG. 18 is a schematic diagram of a line fit provided by an embodiment of the present invention;
FIG. 19 is a schematic diagram of a slope curve provided in accordance with an embodiment of the present invention;
FIG. 20 is a schematic diagram of a trigonometric function provided by an embodiment of the present invention;
fig. 21 is a schematic structural diagram of a high altitude parabolic detection apparatus based on trajectory analysis according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. 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.
Fig. 1 illustrates an exemplary system architecture to which embodiments of the present invention are applicable, which includes a server 100, where the server 100 may include a processor 110, a communication interface 120, and a memory 130.
The communication interface 120 is configured to communicate with the camera and transmit the monitoring video collected by the camera.
The processor 110 is a control center of the server 100, connects various parts of the entire server 100 using various interfaces and routes, performs various functions of the server 100 and processes data by operating or executing software programs and/or modules stored in the memory 130 and calling data stored in the memory 130. Alternatively, processor 110 may include one or more processing units.
The memory 130 may be used to store software programs and modules, and the processor 110 executes various functional applications and data processing by operating the software programs and modules stored in the memory 130. The memory 130 may mainly 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, and the like; the storage data area may store data created according to a business process, and the like. Further, the memory 130 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
It should be noted that the structure shown in fig. 1 is only an example, and the embodiment of the present invention is not limited thereto.
Based on the above description, fig. 2 shows in detail a flow of a high altitude parabolic detection method based on trajectory analysis according to an embodiment of the present invention, where the flow may be executed by a high altitude parabolic detection apparatus based on trajectory analysis.
As shown in fig. 2, the process specifically includes:
Acquiring each frame of image of monitoring video acquired in real time, wherein the monitoring video can be video when a camera is used for monitoring a high-rise building, the video is transmitted by one frame, and each frame of image can be an image as shown in figure 3.
And step 202, carrying out moving object detection on the multiple frames of images, and determining a moving object on each frame of image.
Because there is an object in the image and there is no object in the image that is different, it is possible to compare the current frame image with the previous frame image to obtain whether the current frame image has an object, and specifically, it is possible to perform background subtraction processing on any frame image in the multiple frame images and the previous frame image of any frame image to determine different points in any frame image and the previous frame image of any frame image. And then carrying out image filtering processing on different points in any frame image and a previous frame image of any frame image to obtain a moving object on each frame image.
Currently, when a moving object is determined on each frame image, a background subtraction method is generally adopted, and a camera shown in fig. 3 acquires a background image of a monitoring video, which is a long-term cumulative average calculation result.
The arrows in fig. 4 indicate the object of a parabolic phenomenon on a certain floor, and the analysis of fig. 4, 5 and 6 in the time domain is a complete high altitude parabolic phenomenon. The time domain analysis of fig. 4, 7 and 8 is to simulate the bird flying phenomenon; any single picture can be taken as an accidental phenomenon, such as a person on a window, or a strong light reflection phenomenon (a high-altitude parabolic scene is lower in utilization rate than other video AI scenes, so that the capture rate of the picture is lower).
Fig. 9 is the contour diagram (data contour of picture RGB) of background fig. 3, and it can be seen that the total number of coordinate points in the horizontal direction is imax (1148), the total number of coordinate points in the vertical direction is jmax (644), fig. 10 is the contour diagram of fig. 4, and the arrow in fig. 10 shows the behavior of a suspected high altitude parabola. The difference between fig. 10 and fig. 9 (difference between RGB values of points corresponding to horizontal and vertical coordinates of the two images: pic8(i, j) -pic9(i, j) ═ FG1_ diff1(i, j)) can be obtained, and then the difference between the two frames of images is obtained by performing a switching operation based on dilation and erosion, and a general image filtering algorithm such as median filtering and connected domain filtering, so that fig. 11 can be obtained. This can be done in the same way as fig. 12 to 15. This completes the motion detection.
When the moving object is determined, the center coordinates of the moving object on each frame image can be determined, mainly, the image value of the non-moving area on each frame image where the moving object is determined is set to 0, the image value of the moving area is set to non-0, and then the coordinates of each center point can be obtained by using the program in fig. 16. Then, the central point coordinates of each of fig. 11 to 15 are obtained by the above processing, and finally, the central point coordinates are overlapped, so that the result that all the central point coordinates are located on one graph can be obtained, or a central point coordinate set can be obtained, as shown in fig. 17.
And 204, performing straight line fitting according to the central coordinates of the moving object on each frame image to obtain a motion trail equation of the moving object.
Because the high-altitude parabola is vertical motion or parabola-like vertical motion, straight line fitting can be carried out after the central coordinate is obtained, and the moving trajectory equation of the moving object is obtained mainly by adopting a least square method to carry out straight line fitting on the central coordinate of the moving object on each frame of image.
For example, fitting with y ═ kx + b, according to the least squares method, yields:
wherein N is the number of fitted central coordinates, and x and y respectively represent the horizontal and vertical coordinates of the central coordinates; k is the slope of the motion trajectory equation and b is a constant of the motion trajectory equation.
FIG. 18 is the result of the fit, where the thicker line (A, B, C three points) has the fitting equation: y is 17.4 x-8195; the fit equation for the thinner line (A, D, E three points) is: y-0.226 x + 620.
And step 205, verifying the motion trajectory equation of the moving object to determine the high-altitude parabolic object.
After the motion trail equation is fitted, the motion trail equation needs to be verified, and whether the motion trail equation meets corresponding conditions is mainly verified, so that whether the motion trail is the motion trail of the object parabolic in high altitude is judged, and whether the motion trail is the object parabolic in high altitude can be determined.
Specifically, the following verification methods may be included:
and determining whether the slope in the motion trail equation of the moving object meets a preset range. And determining the fitting error of the motion trail equation according to the motion trail equation and the central coordinates of the moving object on each frame image, and determining whether the fitting error is smaller than a preset error. And determining the motion acceleration of the moving object according to the motion track equation and the center coordinates of the moving object on each frame image, and determining whether the motion acceleration accords with a preset acceleration range.
The object which is a high-altitude parabola can be confirmed only after the verification is passed.
For example, the analysis results shown in table 1 can be obtained by analyzing and comparing the trajectory of a normal high altitude parabolic trajectory with the trajectory of a bird flying, airing clothes, and the like. By judgment, the ABC horizontal coordinates are known to have small difference, the vertical coordinates are gradually reduced, and a parabolic motion can be presumed; the ADE horizontal and vertical coordinates are greatly changed, and the disturbance such as bird flying can be presumed to be made into disordered movement. When the motion continues around point a, it can be presumed that: human probes or clothes drying and the like.
TABLE 1
The following judgment is made from three aspects based on the equation, and all the three conditions are satisfied, namely the high altitude parabola.
First, determining the range of values of slope (k):
the value range of k directly determines the direction of the straight line in space, the high altitude parabola is a kind of vertical motion, the slope curve is shown in fig. 19, the included angle between the vertical motion and the ground is 90 ° (pi/2), the value range of k can be set as (beta, infinity) (∞, beta), beta is a threshold value, and the threshold value needs to be determined according to data such as the resolution of the image, the distance between the camera and the building, the inclination angle of the camera and the like. The thicker line in fig. 18 (three points A, B, C) has a value of k of 17.4; the value of k for the thinner line (A, D, E three points) is-0.226.
Secondly, determining the fitting error:
the deviation degree of the fitting point and the straight line is reflected by the fitting error, the deviation degree of the straight line motion and the straight line is small, and the deviation degree of other motions is high. The calculation formula of the fitting error is as follows:
where error is the fitting error, y' is the ordinate predicted from the abscissa of the fitted points, y is the ordinate of the fitted points, and N is the number of fitted points.
Substituting the abscissa of the fitted point into the motion trail equation obtained by the fitting to obtain a predicted ordinate y ', for example, the abscissa of the point a in fig. 18 is 501, substituting the abscissa into the motion trail equation of the thicker line to obtain y ' of 522.4, the actual abscissa y of the point a is 520, and sequentially calculating y ' of each point to obtain an error value of 2.93 of the thicker line (A, B, C three points) in fig. 18; the error value for the thinner line (A, D, E three points) was 15.13. It is clear that the smaller the error value the better.
Thirdly, determining the running acceleration:
the normal vertical motion running acceleration is close to g, and the threshold range may be [0.5g, 1.5g ] in consideration of the influence of wind resistance, force given when the user takes out his hand.
The acceleration formula: a is Δ V/Δ t;
according to the acceleration formula, in order to obtain the acceleration a, Δ V and Δ t need to be known, as shown in fig. 18, A, B, C three fitting points, Δ V can pass through BC section speed VBCMinus AB speed VABIs realized by thatBC-VAB. The time difference Δ t is the inter-frame difference of the selected image, which should be represented here by the time difference between the two fitting points B, C.
Above VABThe velocity for this distance between the two fitting points A and B is intended to obtain the VABThe pixel distance between the two fitting points needs to be known, and taking A (501, 520) and B (495, 423) as an example, the pixel distance Δ d between the two fitting points can be obtained A, BABIs composed of
Accordingly, an image between the two fitting points of B, C can be obtainedElement distance Δ dBCIs composed of
Then, a mapping relation between the pixel distance and the actual distance can be obtained according to the distance between the camera and the building and the inclination angle of the camera, so as to obtain an actual distance difference Δ s between two fitted points, for example, A, B where the actual distance difference between the two fitted points is Δ sABB, C actual distance difference between two fitted points is Δ sBC. Wherein A, B the time difference of the images corresponding to the two fitting points is DeltatABB, C the time difference between the images corresponding to the two fitting points is Δ tBC。
Thus, the speed of the distance between the two fitting points, i.e. V, can be obtained according to the actual distance difference and the time difference between the two fitting pointsAB＝ΔsAB/ΔtAB，VBC＝ΔsBC/ΔtBC。
When determining the actual distance difference between two fitting points, the actual distance represented by the distance between two pixels in the image is first known. The specific calculation method is as follows:
as shown in fig. 20, the vertical distance h ═ d × tan (α) of the building that can be photographed by the camera is obtained according to the trigonometric function, d is the actual distance between the camera and the building, and α is the elevation angle photographed by the camera. The above embodiment has mentioned that the image resolution is imax jmax, and jmax is the number of vertical dots, so that the distance between two adjacent pixels in the image can be obtained as h/jmax (d _ tan (α))/jmax.
Suppose that the current commonly used floor interval is 3.3 meters, the number of floors shot by each camera is n, the longitudinal distance h1 of the floor that the camera can shoot is 3.3n, but when the image detection, the first step is to identify the floor first, namely to identify the floor and the background, if the longitudinal point number of the floor in the image obtained at this moment is jmax1, the distance between two adjacent pixel points corresponding to the floor in the image is: 3.3n/jmax 1. Then multiplying the pixel distance between the two fitting points by the distance 3.3n/jmax1 between two adjacent pixel points in the image to obtain the actual distance difference between the two fitting pointsTake A, B two fitting points as an example, Δ sAB＝(ΔdAB3.3n)/jmax1, and B, C the difference between the actual distances of the two fitted points is Δ sBC＝(ΔdBC*3.3n)/jmax1。
By the resulting actual distance difference Δ sABAnd Δ sBCThereafter, a velocity V between the two fitting points is obtained A, BAB＝ΔsAB/ΔtABAnd B, C speed V between the two points of fitBC＝ΔsBC/ΔtBCThen, the speed difference Δ V ═ V can be obtainedBC-VABFurther, the acceleration a becomes Δ V/Δ t.
The embodiment shows that the multi-frame images of the current monitoring video are obtained, the moving object detection is carried out on the multi-frame images, the moving object on each frame image is determined, each frame image of the determined moving object is processed, the center coordinate of the moving object on each frame image is determined, straight line fitting is carried out according to the center coordinate of the moving object on each frame image, the motion trail equation of the moving object is obtained, the motion trail equation of the moving object is verified, and the high-altitude parabolic object is determined. The method comprises the steps of firstly carrying out motion detection on each frame of image to obtain a moving object on each frame of image, then carrying out motion trajectory equation verification according to a motion trajectory equation of coordinates of the moving object on each frame of image, and thus determining the object with the parabolic high altitude, realizing active detection of the parabolic high altitude, solving the problem that deep learning is difficult to identify, and improving detection accuracy.
Based on the same technical concept, fig. 21 exemplarily shows a structure of a high-altitude parabolic detection apparatus based on trajectory analysis according to an embodiment of the present invention, where the apparatus can perform a high-altitude parabolic detection process based on trajectory analysis.
As shown in fig. 21, the apparatus specifically includes:
an obtaining unit 2101, configured to obtain a multi-frame image of a current monitoring video;
a processing unit 2102 configured to perform moving object detection on the multiple frames of images, and determine a moving object on each frame of image; processing each frame image of which the moving object is determined, and determining the center coordinate of the moving object on each frame image; performing linear fitting according to the central coordinates of the moving object on each frame image to obtain a motion trail equation of the moving object; and verifying the motion trail equation of the moving object to determine the high-altitude parabolic object.
Optionally, the processing unit 2102 is specifically configured to:
performing background subtraction processing on any frame of image in the multiple frames of images and a previous frame of image of the any frame of image to determine different points in the any frame of image and the previous frame of image of the any frame of image;
and carrying out image filtering processing on different points in any frame image and the previous frame image of any frame image to obtain a moving object on each frame image.
Optionally, the processing unit 2102 is specifically configured to:
and performing linear fitting on the central coordinates of the moving object on each frame image by using a least square method to obtain a motion trail equation of the moving object.
Optionally, the processing unit 2102 is specifically configured to:
determining whether the slope in the motion trail equation of the moving object meets a preset range;
determining a fitting error of the motion trail equation according to the motion trail equation and the central coordinates of the moving object on each frame image, and determining whether the fitting error is smaller than a preset error;
and determining the motion acceleration of the moving object according to the motion track equation and the central coordinates of the moving object on each frame image, and determining whether the motion acceleration accords with a preset acceleration range.
Based on the same technical concept, an embodiment of the present invention further provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instructions stored in the memory and executing the high-altitude parabolic detection method based on the trajectory analysis according to the obtained program.
Based on the same technical concept, the embodiment of the invention also provides a computer-readable non-volatile storage medium, which includes computer-readable instructions, and when the computer reads and executes the computer-readable instructions, the computer is enabled to execute the high altitude parabolic detection method based on trajectory analysis.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A high-altitude parabolic detection method based on trajectory analysis is characterized by comprising the following steps:
acquiring a multi-frame image of a current monitoring video;
carrying out moving object detection on the multiple frames of images to determine moving objects on each frame of image;
processing each frame image of which the moving object is determined, and determining the center coordinate of the moving object on each frame image;
performing linear fitting according to the central coordinates of the moving object on each frame image to obtain a motion trail equation of the moving object;
and verifying the motion trail equation of the moving object to determine the high-altitude parabolic object.
2. The method of claim 1, wherein the performing motion object detection on the plurality of frames of images to determine the motion object on each frame of image comprises:
performing background subtraction processing on any frame of image in the multiple frames of images and a previous frame of image of the any frame of image to determine different points in the any frame of image and the previous frame of image of the any frame of image;
and carrying out image filtering processing on different points in any frame image and the previous frame image of any frame image to obtain a moving object on each frame image.
3. The method of claim 1, wherein the performing a straight line fitting according to the center coordinates of the moving object on each frame image to obtain the motion trajectory equation of the moving object comprises:
and performing linear fitting on the central coordinates of the moving object on each frame image by using a least square method to obtain a motion trail equation of the moving object.
4. The method of any of claims 1 to 3, wherein the validating the motion trajectory equation for the moving object comprises:
determining whether the slope in the motion trail equation of the moving object meets a preset range;
determining a fitting error of the motion trail equation according to the motion trail equation and the central coordinates of the moving object on each frame image, and determining whether the fitting error is smaller than a preset error;
and determining the motion acceleration of the moving object according to the motion track equation and the central coordinates of the moving object on each frame image, and determining whether the motion acceleration accords with a preset acceleration range.
5. A high altitude parabolic detection device based on trajectory analysis is characterized by comprising:
the acquisition unit is used for acquiring multi-frame images of the current monitoring video;
the processing unit is used for carrying out moving object detection on the multi-frame images and determining moving objects on each frame image; processing each frame image of which the moving object is determined, and determining the center coordinate of the moving object on each frame image; performing linear fitting according to the central coordinates of the moving object on each frame image to obtain a motion trail equation of the moving object; and verifying the motion trail equation of the moving object to determine the high-altitude parabolic object.
6. The apparatus as claimed in claim 5, wherein said processing unit is specifically configured to:
performing background subtraction processing on any frame of image in the multiple frames of images and a previous frame of image of the any frame of image to determine different points in the any frame of image and the previous frame of image of the any frame of image;
and carrying out image filtering processing on different points in any frame image and the previous frame image of any frame image to obtain a moving object on each frame image.
7. The apparatus as claimed in claim 5, wherein said processing unit is specifically configured to:
and performing linear fitting on the central coordinates of the moving object on each frame image by using a least square method to obtain a motion trail equation of the moving object.
8. The apparatus according to any one of claims 5 to 7, wherein the processing unit is specifically configured to:
determining whether the slope in the motion trail equation of the moving object meets a preset range;
determining a fitting error of the motion trail equation according to the motion trail equation and the central coordinates of the moving object on each frame image, and determining whether the fitting error is smaller than a preset error;
and determining the motion acceleration of the moving object according to the motion track equation and the central coordinates of the moving object on each frame image, and determining whether the motion acceleration accords with a preset acceleration range.
9. A computing device, comprising:
a memory for storing program instructions;
a processor for calling program instructions stored in said memory to execute the method of any one of claims 1 to 4 in accordance with the obtained program.
10. A computer-readable non-transitory storage medium including computer-readable instructions which, when read and executed by a computer, cause the computer to perform the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010348684.XA CN111553274A (en) | 2020-04-28 | 2020-04-28 | High-altitude parabolic detection method and device based on trajectory analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010348684.XA CN111553274A (en) | 2020-04-28 | 2020-04-28 | High-altitude parabolic detection method and device based on trajectory analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111553274A true CN111553274A (en) | 2020-08-18 |
Family
ID=72001710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010348684.XA Withdrawn CN111553274A (en) | 2020-04-28 | 2020-04-28 | High-altitude parabolic detection method and device based on trajectory analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111553274A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112033351A (en) * | 2020-08-05 | 2020-12-04 | 青岛聚好联科技有限公司 | Monocular camera-based distance measuring method and electronic equipment |
| CN112183355A (en) * | 2020-09-28 | 2021-01-05 | 北京理工大学 | Effluent height detection system and method based on binocular vision and deep learning |
| CN112184774A (en) * | 2020-09-30 | 2021-01-05 | 青岛聚好联科技有限公司 | Method and device for determining high-altitude parabolic hazard degree |
| CN112308000A (en) * | 2020-11-06 | 2021-02-02 | 安徽清新互联信息科技有限公司 | High-altitude parabolic detection method based on space-time information |
| CN112325780A (en) * | 2020-10-29 | 2021-02-05 | 青岛聚好联科技有限公司 | Distance measuring and calculating method and device based on community monitoring |
| CN112330743A (en) * | 2020-11-06 | 2021-02-05 | 安徽清新互联信息科技有限公司 | High-altitude parabolic detection method based on deep learning |
| CN112800868A (en) * | 2021-01-13 | 2021-05-14 | 华南理工大学 | High-altitude parabolic monitoring method based on event camera acquisition and analysis device |
| CN112884801A (en) * | 2021-02-02 | 2021-06-01 | 普联技术有限公司 | High altitude parabolic detection method, device, equipment and storage medium |
| 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 |
| CN112926538A (en) * | 2021-04-08 | 2021-06-08 | 广州绿简智能科技有限公司 | High-altitude parabolic identification method based on monitoring video |
| CN113409360A (en) * | 2021-06-29 | 2021-09-17 | 深圳市商汤科技有限公司 | High altitude parabolic detection method and device, equipment and computer storage medium |
| WO2022078182A1 (en) * | 2020-10-16 | 2022-04-21 | 腾讯科技（深圳）有限公司 | Throwing position acquisition method and apparatus, computer device and storage medium |
| WO2023273011A1 (en) * | 2021-06-29 | 2023-01-05 | 深圳市商汤科技有限公司 | Method, apparatus and device for detecting object thrown from height, and computer storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105163067A (en) * | 2015-08-12 | 2015-12-16 | 武汉大学 | High toss act evidence obtaining system based on digital image processing technology |
| 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 |
| CN110275042A (en) * | 2019-05-07 | 2019-09-24 | 深圳市零壹移动互联***有限公司 | A kind of throwing object in high sky detection method based on computer vision and radio signal analysis |
| 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 |
-
2020
- 2020-04-28 CN CN202010348684.XA patent/CN111553274A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105163067A (en) * | 2015-08-12 | 2015-12-16 | 武汉大学 | High toss act evidence obtaining system based on digital image processing technology |
| 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 |
| CN110275042A (en) * | 2019-05-07 | 2019-09-24 | 深圳市零壹移动互联***有限公司 | A kind of throwing object in high sky detection method based on computer vision and radio signal analysis |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 刘义亭;董梦超;黄家才;范子霄;宗文锦;郭婧;: "基于OpenMV的目标跟踪***设计" * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112033351A (en) * | 2020-08-05 | 2020-12-04 | 青岛聚好联科技有限公司 | Monocular camera-based distance measuring method and electronic equipment |
| CN112183355A (en) * | 2020-09-28 | 2021-01-05 | 北京理工大学 | Effluent height detection system and method based on binocular vision and deep learning |
| CN112183355B (en) * | 2020-09-28 | 2022-12-27 | 北京理工大学 | Effluent height detection system and method based on binocular vision and deep learning |
| CN112184774A (en) * | 2020-09-30 | 2021-01-05 | 青岛聚好联科技有限公司 | Method and device for determining high-altitude parabolic hazard degree |
| WO2022078182A1 (en) * | 2020-10-16 | 2022-04-21 | 腾讯科技（深圳）有限公司 | Throwing position acquisition method and apparatus, computer device and storage medium |
| CN112325780A (en) * | 2020-10-29 | 2021-02-05 | 青岛聚好联科技有限公司 | Distance measuring and calculating method and device based on community monitoring |
| CN112330743A (en) * | 2020-11-06 | 2021-02-05 | 安徽清新互联信息科技有限公司 | High-altitude parabolic detection method based on deep learning |
| CN112308000A (en) * | 2020-11-06 | 2021-02-02 | 安徽清新互联信息科技有限公司 | High-altitude parabolic detection method based on space-time information |
| CN112308000B (en) * | 2020-11-06 | 2023-03-07 | 安徽清新互联信息科技有限公司 | High-altitude parabolic detection method based on space-time information |
| CN112330743B (en) * | 2020-11-06 | 2023-03-10 | 安徽清新互联信息科技有限公司 | High-altitude parabolic detection method based on deep learning |
| CN112800868A (en) * | 2021-01-13 | 2021-05-14 | 华南理工大学 | High-altitude parabolic monitoring method based on event camera acquisition and analysis device |
| CN112884801A (en) * | 2021-02-02 | 2021-06-01 | 普联技术有限公司 | High altitude parabolic detection method, device, equipment and storage medium |
| 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 |
| CN112926538A (en) * | 2021-04-08 | 2021-06-08 | 广州绿简智能科技有限公司 | High-altitude parabolic identification method based on monitoring video |
| CN113409360A (en) * | 2021-06-29 | 2021-09-17 | 深圳市商汤科技有限公司 | High altitude parabolic detection method and device, equipment and computer storage medium |
| WO2023273011A1 (en) * | 2021-06-29 | 2023-01-05 | 深圳市商汤科技有限公司 | Method, apparatus and device for detecting object thrown from height, and computer storage medium |
| WO2023273010A1 (en) * | 2021-06-29 | 2023-01-05 | 深圳市商汤科技有限公司 | High-rise littering detection method, apparatus, and device, and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111553274A (en) | High-altitude parabolic detection method and device based on trajectory analysis | |
| US10769480B2 (en) | Object detection method and system | |
| CN105654512B (en) | A kind of method for tracking target and device | |
| US9183431B2 (en) | Apparatus and method for providing activity recognition based application service | |
| CN110287907B (en) | Object detection method and device | |
| CN103093198B (en) | A kind of crowd density monitoring method and device | |
| WO2021139049A1 (en) | Detection method, detection apparatus, monitoring device, and computer readable storage medium | |
| US20060056702A1 (en) | Image processing apparatus and image processing method | |
| JP7272024B2 (en) | Object tracking device, monitoring system and object tracking method | |
| CN108665541B (en) | A kind of ground drawing generating method and device and robot based on laser sensor | |
| CN107133969A (en) | A kind of mobile platform moving target detecting method based on background back projection | |
| CN109791615A (en) | For detecting and tracking the method, target object tracking equipment and computer program product of target object | |
| CN112733690A (en) | High-altitude parabolic detection method and device and electronic equipment | |
| CN106991418A (en) | Winged insect detection method, device and terminal | |
| CN108776974A (en) | A kind of real-time modeling method method suitable for public transport scene | |
| JP6789876B2 (en) | Devices, programs and methods for tracking objects using pixel change processed images | |
| CN105469054B (en) | The model building method of normal behaviour and the detection method of abnormal behaviour | |
| CN111627049A (en) | High-altitude parabola determination method and device, storage medium and processor | |
| CN112184767A (en) | Method, device, equipment and storage medium for tracking moving object track | |
| CN105043395A (en) | Real-time dynamic location method for moon surface soft landing of aircraft | |
| CN115482556A (en) | Method for key point detection model training and virtual character driving and corresponding device | |
| Kyrkou | C 3 Net: end-to-end deep learning for efficient real-time visual active camera control | |
| CN108961287B (en) | Intelligent shelf triggering method, intelligent shelf system, storage medium and electronic equipment | |
| CN111901499B (en) | Method and equipment for calculating actual pixel distance in video image | |
| EP4089649A1 (en) | Neuromorphic cameras for aircraft |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200818 |